Merge remote-tracking branch 'origin/master' into codex/project-instruction-files

# Conflicts:
#	AGENTS.md
#	docs/architecture.md
#	docs/event-producer-consumer.md
#	docs/module-graph.md
#	docs/rfc/INDEX.md
#	packages/bash/bash-local/tests/executor.spec.ts
#	packages/bash/bash-local/tests/run.spec.ts
#	packages/core/agent-core/src/index.ts
#	packages/core/agent-core/tests/agent-core.spec.ts
#	packages/fs/fs-local/src/fsio.ts
#	packages/ui/acp-agent/package.json
#	packages/ui/acp-agent/src/index.ts
#	packages/ui/acp-agent/tsconfig.json
#	packages/ui/stdio-agent/package.json
#	packages/ui/stdio-agent/tsconfig.json
#	packages/util/README.md
#	pnpm-lock.yaml
#	tsconfig.build.json
#	tsconfig.json

packages/README.md

@@ -12,14 +12,18 @@ Packages are grouped by modular role at `packages/<group>/<pkg>/`. The group dir
 | [`prompt/`](prompt/README.md) | Prompt and request-context extensions that shape model inputs | Product — stable surface |
 | [`llm/`](llm/README.md) | LLM capability family: the abstract service + provider adapters | Product — stable surface |
 | [`bash/`](bash/README.md) | Bash capability family: the executor seam, a local impl, and the model-facing tool | Product — stable surface |
+| [`code-runtime/`](code-runtime/README.md) | Code-execution capability family: the abstract runtime seam for model-written programs + a worker-thread backend | Product — stable surface |
 | [`fs/`](fs/README.md) | Filesystem capability family: the abstract seam, a local impl, and the model-facing file tools | Product — stable surface |
 | [`compact/`](compact/README.md) | Compaction capability family: the abstract seam + a basic backend (tool deferred) | Product — stable surface |
 | [`subagent/`](subagent/README.md) | Subagent capability family: the provider-registry seam and the model-facing delegation tool | Product — stable surface |
 | [`web/`](web/README.md) | Web capability family: the abstract seam, search/fetch provider impls, and the model-facing web tools | Product — stable surface |
-| [`todo/`](todo/README.md) | Todo/planning family: the model-facing `todo_write` tool (whole-list task tracking on the session log) | Product — stable surface |
+| [`timeout/`](timeout/README.md) | Tool-call timeout policy: the `tools/execute` deadline enforcer | Product — stable surface |
+| [`todo/`](todo/README.md) | Todo/planning family: the model-facing `todo_write` tool | Product — stable surface |
+| [`guard/`](guard/README.md) | Loop-hygiene guards: advisory repeat-call reminders | Product — stable surface |
+| [`cordis/`](cordis/README.md) | Self-referential runtime toolset: inspect the live runtime's plugins and services, mount/unmount model-written plugins ([design](../docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md)) | Product — stable surface |
 | [`hooks/`](hooks/README.md) | Hook bridges + the shared Claude Code / Codex wire-protocol library | Product — stable surface |
 | [`session-persistence/`](session-persistence/README.md) | Persistence capability family: the seam + JSONL/SQLite backends | Product — stable surface |
-| [`ui/`](ui/README.md) | Editor/client integration surfaces (the ACP bridge) + the app packages | Product — stable surface |
+| [`ui/`](ui/README.md) | Editor/client integration surfaces: ACP bridge, app packages, user-interaction seam, ask-user tool | Product — stable surface |
 | [`support/`](support/README.md) | Dev/test/example infrastructure (invariants, replay adapter, subagent mock) | Support — lower compatibility expectations |
 | [`util/`](util/README.md) | Low-level zero-dependency utilities shared across groups (`Branded<B>`, path helpers) | Support — small, stable, harness-dep-free |
 
@@ -29,6 +33,6 @@ The split is the point: a package's group says whether it is part of the product
 
 The inter-package dependency graph is generated: [docs/module-graph.md](../docs/module-graph.md) (`pnpm run gen-module-graph`, freshness-gated in CI).
 
-The rule it must obey: **extension plugins depend on interfaces, never on the concrete loop.** `dsh-agent-loop` is swappable — UI/hook/tool plugins keep working against the `dsh-agent` vocabulary if the loop is replaced. The sanctioned exception is a **composition/bundle** package like `dsh-agent-core`, whose whole job is to assemble the concrete spine: it depends on `dsh-agent-loop` (and the other concrete spine plugins) on purpose. The rule constrains plugins that EXTEND the system, not the bundle that COMPOSES it — swapping the loop means shipping a different bundle, not rewiring every extension. A swappable capability splits into interface / implementation / consumer packages (the bash trio is the template — see [capability seams](../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md)).
+The rule it must obey: **extension plugins depend on interfaces, never on the concrete loop.** `dsh-agent-loop` is swappable — UI/hook/tool plugins keep working against the `dsh-agent` vocabulary if the loop is replaced. The sanctioned exception is a **composition/bundle** package like `dsh-agent-core`, whose whole job is to assemble the concrete spine: it depends on `dsh-agent-loop` (and the other concrete spine plugins) on purpose. The rule constrains plugins that EXTEND the system, not the bundle that COMPOSES it. A swappable capability splits into interface / implementation / consumer packages (the bash trio is the template — see [capability seams](../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md)).
 
 Each package has its own `README.md` with purpose, service API, events, extension points, and deliberate non-goals (TODOs).

packages/bash/bash-local/package.json

@@ -23,6 +23,7 @@
   "license": "BSD-3-Clause",
   "peerDependencies": {
     "@deepseek-ai/dsh-bash": "^0.0.1",
+    "@deepseek-ai/dsh-timeout": "^0.0.1",
     "cordis": "^4.0.0-rc.6"
   },
   "dependencies": {
@@ -30,6 +31,7 @@
   },
   "devDependencies": {
     "@deepseek-ai/dsh-bash": "workspace:^",
+    "@deepseek-ai/dsh-timeout": "workspace:^",
     "cordis": "^4.0.0-rc.6"
   }
 }

packages/bash/bash-local/src/index.ts

@@ -18,6 +18,7 @@ import { Context } from 'cordis'
 import z from 'schemastery'
 import { BashExecutor, BashTaskId } from '@deepseek-ai/dsh-bash'
 import type { BashExecRequest, BashExecSpec, BashRunResult, BashTask, BashTaskRead, OwnerToken } from '@deepseek-ai/dsh-bash'
+import { clampTimeout, deadline, timeoutOf } from '@deepseek-ai/dsh-timeout'
 import { DEFAULT_GRACE_MS, runBash } from './run.ts'
 import type { RunInternals, RunningBash } from './run.ts'
 
@@ -114,8 +115,12 @@ export class LocalBashExecutor extends BashExecutor {
    * values and never re-default.
    */
   resolve(request: BashExecRequest): BashExecSpec {
-    if (request.timeoutMs !== undefined) assertPositiveFinite('request.timeoutMs', request.timeoutMs)
-    const timeoutMs = Math.min(request.timeoutMs ?? this.config.timeoutMs, this.config.maxTimeoutMs)
+    const timeoutMs = clampTimeout(
+      request.timeoutMs,
+      this.config.timeoutMs,
+      this.config.maxTimeoutMs,
+      'bash-local: request.timeoutMs',
+    )
     return {
       command: request.command,
       workdir: request.workdir ?? this.config.cwd ?? process.cwd(),
@@ -132,29 +137,39 @@ export class LocalBashExecutor extends BashExecutor {
   }
 
   async run(spec: BashExecSpec): Promise<BashRunResult> {
+    // One fused deadline drives both the timeout and upstream cancellation;
+    // runBash listens on d.signal and runs the SIGTERM→grace→SIGKILL kill.
+    // `using` clears the timer across the awaited process lifetime.
+    using d = deadline(spec.signal, spec.timeoutMs, 'BASH_TIMEOUT')
     const outcome = await runBash({
       command: spec.command,
       cwd: spec.workdir,
-      timeoutMs: spec.timeoutMs,
       maxOutputBytes: this.config.maxOutputBytes,
       graceMs: this.config.graceMs,
-      signal: spec.signal,
+      signal: d.signal,
       stdin: spec.stdin,
       env: spec.env,
     }, this.internals).done
-    return { ...outcome, timeoutMs: spec.timeoutMs }
+    // Classify the FIRST abort reason: a BASH_TIMEOUT TimeoutReason means our
+    // timeout cut the command short; any other abort — an upstream cancel, or a
+    // foreign (outer) deadline's timeout under nesting — is aborted. Scoping to
+    // our own code keeps a nested outer deadline from reading as our timeout.
+    // Mutually exclusive by construction — the fused signal reports one cause.
+    const timedOut = timeoutOf(d.signal, 'BASH_TIMEOUT') !== undefined
+    const aborted = d.signal.aborted && !timedOut
+    return { ...outcome, timedOut, aborted, timeoutMs: spec.timeoutMs }
   }
 
   start(spec: BashExecSpec): BashTask {
     // No timeout for background tasks (matches Claude Code, which detaches
     // the timeout when backgrounding); callers stop tasks via kill() — or
     // via spec.signal, which the seam contract honors for background runs
-    // too (runBash wires it to the group kill). spec.timeoutMs is ignored
-    // here by design.
+    // too (runBash wires it to the group kill). No deadline is created here,
+    // so spec.timeoutMs is ignored by design — background tasks stay
+    // timeout-free (see the timeout-library RFC).
     const running = runBash({
       command: spec.command,
       cwd: spec.workdir,
-      timeoutMs: 0,
       maxOutputBytes: this.config.maxOutputBytes,
       graceMs: this.config.graceMs,
       signal: spec.signal,
@@ -174,8 +189,10 @@ export class LocalBashExecutor extends BashExecutor {
       stdoutOffset: 0,
       stderrOffset: 0,
       done: running.done.then((outcome) => {
-        // Abort-killed tasks report as killed, not completed.
-        if (task.status === 'running') task.status = outcome.aborted ? 'killed' : 'completed'
+        // Abort-killed tasks report as killed, not completed. Background runs
+        // forward only the upstream signal (no timeout), so its aborted state
+        // is the authoritative "was this cancelled" signal.
+        if (task.status === 'running') task.status = spec.signal?.aborted === true ? 'killed' : 'completed'
         task.exitCode = outcome.exitCode
         task.signal = outcome.signal
         this.notifyTaskDone(task)

packages/bash/bash-local/src/run.ts

@@ -6,6 +6,12 @@
  * Everything here is deliberately free of Cordis concepts so it can be unit
  * tested in isolation; `LocalBashExecutor` owns lifecycle and configuration.
  *
+ * runBash owns NO timing: it kills the process group when its `spec.signal`
+ * fires and does not distinguish a timeout from a cancel. The executor fuses
+ * timeout + upstream cancellation into that one signal via
+ * `@deepseek-ai/dsh-timeout`'s `deadline`, and classifies the outcome from the
+ * signal afterward — the timing/classification half is shared, the kill is not.
+ *
  * Design notes (surveyed against Claude Code, OpenCode, Codex, and pi — see
  * the package README): spawn-per-call with `detached: true` so the child
  * leads its own process group; kills target the group (`kill(-pid)`) so
@@ -56,6 +62,8 @@ export const SENSITIVE_ENV_PATTERN = /KEY|SECRET|TOKEN/i
  * by in-process plugins (the hooks bridges), not the model — `dsh-tool-bash`
  * builds its request from named fields only and does not forward model input
  * here (see its README, § "The tool builds its request from named args only").
+ * @param extra - caller-supplied entries merged last; an explicit entry wins even against the scrub and the overrides.
+ * @returns the environment to hand to `spawn` for the child process.
  */
 export function childEnv(extra?: Record<string, string>): NodeJS.ProcessEnv {
   const env: NodeJS.ProcessEnv = {}
@@ -69,13 +77,17 @@ export function childEnv(extra?: Record<string, string>): NodeJS.ProcessEnv {
 export interface SpawnSpec {
   command: string
   cwd: string
-  /** Kill the process group after this many milliseconds. 0 = no timeout. */
-  timeoutMs: number
   /** Per-stream in-memory cap; overflow spills to disk (tail kept in memory). */
   maxOutputBytes: number
   /** Grace period between the SIGTERM and the SIGKILL escalation on a kill. */
   graceMs: number
-  /** Abort signal — kills the process group when fired. */
+  /**
+   * Abort signal — kills the process group when it fires. The executor owns
+   * timing: `run()` passes a fused timeout/cancel deadline signal (see
+   * `@deepseek-ai/dsh-timeout`), `start()` passes the bare upstream signal.
+   * runBash only listens and kills; it does NOT classify why (the executor
+   * reads the signal's reason afterward).
+   */
   signal?: AbortSignal | undefined
   /**
    * Bytes to write to the child's stdin, then close it. Absent (or empty)
@@ -92,12 +104,15 @@ export interface SpawnSpec {
   env?: Record<string, string> | undefined
 }
 
-/** Raw outcome of one closed process (before result shaping). */
+/**
+ * Raw outcome of one closed process (before result shaping). Deliberately
+ * carries NO timeout/cancel classification: runBash kills on abort but does not
+ * decide why — the executor's `run()`/`start()` reads the deadline signal it
+ * owns to classify `timedOut`/`aborted` (see the package README).
+ */
 export interface SpawnOutcome {
   exitCode: number | null
   signal: NodeJS.Signals | null
-  timedOut: boolean
-  aborted: boolean
   stdout: CollectedOutput
   stderr: CollectedOutput
 }
@@ -147,6 +162,14 @@ export class OutputCollector {
     private readonly spillDir: string,
   ) {}
 
+  /**
+   * Ingest one stream chunk, counting it toward the whole-stream total. On
+   * first overflow of the in-memory cap a spill file is opened and every chunk
+   * (already-collected ones included) is appended there from then on; the
+   * in-memory tail then drops whole chunks from its head (or the head of a
+   * single over-cap chunk) until it fits the cap again.
+   * @param chunk - the raw bytes from one stream 'data' event.
+   */
   push(chunk: Buffer): void {
     this.total += chunk.length
     const overflows = this.bytes + chunk.length > this.maxBytes
@@ -190,7 +213,10 @@ export class OutputCollector {
   // the bottom of this file) and `totalBytes` is read only by a test. The live
   // background-poll path goes through `readFrom()`, so inline snapshot() into
   // finalize() and drop or privatize the totalBytes getter.
-  /** Read the collected tail without finalizing (the final-result snapshot). */
+  /**
+   * Read the collected tail without finalizing (the final-result snapshot).
+   * @returns the retained tail text, the truncation flag, and the spill path when one was created.
+   */
   snapshot(): CollectedOutput {
     return {
       text: Buffer.concat(this.chunks).toString('utf8'),
@@ -209,6 +235,8 @@ export class OutputCollector {
    * pushed since `fromByte`. When `fromByte` has already slid out of the
    * in-memory tail window, the read is `lossy` — it returns the whole
    * retained tail and the gap is only recoverable from the spill file.
+   * @param fromByte - whole-stream offset to resume from (a prior read's `nextOffset`; 0 for the first read).
+   * @returns the delta text, the offset for the next read, the `lossy` flag, and the spill path when one was created.
    */
   readFrom(fromByte: number): { text: string; nextOffset: number; lossy: boolean; spillPath?: string } {
     const windowStart = this.total - this.bytes
@@ -223,7 +251,12 @@ export class OutputCollector {
     }
   }
 
-  /** Close the spill file (if any) and return the final output. */
+  /**
+   * Close the spill file (if any) and return the final output. A failed close
+   * (delayed writeback fault) stops advertising the spill path — the file may
+   * be missing its tail — but still returns the in-memory result.
+   * @returns the final collected output: tail text, truncation flag, and the spill path when intact.
+   */
   finalize(): CollectedOutput {
     if (this.spillFd !== undefined) {
       try {
@@ -249,6 +282,8 @@ export class OutputCollector {
  * host process — a kill that cannot be delivered is reported by the process
  * NOT dying, which callers already handle via escalation/timeouts. No-op for
  * non-positive pids (spawn never started a process).
+ * @param pid - the group leader's pid; non-positive means the spawn failed and the call is a no-op.
+ * @param sig - the signal to deliver to the whole group.
  */
 export function killGroup(pid: number, sig: NodeJS.Signals): void {
   if (pid <= 0) return
@@ -290,6 +325,9 @@ export interface RunningBash {
  * exec sessions addressable via session ids + stdin writes. We deliberately
  * spawn a fresh non-login `bash -c` per call for determinism (no rc files,
  * no inherited shell state); revisit when real workflows demand it.
+ * @param spec - the fully-resolved run (command, cwd, limits); no defaulting happens here.
+ * @param internals - test-only knobs; omitted fields fall back to the private per-process spill dir.
+ * @returns the live handle: pid, the two live collectors, the outcome promise, and `kill()`.
  */
 export function runBash(spec: SpawnSpec, internals: RunInternals = {}): RunningBash {
   const spillDir = internals.spillDir ?? privateSpillDir()
@@ -318,9 +356,6 @@ export function runBash(spec: SpawnSpec, internals: RunInternals = {}): RunningB
   child.stdout.on('data', (chunk: Buffer) => { stdout.push(chunk) })
   child.stderr.on('data', (chunk: Buffer) => { stderr.push(chunk) })
 
-  let timedOut = false
-  let aborted = false
-  let killTimer: NodeJS.Timeout | undefined
   let graceTimer: NodeJS.Timeout | undefined
 
   // pid is undefined when the spawn itself fails (bad cwd, missing binary);
@@ -333,17 +368,12 @@ export function runBash(spec: SpawnSpec, internals: RunInternals = {}): RunningB
     graceTimer = setTimeout(() => { killGroup(pid, 'SIGKILL') }, spec.graceMs)
   }
 
-  if (spec.timeoutMs > 0) {
-    killTimer = setTimeout(() => {
-      timedOut = true
-      kill()
-    }, spec.timeoutMs)
-  }
-
-  const onAbort = (): void => {
-    aborted = true
-    kill()
-  }
+  // runBash owns no timer: the executor's `run()` fuses timeout+cancel into one
+  // deadline signal (`@deepseek-ai/dsh-timeout`) and passes it here; we only
+  // listen and run the SIGTERM→grace→SIGKILL kill. Whether the abort was a
+  // timeout or an upstream cancel is classified by the executor from that
+  // signal, not tracked here.
+  const onAbort = (): void => { kill() }
   spec.signal?.addEventListener('abort', onAbort, { once: true })
 
   // Write stdin and close it, but ONLY when the caller supplied bytes — with no
@@ -376,14 +406,11 @@ export function runBash(spec: SpawnSpec, internals: RunInternals = {}): RunningB
       resolve({
         exitCode,
         signal,
-        timedOut,
-        aborted,
         stdout: stdout.finalize(),
         stderr: stderr.finalize(),
       })
     })
     function cleanup(): void {
-      if (killTimer !== undefined) clearTimeout(killTimer)
       if (graceTimer !== undefined) clearTimeout(graceTimer)
       spec.signal?.removeEventListener('abort', onAbort)
     }

packages/bash/bash-local/tests/executor.spec.ts

@@ -40,12 +40,14 @@ async function readUntil(
 ): Promise<BashTaskRead> {
   const deadline = Date.now() + timeoutMs
   let last: BashTaskRead | undefined
+  let delta = ''
   while (Date.now() < deadline) {
     last = bash.readOutput(id)
-    if (last.delta.includes(expected)) return last
+    delta += last.delta
+    if (delta.includes(expected)) return { ...last, delta }
     await new Promise(resolve => setTimeout(resolve, 20))
   }
-  throw new Error(`task ${id} output did not include ${JSON.stringify(expected)}; last delta was ${JSON.stringify(last?.delta ?? '')}`)
+  throw new Error(`task ${id} output did not include ${JSON.stringify(expected)}; output was ${JSON.stringify(delta)}, last delta was ${JSON.stringify(last?.delta ?? '')}`)
 }
 
 describe('LocalBashExecutor.run', () => {
@@ -90,8 +92,8 @@ describe('LocalBashExecutor.run', () => {
 
   it('kill escalation uses the configured graceMs (a TERM-trapping task dies by SIGKILL)', async () => {
     const { bash } = await setup() // setup pins graceMs: 200 via config
-    const task = bash.start(bash.resolve({ command: 'trap \'\' TERM; echo trap-ready; sleep 60' }))
-    await readUntil(bash, task.id, 'trap-ready')
+    const task = bash.start(bash.resolve({ command: 'trap \'\' TERM; echo ready; while :; do sleep 60 & wait $!; done' }))
+    await readUntil(bash, task.id, 'ready\n')
     bash.kill(task.id)
     await task.done
     expect(task.signal).toBe('SIGKILL')
@@ -101,6 +103,8 @@ describe('LocalBashExecutor.run', () => {
     const { bash } = await setup({ timeoutMs: 60_000 })
     const result = await bash.run(bash.resolve({ command: 'sleep 60', timeoutMs: 100 }))
     expect(result.timedOut).toBe(true)
+    // Mutually exclusive: a timeout classifies as timedOut, never also aborted.
+    expect(result.aborted).toBe(false)
     expect(result.timeoutMs).toBe(100)
   })
 
@@ -111,6 +115,20 @@ describe('LocalBashExecutor.run', () => {
     setTimeout(() => { controller.abort() }, 50)
     const result = await pending
     expect(result.aborted).toBe(true)
+    // Mutually exclusive: an upstream cancel classifies as aborted, never also timedOut.
+    expect(result.timedOut).toBe(false)
+  })
+
+  it('classifies a self-killed command as neither timed out nor aborted', async () => {
+    // The command kills itself (SIGTERM) with no timeout and no upstream abort:
+    // the deadline signal never fires, so both classifications are false — the
+    // fused-signal classification reports the cause that cut the command short,
+    // and here nothing the executor owns did.
+    const { bash } = await setup({ timeoutMs: 60_000 })
+    const result = await bash.run(bash.resolve({ command: 'kill -TERM $$' }))
+    expect(result.signal).toBe('SIGTERM')
+    expect(result.timedOut).toBe(false)
+    expect(result.aborted).toBe(false)
   })
 
   it('rejects on spawn failure (bad workdir)', async () => {

packages/bash/bash-local/tests/run.spec.ts

@@ -26,7 +26,6 @@ function spec(command: string, overrides: Partial<Parameters<typeof runBash>[0]>
   return {
     command,
     cwd: process.cwd(),
-    timeoutMs: 0,
     maxOutputBytes: 64_000,
     graceMs: 3_000,
     ...overrides,
@@ -56,17 +55,18 @@ async function waitForStdout(running: RunningBash, expected: string, timeoutMs =
   throw new Error(`stdout did not include ${JSON.stringify(expected)} after ${timeoutMs}ms`)
 }
 
-async function waitForFileText(path: string, timeoutMs = 5_000): Promise<string> {
+async function waitForPidFile(path: string, timeoutMs = 5_000): Promise<number> {
   const deadline = Date.now() + timeoutMs
   while (Date.now() < deadline) {
     try {
-      return readFileSync(path, 'utf8')
-    } catch (error: unknown) {
-      if (typeof error !== 'object' || error === null || !('code' in error) || error.code !== 'ENOENT') throw error
-      await new Promise(resolve => setTimeout(resolve, 20))
+      const pid = Number(readFileSync(path, 'utf8').trim())
+      if (Number.isSafeInteger(pid) && pid > 0) return pid
+    } catch {
+      // The child shell has not written the pid file yet.
     }
+    await new Promise(resolve => setTimeout(resolve, 20))
   }
-  throw new Error(`file ${path} did not appear after ${timeoutMs}ms`)
+  throw new Error(`pid file ${path} was not written after ${timeoutMs}ms`)
 }
 
 describe('runBash', () => {
@@ -74,8 +74,6 @@ describe('runBash', () => {
     const result = await runBash(spec('echo hello')).done
     expect(result.exitCode).toBe(0)
     expect(result.signal).toBeNull()
-    expect(result.timedOut).toBe(false)
-    expect(result.aborted).toBe(false)
     expect(result.stdout.text).toBe('hello\n')
     expect(result.stdout.truncated).toBe(false)
     expect(result.stderr.text).toBe('')
@@ -110,17 +108,22 @@ describe('runBash', () => {
     expect(result.stdout.text.trim()).toMatch(/\/tmp$/)
   })
 
-  it('kills with SIGTERM on timeout', async () => {
+  it('kills the process group with SIGTERM when the signal fires', async () => {
+    // runBash owns no timer: it kills on abort. The executor drives the timeout
+    // by firing this signal via a deadline (see executor.spec.ts); here we
+    // assert the kill itself lands as SIGTERM.
+    const controller = new AbortController()
     const start = Date.now()
-    const result = await runBash(spec('sleep 60', { timeoutMs: 100 })).done
+    const running = runBash(spec('sleep 60', { signal: controller.signal }))
+    setTimeout(() => { controller.abort('deadline') }, 100)
+    const result = await running.done
     expect(Date.now() - start).toBeLessThan(5_000)
-    expect(result.timedOut).toBe(true)
     expect(result.signal).toBe('SIGTERM')
     expect(result.exitCode).toBeNull()
   })
 
   it('escalates to SIGKILL when SIGTERM is trapped', async () => {
-    const running = runBash(spec('trap \'\' TERM; echo ready; sleep 60', { graceMs: 200 }))
+    const running = runBash(spec('trap \'\' TERM; echo ready; while :; do sleep 60 & wait $!; done', { graceMs: 200 }))
     await waitForStdout(running, 'ready\n')
     running.kill()
     const result = await running.done
@@ -132,7 +135,7 @@ describe('runBash', () => {
     // group must take the sleep down with bash.
     const pidFile = join(spillDir, `grandchild-${Date.now()}.pid`)
     const running = runBash(spec(`sleep 60 & echo $! > ${pidFile}; wait`))
-    const grandchild = Number((await waitForFileText(pidFile)).trim())
+    const grandchild = await waitForPidFile(pidFile)
     expect(grandchild).toBeGreaterThan(0)
 
     running.kill()
@@ -146,7 +149,6 @@ describe('runBash', () => {
     const running = runBash(spec('sleep 60', { signal: controller.signal }))
     setTimeout(() => { controller.abort('user cancelled') }, 50)
     const result = await running.done
-    expect(result.aborted).toBe(true)
     expect(result.signal).toBe('SIGTERM')
   })
 
@@ -223,7 +225,6 @@ describe('stdin and extra env (set by in-process plugins)', () => {
     const big = 'x'.repeat(1024 * 1024)
     const result = await runBash(spec('exit 7', { stdin: big })).done
     expect(result.exitCode).toBe(7)
-    expect(result.aborted).toBe(false)
   })
 })
 
@@ -351,11 +352,11 @@ describe('abort edge cases', () => {
       .toThrow(/aborted before spawn: aborted/)
   })
 
-  it('reports an externally self-killed command without the timeout marker', async () => {
+  it('reports the terminating signal of an externally self-killed command', async () => {
+    // runBash reports the raw signal; whether it counts as timeout/cancel is the
+    // executor's classification (a self-kill is neither) — see executor.spec.ts.
     const result = await runBash(spec('kill -TERM $$')).done
     expect(result.signal).toBe('SIGTERM')
-    expect(result.timedOut).toBe(false)
-    expect(result.aborted).toBe(false)
   })
 })
 
@@ -408,10 +409,9 @@ describe('review fixes: env scrubbing and spill hardening', () => {
 
   it('honors AbortSignal on background-style runs (no timeout)', async () => {
     const controller = new AbortController()
-    const running = runBash(spec('sleep 60', { timeoutMs: 0, signal: controller.signal }))
+    const running = runBash(spec('sleep 60', { signal: controller.signal }))
     setTimeout(() => { controller.abort() }, 50)
     const result = await running.done
-    expect(result.aborted).toBe(true)
     expect(result.signal).toBe('SIGTERM')
   })
 })

packages/bash/bash-local/tsconfig.json

@@ -20,6 +20,9 @@
     {
       "path": "../../util/brand"
     },
+    {
+      "path": "../../util/timeout"
+    },
     {
       "path": "../../bash/bash"
     }

packages/bash/bash/src/types.ts

@@ -11,7 +11,11 @@ import type { Branded } from '@deepseek-ai/dsh-brand'
 /** Identifies one background task within an executor (generated `bash-N`). */
 export type BashTaskId = Branded<'BashTaskId'>
 
-/** Brand a string as a {@link BashTaskId}. */
+/**
+ * Brand a string as a {@link BashTaskId}.
+ * @param id - the raw task-id string (the executor generates `bash-N`).
+ * @returns the same string, branded; no validation is performed.
+ */
 export function BashTaskId(id: string): BashTaskId {
   return id as BashTaskId
 }
@@ -26,7 +30,12 @@ export function BashTaskId(id: string): BashTaskId {
  */
 export type OwnerToken = Branded<'OwnerToken'>
 
-/** Brand a string as an {@link OwnerToken}. */
+/**
+ * Brand a string as an {@link OwnerToken}. Only the consuming boundary
+ * (`dsh-tool-bash`) should cast its own id vocabulary in — see the type's doc.
+ * @param id - the consumer's raw owner identity (the tool layer passes the owning agent's session id).
+ * @returns the same string, branded; no validation is performed.
+ */
 export function OwnerToken(id: string): OwnerToken {
   return id as OwnerToken
 }

packages/bash/tool-bash/src/index.ts

@@ -99,6 +99,8 @@ function streamText(output: CollectedOutput): string {
  * stderr section, then exit-status markers. Non-zero exits are REPORTED, not
  * errored — the model decides how to react; only infrastructure failures
  * (spawn errors, aborts) surface as isError results.
+ * @param result - the completed foreground run from the executor.
+ * @returns the model-facing text: output body (or `(no output)`), then any timeout/signal/exit markers, each on its own line.
  */
 export function renderResult(result: BashRunResult): string {
   const out = streamText(result.stdout)

packages/code-runtime/README.md

@@ -0,0 +1,10 @@
+# code-runtime/ — code-execution capability family
+
+The code-execution capability seam (see [capability seams](../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md)): an abstract runtime interface for executing one model-written program against host-provided async bindings, capturing what it printed and returned. The consumer is the tool registry's Code Mode, specified alongside the seam in the [Code Mode RFC](../../docs/rfc/proposed/feature/2026-06-15-code-mode.md). **Product** packages.
+
+| Package | Role | ctx key |
+|---|---|---|
+| `code-runtime/` | Abstract code-execution seam (interface + vocabulary) | `ctx.codeRuntime` |
+| [`code-runtime-worker/`](code-runtime-worker/README.md) | Worker-thread backend: fresh worker per run, TypeScript via host-side type-strip (annotations advisory, never type-checked), port-bridged bindings, budget/heap containment | registers `ctx.codeRuntime` |
+
+The interface lives at `code-runtime/code-runtime/`; the shipped backend at `code-runtime/code-runtime-worker/`. Backends differ by execution substrate (worker thread, process, container) and by source language — both readonly descriptors on the service — and register `ctx.codeRuntime` without touching the interface or its consumer; that split is what makes a hardened backend a drop-in later.

packages/code-runtime/code-runtime-worker/README.md

@@ -0,0 +1,32 @@
+# @deepseek-ai/dsh-code-runtime-worker
+
+Worker-thread implementation of the [`@deepseek-ai/dsh-code-runtime`](../code-runtime/README.md) seam: `WorkerCodeRuntime` runs each program in ONE fresh Node `worker_threads.Worker` — TypeScript in, type-stripped host-side, bindings bridged over the message port, `{ value, logs, error? }` out. **Containment, not a security boundary**: trust posture is bash-equivalent by design (the [Code Mode RFC](../../../docs/rfc/proposed/feature/2026-06-15-code-mode.md) § Trust posture), with containment bash does not have — separate isolate, empty environment, heap cap, hard termination.
+
+## Config
+
+```yaml
+- id: code-runtime
+  name: '@deepseek-ai/dsh-code-runtime-worker'
+  config:
+    computeMs: 60000              # busy-time budget (measured event-loop active time)
+    maxWallMs: 600000             # wall-clock ceiling; never pauses for anything
+    maxLogBytes: 65536            # shared byte budget for captured log text
+    maxValueBytes: 32768          # rendered-completion-value cap
+    maxOldGenerationSizeMb: 512   # worker heap cap (resourceLimits)
+```
+
+Every field is validated (positive numbers) and defaulted; there are no other tunables.
+
+## Design
+
+- **One fresh worker per run, no pooling** — a program's world dies with its worker: no cross-run state to log, state bleed unrepresentable, runs reconstructable from the session log alone.
+- **Type-strip host-side, in execution context** — the program is wrapped in an async-function shell, stripped with `node:module`'s `stripTypeScriptTypes` (erasable syntax only — `enum`/namespaces are rejected as a program `exception` and no worker spawns), and sliced back out byte-positioned; it then executes as the body of an `AsyncFunction`, so top-level `await`/`return` work.
+- **The port assumes a hostile peer** — model code can reach `parentPort` and forge traffic, so every inbound message is shape-validated and REBUILT before anything reads it (`null`, primitives, junk types, and malformed payloads drop without a throw; forged extra fields never ride along), the host answers each call id at most once, resolves binding names as OWN properties only (a forged `constructor` cannot walk a prototype chain), drops post-settlement replies, and converts a non-cloneable binding resolution into an error reply. Forged `log`/`done` messages cannot bypass the caps: one host-side ledger bounds everything that lands in `logs`, and the completion value is re-capped host-side. Worker-side namespaces are null-prototype with `defineProperty`, so `__proto__`-shaped binding names are ordinary keys.
+- **Two independent budgets, because the peer is hostile** — `computeMs` meters the worker's MEASURED busy time (`worker.performance.eventLoopUtilization()` polling): a hot loop cannot hide behind a pending decoy dispatch, and a program awaiting a slow tool accrues nothing. `maxWallMs` backstops what busy time cannot see (awaiting a promise nobody resolves). Both funnel into `worker.terminate()`, which ends hot synchronous loops too; heap overflow surfaces as the worker's OOM exit (`kind: 'worker-exit'`).
+- **Logs stream eagerly** — console/stdout/stderr entries cross the port as they happen, so a timed-out or killed program still shows what it printed. ONE shared `maxLogBytes` ledger bounds everything: streamed entries, forged port traffic, and pipe bytes that bypass the patched streams (appended after), with the overflow marked in-band once.
+- **Empty environment** — the worker gets `env: {}` and `execArgv: []`: no ambient credentials (stronger than the scrubbed-env rule for spawned commands) and no inherited loader flags.
+- **Dispose to quiescence** — teardown fails in-flight runs as `abort` and AWAITS each worker's exit before resolving.
+
+## The worker entry, unbuilt and built
+
+`worker.ts` is deliberately erasable-only TypeScript with type-only cross-package imports: unbuilt (vitest/tsx), the host spawns `src/worker.ts` directly and Node's native type stripping loads it; built, the entry ships as the sibling bundle `lib/worker.js` (its own tsdown entry). The built path is pinned by `tests/built-lib.e2e.ts`, the real-load-path guard from [docs/testing.md](../../../docs/testing.md).

packages/code-runtime/code-runtime-worker/package.json

@@ -0,0 +1,36 @@
+{
+  "name": "@deepseek-ai/dsh-code-runtime-worker",
+  "description": "Worker-thread implementation of the DeepSeek Harness code-execution seam",
+  "version": "0.0.1",
+  "private": true,
+  "type": "module",
+  "main": "lib/index.js",
+  "types": "lib/types/index.d.ts",
+  "exports": {
+    ".": {
+      "types": "./lib/types/index.d.ts",
+      "default": "./lib/index.js"
+    },
+    "./src/*": "./src/*",
+    "./package.json": "./package.json"
+  },
+  "files": [
+    "lib/index.js",
+    "lib/worker.js",
+    "lib/types/**/*.d.ts",
+    "lib/types/**/*.d.ts.map",
+    "src"
+  ],
+  "license": "BSD-3-Clause",
+  "peerDependencies": {
+    "@deepseek-ai/dsh-code-runtime": "^0.0.1",
+    "cordis": "^4.0.0-rc.6"
+  },
+  "dependencies": {
+    "schemastery": "^3.18.0"
+  },
+  "devDependencies": {
+    "@deepseek-ai/dsh-code-runtime": "workspace:^",
+    "cordis": "^4.0.0-rc.6"
+  }
+}

packages/code-runtime/code-runtime-worker/src/bootstrap.ts

@@ -0,0 +1,301 @@
+/**
+ * Worker-side execution logic, written as plain functions over an injected
+ * port so the unit suite can run every line IN-PROCESS against a fake port
+ * (a real worker thread is a separate V8 isolate the coverage provider
+ * cannot observe). The real worker entry (`worker.ts`) is a thin
+ * self-executing glue file over {@link runWorkerMain}, excluded from
+ * coverage the same way `bin.ts` entrypoints are, and exercised end-to-end
+ * by the integration tests that spawn real workers.
+ *
+ * @module @deepseek-ai/dsh-code-runtime-worker/src/bootstrap
+ */
+
+import { inspect } from 'node:util'
+import { serialize } from 'node:v8'
+import type { CodeLogEntry } from '@deepseek-ai/dsh-code-runtime'
+import { logTruncationMarker } from './protocol.ts'
+import type { DoneMessage, ReplyMessage, WorkerBootData, WorkerToHost } from './protocol.ts'
+
+/** The port surface the bootstrap needs — satisfied by `parentPort` and by the tests' fake. */
+export interface BootstrapPort {
+  postMessage(message: WorkerToHost): void
+  on(event: 'message', listener: (message: ReplyMessage) => void): void
+}
+
+/**
+ * A writable stream's `write` slot, as the bootstrap patches it (see
+ * {@link captureStreamWrites}). Method-typed so the real
+ * `process.stdout`/`process.stderr` (narrower chunk parameters) remain
+ * assignable.
+ */
+export interface PatchableStream {
+  write(chunk: unknown, ...rest: unknown[]): boolean
+}
+
+/**
+ * Ordered log capture under one shared byte budget, delivered to a sink as
+ * each entry lands (the real sink streams entries over the port eagerly, so
+ * captured output survives a mid-run termination). Once the budget is
+ * exhausted it emits exactly one in-band marker entry (on the `stderr`
+ * diagnostics channel) and silently drops everything after — the cap is a
+ * blast-radius bound, so "how much was lost" intentionally stays unmeasured.
+ */
+export class LogBuffer {
+  private remaining: number
+  private truncated = false
+  // Explicit fields, not constructor parameter properties: this module loads
+  // under Node's native strip-only mode, which rejects non-erasable syntax —
+  // and parameter properties are non-erasable.
+  private readonly maxBytes: number
+  private readonly sink: (entry: CodeLogEntry) => void
+
+  constructor(maxBytes: number, sink: (entry: CodeLogEntry) => void) {
+    this.maxBytes = maxBytes
+    this.sink = sink
+    this.remaining = maxBytes
+  }
+
+  /**
+   * Emit one entry to the sink, charging its text against the budget (drops + marks once exhausted).
+   * @param entry - the log entry to deliver.
+   */
+  push(entry: CodeLogEntry): void {
+    if (this.truncated) return
+    const cost = Buffer.byteLength(entry.text, 'utf8')
+    if (cost > this.remaining) {
+      this.truncated = true
+      this.sink({ source: 'stderr', text: logTruncationMarker(this.maxBytes) })
+      return
+    }
+    this.remaining -= cost
+    this.sink(entry)
+  }
+}
+
+/** The five console methods the shim captures, in the seam's level vocabulary. */
+const CONSOLE_LEVELS = ['log', 'info', 'warn', 'error', 'debug'] as const
+
+/**
+ * A `console` replacement whose five leveled methods render their arguments
+ * `util.inspect`-style (matching real console formatting closely enough for
+ * a model to recognize its own output) into the buffer. Only these five
+ * exist — the program gets a deliberately small console, not Node's full
+ * surface.
+ * @param logs - the buffer every rendered line is pushed into.
+ * @returns the five-method console object handed to the program.
+ */
+export function makeConsoleShim(logs: LogBuffer): Record<(typeof CONSOLE_LEVELS)[number], (...args: unknown[]) => void> {
+  const render = (args: unknown[]): string =>
+    args.map(arg => typeof arg === 'string' ? arg : inspect(arg, INSPECT_OPTIONS)).join(' ')
+  const shim = Object.create(null) as Record<(typeof CONSOLE_LEVELS)[number], (...args: unknown[]) => void>
+  for (const level of CONSOLE_LEVELS) {
+    shim[level] = (...args: unknown[]) => { logs.push({ source: 'console', level, text: render(args) }) }
+  }
+  return shim
+}
+
+/**
+ * Redirect a stream's `write` into the log buffer (the program-visible
+ * `process.stdout`/`process.stderr` in the real worker), so raw writes land
+ * in emission order alongside console output instead of racing down a pipe.
+ * The shim keeps Node's `write(chunk[, encoding][, callback])` contract: the
+ * callback fires asynchronously once the chunk is admitted (a program
+ * awaiting flush completion must complete, not sit until the wall timeout),
+ * even for writes the exhausted budget drops.
+ * @param logs - the buffer captured writes are pushed into.
+ * @param stream - the stream whose `write` slot is patched.
+ * @param source - the log source the captured writes are attributed to.
+ * @returns the restore function (the in-process tests un-patch; the real
+ *   worker never needs to).
+ */
+export function captureStreamWrites(logs: LogBuffer, stream: PatchableStream, source: 'stdout' | 'stderr'): () => void {
+  // The slot's VALUE is stored for restore and reassigned — never invoked
+  // detached, so the unbound-method concern does not apply.
+  // eslint-disable-next-line @typescript-eslint/unbound-method
+  const original = stream.write
+  stream.write = (chunk: unknown, ...rest: unknown[]): boolean => {
+    logs.push({ source, text: typeof chunk === 'string' ? chunk : String(chunk) })
+    // Node's optional-encoding shape: the callback is whichever of the next
+    // two positions holds a function (a non-function there is the encoding).
+    const callback = [rest[0], rest[1]].find(
+      (arg): arg is (error?: Error | null) => void => typeof arg === 'function',
+    )
+    if (callback) queueMicrotask(() => { callback(null) })
+    return true
+  }
+  return () => { stream.write = original }
+}
+
+/** Bounded inspect options: deep enough to be useful, bounded so a pathological value cannot explode the rendering. */
+const INSPECT_OPTIONS = { depth: 4, maxArrayLength: 100, maxStringLength: 10_000 } as const
+
+/**
+ * The longest prefix of `text` whose UTF-8 encoding fits `maxBytes`, cut at
+ * a code-point boundary (never mid-surrogate-pair). The byte caps are BYTE
+ * caps — `String.prototype.slice` counts UTF-16 code units, up to 3× smaller
+ * than what a multibyte string actually costs across the boundary.
+ * @param text - the string to bound.
+ * @param maxBytes - the UTF-8 byte budget the prefix must fit.
+ * @returns the prefix (all of `text` when it already fits).
+ */
+export function truncateUtf8Bytes(text: string, maxBytes: number): string {
+  if (Buffer.byteLength(text, 'utf8') <= maxBytes) return text
+  let bytes = 0
+  let end = 0
+  for (const char of text) {
+    const cost = Buffer.byteLength(char, 'utf8')
+    if (bytes + cost > maxBytes) break
+    bytes += cost
+    end += char.length
+  }
+  return text.slice(0, end)
+}
+
+/**
+ * Prepare the program's completion value for the done message: a value whose
+ * MEASURED cross-boundary size fits `maxValueBytes` crosses raw — exact
+ * bytes for a string, the structured-clone wire size (`v8.serialize`) for
+ * everything else, so a huge container whose BOUNDED inspect rendering
+ * happens to be small cannot smuggle itself past the cap. Anything else
+ * (non-cloneable, or oversized) is REPLACED by its bounded `util.inspect`
+ * rendering, byte-truncated ({@link truncateUtf8Bytes}) with an in-band
+ * marker — the seam contract's "a non-transferable value is replaced by a
+ * string rendering", extended to oversized ones so a huge return cannot
+ * flood the host.
+ * @param value - the program's completion value.
+ * @param maxValueBytes - the byte cap for the value.
+ * @returns the done-message fragment: `{}` for `undefined`, else `{ value }`.
+ */
+export function prepareValue(value: unknown, maxValueBytes: number): { value?: unknown } {
+  if (value === undefined) return {}
+  if (typeof value === 'string') {
+    if (Buffer.byteLength(value, 'utf8') <= maxValueBytes) return { value }
+  } else {
+    let size: number | undefined
+    try {
+      size = serialize(value).byteLength
+    } catch {
+      // Only the verdict matters: the value has parts the structured-clone
+      // algorithm rejects (functions, classes, …) and must cross as its
+      // rendering instead.
+      size = undefined
+    }
+    if (size !== undefined && size <= maxValueBytes) return { value }
+  }
+  const rendered = typeof value === 'string' ? value : inspect(value, INSPECT_OPTIONS)
+  const capped = Buffer.byteLength(rendered, 'utf8') > maxValueBytes
+    ? `${truncateUtf8Bytes(rendered, maxValueBytes)}… [truncated]`
+    : rendered
+  return { value: capped }
+}
+
+/** One awaited binding call's settlement handles, keyed by call id in the pending map. */
+export interface PendingCall {
+  resolve(value: unknown): void
+  reject(error: Error): void
+}
+
+/**
+ * Route host replies into the pending-call map: each reply settles its call
+ * at most once, and a reply for an unknown id (stray, or a duplicate answer
+ * to an id already settled) is ignored. Shared wiring between
+ * {@link runWorkerMain} and the tests that exercise {@link makeNamespaces}
+ * standalone.
+ * @param port - the port whose `message` events carry the replies.
+ * @param pending - the id-keyed map of unsettled binding calls.
+ */
+export function wireReplies(port: BootstrapPort, pending: Map<number, PendingCall>): void {
+  port.on('message', (message: ReplyMessage) => {
+    const entry = pending.get(message.id)
+    if (!entry) return
+    pending.delete(message.id)
+    if (message.ok) entry.resolve(message.value)
+    else entry.reject(new Error(message.message))
+  })
+}
+
+/**
+ * Build the binding namespace objects the program sees: one null-prototype
+ * global per namespace, each declared name an own enumerable async function
+ * that bridges over the port (`__proto__`/`constructor`/`toString` are
+ * ordinary keys, never prototype collisions). A non-cloneable argument
+ * rejects that one call with a descriptive error; the host's reply (`ok`
+ * false) rejects it likewise, so a failed tool call surfaces in the program
+ * as an ordinary promise rejection.
+ * @param data - the boot payload's namespace declarations (globals + names).
+ * @param port - the port binding calls are posted to.
+ * @param pending - the id-keyed map each posted call parks its handles in.
+ * @param nextId - the shared mutable id counter (worker-issued correlation ids).
+ * @returns one namespace object per declaration, in declaration order.
+ */
+export function makeNamespaces(
+  data: Pick<WorkerBootData, 'namespaces'>,
+  port: BootstrapPort,
+  pending: Map<number, PendingCall>,
+  nextId: { value: number },
+): Record<string, unknown>[] {
+  return data.namespaces.map(({ global, names }) => {
+    const namespace = Object.create(null) as Record<string, unknown>
+    for (const name of names) {
+      Object.defineProperty(namespace, name, {
+        enumerable: true,
+        value: (args: unknown): Promise<unknown> => new Promise((resolve, reject) => {
+          const id = nextId.value++
+          pending.set(id, { resolve, reject })
+          try {
+            port.postMessage({ type: 'call', id, global, name, args })
+          } catch (error: unknown) {
+            pending.delete(id)
+            reject(new Error(`binding arguments must be structured-cloneable: ${error instanceof Error ? error.message : String(error)}`))
+          }
+        }),
+      })
+    }
+    return namespace
+  })
+}
+
+/**
+ * Run one program to settlement and post the {@link DoneMessage}: wires the
+ * reply handler, materializes the namespaces and console shim, compiles the
+ * type-stripped body as an async function (top-level `await`/`return`
+ * work), and reports a thrown program error as the done message's `error`
+ * field. Exactly one done message is ever posted.
+ * @param port - the message port to the host (the real `parentPort`, or the tests' fake).
+ * @param data - the boot payload the host sent.
+ * @param streams - the stream objects whose `write` is captured (the real
+ *   `process.stdout`/`process.stderr` in the worker; fakes in tests).
+ * @returns resolves after the done message is posted (the tests await it;
+ *   the real entry lets the worker exit naturally).
+ */
+export async function runWorkerMain(
+  port: BootstrapPort,
+  data: WorkerBootData,
+  streams: { stdout: PatchableStream; stderr: PatchableStream },
+): Promise<void> {
+  const logs = new LogBuffer(data.maxLogBytes, (entry) => { port.postMessage({ type: 'log', entry }) })
+  captureStreamWrites(logs, streams.stdout, 'stdout')
+  captureStreamWrites(logs, streams.stderr, 'stderr')
+
+  const pending = new Map<number, PendingCall>()
+  wireReplies(port, pending)
+
+  const nextId = { value: 1 }
+  const namespaces = makeNamespaces(data, port, pending, nextId)
+  const consoleShim = makeConsoleShim(logs)
+
+  let done: DoneMessage
+  try {
+    // The async function constructor, reached through an instance because
+    // `AsyncFunction` is not a global. The program body is strict-mode.
+    /* v8 ignore next -- the arrow exists only to reach the AsyncFunction constructor; it is never invoked. */
+    const AsyncFunction = (async () => {}).constructor as new (...args: string[]) => (...fnArgs: unknown[]) => Promise<unknown>
+    const fn = new AsyncFunction(...data.namespaces.map(namespace => namespace.global), 'console', `'use strict';\n${data.code}`)
+    const value = await fn(...namespaces, consoleShim)
+    done = { type: 'done', ...prepareValue(value, data.maxValueBytes) }
+  } catch (error: unknown) {
+    const message = error instanceof Error ? error.stack ?? error.message : String(error)
+    done = { type: 'done', error: { message } }
+  }
+  port.postMessage(done)
+}

packages/code-runtime/code-runtime-worker/src/index.ts

@@ -0,0 +1,441 @@
+/**
+ * Worker-thread implementation of the code-execution seam: one fresh Node
+ * worker per run, executing the model's TypeScript after a host-side
+ * type-strip, with bindings bridged over the message port. Containment, not
+ * a security boundary (bash-equivalent trust — see the Code Mode RFC's
+ * trust-posture section): the worker gets an EMPTY environment, a heap cap,
+ * and two independent budgets — `computeMs` metered on the worker's
+ * measured event-loop busy time (a hot loop cannot hide behind a pending
+ * binding call) and a never-pausing `maxWallMs` ceiling — all funneling
+ * into `worker.terminate()`, which ends hot synchronous loops too.
+ *
+ * @module @deepseek-ai/dsh-code-runtime-worker
+ */
+
+import { Worker } from 'node:worker_threads'
+import { stripTypeScriptTypes } from 'node:module'
+import { Context } from 'cordis'
+import z from 'schemastery'
+import { CodeRuntime } from '@deepseek-ai/dsh-code-runtime'
+import type { CodeBindingFunction, CodeLogEntry, CodeRunFailure, CodeRunRequest, CodeRunResult } from '@deepseek-ai/dsh-code-runtime'
+import { prepareValue, truncateUtf8Bytes } from './bootstrap.ts'
+import { logTruncationMarker } from './protocol.ts'
+import type { ReplyMessage, WorkerBootData, WorkerToHost } from './protocol.ts'
+
+export type { BootstrapPort, PatchableStream } from './bootstrap.ts'
+export type { CallMessage, DoneMessage, ReplyMessage, WorkerBootData, WorkerToHost } from './protocol.ts'
+
+/** Plugin config: every execution cap, changeable from `cordis.yml` (no hardcoded tunables). */
+export interface Config {
+  /**
+   * Busy-time budget in milliseconds: the run fails with kind `'timeout'`
+   * once the worker's MEASURED event-loop active time
+   * (`worker.performance.eventLoopUtilization()`) exceeds this. Metering
+   * measured busy time — not wall time, not host-side pending-call
+   * bookkeeping — is what makes the budget both fair (a program awaiting a
+   * slow tool accrues nothing) and ungameable (a hot loop accrues whether
+   * or not a decoy dispatch is in flight).
+   */
+  computeMs?: number
+  /**
+   * Wall-clock ceiling in milliseconds; never pauses for anything. The
+   * backstop for what busy-time cannot see (a program awaiting a promise
+   * nobody will resolve).
+   */
+  maxWallMs?: number
+  /** Shared byte budget for captured log text (console + raw stream writes), truncation marked in-band. */
+  maxLogBytes?: number
+  /**
+   * Byte cap for the completion value, measured by its real cross-boundary
+   * size (string bytes, or structured-clone wire size); an oversized or
+   * non-cloneable value crosses as a capped string rendering.
+   */
+  maxValueBytes?: number
+  /** The worker's max old-generation heap in MiB (`resourceLimits`); overflow kills the worker, surfacing as kind `'worker-exit'`. */
+  maxOldGenerationSizeMb?: number
+}
+
+/** {@link Config} after schemastery fills the defaults (every field present). */
+type ResolvedConfig = Required<Config>
+
+/**
+ * How often the host samples the worker's event-loop utilization for the
+ * `computeMs` budget. An internal cadence, not config: the only effect of
+ * the interval is budget-expiry granularity (a run can overshoot by up to
+ * one interval), and nothing a deployment could tune here improves that
+ * without burning host CPU.
+ */
+const ELU_POLL_INTERVAL_MS = 25
+
+/** ECMAScript reserved words that cannot be async-function parameter names — rejected as binding globals. */
+const RESERVED_WORDS = new Set([
+  'await', 'break', 'case', 'catch', 'class', 'const', 'continue', 'debugger', 'default', 'delete', 'do',
+  'else', 'enum', 'export', 'extends', 'false', 'finally', 'for', 'function', 'if', 'import', 'in',
+  'instanceof', 'new', 'null', 'return', 'super', 'switch', 'this', 'throw', 'true', 'try', 'typeof',
+  'var', 'void', 'while', 'with', 'yield', 'let', 'static', 'implements', 'interface', 'package',
+  'private', 'protected', 'public', 'arguments', 'eval',
+])
+
+/** Valid async-function parameter name (the binding global becomes one). */
+const IDENTIFIER = /^[A-Za-z_$][A-Za-z0-9_$]*$/
+
+/**
+ * The shell a program is wrapped in for the type-strip, matching the
+ * grammatical context it will execute in (an async function body, where
+ * top-level `return` and `await` are legal — a bare module parse would
+ * reject the `return`). Strip mode is position-preserving (removed syntax
+ * becomes whitespace, nothing shifts), so the wrapper survives the strip
+ * byte-identical and the body slices back out with the model's own
+ * line/column positions intact.
+ */
+const STRIP_WRAP = { prefix: 'async function __dsh_program__() {\n', suffix: '\n}' } as const
+
+/** One in-flight run's host-side state, tracked for disposal. */
+interface LiveRun {
+  worker: Worker
+  settle(failure: CodeRunFailure): void
+  finished: Promise<void>
+}
+
+/**
+ * The worker entry module. Source runs unbuilt (`src/worker.ts`, loadable
+ * directly on this repo's Node range via native type stripping — the file
+ * is erasable-only with type-only relative imports); the built package
+ * ships it as a sibling bundle (`lib/worker.js`, its own tsdown entry).
+ * The URL *pathname*'s extension says which world this module is in —
+ * pathname, because dev-time module runners (vitest) may suffix
+ * `import.meta.url` with a query string; relative resolution drops it.
+ */
+/* v8 ignore next -- the './worker.js' arm is the built-lib world, unreachable unbuilt by construction; the built-lib e2e pins it. */
+const WORKER_URL = new URL(new URL(import.meta.url).pathname.endsWith('.ts') ? './worker.ts' : './worker.js', import.meta.url)
+
+/** Render an unknown thrown value as a message, `Error` or not. */
+function messageOf(error: unknown): string {
+  return error instanceof Error ? error.message : String(error)
+}
+
+/** The log sources / console levels the seam vocabulary admits, as runtime sets for inbound-message validation. */
+const LOG_SOURCES = new Set<string>(['console', 'stdout', 'stderr'])
+const LOG_LEVELS = new Set<string>(['log', 'info', 'warn', 'error', 'debug'])
+
+/**
+ * Runtime shape gate for inbound port traffic. The peer runs MODEL CODE and
+ * can post anything — `null`, primitives, objects with poisoned fields — so
+ * the compile-time `WorkerToHost` type means nothing here: everything is
+ * re-validated and REBUILT field by field (a forged extra field never rides
+ * along; a non-number call id can never be echoed into a reply). Junk returns
+ * `undefined` and is dropped — a throw in the host's `message` listener would
+ * crash the host process.
+ */
+function parseWorkerMessage(raw: unknown): WorkerToHost | undefined {
+  if (typeof raw !== 'object' || raw === null) return undefined
+  const m = raw as Record<string, unknown>
+  switch (m.type) {
+    case 'call': {
+      if (typeof m.id !== 'number' || typeof m.global !== 'string' || typeof m.name !== 'string') return undefined
+      return { type: 'call', id: m.id, global: m.global, name: m.name, args: m.args }
+    }
+    case 'log': {
+      const entry = m.entry
+      if (typeof entry !== 'object' || entry === null) return undefined
+      const e = entry as Record<string, unknown>
+      if (typeof e.text !== 'string') return undefined
+      if (typeof e.source !== 'string' || !LOG_SOURCES.has(e.source)) return undefined
+      if (e.level !== undefined && (typeof e.level !== 'string' || !LOG_LEVELS.has(e.level))) return undefined
+      return {
+        type: 'log',
+        entry: {
+          source: e.source as CodeLogEntry['source'],
+          ...e.level !== undefined ? { level: e.level as Exclude<CodeLogEntry['level'], undefined> } : {},
+          text: e.text,
+        },
+      }
+    }
+    case 'done': {
+      if (m.error === undefined) return { type: 'done', ...m.value !== undefined ? { value: m.value } : {} }
+      const error = m.error
+      if (typeof error !== 'object' || error === null) return undefined
+      const message = (error as Record<string, unknown>).message
+      if (typeof message !== 'string') return undefined
+      return { type: 'done', ...m.value !== undefined ? { value: m.value } : {}, error: { message } }
+    }
+    default: return undefined
+  }
+}
+
+/**
+ * Headroom the host's value re-cap grants over `maxValueBytes`: exactly the
+ * truncation suffix {@link prepareValue} appends, so a value the WORKER
+ * already capped (byte-exact prefix + this marker) passes through unchanged
+ * instead of being marked twice.
+ */
+const VALUE_RENDER_SLACK = Buffer.byteLength('… [truncated]', 'utf8')
+
+/**
+ * The shipped {@link CodeRuntime} backend (`ctx.codeRuntime`). Registers as
+ * the `codeRuntime` service; every cap comes from validated config. See the
+ * module doc for the containment model and the class JSDoc on the seam for
+ * the contract this implements (error-as-field, hostile-peer port,
+ * no cross-run state, dispose to quiescence).
+ */
+export class WorkerCodeRuntime extends CodeRuntime {
+  static Config: z<Config> = z.object({
+    computeMs: z.number().default(60_000),
+    maxWallMs: z.number().default(600_000),
+    maxLogBytes: z.number().default(65_536),
+    maxValueBytes: z.number().default(32_768),
+    maxOldGenerationSizeMb: z.number().default(512),
+  })
+
+  readonly language = 'typescript'
+  readonly isolation = 'worker-thread'
+
+  private readonly config: ResolvedConfig
+  private readonly live = new Set<LiveRun>()
+  private disposed = false
+
+  constructor(ctx: Context, config: Config) {
+    super(ctx)
+    // Schemastery filled the defaults; the cast records that. Positivity is a
+    // semantic check the schema's plain number type does not carry.
+    this.config = config as ResolvedConfig
+    for (const [key, value] of Object.entries(this.config)) {
+      if (!(Number.isFinite(value) && value > 0)) throw new Error(`dsh-code-runtime-worker: config.${key} must be a positive number, got ${String(value)}`)
+    }
+    ctx.effect(() => () => this.teardown(), 'worker code-runtime teardown')
+  }
+
+  /**
+   * Dispose to quiescence: mark the service unusable, fail every in-flight
+   * run as aborted, and AWAIT each worker's exit so no worker outlives the
+   * fiber.
+   */
+  private async teardown(): Promise<void> {
+    this.disposed = true
+    const runs = [...this.live]
+    for (const run of runs) run.settle({ kind: 'abort', message: 'runtime disposed' })
+    await Promise.all(runs.map(run => run.finished))
+  }
+
+  /**
+   * Execute one program in a fresh worker. Program outcomes — including a
+   * type-strip syntax error, which never spawns a worker — resolve with
+   * `result.error`; the method rejects only for seam misuse (a disposed
+   * runtime, an invalid binding namespace).
+   * @param request - the program, its bindings, and the abort signal.
+   * @returns the run's outcome per the seam contract.
+   */
+  async run(request: CodeRunRequest): Promise<CodeRunResult> {
+    if (this.disposed) throw new Error('dsh-code-runtime-worker: run() after disposal')
+    const bindings = this.validateBindings(request)
+    if (request.signal?.aborted) {
+      return { logs: [], error: { kind: 'abort', message: String(request.signal.reason) } }
+    }
+
+    let code: string
+    try {
+      const stripped = stripTypeScriptTypes(STRIP_WRAP.prefix + request.program + STRIP_WRAP.suffix)
+      code = stripped.slice(STRIP_WRAP.prefix.length, stripped.length - STRIP_WRAP.suffix.length)
+    } catch (error: unknown) {
+      // A program that does not survive the type-strip (syntax error,
+      // non-erasable syntax like `enum`) is a program failure, reported the
+      // same way a thrown exception would be — and no worker ever spawns.
+      return { logs: [], error: { kind: 'exception', message: messageOf(error) } }
+    }
+
+    return await this.execute(request, code, bindings)
+  }
+
+  /** Reject (seam misuse) malformed binding namespaces: non-identifier or reserved globals, duplicates, and the `console` collision. */
+  private validateBindings(request: CodeRunRequest): Map<string, Record<string, CodeBindingFunction>> {
+    const bindings = new Map<string, Record<string, CodeBindingFunction>>()
+    for (const namespace of request.bindings) {
+      if (!IDENTIFIER.test(namespace.global) || RESERVED_WORDS.has(namespace.global)) {
+        throw new Error(`dsh-code-runtime-worker: binding global ${JSON.stringify(namespace.global)} is not a usable identifier`)
+      }
+      if (namespace.global === 'console' || bindings.has(namespace.global)) {
+        throw new Error(`dsh-code-runtime-worker: duplicate binding global ${JSON.stringify(namespace.global)}`)
+      }
+      bindings.set(namespace.global, namespace.functions)
+    }
+    return bindings
+  }
+
+  /** Spawn the worker for one validated, type-stripped run and drive it to settlement. */
+  private execute(
+    request: CodeRunRequest,
+    code: string,
+    bindings: Map<string, Record<string, CodeBindingFunction>>,
+  ): Promise<CodeRunResult> {
+    const bootData: WorkerBootData = {
+      code,
+      namespaces: [...bindings].map(([global, functions]) => ({ global, names: Object.keys(functions) })),
+      maxLogBytes: this.config.maxLogBytes,
+      maxValueBytes: this.config.maxValueBytes,
+    }
+    const worker = new Worker(WORKER_URL, {
+      workerData: bootData,
+      // Model code gets NO ambient environment — stronger than the scrubbed
+      // env the defensive-patterns rule requires for spawned commands.
+      env: {},
+      // Hermetic flags too: without this the worker inherits the host
+      // process's execArgv (a test runner's or tsx's loader hooks), which a
+      // bare isolate with an empty environment cannot satisfy. The entry
+      // needs nothing beyond native type stripping, on this repo's whole
+      // Node range.
+      execArgv: [],
+      resourceLimits: { maxOldGenerationSizeMb: this.config.maxOldGenerationSizeMb },
+      // Backstop capture: the bootstrap patches JS-level writes into its own
+      // ordered buffer, so these pipes normally stay silent; anything that
+      // still arrives (native-level writes) is appended after the done logs.
+      stdout: true,
+      stderr: true,
+    })
+
+    return new Promise<CodeRunResult>((resolve) => {
+      let settled = false
+      const answered = new Set<number>()
+      const logs: CodeLogEntry[] = []
+      const strayLogs: CodeLogEntry[] = []
+
+      // ONE host-side ledger for everything that lands in `logs`/`strayLogs`,
+      // whatever the path: honest port entries, FORGED port entries (model
+      // code posting `log` messages directly, bypassing the worker-side
+      // LogBuffer), and stray pipe bytes. On the first overflow it emits the
+      // same in-band marker the worker's LogBuffer would and drops the rest,
+      // so the documented cap is one shared `maxLogBytes` however it is hit.
+      let logBudget = this.config.maxLogBytes
+      let logsTruncated = false
+      const admit = (entry: CodeLogEntry, sink: CodeLogEntry[]): void => {
+        if (logsTruncated) return
+        const cost = Buffer.byteLength(entry.text, 'utf8')
+        if (cost > logBudget) {
+          logsTruncated = true
+          sink.push({ source: 'stderr', text: logTruncationMarker(this.config.maxLogBytes) })
+          return
+        }
+        logBudget -= cost
+        sink.push(entry)
+      }
+
+      // No settled guard: `finish` snapshots the arrays when it resolves, so
+      // a chunk flushing after settlement mutates only the discarded buffers,
+      // and the ledger bounds that growth until the pipes close.
+      const captureStray = (source: 'stdout' | 'stderr') => (chunk: Buffer) => {
+        admit({ source, text: chunk.toString('utf8') }, strayLogs)
+      }
+      worker.stdout.on('data', captureStray('stdout'))
+      worker.stderr.on('data', captureStray('stderr'))
+
+      // Settlement: exactly one outcome wins; every path funnels through
+      // here, cleans up the timers/listeners, terminates the worker, and
+      // resolves only after the worker actually exited (quiescence). Logs
+      // streamed eagerly before the settlement are kept — a timed-out or
+      // killed program still shows the model what it printed.
+      let finishResolve!: () => void
+      const finished = new Promise<void>((done) => { finishResolve = done })
+      const finish = (result: Omit<CodeRunResult, 'logs'>): void => {
+        if (settled) return
+        settled = true
+        clearInterval(eluTimer)
+        clearTimeout(wallTimer)
+        request.signal?.removeEventListener('abort', onAbort)
+        this.live.delete(live)
+        void worker.terminate().then(() => {
+          finishResolve()
+          resolve({ ...result, logs: [...logs, ...strayLogs] })
+        })
+      }
+
+      const onDone = (message: WorkerToHost): void => {
+        if (message.type !== 'done') return
+        // Re-cap the completion value HOST-side: the honest path already
+        // capped it in the worker (prepareValue there), but a forged done
+        // message bypasses the bootstrap entirely — without this, model code
+        // could flood the host past maxValueBytes. Honest values pass
+        // unchanged (see VALUE_RENDER_SLACK); the error text is bounded too.
+        finish({
+          ...prepareValue(message.value, this.config.maxValueBytes + VALUE_RENDER_SLACK),
+          ...message.error ? { error: { kind: 'exception' as const, message: truncateUtf8Bytes(message.error.message, this.config.maxValueBytes) } } : {},
+        })
+      }
+
+      const onCall = (message: WorkerToHost): void => {
+        if (message.type !== 'call' || settled) return
+        // Hostile-peer rules: a duplicate id is ignored, an unknown name is
+        // answered with a failure, and a binding throw/reject becomes the
+        // program-side rejection — contained here, never a host crash.
+        if (answered.has(message.id)) return
+        answered.add(message.id)
+        const reply = (payload: ReplyMessage): void => {
+          if (settled) return
+          try {
+            worker.postMessage(payload)
+          } catch {
+            // The reply value failed structured clone; renegotiate as an error
+            // reply, which is always clone-plain. Nothing else throws here.
+            worker.postMessage({ type: 'reply', id: message.id, ok: false, message: 'binding resolution is not structured-cloneable' })
+          }
+        }
+        const record = bindings.get(message.global)
+        // Own-property lookup only: a forged name like 'constructor' or
+        // 'hasOwnProperty' must not walk the record's prototype chain and
+        // reach a callable the consumer never declared.
+        const fn = record && Object.hasOwn(record, message.name) ? record[message.name] : undefined
+        if (typeof fn !== 'function') {
+          reply({ type: 'reply', id: message.id, ok: false, message: `unknown binding ${JSON.stringify(`${message.global}.${message.name}`)}` })
+          return
+        }
+        void (async () => {
+          try {
+            reply({ type: 'reply', id: message.id, ok: true, value: await fn(message.args) })
+          } catch (error: unknown) {
+            reply({ type: 'reply', id: message.id, ok: false, message: messageOf(error) })
+          }
+        })()
+      }
+
+      worker.on('message', (raw: unknown) => {
+        // Parse before touching: the peer can post ANY shape, and a throw in
+        // this listener would crash the host process. Junk drops silently.
+        const message = parseWorkerMessage(raw)
+        if (!message) return
+        if (message.type === 'log' && !settled) admit(message.entry, logs)
+        onCall(message)
+        onDone(message)
+      })
+      worker.on('error', (error: Error) => {
+        finish({ error: { kind: 'worker-exit', message: `worker error: ${error.message}` } })
+      })
+      worker.on('exit', (exitCode: number) => {
+        finish({ error: { kind: 'worker-exit', message: `worker exited with code ${exitCode} before completing` } })
+      })
+
+      // The compute budget reads the worker's own measured busy time, so a
+      // hot loop expires it no matter what dispatches are in flight, while a
+      // program idling on a slow binding accrues nothing.
+      const eluTimer = setInterval(() => {
+        const elu = worker.performance.eventLoopUtilization()
+        if (elu.active > this.config.computeMs) {
+          finish({ error: { kind: 'timeout', message: `compute budget exhausted (${this.config.computeMs}ms busy)` } })
+        }
+      }, ELU_POLL_INTERVAL_MS)
+      const wallTimer = setTimeout(() => {
+        finish({ error: { kind: 'timeout', message: `wall-clock ceiling reached (${this.config.maxWallMs}ms)` } })
+      }, this.config.maxWallMs)
+      const onAbort = (): void => {
+        finish({ error: { kind: 'abort', message: String(request.signal?.reason) } })
+      }
+      request.signal?.addEventListener('abort', onAbort, { once: true })
+
+      const live: LiveRun = {
+        worker,
+        finished,
+        settle: (failure: CodeRunFailure) => { finish({ error: failure }) },
+      }
+      this.live.add(live)
+    })
+  }
+}
+
+export default WorkerCodeRuntime

packages/code-runtime/code-runtime-worker/src/protocol.ts

@@ -0,0 +1,78 @@
+/**
+ * Wire protocol between the host runtime and the worker bootstrap. Everything
+ * crossing the message port is structured-clone-plain and versionless — both
+ * ends ship in this package, always at the same version. The host treats
+ * inbound traffic as HOSTILE (the worker runs model code, which can reach
+ * `parentPort` via `import('node:worker_threads')` and forge any of these
+ * shapes); the worker treats inbound traffic as trusted.
+ *
+ * @module @deepseek-ai/dsh-code-runtime-worker/src/protocol
+ */
+
+import type { CodeLogEntry } from '@deepseek-ai/dsh-code-runtime'
+
+/** What the host hands the worker at spawn, via `workerData`. */
+export interface WorkerBootData {
+  /** The type-stripped (plain JS) program body. */
+  code: string
+  /** Binding namespaces to materialize: the global name plus the function names (functions themselves stay host-side). */
+  namespaces: { global: string; names: string[] }[]
+  /** Shared byte budget for captured log text; exceeding it drops further entries after one in-band marker. */
+  maxLogBytes: number
+  /** Byte cap for the rendered completion value (see the value-preparation contract in bootstrap.ts). */
+  maxValueBytes: number
+}
+
+/** Worker → host: one bridged binding call. */
+export interface CallMessage {
+  type: 'call'
+  /** Worker-issued correlation id; the host answers each id at most once and ignores duplicates. */
+  id: number
+  /** The namespace global the call targets. */
+  global: string
+  /** The function name within the namespace. */
+  name: string
+  /** The single argument, structured-clone-plain. */
+  args: unknown
+}
+
+/** Worker → host: one captured log entry, streamed eagerly so output survives a mid-run termination (timeout, abort, OOM). */
+export interface LogMessage {
+  type: 'log'
+  entry: CodeLogEntry
+}
+
+/**
+ * Worker → host: the program settled. `error` carries a program exception
+ * (the only failure the bootstrap itself can report — budgets, aborts, and
+ * substrate death are observed host-side). `value` is present only on a
+ * clean completion that produced one (already size-capped and
+ * clone-safe per the bootstrap's value preparation). Logs are NOT carried
+ * here — they streamed eagerly as {@link LogMessage}s.
+ */
+export interface DoneMessage {
+  type: 'done'
+  value?: unknown
+  error?: { message: string }
+}
+
+/** Every message the worker sends. */
+export type WorkerToHost = CallMessage | LogMessage | DoneMessage
+
+/** Host → worker: the answer to one {@link CallMessage}. */
+export type ReplyMessage =
+  | { type: 'reply'; id: number; ok: true; value: unknown }
+  | { type: 'reply'; id: number; ok: false; message: string }
+
+/**
+ * The in-band marker entry text announcing that log capture stopped at the
+ * byte budget. Shared wire vocabulary: the worker's LogBuffer emits it when
+ * ITS budget exhausts, and the host emits the identical text when its own
+ * ledger drops an entry first (forged port traffic, stray pipe bytes) — so
+ * a truncated run reads the same however the cap was hit.
+ * @param maxBytes - the configured `maxLogBytes` the marker names.
+ * @returns the marker line.
+ */
+export function logTruncationMarker(maxBytes: number): string {
+  return `[dsh-code-runtime-worker] log capture truncated at ${maxBytes} bytes`
+}

packages/code-runtime/code-runtime-worker/src/worker.ts

@@ -0,0 +1,20 @@
+/**
+ * The worker-thread entrypoint: self-executing glue over
+ * `bootstrap.ts`'s {@link runWorkerMain}, kept to the spawn wiring alone.
+ * Like `bin.ts` CLI entrypoints, this file executes only inside a spawned
+ * worker isolate — a place the coverage provider cannot observe — so it is
+ * excluded from the coverage gate while every line of actual logic lives in
+ * `bootstrap.ts`, unit-tested in-process; the real spawn path is pinned by
+ * the integration tests that run genuine workers.
+ *
+ * @module @deepseek-ai/dsh-code-runtime-worker/src/worker
+ */
+
+import { parentPort, workerData } from 'node:worker_threads'
+import { runWorkerMain } from './bootstrap.ts'
+import type { WorkerBootData } from './protocol.ts'
+
+// A worker always has a parent port; guard loudly rather than run detached.
+if (!parentPort) throw new Error('dsh-code-runtime-worker: worker entry loaded outside a worker thread')
+
+await runWorkerMain(parentPort, workerData as WorkerBootData, { stdout: process.stdout, stderr: process.stderr })

packages/code-runtime/code-runtime-worker/tests/bootstrap.spec.ts

@@ -0,0 +1,273 @@
+import { describe, expect, it } from 'vitest'
+import { EventEmitter } from 'node:events'
+import { LogBuffer, makeConsoleShim, makeNamespaces, captureStreamWrites, prepareValue, runWorkerMain, truncateUtf8Bytes, wireReplies } from '@deepseek-ai/dsh-code-runtime-worker/src/bootstrap.ts'
+import type { BootstrapPort, PatchableStream, PendingCall } from '@deepseek-ai/dsh-code-runtime-worker/src/bootstrap.ts'
+import type { ReplyMessage, WorkerToHost } from '@deepseek-ai/dsh-code-runtime-worker/src/protocol.ts'
+import type { CodeLogEntry } from '@deepseek-ai/dsh-code-runtime'
+
+/**
+ * An in-process stand-in for the worker's parentPort: the test plays the
+ * HOST side — inspect what the bootstrap posted, feed replies back — so
+ * every line of worker-side logic runs under coverage without spawning an
+ * isolate (real-worker behavior is pinned by runtime.spec.ts).
+ */
+class FakePort implements BootstrapPort {
+  sent: WorkerToHost[] = []
+  private readonly emitter = new EventEmitter()
+  /** Host-scripted responder; return undefined to leave the call pending. */
+  respond: (message: WorkerToHost) => ReplyMessage | undefined = () => undefined
+
+  postMessage(message: WorkerToHost): void {
+    this.sent.push(message)
+    const reply = this.respond(message)
+    if (reply) queueMicrotask(() => this.emitter.emit('message', reply))
+  }
+
+  on(event: 'message', listener: (message: ReplyMessage) => void): void {
+    this.emitter.on(event, listener)
+  }
+
+  deliver(message: ReplyMessage): void {
+    this.emitter.emit('message', message)
+  }
+
+  logs(): CodeLogEntry[] {
+    return this.sent.filter(message => message.type === 'log').map(message => message.entry)
+  }
+
+  done(): WorkerToHost | undefined {
+    return this.sent.find(message => message.type === 'done')
+  }
+}
+
+function fakeStreams(): { stdout: PatchableStream; stderr: PatchableStream } {
+  return { stdout: { write: () => true }, stderr: { write: () => true } }
+}
+
+const BOOT = { maxLogBytes: 65_536, maxValueBytes: 32_768 }
+
+describe('LogBuffer', () => {
+  it('streams entries to the sink until the byte budget, then emits one marker and drops the rest', () => {
+    const seen: CodeLogEntry[] = []
+    const buffer = new LogBuffer(10, entry => seen.push(entry))
+    buffer.push({ source: 'console', level: 'log', text: '12345' })
+    buffer.push({ source: 'console', level: 'log', text: '123456' })
+    buffer.push({ source: 'console', level: 'log', text: 'dropped' })
+    expect(seen.map(entry => entry.text)).toEqual([
+      '12345',
+      '[dsh-code-runtime-worker] log capture truncated at 10 bytes',
+    ])
+  })
+})
+
+describe('makeConsoleShim', () => {
+  it('captures the five levels and renders non-strings inspect-style', () => {
+    const seen: CodeLogEntry[] = []
+    const shim = makeConsoleShim(new LogBuffer(1_000, entry => seen.push(entry)))
+    shim.log('plain', { a: 1 })
+    shim.info('i')
+    shim.warn('w')
+    shim.error('e')
+    shim.debug('d')
+    expect(seen.map(entry => entry.level)).toEqual(['log', 'info', 'warn', 'error', 'debug'])
+    expect(seen[0]?.text).toBe('plain { a: 1 }')
+    expect(seen.every(entry => entry.source === 'console')).toBe(true)
+  })
+})
+
+describe('captureStreamWrites', () => {
+  it('redirects writes into the buffer and restores on request', () => {
+    const seen: CodeLogEntry[] = []
+    const buffer = new LogBuffer(1_000, entry => seen.push(entry))
+    let underlying = ''
+    const stream: PatchableStream = { write: (chunk: unknown) => { underlying += String(chunk); return true } }
+    const restore = captureStreamWrites(buffer, stream, 'stdout')
+    stream.write('captured', 'utf8')
+    stream.write(Buffer.from('bytes'))
+    restore()
+    stream.write('after')
+    expect(seen.map(entry => entry.text)).toEqual(['captured', 'bytes'])
+    expect(seen[0]).toMatchObject({ source: 'stdout' })
+    expect(underlying).toBe('after')
+  })
+
+  it('invokes the write callback asynchronously, in both optional-encoding shapes', async () => {
+    const buffer = new LogBuffer(1_000, () => {})
+    const stream: PatchableStream = { write: () => true }
+    captureStreamWrites(buffer, stream, 'stdout')
+    const calls: (Error | null | undefined)[] = []
+    stream.write('two-arg', (error?: Error | null) => calls.push(error))
+    stream.write('three-arg', 'utf8', (error?: Error | null) => calls.push(error))
+    // Node's contract: the callback fires after the write call returns.
+    expect(calls).toEqual([])
+    await new Promise<void>(resolve => stream.write('awaited flush', resolve))
+    expect(calls).toEqual([null, null])
+  })
+
+  it('still fires the callback for a write the exhausted budget drops', async () => {
+    const buffer = new LogBuffer(4, () => {})
+    const stream: PatchableStream = { write: () => true }
+    captureStreamWrites(buffer, stream, 'stdout')
+    stream.write('this write overflows the budget and is dropped')
+    await new Promise<void>(resolve => stream.write('also dropped', resolve))
+  })
+})
+
+describe('prepareValue', () => {
+  it('omits undefined, passes small cloneable values raw', () => {
+    expect(prepareValue(undefined, 100)).toEqual({})
+    expect(prepareValue({ a: [1, 'two'] }, 100)).toEqual({ value: { a: [1, 'two'] } })
+  })
+
+  it('replaces a non-cloneable value with its rendering', () => {
+    const { value } = prepareValue({ fn: () => 1 }, 1_000)
+    expect(typeof value).toBe('string')
+    expect(value).toContain('fn')
+  })
+
+  it('replaces an oversized value with a truncation-marked capped rendering', () => {
+    const { value } = prepareValue('x'.repeat(50), 10)
+    expect(value).toBe(`${'x'.repeat(10)}… [truncated]`)
+  })
+
+  it('measures a container by its structured-clone wire size, not its bounded rendering', () => {
+    // The bounded inspect rendering of a huge array is tiny ("... N more
+    // items"), but its real cross-boundary size is not — the cap must catch
+    // it, replacing the value with that bounded rendering.
+    const huge = new Array(50_000).fill(7)
+    const { value } = prepareValue(huge, 1_000)
+    expect(typeof value).toBe('string')
+    expect(value).toContain('more items')
+  })
+
+  it('caps a multibyte string by UTF-8 bytes, not UTF-16 length', () => {
+    // 4 code units but 12 UTF-8 bytes: a length-counting cap would pass the
+    // full string through untruncated.
+    expect(prepareValue('€€€€', 4)).toEqual({ value: '€… [truncated]' })
+  })
+
+  it('caps a multibyte rendering by UTF-8 bytes too', () => {
+    // Wire size (24-byte string inside an array) exceeds the cap, so the
+    // value crosses as its rendering — whose truncation must also be
+    // byte-exact: "[ '" (3 bytes) + two € (6 bytes) = 9; a third € would
+    // overflow the 10-byte budget.
+    expect(prepareValue(['€€€€€€€€'], 10)).toEqual({ value: "[ '€€… [truncated]" })
+  })
+})
+
+describe('truncateUtf8Bytes', () => {
+  it('returns a fitting string whole', () => {
+    expect(truncateUtf8Bytes('fits', 4)).toBe('fits')
+  })
+
+  it('cuts at a code-point boundary, never mid-surrogate-pair', () => {
+    // Each 😀 is one code point, two code units, four UTF-8 bytes: a 5-byte
+    // budget fits exactly one — and never leaves a lone surrogate behind.
+    const cut = truncateUtf8Bytes('😀😀', 5)
+    expect(cut).toBe('😀')
+    expect(Buffer.byteLength(truncateUtf8Bytes('😀😀', 3), 'utf8')).toBe(0)
+  })
+})
+
+describe('makeNamespaces', () => {
+  it('exposes prototype-colliding names as ordinary own properties', async () => {
+    const port = new FakePort()
+    port.respond = message => message.type === 'call' ? { type: 'reply', id: message.id, ok: true, value: `${message.name}-ok` } : undefined
+    const pending = new Map<number, PendingCall>()
+    wireReplies(port, pending)
+    const [tools] = makeNamespaces({ namespaces: [{ global: 'tools', names: ['__proto__', 'constructor', 'toString'] }] }, port, pending, { value: 1 }) as [Record<string, (args: unknown) => Promise<unknown>>]
+    expect(Object.getPrototypeOf(tools)).toBeNull()
+    await expect(tools['__proto__']?.({})).resolves.toBe('__proto__-ok')
+    await expect(tools['constructor']?.({})).resolves.toBe('constructor-ok')
+    await expect(tools['toString']?.({})).resolves.toBe('toString-ok')
+  })
+
+  it('rejects a non-cloneable argument without leaking the pending entry', async () => {
+    let firstCall = true
+    const throwingPort: BootstrapPort = {
+      // First call throws an Error (the real DataCloneError shape), the
+      // second a bare string — the rejection renders both.
+      postMessage: () => {
+        if (firstCall) { firstCall = false; throw new Error('DataCloneError-ish') }
+        throw 'raw-clone-failure'
+      },
+      on: () => {},
+    }
+    const pending = new Map<number, PendingCall>()
+    const [tools] = makeNamespaces({ namespaces: [{ global: 'tools', names: ['x'] }] }, throwingPort, pending, { value: 1 }) as [Record<string, (args: unknown) => Promise<unknown>>]
+    await expect(tools.x?.(() => 1)).rejects.toThrow(/structured-cloneable: DataCloneError-ish/)
+    await expect(tools.x?.(() => 1)).rejects.toThrow(/structured-cloneable: raw-clone-failure/)
+    expect(pending.size).toBe(0)
+  })
+})
+
+describe('runWorkerMain', () => {
+  it('runs a program end-to-end: bindings, console, return value', async () => {
+    const port = new FakePort()
+    port.respond = message => message.type === 'call' ? { type: 'reply', id: message.id, ok: true, value: (message.args as { n: number }).n * 2 } : undefined
+    await runWorkerMain(port, {
+      ...BOOT,
+      code: 'const doubled = await tools.double({ n: 21 }); console.log("got", doubled); return { doubled };',
+      namespaces: [{ global: 'tools', names: ['double'] }],
+    }, fakeStreams())
+    expect(port.logs()).toEqual([{ source: 'console', level: 'log', text: 'got 42' }])
+    expect(port.done()).toEqual({ type: 'done', value: { doubled: 42 } })
+  })
+
+  it('reports a thrown program error on the done message', async () => {
+    const port = new FakePort()
+    await runWorkerMain(port, { ...BOOT, code: 'throw new Error("boom")', namespaces: [] }, fakeStreams())
+    const done = port.done()
+    expect(done?.type).toBe('done')
+    expect(done?.type === 'done' ? done.error?.message : undefined).toContain('boom')
+    expect(done?.type === 'done' ? done.value : undefined).toBeUndefined()
+  })
+
+  it('renders non-Error throws and stack-less Errors on the done message', async () => {
+    const rawPort = new FakePort()
+    await runWorkerMain(rawPort, { ...BOOT, code: 'throw "raw-throw"', namespaces: [] }, fakeStreams())
+    expect(rawPort.done()).toEqual({ type: 'done', error: { message: 'raw-throw' } })
+
+    const barePort = new FakePort()
+    await runWorkerMain(barePort, { ...BOOT, code: 'const e = new Error("bare"); e.stack = undefined; throw e', namespaces: [] }, fakeStreams())
+    expect(barePort.done()).toEqual({ type: 'done', error: { message: 'bare' } })
+  })
+
+  it('surfaces a host failure reply as a program-side rejection it can catch', async () => {
+    const port = new FakePort()
+    port.respond = message => message.type === 'call' ? { type: 'reply', id: message.id, ok: false, message: 'denied by host' } : undefined
+    await runWorkerMain(port, {
+      ...BOOT,
+      code: 'try { await tools.x({}) } catch (error) { return `caught: ${error.message}` }',
+      namespaces: [{ global: 'tools', names: ['x'] }],
+    }, fakeStreams())
+    expect(port.done()).toEqual({ type: 'done', value: 'caught: denied by host' })
+  })
+
+  it('ignores replies for unknown pending ids', async () => {
+    const port = new FakePort()
+    port.respond = (message) => {
+      if (message.type !== 'call') return undefined
+      // Deliver a stray reply first; the real one follows.
+      port.deliver({ type: 'reply', id: 9_999, ok: true, value: 'stray' })
+      return { type: 'reply', id: message.id, ok: true, value: 'real' }
+    }
+    await runWorkerMain(port, {
+      ...BOOT,
+      code: 'return await tools.x({})',
+      namespaces: [{ global: 'tools', names: ['x'] }],
+    }, fakeStreams())
+    expect(port.done()).toEqual({ type: 'done', value: 'real' })
+  })
+
+  it('captures raw stream writes through the patched process streams', async () => {
+    const port = new FakePort()
+    const streams = fakeStreams()
+    await runWorkerMain(port, { ...BOOT, code: 'return 1', namespaces: [] }, streams)
+    streams.stdout.write('never seen — already restored? no: patch persists in worker')
+    // The patch stays installed for the worker's lifetime; writes during the
+    // program landed in order. Here the program wrote nothing via streams, so
+    // only the post-run write above went through the patched slot.
+    expect(port.logs().at(-1)).toMatchObject({ source: 'stdout' })
+  })
+})

packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts

@@ -0,0 +1,55 @@
+import { spawn } from 'node:child_process'
+import { existsSync } from 'node:fs'
+import { join } from 'node:path'
+import { fileURLToPath } from 'node:url'
+import { describe, expect, it } from 'vitest'
+
+/**
+ * BUILT-ARTIFACT smoke for the published package (the real-load-path guard
+ * from docs/testing.md): the unit suite runs `src/` under vitest, where the
+ * worker entry resolves to `src/worker.ts` — a consumer runs `lib/index.js`
+ * under plain `node`, where it must resolve the sibling `lib/worker.js`
+ * bundle instead. This spawns plain `node` (NOT tsx) from inside the package
+ * directory and imports the package BY NAME, so resolution flows through the
+ * real `exports` map exactly as it would from a downstream install; the
+ * program exercises the type-strip, the worker spawn, the binding bridge,
+ * and log capture end-to-end through the built bundles.
+ *
+ * It build-gates: SKIPS when the built artifacts are absent (suite run
+ * without `pnpm run build`); CI runs it after the build step. KEYLESS — no
+ * model is involved.
+ */
+
+const pkgDir = fileURLToPath(new URL('..', import.meta.url))
+const built = ['lib/index.js', 'lib/worker.js'].every(file => existsSync(join(pkgDir, file)))
+  && existsSync(join(pkgDir, '../code-runtime/lib/index.js'))
+
+describe.skipIf(!built)('built lib real load path (plain node)', () => {
+  it('runs a TypeScript program with a binding through lib/index.js and its lib/worker.js entry', async () => {
+    const script = `
+      const { Context } = await import('cordis')
+      const { WorkerCodeRuntime } = await import('@deepseek-ai/dsh-code-runtime-worker')
+      const ctx = new Context()
+      await ctx.plugin(WorkerCodeRuntime, {})
+      const result = await ctx.codeRuntime.run({
+        program: 'const doubled: number = await tools.double({ n: 21 }); console.log("halfway", doubled); return doubled;',
+        bindings: [{ global: 'tools', functions: { double: async args => args.n * 2 } }],
+      })
+      console.log(JSON.stringify(result))
+      process.exit(0)
+    `
+    const child = spawn(process.execPath, ['--input-type=module', '-e', script], { cwd: pkgDir, stdio: ['ignore', 'pipe', 'pipe'] })
+    let stdout = ''
+    let stderr = ''
+    child.stdout.on('data', (chunk: Buffer) => { stdout += chunk.toString('utf8') })
+    child.stderr.on('data', (chunk: Buffer) => { stderr += chunk.toString('utf8') })
+    const exitCode = await new Promise<number | null>(resolve => child.on('close', resolve))
+
+    expect(exitCode, `stderr:\n${stderr}`).toBe(0)
+    const lastLine = stdout.trim().split('\n').at(-1) ?? ''
+    const result = JSON.parse(lastLine) as { value?: unknown; logs: { source: string; level?: string; text: string }[]; error?: unknown }
+    expect(result.error).toBeUndefined()
+    expect(result.value).toBe(42)
+    expect(result.logs).toContainEqual({ source: 'console', level: 'log', text: 'halfway 42' })
+  })
+})

packages/code-runtime/code-runtime-worker/tests/runtime.spec.ts

@@ -0,0 +1,451 @@
+import { describe, expect, it } from 'vitest'
+import { Context } from 'cordis'
+import { WorkerCodeRuntime } from '@deepseek-ai/dsh-code-runtime-worker'
+import type { Config } from '@deepseek-ai/dsh-code-runtime-worker'
+import type { CodeRunResult } from '@deepseek-ai/dsh-code-runtime'
+
+/**
+ * Integration suite over REAL worker threads (no mocks — workers are cheap
+ * and local, per docs/testing.md's real-over-mock policy). Each test builds
+ * a fresh context so budgets can be tuned per case.
+ */
+async function setup(config: Config = {}) {
+  const ctx = new Context()
+  await ctx.plugin(WorkerCodeRuntime, config)
+  const runtime = ctx.codeRuntime as WorkerCodeRuntime
+  return { ctx, runtime }
+}
+
+/** Convenience: one namespace `tools` with the given functions. */
+function tools(functions: Record<string, (args: unknown) => Promise<unknown>>) {
+  return [{ global: 'tools', functions }]
+}
+
+describe('WorkerCodeRuntime — programs and bindings (real workers)', () => {
+  it('registers with the seam descriptors', async () => {
+    const { runtime } = await setup()
+    expect(runtime.language).toBe('typescript')
+    expect(runtime.isolation).toBe('worker-thread')
+  })
+
+  it('runs TypeScript (erasable syntax), captures console/stdout in order, returns the value', async () => {
+    const { runtime } = await setup()
+    const result = await runtime.run({
+      program: `
+        interface Point { x: number; y: number }
+        const p: Point = { x: 1, y: 2 } as Point;
+        console.log('point', p);
+        process.stdout.write('raw-out\\n');
+        console.warn('careful');
+        return p.x + p.y;
+      `,
+      bindings: [],
+    })
+    expect(result.error).toBeUndefined()
+    expect(result.value).toBe(3)
+    expect(result.logs.map(entry => [entry.source, entry.level ?? null])).toEqual([
+      ['console', 'log'],
+      ['stdout', null],
+      ['console', 'warn'],
+    ])
+    expect(result.logs[0]?.text).toBe('point { x: 1, y: 2 }')
+  })
+
+  it('bridges binding calls both ways and rejects the program-side call on a host rejection', async () => {
+    const { runtime } = await setup()
+    const calls: unknown[] = []
+    const result = await runtime.run({
+      program: `
+        const first = await tools.echo({ n: 1 });
+        let caught = '';
+        try { await tools.fail({}) } catch (error) { caught = error.message }
+        let caughtRaw = '';
+        try { await tools.failRaw({}) } catch (error) { caughtRaw = error.message }
+        return { first, caught, caughtRaw };
+      `,
+      bindings: tools({
+        echo: async (args) => { calls.push(args); return { echoed: args } },
+        fail: async () => { throw new Error('nope') },
+        // A non-Error throw: the host renders it, the program still catches.
+        failRaw: async () => { throw 'raw-nope' },
+      }),
+    })
+    expect(result.error).toBeUndefined()
+    expect(result.value).toEqual({ first: { echoed: { n: 1 } }, caught: 'nope', caughtRaw: 'raw-nope' })
+    expect(calls).toEqual([{ n: 1 }])
+  })
+
+  it('reports non-erasable syntax as an exception without spawning a worker', async () => {
+    const { runtime } = await setup()
+    const result = await runtime.run({ program: 'enum E { A }\nreturn 1', bindings: [] })
+    expect(result.error?.kind).toBe('exception')
+    expect(result.error?.message).toMatch(/enum|strip/i)
+  })
+
+  it('reports a runtime throw as an exception with the message', async () => {
+    const { runtime } = await setup()
+    const result = await runtime.run({ program: 'throw new Error("kaboom")', bindings: [] })
+    expect(result.error?.kind).toBe('exception')
+    expect(result.error?.message).toContain('kaboom')
+  })
+
+  it('gives the program an EMPTY environment', async () => {
+    const { runtime } = await setup()
+    const result = await runtime.run({ program: 'return JSON.stringify(process.env)', bindings: [] })
+    expect(result.value).toBe('{}')
+  })
+
+  it('replaces a non-cloneable return value with a string rendering', async () => {
+    const { runtime } = await setup()
+    const result = await runtime.run({ program: 'return { f: () => 1 }', bindings: [] })
+    expect(typeof result.value).toBe('string')
+  })
+
+  it('completes a program that returns nothing with no value at all', async () => {
+    const { runtime } = await setup()
+    const result = await runtime.run({ program: 'const x = 1', bindings: [] })
+    expect(result.error).toBeUndefined()
+    expect('value' in result).toBe(false)
+  })
+
+  it('keeps logs streamed before a failure', async () => {
+    const { runtime } = await setup()
+    const result = await runtime.run({
+      program: 'console.log("before"); throw new Error("after-log")',
+      bindings: [],
+    })
+    expect(result.error?.kind).toBe('exception')
+    expect(result.logs.map(entry => entry.text)).toContain('before')
+  })
+})
+
+describe('WorkerCodeRuntime — budgets and containment (real workers)', () => {
+  it('ends a hot loop at the compute budget — including behind a pending decoy dispatch', async () => {
+    const { runtime } = await setup({ computeMs: 300, maxWallMs: 30_000 })
+    const result = await runtime.run({
+      // The decoy: fire a call at a never-resolving binding WITHOUT awaiting,
+      // then spin. Host-side pending-call bookkeeping would pause a naive
+      // budget here; measured busy time cannot be fooled.
+      program: 'void tools.slow({}); for (;;) {}',
+      bindings: tools({ slow: () => new Promise(() => {}) }),
+    })
+    expect(result.error?.kind).toBe('timeout')
+    expect(result.error?.message).toContain('compute budget')
+  }, 15_000)
+
+  it('does not charge time spent awaiting a slow binding against the compute budget', async () => {
+    const { runtime } = await setup({ computeMs: 250, maxWallMs: 30_000 })
+    const result = await runtime.run({
+      program: 'return await tools.slow({})',
+      bindings: tools({ slow: () => new Promise(resolve => setTimeout(() => { resolve('slow-done') }, 700)) }),
+    })
+    expect(result.error).toBeUndefined()
+    expect(result.value).toBe('slow-done')
+  }, 15_000)
+
+  it('ends an idle-forever run at the wall-clock ceiling', async () => {
+    const { runtime } = await setup({ computeMs: 30_000, maxWallMs: 400 })
+    const result = await runtime.run({
+      program: 'await tools.never({}); return 1',
+      bindings: tools({ never: () => new Promise(() => {}) }),
+    })
+    expect(result.error?.kind).toBe('timeout')
+    expect(result.error?.message).toContain('wall-clock ceiling')
+  }, 15_000)
+
+  it('reports an abort mid-run and stops the worker', async () => {
+    const { runtime } = await setup()
+    const controller = new AbortController()
+    setTimeout(() => { controller.abort('user-cancel') }, 150)
+    const result = await runtime.run({ program: 'for (;;) {}', bindings: [], signal: controller.signal })
+    expect(result.error).toEqual({ kind: 'abort', message: 'user-cancel' })
+  }, 15_000)
+
+  it('reports a pre-aborted signal without spawning', async () => {
+    const { runtime } = await setup()
+    const controller = new AbortController()
+    controller.abort('too-late')
+    const result = await runtime.run({ program: 'return 1', bindings: [], signal: controller.signal })
+    expect(result.error).toEqual({ kind: 'abort', message: 'too-late' })
+  })
+
+  it('drops a binding resolution that lands after the run settled', async () => {
+    const { runtime } = await setup()
+    const controller = new AbortController()
+    let replyDelivered!: Promise<void>
+    const result = await runtime.run({
+      program: 'void tools.late({}); for (;;) {}',
+      bindings: tools({
+        // Anchored on invocation: abort 100ms after the call reaches the
+        // host, resolve 400ms after — by then the run has settled, so the
+        // resolution's reply hits the post-settlement drop.
+        late: () => new Promise((resolve) => {
+          setTimeout(() => { controller.abort('cancel-now') }, 100)
+          replyDelivered = new Promise(done => setTimeout(() => { resolve('too-late'); done() }, 400))
+        }),
+      }),
+      signal: controller.signal,
+    })
+    expect(result.error).toEqual({ kind: 'abort', message: 'cancel-now' })
+    // Let the late resolution actually fire so its reply executes instead of
+    // being cancelled with the test.
+    await replyDelivered
+  }, 15_000)
+
+  it('contains an OOM under resourceLimits as worker-exit, host process healthy', async () => {
+    const { runtime } = await setup({ maxOldGenerationSizeMb: 32 })
+    const result = await runtime.run({
+      program: 'const hog = []; for (;;) hog.push(new Array(1e6).fill(1));',
+      bindings: [],
+    })
+    expect(result.error?.kind).toBe('worker-exit')
+    // And the host is fine: run something else.
+    const after = await runtime.run({ program: 'return "alive"', bindings: [] })
+    expect(after.value).toBe('alive')
+  }, 30_000)
+
+  it('truncates runaway log output at the byte budget with an in-band marker', async () => {
+    const { runtime } = await setup({ maxLogBytes: 300 })
+    const result = await runtime.run({
+      program: 'for (let i = 0; i < 1000; i++) console.log("spam line", i); return 1',
+      bindings: [],
+    })
+    expect(result.logs.at(-1)?.text).toContain('truncated at 300 bytes')
+    const total = result.logs.reduce((sum, entry) => sum + Buffer.byteLength(entry.text, 'utf8'), 0)
+    expect(total).toBeLessThan(1_000)
+  })
+
+  it('caps an oversized return value with a truncation marker', async () => {
+    const { runtime } = await setup({ maxValueBytes: 64 })
+    const result = await runtime.run({ program: 'return "y".repeat(10_000)', bindings: [] })
+    expect(result.value).toBe(`${'y'.repeat(64)}… [truncated]`)
+  })
+
+  it('caps a multibyte return value by UTF-8 bytes, not string length', async () => {
+    // 4 code units, 12 UTF-8 bytes: a length-counting cap would let the full
+    // string cross. The worker's byte-exact capped rendering then passes the
+    // host re-cap unchanged (cap + marker is exactly the granted slack).
+    const { runtime } = await setup({ maxValueBytes: 4 })
+    const result = await runtime.run({ program: 'return "€€€€"', bindings: [] })
+    expect(result.value).toBe('€… [truncated]')
+  })
+
+  it('completes a program that awaits its write callback, capturing the chunk', async () => {
+    // Node's write(chunk[, encoding][, callback]) contract: dropping the
+    // callback would leave this promise pending until the wall ceiling and
+    // misreport a completed program as a timeout.
+    const { runtime } = await setup({ maxWallMs: 2_000 })
+    const result = await runtime.run({
+      program: 'await new Promise(resolve => process.stdout.write("flushed", resolve)); return "done"',
+      bindings: [],
+    })
+    expect(result.error).toBeUndefined()
+    expect(result.value).toBe('done')
+    expect(result.logs).toContainEqual({ source: 'stdout', text: 'flushed' })
+  })
+
+  it('caps a huge container whose bounded rendering is small (wire size, not rendering, is what counts)', async () => {
+    const { runtime } = await setup()
+    const result = await runtime.run({ program: 'return new Array(50_000).fill(7)', bindings: [] })
+    expect(result.error).toBeUndefined()
+    expect(typeof result.value).toBe('string')
+    expect(result.value).toContain('more items')
+  })
+
+  it('captures pipe writes that bypass the patched write slot as stray logs, capped by the same budget', async () => {
+    const { runtime } = await setup({ maxLogBytes: 4 })
+    const result = await runtime.run({
+      // The bootstrap patches the stream instance's own `write`; going
+      // through the prototype's slot reaches the real pipe underneath, so
+      // the bytes arrive host-side as stray data. The pauses keep the two
+      // writes in separate pipe chunks and let them land before settlement.
+      program: `
+        const write = (text) => Object.getPrototypeOf(process.stdout).write.call(process.stdout, text);
+        write('abcd');
+        await new Promise(resolve => setTimeout(resolve, 150));
+        write('ef');
+        await new Promise(resolve => setTimeout(resolve, 100));
+        return 1;
+      `,
+      bindings: [],
+    })
+    expect(result.error).toBeUndefined()
+    expect(result.logs).toContainEqual({ source: 'stdout', text: 'abcd' })
+    expect(result.logs.map(entry => entry.text)).not.toContain('ef')
+  }, 15_000)
+})
+
+describe('WorkerCodeRuntime — hostile programs (real workers)', () => {
+  it('survives forged port traffic: unknown binding names, duplicate ids, junk shapes', async () => {
+    const { runtime } = await setup()
+    const result = await runtime.run({
+      program: `
+        const { parentPort } = await import('node:worker_threads');
+        parentPort.postMessage({ type: 'call', id: 7777, global: 'tools', name: 'missing', args: {} });
+        parentPort.postMessage({ type: 'call', id: 7777, global: 'tools', name: 'missing', args: {} });
+        parentPort.postMessage({ type: 'call', id: 7778, global: 'tools', name: 'constructor', args: {} });
+        parentPort.postMessage({ type: 'junk' });
+        return await tools.real({});
+      `,
+      bindings: tools({ real: async () => 'still-works' }),
+    })
+    expect(result.error).toBeUndefined()
+    expect(result.value).toBe('still-works')
+  })
+
+  it('survives arbitrary junk on the port: non-objects, junk types, malformed calls, logs, and dones', async () => {
+    const { runtime } = await setup()
+    const result = await runtime.run({
+      program: `
+        const { parentPort } = await import('node:worker_threads');
+        for (const junk of [
+          null, 42, 'junk', [],
+          { type: 'nope' },
+          { type: 'call' },
+          { type: 'call', id: 'x', global: 'tools', name: 'real', args: {} },
+          { type: 'call', id: 1e9, global: 7, name: 'real', args: {} },
+          { type: 'call', id: 1e9, global: 'tools', name: 7, args: {} },
+          { type: 'log' },
+          { type: 'log', entry: null },
+          { type: 'log', entry: { source: 'stdout', text: 7 } },
+          { type: 'log', entry: { source: 'nope', text: 'x' } },
+          { type: 'log', entry: { source: 'console', level: 'nope', text: 'x' } },
+          { type: 'log', entry: { source: 'console', level: 7, text: 'x' } },
+          { type: 'done', error: 5 },
+          { type: 'done', error: { message: 5 } },
+        ]) parentPort.postMessage(junk);
+        return await tools.real({});
+      `,
+      bindings: tools({ real: async () => 'still-works' }),
+    })
+    expect(result.error).toBeUndefined()
+    expect(result.value).toBe('still-works')
+    expect(result.logs).toEqual([])
+  })
+
+  it('caps forged log floods and forged done values at the configured budgets, dropping forged extra fields', async () => {
+    const { runtime } = await setup({ maxLogBytes: 200, maxValueBytes: 64 })
+    const result = await runtime.run({
+      // Forged messages bypass the worker-side LogBuffer and prepareValue
+      // entirely — only the host-side ledger and re-cap stand between model
+      // code and an unbounded result.
+      program: `
+        const { parentPort } = await import('node:worker_threads');
+        for (let i = 0; i < 50; i++) parentPort.postMessage({ type: 'log', entry: { source: 'stdout', text: 'F'.repeat(100), forged: true } });
+        parentPort.postMessage({ type: 'done', value: 'V'.repeat(100000) });
+        for (;;) {}
+      `,
+      bindings: [],
+    })
+    expect(typeof result.value).toBe('string')
+    const value = result.value as string
+    expect(value.startsWith('V'.repeat(64))).toBe(true)
+    expect(value.endsWith('… [truncated]')).toBe(true)
+    expect(value.length).toBeLessThan(120)
+    const marker = '[dsh-code-runtime-worker] log capture truncated at 200 bytes'
+    const total = result.logs.reduce((sum, entry) => sum + Buffer.byteLength(entry.text, 'utf8'), 0)
+    expect(total).toBeLessThanOrEqual(200 + Buffer.byteLength(marker, 'utf8'))
+    expect(result.logs.at(-1)?.text).toBe(marker)
+    expect(result.logs.every(entry => !('forged' in entry))).toBe(true)
+  })
+
+  it('accepts a forged done carrying both value and error (self-sabotage, contained)', async () => {
+    const { runtime } = await setup()
+    const result = await runtime.run({
+      program: `
+        const { parentPort } = await import('node:worker_threads');
+        parentPort.postMessage({ type: 'done', value: 'lied', error: { message: 'fake failure' } });
+        for (;;) {}
+      `,
+      bindings: [],
+    })
+    expect(result.value).toBe('lied')
+    expect(result.error).toEqual({ kind: 'exception', message: 'fake failure' })
+  })
+
+  it('byte-bounds forged multibyte error text at the host', async () => {
+    // Forged error text bypasses the worker entirely; the host bound is a
+    // BYTE bound (two € = 6 bytes fit an 8-byte cap, a third would not).
+    const { runtime } = await setup({ maxValueBytes: 8 })
+    const result = await runtime.run({
+      program: `
+        const { parentPort } = await import('node:worker_threads');
+        parentPort.postMessage({ type: 'done', error: { message: '€'.repeat(1000) } });
+        for (;;) {}
+      `,
+      bindings: [],
+    })
+    expect(result.error).toEqual({ kind: 'exception', message: '€€' })
+  })
+
+  it('answers a binding whose resolution cannot be cloned with a failure reply', async () => {
+    const { runtime } = await setup()
+    const result = await runtime.run({
+      program: 'try { await tools.bad({}) } catch (error) { return error.message }',
+      bindings: tools({ bad: async () => (() => 1) }),
+    })
+    expect(result.value).toContain('not structured-cloneable')
+  })
+
+  it('exposes binding names that collide with Object.prototype as ordinary functions', async () => {
+    const { runtime } = await setup()
+    const result = await runtime.run({
+      program: 'return [await tools["__proto__"]({}), await tools["constructor"]({}), typeof tools["hasOwnProperty"]]',
+      // Computed keys: a literal `'__proto__': …` entry would SET the record's
+      // prototype instead of declaring a binding of that name.
+      bindings: tools({ ['__proto__']: async () => 'proto-ok', ['constructor']: async () => 'ctor-ok' }),
+    })
+    expect(result.value).toEqual(['proto-ok', 'ctor-ok', 'undefined'])
+  })
+})
+
+describe('WorkerCodeRuntime — seam misuse and lifecycle', () => {
+  it('rejects invalid binding globals loudly (identifier, reserved word, duplicate, console)', async () => {
+    const { runtime } = await setup()
+    const cases: [string, RegExp][] = [
+      ['not valid!', /not a usable identifier/],
+      ['await', /not a usable identifier/],
+      ['console', /duplicate binding global/],
+    ]
+    for (const [global, message] of cases) {
+      await expect(runtime.run({ program: 'return 1', bindings: [{ global, functions: {} }] })).rejects.toThrow(message)
+    }
+    await expect(runtime.run({
+      program: 'return 1',
+      bindings: [{ global: 'tools', functions: {} }, { global: 'tools', functions: {} }],
+    })).rejects.toThrow(/duplicate binding global/)
+  })
+
+  it('rejects config values that are not positive numbers', async () => {
+    const ctx = new Context()
+    await expect(ctx.plugin(WorkerCodeRuntime, { computeMs: -1 })).rejects.toThrow(/positive number/)
+  })
+
+  it('keeps runs isolated: no state survives from one run to the next', async () => {
+    const { runtime } = await setup()
+    await runtime.run({ program: 'globalThis.leak = "value"; return 1', bindings: [] })
+    const second = await runtime.run({ program: 'return typeof globalThis.leak', bindings: [] })
+    expect(second.value).toBe('undefined')
+  })
+
+  it('disposal aborts in-flight runs, awaits worker exit, and rejects later runs', async () => {
+    const ctx = new Context()
+    const fiber = await ctx.plugin(WorkerCodeRuntime)
+    const runtime = ctx.codeRuntime as WorkerCodeRuntime
+    const inflight: Promise<CodeRunResult> = runtime.run({ program: 'for (;;) {}', bindings: [] })
+    // Give the worker a moment to actually start spinning.
+    await new Promise(resolve => setTimeout(resolve, 200))
+    await fiber.dispose()
+    const result = await inflight
+    expect(result.error).toEqual({ kind: 'abort', message: 'runtime disposed' })
+    await expect(runtime.run({ program: 'return 1', bindings: [] })).rejects.toThrow(/after disposal/)
+  }, 15_000)
+
+  it('removes ctx.codeRuntime when the providing fiber disposes (HMR safety)', async () => {
+    const ctx = new Context()
+    const fiber = await ctx.plugin(WorkerCodeRuntime)
+    expect(ctx.get('codeRuntime')).toBeInstanceOf(WorkerCodeRuntime)
+    await fiber.dispose()
+    expect(ctx.get('codeRuntime')).toBeUndefined()
+  })
+})

packages/code-runtime/code-runtime-worker/tsconfig.json

@@ -0,0 +1,24 @@
+{
+  "extends": "../../../tsconfig.base.json",
+  "compilerOptions": {
+    "rootDir": "src",
+    "outDir": "lib/types"
+  },
+  "include": [
+    "src"
+  ],
+  "references": [
+    {
+      "path": "../../../vendor/cosmokit"
+    },
+    {
+      "path": "../../../vendor/cordis"
+    },
+    {
+      "path": "../../../vendor/schemastery"
+    },
+    {
+      "path": "../code-runtime"
+    }
+  ]
+}

packages/code-runtime/code-runtime-worker/tsdown.config.ts

@@ -0,0 +1,35 @@
+import { defineConfig } from 'tsdown'
+
+/**
+ * Package-shape override (see the root tsdown.config.ts): besides the
+ * default lib/index.js bundle, the worker BOOTSTRAP ships as its own
+ * sibling entry — `new Worker(new URL('./worker.js', import.meta.url))`
+ * loads it as a file, so it cannot be part of the index bundle. TWO
+ * single-entry builds, not one two-entry build: a multi-entry build emits
+ * the shared bootstrap module as a `lib/bootstrap-*.js` chunk both bundles
+ * import, which the package.json `files` whitelist (deliberately exact)
+ * would omit from the packed artifact — each single-entry build inlines its
+ * own bootstrap copy instead, keeping every shipped file self-contained.
+ */
+export default defineConfig([
+  {
+    entry: ['lib/types/index.js'],
+    outDir: 'lib',
+    format: ['esm'],
+    platform: 'node',
+    target: 'es2024',
+    fixedExtension: false,
+    dts: false,
+    clean: false,
+  },
+  {
+    entry: ['lib/types/worker.js'],
+    outDir: 'lib',
+    format: ['esm'],
+    platform: 'node',
+    target: 'es2024',
+    fixedExtension: false,
+    dts: false,
+    clean: false,
+  },
+])

packages/code-runtime/code-runtime/README.md

@@ -0,0 +1,19 @@
+# @deepseek-ai/dsh-code-runtime
+
+The **code-execution seam**: an abstract `CodeRuntime` service (`ctx.codeRuntime`) defining WHAT a code runtime does — run one model-written program against a set of host-provided async bindings and report `{ value, logs, error? }` — without saying HOW.
+
+This package is the interface third of the capability (the bash trio is the template — see [capability seams](../../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md)): implementations subclass `CodeRuntime` and register the service; the consumer is the tool registry's Code Mode, which generates the model-facing SDK and bridges tool dispatch — both specified in the [Code Mode RFC](../../../docs/rfc/proposed/feature/2026-06-15-code-mode.md), whose first implementation is a Node worker-thread backend. The runtime knows nothing about tools or sessions: it is handed named async functions and a program string, and everything tool-shaped stays with the consumer.
+
+## Service API (`ctx.codeRuntime`)
+
+| Member | Semantics |
+|---|---|
+| `run(request)` | Execute one program against the request's bindings. **Resolves with an error FIELD for every program outcome** — parse/transform failure, thrown exception, budget expiry, abort, substrate death (`CodeRunFailure`'s orthogonal `kind` taxonomy); it rejects only for caller misuse of the seam itself (e.g. a run submitted after disposal). The program runs as the body of an async function: top-level `await`/`return` work, and the completion value becomes `result.value` when it survives the serialization boundary. |
+| `language` | Readonly descriptor: the source language `run` expects (`'typescript'` is the well-known value). Informational, not gating — a consumer that generates language-specific presentation switches on it and fails loud on a language it cannot present. |
+| `isolation` | Readonly descriptor: the execution substrate (`'worker-thread'`, `'process'`, `'container'`). A label for deployments and diagnostics, **not a security claim**. |
+
+Semantics every implementation must honor (contract details in the class JSDoc): binding calls bridge to the caller's functions verbatim with structured-cloneable arguments/resolutions; the program is treated as a hostile peer (arbitrary binding names are own properties, malformed traffic never crashes the host); no state survives between runs; disposal terminates in-flight runs AND awaits their exit before completing.
+
+## Vocabulary
+
+`CodeRunRequest` (`program`, `bindings`, `signal?`) carries everything the runtime acts on — defaulting (time budgets, output caps) is the implementation's validated config, never a hidden `??` inside `run()`. `bindings` is a list of `CodeBindingNamespace`s (`global` + `functions`), each exposed to the program as one global object of async callables. `CodeRunResult` reports the completion `value?`, the ordered `logs` (`CodeLogEntry`: `console`/`stdout`/`stderr` source, console `level`, capped text), and the `error?` (`CodeRunFailure`: `kind` + model-feedable `message`). See `src/types.ts` for the full contracts.

packages/code-runtime/code-runtime/package.json

@@ -0,0 +1,30 @@
+{
+  "name": "@deepseek-ai/dsh-code-runtime",
+  "description": "Abstract code-execution seam (ctx.codeRuntime) for the DeepSeek Harness",
+  "version": "0.0.1",
+  "private": true,
+  "type": "module",
+  "main": "lib/index.js",
+  "types": "lib/types/index.d.ts",
+  "exports": {
+    ".": {
+      "types": "./lib/types/index.d.ts",
+      "default": "./lib/index.js"
+    },
+    "./src/*": "./src/*",
+    "./package.json": "./package.json"
+  },
+  "files": [
+    "lib/index.js",
+    "lib/types/**/*.d.ts",
+    "lib/types/**/*.d.ts.map",
+    "src"
+  ],
+  "license": "BSD-3-Clause",
+  "peerDependencies": {
+    "cordis": "^4.0.0-rc.6"
+  },
+  "devDependencies": {
+    "cordis": "^4.0.0-rc.6"
+  }
+}

packages/code-runtime/code-runtime/src/index.ts

@@ -0,0 +1,93 @@
+/**
+ * The code-execution seam (`ctx.codeRuntime`): an abstract service defining
+ * WHAT a code runtime does — run one model-written program against a set of
+ * host-provided async bindings and report `{ value, logs, error? }` — without
+ * saying HOW. Implementations subclass {@link CodeRuntime} and register
+ * themselves as the `codeRuntime` service; backends may differ by execution
+ * substrate (worker thread, separate process, container) and by source
+ * language, both declared as readonly descriptors. The design and its
+ * consumer (the tool registry's Code Mode) are specified in the Code Mode RFC
+ * (docs/rfc/proposed/feature/2026-06-15-code-mode.md).
+ *
+ * The split mirrors the bash seam (`BashExecutor`): the runtime knows nothing
+ * about tools or sessions — it is handed named async functions and a program,
+ * and everything tool-shaped stays with the consumer.
+ *
+ * @module @deepseek-ai/dsh-code-runtime
+ */
+
+import { Context, Service } from 'cordis'
+import type { CodeRunRequest, CodeRunResult } from './types.ts'
+
+export type {
+  CodeBindingFunction,
+  CodeBindingNamespace,
+  CodeLogEntry,
+  CodeRunFailure,
+  CodeRunRequest,
+  CodeRunResult,
+} from './types.ts'
+
+declare module 'cordis' {
+  interface Context {
+    codeRuntime: CodeRuntime
+  }
+}
+
+/**
+ * Abstract code-execution service. Subclass, implement {@link run} and the
+ * two descriptors, and load the subclass as a plugin — it registers as
+ * `ctx.codeRuntime` (one implementation per context; loading a second throws,
+ * cordis' standard duplicate-service behavior).
+ *
+ * Semantics every implementation must honor:
+ * - {@link run} resolves with an error FIELD for every program outcome —
+ *   parse/transform failures, thrown exceptions, budget expiry, abort,
+ *   substrate death ({@link CodeRunFailure}'s taxonomy). It REJECTS only for
+ *   caller misuse of the seam itself (e.g. a run submitted after disposal).
+ * - Binding calls bridge to the caller's {@link CodeBindingFunction}s
+ *   verbatim; arguments and resolutions must be structured-cloneable, and the
+ *   runtime treats the program as a hostile peer (arbitrary binding names are
+ *   own properties, malformed traffic is rejected or ignored, never crashes
+ *   the host).
+ * - Runs are isolated from each other: no state survives from one run to the
+ *   next through the runtime.
+ * - Disposal reaches quiescence: in-flight runs are terminated AND awaited
+ *   before the service's own teardown completes (no orphan substrate survives
+ *   `fiber.dispose()`).
+ */
+export abstract class CodeRuntime extends Service {
+  /**
+   * The source language {@link run} expects `program` to be written in, as a
+   * lowercase identifier. Informational, not gating — a consumer that
+   * generates language-specific presentation (typed SDK stubs, usage
+   * instructions) switches on it and fails loud on a language it cannot
+   * present. Well-known value: `'typescript'`.
+   */
+  abstract readonly language: string
+
+  /**
+   * The execution substrate, as a lowercase identifier. Informational, not
+   * gating — a descriptor so deployments and diagnostics can tell backends
+   * apart, not a security claim. Well-known values: `'worker-thread'`,
+   * `'process'`, `'container'`.
+   */
+  abstract readonly isolation: string
+
+  constructor(ctx: Context) {
+    super(ctx, 'codeRuntime')
+  }
+
+  /**
+   * Execute one program against the request's bindings and capture what it
+   * emitted. See the class doc for the resolution contract (error is a result
+   * field; rejection means seam misuse only).
+   * @param request - the program, its bindings, and the abort signal; the
+   *   request carries everything the runtime acts on, with no hidden defaults.
+   * @returns the run's outcome: completion value (when transferable), the
+   *   ordered log capture, and the failure (if any).
+   */
+  abstract run(request: CodeRunRequest): Promise<CodeRunResult>
+}
+
+export default CodeRuntime

packages/code-runtime/code-runtime/src/types.ts

@@ -0,0 +1,105 @@
+/**
+ * Vocabulary types for the code-execution seam: what a caller hands a
+ * {@link ../index.ts | CodeRuntime} and what it gets back. Pure types — no
+ * runtime code lives here.
+ *
+ * @module @deepseek-ai/dsh-code-runtime/src/types
+ */
+
+/**
+ * One host-side function exposed to the program as an async callable. The
+ * runtime bridges calls to it (possibly across a serialization boundary), so
+ * `args` and the resolution value MUST be structured-cloneable; a runtime
+ * rejects a non-cloneable value with a descriptive error rather than
+ * corrupting the run. A rejection of this function surfaces inside the
+ * program as a rejection of the corresponding call.
+ */
+export type CodeBindingFunction = (args: unknown) => Promise<unknown>
+
+/**
+ * A named group of {@link CodeBindingFunction}s the runtime exposes to the
+ * program as one global object (e.g. `tools`). Function names are arbitrary
+ * strings — a runtime must treat names like `__proto__` or `constructor` as
+ * ordinary own properties (null-prototype construction), never as prototype
+ * collisions.
+ */
+export interface CodeBindingNamespace {
+  /** The global identifier the program sees (must be a valid JS identifier). */
+  global: string
+  /** The callable members, keyed by the exact name the program calls. */
+  functions: Record<string, CodeBindingFunction>
+}
+
+/**
+ * One run: the program source plus everything the runtime acts on. Per the
+ * explicit-over-implicit convention, defaulting (time budgets, output caps)
+ * is the implementation's validated config — a request carries no optional
+ * tuning knobs for a hidden `??` to fill in.
+ */
+export interface CodeRunRequest {
+  /**
+   * The program source, in the runtime's {@link ../index.ts | language}. It
+   * runs as the body of an async function: top-level `await` and `return`
+   * are available, and the completion value becomes
+   * {@link CodeRunResult.value}.
+   */
+  program: string
+  /** Host functions exposed to the program, one global object per namespace. */
+  bindings: CodeBindingNamespace[]
+  /**
+   * Abort the run: the runtime stops the program (hard, even mid-loop) and
+   * resolves with a {@link CodeRunFailure} of kind `'abort'`. In-flight
+   * binding calls are the CALLER's to settle — the runtime only stops asking.
+   */
+  signal?: AbortSignal
+}
+
+/**
+ * One captured output entry, in emission order. `source` says which channel
+ * produced it: the program's `console` (shimmed by the runtime), or a stray
+ * write to the underlying stdout/stderr streams.
+ */
+export interface CodeLogEntry {
+  /** Which channel produced the text. */
+  source: 'console' | 'stdout' | 'stderr'
+  /** The console method used; present only when `source` is `'console'`. */
+  level?: 'log' | 'info' | 'warn' | 'error' | 'debug'
+  /** The captured text (possibly truncated by the implementation's caps, marked in-band). */
+  text: string
+}
+
+/**
+ * Why a run failed. The kinds are orthogonal outcomes reported independently
+ * (per docs/defensive-patterns.md): a budget expiry is not an exception, an
+ * abort is not a timeout, and a substrate death is neither.
+ *
+ * - `'exception'` — the program threw or failed to parse/transform.
+ * - `'timeout'` — an implementation-owned budget expired; the message says which.
+ * - `'abort'` — {@link CodeRunRequest.signal} fired.
+ * - `'worker-exit'` — the execution substrate died without settling (e.g. OOM).
+ */
+export interface CodeRunFailure {
+  /** The failure class (see the interface doc for each kind's meaning). */
+  kind: 'exception' | 'timeout' | 'abort' | 'worker-exit'
+  /** Human-readable detail, suitable for feeding back to a model to self-correct. */
+  message: string
+}
+
+/**
+ * The outcome of one run. An error is a FIELD on a resolved result, never a
+ * rejection of `run()` — reporting a failed program is the caller's job, not
+ * an exception path.
+ */
+export interface CodeRunResult {
+  /**
+   * The program's completion value (its top-level `return`), when it ran to
+   * completion and the value survived the runtime's serialization boundary;
+   * a non-transferable value is replaced by a string rendering, and a failed
+   * or value-less run leaves this absent.
+   */
+  value?: unknown
+  /** Everything the program emitted, in order (capped by the implementation). */
+  logs: CodeLogEntry[]
+  /** Present iff the run failed; see {@link CodeRunFailure} for the taxonomy. */
+  error?: CodeRunFailure
+}

packages/code-runtime/code-runtime/tests/service.spec.ts

@@ -0,0 +1,87 @@
+import { describe, expect, it } from 'vitest'
+import { Context } from 'cordis'
+import { CodeRuntime } from '@deepseek-ai/dsh-code-runtime'
+import type { CodeRunRequest, CodeRunResult } from '@deepseek-ai/dsh-code-runtime'
+
+/**
+ * Minimal concrete runtime: records requests, "executes" by invoking every
+ * binding once in declaration order, and lets tests script the outcome. The
+ * seam package ships no implementation, so the contract is exercised through
+ * the smallest subclass that honors it.
+ */
+class StubRuntime extends CodeRuntime {
+  readonly language = 'typescript'
+  readonly isolation = 'in-process-stub'
+  requests: CodeRunRequest[] = []
+  nextResult: CodeRunResult = { logs: [] }
+
+  async run(request: CodeRunRequest): Promise<CodeRunResult> {
+    this.requests.push(request)
+    if (request.signal?.aborted) {
+      return { logs: [], error: { kind: 'abort', message: String(request.signal.reason) } }
+    }
+    for (const namespace of request.bindings) {
+      for (const fn of Object.values(namespace.functions)) {
+        await fn({ from: 'stub' })
+      }
+    }
+    return this.nextResult
+  }
+}
+
+async function setup() {
+  const ctx = new Context()
+  await ctx.plugin(StubRuntime)
+  const runtime = ctx.codeRuntime as StubRuntime
+  return { ctx, runtime }
+}
+
+describe('CodeRuntime service seam', () => {
+  it('registers as ctx.codeRuntime and serves the abstract API', async () => {
+    const { runtime } = await setup()
+    expect(runtime.language).toBe('typescript')
+    expect(runtime.isolation).toBe('in-process-stub')
+
+    const calls: unknown[] = []
+    const result = await runtime.run({
+      program: 'return 1',
+      bindings: [{ global: 'tools', functions: { probe: async args => void calls.push(args) } }],
+    })
+    expect(result).toEqual({ logs: [] })
+    expect(calls).toEqual([{ from: 'stub' }])
+    expect(runtime.requests).toHaveLength(1)
+  })
+
+  it('reports a failed run as an error field on a resolved result, never a rejection', async () => {
+    const { runtime } = await setup()
+    runtime.nextResult = {
+      logs: [{ source: 'console', level: 'error', text: 'boom' }],
+      error: { kind: 'exception', message: 'boom' },
+    }
+    const result = await runtime.run({ program: 'throw new Error("boom")', bindings: [] })
+    expect(result.error).toEqual({ kind: 'exception', message: 'boom' })
+    expect(result.value).toBeUndefined()
+  })
+
+  it('reports a pre-aborted signal as an abort failure', async () => {
+    const { runtime } = await setup()
+    const controller = new AbortController()
+    controller.abort('cancelled')
+    const result = await runtime.run({ program: 'return 1', bindings: [], signal: controller.signal })
+    expect(result.error).toEqual({ kind: 'abort', message: 'cancelled' })
+  })
+
+  it('is removed from the context when the providing fiber disposes (HMR safety)', async () => {
+    const ctx = new Context()
+    const fiber = await ctx.plugin(StubRuntime)
+    expect(ctx.get('codeRuntime')).toBeInstanceOf(StubRuntime)
+
+    await fiber.dispose()
+    expect(ctx.get('codeRuntime')).toBeUndefined()
+  })
+
+  it('rejects a second implementation in the same context (duplicate service)', async () => {
+    const { ctx } = await setup()
+    await expect(ctx.plugin(StubRuntime)).rejects.toThrow(/registered/)
+  })
+})

packages/code-runtime/code-runtime/tsconfig.json

@@ -0,0 +1,18 @@
+{
+  "extends": "../../../tsconfig.base.json",
+  "compilerOptions": {
+    "rootDir": "src",
+    "outDir": "lib/types"
+  },
+  "include": [
+    "src"
+  ],
+  "references": [
+    {
+      "path": "../../../vendor/cosmokit"
+    },
+    {
+      "path": "../../../vendor/cordis"
+    }
+  ]
+}

packages/compact/compact-basic/README.md

@@ -8,7 +8,7 @@ This is the implementation tier of the compaction capability — see the [interf
 
 The abstract contract states only WHAT compaction does; this backend owns every HOW decision:
 
-- **Token estimation** — `estimateContentTokens()`: chars divided by the `charsPerToken` config (default 4) with per-block structural overhead (`text`/`reasoning` = `ceil(len/charsPerToken) + 4`, `tool-call` from name + arguments, `tool-result` recursive, unknown blocks via JSON length).
+- **Token estimation** — `estimateContentTokens()`: chars divided by the `charsPerToken` config (default 4) with per-block structural overhead (`text`/`reasoning` = `ceil(len/charsPerToken) + 4`, `tool-call` from name + arguments, `tool-result` recursive, unknown blocks via JSON length). The pressure gate estimates the NEXT request via `estimatePressure()`: the session prefix (the `agent/session-prefix` product — composed by the loop BEFORE the pre-step seam and handed through it, so the gate counts the prefix this instance will actually send in front of the history, never a stale logged one) + the derived history + the system prompt.
 - **Retention policy** — `compactIfNeeded()` walks the surface nodes tail→head summing per-node token estimates, and retains the smallest tail-run of WHOLE units (a closed step, or a single no-step node such as a pre-step `user/message` or inter-step `steering/message`) whose total reaches `retainTokens`; everything older is compacted. Retention is **turn-agnostic** — turn boundaries play no role, so a single runaway turn that alone exceeds the window compacts its OWN early closed steps rather than being retained verbatim (the failure mode that motivated dropping turn-protection: a tool-heavy turn must stay compactable or the harness dies exactly when compaction is needed). The only structural guard is **tool-pairing balance**: the compacted region's edges are balanced cuts on the surface (no unanswered tool-call crosses either edge), so it never splits a step's `assistant/message` tool-calls from their `tool/result`s. When the only compactable content left is an un-splittable open tail step, it declines (returns `null`) and retries once an older step closes. **Single-unit overflow is out of scope, by design**: if one retained unit (a single closed step, or a large pasted `user/message`) ALONE exceeds the budget, compaction cannot help and the call may go out over-budget — bounding an individual unit's size is a separate concern. `compactRegion()` enforces tool-pairing balance strictly, throwing on a boundary that would split a step. `dsh-session` exports `isToolPairingBalanced` for the check.
 - **Dynamic convergence** — no static summary-length config pretends to bound what the model will write. If framing/estimator/system overhead leaves the compacted surface above threshold, `compactIfNeeded()` re-compacts the head checkpoint up to `compactionRetries` extra times; if it still cannot get below threshold, it throws. A summary whose estimated stored size is not smaller than the shadowed content fails closed before it mutates the surface.
 - **Summarization** — `summarize()`: a `GenerateOptions` request assembled via `BlockAssembler` with a fixed system prompt that asks for a structured checkpoint (Primary Request and Intent · Key Technical Concepts · Files and Code · Errors and Fixes · Pending Tasks · Current Work · Next Step · Critical Context), every section mandatory, exact paths/commands/identifiers preserved. The request is a direct one-shot `ctx.llm.stream()` call — NOT a loop step, so it does not run `agent/request` (that seam shapes the loop's conversation requests); the model comes from `summarizationModel` falling back to the agent's own, and per-call routing happens at `llm/stream` like any other direct call. `maxTokens` is the provider-side generation cap; only text blocks from the model's reply are kept before the checkpoint is stored (reasoning is dropped so private chain-of-thought never leaks into the durable summary, and a stray `tool-call` is dropped so the synthesized `user/message` summary cannot land an orphaned call with no matching `tool-result`). The compacted region is flattened to a plain-text transcript first: text and reasoning contribute their text, and every non-text block (tool-call, tool-result, plugin-added types) contributes a type-tagged placeholder (`[tool-call: name(args)]`, `[tool-result: …]`, …) so the summarizer is told what existed rather than silently dropping it.

packages/compact/compact-basic/src/index.ts

@@ -30,7 +30,7 @@
  */
 
 import { Context } from 'cordis'
-import { CompactService } from '@deepseek-ai/dsh-compact'
+import { CompactService, renderTranscript } from '@deepseek-ai/dsh-compact'
 import type { CompactionResult } from '@deepseek-ai/dsh-compact'
 import { BlockAssembler } from '@deepseek-ai/dsh-llm'
 import type { ContentBlock, FinishReason, GenerateOptions, Message } from '@deepseek-ai/dsh-llm'
@@ -183,11 +183,11 @@ export class BasicCompactService extends CompactService {
       // log-only `compact/*` records and the replacement node cleanly outside a
       // step, so a crash mid-compaction leaves an inert orphan the turn-repair
       // closes — never a half-open step.
-      ctx.on('agent/pre-step', async (agent: Agent, _turn: number, _step: number, fullSystemPrompt: string, signal: AbortSignal) => {
+      ctx.on('agent/pre-step', async (agent: Agent, _turn: number, _step: number, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal) => {
         try {
-          const result = await this.compactIfNeeded(agent, fullSystemPrompt, signal)
+          const result = await this.compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal)
           if (result) {
-            const after = this.estimateTokens(agent.session.deriveMessages(), fullSystemPrompt)
+            const after = this.estimatePressure(agent.session, fullSystemPrompt, sessionPrefix)
             ctx.logger.info(
               `compaction: shadowed ${result.shadowedSeqs.length} surface nodes ` +
               `(seqs ${result.shadowedRange.start}-${result.shadowedRange.end}, ` +
@@ -216,6 +216,11 @@ export class BasicCompactService extends CompactService {
    * Estimate the token count of content blocks — chars divided by the
    * `charsPerToken` config, with per-block overhead. Override in a subclass to
    * plug in a real tokenizer.
+   *
+   * @param blocks - the blocks to estimate; `tool-result` blocks recurse into
+   *   their nested content, and unknown (merge-extended) types fall back to
+   *   their JSON-stringified length.
+   * @returns the estimated token count.
    */
   estimateContentTokens(blocks: readonly ContentBlock[]): number {
     const { charsPerToken } = this.config
@@ -246,6 +251,11 @@ export class BasicCompactService extends CompactService {
   /**
    * Estimate token count for a single session event. Returns 0 for non-message
    * event types (boundaries, chunks, usage, errors, compact markers).
+   *
+   * @param event - any session event; only the message-bearing types carry
+   *   content to count.
+   * @returns the estimated token count of the event's content, or 0 for a
+   *   non-message event.
    */
   estimateEventTokens(event: SessionEvent): number {
     switch (event.type) {
@@ -260,7 +270,14 @@ export class BasicCompactService extends CompactService {
     }
   }
 
-  /** Estimate total tokens across a list of messages plus optional system prompt. */
+  /**
+   * Estimate total tokens across a list of messages plus optional system prompt.
+   *
+   * @param messages - the derived conversation messages; each adds a fixed
+   *   role-framing overhead on top of its content estimate.
+   * @param systemPrompt - counted at chars / `charsPerToken` when provided.
+   * @returns the estimated token footprint of the whole request.
+   */
   estimateTokens(messages: readonly Message[], systemPrompt?: string): number {
     let total = 0
     for (const msg of messages) {
@@ -293,6 +310,13 @@ export class BasicCompactService extends CompactService {
    * used (`model`, `maxTokens`) — the caller logs the envelope on the
    * `compact/summary` provenance event, so an overriding subclass (template
    * or remote summarizer) reports its own envelope honestly.
+   *
+   * @param text - plain-text rendering of the conversation region to condense.
+   * @param agent - supplies the fallback model and the session id stamped on
+   *   the call; throws when neither it nor the config names a model.
+   * @param signal - optional abort signal, forwarded into the model call.
+   * @returns the text-only summary blocks plus the call envelope used
+   *   (`model`, and `maxTokens` when the summarizer has a cap).
    */
   async summarize(
     text: string, agent: Agent, signal?: AbortSignal,
@@ -335,11 +359,23 @@ export class BasicCompactService extends CompactService {
   // ---- Core API (implements the abstract contract) ----
 
   /**
-   * The sole token-pressure gate: estimate the current surface-derived history,
-   * and if it exceeds the threshold (`contextWindow * thresholdRatio`), compact
+   * The sole token-pressure gate: estimate the NEXT request's pressure — the
+   * session prefix + the surface-derived history + the system prompt
+   * ({@link estimatePressure}) — and if it exceeds the threshold
+   * (`contextWindow * thresholdRatio`), compact
    * the oldest surface nodes outside the `retainTokens` budget. The auto-
    * compaction listener delegates here rather than pre-checking, so this is the
-   * only place the decision lives.
+   * only place the decision lives. The prefix counts because every request
+   * carries it in front of the history (`EpochHeader.messagePrefix`) even
+   * though it is not derived history — omitting it would under-estimate by
+   * exactly the prefix and let a deployment at the window edge skip
+   * compaction, then ship an over-window request. The loop composes the
+   * prefix BEFORE the pre-step seam and hands it through, so the gate sees
+   * this instance's actual prefix (never a previous instance's logged one —
+   * a resumed/forked instance whose contributor grew is gated on the grown
+   * value from its very first step). Compaction itself can only
+   * shrink HISTORY: a prefix that alone approaches the window is a
+   * configuration error no compactor fixes.
    *
    * Retention is a UNIFORM tail→head walk over the whole surface — turn
    * boundaries play NO role. Walking node-by-node from the tail and summing
@@ -363,13 +399,14 @@ export class BasicCompactService extends CompactService {
   override async compactIfNeeded(
     agent: Agent,
     fullSystemPrompt: string,
+    sessionPrefix: readonly Message[],
     signal: AbortSignal,
   ): Promise<CompactionResult | null> {
     const session = agent.session
     const threshold = Math.floor(this.config.contextWindow * this.config.thresholdRatio)
     let result: CompactionResult | null = null
     for (let attempt = 0; attempt <= this.config.compactionRetries; attempt++) {
-      const totalTokens = this.estimateTokens(session.deriveMessages(), fullSystemPrompt)
+      const totalTokens = this.estimatePressure(session, fullSystemPrompt, sessionPrefix)
       if (totalTokens < threshold) return result
 
       const range = this._compactableRange(session)
@@ -383,7 +420,7 @@ export class BasicCompactService extends CompactService {
       result = await this.compactRegion(session, range.start, range.end, agent, signal)
     }
 
-    const totalTokens = this.estimateTokens(session.deriveMessages(), fullSystemPrompt)
+    const totalTokens = this.estimatePressure(session, fullSystemPrompt, sessionPrefix)
     if (totalTokens < threshold) return result
 
     throw new Error(
@@ -392,6 +429,20 @@ export class BasicCompactService extends CompactService {
     )
   }
 
+  /**
+   * Estimated token pressure of the NEXT request: the session prefix
+   * (`EpochHeader.messagePrefix` — request-only messages the loop sends in
+   * front of the derived history, composed before the pre-step seam and
+   * handed to the gate), the derived history, and the system prompt.
+   * @param session - the session whose next request is being estimated.
+   * @param fullSystemPrompt - the assembled system prompt (counts toward pressure).
+   * @param sessionPrefix - the instance's composed session prefix (counts toward pressure).
+   * @returns the estimated token total the next request will carry.
+   */
+  estimatePressure(session: Session, fullSystemPrompt: string, sessionPrefix: readonly Message[]): number {
+    return this.estimateTokens([...sessionPrefix, ...session.deriveMessages()], fullSystemPrompt)
+  }
+
   override async compactRegion(
     session: Session,
     start: number,
@@ -459,7 +510,7 @@ export class BasicCompactService extends CompactService {
 
     try {
       // --- Extract text and summarize ---
-      const text = this._extractText(session, shadowedSeqs)
+      const text = renderTranscript(session.events, shadowedSeqs)
       const { summary, model, maxTokens } = await this.summarize(text, agent, signal)
 
       // Estimate token count of the shadowed content for provenance.
@@ -655,101 +706,6 @@ export class BasicCompactService extends CompactService {
     }
     return null
   }
-
-  /**
-   * Extract plain-text conversation from a set of surface node seqs, for
-   * feeding into the summarization model. Walks the seqs in the order given
-   * (surface order, as `compactRegion` slices the surface-node list) so the
-   * summary follows the conversation as the model sees it — which, after a
-   * `replace`, is NOT ascending log-seq order (a high-seq summary node heads the
-   * surface before older retained lower-seq nodes).
-   */
-  private _extractText(session: Session, seqs: number[]): string {
-    const lines: string[] = []
-
-    // Walk seqs in the order given (surface order, as compactRegion slices the
-    // surface-node list) — NOT ascending log-seq order. After a replace the
-    // summary node carries a fresh high seq while sitting at the head of the
-    // surface before older retained lower-seq nodes, so a log-order scan would
-    // feed the transcript out of order and break the checkpoint-merge prompt.
-    for (const seq of seqs) {
-      const event = session.events[seq]
-      /* v8 ignore next -- seq is a surface-node seq, always a valid log index by construction */
-      if (!event) continue
-
-      switch (event.type) {
-        case 'user/message': {
-          const text = this._blocksToText(event.data.content)
-          if (text) lines.push(`User: ${text}`)
-          break
-        }
-        case 'assistant/message': {
-          const text = this._blocksToText(event.data.content)
-          if (text) lines.push(`Assistant: ${text}`)
-          break
-        }
-        case 'tool/result': {
-          const text = this._blocksToText(event.data.content)
-          const label = event.data.isError ? 'Tool error' : 'Tool result'
-          if (text) lines.push(`${label} (call ${event.data.callId}): ${text}`)
-          break
-        }
-        case 'context/message': {
-          const text = this._blocksToText(event.data.content)
-          if (text) lines.push(`[Context: ${text}]`)
-          break
-        }
-        case 'steering/message': {
-          const text = this._blocksToText(event.data.content)
-          if (text) lines.push(`[Steering: ${text}]`)
-          break
-        }
-        // SessionEventMap is merge-extensible — unknown types are
-        // non-message events that carry no extractable text.
-        /* v8 ignore next 2 -- seqs only name surface nodes, always one of the 5 handled SurfaceEventTypes; unreachable */
-        default:
-          break
-      }
-    }
-
-    return lines.join('\n\n')
-  }
-
-  /**
-   * Render content blocks to a single plain-text string for the summarization
-   * prompt. Text and reasoning contribute their text; every other block type
-   * contributes a type-tagged placeholder (`[tool-call: name(args)]`,
-   * `[tool-result: …]`, …) so the summarizer is told what non-text content
-   * existed in the region rather than silently losing it. Blocks join with
-   * newlines; empty-text blocks contribute nothing.
-   */
-  private _blocksToText(blocks: readonly ContentBlock[]): string {
-    const parts: string[] = []
-    for (const block of blocks) {
-      switch (block.type) {
-        case 'text':
-          if (block.text) parts.push(block.text)
-          break
-        case 'reasoning':
-          if (block.text) parts.push(`[reasoning: ${block.text}]`)
-          break
-        case 'tool-call':
-          parts.push(`[tool-call: ${block.name}(${block.arguments})]`)
-          break
-        case 'tool-result': {
-          const inner = this._blocksToText(block.content)
-          parts.push(inner ? `[tool-result: ${inner}]` : '[tool-result]')
-          break
-        }
-        // ContentBlockMap is merge-extensible — render an unknown block as a
-        // bare type-tagged placeholder so a plugin-added block type is still
-        // signalled to the summarizer rather than dropped.
-        default:
-          parts.push(`[${(block as ContentBlock).type}]`)
-      }
-    }
-    return parts.join('\n')
-  }
 }
 
 export default BasicCompactService

packages/compact/compact-basic/src/types.ts

@@ -54,6 +54,9 @@ export type ResolvedConfig = Required<BasicCompactConfig>
  * each committed summary must be smaller than the content it shadows, and
  * `compactIfNeeded` may re-compact up to `compactionRetries` extra times before
  * throwing if the surface still exceeds the threshold.
+ *
+ * @param config - the raw, unresolved backend config.
+ * @returns the validated config with `auto` and `charsPerToken` defaulted.
  */
 export function resolveConfig(config: BasicCompactConfig): ResolvedConfig {
   const resolved: ResolvedConfig = { auto: true, charsPerToken: 4, ...config }

packages/compact/compact-basic/tests/compact-basic.spec.ts

@@ -557,6 +557,24 @@ describe('BasicCompactService.compactIfNeeded', () => {
     expect(result!.shadowedSeqs.length).toBeGreaterThan(0)
   })
 
+  it('counts the session prefix toward pressure (every request carries it in front of the history)', async () => {
+    const svc = createTestService({ contextWindow: 200, thresholdRatio: 0.5, retainTokens: 10 })
+    const session = multiTurnSession(3, 1) // 6 derived messages ≈ 84 estimated tokens — under the 100 threshold alone
+    expect(await compactIfNeeded(svc, session, '', 'm', SIGNAL)).toBeNull()
+
+    // The loop composes the agent/session-prefix product before the pre-step
+    // seam and hands it to the gate; it rides every request, so pressure must
+    // include it — the same history now crosses the threshold.
+    const sessionPrefix: Message[] = [
+      { role: 'user', content: [{ type: 'text', text: `opener one.${LONG_FIXTURE_TEXT}` }] },
+      { role: 'user', content: [{ type: 'text', text: `opener two.${LONG_FIXTURE_TEXT}` }] },
+    ]
+    const result = await compactIfNeeded(svc, session, '', 'm', SIGNAL, sessionPrefix)
+    expect(result).not.toBeNull()
+    // The prefix itself is NOT history: compaction shadowed surface nodes only.
+    expect(sessionPrefix).toHaveLength(2)
+  })
+
   it('returns the first compaction result when a zero-retry pass converges after the loop', async () => {
     // With compactionRetries=0 there is no next-loop threshold check after the
     // first mutation, so the success path is the post-loop `return result`.
@@ -982,8 +1000,9 @@ function compactIfNeeded(
   fullSystemPrompt: string,
   model: string,
   signal: AbortSignal,
+  sessionPrefix: readonly Message[] = [],
 ) {
-  return svc.compactIfNeeded(stubAgent(session, model), fullSystemPrompt, signal)
+  return svc.compactIfNeeded(stubAgent(session, model), fullSystemPrompt, sessionPrefix, signal)
 }
 
 function compactRegion(
@@ -1151,7 +1170,7 @@ describe('BasicCompactService.summarize (real ctx.llm.stream)', () => {
 describe('BasicCompactService auto-compaction (agent/pre-step listener)', () => {
   /** Fire the agent/pre-step serial checkpoint as the loop does. */
   function firePreStep(ctx: Context, agent: Agent, step: number, fullSystemPrompt: string): Promise<unknown> {
-    return ctx.serial('agent/pre-step', agent, 1, step, fullSystemPrompt, SIGNAL)
+    return ctx.serial('agent/pre-step', agent, 1, step, fullSystemPrompt, [], SIGNAL)
   }
 
   it('compacts (mutating the surface) when over threshold', async () => {
@@ -1253,7 +1272,7 @@ describe('BasicCompactService auto-compaction (agent/pre-step listener)', () =>
     const session = multiTurnSession(5, 1)
     const agent = stubAgent(session, 'agent-model')
 
-    await ctx.serial('agent/pre-step', agent, 1, 1, '', SIGNAL)
+    await ctx.serial('agent/pre-step', agent, 1, 1, '', [], SIGNAL)
 
     expect(adapter.lastOptions?.model).toBe('routed-model')
     expect(session.events.some(e => e.type === 'compact/summary')).toBe(true)
@@ -1278,7 +1297,7 @@ describe('BasicCompactService auto-compaction (agent/pre-step listener)', () =>
   })
 })
 
-describe('BasicCompactService._extractText branches', () => {
+describe('BasicCompactService transcript rendering (delegated to dsh-compact)', () => {
   it('renders reasoning, context, and steering messages', async () => {
     const svc = createTestService()
     const s = new Session(SessionId('rich'))
@@ -1392,7 +1411,7 @@ describe('BasicCompactService edge cases', () => {
     const session = multiTurnSession(4, 1)
     const agent = stubAgent(session, 'test-model')
 
-    await ctx.serial('agent/pre-step', agent, 1, 1, '', SIGNAL)
+    await ctx.serial('agent/pre-step', agent, 1, 1, '', [], SIGNAL)
     expect(session.events.some(e => e.type === 'compact/summary')).toBe(true)
     // The surface was mutated; the head message is the framed summary checkpoint.
     expect(session.deriveMessages()[0]!.content).toContainEqual({ type: 'text', text: 'SUMMARY' })
@@ -1472,7 +1491,7 @@ describe('BasicCompactService edge cases', () => {
     const agent = stubAgent(session, 'test-model')
     const before = session.surface.nodes.length
 
-    await ctx.serial('agent/pre-step', agent, 1, 1, '', SIGNAL)
+    await ctx.serial('agent/pre-step', agent, 1, 1, '', [], SIGNAL)
     // The failure was swallowed; the surface is untouched and a warning logged.
     expect(session.surface.nodes.length).toBe(before)
     expect(session.events.some(e => e.type === 'compact/summary')).toBe(false)
@@ -1489,7 +1508,7 @@ describe('BasicCompactService edge cases', () => {
     const agent = stubAgent(session, 'test-model')
     const bigSystem = 'x'.repeat(900) // ceil(900/4)=225 > threshold 200
 
-    await ctx.serial('agent/pre-step', agent, 1, 1, bigSystem, SIGNAL)
+    await ctx.serial('agent/pre-step', agent, 1, 1, bigSystem, [], SIGNAL)
     expect(session.events.some(e => e.type === 'compact/start')).toBe(false)
     expect(svc.summarizeCalls.length).toBe(0)
   })

packages/compact/compact/README.md

@@ -6,7 +6,7 @@ This package is the interface tier of the compaction capability, split so each c
 
 | Package | Role |
 |---|---|
-| `@deepseek-ai/dsh-compact` (this) | the interface: abstract service + `compact/*` events + `CompactionResult` |
+| `@deepseek-ai/dsh-compact` (this) | the interface: abstract service + `compact/*` events + `CompactionResult` + the shared transcript renderer (`renderTranscript`/`renderContentBlocks`) |
 | `@deepseek-ai/dsh-compact-basic` (deferred) | a backend: chars-per-token estimation (`charsPerToken`, default 4) + token-budget retention + `llm.stream()` summarization |
 | `@deepseek-ai/dsh-tool-compact` (deferred) | the model-facing `/compact` tool over `ctx.compact` |
 
@@ -18,7 +18,7 @@ Both methods are **abstract** — the backend owns the entire strategy (token es
 
 | Member | Semantics |
 |---|---|
-| `compactIfNeeded(agent, fullSystemPrompt, signal)` | Estimate the surface-derived history size; if over the backend's threshold, compact an older range via `compactRegion`, keeping recent context intact. Returns the `CompactionResult`, or `null` if nothing needed compacting. All parameters required — the loop's `agent/pre-step` checkpoint supplies the agent, assembled `fullSystemPrompt`, and turn `signal`. A backend's summarization request is a direct `ctx.llm.stream()` call (not a loop step), so per-call interception happens at `llm/stream`. |
+| `compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal)` | Estimate the surface-derived history size; if over the backend's threshold, compact an older range via `compactRegion`, keeping recent context intact. Returns the `CompactionResult`, or `null` if nothing needed compacting. All parameters required — the loop's `agent/pre-step` checkpoint supplies the agent, assembled `fullSystemPrompt`, composed `sessionPrefix` (request-only messages every request carries but the derived history omits — the pressure estimate must count them), and turn `signal`. A backend's summarization request is a direct `ctx.llm.stream()` call (not a loop step), so per-call interception happens at `llm/stream`. |
 | `compactRegion(session, start, end, agent, signal?)` | Forcibly summarize surface nodes `[start, end]` (inclusive seqs) into a single replacement node. **Throws** if a compaction is already in progress, if `start`/`end` aren't surface nodes, or if `start` is positioned after `end` on the surface. The range is a SURFACE-POSITION span, not a numeric seq interval — after a prior replace lands a fresh high-seq summary node at the shadowed range's position, surface order no longer tracks seq order. |
 
 `compactIfNeeded` takes a required `signal`; `compactRegion`'s is optional. A backend that summarizes via `ctx.llm.stream()` **must** forward it into the call's `GenerateOptions.signal`, so an abort or fiber dispose tears down the in-flight summarization instead of leaving an orphaned model call running past the cancellation. The session being compacted comes from the agent context; the turn that the `compact/*` events belong to is recoverable from the log (the currently-open turn), so the backend stamps it from the log rather than trusting a caller-supplied value.
@@ -43,7 +43,7 @@ Compaction is serialized via a log-recorded lock: `compactRegion` refuses to sta
 
 ## Events
 
-The `compact/*` events extend `SessionEventMap` (merge-extensible) via declaration merging — they are session events, not cordis `Events`, and all three are log-only (no `surfaceOp`). Per-event payloads and semantics are in the generated [persistence log event catalog](../../../docs/persistence-catalog/log-events.md).
+The `compact/*` events extend `SessionEventMap` (merge-extensible) via declaration merging — they are session events, not cordis `Events`, and all three are log-only (no `surfaceOp`). Per-event payloads and semantics are in the generated [persistence log event catalog](../../../docs/persistence-catalog.md).
 
 ## Implementing a backend
 

packages/compact/compact/src/index.ts

@@ -22,10 +22,12 @@
  */
 
 import { Context, Service } from 'cordis'
+import type { Message } from '@deepseek-ai/dsh-llm'
 import type { Session } from '@deepseek-ai/dsh-session'
 import type { CompactionResult } from './types.ts'
 
 export type { CompactionResult } from './types.ts'
+export { renderContentBlocks, renderTranscript } from './render.ts'
 
 /** Minimal agent context compaction needs without depending on the agent package. */
 export interface CompactAgentContext {
@@ -68,16 +70,20 @@ export abstract class CompactService extends Service {
   /**
    * Check token pressure and compact if the conversation is too large.
    *
-   * Estimates the current surface-derived history size (including the system
-   * prompt), and if it exceeds the backend's threshold, compacts an older range
+   * Estimates the NEXT request's size — the session prefix, the
+   * surface-derived history, and the system prompt — and if it exceeds the
+   * backend's threshold, compacts an older range
    * via {@link compactRegion}, keeping recent context intact. Returns `null`
    * when no compaction is needed.
    *
    * Scope and guarantees a backend MUST honor:
-   * - **Surface-derived history only.** The decision is made against the history
-   *   derived from the session surface — the only thing compaction can act on.
-   *   Non-surface context injected downstream (into the request `messages` by a
-   *   later listener) is out of this accounting by construction.
+   * - **Compaction acts on surface-derived history only**, but the ESTIMATE
+   *   counts everything the request carries: the loop composes the session
+   *   prefix before the pre-step seam fires and hands it here, so the gate
+   *   sees the prefix this instance will actually send (`EpochHeader.messagePrefix`
+   *   — request-only, never derived history). Non-surface context injected
+   *   downstream (into the request `messages` by a later listener) is out of
+   *   this accounting by construction.
    * - **Head-anchored, best-effort.** Auto-compaction consolidates from the
    *   surface HEAD up to a balanced tool-pairing cutoff, so a prior head
    *   checkpoint is
@@ -88,10 +94,14 @@ export abstract class CompactService extends Service {
    * - **Single-unit overflow is out of scope.** If a single retained unit (one
    *   closed step, or a large free node such as a pasted `user/message`) ALONE
    *   exceeds the budget, compaction cannot help and the call may go out
-   *   over-budget. Bounding an individual unit's size is a separate concern.
+   *   over-budget. Bounding an individual unit's size is a separate concern —
+   *   as is a session prefix that alone approaches the window (a
+   *   configuration error no compactor fixes: compaction cannot shrink the
+   *   prefix).
    *
    * @param agent - agent context owning the session surface and model options.
    * @param fullSystemPrompt - assembled system prompt, counted toward the estimate.
+   * @param sessionPrefix - the instance's composed session prefix, counted toward the estimate.
    * @param signal - cancellation signal. A backend summarizing via
    *   `ctx.llm.stream()` MUST forward this into the call's `GenerateOptions.signal`
    *   so an abort/dispose tears down the in-flight summarization rather than
@@ -101,6 +111,7 @@ export abstract class CompactService extends Service {
   abstract compactIfNeeded(
     agent: CompactAgentContext,
     fullSystemPrompt: string,
+    sessionPrefix: readonly Message[],
     signal: AbortSignal,
   ): Promise<CompactionResult | null>
 

packages/compact/compact/src/render.ts

@@ -0,0 +1,118 @@
+/**
+ * Plain-text transcript rendering over session events: the shared projection
+ * used wherever a compaction-class consumer needs "what a model once saw" as
+ * readable text — a summarizer's input, or a recall tool's output.
+ *
+ * Extracted from the basic backend's private helpers so the summarize path and
+ * the recall read path render one span identically (two renderers would drift,
+ * and a recall reader would then see a different transcript than the one the
+ * summary was written from). Both functions are pure over their arguments: no
+ * session access beyond the provided events, no clock, no randomness — a
+ * rendered span is a pure function of the log, so replay reproduces it
+ * byte-identically.
+ *
+ * @module @deepseek-ai/dsh-compact/render
+ */
+
+import type { ContentBlock } from '@deepseek-ai/dsh-llm'
+import type { SessionEvent } from '@deepseek-ai/dsh-session'
+
+/**
+ * Render content blocks to a single plain-text string. Text and reasoning
+ * contribute their text (reasoning wrapped as `[reasoning: …]`); every other
+ * block type contributes a type-tagged placeholder (`[tool-call: name(args)]`,
+ * `[tool-result: …]`, …) so the reader is told what non-text content existed
+ * rather than silently losing it. A `tool-result` block recurses into its
+ * nested content (`[tool-result: <inner rendering>]`), falling back to a bare
+ * `[tool-result]` when the nested content renders to nothing. Blocks join
+ * with newlines; empty-text blocks contribute nothing.
+ *
+ * @param blocks - the content blocks to render.
+ * @returns the newline-joined plain-text rendering; empty string when nothing renders.
+ */
+export function renderContentBlocks(blocks: readonly ContentBlock[]): string {
+  const parts: string[] = []
+  for (const block of blocks) {
+    switch (block.type) {
+      case 'text':
+        if (block.text) parts.push(block.text)
+        break
+      case 'reasoning':
+        if (block.text) parts.push(`[reasoning: ${block.text}]`)
+        break
+      case 'tool-call':
+        parts.push(`[tool-call: ${block.name}(${block.arguments})]`)
+        break
+      case 'tool-result': {
+        const inner = renderContentBlocks(block.content)
+        parts.push(inner ? `[tool-result: ${inner}]` : '[tool-result]')
+        break
+      }
+      // ContentBlockMap is merge-extensible — render an unknown block as a
+      // bare type-tagged placeholder so a plugin-added block type is still
+      // signalled to the reader rather than dropped.
+      default:
+        parts.push(`[${(block as ContentBlock).type}]`)
+    }
+  }
+  return parts.join('\n')
+}
+
+/**
+ * Render a set of surface-node seqs as a `User:`/`Assistant:`/`Tool result:`
+ * transcript. Walks `seqs` in the order given — callers pass surface order
+ * (e.g. a `compactRegion` slice of the surface-node list), which after a
+ * `replace` is NOT ascending log-seq order (a high-seq summary node can sit at
+ * the head of the surface before older retained lower-seq nodes); a log-order
+ * scan would render the transcript out of order.
+ *
+ * Only the five surface (message-producing) event types render; a seq naming
+ * any other event type contributes nothing. `SessionEventMap` is
+ * merge-extensible, so unknown types are simply non-message events with no
+ * renderable text.
+ *
+ * @param events - the session log the seqs index into (`session.events`).
+ * @param seqs - the surface-node seqs to render, in surface order.
+ * @returns the transcript, entries joined by blank lines; empty string when nothing renders.
+ */
+export function renderTranscript(events: readonly SessionEvent[], seqs: readonly number[]): string {
+  const lines: string[] = []
+
+  for (const seq of seqs) {
+    const event = events[seq]
+    if (!event) continue
+
+    switch (event.type) {
+      case 'user/message': {
+        const text = renderContentBlocks(event.data.content)
+        if (text) lines.push(`User: ${text}`)
+        break
+      }
+      case 'assistant/message': {
+        const text = renderContentBlocks(event.data.content)
+        if (text) lines.push(`Assistant: ${text}`)
+        break
+      }
+      case 'tool/result': {
+        const text = renderContentBlocks(event.data.content)
+        const label = event.data.isError ? 'Tool error' : 'Tool result'
+        if (text) lines.push(`${label} (call ${event.data.callId}): ${text}`)
+        break
+      }
+      case 'context/message': {
+        const text = renderContentBlocks(event.data.content)
+        if (text) lines.push(`[Context: ${text}]`)
+        break
+      }
+      case 'steering/message': {
+        const text = renderContentBlocks(event.data.content)
+        if (text) lines.push(`[Steering: ${text}]`)
+        break
+      }
+      default:
+        break
+    }
+  }
+
+  return lines.join('\n\n')
+}

packages/compact/compact/tests/compact.spec.ts

@@ -2,6 +2,7 @@ import { describe, expect, it } from 'vitest'
 import { Context } from 'cordis'
 import { CompactService } from '@deepseek-ai/dsh-compact'
 import type { CompactionResult } from '@deepseek-ai/dsh-compact'
+import type { Message } from '@deepseek-ai/dsh-llm'
 import { Session, SessionId } from '@deepseek-ai/dsh-session'
 import type { CompactAgentContext } from '@deepseek-ai/dsh-compact'
 
@@ -18,6 +19,7 @@ class StubCompactService extends CompactService {
   override async compactIfNeeded(
     _agent: CompactAgentContext,
     _fullSystemPrompt: string,
+    _sessionPrefix: readonly Message[],
     signal: AbortSignal,
   ): Promise<CompactionResult | null> {
     this.lastSignal = signal
@@ -78,7 +80,7 @@ describe('CompactService seam', () => {
     const ctx = new Context()
     const svc = new StubCompactService(ctx)
     const session = new Session(SessionId('s'))
-    expect(await svc.compactIfNeeded(stubAgent(session), '', new AbortController().signal)).toBeNull()
+    expect(await svc.compactIfNeeded(stubAgent(session), '', [], new AbortController().signal)).toBeNull()
   })
 
   it('compact/* events merge into SessionEventMap and are log-only', async () => {
@@ -107,7 +109,7 @@ describe('CompactService seam', () => {
     await svc.compactRegion(session, 0, 0, stubAgent(session, 'm'), controller.signal)
     expect(svc.lastSignal).toBe(controller.signal)
 
-    await svc.compactIfNeeded(stubAgent(session), '', controller.signal)
+    await svc.compactIfNeeded(stubAgent(session), '', [], controller.signal)
     expect(svc.lastSignal).toBe(controller.signal)
   })
 })

packages/compact/compact/tests/render.spec.ts

@@ -0,0 +1,138 @@
+import { describe, expect, it } from 'vitest'
+import { renderContentBlocks, renderTranscript } from '@deepseek-ai/dsh-compact'
+import { Session, SessionId } from '@deepseek-ai/dsh-session'
+import type { ContentBlock } from '@deepseek-ai/dsh-llm'
+import { CallId } from '@deepseek-ai/dsh-llm'
+
+function session(): Session {
+  return new Session(SessionId('render-spec'))
+}
+
+describe('renderContentBlocks', () => {
+  it('renders text blocks verbatim and skips empty ones', () => {
+    expect(renderContentBlocks([
+      { type: 'text', text: 'hello' },
+      { type: 'text', text: '' },
+      { type: 'text', text: 'world' },
+    ])).toBe('hello\nworld')
+  })
+
+  it('wraps reasoning, skipping empty reasoning', () => {
+    expect(renderContentBlocks([
+      { type: 'reasoning', text: 'think' },
+      { type: 'reasoning', text: '' },
+    ])).toBe('[reasoning: think]')
+  })
+
+  it('renders tool-call as a name(args) placeholder', () => {
+    expect(renderContentBlocks([
+      { type: 'tool-call', id: CallId('c1'), name: 'read', arguments: '{"filePath":"a"}' },
+    ])).toBe('[tool-call: read({"filePath":"a"})]')
+  })
+
+  it('renders tool-result with nested content, and bare when empty', () => {
+    expect(renderContentBlocks([
+      { type: 'tool-result', toolCallId: CallId('c1'), content: [{ type: 'text', text: 'ok' }] },
+      { type: 'tool-result', toolCallId: CallId('c2'), content: [] },
+    ])).toBe('[tool-result: ok]\n[tool-result]')
+  })
+
+  it('renders an unknown (merge-extended) block type as a bare type tag', () => {
+    const unknown = { type: 'image', data: 'zzz' } as unknown as ContentBlock
+    expect(renderContentBlocks([unknown])).toBe('[image]')
+  })
+
+  it('returns the empty string for no blocks', () => {
+    expect(renderContentBlocks([])).toBe('')
+  })
+})
+
+describe('renderTranscript', () => {
+  it('renders each surface event type with its label, in the seq order given', () => {
+    const s = session()
+    const user = s.append('user/message', {
+      content: [{ type: 'text', text: 'fix the bug' }],
+      source: { kind: 'user' },
+    }, { surfaceOp: 'append' })
+    const assistant = s.append('assistant/message', {
+      turn: 0, step: 0,
+      content: [{ type: 'text', text: 'looking' }],
+    }, { surfaceOp: 'append' })
+    const result = s.append('tool/result', {
+      turn: 0, step: 0, callId: CallId('c1'),
+      content: [{ type: 'text', text: 'exit 0' }],
+      isError: false,
+    }, { surfaceOp: 'append' })
+    const context = s.append('context/message', {
+      content: [{ type: 'text', text: 'file changed' }],
+      source: { kind: 'plugin', plugin: 'fs' },
+    }, { surfaceOp: 'append' })
+    const steering = s.append('steering/message', {
+      turn: 0,
+      content: [{ type: 'text', text: 'stop that' }],
+      source: { kind: 'user' },
+    }, { surfaceOp: 'append' })
+
+    expect(renderTranscript(s.events, [user.seq, assistant.seq, result.seq, context.seq, steering.seq])).toBe([
+      'User: fix the bug',
+      'Assistant: looking',
+      'Tool result (call c1): exit 0',
+      '[Context: file changed]',
+      '[Steering: stop that]',
+    ].join('\n\n'))
+  })
+
+  it('labels an error tool result "Tool error"', () => {
+    const s = session()
+    const result = s.append('tool/result', {
+      turn: 0, step: 0, callId: CallId('c9'),
+      content: [{ type: 'text', text: 'boom' }],
+      isError: true,
+    }, { surfaceOp: 'append' })
+    expect(renderTranscript(s.events, [result.seq])).toBe('Tool error (call c9): boom')
+  })
+
+  it('renders NON-log-order seqs in the order given (surface order after a replace)', () => {
+    const s = session()
+    const first = s.append('user/message', {
+      content: [{ type: 'text', text: 'first' }],
+      source: { kind: 'user' },
+    }, { surfaceOp: 'append' })
+    const second = s.append('user/message', {
+      content: [{ type: 'text', text: 'second' }],
+      source: { kind: 'user' },
+    }, { surfaceOp: 'append' })
+    expect(renderTranscript(s.events, [second.seq, first.seq])).toBe('User: second\n\nUser: first')
+  })
+
+  it('skips events that render to nothing, non-message events, and seqs with no event', () => {
+    const s = session()
+    const empty = s.append('user/message', {
+      content: [{ type: 'text', text: '' }],
+      source: { kind: 'user' },
+    }, { surfaceOp: 'append' })
+    const emptyAssistant = s.append('assistant/message', {
+      turn: 0, step: 0,
+      content: [{ type: 'text', text: '' }],
+    }, { surfaceOp: 'append' })
+    const emptyResult = s.append('tool/result', {
+      turn: 0, step: 0, callId: CallId('c3'),
+      content: [{ type: 'text', text: '' }],
+      isError: false,
+    }, { surfaceOp: 'append' })
+    const emptyContext = s.append('context/message', {
+      content: [{ type: 'text', text: '' }],
+      source: { kind: 'plugin', plugin: 'fs' },
+    }, { surfaceOp: 'append' })
+    const emptySteering = s.append('steering/message', {
+      turn: 0,
+      content: [{ type: 'text', text: '' }],
+      source: { kind: 'user' },
+    }, { surfaceOp: 'append' })
+    // A log-only (non-surface) event type: contributes nothing to a transcript.
+    const lock = s.append('compact/start', { turn: 0 })
+    expect(renderTranscript(s.events, [
+      empty.seq, emptyAssistant.seq, emptyResult.seq, emptyContext.seq, emptySteering.seq, lock.seq, 9999,
+    ])).toBe('')
+  })
+})

packages/cordis/README.md

@@ -0,0 +1,7 @@
+# packages/cordis — the self-referential runtime toolset
+
+Model-facing tools over the live cordis runtime the agent itself runs inside: inspect the loaded plugins and service surface, mount model-written plugins, and dispose them again. Design home: [the toolset RFC](../../docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md).
+
+| Package | Role | ctx key |
+|---|---|---|
+| [`tool-cordis/`](tool-cordis/README.md) | The `cordis_inspect` / `cordis_mount` / `cordis_unmount` tools: read the runtime, evaluate model-written plugin code in a `node:vm` sandbox, and manage the dynamic mounts under one group fiber | registers on `ctx.tools` |

packages/cordis/tool-cordis/README.md

@@ -0,0 +1,33 @@
+# @deepseek-ai/dsh-tool-cordis
+
+The self-referential cordis toolset: three model-facing tools over the live runtime the agent runs inside. Design home — sandbox semantics, mount lifecycle, cross-mount composition, the generated API catalog, standing decisions: [the toolset RFC](../../../docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md).
+
+## What it does
+
+- `cordis_inspect` — read-only report over the runtime: services, the loaded-plugin list, registered tools, the dynamic-mount table, and the catalog-backed `api` / `events` references.
+- `cordis_mount` — evaluates model-written JavaScript (the body of an async function) in a `node:vm` sandbox; the code must `return` a cordis plugin, which is mounted under the `cordis-dynamic` group fiber and tracked as `dyn-<n>`.
+- `cordis_unmount` — disposes one mount by id, returning only after quiescence.
+
+Exact model-facing schemas: [the generated tool catalog](../../../docs/tool-catalog.md).
+
+## Trust stance
+
+The sandbox isolates the global context only — it is not a security boundary. No Node API is provided: `require`, the timers, and `fetch` are callable traps that throw a redirect to the cordis alternative (`ctx.fs` / `ctx.web` / `ctx.bash` / `inject: ['timer']` + `ctx.setTimeout`); `process` and `Buffer` are `undefined`; `globalThis` writes stay inside. These traps steer honest code onto the cordis services; they do not contain a mount that goes looking — the host-realm helpers on the sandbox global (`harness`, `console`, `btoa`) are reachable functions, so mount code can reach the host realm and Node through one of them, which is fine because `ctx` is fully privileged anyway. The `ctx` a mounted plugin's `apply` receives is a whitelist façade — register tools, observe events, provide/consume services, use timers; framework internals (`ctx.root`, `ctx.fiber`, `ctx.extend`, `ctx.plugin`, …) are withheld — but the capabilities it does expose reach the real runtime, so load this plugin as deliberately as you would grant a bash tool.
+
+## Config
+
+| Field | Default | Meaning |
+|---|---|---|
+| `vmTimeoutMs` | `5000` | Bound on the SYNCHRONOUS portion of mount-code evaluation; an async body escapes it |
+
+## The generated API catalog
+
+`src/api-catalog.ts` is generated by `scripts/gen-cordis-api.ts` from the same AST walk as [docs/cordis-catalog](../../../docs/cordis-catalog/services.md) and freshness-gated by `pnpm run verify-cordis-api` (in `doc-sync`) — never edit it by hand. `cordis_inspect` intersects it with the live service store at call time.
+
+## Rendering
+
+All three tools render `generic` cards (`read` / `execute` / `delete`); `cordis_mount` carries the mount code as `rawInput`. Presenters are pure functions of the args; results keep the default text rendering.
+
+## Export shape
+
+Namespace plugin: named exports `name` / `inject` / `Config` / `apply`, no default export ([docs/postmortem/0001](../../../docs/postmortem/0001-acp-default-export-drops-inject.md)).

packages/cordis/tool-cordis/package.json

@@ -0,0 +1,42 @@
+{
+  "name": "@deepseek-ai/dsh-tool-cordis",
+  "description": "Self-referential cordis toolset: inspect the live runtime, mount and dispose model-written plugins",
+  "version": "0.0.1",
+  "private": true,
+  "type": "module",
+  "main": "lib/index.js",
+  "types": "lib/types/index.d.ts",
+  "exports": {
+    ".": {
+      "types": "./lib/types/index.d.ts",
+      "default": "./lib/index.js"
+    },
+    "./src/*": "./src/*",
+    "./package.json": "./package.json"
+  },
+  "files": [
+    "lib/index.js",
+    "lib/types/**/*.d.ts",
+    "lib/types/**/*.d.ts.map",
+    "src"
+  ],
+  "license": "BSD-3-Clause",
+  "peerDependencies": {
+    "@deepseek-ai/dsh-tools": "^0.0.1",
+    "cordis": "^4.0.0-rc.6"
+  },
+  "dependencies": {
+    "schemastery": "^3.18.0"
+  },
+  "devDependencies": {
+    "@deepseek-ai/dsh-agent": "workspace:^",
+    "@deepseek-ai/dsh-agent-loop": "workspace:^",
+    "@deepseek-ai/dsh-llm": "workspace:^",
+    "@deepseek-ai/dsh-session": "workspace:^",
+    "@deepseek-ai/dsh-system-prompt": "workspace:^",
+    "@deepseek-ai/dsh-tools": "workspace:^",
+    "@cordisjs/plugin-loader": "^1.0.0-rc.4",
+    "cordis": "^4.0.0-rc.6",
+    "@cordisjs/plugin-timer": "workspace:^"
+  }
+}

packages/cordis/tool-cordis/src/api-catalog.ts

@@ -0,0 +1,855 @@
+/**
+ * Generated by scripts/gen-cordis-api.ts — do not edit by hand; run
+ * `pnpm run gen-cordis-api` to regenerate (freshness-gated by
+ * `pnpm run verify-cordis-api` in doc-sync).
+ *
+ * The machine-readable cordis API catalog `cordis_inspect` serves to the
+ * model: harness services (summary + public method signatures), harness
+ * events (mode + signature), and the inherited `ctx` surface. Produced by
+ * the same AST walk as docs/cordis-catalog, so this data and the rendered
+ * docs cannot diverge.
+ *
+ * @module @deepseek-ai/dsh-tool-cordis/api-catalog
+ */
+
+/** One harness `ctx.<key>` service: its one-line summary and public method signatures. */
+export interface ServiceApiEntry {
+  /** The `ctx.<key>` name, e.g. `tools`. */
+  key: string
+  /** First sentence of the service class JSDoc. */
+  summary: string
+  /** Public method signatures, bodies stripped, in source order. */
+  methods: readonly string[]
+}
+
+/** One harness event: its dispatch mode, exact signature, and one-line summary. */
+export interface EventApiEntry {
+  /** The scoped event name, e.g. `agent/status`. */
+  name: string
+  /** The dispatch mode from the declaration's `@mode` tag. */
+  mode: string
+  /** The exact listener signature, whitespace-normalized. */
+  signature: string
+  /** First sentence of the event JSDoc. */
+  summary: string
+}
+
+/** One inherited (cordis core + loader/hmr/timer) `ctx` member group with its summary. */
+export interface InheritedApiEntry {
+  /** The `ctx` member name(s), e.g. `ctx.on / ctx.once`. */
+  name: string
+  /** One-line summary of what the member does. */
+  summary: string
+}
+
+/** One named type shape the service signatures reference. */
+export interface TypeApiEntry {
+  /** The exported type/interface name, e.g. `BashRunResult`. */
+  name: string
+  /** The full declaration text, comments stripped. */
+  declaration: string
+}
+
+/** Every harness `ctx.<key>` service, sorted by key. */
+export const SERVICE_API: readonly ServiceApiEntry[] = [
+  {
+    key: 'agentLoop',
+    summary: 'The agent-loop plugin (`ctx.agentLoop`): creates ReactLoopAgents, runs their loops, and registers them in `ctx.agents`.',
+    methods: [
+      'create(id: AgentId, options: AgentOptions = {}): ReactLoopAgent',
+      'createAgent(options: CreateAgentOptions): AgentHandle',
+      'async resume(options: ResumeAgentOptions): Promise<AgentHandle>',
+    ],
+  },
+  {
+    key: 'agents',
+    summary: 'Agent registry (`ctx.agents`): tracks live agents so UI, hook, and orchestrator plugins can find them without depending on the concrete loop package.',
+    methods: [
+      'setFactory(factory: AgentFactory): () => void',
+      'create(options: CreateAgentOptions): AgentHandle',
+      'async resume(options: ResumeAgentOptions): Promise<AgentHandle>',
+      'register(agent: Agent): () => void',
+      'get(id: AgentId): Agent | undefined',
+      'list(): Agent[]',
+    ],
+  },
+  {
+    key: 'bash',
+    summary: 'Abstract bash execution service.',
+    methods: [
+      'abstract resolve(request: BashExecRequest): BashExecSpec',
+      'abstract run(spec: BashExecSpec): Promise<BashRunResult>',
+      'abstract start(spec: BashExecSpec): BashTask',
+      'abstract get(id: BashTaskId): BashTask | undefined',
+      'abstract ownerOf(id: BashTaskId): OwnerToken | undefined',
+      'abstract list(): BashTask[]',
+      'abstract readOutput(id: BashTaskId): BashTaskRead',
+      'abstract kill(id: BashTaskId): boolean',
+      'onTaskDone(listener: BashTaskListener): () => void',
+    ],
+  },
+  {
+    key: 'codeRuntime',
+    summary: 'Abstract code-execution service.',
+    methods: [
+      'abstract run(request: CodeRunRequest): Promise<CodeRunResult>',
+    ],
+  },
+  {
+    key: 'compact',
+    summary: 'Abstract compaction service.',
+    methods: [
+      'abstract compactIfNeeded( agent: CompactAgentContext, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal, ): Promise<CompactionResult | null>',
+      'abstract compactRegion( session: Session, start: number, end: number, agent: CompactAgentContext, signal?: AbortSignal, ): Promise<CompactionResult>',
+    ],
+  },
+  {
+    key: 'fs',
+    summary: 'Abstract filesystem provider service.',
+    methods: [
+      'abstract resolve(path: string, opts?: { cwd?: string }): Promise<FsTarget>',
+      'abstract stat(target: FsTarget, signal?: AbortSignal): Promise<FsInfo | undefined>',
+      'abstract readText(target: FsTarget, signal?: AbortSignal): Promise<string>',
+      'abstract streamText(target: FsTarget, signal?: AbortSignal): Promise<AsyncIterable<string>>',
+      'abstract listDir(target: FsTarget, signal?: AbortSignal): Promise<FsDirEntry[]>',
+      'abstract writeText(target: FsTarget, content: string, expected?: FsWriteIntent, signal?: AbortSignal): Promise<FsWriteOutcome>',
+      'abstract editText(target: FsTarget, edit: FsEditRequest, expected?: { version: FsVersion }, signal?: AbortSignal): Promise<FsEditOutcome>',
+    ],
+  },
+  {
+    key: 'llm',
+    summary: 'The abstract `llm` service: an adapter registry plus a streaming model-call surface, interceptable via the `llm/stream` waterfall.',
+    methods: [
+      'registerAdapter(models: string[], adapter: LlmAdapter): () => void',
+      'models(): string[]',
+      'stream(options: GenerateOptions): AsyncIterable<StreamChunk>',
+    ],
+  },
+  {
+    key: 'sessionPersistence',
+    summary: 'Abstract durable session-persistence service.',
+    methods: [
+      'abstract create(meta: SessionHeader): Promise<void>',
+      'abstract append(id: SessionId, events: readonly SessionEvent[]): Promise<void>',
+      'abstract load(id: SessionId): Promise<{ meta: SessionHeader; events: SessionEvent[] }>',
+      'abstract list(): Promise<SessionHeader[]>',
+    ],
+  },
+  {
+    key: 'sessions',
+    summary: 'In-memory session store (`ctx.sessions`).',
+    methods: [
+      'create(id?: SessionId, options?: CreateSessionOptions): Session',
+      'prepare(id?: SessionId, options?: CreateSessionOptions): Session',
+      'enter(session: Session): () => void',
+      'announce(session: Session): void',
+      'get(id: SessionId): Session | undefined',
+      'list(): Session[]',
+      'fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId): Session',
+    ],
+  },
+  {
+    key: 'subagents',
+    summary: 'The `subagents` service: a registry of named SubagentProviders and a capability-checked start surface.',
+    methods: [
+      'registerProvider(provider: SubagentProvider): () => void',
+      'getProvider(name: string): SubagentProvider | undefined',
+      'list(): string[]',
+      'start(name: string, request: SubagentStartRequest): SubagentRun',
+    ],
+  },
+  {
+    key: 'systemPrompt',
+    summary: 'Registry service (`ctx.systemPrompt`): plugins contribute ordered text sections, tool-schema providers, and named prompt variables; the agent loop calls `assemble(context)` once per step.',
+    methods: [
+      'section(section: PromptSection): () => void',
+      'tools(provider: () => ToolSchema[]): () => void',
+      'variable(name: string, provider: (context: AssembleContext) => string | undefined): () => void',
+      'async assemble(context: AssembleContext = {}): Promise<PromptAssembly>',
+    ],
+  },
+  {
+    key: 'tools',
+    summary: 'Tool registry (`ctx.tools`): tool plugins register definitions; the agent loop executes calls through the `tools/pre-execute` → `tools/execute` → `tools/post-execute` pipeline.',
+    methods: [
+      'register(definition: ToolDefinition): () => void',
+      'get(name: string): ToolDefinition | undefined',
+      'schemas(): ToolSchema[]',
+      'async execute(exec: ToolExecution): Promise<ToolExecutionResult>',
+    ],
+  },
+  {
+    key: 'userInteraction',
+    summary: '`ctx.userInteraction`: one active UI provider plus an `ask()` surface.',
+    methods: [
+      'registerProvider(provider: UserInteractionProvider): () => void',
+      'async ask(request: AskUserQuestionRequest): Promise<AskUserQuestionAnswer>',
+    ],
+  },
+  {
+    key: 'web',
+    summary: 'The web access service.',
+    methods: [
+      'registerSearchProvider(provider: WebSearchProvider): () => void',
+      'registerFetchProvider(provider: WebFetchProvider): () => void',
+      'async search(request: WebSearchRequest, exec?: WebExecContext): Promise<WebSearchResult>',
+      'async fetch(request: WebFetchRequest, exec?: WebExecContext): Promise<WebFetchResult>',
+    ],
+  },
+]
+
+/** Every harness event, sorted by name. */
+export const EVENT_API: readonly EventApiEntry[] = [
+  {
+    name: 'agent/created',
+    mode: 'emit',
+    signature: '\'agent/created\'(agent: Agent): void',
+    summary: 'An agent was registered in the AgentRegistry and is ready to receive messages.',
+  },
+  {
+    name: 'agent/disposed',
+    mode: 'emit',
+    signature: '\'agent/disposed\'(agent: Agent): void',
+    summary: 'An agent was disposed and removed from the registry; its fiber and any in-flight turn have been torn down.',
+  },
+  {
+    name: 'agent/error',
+    mode: 'emit',
+    signature: '\'agent/error\'(agent: Agent, turn: number, step: number, error: Error): void',
+    summary: 'A step or turn errored.',
+  },
+  {
+    name: 'agent/pre-step',
+    mode: 'serial',
+    signature: '\'agent/pre-step\'(agent: Agent, turn: number, step: number, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal): Promise<void> | void',
+    summary: 'Awaited pre-step surface-mutation checkpoint, fired once per step AFTER `turn/start` (and after the prior step closed) but BEFORE this step\'s `step/start` — so anything a listener appends lands OUTSIDE the step, between `turn/start`/`step/end` and the upcoming `step/start`.',
+  },
+  {
+    name: 'agent/prompt-submit',
+    mode: 'waterfall',
+    signature: '\'agent/prompt-submit\'(agent: Agent, content: ContentBlock[], source: MessageSource, next: () => Promise<PromptDecision>): Promise<PromptDecision>',
+    summary: 'Waterfall: decide what happens to ONE drained queued message before it becomes a `user/message` — allow (optionally rewriting the prompt bytes or attaching `additionalContext`) or block it.',
+  },
+  {
+    name: 'agent/queued',
+    mode: 'emit',
+    signature: '\'agent/queued\'(agent: Agent, content: ContentBlock[], info: { source: MessageSource; steering: boolean }): void',
+    summary: 'A message entered the agent\'s inbox (queued or steering).',
+  },
+  {
+    name: 'agent/request',
+    mode: 'waterfall',
+    signature: '\'agent/request\'(agent: Agent, turn: number, step: number, config: LlmCallConfig, next: () => Promise<LlmCallConfig>): Promise<LlmCallConfig>',
+    summary: 'Waterfall: shape the step\'s call configuration — model switching, sampling overrides — by returning a replacement LlmCallConfig (the frozen seed is the config the loop would otherwise use).',
+  },
+  {
+    name: 'agent/session-prefix',
+    mode: 'waterfall',
+    signature: '\'agent/session-prefix\'(agent: Agent, prefix: Message[], signal: AbortSignal, next: () => Promise<Message[]>): Promise<Message[]>',
+    summary: 'Waterfall: compose the SESSION PREFIX — request-only messages placed in front of the ENTIRE derived history (directly after the provider\'s system slot) on every request this loop instance sends.',
+  },
+  {
+    name: 'agent/session-start',
+    mode: 'emit',
+    signature: '\'agent/session-start\'(agent: Agent, source: SessionStartSource): void',
+    summary: 'The agent\'s session lifecycle began, fired once before its first turn.',
+  },
+  {
+    name: 'agent/status',
+    mode: 'emit',
+    signature: '\'agent/status\'(agent: Agent, status: AgentStatus): void',
+    summary: 'Agent status changed (`idle` ⇄ `running`, or → `disposed`).',
+  },
+  {
+    name: 'agent/step-result',
+    mode: 'waterfall',
+    signature: '\'agent/step-result\'(agent: Agent, turn: number, step: number, message: Message, next: () => Promise<Message>): Promise<Message>',
+    summary: 'Waterfall: post-process the assembled assistant Message before tool dispatch (validation, content rewriting, …).',
+  },
+  {
+    name: 'agent/turn-continuation',
+    mode: 'waterfall',
+    signature: '\'agent/turn-continuation\'(agent: Agent, turn: number, defaultDecision: ContinuationDecision, next: () => Promise<ContinuationDecision>): Promise<ContinuationDecision>',
+    summary: 'Waterfall: override the turn-continuation decision via a typed ContinuationDecision.',
+  },
+  {
+    name: 'fs/edit-intent',
+    mode: 'waterfall',
+    signature: '\'fs/edit-intent\'(target: FsTarget, actor: object | undefined, next: () => { version: FsVersion } | undefined | Promise<{ version: FsVersion } | undefined>): Promise<{ version: FsVersion } | undefined>',
+    summary: 'Single-slot decision: produce the optional version guard for the next FileSystem.editText.',
+  },
+  {
+    name: 'fs/observed',
+    mode: 'emit',
+    signature: '\'fs/observed\'(target: FsTarget, version: FsVersion, actor: object | undefined): void',
+    summary: 'Record that an actor observed a target at a version, after a successful read/write/edit.',
+  },
+  {
+    name: 'fs/write-intent',
+    mode: 'waterfall',
+    signature: '\'fs/write-intent\'(target: FsTarget, actor: object | undefined, next: () => FsWriteIntent | undefined | Promise<FsWriteIntent | undefined>): Promise<FsWriteIntent | undefined>',
+    summary: 'Single-slot decision: produce the write intent for the next FileSystem.writeText.',
+  },
+  {
+    name: 'llm/stream',
+    mode: 'waterfall',
+    signature: '\'llm/stream\'(this: LlmService, options: GenerateOptions, next: () => AsyncIterable<StreamChunk>): AsyncIterable<StreamChunk>',
+    summary: 'Waterfall around every streaming model call (retry, replay, routing).',
+  },
+  {
+    name: 'session/created',
+    mode: 'emit',
+    signature: '\'session/created\'(session: Session): void',
+    summary: 'A session was created in the store.',
+  },
+  {
+    name: 'session/event',
+    mode: 'emit',
+    signature: '\'session/event\'(session: Session, event: SessionEvent): void',
+    summary: 'An event was appended to a session log (sync, fire-and-forget).',
+  },
+  {
+    name: 'session/flush',
+    mode: 'parallel',
+    signature: '\'session/flush\'(session: Session): Promise<void> | void',
+    summary: 'Awaited durability checkpoint.',
+  },
+  {
+    name: 'subagent/end',
+    mode: 'emit',
+    signature: '\'subagent/end\'(info: SubagentRunEndInfo): void',
+    summary: 'A subagent run settled — emitted when SubagentRun.result resolves (any stop reason).',
+  },
+  {
+    name: 'subagent/provider-added',
+    mode: 'emit',
+    signature: '\'subagent/provider-added\'(provider: SubagentProvider): void',
+    summary: 'A provider became resolvable in the SubagentService registry.',
+  },
+  {
+    name: 'subagent/provider-removed',
+    mode: 'emit',
+    signature: '\'subagent/provider-removed\'(name: string): void',
+    summary: 'A provider left the registry (its plugin\'s fiber was disposed — an unload or an HMR reload).',
+  },
+  {
+    name: 'subagent/start',
+    mode: 'emit',
+    signature: '\'subagent/start\'(info: SubagentRunInfo): void',
+    summary: 'A subagent run started — emitted after the provider is resolved and its capabilities validated, as the child run begins.',
+  },
+  {
+    name: 'system-prompt/assemble',
+    mode: 'waterfall',
+    signature: '\'system-prompt/assemble\'(this: SystemPrompt, assembly: PromptAssembly, context: AssembleContext, next: () => Promise<PromptAssembly>): Promise<PromptAssembly>',
+    summary: 'Waterfall around prompt assembly — mutate or extend the PromptAssembly (sections + tools + variables) before it is rendered.',
+  },
+  {
+    name: 'system-prompt/change',
+    mode: 'emit',
+    signature: '\'system-prompt/change\'(): void',
+    summary: 'A section, tool provider, or variable provider was registered or unregistered (the assembly inputs changed).',
+  },
+  {
+    name: 'tools/change',
+    mode: 'emit',
+    signature: '\'tools/change\'(): void',
+    summary: 'A tool was registered or unregistered (the available tool set changed).',
+  },
+  {
+    name: 'tools/execute',
+    mode: 'waterfall',
+    signature: '\'tools/execute\'(this: ToolRegistry, exec: ToolExecution, next: () => Promise<ToolExecutionResult>): Promise<ToolExecutionResult>',
+    summary: 'Around-dispatch waterfall wrapping the registry\'s core tool dispatch, between the `tools/pre-execute` gate and the `tools/post-execute` seam.',
+  },
+  {
+    name: 'tools/post-execute',
+    mode: 'waterfall',
+    signature: '\'tools/post-execute\'(this: ToolRegistry, exec: ToolExecution, result: ToolExecutionResult, next: () => Promise<PostToolDecision>): Promise<PostToolDecision>',
+    summary: 'Waterfall AFTER a tool runs — where hook plugins inspect the result and accept it (optionally REPLACING the model-facing content, and/or attaching `additionalContext` for the next request) or block it with corrective `feedback` (Claude Code\'s `PostToolUse`).',
+  },
+  {
+    name: 'tools/pre-execute',
+    mode: 'waterfall',
+    signature: '\'tools/pre-execute\'(this: ToolRegistry, exec: ToolExecution, next: () => Promise<PreToolDecision>): Promise<PreToolDecision>',
+    summary: 'Waterfall BEFORE a tool runs — the gate where sandbox, permission, and hook plugins allow or deny a call (Claude Code\'s `PreToolUse`).',
+  },
+]
+
+/** Shapes of every exported type the SERVICE_API signatures reference (transitively), sorted by name. */
+export const TYPE_API: readonly TypeApiEntry[] = [
+  {
+    name: 'Agent',
+    declaration: 'export interface Agent {\n    readonly id: AgentId;\n    readonly options: AgentOptions;\n    readonly session: Session;\n    readonly status: AgentStatus;\n    send(content: ContentBlock[], options?: SendOptions): void;\n    steer(content: ContentBlock[], options?: SendOptions): void;\n    inject(content: ContentBlock[], options?: SendOptions): void;\n    cancel(reason?: string): void;\n    whenIdle(): Promise<void>;\n}',
+  },
+  {
+    name: 'AgentFactory',
+    declaration: 'export interface AgentFactory {\n    createAgent(options: CreateAgentOptions): AgentHandle;\n    resume(options: ResumeAgentOptions): Promise<AgentHandle>;\n}',
+  },
+  {
+    name: 'AgentHandle',
+    declaration: 'export interface AgentHandle {\n    agent: Agent;\n    dispose(): Promise<void>;\n}',
+  },
+  {
+    name: 'AgentId',
+    declaration: 'export type AgentId = Branded<\'AgentId\'>;',
+  },
+  {
+    name: 'AgentOptions',
+    declaration: 'export interface AgentOptions {\n    model?: string;\n}',
+  },
+  {
+    name: 'AgentStatus',
+    declaration: 'export type AgentStatus = \'idle\' | \'running\' | \'disposed\';',
+  },
+  {
+    name: 'AskUserQuestionAnswer',
+    declaration: 'export interface AskUserQuestionAnswer {\n    answers: AskUserQuestionAnswerItem[];\n}',
+  },
+  {
+    name: 'AskUserQuestionAnswerItem',
+    declaration: 'export interface AskUserQuestionAnswerItem {\n    id: string;\n    selected: string[];\n    custom?: string;\n}',
+  },
+  {
+    name: 'AskUserQuestionItem',
+    declaration: 'export interface AskUserQuestionItem {\n    id: string;\n    question: string;\n    header?: string;\n    options?: AskUserQuestionOption[];\n    multiSelect?: boolean;\n}',
+  },
+  {
+    name: 'AskUserQuestionOption',
+    declaration: 'export interface AskUserQuestionOption {\n    label: string;\n    description?: string;\n}',
+  },
+  {
+    name: 'AskUserQuestionRequest',
+    declaration: 'export interface AskUserQuestionRequest {\n    questions: AskUserQuestionItem[];\n    agent?: Agent;\n    signal?: AbortSignal;\n}',
+  },
+  {
+    name: 'AssembleContext',
+    declaration: 'export interface AssembleContext {\n}',
+  },
+  {
+    name: 'AssembledSection',
+    declaration: 'export interface AssembledSection {\n    name: string;\n    order: number;\n    text: string;\n}',
+  },
+  {
+    name: 'BashExecRequest',
+    declaration: 'export interface BashExecRequest {\n    command: string;\n    workdir?: string | undefined;\n    timeoutMs?: number | undefined;\n    signal?: AbortSignal | undefined;\n    stdin?: string | undefined;\n    env?: Record<string, string> | undefined;\n    owner?: OwnerToken | undefined;\n}',
+  },
+  {
+    name: 'BashExecSpec',
+    declaration: 'export interface BashExecSpec {\n    command: string;\n    workdir: string;\n    timeoutMs: number;\n    signal?: AbortSignal | undefined;\n    stdin?: string | undefined;\n    env?: Record<string, string> | undefined;\n    owner: OwnerToken | undefined;\n}',
+  },
+  {
+    name: 'BashRunResult',
+    declaration: 'export interface BashRunResult {\n    exitCode: number | null;\n    signal: NodeJS.Signals | null;\n    timedOut: boolean;\n    aborted: boolean;\n    timeoutMs: number;\n    stdout: CollectedOutput;\n    stderr: CollectedOutput;\n}',
+  },
+  {
+    name: 'BashTask',
+    declaration: 'export interface BashTask {\n    readonly id: BashTaskId;\n    readonly command: string;\n    status: BashTaskStatus;\n    exitCode: number | null;\n    signal: NodeJS.Signals | null;\n    readonly done: Promise<void>;\n}',
+  },
+  {
+    name: 'BashTaskId',
+    declaration: 'export type BashTaskId = Branded<\'BashTaskId\'>;',
+  },
+  {
+    name: 'BashTaskListener',
+    declaration: 'export type BashTaskListener = (task: BashTask) => void;',
+  },
+  {
+    name: 'BashTaskRead',
+    declaration: 'export interface BashTaskRead {\n    task: BashTask;\n    delta: string;\n    lossy: boolean;\n    stdoutSpillPath?: string;\n    stderrSpillPath?: string;\n}',
+  },
+  {
+    name: 'BashTaskStatus',
+    declaration: 'export type BashTaskStatus = \'running\' | \'completed\' | \'killed\';',
+  },
+  {
+    name: 'Branded',
+    declaration: 'export type Branded<B extends string> = string & {\n    readonly [BRAND]: B;\n};',
+  },
+  {
+    name: 'CallId',
+    declaration: 'export type CallId = Branded<\'CallId\'>;',
+  },
+  {
+    name: 'CodeBindingFunction',
+    declaration: 'export type CodeBindingFunction = (args: unknown) => Promise<unknown>;',
+  },
+  {
+    name: 'CodeBindingNamespace',
+    declaration: 'export interface CodeBindingNamespace {\n    global: string;\n    functions: Record<string, CodeBindingFunction>;\n}',
+  },
+  {
+    name: 'CodeLogEntry',
+    declaration: 'export interface CodeLogEntry {\n    source: \'console\' | \'stdout\' | \'stderr\';\n    level?: \'log\' | \'info\' | \'warn\' | \'error\' | \'debug\';\n    text: string;\n}',
+  },
+  {
+    name: 'CodeRunFailure',
+    declaration: 'export interface CodeRunFailure {\n    kind: \'exception\' | \'timeout\' | \'abort\' | \'worker-exit\';\n    message: string;\n}',
+  },
+  {
+    name: 'CodeRunRequest',
+    declaration: 'export interface CodeRunRequest {\n    program: string;\n    bindings: CodeBindingNamespace[];\n    signal?: AbortSignal;\n}',
+  },
+  {
+    name: 'CodeRunResult',
+    declaration: 'export interface CodeRunResult {\n    value?: unknown;\n    logs: CodeLogEntry[];\n    error?: CodeRunFailure;\n}',
+  },
+  {
+    name: 'CollectedOutput',
+    declaration: 'export interface CollectedOutput {\n    text: string;\n    truncated: boolean;\n    spillPath?: string;\n}',
+  },
+  {
+    name: 'CompactAgentContext',
+    declaration: 'export interface CompactAgentContext {\n    session: Session;\n    options: {\n        model?: string;\n    };\n}',
+  },
+  {
+    name: 'CompactionResult',
+    declaration: 'export interface CompactionResult {\n    startSeq: number;\n    summarySeq: number;\n    endSeq: number;\n    summary: ContentBlock[];\n    shadowedRange: {\n        start: number;\n        end: number;\n    };\n    shadowedSeqs: number[];\n    shadowedTokenCount: number;\n}',
+  },
+  {
+    name: 'ContentBlockMap',
+    declaration: 'export interface ContentBlockMap {\n    \'text\': TextBlock;\n    \'reasoning\': ReasoningBlock;\n    \'tool-call\': ToolCallBlock;\n    \'tool-result\': ToolResultBlock;\n}',
+  },
+  {
+    name: 'ContentBlockType',
+    declaration: 'export type ContentBlockType = keyof ContentBlockMap;',
+  },
+  {
+    name: 'CreateAgentOptions',
+    declaration: 'export interface CreateAgentOptions {\n    agentId: AgentId;\n    sessionId: SessionId;\n    meta?: {\n        cwd?: string;\n        parentSession?: SessionId;\n        seedLength?: number;\n    };\n    seed?: SessionEvent[];\n    agentOptions?: AgentOptions;\n}',
+  },
+  {
+    name: 'CreateSessionOptions',
+    declaration: 'export interface CreateSessionOptions {\n    seed?: SessionEvent[];\n    meta?: {\n        cwd?: string;\n        parentSession?: SessionId;\n        createdAt?: number;\n        seedLength?: number;\n    };\n}',
+  },
+  {
+    name: 'DiffCallView',
+    declaration: 'export interface DiffCallView {\n    card: \'diff\';\n    title: string;\n    diffs: FileDiff[];\n    locations?: FileLocation[];\n}',
+  },
+  {
+    name: 'DiffResultView',
+    declaration: 'export interface DiffResultView {\n    card: \'diff\';\n    title?: string;\n    diffs: FileDiff[];\n}',
+  },
+  {
+    name: 'FileDiff',
+    declaration: 'export interface FileDiff {\n    path: string;\n    oldText: string | null;\n    newText: string;\n}',
+  },
+  {
+    name: 'FileLocation',
+    declaration: 'export interface FileLocation {\n    path: string;\n    line?: number;\n}',
+  },
+  {
+    name: 'FinishReason',
+    declaration: 'export type FinishReason = FinishReasonMap[keyof FinishReasonMap];',
+  },
+  {
+    name: 'FinishReasonMap',
+    declaration: 'export interface FinishReasonMap {\n    \'stop\': {\n        kind: \'stop\';\n    };\n    \'tool-calls\': {\n        kind: \'tool-calls\';\n    };\n    \'max-tokens\': {\n        kind: \'max-tokens\';\n    };\n    \'aborted\': {\n        kind: \'aborted\';\n    };\n    \'error\': {\n        kind: \'error\';\n        message: string;\n        code?: string;\n    };\n}',
+  },
+  {
+    name: 'FsDirEntry',
+    declaration: 'export interface FsDirEntry {\n    name: string;\n    type: \'file\' | \'directory\' | \'other\';\n    target: FsTarget;\n    version?: FsVersion;\n    size?: number;\n}',
+  },
+  {
+    name: 'FsEditOutcome',
+    declaration: 'export interface FsEditOutcome {\n    version: FsVersion;\n    before: string;\n    after: string;\n}',
+  },
+  {
+    name: 'FsEditRequest',
+    declaration: 'export interface FsEditRequest {\n    oldString: string;\n    newString: string;\n    replaceAll: boolean;\n}',
+  },
+  {
+    name: 'FsInfo',
+    declaration: 'export interface FsInfo {\n    version: FsVersion;\n    type: \'file\' | \'directory\' | \'other\';\n    size?: number;\n}',
+  },
+  {
+    name: 'FsTarget',
+    declaration: 'export interface FsTarget {\n    targetKey: FsTargetKey;\n    displayPath: string;\n}',
+  },
+  {
+    name: 'FsTargetKey',
+    declaration: 'export type FsTargetKey = Branded<\'FsTargetKey\'>;',
+  },
+  {
+    name: 'FsVersion',
+    declaration: 'export type FsVersion = Branded<\'FsVersion\'>;',
+  },
+  {
+    name: 'FsWriteIntent',
+    declaration: 'export type FsWriteIntent = {\n    kind: \'createIfAbsent\';\n} | {\n    kind: \'replaceIfVersion\';\n    version: FsVersion;\n};',
+  },
+  {
+    name: 'FsWriteOutcome',
+    declaration: 'export interface FsWriteOutcome {\n    operation: \'create\' | \'update\';\n    version: FsVersion;\n    before: string | null;\n    after: string;\n}',
+  },
+  {
+    name: 'GenerateOptions',
+    declaration: 'export interface GenerateOptions {\n    model: string;\n    messages: Message[];\n    system?: string;\n    tools?: ToolSchema[];\n    temperature?: number;\n    maxTokens?: number;\n    stop?: string[];\n    signal?: AbortSignal;\n    sessionId?: Branded<\'SessionId\'>;\n}',
+  },
+  {
+    name: 'GenericCallView',
+    declaration: 'export interface GenericCallView {\n    card: \'generic\';\n    title: string;\n    kind?: ToolCallKind;\n    rawInput?: unknown;\n    content?: ContentBlock[];\n    locations?: FileLocation[];\n}',
+  },
+  {
+    name: 'GenericResultView',
+    declaration: 'export interface GenericResultView {\n    card: \'generic\';\n    title?: string;\n    content?: ContentBlock[];\n}',
+  },
+  {
+    name: 'HookContext',
+    declaration: 'export interface HookContext {\n    content: ContentBlock[];\n    source: MessageSource;\n}',
+  },
+  {
+    name: 'Message',
+    declaration: 'export interface Message {\n    role: \'system\' | \'user\' | \'assistant\';\n    content: ContentBlock[];\n}',
+  },
+  {
+    name: 'MessageSource',
+    declaration: 'export type MessageSource = MessageSourceMap[keyof MessageSourceMap];',
+  },
+  {
+    name: 'MessageSourceMap',
+    declaration: 'export interface MessageSourceMap {\n    user: {\n        kind: \'user\';\n    };\n    plugin: {\n        kind: \'plugin\';\n        plugin: string;\n    };\n}',
+  },
+  {
+    name: 'OwnerToken',
+    declaration: 'export type OwnerToken = Branded<\'OwnerToken\'>;',
+  },
+  {
+    name: 'PromptAssembly',
+    declaration: 'export interface PromptAssembly {\n    sections: AssembledSection[];\n    tools: ToolSchema[];\n    variables: Record<string, string | undefined>;\n}',
+  },
+  {
+    name: 'PromptSection',
+    declaration: 'export interface PromptSection {\n    name: string;\n    order: number;\n    text: string | ((context: AssembleContext) => string);\n}',
+  },
+  {
+    name: 'ReasoningBlock',
+    declaration: 'export interface ReasoningBlock {\n    type: \'reasoning\';\n    text: string;\n}',
+  },
+  {
+    name: 'ResumeAgentOptions',
+    declaration: 'export interface ResumeAgentOptions {\n    agentId: AgentId;\n    resumeSessionId: SessionId;\n    agentOptions?: AgentOptions;\n}',
+  },
+  {
+    name: 'SendOptions',
+    declaration: 'export interface SendOptions {\n    source?: MessageSource;\n}',
+  },
+  {
+    name: 'SessionEvent',
+    declaration: 'export type SessionEvent<T extends SessionEventType = SessionEventType> = {\n    [K in SessionEventType]: {\n        type: K;\n        seq: number;\n        time: number;\n        data: SessionEventMap[K];\n    } & (K extends SurfaceEventType ? {\n        sourceEventSeqs?: number[];\n        surfaceOp?: SurfaceOp;\n    } : object);\n}[T];',
+  },
+  {
+    name: 'SessionEventMap',
+    declaration: 'export interface SessionEventMap {\n    \'turn/start\': {\n        turn: number;\n        trigger: TurnTrigger;\n    };\n    \'turn/end\': {\n        turn: number;\n        reason: TurnEndReason;\n    };\n    \'step/start\': {\n        turn: number;\n        step: number;\n    };\n    \'step/end\': {\n        turn: number;\n        step: number;\n    };\n    \'user/message\': {\n        content: ContentBlock[];\n        source: MessageSource;\n    };\n    \'prompt/blocked\': {\n        content: ContentBlock[];\n        source: MessageSource;\n        reason: string;\n    };\n    \'context/message\': {\n        content: ContentBlock[];\n        source: MessageSource;\n    };\n    \'assistant/chunk\': {\n        turn: number;\n        step: number;\n        chunk: StreamChunk;\n    };\n    \'assistant/message\': {\n        turn: number;\n        step: number;\n        content: ContentBlock[];\n        usage?: TokenUsage;\n    };\n    \'tool/call\': {\n        turn: number;\n        step: number;\n        callId: CallId;\n        name: string;\n        arguments: string;\n    };\n    \'tool/result\': {\n        turn: number;\n        step: number;\n        callId: CallId;\n        content: ContentBlock[];\n        isError: boolean;\n        error?: {\n            name: string;\n            code: string;\n        };\n        meta?: unknown;\n    };\n    \'steering/message\': {\n        turn: number;\n        content: ContentBlock[];\n        source: MessageSource;\n    };\n    \'todo/write\': {\n        todos: TodoItem[];\n    };\n    \'request/header\': {\n        header: E /* …truncated — full shape in source */',
+  },
+  {
+    name: 'SessionEventType',
+    declaration: 'export type SessionEventType = keyof SessionEventMap;',
+  },
+  {
+    name: 'SessionForkSource',
+    declaration: 'export type SessionForkSource = Session | SessionId;',
+  },
+  {
+    name: 'SessionHeader',
+    declaration: 'export interface SessionHeader {\n    version: number;\n    id: SessionId;\n    createdAt: number;\n    cwd?: string;\n    parentSession?: SessionId;\n    seedLength?: number;\n}',
+  },
+  {
+    name: 'SessionId',
+    declaration: 'export type SessionId = Branded<\'SessionId\'>;',
+  },
+  {
+    name: 'StreamChunk',
+    declaration: 'export type StreamChunk = {\n    type: \'block-start\';\n    index: number;\n    blockType: ContentBlockType;\n} | {\n    type: \'text-delta\';\n    index: number;\n    text: string;\n} | {\n    type: \'reasoning-delta\';\n    index: number;\n    text: string;\n} | {\n    type: \'tool-call-delta\';\n    index: number;\n    id: CallId;\n    name?: string;\n    argumentsDelta: string;\n} | {\n    type: \'block-end\';\n    index: number;\n    block: ContentBlock;\n} | {\n    type: \'usage\';\n    usage: TokenUsage;\n} | {\n    type: \'finish\';\n    reason: FinishReason;\n};',
+  },
+  {
+    name: 'StructuredOutputSchema',
+    declaration: 'export type StructuredOutputSchema = StructuredSchemaNode & {\n    type: \'object\';\n};',
+  },
+  {
+    name: 'StructuredScalar',
+    declaration: 'export type StructuredScalar = string | number | boolean | null;',
+  },
+  {
+    name: 'StructuredSchemaNode',
+    declaration: 'export interface StructuredSchemaNode {\n    type: StructuredSchemaType;\n    properties?: Record<string, StructuredSchemaNode>;\n    required?: string[];\n    additionalProperties?: boolean;\n    items?: StructuredSchemaNode;\n    enum?: StructuredScalar[];\n    const?: StructuredScalar;\n    description?: string;\n    title?: string;\n    default?: unknown;\n    examples?: unknown;\n}',
+  },
+  {
+    name: 'StructuredSchemaType',
+    declaration: 'export type StructuredSchemaType = \'object\' | \'array\' | \'string\' | \'number\' | \'integer\' | \'boolean\' | \'null\';',
+  },
+  {
+    name: 'SubagentCapabilities',
+    declaration: 'export interface SubagentCapabilities {\n    outputSchema: boolean;\n    depthLimit: boolean;\n    toolFilter: boolean;\n}',
+  },
+  {
+    name: 'SubagentProvider',
+    declaration: 'export interface SubagentProvider {\n    readonly name: string;\n    readonly capabilities: SubagentCapabilities;\n    readonly inheritsParentContext: boolean;\n    start(request: SubagentStartRequest): SubagentRun;\n}',
+  },
+  {
+    name: 'SubagentResult',
+    declaration: 'export interface SubagentResult {\n    output: ContentBlock[];\n    structured?: unknown;\n    stopReason: SubagentStopReason;\n}',
+  },
+  {
+    name: 'SubagentRun',
+    declaration: 'export interface SubagentRun {\n    readonly id: AgentId;\n    readonly result: Promise<SubagentResult>;\n    cancel(reason?: string): void;\n    dispose(): Promise<void>;\n    sendMessage?(content: ContentBlock[]): void;\n    resume?(content: ContentBlock[]): SubagentRun;\n}',
+  },
+  {
+    name: 'SubagentStartRequest',
+    declaration: 'export interface SubagentStartRequest {\n    prompt: ContentBlock[];\n    parent: Agent;\n    signal?: AbortSignal;\n    agentOptions?: AgentOptions;\n    outputSchema?: StructuredOutputSchema;\n    maxDepth?: number;\n    toolFilter?: {\n        allow?: string[];\n        deny?: string[];\n    };\n}',
+  },
+  {
+    name: 'SubagentStopReason',
+    declaration: 'export type SubagentStopReason = SubagentStopReasonMap[keyof SubagentStopReasonMap];',
+  },
+  {
+    name: 'SubagentStopReasonMap',
+    declaration: 'export interface SubagentStopReasonMap {\n    completed: \'completed\';\n    aborted: \'aborted\';\n    error: \'error\';\n    \'max-tokens\': \'max-tokens\';\n    refusal: \'refusal\';\n}',
+  },
+  {
+    name: 'SurfaceEventType',
+    declaration: 'export type SurfaceEventType = \'user/message\' | \'assistant/message\' | \'tool/result\' | \'context/message\' | \'steering/message\';',
+  },
+  {
+    name: 'SurfaceOp',
+    declaration: 'export type SurfaceOp = \'append\' | {\n    op: \'replace\';\n    start: number;\n    end: number;\n};',
+  },
+  {
+    name: 'TerminalCallView',
+    declaration: 'export interface TerminalCallView {\n    card: \'terminal\';\n    title: string;\n    description?: string;\n    cwd?: string;\n}',
+  },
+  {
+    name: 'TerminalResultView',
+    declaration: 'export interface TerminalResultView {\n    card: \'terminal\';\n    title?: string;\n    output?: string;\n    exitCode?: number;\n    signal?: string;\n}',
+  },
+  {
+    name: 'TodoItem',
+    declaration: 'export interface TodoItem {\n    content: string;\n    status: \'pending\' | \'in_progress\' | \'completed\';\n}',
+  },
+  {
+    name: 'TokenUsage',
+    declaration: 'export interface TokenUsage {\n    inputTokens: number;\n    outputTokens: number;\n    cacheReadTokens?: number;\n    cacheWriteTokens?: number;\n    reasoningTokens?: number;\n}',
+  },
+  {
+    name: 'ToolCallBlock',
+    declaration: 'export interface ToolCallBlock {\n    type: \'tool-call\';\n    id: CallId;\n    name: string;\n    arguments: string;\n}',
+  },
+  {
+    name: 'ToolCallKind',
+    declaration: 'export type ToolCallKind = \'read\' | \'edit\' | \'delete\' | \'move\' | \'search\' | \'execute\' | \'fetch\' | \'other\';',
+  },
+  {
+    name: 'ToolCallView',
+    declaration: 'export type ToolCallView = GenericCallView | TerminalCallView | DiffCallView;',
+  },
+  {
+    name: 'ToolDefinition',
+    declaration: 'export interface ToolDefinition extends ToolSchema {\n    execute(args: unknown, exec: ToolExecution): Promise<ToolExecuteReturn>;\n    timeoutMs?: number;\n    presentCall?(args: unknown): ToolCallView | undefined;\n    presentResult?(args: unknown, result: ToolResult): ToolResultView | undefined;\n}',
+  },
+  {
+    name: 'ToolErrorInfo',
+    declaration: 'export interface ToolErrorInfo {\n    name: string;\n    code: string;\n}',
+  },
+  {
+    name: 'ToolExecuteReturn',
+    declaration: 'export type ToolExecuteReturn = ContentBlock[] | {\n    content: ContentBlock[];\n    meta?: unknown;\n};',
+  },
+  {
+    name: 'ToolExecution',
+    declaration: 'export interface ToolExecution {\n    callId: CallId;\n    name: string;\n    arguments: unknown;\n    agent?: Agent;\n    signal?: AbortSignal;\n}',
+  },
+  {
+    name: 'ToolExecutionResult',
+    declaration: 'export interface ToolExecutionResult {\n    callId: CallId;\n    content: ContentBlock[];\n    isError: boolean;\n    error?: ToolErrorInfo;\n    additionalContext?: HookContext;\n    meta?: unknown;\n}',
+  },
+  {
+    name: 'ToolResult',
+    declaration: 'export interface ToolResult {\n    content: ContentBlock[];\n    isError: boolean;\n    meta?: unknown;\n}',
+  },
+  {
+    name: 'ToolResultBlock',
+    declaration: 'export interface ToolResultBlock {\n    type: \'tool-result\';\n    toolCallId: CallId;\n    content: ContentBlock[];\n    isError?: boolean;\n}',
+  },
+  {
+    name: 'ToolResultView',
+    declaration: 'export type ToolResultView = GenericResultView | TerminalResultView | DiffResultView;',
+  },
+  {
+    name: 'ToolSchema',
+    declaration: 'export interface ToolSchema {\n    name: string;\n    description: string;\n    parameters: Record<string, unknown>;\n}',
+  },
+  {
+    name: 'TurnEndReason',
+    declaration: 'export type TurnEndReason = TurnEndReasonMap[keyof TurnEndReasonMap];',
+  },
+  {
+    name: 'TurnEndReasonMap',
+    declaration: 'export interface TurnEndReasonMap {\n    completed: {\n        kind: \'completed\';\n    };\n    aborted: {\n        kind: \'aborted\';\n        reason?: string;\n    };\n    error: {\n        kind: \'error\';\n        step: number;\n        message: string;\n        code?: string;\n    };\n    disposed: {\n        kind: \'disposed\';\n    };\n    \'max-tokens\': {\n        kind: \'max-tokens\';\n    };\n    rejected: {\n        kind: \'rejected\';\n        reason: string;\n    };\n    interrupted: {\n        kind: \'interrupted\';\n    };\n}',
+  },
+  {
+    name: 'TurnTrigger',
+    declaration: 'export type TurnTrigger = TurnTriggerMap[keyof TurnTriggerMap];',
+  },
+  {
+    name: 'TurnTriggerMap',
+    declaration: 'export interface TurnTriggerMap {\n    message: {\n        kind: \'message\';\n        source: MessageSource;\n    };\n    injection: {\n        kind: \'injection\';\n        source: MessageSource;\n    };\n}',
+  },
+  {
+    name: 'UserInteractionProvider',
+    declaration: 'export interface UserInteractionProvider {\n    ask(request: AskUserQuestionRequest): Promise<AskUserQuestionAnswer>;\n}',
+  },
+  {
+    name: 'WebExecContext',
+    declaration: 'export interface WebExecContext {\n    readonly signal?: AbortSignal;\n}',
+  },
+  {
+    name: 'WebFetchBody',
+    declaration: 'export type WebFetchBody = {\n    readonly kind: \'html\';\n    readonly content: string;\n} | {\n    readonly kind: \'text\';\n    readonly content: string;\n};',
+  },
+  {
+    name: 'WebFetchProvider',
+    declaration: 'export interface WebFetchProvider {\n    readonly id: string;\n    status(): WebProviderStatus;\n    fetch(request: WebFetchRequest, exec?: WebExecContext): Promise<WebFetchResult>;\n}',
+  },
+  {
+    name: 'WebFetchRequest',
+    declaration: 'export interface WebFetchRequest {\n    readonly url: string;\n    readonly timeoutMs?: number;\n}',
+  },
+  {
+    name: 'WebFetchResult',
+    declaration: 'export interface WebFetchResult {\n    readonly providerId: string;\n    readonly url: string;\n    readonly statusCode: number;\n    readonly body: WebFetchBody;\n    readonly truncated: boolean;\n}',
+  },
+  {
+    name: 'WebProviderStatus',
+    declaration: 'export type WebProviderStatus = {\n    readonly available: true;\n} | {\n    readonly available: false;\n    readonly reason: \'missing-credential\' | \'misconfigured\';\n};',
+  },
+  {
+    name: 'WebSearchProvider',
+    declaration: 'export interface WebSearchProvider {\n    readonly id: string;\n    status(): WebProviderStatus;\n    search(request: WebSearchRequest, exec?: WebExecContext): Promise<WebSearchResult>;\n}',
+  },
+  {
+    name: 'WebSearchRequest',
+    declaration: 'export interface WebSearchRequest {\n    readonly query: string;\n    readonly maxResults?: number;\n}',
+  },
+  {
+    name: 'WebSearchResult',
+    declaration: 'export interface WebSearchResult {\n    readonly providerId: string;\n    readonly query: string;\n    readonly content?: string;\n    readonly sources: readonly WebSearchSource[];\n    readonly truncated: boolean;\n}',
+  },
+  {
+    name: 'WebSearchSource',
+    declaration: 'export interface WebSearchSource {\n    readonly url: string;\n    readonly title?: string;\n    readonly snippet?: string;\n    readonly publishedAt?: string;\n}',
+  },
+]
+
+/** The inherited `ctx` surface (cordis core + loader/hmr/timer), in curated order. */
+export const INHERITED_CTX_API: readonly InheritedApiEntry[] = [
+  { name: 'ctx.on / ctx.once', summary: 'Register an event listener (disposable).' },
+  { name: 'ctx.emit / ctx.parallel / ctx.serial / ctx.bail / ctx.waterfall', summary: 'Dispatch an event (sync / awaited / first-bail / veto-chain).' },
+  { name: 'ctx.plugin / ctx.inject', summary: 'Load a plugin / declare required services.' },
+  { name: 'ctx.effect', summary: 'Register a disposable side effect tied to the fiber.' },
+  { name: 'ctx.get / ctx.set / ctx.provide / ctx.accessor / ctx.mixin', summary: 'Low-level service-store access and binding.' },
+  { name: 'ctx.extend / ctx.isolate / ctx.intercept', summary: 'Derive a child context (scoped services / isolation / interception).' },
+  { name: 'ctx.root / ctx.scope / ctx.fiber / ctx.registry / ctx.reflect / ctx.events / ctx.logger', summary: 'Ambient handles onto the running context graph.' },
+  { name: 'ctx.timer (+ interval / timeout / throttle / debounce / setTimeout / setInterval)', summary: 'Disposable timer helpers. The `timer` key is provided at runtime; the six helpers are mixed onto ctx directly (declared via Pick).' },
+  { name: 'ctx.loader', summary: 'The config Loader that booted the app (present under the loader).' },
+  { name: 'ctx.hmr', summary: 'The hot-module-reload watcher (present under the hmr plugin).' },
+]

packages/cordis/tool-cordis/src/fiber-state.ts

@@ -0,0 +1,39 @@
+/**
+ * Runtime mirror of the cordis `FiberState` const enum plus human-readable
+ * labels, shared by the mount lifecycle (state reporting) and the inspect
+ * renderers (plugin-list and mount-table labels).
+ *
+ * Cordis exposes `FiberState` as a `const enum`: there is no runtime object for
+ * Node's type-stripping runner to import, so the members are mirrored here as
+ * values — each typed (via the type-only import) as the cordis enum member it
+ * mirrors, so enum-typed reads like `fiber.state` compare against them under a
+ * shared enum type. Source of truth: vendor/cordis/src/fiber.ts (pinned; drift
+ * only happens through a deliberate vendor sync).
+ *
+ * @module @deepseek-ai/dsh-tool-cordis/fiber-state
+ */
+
+import type { FiberState as FiberStateEnum } from 'cordis'
+
+/** Value mirror of the cordis `FiberState` const enum (see the module doc for why a mirror exists). */
+export const FiberState = {
+  PENDING: 0 as FiberStateEnum.PENDING,
+  LOADING: 1 as FiberStateEnum.LOADING,
+  ACTIVE: 2 as FiberStateEnum.ACTIVE,
+  FAILED: 3 as FiberStateEnum.FAILED,
+  DISPOSED: 4 as FiberStateEnum.DISPOSED,
+  UNLOADING: 5 as FiberStateEnum.UNLOADING,
+} as const
+
+/** The cordis `FiberState` enum type, re-exported so mirror consumers need one import. */
+export type FiberState = FiberStateEnum
+
+/** Human-readable label for each {@link FiberState}, keyed by member (inlining-safe — no reverse mapping). */
+export const STATE_LABELS: Record<FiberState, string> = {
+  [FiberState.PENDING]: 'pending',
+  [FiberState.LOADING]: 'loading',
+  [FiberState.ACTIVE]: 'active',
+  [FiberState.FAILED]: 'failed',
+  [FiberState.DISPOSED]: 'disposed',
+  [FiberState.UNLOADING]: 'unloading',
+}

packages/cordis/tool-cordis/src/guard.ts

@@ -0,0 +1,447 @@
+/**
+ * The registration boundary between sandboxed mount code and the real runtime:
+ * SchemaSpec normalization + validation with teaching errors, the
+ * marker-guarded `harness.defineTool` / `harness.registerTool` pair, the
+ * SANDBOX CONTEXT FAÇADE a mounted plugin's `apply` receives in place of the
+ * real `ctx`, and the plugin-shape helpers the mount lifecycle narrows sandbox
+ * return values with.
+ *
+ * The façade is a WHITELIST, not a pass-through proxy. Mount code needs to do
+ * exactly four things — register a tool, listen to an event, provide a service,
+ * call an injected service (timers included) — so the façade exposes only those
+ * verbs and the injected services, each object-valued service individually
+ * wrapped (a primitive provided value passes through as-is — see
+ * {@link sandboxContext}). Every framework plumbing member (`root`, `parent`, `scope`, `fiber`, `reflect`, `registry`,
+ * `events`, `extend`, `isolate`, `intercept`, `plugin`, `set`, `mixin`, …) is
+ * DENIED with a teaching error rather than passed through. This closes an
+ * entire escape class at once: a pass-through proxy that only special-cased
+ * `ctx.tools` still handed back the raw context through `ctx.root`,
+ * `ctx.extend()`, or a service instance's `.ctx`, and mount code could then
+ * `ctx.root.tools.register({…})` to bypass the marker check and host-realm
+ * normalization — a raw vm-realm result then errors a real agent turn at the
+ * session-log plainness check. The whitelist has no such hole: there is no
+ * context-valued member to reach, and any injected-service method that returns
+ * a `Context` is rejected (harness services never do — see {@link denyContext}).
+ *
+ * Two realm facts drive the tool path. Objects built inside the vm carry the vm
+ * realm's `Object.prototype`, and the session log's append-time plainness check
+ * (`dsh-session`'s `isJsonValue`, a prototype-identity comparison) rejects
+ * foreign-realm data — so every dynamic tool's `execute` return is JSON
+ * round-tripped into the host realm and shape-checked against the two
+ * `ToolExecuteReturn` forms before it reaches the registry (the registry
+ * trusts the shape blindly — it spreads `result.content`, so an unvalidated
+ * `{ content: 'ok' }` would enter the session log as `['o','k']` and silently
+ * corrupt the next model request), and the schema itself is rebuilt as fresh
+ * host-realm objects. And a malformed tool
+ * schema must fail at REGISTRATION, not when a later request assembles it — so
+ * dynamic tool registration accepts only definitions produced by the sandbox's
+ * `harness.defineTool`, which normalizes `parameters` up front.
+ *
+ * Normalize, don't lecture, where the input has exactly one meaning: models
+ * write the JSON-Schema dialect by strong prior (the `{ type: 'object',
+ * properties, required: […] }` wrapper, `type: 'integer'`, `required: false`),
+ * and each rejection costs a model turn — so those convert to the SchemaSpec
+ * DSL silently, and only genuinely meaningless input (an unknown type, a
+ * non-boolean `required`) is rejected, with the error enumerating the valid
+ * vocabulary.
+ *
+ * @module @deepseek-ai/dsh-tool-cordis/guard
+ */
+
+import { Context } from 'cordis'
+import type { Plugin } from 'cordis'
+import { defineTool } from '@deepseek-ai/dsh-tools'
+import type { ToolDefinition, ToolExecuteReturn } from '@deepseek-ai/dsh-tools'
+
+const DYNAMIC_TOOL = Symbol('tool-cordis.dynamic-tool')
+const SCHEMA_TYPES = new Set<unknown>(['string', 'number', 'boolean', 'object', 'array'])
+const VALID_TYPES = '\'string\' | \'number\' | \'boolean\' | \'object\' | \'array\''
+
+type DynamicToolDefinition = ToolDefinition & { [DYNAMIC_TOOL]: true }
+type DynamicToolMarker = { [DYNAMIC_TOOL]?: unknown }
+
+function isPlainRecord(value: unknown): value is Record<string, unknown> {
+  return Object.prototype.toString.call(value) === '[object Object]'
+}
+
+/**
+ * Normalize a sandbox-provided `parameters` value into a fresh host-realm
+ * SchemaSpec. Accepts the DSL directly, or the JSON-Schema-style
+ * `{ type: 'object', properties, required: […] }` wrapper models write by
+ * prior — the wrapper unwraps and its `required` array becomes per-property
+ * flags (see the module doc).
+ */
+function normalizeSchemaSpec(value: unknown, path = 'parameters'): Record<string, unknown> {
+  if (!isPlainRecord(value)) {
+    throw new Error(`harness.defineTool ${path} must be a SchemaSpec object`)
+  }
+  let entries = value
+  const requiredNames = new Set<unknown>()
+  if (value.type === 'object' && isPlainRecord(value.properties)) {
+    if (Array.isArray(value.required)) {
+      for (const name of value.required) requiredNames.add(name)
+    }
+    entries = value.properties
+  }
+  const spec: Record<string, unknown> = {}
+  for (const [key, prop] of Object.entries(entries)) {
+    spec[key] = normalizeSchemaProp(prop, `${path}.${key}`, requiredNames.has(key))
+  }
+  return spec
+}
+
+/** Normalize one property: `integer` → `number`, `required: false` → absent, nested wrappers unwrapped recursively. */
+function normalizeSchemaProp(value: unknown, path: string, forceRequired = false): Record<string, unknown> {
+  if (!isPlainRecord(value)) {
+    throw new Error(`harness.defineTool ${path} must be a SchemaSpec property object`)
+  }
+  const type = value.type === 'integer' ? 'number' : value.type
+  if (!SCHEMA_TYPES.has(type)) {
+    throw new Error(`harness.defineTool ${path} must declare a valid type: ${VALID_TYPES} (got ${JSON.stringify(value.type)})`)
+  }
+  // On an object property a JSON-Schema-style `required` ARRAY names required
+  // children (handled by the nested unwrap below); everywhere else `required`
+  // must be a boolean, and `false` simply reads as optional.
+  const nestedRequiredArray = type === 'object' && Array.isArray(value.required)
+  if (value.required !== undefined && typeof value.required !== 'boolean' && !nestedRequiredArray) {
+    throw new Error(`harness.defineTool ${path}.required must be a boolean when present`)
+  }
+  const prop: Record<string, unknown> = { type }
+  if (forceRequired || value.required === true) prop.required = true
+  if (typeof value.description === 'string') prop.description = value.description
+  if (Array.isArray(value.enum)) prop.enum = [...value.enum as unknown[]]
+  if (value.default !== undefined) prop.default = value.default
+  if (value.properties !== undefined) {
+    if (type !== 'object') {
+      throw new Error(`harness.defineTool ${path}.properties is only valid for type "object"`)
+    }
+    // Re-wrap so the nested unwrap applies a nested `required` array too.
+    prop.properties = normalizeSchemaSpec(
+      { type: 'object', properties: value.properties, required: value.required },
+      `${path}.properties`,
+    )
+  }
+  if (value.items !== undefined) {
+    if (type !== 'array') {
+      throw new Error(`harness.defineTool ${path}.items is only valid for type "array"`)
+    }
+    prop.items = normalizeSchemaProp(value.items, `${path}.items`)
+  }
+  return prop
+}
+
+function markDynamicTool(tool: ToolDefinition): DynamicToolDefinition {
+  Object.defineProperty(tool, DYNAMIC_TOOL, { value: true })
+  return tool as DynamicToolDefinition
+}
+
+function assertDynamicTool(tool: unknown): asserts tool is DynamicToolDefinition {
+  if (!isPlainRecord(tool) || (tool as DynamicToolMarker)[DYNAMIC_TOOL] !== true) {
+    throw new Error('dynamic tool registration must use a tool returned by harness.defineTool(...)')
+  }
+}
+
+/**
+ * Structurally a content block, checked AFTER the JSON round-trip: a plain
+ * object carrying a string `type` tag. Deliberately nothing deeper — the
+ * ContentBlock union is merge-extensible (an unknown tag must pass), and every
+ * downstream consumer dispatches on `type` and falls through unknowns.
+ */
+function isContentBlockShape(value: unknown): boolean {
+  return isPlainRecord(value) && typeof value.type === 'string'
+}
+
+/**
+ * How much of an invalid execute return the teaching error echoes back — a
+ * huge blob would burn the model turn the error is trying to save.
+ */
+const RETURN_PREVIEW_LIMIT = 120
+
+/**
+ * Compact JSON preview of an invalid execute return for the teaching error
+ * (`String(…)` for the un-stringifiable undefined case), truncated to
+ * {@link RETURN_PREVIEW_LIMIT}.
+ */
+function describeReturn(value: unknown): string {
+  // JSON.stringify is TYPED as always returning string, but it yields
+  // undefined for an undefined input (the routed forgot-return case) — the
+  // assertion widens the type back to the runtime truth.
+  const json = JSON.stringify(value) as string | undefined
+  if (json === undefined) return String(value)
+  return json.length > RETURN_PREVIEW_LIMIT ? `${json.slice(0, RETURN_PREVIEW_LIMIT)}…` : json
+}
+
+/**
+ * Validate a round-tripped `execute` return against the two shapes
+ * {@link ToolExecuteReturn} allows: an ARRAY of content blocks, or
+ * `{ content: blocks, meta? }`. The registry trusts the shape blindly — it
+ * spreads `result.content`, so an unvalidated `{ content: 'ok' }` would enter
+ * the session log as `['o','k']` and silently corrupt the next model request —
+ * so a wrong shape fails THIS call with a teaching error instead.
+ */
+function assertExecuteReturn(value: unknown): ToolExecuteReturn {
+  if (Array.isArray(value) && value.every(isContentBlockShape)) {
+    return value as ToolExecuteReturn
+  }
+  if (isPlainRecord(value) && Array.isArray(value.content) && value.content.every(isContentBlockShape)) {
+    return value as ToolExecuteReturn
+  }
+  throw new Error(
+    `execute returned ${describeReturn(value)} — a tool's execute must return an ARRAY of content blocks, never a bare string:\n`
+    + '  ✓ return [{ type: \'text\', text: someString }]\n'
+    + '  ✓ return { content: [{ type: \'text\', text: someString }], meta: anyJsonValue }',
+  )
+}
+
+/**
+ * The `harness.defineTool` handed into the sandbox: the real DSL, with
+ * `parameters` normalized into a fresh host-realm SchemaSpec (JSON-Schema
+ * wrapper unwrapped, `integer` mapped, `required: false` dropped) and the
+ * tool's `execute` return normalized into the host realm via a JSON round-trip
+ * (see the module doc). The round-trip projects the return onto exactly what
+ * the log would durably store, and {@link assertExecuteReturn} then vets that
+ * projection — so a non-JSON-serializable OR wrong-shape return surfaces as
+ * that one call's teaching error instead of poisoning the turn.
+ * @param options - the standard `defineTool` options; `parameters` may be the SchemaSpec DSL or a JSON-Schema-style wrapper.
+ * @returns the marker-tagged definition `harness.registerTool` (and the guarded `ctx.tools.register`) accepts.
+ */
+export function sandboxDefineTool(options: Parameters<typeof defineTool>[0]): ToolDefinition {
+  const parameters = normalizeSchemaSpec((options as { parameters?: unknown }).parameters)
+  const tool = defineTool({ ...options, parameters } as Parameters<typeof defineTool>[0])
+  const execute = tool.execute.bind(tool)
+  return markDynamicTool({
+    ...tool,
+    async execute(args, exec) {
+      // JSON.stringify yields NO JSON for an undefined (or function/symbol)
+      // return despite its string-typed signature — route that into
+      // assertExecuteReturn's teaching error rather than letting JSON.parse
+      // throw its cryptic '"undefined" is not valid JSON'.
+      const json = JSON.stringify(await execute(args, exec)) as string | undefined
+      return assertExecuteReturn(json === undefined ? undefined : JSON.parse(json) as unknown)
+    },
+  })
+}
+
+/**
+ * The `harness.registerTool` handed into the sandbox: registers a
+ * marker-verified dynamic tool on the given context's registry.
+ * @param ctx - the (guarded) context whose `tools` service receives the tool.
+ * @param tool - a definition produced by {@link sandboxDefineTool}; anything else is rejected.
+ * @returns the registry disposer for the registration.
+ */
+export function sandboxRegisterTool(ctx: Context, tool: unknown): () => void {
+  assertDynamicTool(tool)
+  return ctx.tools.register(tool)
+}
+
+/**
+ * The verbs a mounted plugin may reach through the sandbox `ctx` façade,
+ * beyond its injected services. `on`/`once` observe events, `provide` exposes
+ * a service to other mounts, and the timer helpers schedule work — each a
+ * fiber effect that unwinds on unmount. Everything else on a real cordis `ctx`
+ * is framework plumbing and is denied. Forwarded LAZILY: the timer helpers are
+ * mixin accessors that throw `without inject` when read on a plugin that did
+ * not inject `timer`, so the façade reads `ctx[verb]` only at call time — the
+ * plugin that never touches a timer never trips that, and one that does gets
+ * cordis's own inject error at the call site.
+ */
+const CTX_VERBS = new Set(['on', 'once', 'provide', 'timeout', 'interval', 'setTimeout', 'setInterval', 'throttle', 'debounce'])
+
+/**
+ * The tool-registry façade: `register` (marker-guarded) plus READ-ONLY
+ * metadata (`schemas`, and `get` returning a schema view, never the live
+ * `ToolDefinition`). Exposing the raw definition would hand mount code the
+ * tool's `execute` function, letting it call another tool directly and bypass
+ * `ToolRegistry.execute` — the pre/post-execute waterfall (permission gates,
+ * accounting) and result normalization. So `get` returns the same
+ * name/description/parameters view as `schemas()`, and nothing invocable.
+ */
+function sandboxTools(ctx: Context): Record<string, unknown> {
+  return {
+    register: (tool: unknown): (() => void) => sandboxRegisterTool(ctx, tool),
+    schemas: () => ctx.tools.schemas(),
+    get: (name: string) => ctx.tools.schemas().find(schema => schema.name === name),
+  }
+}
+
+/**
+ * Reject any injected-service return that is a cordis `Context`. Harness
+ * services return data, never a context; a value that is one would be a
+ * fresh, unguarded handle back into the runtime — the exact escape the façade
+ * exists to close — so it fails loud instead of reaching sandbox code.
+ */
+function denyContext(value: unknown, service: string): unknown {
+  if (value instanceof Context) {
+    throw new Error(
+      `service "${service}" returned a cordis Context, which the sandbox does not expose. `
+      + 'Operate through your own plugin ctx (ctx.on / ctx.provide / ctx.tools.register) '
+      + 'and the services you inject — never another context.',
+    )
+  }
+  return value
+}
+
+/**
+ * Wrap an injected service so its methods forward to the real instance but
+ * their return values pass through {@link denyContext}. Non-function members
+ * (plain data) pass through as-is; a returned Promise is guarded on resolve.
+ */
+function guardedService(service: object, name: string): unknown {
+  return new Proxy(service, {
+    get(target, prop) {
+      const value = Reflect.get(target, prop, target) as unknown
+      if (typeof value !== 'function') return denyContext(value, name)
+      return (...args: unknown[]): unknown => {
+        const result = Reflect.apply(value, target, args) as unknown
+        if (result instanceof Promise) return result.then(v => denyContext(v, name))
+        return denyContext(result, name)
+      }
+    },
+  })
+}
+
+/**
+ * The service names a plugin declared in `inject`, as a lookup set. Whatever
+ * declaration style the plugin used — an `inject: ['bash', 'tools']` array or
+ * the `{ required, optional }` object form — cordis resolves it into a single
+ * name-keyed map on the fiber before `apply` runs (`{ bash: null, tools: null }`),
+ * so the gate just reads that map's keys. A mount may reach only the services
+ * it declared — that is what lets cordis park the mount when a declared
+ * provider unmounts.
+ */
+function declaredInjects(ctx: Context): Set<string> {
+  return new Set(Object.keys(ctx.fiber.inject))
+}
+
+/**
+ * The sandbox context façade handed to a mounted plugin's `apply` in place of
+ * the real `ctx`. A whitelist (see the module doc): the registration/eventing
+ * verbs, the timer helpers, a guarded `tools`, and injected services resolved
+ * through a guarded `get` / property access. A service is reachable only if the
+ * plugin DECLARED it in `inject` — an undeclared service is denied even when a
+ * global provider exists, so cordis's activation/unload semantics (park the
+ * mount when a declared provider goes away) actually bind. Every
+ * framework-plumbing member is denied with a teaching error; there is no
+ * context-valued member to reach.
+ */
+function sandboxContext(ctx: Context): Context {
+  const tools = sandboxTools(ctx)
+  const declared = declaredInjects(ctx)
+  // A framework member or an undeclared service — distinguish the two so the
+  // error teaches the right fix (declare it in inject vs it is withheld).
+  const denyRead = (prop: string): never => {
+    if (ctx.get(prop) !== undefined) {
+      throw new Error(
+        `service "${prop}" is not injected. Declare it: inject: ['${prop}', …] on your plugin, `
+        + 'so cordis parks this mount if the provider is later unmounted.',
+      )
+    }
+    throw new Error(
+      `sandbox ctx does not expose "${prop}". Available: ctx.tools.register / ctx.on / ctx.provide / `
+      + 'the timer helpers (ctx.setTimeout, ctx.interval, …) and any service you declared in inject. '
+      + 'Framework internals (root, fiber, registry, extend, plugin, …) are withheld by design.',
+    )
+  }
+  // Read a service for either access path (property or `get`). `tools` is the
+  // façade's own surface. An UNDECLARED name is denied with the teaching
+  // error; a DECLARED one resolves to the guarded service. A declared inject
+  // is required in cordis (the fiber only activates once every declared
+  // service is live), so at `apply`/`execute` time `ctx.get(name)` is present
+  // for a declared name — no undefined case to handle here. `provide()`
+  // accepts ANY value though (cross-mount composition advertises
+  // `ctx.provide('name', value)`), so a primitive or null value passes
+  // through unwrapped: Proxy throws on a non-object target, and only an
+  // object can carry a method that hands back a Context.
+  const readService = (name: string): unknown => {
+    if (name === 'tools') return tools
+    if (!declared.has(name)) return denyRead(name)
+    const service = denyContext(ctx.get(name), name)
+    if (service === null || (typeof service !== 'object' && typeof service !== 'function')) return service
+    return guardedService(service, name)
+  }
+  const get = (name: string): unknown => readService(name)
+  return new Proxy({}, {
+    get(_target, prop) {
+      if (prop === 'tools') return tools
+      if (prop === 'get') return get
+      if (typeof prop !== 'string') return undefined
+      // Lazy verb forwarder — reads `ctx[verb]` only when called, so a plugin
+      // that never uses a timer never triggers the timer mixin's inject check
+      // (cordis raises its own "without inject" error there for undeclared timer use).
+      if (CTX_VERBS.has(prop)) {
+        return (...args: unknown[]): unknown => {
+          const method = ctx[prop as keyof Context]
+          return Reflect.apply(method as (...a: unknown[]) => unknown, ctx, args)
+        }
+      }
+      return readService(prop)
+    },
+    // A façade is not the real ctx; block writes rather than let mount code
+    // stash state on a throwaway object and think it persisted.
+    set(_target, prop) {
+      throw new Error(`sandbox ctx is read-only; cannot assign "${String(prop)}"`)
+    },
+    // `in` reflects reachability: the façade surface plus DECLARED services
+    // (whether or not currently live). Does not resolve/wrap — no throw.
+    has: (_target, prop) => prop === 'tools' || prop === 'get'
+      || (typeof prop === 'string' && (CTX_VERBS.has(prop) || declared.has(prop))),
+  }) as unknown as Context
+}
+
+/**
+ * Narrow an arbitrary sandbox return value to a mountable cordis plugin: a
+ * function, or an object with an `apply` function. (A bare function passes the
+ * first arm, so the object arm never sees `Function.prototype.apply`.)
+ * @param value - whatever the mount code returned.
+ * @returns whether the value is mountable via `ctx.plugin`.
+ */
+export function isPlugin(value: unknown): value is Plugin {
+  if (typeof value === 'function') return true
+  return typeof value === 'object' && value !== null
+    && typeof (value as { apply?: unknown }).apply === 'function'
+}
+
+/**
+ * Wrap a plugin so its `apply` receives the sandbox context façade instead of
+ * the real `ctx` (see {@link sandboxContext} and the module doc). Both
+ * function-form and object-form plugins go through the same wrap; the plugin's
+ * own `inject` declaration is preserved (cordis reads it from the plugin
+ * object, and pending/active gating happens on the real fiber before `apply`
+ * runs), so cross-mount provide/inject works unmodified.
+ *
+ * `ctx.effect(customCleanup)` is deliberately absent from the façade for now —
+ * `on` / `provide` / `tools.register` cover every mount seen so far, and each
+ * is already a fiber effect. FIXME(sandbox-effect): expose a guarded `effect`
+ * once a real mount needs a bespoke disposer.
+ * @param plugin - the plugin the mount code returned.
+ * @returns an equivalent plugin whose `apply` sees the sandbox context façade.
+ */
+export function guardedPlugin(plugin: Plugin): Plugin {
+  if (typeof plugin === 'function') {
+    const functionPlugin = plugin as (ctx: Context, config?: unknown) => unknown
+    return {
+      name: pluginName(plugin),
+      apply(ctx: Context, config?: unknown) {
+        return functionPlugin(sandboxContext(ctx), config)
+      },
+    }
+  }
+  const objectPlugin = plugin as { apply(ctx: Context, config?: unknown): unknown }
+  return {
+    ...plugin,
+    apply(ctx: Context, config?: unknown) {
+      return objectPlugin.apply(sandboxContext(ctx), config)
+    },
+  }
+}
+
+/**
+ * Display name for a mounted plugin: its `name` property, else anonymous.
+ * @param plugin - the plugin the mount code returned.
+ * @returns the human-readable name used in mount results and inspect output.
+ */
+export function pluginName(plugin: Plugin): string {
+  const named = (plugin as { name?: unknown }).name
+  if (typeof named === 'string' && named.length > 0) return named
+  return '<anonymous>'
+}

packages/cordis/tool-cordis/src/index.ts

@@ -0,0 +1,236 @@
+/**
+ * The self-referential cordis toolset: three model-facing tools that let the
+ * agent inspect and MODIFY the live cordis runtime it is running inside.
+ *
+ * - `cordis_inspect` — read-only: provided services, the flat plugin list
+ *   with lifecycle states, registered tools, the dynamic mounts, and the
+ *   catalog-backed `api` / `events` references.
+ * - `cordis_mount` — evaluate model-written code in a `node:vm` sandbox; the
+ *   code returns a cordis plugin, which is mounted as a child of a dedicated
+ *   `cordis-dynamic` group fiber and tracked under an id (`dyn-1`, `dyn-2`, …).
+ * - `cordis_unmount` — dispose one dynamic mount by id, awaiting quiescence.
+ *
+ * Everything the model's plugin registers (listeners via `ctx.on`, tools via
+ * `harness.registerTool`, services via `ctx.provide`) is an effect on the
+ * dynamic fiber, so unmounting — or disposing this plugin itself (HMR) — cleans
+ * it all up through the ordinary cordis lifecycle. The group fiber exists
+ * exactly so the dynamic mounts form ONE subtree, disposed as a unit with
+ * this plugin. Design home:
+ * docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md.
+ *
+ * The vm sandbox guards against ACCIDENTAL global pollution only, and the `ctx`
+ * a mounted plugin's `apply` receives is a WHITELIST façade (register a tool,
+ * observe events, provide/consume services, use timers — framework internals
+ * withheld; see the guard module). Neither is a security boundary: the verbs
+ * the façade DOES expose reach the real runtime unsandboxed (a mounted tool can
+ * shell out through `ctx.bash`), so a deployment loads this plugin as
+ * deliberately as it grants a bash tool. Design home:
+ * docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md.
+ *
+ * Plugin export shape: named exports, NO default. The cordis Loader's
+ * `unwrapExports` does `exports.default ?? exports`, so a stray default would
+ * collapse the module to the bare `apply` and drop `inject`, crashing at load
+ * (see docs/postmortem/0001).
+ *
+ * @module @deepseek-ai/dsh-tool-cordis
+ */
+
+import type { Context } from 'cordis'
+import z from 'schemastery'
+import { defineTool } from '@deepseek-ai/dsh-tools'
+import { STATE_LABELS } from './fiber-state.ts'
+import { isPlugin, pluginName } from './guard.ts'
+import { describeApi, describeDynamic, describeEvents, describePlugins, describeServices, describeTools } from './inspect.ts'
+import { missingServices, mountDynamic } from './mount.ts'
+import type { DynamicMount } from './mount.ts'
+import { presentInspectCall, presentMountCall, presentUnmountCall } from './present.ts'
+import { createSandbox, evaluateMountCode } from './sandbox.ts'
+
+export const name = 'tool-cordis'
+export const inject = ['tools']
+
+/** Config for the tool-cordis plugin: the sandbox evaluation bound. */
+export interface Config {
+  /**
+   * Milliseconds the SYNCHRONOUS portion of mount code may run in the vm
+   * before evaluation is aborted (default 5000). An async body escapes this
+   * bound — see docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md for the trust stance.
+   */
+  vmTimeoutMs?: number
+}
+
+/** Schemastery validator for {@link Config}: `vmTimeoutMs` must be at least 1 (defaults to 5000). */
+export const Config: z<Config> = z.object({
+  vmTimeoutMs: z.number().min(1).default(5000),
+})
+
+/** {@link Config} with every defaulted field present, as schemastery resolves it at load. */
+type ResolvedConfig = Required<Config>
+
+/**
+ * Mount the three cordis tools on `ctx.tools` and create the `cordis-dynamic`
+ * group fiber every dynamic mount hangs under.
+ * @param ctx - the plugin context (`tools` injected).
+ * @param config - the schemastery-resolved {@link Config}.
+ */
+export function apply(ctx: Context, config: Config): void {
+  const { vmTimeoutMs } = config as ResolvedConfig
+  // The one group fiber every dynamic mount hangs under. Mounted here (a child
+  // of this plugin's fiber) so disposing tool-cordis cascades over the whole
+  // dynamic subtree — the ordinary parent→child fiber lifecycle, nothing extra.
+  const group = ctx.plugin({ name: 'cordis-dynamic', apply: () => {} })
+
+  const mounts = new Map<string, DynamicMount>()
+  let nextId = 1
+
+  ctx.tools.register(defineTool({
+    name: 'cordis_inspect',
+    description:
+      'Inspect the live cordis runtime that is running THIS agent. Read-only. '
+      + 'Sections: `services` (every provided ctx service and the plugin fiber that owns it), '
+      + '`plugins` (a flat list of the loaded plugins with their lifecycle states), '
+      + '`tools` (the model-facing tools currently registered, i.e. what you can call), '
+      + '`dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), '
+      + '`api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), '
+      + '`events` (every harness event with its dispatch mode and exact signature — pick listener targets here). '
+      + 'Omit `what` to get all six sections.',
+    parameters: {
+      what: {
+        type: 'string',
+        enum: ['services', 'plugins', 'tools', 'dynamic', 'api', 'events'],
+        description: 'Limit the report to one section. Omit for all sections.',
+      },
+    },
+    execute(args): Promise<{ type: 'text'; text: string }[]> {
+      const sections: [heading: string, body: () => string[]][] = [
+        ['services', () => describeServices(ctx)],
+        ['plugins', () => describePlugins(ctx)],
+        ['tools', () => describeTools(ctx)],
+        ['dynamic', () => describeDynamic(ctx, mounts)],
+        ['api', () => describeApi(ctx)],
+        ['events', () => describeEvents()],
+      ]
+      const selected = sections.filter(([heading]) => args.what === undefined || args.what === heading)
+      const text = selected
+        .map(([heading, body]) => `## ${heading}\n${body().join('\n')}`)
+        .join('\n\n')
+      return Promise.resolve([{ type: 'text', text }])
+    },
+    presentCall: presentInspectCall,
+  }))
+
+  ctx.tools.register(defineTool({
+    name: 'cordis_mount',
+    description:
+      'Mount a NEW cordis plugin into the live runtime that is running THIS agent '
+      + '(self-modification). `code` runs as the body of an async JavaScript function '
+      + 'in an isolated sandbox and MUST `return` a plugin. Two forms: '
+      + 'FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register '
+      + 'tools, listen to events, and provide services, but reaching ANY service (e.g. '
+      + 'ctx.bash) throws; use it only when you need no services. '
+      + 'OBJECT form `return { name?, inject: [\'bash\', \'llm\', …], apply(ctx) { … } }` '
+      + '— declares dependencies, and cordis activates the plugin only after the '
+      + 'services exist; PREFER this form. You may reach ONLY the services you list in '
+      + 'inject: an undeclared service throws even if it exists, because an undeclared '
+      + 'dependency would not be cleaned up if its provider is unmounted. '
+      + 'BEFORE calling a service from your code, read cordis_inspect what:"api" — it lists '
+      + 'method signatures AND the type shapes of their arguments/returns (do not guess a '
+      + 'field\'s type; e.g. a bash run\'s stdout is an object, not a string). '
+      + 'Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe '
+      + 'events (see cordis_inspect what:"events"), or call '
+      + '`harness.registerTool(ctx, harness.defineTool({ name, description, parameters: '
+      + '{ text: { type: \'string\', required: true } }, async execute(args) { … } }))` '
+      + 'to give yourself a new tool — it becomes callable on your NEXT step. '
+      + 'Tool parameters: each key IS a property — { type: \'string\'|\'number\'|\'boolean\'|\'object\'|\'array\', '
+      + 'required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style '
+      + '{ type: \'object\', properties, required: […] } wrapper and type \'integer\' are also accepted and normalized. A '
+      + 'tool\'s `execute` MUST return an ARRAY of content blocks, e.g. `return '
+      + '[{ type: \'text\', text: someString }]` — never a bare string. '
+      + 'Mounts can COMPOSE: one plugin may `ctx.provide(\'name\', value)` a service and '
+      + 'another may declare `inject: [\'name\']` to consume it — the consumer stays pending '
+      + 'until the provider exists and returns to pending when the provider is unmounted. '
+      + 'Everything registered inside `apply` is cleaned up automatically on unmount. '
+      + 'Sandbox globals: `console` (tagged `[cordis:<id>]`, writes through to the harness '
+      + 'terminal), `harness.defineTool`, `harness.registerTool`, '
+      + '`btoa`, `atob`, `TextEncoder`, `TextDecoder`. '
+      + 'Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, '
+      + 'never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect '
+      + 'errors; `process` and `Buffer` are undefined. Instead use inject: [\'fs\'] + ctx.fs for '
+      + 'files, inject: [\'web\'] + ctx.web for HTTP, inject: [\'bash\'] + ctx.bash for processes, '
+      + 'and inject: [\'timer\'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, '
+      + 'auto-cleaned on unmount) — cordis_inspect what:"api" shows what THIS runtime provides. '
+      + 'Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). '
+      + 'Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a '
+      + 'trailing `next` callback which MUST be called — returning without `next()` '
+      + 'VETOES the call; prefer plain notification events unless you intend to '
+      + 'intercept. (2) Never await something that only resolves after the current '
+      + 'turn (your code runs INSIDE a tool call of that turn — it would deadlock). '
+      + '(3) Your `ctx` is a restricted façade: you can register tools, observe '
+      + 'events, provide/consume services, and use timers, but framework internals '
+      + '(ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a '
+      + 'security boundary though — the services you inject (e.g. ctx.bash) reach the '
+      + 'real runtime.',
+    parameters: {
+      code: {
+        type: 'string',
+        required: true,
+        description: 'Body of an async JS function; must `return` the plugin to mount.',
+      },
+    },
+    async execute(args) {
+      const id = `dyn-${nextId++}`
+      const sandbox = createSandbox(id)
+      const evaluated = await evaluateMountCode(sandbox, args.code, id, vmTimeoutMs)
+      if (!isPlugin(evaluated)) {
+        if (evaluated === undefined) {
+          throw new Error(
+            'mount code returned `undefined` — did you forget `return`?\n'
+            + '  ✓ return (ctx) => { … }\n'
+            + '  ✓ return { name: \'…\', inject: […], apply(ctx) { … } }',
+          )
+        }
+        throw new Error(
+          'mount code must `return` a plugin: a function, or an object with an `apply(ctx)` method',
+        )
+      }
+      const fiber = await mountDynamic(group, evaluated)
+      mounts.set(id, { fiber, pluginName: pluginName(evaluated) })
+      // A settled fiber that is not ACTIVE is waiting on unsatisfied inject —
+      // legal cordis semantics (it activates when the service appears), so keep
+      // it mounted but tell the model what it is waiting for.
+      const missing = missingServices(ctx, fiber)
+      const state = STATE_LABELS[fiber.state]
+      const note = missing.length > 0
+        ? ` — waiting for service(s): ${missing.join(', ')} (activates when provided)`
+        : ''
+      return [{ type: 'text', text: `mounted ${id} (plugin "${pluginName(evaluated)}", state: ${state}${note})` }]
+    },
+    presentCall: presentMountCall,
+  }))
+
+  ctx.tools.register(defineTool({
+    name: 'cordis_unmount',
+    description:
+      'Dispose a plugin previously mounted with cordis_mount, by id. All its '
+      + 'registrations (event listeners, tools, services) are cleaned up through '
+      + 'the cordis effect lifecycle. Returns only after disposal has fully '
+      + 'completed (quiescence, not just a request to stop).',
+    parameters: {
+      id: {
+        type: 'string',
+        required: true,
+        description: 'The dynamic mount id returned by cordis_mount (e.g. "dyn-1").',
+      },
+    },
+    async execute(args) {
+      const mount = mounts.get(args.id)
+      if (!mount) {
+        throw new Error(`no dynamic plugin with id "${args.id}" (list mounts with cordis_inspect what:"dynamic")`)
+      }
+      await mount.fiber.dispose()
+      mounts.delete(args.id)
+      return [{ type: 'text', text: `unmounted ${args.id} (plugin "${mount.pluginName}")` }]
+    },
+    presentCall: presentUnmountCall,
+  }))
+}

packages/cordis/tool-cordis/src/inspect.ts

@@ -0,0 +1,191 @@
+/**
+ * Read-only renderers over the live runtime for `cordis_inspect`: the service
+ * list, the flat plugin list, the registered tools, the dynamic-mount
+ * table (with per-mount provides/waits), and the catalog-backed `api` /
+ * `events` sections. Every renderer is a pure function of the runtime handles
+ * it receives — no session state, no clock — so inspect output is exactly the
+ * runtime it describes.
+ *
+ * @module @deepseek-ai/dsh-tool-cordis/inspect
+ */
+
+import type { Context, Fiber } from 'cordis'
+import { EVENT_API, INHERITED_CTX_API, SERVICE_API, TYPE_API } from './api-catalog.ts'
+import type { EventApiEntry, InheritedApiEntry, ServiceApiEntry, TypeApiEntry } from './api-catalog.ts'
+import { FiberState, STATE_LABELS } from './fiber-state.ts'
+import { missingServices } from './mount.ts'
+import type { DynamicMount } from './mount.ts'
+
+/** The live service registrations from `ctx.reflect.store` (map + filter keeps the possibly-undefined index read branch-free). */
+function liveImpls(ctx: Context): { name: string; fiber: Fiber }[] {
+  const store = ctx.reflect.store
+  return Object.getOwnPropertySymbols(store)
+    .map(key => store[key])
+    .filter((impl): impl is NonNullable<typeof impl> => impl !== undefined)
+}
+
+/** Whether `fiber` is `root` itself or mounted anywhere inside `root`'s subtree. */
+function withinFiber(fiber: Fiber, root: Fiber): boolean {
+  let current = fiber
+  while (true) {
+    if (current === root) return true
+    const parent = current.parent.fiber
+    if (parent === current) return false
+    current = parent
+  }
+}
+
+/** The service names provided by a mount's fiber subtree, sorted. */
+function providedBy(ctx: Context, fiber: Fiber): string[] {
+  return liveImpls(ctx)
+    .filter(impl => withinFiber(impl.fiber, fiber))
+    .map(impl => impl.name)
+    .sort()
+}
+
+/**
+ * The `services` section: every provided ctx service with its owning fiber,
+ * annotating non-active owners with their lifecycle state.
+ * @param ctx - the runtime to enumerate.
+ * @returns one line per service, or a single placeholder line when none are provided.
+ */
+export function describeServices(ctx: Context): string[] {
+  const lines = liveImpls(ctx).map((impl) => {
+    const active = impl.fiber.state === FiberState.ACTIVE
+    return `- ${impl.name} (provided by ${impl.fiber.name}${active ? '' : `, ${STATE_LABELS[impl.fiber.state]}`})`
+  })
+  return lines.length > 0 ? lines : ['(no services provided)']
+}
+
+/**
+ * The `plugins` section: a flat list of every fiber the registry knows, one
+ * line per fiber with its lifecycle state, sorted by plugin name (a plugin
+ * mounted more than once repeats — one line per instance). Dynamic mounts are
+ * listed like any other plugin; their ids live in the `dynamic` section.
+ * @param ctx - the runtime whose registry is enumerated.
+ * @returns one line per loaded plugin fiber.
+ */
+export function describePlugins(ctx: Context): string[] {
+  const fibers: Fiber[] = []
+  for (const runtime of ctx.registry.values()) {
+    for (const fiber of runtime.fibers) fibers.push(fiber)
+  }
+  return fibers
+    .sort((a, b) => a.name.localeCompare(b.name))
+    .map(fiber => `- ${fiber.name} [${STATE_LABELS[fiber.state]}]`)
+}
+
+/**
+ * The `tools` section: the model-facing tool names currently registered.
+ * @param ctx - the runtime whose tool registry is read.
+ * @returns one line per registered tool.
+ */
+export function describeTools(ctx: Context): string[] {
+  return ctx.tools.schemas().map(schema => `- ${schema.name}`)
+}
+
+/**
+ * The `dynamic` section: one line per mount with id, plugin name, lifecycle
+ * state, the services its subtree provides, and — for a pending mount — the
+ * services it waits for.
+ * @param ctx - the runtime the mounts live in.
+ * @param mounts - the tracked mounts, in mount order.
+ * @returns one line per mount, or a single placeholder line when none exist.
+ */
+export function describeDynamic(ctx: Context, mounts: ReadonlyMap<string, DynamicMount>): string[] {
+  if (mounts.size === 0) return ['(no dynamic plugins mounted)']
+  return [...mounts].map(([id, mount]) => {
+    const provides = providedBy(ctx, mount.fiber)
+    const waiting = missingServices(ctx, mount.fiber)
+    const providesNote = provides.length > 0 ? ` — provides: ${provides.join(', ')}` : ''
+    const waitingNote = waiting.length > 0 ? ` — waiting for: ${waiting.join(', ')}` : ''
+    return `- ${id}: ${mount.pluginName} [${STATE_LABELS[mount.fiber.state]}]${providesNote}${waitingNote}`
+  })
+}
+
+/**
+ * The transitive closure of catalogued type shapes referenced (word-bounded)
+ * by the seed texts — the runtime scoping that keeps the `api` section to the
+ * shapes the LIVE signatures actually mention.
+ */
+function typeClosure(seeds: string[], types: readonly TypeApiEntry[]): TypeApiEntry[] {
+  const included = new Map<string, TypeApiEntry>()
+  let frontier = seeds
+  while (frontier.length > 0) {
+    const next: string[] = []
+    for (const entry of types) {
+      if (included.has(entry.name)) continue
+      const pattern = new RegExp(`\\b${entry.name}\\b`)
+      if (frontier.some(text => pattern.test(text))) {
+        included.set(entry.name, entry)
+        next.push(entry.declaration)
+      }
+    }
+    frontier = next
+  }
+  return [...included.values()].sort((a, b) => a.name.localeCompare(b.name))
+}
+
+/**
+ * The `api` section: the generated service catalog intersected with the LIVE
+ * runtime — catalogued live services render summary + method signatures, live
+ * services without a catalog entry (e.g. ones another mount provides) render
+ * name + owning fiber, catalog services that are not running are listed
+ * tersely, the type shapes the live signatures reference follow, and the
+ * inherited `ctx` surface closes the section.
+ * @param ctx - the runtime to intersect the catalog with.
+ * @param api - the service catalog (the generated one by default; injectable for tests).
+ * @param inherited - the inherited `ctx` surface lines (generated by default; injectable for tests).
+ * @param types - the type-shape catalog (generated by default; injectable for tests).
+ * @returns the section lines.
+ */
+export function describeApi(
+  ctx: Context,
+  api: readonly ServiceApiEntry[] = SERVICE_API,
+  inherited: readonly InheritedApiEntry[] = INHERITED_CTX_API,
+  types: readonly TypeApiEntry[] = TYPE_API,
+): string[] {
+  const live = new Map<string, string>()
+  for (const impl of liveImpls(ctx)) live.set(impl.name, impl.fiber.name)
+  const lines: string[] = []
+  const liveMethodTexts: string[] = []
+  for (const entry of api) {
+    if (!live.has(entry.key)) continue
+    lines.push(`- ${entry.key} — ${entry.summary}`)
+    for (const method of entry.methods) {
+      lines.push(`    ${method}`)
+      liveMethodTexts.push(method)
+    }
+  }
+  const catalogued = new Set(api.map(entry => entry.key))
+  for (const [name, fiber] of [...live].sort(([a], [b]) => a.localeCompare(b))) {
+    if (!catalogued.has(name)) lines.push(`- ${name} (provided by ${fiber}, no catalog entry)`)
+  }
+  const notRunning = api.filter(entry => !live.has(entry.key)).map(entry => entry.key)
+  if (notRunning.length > 0) lines.push(`not running (loadable services with no live provider): ${notRunning.join(', ')}`)
+  const shapes = typeClosure(liveMethodTexts, types)
+  if (shapes.length > 0) {
+    lines.push('type shapes (referenced by the signatures above — read these before assuming a field is a string):')
+    for (const shape of shapes) {
+      for (const declLine of shape.declaration.split('\n')) lines.push(`    ${declLine}`)
+    }
+  }
+  lines.push('inherited ctx API:')
+  for (const entry of inherited) lines.push(`- ${entry.name} — ${entry.summary}`)
+  return lines
+}
+
+/**
+ * The `events` section: every harness event with its dispatch mode, one-line
+ * summary, and exact signature, closed by the waterfall caution.
+ * @param events - the event catalog (the generated one by default; injectable for tests).
+ * @returns the section lines.
+ */
+export function describeEvents(events: readonly EventApiEntry[] = EVENT_API): string[] {
+  const lines = events.flatMap(event => [
+    `- ${event.name} [${event.mode}] — ${event.summary}`,
+    `    ${event.signature}`,
+  ])
+  lines.push('waterfall listeners receive a trailing next() and MUST call it to delegate — returning without next() vetoes the chain.')
+  return lines
+}

packages/cordis/tool-cordis/src/mount.ts

@@ -0,0 +1,64 @@
+/**
+ * Dynamic-mount lifecycle over the `cordis-dynamic` group fiber: settle a
+ * sandbox-produced plugin as a child fiber (never leaving a failed fiber
+ * mounted), and report the services a settled-but-pending fiber still waits
+ * for. Disposal needs no helper — a mount unwinds through an ordinary awaited
+ * `fiber.dispose()`, because everything the plugin registered is an effect on
+ * its fiber.
+ *
+ * @module @deepseek-ai/dsh-tool-cordis/mount
+ */
+
+import type { Context, Fiber, Plugin } from 'cordis'
+import { guardedPlugin } from './guard.ts'
+
+/** One tracked dynamic mount: the fiber plus the display name captured at mount time. */
+export interface DynamicMount {
+  /** The child fiber under the `cordis-dynamic` group. */
+  fiber: Fiber
+  /** The plugin's display name at mount time (its `name`, else `<anonymous>`). */
+  pluginName: string
+}
+
+/**
+ * Mount a plugin under the group fiber and settle it. The group fiber loads
+ * asynchronously right after the owning plugin's `apply`, so it is awaited
+ * before hanging a child off its context. The child fiber's `await()` settles
+ * its lifecycle work and rethrows a startup error (e.g. a throwing `apply`);
+ * on error the fiber is disposed first — a failed mount never lingers.
+ * @param group - the `cordis-dynamic` group fiber every mount hangs under.
+ * @param plugin - the plugin the sandbox returned; wrapped with the registration guard before mounting.
+ * @returns the settled child fiber (possibly pending on unsatisfied `inject`).
+ */
+export async function mountDynamic(group: Fiber, plugin: Plugin): Promise<Fiber> {
+  await group.await()
+  const fiber = group.ctx.plugin(guardedPlugin(plugin))
+  try {
+    await fiber.await()
+  } catch (error) {
+    await fiber.dispose()
+    const message = error instanceof Error ? error.message : String(error)
+    // The commonest startup collision is remounting a NEW version of a tool
+    // while the old mount still holds the name — teach the replace recipe.
+    if (message.includes('already registered')) {
+      throw new Error(
+        `${message} — to REPLACE something an earlier mount registered, first cordis_unmount that mount's id `
+        + '(find it with cordis_inspect what:"dynamic"), then mount the new version.',
+      )
+    }
+    throw error instanceof Error ? error : new Error(message)
+  }
+  return fiber
+}
+
+/**
+ * The services a fiber declared in `inject` that do not exist yet — a settled
+ * fiber that is not active is waiting on exactly these (legal cordis
+ * semantics: it activates when the service appears).
+ * @param ctx - the context to resolve service existence against.
+ * @param fiber - the mount fiber whose `inject` declarations are checked.
+ * @returns the missing service names, in declaration order.
+ */
+export function missingServices(ctx: Context, fiber: Fiber): string[] {
+  return Object.keys(fiber.inject).filter(service => ctx.get(service) === undefined)
+}

packages/cordis/tool-cordis/src/present.ts

@@ -0,0 +1,51 @@
+/**
+ * ACP render intents for the three cordis tools — all `generic` cards, decided
+ * up front as part of the tool design. Presenters are pure functions of the
+ * call arguments (they run on replay too): no I/O, no session state, no clock.
+ * No `presentResult` overrides exist — the tools' text results are their
+ * correct completed rendering.
+ *
+ * @module @deepseek-ai/dsh-tool-cordis/present
+ */
+
+import type { GenericCallView } from '@deepseek-ai/dsh-tools'
+
+/**
+ * The `cordis_inspect` call card: a read, titled with the requested section.
+ * @param args - the validated call arguments.
+ * @returns the generic card the ACP bridge renders.
+ */
+export function presentInspectCall(args: { what?: string }): GenericCallView {
+  return {
+    card: 'generic',
+    kind: 'read',
+    title: args.what === undefined ? 'Inspect cordis runtime' : `Inspect cordis runtime: ${args.what}`,
+  }
+}
+
+/**
+ * The `cordis_mount` call card: an execute carrying the mount code as raw input.
+ * @param args - the validated call arguments.
+ * @returns the generic card the ACP bridge renders.
+ */
+export function presentMountCall(args: { code: string }): GenericCallView {
+  return {
+    card: 'generic',
+    kind: 'execute',
+    title: 'Mount plugin into live cordis runtime',
+    rawInput: { code: args.code },
+  }
+}
+
+/**
+ * The `cordis_unmount` call card: a delete, titled with the mount id.
+ * @param args - the validated call arguments.
+ * @returns the generic card the ACP bridge renders.
+ */
+export function presentUnmountCall(args: { id: string }): GenericCallView {
+  return {
+    card: 'generic',
+    kind: 'delete',
+    title: `Unmount ${args.id}`,
+  }
+}

packages/cordis/tool-cordis/src/sandbox.ts

@@ -0,0 +1,201 @@
+/**
+ * The `node:vm` sandbox `cordis_mount` code evaluates in: a fresh realm whose
+ * globals are a tagged write-through console, the `harness` registration
+ * helpers, the encoding primitives a bare vm context lacks, and callable traps
+ * over the Node APIs the sandbox deliberately withholds. Capability access is
+ * routed through cordis services, never Node built-ins: filesystem work goes
+ * through `ctx.fs`, network through `ctx.web`, processes through `ctx.bash`,
+ * timers through the `ctx.timer` helpers (fiber effects, unwound on unmount)
+ * — so a well-behaved mount stays inspectable and disposable. That routing is
+ * STEERING toward the cordis services, not containment: the sandbox guards
+ * against ACCIDENTAL global pollution, and it is not a security boundary. The
+ * host-realm helpers on the sandbox global (`harness`, `console`, `btoa`) are
+ * reachable functions, so a mount that goes looking — e.g. through such a
+ * helper's `.constructor` — can still reach the host realm; that is accepted,
+ * because the `ctx` a mounted plugin's `apply` later receives is the real,
+ * fully privileged runtime handle, and that is the point of the toolset.
+ *
+ * @module @deepseek-ai/dsh-tool-cordis/sandbox
+ */
+
+import { createContext, runInContext } from 'node:vm'
+import { sandboxDefineTool, sandboxRegisterTool } from './guard.ts'
+
+/**
+ * A write-through console for one sandbox, tagging every line with the mount
+ * id. Write-through (host stdout/stderr), NOT buffered into the tool result:
+ * a mounted listener fires long after the mount call returned, and its output
+ * must land somewhere the user can see — for the stdio demo, the terminal.
+ */
+function taggedConsole(id: string): Record<'log' | 'info' | 'warn' | 'error' | 'debug', (...args: unknown[]) => void> {
+  const tag = `[cordis:${id}]`
+  const log = (...args: unknown[]): void => { console.log(tag, ...args) }
+  const error = (...args: unknown[]): void => { console.error(tag, ...args) }
+  return { log, info: log, warn: log, debug: log, error }
+}
+
+/**
+ * Per-sandbox prelude: give the vm realm's own constructors a
+ * `Symbol.hasInstance` that checks BOTH realms. Model code runs against a
+ * fresh vm realm, but most objects it touches are HOST-realm (the `args` a
+ * tool's `execute` receives, event payloads a listener observes, service
+ * return values), so a plain `x instanceof Array` / `instanceof Object` in
+ * sandbox code would silently be false. The patch replaces each vm
+ * constructor's own `[Symbol.hasInstance]` with "ordinary check against the
+ * vm constructor OR the host counterpart" — the ordinary algorithm is a pure
+ * prototype-chain walk, so calling it with the host constructor as receiver
+ * needs no host-side change. ONLY vm-realm globals are modified; host
+ * intrinsics are passed in as values and never touched.
+ */
+const DUAL_REALM_INSTANCEOF_PRELUDE = `
+(hostIntrinsics) => {
+  'use strict'
+  const ordinary = Function.prototype[Symbol.hasInstance]
+  for (const name of Object.keys(hostIntrinsics)) {
+    const VmCtor = globalThis[name]
+    const HostCtor = hostIntrinsics[name]
+    if (typeof VmCtor !== 'function' || typeof HostCtor !== 'function') continue
+    Object.defineProperty(VmCtor, Symbol.hasInstance, {
+      value: (instance) => ordinary.call(VmCtor, instance) || ordinary.call(HostCtor, instance),
+      configurable: true,
+    })
+  }
+}
+`
+
+/** Run {@link DUAL_REALM_INSTANCEOF_PRELUDE} in a freshly created sandbox, handing it the host intrinsics to pair up. */
+function patchDualRealmInstanceof(sandbox: object): void {
+  const patch = runInContext(DUAL_REALM_INSTANCEOF_PRELUDE, sandbox) as (intrinsics: Record<string, unknown>) => void
+  patch({ Object, Array, Function, Error, TypeError, RangeError, SyntaxError, Promise, RegExp, Date, Map, Set })
+}
+
+const TIMER_REDIRECT
+  = 'Node timers are unavailable. Use the cordis timer service instead: declare inject: [\'timer\'] on your plugin '
+    + 'and call ctx.setTimeout / ctx.setInterval — those are fiber effects, cleaned up automatically on unmount.'
+
+/**
+ * The callable Node APIs the sandbox deliberately disables, each mapped to the
+ * cordis alternative its trap error names. Only FUNCTION-shaped globals are
+ * trapped — a data-shaped global like `process` stays `undefined`, because a
+ * throwing accessor would detonate the common `typeof process` feature probe
+ * at resolution time.
+ */
+const NODE_API_REDIRECTS: Record<string, string> = {
+  require:
+    'Node modules are unavailable. Use the cordis services on ctx instead — e.g. inject: [\'fs\'] for files, '
+    + '[\'web\'] for HTTP, [\'bash\'] for processes; cordis_inspect what:"api" lists what THIS runtime provides.',
+  setTimeout: TIMER_REDIRECT,
+  setInterval: TIMER_REDIRECT,
+  setImmediate: TIMER_REDIRECT,
+  clearTimeout: TIMER_REDIRECT,
+  clearInterval: TIMER_REDIRECT,
+  fetch:
+    'Network access goes through the cordis web service: declare inject: [\'web\'] and call ctx.web '
+    + '(see cordis_inspect what:"api" for its methods).',
+}
+
+/** Build the trap functions for {@link NODE_API_REDIRECTS}: calling one throws the redirect. */
+function nodeApiTraps(): Record<string, () => never> {
+  const traps: Record<string, () => never> = {}
+  for (const [name, redirect] of Object.entries(NODE_API_REDIRECTS)) {
+    traps[name] = () => {
+      throw new Error(`${name} is not available in the mount sandbox — ${redirect}`)
+    }
+  }
+  return traps
+}
+
+/**
+ * Build the vm context one `cordis_mount` call evaluates in: the tagged
+ * console, the `harness` registration helpers, the encoding primitives, the
+ * Node-API traps, and the dual-realm `instanceof` patch, already
+ * `createContext`-ed.
+ * @param id - the mount id (`dyn-<n>`), used as the console tag and filename stem.
+ * @returns the contextified sandbox object to pass to {@link evaluateMountCode}.
+ */
+export function createSandbox(id: string): object {
+  const sandbox = {
+    ...nodeApiTraps(),
+    console: taggedConsole(id),
+    harness: { defineTool: sandboxDefineTool, registerTool: sandboxRegisterTool },
+    // Web APIs absent from fresh vm contexts — made available so the model
+    // can encode/decode base64 without Buffer (which is also absent). Host
+    // closures over Buffer, never Buffer itself.
+    btoa: (s: string) => Buffer.from(s, 'utf-8').toString('base64'),
+    atob: (s: string) => Buffer.from(s, 'base64').toString('utf-8'),
+    TextEncoder,
+    TextDecoder,
+  }
+  createContext(sandbox)
+  patchDualRealmInstanceof(sandbox)
+  return sandbox
+}
+
+/**
+ * Cross-realm SyntaxError detection: a compile failure inside `runInContext`
+ * constructs its error in the SANDBOX realm, so a host `instanceof
+ * SyntaxError` is silently false — the `name` property is the realm-safe tag.
+ */
+function isSyntaxError(error: unknown): error is Error {
+  return typeof error === 'object' && error !== null && (error as { name?: unknown }).name === 'SyntaxError'
+}
+
+/**
+ * The parse-failure context a vm `SyntaxError` carries: the vm prints the
+ * offending source line and a caret before the message, which is exactly what
+ * a model needs to self-correct — surface it instead of the bare message.
+ * Falls back to `String(error)` when the stack carries no such prelude.
+ * @param error - the `SyntaxError` (host- or sandbox-realm) thrown while compiling mount code.
+ * @returns the stack prefix up to and including the `SyntaxError: …` line.
+ */
+export function syntaxErrorContext(error: Error): string {
+  const lines = (error.stack ?? '').split('\n')
+  const messageIndex = lines.findIndex(line => line.startsWith('SyntaxError'))
+  if (messageIndex === -1) return String(error)
+  return lines.slice(0, messageIndex + 1).join('\n')
+}
+
+/**
+ * Evaluate mount code as the body of an async function inside the sandbox.
+ * `vmTimeoutMs` only bounds the SYNCHRONOUS portion; an async body escapes it
+ * — acceptable under the module's trust stance. A parse failure is answered
+ * with the offending line + caret and a teaching hint: TypeScript syntax on
+ * the failing line gets the remove-annotations fix, anything else gets the
+ * function-body/bracket-balance reminder (models habitually close the returned
+ * plugin object with `});` as if it were a callback argument).
+ * @param sandbox - the contextified object from {@link createSandbox}.
+ * @param code - the model-written function body; must `return` a plugin.
+ * @param id - the mount id, used as the vm filename (`cordis-mount-<id>.js`).
+ * @param vmTimeoutMs - the synchronous evaluation bound in milliseconds.
+ * @returns whatever the code returned, still un-narrowed (the mount lifecycle checks plugin shape).
+ */
+export async function evaluateMountCode(sandbox: object, code: string, id: string, vmTimeoutMs: number): Promise<unknown> {
+  try {
+    return await runInContext(
+      `(async () => {\n${code}\n})()`,
+      sandbox,
+      { filename: `cordis-mount-${id}.js`, timeout: vmTimeoutMs },
+    )
+  } catch (error) {
+    if (!isSyntaxError(error)) throw error
+    const context = syntaxErrorContext(error)
+    // Scope the TypeScript heuristic to the OFFENDING line, not the whole
+    // code: an ` as ` inside an ordinary description string must not turn a
+    // plain syntax error into a misleading remove-annotations message.
+    const offendingLine = context.split('\n')[1] ?? ''
+    if (/\bas\b/.test(offendingLine)) {
+      throw new Error(
+        `mount code failed to parse:\n${context}\n`
+        + 'The sandbox runs plain JavaScript, not TypeScript. Remove type annotations:\n'
+        + '  ✗ { type: \'text\' as const, text: x }\n'
+        + '  ✓ { type: \'text\', text: x }',
+      )
+    }
+    throw new Error(
+      `mount code failed to parse:\n${context}\n`
+      + 'Note: `code` runs as the BODY of an async function (line numbers are offset by the 1-line wrapper). '
+      + 'Check bracket balance — ending the returned plugin object with `});` closes a call that was never opened; '
+      + 'a plain `return { … }` ends with `}` (an optional `;`), never `)`.',
+    )
+  }
+}

packages/cordis/tool-cordis/tests/cross-mount.spec.ts

@@ -0,0 +1,143 @@
+import { describe, expect, it } from 'vitest'
+import { call, CONSUMER_CODE, PROVIDER_CODE, setup, text } from './helpers.ts'
+
+/**
+ * Cross-mount composition through ordinary cordis provide/inject semantics:
+ * one mount provides a service, another injects it, and mount ids stay the
+ * lifecycle handles. Every assertion is against the WORLD — the registry, the
+ * service store, real tool dispatch — not the tool's own summary line.
+ */
+
+describe('cross-mount provide/inject', () => {
+  it('provider first: the consumer activates immediately and its tool reaches the provided service', async () => {
+    const ctx = await setup()
+    const provider = await call(ctx, 'cordis_mount', { code: PROVIDER_CODE })
+    expect(text(provider)).toContain('state: active')
+
+    const consumer = await call(ctx, 'cordis_mount', { code: CONSUMER_CODE })
+    expect(consumer.isError).toBe(false)
+    expect(text(consumer)).toContain('state: active')
+
+    // The vm-realm service value is callable across mounts, and the result
+    // normalizes into the host realm like any dynamic tool result.
+    const greeted = await call(ctx, 'greet', { name: 'harness' })
+    expect(greeted.isError).toBe(false)
+    expect(text(greeted)).toBe('hi harness')
+  })
+
+  it('consumer first: stays pending naming the missing service, then activates when the provider mounts', async () => {
+    const ctx = await setup()
+    const consumer = await call(ctx, 'cordis_mount', { code: CONSUMER_CODE })
+    expect(consumer.isError).toBe(false)
+    expect(text(consumer)).toContain('state: pending')
+    expect(text(consumer)).toContain('waiting for service(s): greeter')
+    expect(text(await call(ctx, 'cordis_inspect', { what: 'dynamic' }))).toContain('waiting for: greeter')
+    expect(ctx.tools.get('greet')).toBeUndefined()
+
+    await call(ctx, 'cordis_mount', { code: PROVIDER_CODE })
+    expect(ctx.tools.get('greet')).toBeDefined()
+    expect(text(await call(ctx, 'greet', { name: 'late' }))).toBe('hi late')
+  })
+
+  it('unmounting the provider sends the consumer back to pending and unwinds its registrations', async () => {
+    const ctx = await setup()
+    await call(ctx, 'cordis_mount', { code: PROVIDER_CODE })   // dyn-1
+    await call(ctx, 'cordis_mount', { code: CONSUMER_CODE })   // dyn-2
+    expect(ctx.tools.get('greet')).toBeDefined()
+
+    const unmounted = await call(ctx, 'cordis_unmount', { id: 'dyn-1' })
+    expect(unmounted.isError).toBe(false)
+    expect(ctx.tools.get('greet')).toBeUndefined()
+    const report = text(await call(ctx, 'cordis_inspect', { what: 'dynamic' }))
+    expect(report).toContain('dyn-2: greeter-consumer [pending] — waiting for: greeter')
+  })
+
+  it('re-providing the service re-runs the consumer through the same guard (active again, tool back)', async () => {
+    const ctx = await setup()
+    await call(ctx, 'cordis_mount', { code: PROVIDER_CODE })   // dyn-1
+    await call(ctx, 'cordis_mount', { code: CONSUMER_CODE })   // dyn-2
+    await call(ctx, 'cordis_unmount', { id: 'dyn-1' })
+    expect(ctx.tools.get('greet')).toBeUndefined()
+
+    await call(ctx, 'cordis_mount', { code: PROVIDER_CODE })   // dyn-3
+    expect(ctx.tools.get('greet')).toBeDefined()
+    expect(text(await call(ctx, 'greet', { name: 'again' }))).toBe('hi again')
+    expect(text(await call(ctx, 'cordis_inspect', { what: 'dynamic' }))).toContain('dyn-2: greeter-consumer [active]')
+  })
+
+  it('a duplicate provide fails loud with the owning fiber named, and the failed mount is disposed', async () => {
+    const ctx = await setup()
+    await call(ctx, 'cordis_mount', { code: PROVIDER_CODE })
+    const duplicate = await call(ctx, 'cordis_mount', { code: PROVIDER_CODE })
+    expect(duplicate.isError).toBe(true)
+    expect(text(duplicate)).toContain('has been registered')
+    const report = text(await call(ctx, 'cordis_inspect', { what: 'dynamic' }))
+    expect(report).toContain('dyn-1: greeter-provider')
+    expect(report).not.toContain('dyn-2')
+  })
+
+  it('inspect surfaces the linkage: provides on the provider row, the service in services and api sections', async () => {
+    const ctx = await setup()
+    await call(ctx, 'cordis_mount', { code: PROVIDER_CODE })
+    await call(ctx, 'cordis_mount', { code: CONSUMER_CODE })
+
+    const dynamic = text(await call(ctx, 'cordis_inspect', { what: 'dynamic' }))
+    expect(dynamic).toContain('dyn-1: greeter-provider [active] — provides: greeter')
+
+    const services = text(await call(ctx, 'cordis_inspect', { what: 'services' }))
+    expect(services).toContain('- greeter (provided by greeter-provider)')
+
+    const api = text(await call(ctx, 'cordis_inspect', { what: 'api' }))
+    expect(api).toContain('- greeter (provided by greeter-provider, no catalog entry)')
+  })
+
+  it('a primitive (or null) provided value passes through the façade unwrapped, on both read paths', async () => {
+    const ctx = await setup()
+    const provider = await call(ctx, 'cordis_mount', {
+      code: `
+        return {
+          name: 'answer-provider',
+          apply(ctx) {
+            ctx.provide('answer', 42)
+            ctx.provide('nothing', null)
+          },
+        }
+      `,
+    })
+    expect(provider.isError).toBe(false)
+
+    const consumer = await call(ctx, 'cordis_mount', {
+      code: `
+        return {
+          name: 'answer-consumer',
+          inject: ['answer', 'nothing', 'tools'],
+          apply(ctx) {
+            harness.registerTool(ctx, harness.defineTool({
+              name: 'answer',
+              description: 'Read the provided primitive services.',
+              parameters: {},
+              async execute() {
+                return [{ type: 'text', text: ctx.answer + '/' + ctx.get('answer') + '/' + ctx.nothing }]
+              },
+            }))
+          },
+        }
+      `,
+    })
+    expect(consumer.isError).toBe(false)
+    expect(text(consumer)).toContain('state: active')
+    expect(text(await call(ctx, 'answer', {}))).toBe('42/42/null')
+  })
+
+  it('unmounting the consumer leaves the provider and its service intact', async () => {
+    const ctx = await setup()
+    await call(ctx, 'cordis_mount', { code: PROVIDER_CODE })   // dyn-1
+    await call(ctx, 'cordis_mount', { code: CONSUMER_CODE })   // dyn-2
+    await call(ctx, 'cordis_unmount', { id: 'dyn-2' })
+
+    expect(ctx.tools.get('greet')).toBeUndefined()
+    const services = text(await call(ctx, 'cordis_inspect', { what: 'services' }))
+    expect(services).toContain('- greeter (provided by greeter-provider)')
+    expect(text(await call(ctx, 'cordis_inspect', { what: 'dynamic' }))).toContain('dyn-1: greeter-provider [active]')
+  })
+})

packages/cordis/tool-cordis/tests/helpers.ts

@@ -0,0 +1,104 @@
+import { Context } from 'cordis'
+import Timer from '@cordisjs/plugin-timer'
+import { CallId } from '@deepseek-ai/dsh-llm'
+import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
+import ToolRegistry from '@deepseek-ai/dsh-tools'
+import type { ToolDefinition, ToolExecutionResult } from '@deepseek-ai/dsh-tools'
+import * as tool from '../src/index.ts'
+
+/**
+ * Shared spec helpers: a real `SystemPrompt` + `ToolRegistry` + timer +
+ * tool-cordis tree (only the model is absent — the code strings below stand in
+ * for what it would write), plus the canonical mount-code fixtures the suites
+ * share.
+ */
+
+/** Mount the plugin on a fresh context with a real ToolRegistry and the timer service. */
+export async function setup(config?: tool.Config): Promise<Context> {
+  const ctx = new Context()
+  await ctx.plugin(Timer)
+  await ctx.plugin(SystemPrompt)
+  await ctx.plugin(ToolRegistry)
+  await ctx.plugin(tool, config)
+  return ctx
+}
+
+let callCounter = 0
+
+/** Execute a registered tool through the real registry pipeline. */
+export function call(ctx: Context, name: string, args: unknown): Promise<ToolExecutionResult> {
+  return ctx.tools.execute({ callId: CallId(`call-${++callCounter}`), name, arguments: args })
+}
+
+/** Concatenated text blocks of one tool result. */
+export function text(result: ToolExecutionResult): string {
+  return result.content.filter(block => block.type === 'text').map(block => block.text).join('')
+}
+
+/** Mount code for a listener plugin: logs on every `tools/change`. */
+export const LISTENER_CODE = `
+  return {
+    name: 'change-logger',
+    apply(ctx) {
+      ctx.on('tools/change', () => console.log('tools changed'))
+    },
+  }
+`
+
+/** Mount code for a self-made tool: registers `reverse_text` via the sandbox's harness helpers. */
+export const REVERSE_TOOL_CODE = `
+  return {
+    name: 'reverse-text',
+    inject: ['tools'],
+    apply(ctx) {
+      harness.registerTool(ctx, harness.defineTool({
+        name: 'reverse_text',
+        description: 'Reverse a string.',
+        parameters: { text: { type: 'string', required: true } },
+        async execute(args) {
+          return [{ type: 'text', text: args.text.split('').reverse().join('') }]
+        },
+      }))
+    },
+  }
+`
+
+/** Mount code providing a `greeter` service other mounts can inject. */
+export const PROVIDER_CODE = `
+  return {
+    name: 'greeter-provider',
+    apply(ctx) {
+      ctx.provide('greeter', { greet: (name) => 'hi ' + name })
+    },
+  }
+`
+
+/** Mount code consuming the `greeter` service through inject, exposing it as a tool. */
+export const CONSUMER_CODE = `
+  return {
+    name: 'greeter-consumer',
+    inject: ['greeter', 'tools'],
+    apply(ctx) {
+      harness.registerTool(ctx, harness.defineTool({
+        name: 'greet',
+        description: 'Greet someone via the greeter service.',
+        parameters: { name: { type: 'string', required: true } },
+        async execute(args) {
+          return [{ type: 'text', text: ctx.greeter.greet(args.name) }]
+        },
+      }))
+    },
+  }
+`
+
+/** A registrable no-op tool the tests use to trigger a real `tools/change`. */
+export function dummyTool(name: string): ToolDefinition {
+  return {
+    name,
+    description: 'test trigger',
+    parameters: { type: 'object' as const, properties: {} },
+    async execute(): Promise<[]> {
+      return []
+    },
+  }
+}

packages/cordis/tool-cordis/tests/inspect.spec.ts

@@ -0,0 +1,117 @@
+import { describe, expect, it } from 'vitest'
+import type { Context, Fiber } from 'cordis'
+import { FiberState } from '../src/fiber-state.ts'
+import { describeApi, describeEvents, describePlugins, describeServices } from '../src/inspect.ts'
+import { call, LISTENER_CODE, setup, text } from './helpers.ts'
+
+/**
+ * The `cordis_inspect` sections: rendered against the real runtime through the
+ * tool, plus direct renderer calls for the states a minimal harness cannot
+ * reach (empty service store, same-named sibling fibers, a fully-live catalog).
+ */
+
+describe('cordis_inspect', () => {
+  it('reports all six sections by default', async () => {
+    const ctx = await setup()
+    const result = await call(ctx, 'cordis_inspect', {})
+    expect(result.isError).toBe(false)
+    const report = text(result)
+    for (const heading of ['services', 'plugins', 'tools', 'dynamic', 'api', 'events']) {
+      expect(report).toContain(`## ${heading}`)
+    }
+    // The services section sees the real providers; the plugins list shows
+    // this plugin and its dynamic group flat; the tools section lists the
+    // cordis tools.
+    expect(report).toContain('- tools (provided by ToolRegistry)')
+    expect(report).toContain('- tool-cordis [active]')
+    expect(report).toContain('- cordis-dynamic [active]')
+    expect(report).toContain('- cordis_mount')
+    expect(report).toContain('(no dynamic plugins mounted)')
+  })
+
+  it('limits the report to one section via `what`', async () => {
+    const ctx = await setup()
+    const result = await call(ctx, 'cordis_inspect', { what: 'tools' })
+    const report = text(result)
+    expect(report).toContain('## tools')
+    expect(report).not.toContain('## services')
+    expect(report).not.toContain('## plugins')
+  })
+
+  it('shows a mount in the dynamic section and in the flat plugins list', async () => {
+    const ctx = await setup()
+    await call(ctx, 'cordis_mount', { code: LISTENER_CODE })
+    const report = text(await call(ctx, 'cordis_inspect', {}))
+    expect(report).toContain('- dyn-1: change-logger [active]')
+    expect(report).toContain('- change-logger [active]')
+  })
+
+  it('renders the api section from the generated catalog intersected with the LIVE runtime', async () => {
+    const ctx = await setup()
+    const report = text(await call(ctx, 'cordis_inspect', { what: 'api' }))
+    // Live catalogued services render summary + signatures.
+    expect(report).toContain('- tools — ')
+    expect(report).toContain('register(definition: ToolDefinition)')
+    expect(report).toContain('- systemPrompt — ')
+    // Catalogued services with no live provider are listed tersely.
+    expect(report).toMatch(/not running \(loadable services with no live provider\): .*bash/)
+    // The type shapes the LIVE signatures reference follow (closure over the
+    // generated TYPE_API — a consumer can see field types, not just names).
+    expect(report).toContain('type shapes (referenced by the signatures above')
+    expect(report).toContain('export interface ToolExecution')
+    // A type only reachable through a NOT-live service (e.g. bash) is scoped out.
+    expect(report).not.toContain('export interface BashRunResult')
+    // The inherited ctx surface closes the section.
+    expect(report).toContain('inherited ctx API:')
+    expect(report).toContain('- ctx.effect — ')
+  })
+
+  it('renders the events section with mode badges, signatures, and the waterfall caution', async () => {
+    const ctx = await setup()
+    const report = text(await call(ctx, 'cordis_inspect', { what: 'events' }))
+    expect(report).toContain('- tools/change [emit]')
+    expect(report).toContain('- tools/pre-execute [waterfall]')
+    expect(report).toMatch(/'agent\/status'\(/)
+    expect(report).toContain('returning without next() vetoes the chain')
+  })
+})
+
+describe('inspect renderers (direct)', () => {
+  it('describeServices reports an empty store as such, and labels a non-active provider', () => {
+    const empty = { reflect: { store: {} } } as unknown as Context
+    expect(describeServices(empty)).toEqual(['(no services provided)'])
+
+    const pendingFiber = { state: FiberState.PENDING, name: 'half-loaded' } as unknown as Fiber
+    const store: Record<symbol, unknown> = {}
+    store[Symbol('impl')] = { name: 'thing', fiber: pendingFiber }
+    const ctx = { reflect: { store } } as unknown as Context
+    expect(describeServices(ctx)).toEqual(['- thing (provided by half-loaded, pending)'])
+  })
+
+  it('describePlugins lists every fiber flat, sorted by name, one line per instance', () => {
+    const fiber = (name: string): Fiber => ({ name, state: FiberState.ACTIVE }) as unknown as Fiber
+    const ctx = {
+      registry: { values: () => [{ fibers: [fiber('beta'), fiber('alpha')] }, { fibers: [fiber('alpha')] }] },
+    } as unknown as Context
+    expect(describePlugins(ctx)).toEqual([
+      '- alpha [active]',
+      '- alpha [active]',
+      '- beta [active]',
+    ])
+  })
+
+  it('describeApi omits the not-running line and type shapes when nothing applies', async () => {
+    const ctx = await setup()
+    const lines = describeApi(ctx, [{ key: 'tools', summary: 'The registry.', methods: ['register(x): void'] }], [], [])
+    expect(lines[0]).toBe('- tools — The registry.')
+    expect(lines[1]).toBe('    register(x): void')
+    expect(lines.join('\n')).not.toContain('not running')
+    expect(lines.join('\n')).not.toContain('type shapes')
+  })
+
+  it('describeEvents renders an empty catalog as just the waterfall caution', () => {
+    expect(describeEvents([])).toEqual([
+      'waterfall listeners receive a trailing next() and MUST call it to delegate — returning without next() vetoes the chain.',
+    ])
+  })
+})

packages/cordis/tool-cordis/tests/integration.spec.ts

@@ -0,0 +1,74 @@
+import { describe, expect, it } from 'vitest'
+import { Context } from 'cordis'
+import LlmService from '@deepseek-ai/dsh-llm'
+import SessionStore from '@deepseek-ai/dsh-session'
+import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
+import ToolRegistry from '@deepseek-ai/dsh-tools'
+import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent'
+import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
+import * as ToolCordis from '../src/index.ts'
+import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts'
+import { REVERSE_TOOL_CODE } from './helpers.ts'
+
+/**
+ * Full-loop integration: a scripted mock model mounts a plugin that registers
+ * a NEW tool, calls that tool on the very next step (tool schemas are
+ * reassembled per step — the real loop proves the self-extension contract),
+ * and unmounts it again. Only the model is mocked; the sandbox, the fiber
+ * tree, and the session log are real.
+ */
+
+async function harness(adapter: MockAdapter): Promise<Context> {
+  const ctx = new Context()
+  await ctx.plugin(LlmService)
+  await ctx.plugin(SessionStore)
+  await ctx.plugin(SystemPrompt)
+  await ctx.plugin(ToolRegistry)
+  await ctx.plugin(AgentRegistry)
+  await ctx.plugin(AgentLoop, { agents: [] })
+  await ctx.plugin(ToolCordis)
+  ctx.llm.registerAdapter(['mock'], adapter)
+  return ctx
+}
+
+function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
+  return new Promise((resolve) => {
+    const dispose = ctx.on('agent/status', (subject, status) => {
+      if (subject === agent && status === 'idle') {
+        dispose()
+        resolve()
+      }
+    })
+  })
+}
+
+describe('cordis tools through the agent loop', () => {
+  it('mounts a tool, calls it on the next step, and unmounts it — all as real tool/call events', async () => {
+    const adapter = new MockAdapter([
+      toolCallResponse('call-1', 'cordis_mount', { code: REVERSE_TOOL_CODE }, 'Extending myself.'),
+      toolCallResponse('call-2', 'reverse_text', { text: 'harness' }),
+      toolCallResponse('call-3', 'cordis_unmount', { id: 'dyn-1' }),
+      textResponse('Done.'),
+    ])
+    const ctx = await harness(adapter)
+    const agent = ctx.agentLoop.create(AgentId('it-cordis'), { model: 'mock' })
+
+    agent.send([{ type: 'text', text: 'give yourself reverse_text, use it, clean up' }])
+    await waitForIdle(ctx, agent)
+
+    const log = agent.session.events
+    const calls = log.filter(event => event.type === 'tool/call').map(event => event.data.name)
+    expect(calls).toEqual(['cordis_mount', 'reverse_text', 'cordis_unmount'])
+
+    const results = log.filter(event => event.type === 'tool/result')
+    expect(results.map(event => event.data.isError)).toEqual([false, false, false])
+    const reversed = results[1]!.data.content
+      .filter(block => block.type === 'text')
+      .map(block => block.text)
+      .join('')
+    expect(reversed).toBe('ssenrah')
+
+    // After the unmount the self-made tool is gone from the registry.
+    expect(ctx.tools.get('reverse_text')).toBeUndefined()
+  })
+})

packages/cordis/tool-cordis/tests/mount.spec.ts

@@ -0,0 +1,575 @@
+import { afterEach, describe, expect, it, vi } from 'vitest'
+import { isJsonValue } from '@deepseek-ai/dsh-session'
+import { syntaxErrorContext } from '../src/sandbox.ts'
+import { call, dummyTool, LISTENER_CODE, REVERSE_TOOL_CODE, setup, text } from './helpers.ts'
+
+/**
+ * The `cordis_mount` success/failure family: real plugins land on a genuine
+ * cordis fiber tree, their registrations are observable through the real
+ * registry/event bus, and every rejection path teaches the fix.
+ */
+
+afterEach(() => {
+  vi.restoreAllMocks()
+})
+
+describe('cordis_mount', () => {
+  it('mounts a listener plugin that observes real events, tagged-logging through to the host console', async () => {
+    const ctx = await setup()
+    const log = vi.spyOn(console, 'log').mockImplementation(() => {})
+
+    const result = await call(ctx, 'cordis_mount', { code: LISTENER_CODE })
+    expect(result.isError).toBe(false)
+    expect(text(result)).toContain('mounted dyn-1 (plugin "change-logger", state: active)')
+
+    // Fire a REAL tools/change by registering a tool; the mounted listener logs.
+    ctx.tools.register(dummyTool('trigger_a'))
+    expect(log).toHaveBeenCalledWith('[cordis:dyn-1]', 'tools changed')
+  })
+
+  it('mounts a bare-function plugin as <anonymous>, and a named function under its name', async () => {
+    const ctx = await setup()
+    const anonymous = await call(ctx, 'cordis_mount', { code: 'return (ctx) => { ctx.on(\'tools/change\', () => {}) }' })
+    expect(anonymous.isError).toBe(false)
+    expect(text(anonymous)).toContain('plugin "<anonymous>"')
+    const named = await call(ctx, 'cordis_mount', { code: 'return function watcher(ctx) {}' })
+    expect(text(named)).toContain('plugin "watcher"')
+  })
+
+  it('lets the agent give ITSELF a new tool, immediately callable through the registry', async () => {
+    const ctx = await setup()
+    const result = await call(ctx, 'cordis_mount', { code: REVERSE_TOOL_CODE })
+    expect(result.isError).toBe(false)
+
+    expect(ctx.tools.schemas().map(schema => schema.name)).toContain('reverse_text')
+    const reversed = await call(ctx, 'reverse_text', { text: 'harness' })
+    expect(reversed.isError).toBe(false)
+    expect(text(reversed)).toBe('ssenrah')
+  })
+
+  it('normalizes a self-made tool\'s result into the host realm, so the session log accepts it', async () => {
+    // The model's execute builds its content blocks INSIDE the vm, where
+    // Object.prototype is a different object — dsh-session's isJsonValue (the
+    // gate every `tool/result` append runs through) compares prototype
+    // IDENTITY, so a raw foreign-realm result would error the whole turn the
+    // first time the self-made tool runs. harness.defineTool round-trips the
+    // return into host-realm JSON before it reaches the registry.
+    const ctx = await setup()
+    await call(ctx, 'cordis_mount', { code: REVERSE_TOOL_CODE })
+    const reversed = await call(ctx, 'reverse_text', { text: 'harness' })
+    expect(isJsonValue({ content: reversed.content, isError: reversed.isError })).toBe(true)
+  })
+
+  it('threads the { content, meta } object return form through to the registry result', async () => {
+    const ctx = await setup()
+    await call(ctx, 'cordis_mount', {
+      code: `
+        return {
+          name: 'meta-return',
+          inject: ['tools'],
+          apply(ctx) {
+            harness.registerTool(ctx, harness.defineTool({
+              name: 'meta_tool',
+              description: 'attaches a private presentation payload',
+              parameters: {},
+              async execute() {
+                return { content: [{ type: 'text', text: 'ok' }], meta: { kind: 'demo' } }
+              },
+            }))
+          },
+        }
+      `,
+    })
+    const result = await call(ctx, 'meta_tool', {})
+    expect(result.isError).toBe(false)
+    expect(text(result)).toBe('ok')
+    expect(result.meta).toEqual({ kind: 'demo' })
+  })
+
+  it.each([
+    ['a bare string', 'return \'ok\'', '"ok"'],
+    ['an object whose content is a string', 'return { content: \'ok\' }', '{"content":"ok"}'],
+    ['an array of non-objects', 'return [\'ok\']', '["ok"]'],
+    ['blocks missing the type tag', 'return [{ text: \'hi\' }]', '[{"text":"hi"}]'],
+    ['object-form blocks missing the type tag', 'return { content: [{ text: \'hi\' }] }', '{"content":[{"text":"hi"}]}'],
+    ['undefined — a forgotten return', 'return undefined', 'undefined'],
+  ])('rejects an execute return of %s as that one call\'s teaching error', async (_label, returnStatement, preview) => {
+    // The failure this prevents: the registry trusts the return shape
+    // (postExecute spreads result.content), so an unvalidated { content: 'ok' }
+    // would enter the session log as ['o','k'] and silently corrupt the next
+    // model request. The shape check turns it into THIS call's error instead —
+    // one well-formed text block the log and the model can digest.
+    const ctx = await setup()
+    await call(ctx, 'cordis_mount', {
+      code: `
+        return {
+          name: 'bad-return',
+          inject: ['tools'],
+          apply(ctx) {
+            harness.registerTool(ctx, harness.defineTool({
+              name: 'bad_return_tool',
+              description: 'returns a wrong shape',
+              parameters: {},
+              async execute() { ${returnStatement} },
+            }))
+          },
+        }
+      `,
+    })
+    const result = await call(ctx, 'bad_return_tool', {})
+    expect(result.isError).toBe(true)
+    expect(result.content).toHaveLength(1)
+    expect(result.content[0]!.type).toBe('text')
+    expect(text(result)).toContain(`execute returned ${preview}`)
+    expect(text(result)).toContain('must return an ARRAY of content blocks')
+    expect(text(result)).toContain('✓ return { content: [{ type: \'text\', text: someString }], meta: anyJsonValue }')
+  })
+
+  it('truncates a huge invalid execute return in the teaching error', async () => {
+    const ctx = await setup()
+    await call(ctx, 'cordis_mount', {
+      code: `
+        return {
+          name: 'huge-return',
+          inject: ['tools'],
+          apply(ctx) {
+            harness.registerTool(ctx, harness.defineTool({
+              name: 'huge_return_tool',
+              description: 'returns a huge wrong shape',
+              parameters: {},
+              async execute() { return 'x'.repeat(500) },
+            }))
+          },
+        }
+      `,
+    })
+    const result = await call(ctx, 'huge_return_tool', {})
+    expect(result.isError).toBe(true)
+    expect(text(result)).toContain('…')
+    expect(text(result)).not.toContain('x'.repeat(200))
+  })
+
+  it('accepts a JSON-Schema-style parameters wrapper and normalizes it to the DSL', async () => {
+    // The dialect models write by strong prior: the { type:'object',
+    // properties, required: […] } wrapper, `type: 'integer'`, and
+    // `required: false`. All of it has exactly one meaning — normalize instead
+    // of burning a model turn on a lecture.
+    const ctx = await setup()
+    const result = await call(ctx, 'cordis_mount', {
+      code: `
+        return {
+          name: 'json-schema-tool',
+          inject: ['tools'],
+          apply(ctx) {
+            harness.registerTool(ctx, harness.defineTool({
+              name: 'json_schema_tool',
+              description: 'written in the JSON-Schema dialect',
+              parameters: {
+                type: 'object',
+                properties: {
+                  text: { type: 'string', description: 'the text' },
+                  count: { type: 'integer', default: 1 },
+                  mode: { type: 'string', enum: ['fast', 'slow'] },
+                  extra: { type: 'string', required: false },
+                },
+                required: ['text'],
+              },
+              async execute(args) { return [{ type: 'text', text: args.text + ':' + (args.count ?? 0) }] },
+            }))
+          },
+        }
+      `,
+    })
+    expect(result.isError).toBe(false)
+
+    // The registered schema is canonical JSON Schema derived from the DSL:
+    // the required array survived, integer became number, extra is optional.
+    const schema = ctx.tools.schemas().find(s => s.name === 'json_schema_tool')!
+    const parameters = schema.parameters as { properties: Record<string, { type: string; enum?: string[] }>; required?: string[] }
+    expect(parameters.required).toEqual(['text'])
+    expect(parameters.properties.count!.type).toBe('number')
+    expect(parameters.properties.mode!.enum).toEqual(['fast', 'slow'])
+    // Arg validation enforces the normalized spec: text required, extra not.
+    expect((await call(ctx, 'json_schema_tool', { count: 2 })).isError).toBe(true)
+    expect(text(await call(ctx, 'json_schema_tool', { text: 'ok', count: 2 }))).toBe('ok:2')
+  })
+
+  it('normalizes a nested object property carrying a JSON-Schema required array', async () => {
+    // On an object PROPERTY, a JSON-Schema-style `required` array names the
+    // required children — the nested unwrap converts it just like the top level.
+    const ctx = await setup()
+    const result = await call(ctx, 'cordis_mount', {
+      code: `
+        return {
+          name: 'nested-json-schema',
+          inject: ['tools'],
+          apply(ctx) {
+            harness.registerTool(ctx, harness.defineTool({
+              name: 'nested_json_schema_tool',
+              description: 'nested dialect',
+              parameters: {
+                cfg: { type: 'object', properties: { label: { type: 'string' } }, required: ['label'] },
+              },
+              async execute(args) { return [{ type: 'text', text: args.cfg.label }] },
+            }))
+          },
+        }
+      `,
+    })
+    expect(result.isError).toBe(false)
+    const schema = ctx.tools.schemas().find(s => s.name === 'nested_json_schema_tool')!
+    const cfg = (schema.parameters as { properties: { cfg: { required?: string[] } } }).properties.cfg
+    expect(cfg.required).toEqual(['label'])
+    expect(text(await call(ctx, 'nested_json_schema_tool', { cfg: { label: 'hi' } }))).toBe('hi')
+  })
+
+  it.each([
+    ['parameters: 42', 'must be a SchemaSpec object'],
+    ['parameters: { text: 42 }', 'parameters.text must be a SchemaSpec property object'],
+    ['parameters: { text: { type: \'str\' } }', 'parameters.text must declare a valid type: \'string\' | \'number\' | \'boolean\' | \'object\' | \'array\' (got "str")'],
+    ['parameters: { text: { type: \'string\', required: \'yes\' } }', 'parameters.text.required must be a boolean when present'],
+    ['parameters: { text: { type: \'string\', properties: {} } }', 'parameters.text.properties is only valid for type "object"'],
+    ['parameters: { text: { type: \'string\', items: { type: \'string\' } } }', 'parameters.text.items is only valid for type "array"'],
+  ])('rejects a malformed SchemaSpec (%s) with a teaching error', async (parameters, message) => {
+    const ctx = await setup()
+    const result = await call(ctx, 'cordis_mount', {
+      code: `
+        return {
+          name: 'bad-schema',
+          inject: ['tools'],
+          apply(ctx) {
+            harness.registerTool(ctx, harness.defineTool({
+              name: 'bad_schema_tool',
+              description: 'bad',
+              ${parameters},
+              async execute() { return [] },
+            }))
+          },
+        }
+      `,
+    })
+    expect(result.isError).toBe(true)
+    expect(text(result)).toContain(message)
+  })
+
+  it('accepts a nested object/array SchemaSpec (the DSL recursion)', async () => {
+    const ctx = await setup()
+    const result = await call(ctx, 'cordis_mount', {
+      code: `
+        return {
+          name: 'nested-schema',
+          inject: ['tools'],
+          apply(ctx) {
+            harness.registerTool(ctx, harness.defineTool({
+              name: 'nested_schema_tool',
+              description: 'nested',
+              parameters: {
+                item: { type: 'object', required: true, properties: { label: { type: 'string', required: true } } },
+                tags: { type: 'array', items: { type: 'string' } },
+              },
+              async execute(args) { return [{ type: 'text', text: args.item.label }] },
+            }))
+          },
+        }
+      `,
+    })
+    expect(result.isError).toBe(false)
+    const echoed = await call(ctx, 'nested_schema_tool', { item: { label: 'ok' }, tags: ['a'] })
+    expect(text(echoed)).toBe('ok')
+  })
+
+  it('rejects raw dynamic ctx.tools.register calls that bypass harness helpers', async () => {
+    const ctx = await setup()
+    const result = await call(ctx, 'cordis_mount', {
+      code: `
+        return {
+          name: 'raw-register',
+          inject: ['tools'],
+          apply(ctx) {
+            ctx.tools.register({
+              name: 'raw_dynamic_tool',
+              description: 'raw',
+              parameters: { type: 'object', properties: {} },
+              async execute() { return [] },
+            })
+          },
+        }
+      `,
+    })
+
+    expect(result.isError).toBe(true)
+    expect(text(result)).toContain('dynamic tool registration must use a tool returned by harness.defineTool')
+    expect(ctx.tools.get('raw_dynamic_tool')).toBeUndefined()
+  })
+
+  it('guards the registry reached through ctx.get(\'tools\') identically', async () => {
+    const ctx = await setup()
+    const result = await call(ctx, 'cordis_mount', {
+      code: `
+        return {
+          name: 'raw-register-get',
+          apply(ctx) {
+            ctx.get('tools').register({ name: 'raw_via_get', description: 'raw', parameters: {}, async execute() { return [] } })
+          },
+        }
+      `,
+    })
+    expect(result.isError).toBe(true)
+    expect(text(result)).toContain('dynamic tool registration must use a tool returned by harness.defineTool')
+    expect(ctx.tools.get('raw_via_get')).toBeUndefined()
+  })
+
+  it('passes non-register registry members through the guard with correct binding', async () => {
+    const ctx = await setup()
+    const log = vi.spyOn(console, 'log').mockImplementation(() => {})
+    const result = await call(ctx, 'cordis_mount', {
+      code: `
+        return {
+          name: 'schema-reader',
+          inject: ['tools'],
+          apply(ctx) {
+            console.log('sees', ctx.tools.schemas().length, 'tools; mount is', typeof ctx.tools.get('cordis_mount'))
+          },
+        }
+      `,
+    })
+    expect(result.isError).toBe(false)
+    expect(log).toHaveBeenCalledWith('[cordis:dyn-1]', 'sees', 3, 'tools; mount is', 'object')
+  })
+
+  it('keeps a plugin with unsatisfied inject mounted as pending and names what it waits for', async () => {
+    const ctx = await setup()
+    const result = await call(ctx, 'cordis_mount', {
+      code: 'return { name: \'waiter\', inject: [\'no-such-service\'], apply(ctx) {} }',
+    })
+    expect(result.isError).toBe(false)
+    expect(text(result)).toContain('state: pending')
+    expect(text(result)).toContain('waiting for service(s): no-such-service')
+    // Unmounting a pending mount works like any other.
+    const unmounted = await call(ctx, 'cordis_unmount', { id: 'dyn-1' })
+    expect(unmounted.isError).toBe(false)
+  })
+
+  it('rejects code that throws, leaving nothing mounted', async () => {
+    const ctx = await setup()
+    const result = await call(ctx, 'cordis_mount', { code: 'throw new Error(\'boom in sandbox\')' })
+    expect(result.isError).toBe(true)
+    expect(text(result)).toContain('boom in sandbox')
+    expect(text(await call(ctx, 'cordis_inspect', { what: 'dynamic' }))).toContain('(no dynamic plugins mounted)')
+  })
+
+  it('passes non-Error and null throws through untouched (no SyntaxError misclassification)', async () => {
+    const ctx = await setup()
+    const primitive = await call(ctx, 'cordis_mount', { code: 'throw \'plain-string-throw\'' })
+    expect(primitive.isError).toBe(true)
+    expect(text(primitive)).toContain('plain-string-throw')
+    const nullish = await call(ctx, 'cordis_mount', { code: 'throw null' })
+    expect(nullish.isError).toBe(true)
+  })
+
+  it('rejects code that does not return a plugin', async () => {
+    const ctx = await setup()
+    const result = await call(ctx, 'cordis_mount', { code: 'return 42' })
+    expect(result.isError).toBe(true)
+    expect(text(result)).toContain('must `return` a plugin')
+  })
+
+  it('answers a missing return with the two valid plugin forms', async () => {
+    const ctx = await setup()
+    const result = await call(ctx, 'cordis_mount', { code: 'const plugin = (ctx) => {}' })
+    expect(result.isError).toBe(true)
+    expect(text(result)).toContain('did you forget `return`?')
+  })
+
+  it('disposes a plugin whose apply throws, and reports the error', async () => {
+    const ctx = await setup()
+    const result = await call(ctx, 'cordis_mount', {
+      code: 'return { name: \'broken\', apply(ctx) { throw new Error(\'apply exploded\') } }',
+    })
+    expect(result.isError).toBe(true)
+    expect(text(result)).toContain('apply exploded')
+    expect(text(await call(ctx, 'cordis_inspect', { what: 'dynamic' }))).toContain('(no dynamic plugins mounted)')
+  })
+
+  it('rolls back a plugin that collides with an existing tool name, keeping the original tool intact', async () => {
+    const ctx = await setup()
+    const result = await call(ctx, 'cordis_mount', {
+      code: `
+        return {
+          name: 'usurper',
+          inject: ['tools'],
+          apply(ctx) {
+            harness.registerTool(ctx, harness.defineTool({
+              name: 'cordis_mount',
+              description: 'dup',
+              parameters: {},
+              async execute() { return [] },
+            }))
+          },
+        }
+      `,
+    })
+    expect(result.isError).toBe(true)
+    expect(text(result)).toContain('already registered')
+    expect(text(result)).toContain('first cordis_unmount')
+    // The original cordis_mount still dispatches — the failed fiber is gone.
+    const retry = await call(ctx, 'cordis_mount', { code: LISTENER_CODE })
+    expect(retry.isError).toBe(false)
+  })
+
+  it('isolates sandbox globals: no process/Buffer, and globalThis writes do not leak to the host', async () => {
+    const ctx = await setup()
+    const result = await call(ctx, 'cordis_mount', {
+      code: `
+        globalThis.__cordis_tool_leak = 'leaked'
+        return { name: 'probe-' + typeof process + '-' + typeof Buffer, apply(ctx) {} }
+      `,
+    })
+    expect(result.isError).toBe(false)
+    expect(text(result)).toContain('plugin "probe-undefined-undefined"')
+    expect((globalThis as Record<string, unknown>).__cordis_tool_leak).toBeUndefined()
+  })
+
+  it.each([
+    ['require(\'fs\')', 'require is not available in the mount sandbox', 'inject: [\'fs\']'],
+    ['setTimeout(() => {}, 5)', 'setTimeout is not available in the mount sandbox', 'ctx.setTimeout'],
+    ['fetch(\'https://example.com\')', 'fetch is not available in the mount sandbox', 'ctx.web'],
+  ])('traps the Node API call %s with a redirect to the cordis alternative', async (invocation, trapMessage, redirect) => {
+    const ctx = await setup()
+    const result = await call(ctx, 'cordis_mount', { code: `${invocation}\nreturn (ctx) => {}` })
+    expect(result.isError).toBe(true)
+    expect(text(result)).toContain(trapMessage)
+    expect(text(result)).toContain(redirect)
+    expect(text(await call(ctx, 'cordis_inspect', { what: 'dynamic' }))).toContain('(no dynamic plugins mounted)')
+  })
+
+  it('lets a mounted plugin schedule through the cordis timer service (inject: [\'timer\'])', async () => {
+    const ctx = await setup()
+    const log = vi.spyOn(console, 'log').mockImplementation(() => {})
+    const result = await call(ctx, 'cordis_mount', {
+      code: `
+        return {
+          name: 'ticker',
+          inject: ['timer'],
+          apply(ctx) {
+            ctx.setTimeout(() => console.log('tick'), 10)
+          },
+        }
+      `,
+    })
+    expect(result.isError).toBe(false)
+    expect(text(result)).toContain('state: active')
+    await new Promise(resolve => setTimeout(resolve, 50))
+    expect(log).toHaveBeenCalledWith('[cordis:dyn-1]', 'tick')
+  })
+
+  it('provides btoa/atob and the tagged console variants inside the sandbox', async () => {
+    const ctx = await setup()
+    const log = vi.spyOn(console, 'log').mockImplementation(() => {})
+    const error = vi.spyOn(console, 'error').mockImplementation(() => {})
+    const result = await call(ctx, 'cordis_mount', {
+      code: `
+        console.warn('warned')
+        console.error('errored')
+        const round = atob(btoa('hi'))
+        const bytes = new TextEncoder().encode(round)
+        return { name: 'codec-' + new TextDecoder().decode(bytes), apply(ctx) { console.log('applied', typeof ctx.on) } }
+      `,
+    })
+    expect(result.isError).toBe(false)
+    expect(text(result)).toContain('plugin "codec-hi"')
+    expect(log).toHaveBeenCalledWith('[cordis:dyn-1]', 'warned')
+    expect(log).toHaveBeenCalledWith('[cordis:dyn-1]', 'applied', 'function')
+    expect(error).toHaveBeenCalledWith('[cordis:dyn-1]', 'errored')
+  })
+
+  it('answers TypeScript syntax in the plain-JS sandbox with the fix', async () => {
+    const ctx = await setup()
+    const result = await call(ctx, 'cordis_mount', {
+      code: 'return { name: \'ts\' as const, apply(ctx) {} }',
+    })
+    expect(result.isError).toBe(true)
+    expect(text(result)).toContain('plain JavaScript, not TypeScript')
+  })
+
+  it('surfaces the offending line + caret and the bracket-balance hint on a syntax error', async () => {
+    const ctx = await setup()
+    // The canonical model mistake: closing the returned object with `});` as
+    // if it were a callback argument. The word "as" in a STRING elsewhere must
+    // not trigger the TypeScript hint — the heuristic reads the failing line.
+    const result = await call(ctx, 'cordis_mount', {
+      code: 'const note = \'treat pattern as regex\'\nreturn {\n  name: \'oops\',\n  apply(ctx) {}\n});',
+    })
+    expect(result.isError).toBe(true)
+    const message = text(result)
+    expect(message).toContain('failed to parse')
+    expect(message).toContain('});')
+    expect(message).toContain('^')
+    expect(message).toContain('BODY of an async function')
+    expect(message).not.toContain('TypeScript')
+  })
+
+  it('syntaxErrorContext falls back to String(error) when the stack has no vm prelude', () => {
+    const doctored = new SyntaxError('boom')
+    delete (doctored as { stack?: string }).stack
+    expect(syntaxErrorContext(doctored)).toBe('SyntaxError: boom')
+    const plain = new SyntaxError('bang')
+    plain.stack = 'not-a-vm-stack'
+    expect(syntaxErrorContext(plain)).toBe('SyntaxError: bang')
+  })
+
+  it('handles a runtime-thrown SyntaxError (no source-line prelude) with the generic hint', async () => {
+    const ctx = await setup()
+    const result = await call(ctx, 'cordis_mount', { code: 'throw new SyntaxError(\'user-crafted\')' })
+    expect(result.isError).toBe(true)
+    expect(text(result)).toContain('failed to parse')
+    expect(text(result)).toContain('user-crafted')
+  })
+
+  it('honors the configured vmTimeoutMs for the synchronous portion', async () => {
+    const ctx = await setup({ vmTimeoutMs: 50 })
+    const result = await call(ctx, 'cordis_mount', { code: 'while (true) {}' })
+    expect(result.isError).toBe(true)
+    expect(text(result)).toMatch(/timed? ?out/i)
+    expect(text(await call(ctx, 'cordis_inspect', { what: 'dynamic' }))).toContain('(no dynamic plugins mounted)')
+  })
+
+  it('makes instanceof inside the sandbox see BOTH realms (patched vm constructors, host untouched)', async () => {
+    // The args a tool's execute receives are HOST-realm objects; without the
+    // dual-realm Symbol.hasInstance prelude, `args.items instanceof Array` in
+    // sandbox code is silently false. The patch lives on the vm realm's own
+    // constructors only — the host realm's must stay pristine.
+    const ctx = await setup()
+    await call(ctx, 'cordis_mount', {
+      code: `
+        return {
+          name: 'probe-instanceof',
+          inject: ['tools'],
+          apply(ctx) {
+            harness.registerTool(ctx, harness.defineTool({
+              name: 'probe_instanceof',
+              description: 'report instanceof checks across realms',
+              parameters: { items: { type: 'array', required: true, items: { type: 'string' } } },
+              async execute(args) {
+                const checks = {
+                  hostArray: args.items instanceof Array,
+                  hostObject: args instanceof Object,
+                  vmArray: [] instanceof Array,
+                  vmObject: ({}) instanceof Object,
+                }
+                return [{ type: 'text', text: JSON.stringify(checks) }]
+              },
+            }))
+          },
+        }
+      `,
+    })
+    const probed = await call(ctx, 'probe_instanceof', { items: ['a'] })
+    expect(probed.isError).toBe(false)
+    expect(JSON.parse(text(probed))).toEqual({ hostArray: true, hostObject: true, vmArray: true, vmObject: true })
+    // The host realm's constructors keep their default instanceof: no own
+    // Symbol.hasInstance was added to them.
+    expect(Object.getOwnPropertySymbols(Object)).not.toContain(Symbol.hasInstance)
+    expect(Object.getOwnPropertySymbols(Array)).not.toContain(Symbol.hasInstance)
+  })
+})

packages/cordis/tool-cordis/tests/present.spec.ts

@@ -0,0 +1,41 @@
+import { describe, expect, it } from 'vitest'
+import { presentInspectCall, presentMountCall, presentUnmountCall } from '../src/present.ts'
+import { setup } from './helpers.ts'
+
+/**
+ * Render-intent presenters: pure functions of the call args (no I/O, no
+ * session state — they run on replay too), wired onto the registered tools.
+ */
+
+describe('presenters', () => {
+  it('cordis_inspect renders a generic read card titled with the section', () => {
+    expect(presentInspectCall({})).toEqual({ card: 'generic', kind: 'read', title: 'Inspect cordis runtime' })
+    expect(presentInspectCall({ what: 'api' })).toEqual({ card: 'generic', kind: 'read', title: 'Inspect cordis runtime: api' })
+  })
+
+  it('cordis_mount renders a generic execute card carrying the code as raw input', () => {
+    expect(presentMountCall({ code: 'return (ctx) => {}' })).toEqual({
+      card: 'generic',
+      kind: 'execute',
+      title: 'Mount plugin into live cordis runtime',
+      rawInput: { code: 'return (ctx) => {}' },
+    })
+  })
+
+  it('cordis_unmount renders a generic delete card titled with the id', () => {
+    expect(presentUnmountCall({ id: 'dyn-1' })).toEqual({ card: 'generic', kind: 'delete', title: 'Unmount dyn-1' })
+  })
+
+  it('is wired onto the registered definitions through the defineTool soft-validation path', async () => {
+    const ctx = await setup()
+    expect(ctx.tools.get('cordis_inspect')!.presentCall!({ what: 'tools' })).toEqual({
+      card: 'generic',
+      kind: 'read',
+      title: 'Inspect cordis runtime: tools',
+    })
+    expect(ctx.tools.get('cordis_mount')!.presentCall!({ code: 'return 1' })).toMatchObject({ kind: 'execute' })
+    expect(ctx.tools.get('cordis_unmount')!.presentCall!({ id: 'dyn-2' })).toMatchObject({ title: 'Unmount dyn-2' })
+    // Soft validation: presenter args that fail the schema render as no card, never a throw.
+    expect(ctx.tools.get('cordis_unmount')!.presentCall!({ id: 42 })).toBeUndefined()
+  })
+})

packages/cordis/tool-cordis/tests/sandbox-context.spec.ts

@@ -0,0 +1,295 @@
+import { describe, expect, it } from 'vitest'
+import { call, setup, text } from './helpers.ts'
+
+/**
+ * The sandbox context façade is a whitelist, not a pass-through proxy: mount
+ * code reaches only the registration/eventing verbs, the timer helpers, a
+ * guarded `tools`, and its injected services. Every framework-plumbing member
+ * that could hand back an UNGUARDED context — through which a plugin could
+ * `ctx.<escape>.tools.register({…})` to bypass the marker check and host-realm
+ * normalization — is denied. These are the regression guards for that escape
+ * class (the review finding on the original pass-through proxy).
+ */
+
+/** Mount a plugin whose `apply` touches one framework member, and report the error text. */
+async function mountTouching(ctx: Awaited<ReturnType<typeof setup>>, expr: string): Promise<string> {
+  const result = await call(ctx, 'cordis_mount', {
+    code: `return { name: 'probe', inject: ['tools'], apply(ctx) { ${expr} } }`,
+  })
+  expect(result.isError).toBe(true)
+  return text(result)
+}
+
+describe('sandbox context façade — escape surface is closed', () => {
+  it.each([
+    ['ctx.root', 'const c = ctx.root'],
+    ['ctx.parent', 'const c = ctx.parent'],
+    ['ctx.scope', 'const c = ctx.scope'],
+    ['ctx.fiber', 'const f = ctx.fiber'],
+    ['ctx.reflect', 'const r = ctx.reflect'],
+    ['ctx.registry', 'const r = ctx.registry'],
+    ['ctx.events', 'const e = ctx.events'],
+    ['ctx.extend()', 'ctx.extend({})'],
+    ['ctx.isolate()', 'ctx.isolate("x")'],
+    ['ctx.intercept()', 'ctx.intercept("x", {})'],
+    ['ctx.plugin()', 'ctx.plugin({ apply() {} })'],
+    ['ctx.set()', 'ctx.set("tools", 1)'],
+    ['ctx.mixin()', 'ctx.mixin("x", [])'],
+  ])('denies %s with a teaching error', async (_label, expr) => {
+    const ctx = await setup()
+    const message = await mountTouching(ctx, expr)
+    expect(message).toContain('sandbox ctx does not expose')
+    expect(message).toContain('withheld by design')
+  })
+
+  it('the classic ctx.root.tools.register bypass registers nothing and fails loud', async () => {
+    const ctx = await setup()
+    const result = await call(ctx, 'cordis_mount', {
+      code: `
+        return {
+          name: 'root-bypass',
+          inject: ['tools'],
+          apply(ctx) {
+            ctx.root.tools.register({
+              name: 'smuggled',
+              description: 'raw, unguarded',
+              parameters: { type: 'object', properties: {} },
+              async execute() { return [] },
+            })
+          },
+        }
+      `,
+    })
+    expect(result.isError).toBe(true)
+    expect(text(result)).toContain('sandbox ctx does not expose "root"')
+    // The whole point: the bypass never reaches the registry.
+    expect(ctx.tools.get('smuggled')).toBeUndefined()
+  })
+
+  it('rejects assignment to the façade rather than silently dropping it', async () => {
+    const ctx = await setup()
+    const result = await call(ctx, 'cordis_mount', {
+      code: 'return { name: \'writer\', apply(ctx) { ctx.stash = 1 } }',
+    })
+    expect(result.isError).toBe(true)
+    expect(text(result)).toContain('sandbox ctx is read-only')
+  })
+
+  it('denies a service whose method returns a Context (the .ctx escape), registering nothing', async () => {
+    // A cordis Service instance carries `.ctx` (a real Context), so
+    // `ctx.systemPrompt.ctx.root.tools.register(…)` would be a fresh unguarded
+    // handle. The service wrapper's return-value guard rejects any Context on
+    // the way back to sandbox code, so the escape never lands. (`systemPrompt`
+    // is in the setup harness, so the plugin activates and its apply runs.)
+    const ctx = await setup()
+    const result = await call(ctx, 'cordis_mount', {
+      code: `
+        return {
+          name: 'svc-ctx-escape',
+          inject: ['systemPrompt', 'tools'],
+          apply(ctx) {
+            ctx.systemPrompt.ctx.root.tools.register({
+              name: 'smuggled_via_service',
+              description: 'raw, unguarded',
+              parameters: { type: 'object', properties: {} },
+              async execute() { return [] },
+            })
+          },
+        }
+      `,
+    })
+    expect(result.isError).toBe(true)
+    expect(text(result)).toContain('returned a cordis Context, which the sandbox does not expose')
+    expect(ctx.tools.get('smuggled_via_service')).toBeUndefined()
+  })
+
+  it('guards an async injected-service method: a host-realm Promise resolves through the guard', async () => {
+    // The return guard's Promise arm only fires for a HOST-realm Promise
+    // (a vm-realm one is not `instanceof` the host `Promise`). Provide a
+    // host-realm service from the test, then inject + await it from a mount:
+    // the resolved value is non-Context data and passes through.
+    const ctx = await setup()
+    ctx.plugin({
+      name: 'host-async-svc',
+      apply(c) { c.provide('hostAsync', { grab: async () => 'host-fetched' }) },
+    })
+    await call(ctx, 'cordis_mount', {
+      code: `
+        return {
+          name: 'async-consumer',
+          inject: ['hostAsync', 'tools'],
+          apply(ctx) {
+            harness.registerTool(ctx, harness.defineTool({
+              name: 'do_fetch',
+              description: 'awaits the host async service',
+              parameters: {},
+              async execute() {
+                const value = await ctx.hostAsync.grab()
+                return [{ type: 'text', text: value }]
+              },
+            }))
+          },
+        }
+      `,
+    })
+    const result = await call(ctx, 'do_fetch', {})
+    expect(result.isError).toBe(false)
+    expect(text(result)).toBe('host-fetched')
+  })
+
+  it('reads a symbol property as undefined and answers the `in` operator without throwing', async () => {
+    const ctx = await setup()
+    const result = await call(ctx, 'cordis_mount', {
+      code: `
+        return {
+          name: 'introspector',
+          inject: ['tools'],
+          apply(ctx) {
+            const sym = ctx[Symbol.iterator]
+            console.log('probe', sym === undefined, 'tools' in ctx, 'on' in ctx, 'root' in ctx)
+          },
+        }
+      `,
+    })
+    expect(result.isError).toBe(false)
+  })
+})
+
+describe('sandbox context façade — inject gate on services', () => {
+  it('denies an undeclared live service (property access), naming the inject fix', async () => {
+    // `systemPrompt` is a live global service in the setup harness, but this
+    // mount does not declare it — reaching it would let the mount depend on a
+    // provider cordis does not know about, so it is refused.
+    const ctx = await setup()
+    const result = await call(ctx, 'cordis_mount', {
+      code: 'return { name: \'undeclared\', inject: [\'tools\'], apply(ctx) { const s = ctx.systemPrompt } }',
+    })
+    expect(result.isError).toBe(true)
+    expect(text(result)).toContain('service "systemPrompt" is not injected')
+    expect(text(result)).toContain('inject: [\'systemPrompt\', …]')
+  })
+
+  it('denies an undeclared live service reached through ctx.get too', async () => {
+    const ctx = await setup()
+    const result = await call(ctx, 'cordis_mount', {
+      code: 'return { name: \'undeclared-get\', inject: [\'tools\'], apply(ctx) { ctx.get(\'systemPrompt\') } }',
+    })
+    expect(result.isError).toBe(true)
+    expect(text(result)).toContain('service "systemPrompt" is not injected')
+  })
+
+  it('allows a service the mount DID declare in inject', async () => {
+    const ctx = await setup()
+    const result = await call(ctx, 'cordis_mount', {
+      code: `
+        return {
+          name: 'declared',
+          inject: ['systemPrompt', 'tools'],
+          apply(ctx) { console.log('has systemPrompt:', typeof ctx.systemPrompt) }
+        }
+      `,
+    })
+    expect(result.isError).toBe(false)
+    expect(text(result)).toContain('state: active')
+  })
+
+  it('a cross-mount consumer must declare the provider — the undeclared path is refused, not left as a zombie tool', async () => {
+    // The finding's scenario: a consumer registers a tool built on a provider's
+    // service WITHOUT declaring inject. cordis would then never park the
+    // consumer when the provider unmounts, leaving a tool that fails only at
+    // execution. The gate refuses the undeclared access up front, so the
+    // dependency is always visible to cordis.
+    const ctx = await setup()
+    await call(ctx, 'cordis_mount', {
+      code: 'return { name: \'greeter-provider\', apply(ctx) { ctx.provide(\'greeter\', { greet: (n) => \'hi \' + n }) } }',
+    })
+    const undeclared = await call(ctx, 'cordis_mount', {
+      code: `
+        return {
+          name: 'sloppy-consumer',
+          inject: ['tools'],
+          apply(ctx) {
+            harness.registerTool(ctx, harness.defineTool({
+              name: 'greet_undeclared',
+              description: 'uses greeter without declaring it',
+              parameters: { n: { type: 'string', required: true } },
+              async execute(args) { return [{ type: 'text', text: ctx.greeter.greet(args.n) }] },
+            }))
+          },
+        }
+      `,
+    })
+    // The tool registers (its execute is lazy), but calling it hits the gate:
+    // `ctx.greeter` is undeclared, so it fails with the teaching error rather
+    // than silently working and later stranding.
+    expect(undeclared.isError).toBe(false)
+    const called = await call(ctx, 'greet_undeclared', { n: 'x' })
+    expect(called.isError).toBe(true)
+    expect(text(called)).toContain('service "greeter" is not injected')
+  })
+})
+
+describe('sandbox tools façade — get is a read-only schema view', () => {
+  it('ctx.tools.get returns a schema, not the live ToolDefinition with execute', async () => {
+    // The finding: returning the raw ToolDefinition hands mount code the
+    // tool's execute function, letting it bypass ToolRegistry.execute (and its
+    // pre/post hooks). get now returns the same name/description/parameters
+    // view as schemas(), with no execute. Asserted via a self-made tool that
+    // reports the shape it saw — world-checked, not self-reported.
+    const ctx = await setup()
+    await call(ctx, 'cordis_mount', {
+      code: `
+        return {
+          name: 'reporter',
+          inject: ['tools'],
+          apply(ctx) {
+            harness.registerTool(ctx, harness.defineTool({
+              name: 'report_view',
+              description: 'reports the shape of a tool view',
+              parameters: {},
+              async execute() {
+                const view = ctx.tools.get('cordis_mount')
+                return [{ type: 'text', text: JSON.stringify({
+                  hasExecute: 'execute' in view,
+                  hasPresentCall: 'presentCall' in view,
+                  name: view.name,
+                  keys: Object.keys(view).sort(),
+                }) }]
+              },
+            }))
+          },
+        }
+      `,
+    })
+    const reported = await call(ctx, 'report_view', {})
+    expect(reported.isError).toBe(false)
+    const shape = JSON.parse(text(reported)) as { hasExecute: boolean; hasPresentCall: boolean; name: string; keys: string[] }
+    expect(shape.hasExecute).toBe(false)
+    expect(shape.hasPresentCall).toBe(false)
+    expect(shape.name).toBe('cordis_mount')
+    expect(shape.keys).toEqual(['description', 'name', 'parameters'])
+  })
+
+  it('ctx.tools.get returns undefined for an unknown tool', async () => {
+    const ctx = await setup()
+    await call(ctx, 'cordis_mount', {
+      code: `
+        return {
+          name: 'unknown-probe',
+          inject: ['tools'],
+          apply(ctx) {
+            harness.registerTool(ctx, harness.defineTool({
+              name: 'probe_unknown',
+              description: 'reports whether an unknown tool resolves',
+              parameters: {},
+              async execute() {
+                return [{ type: 'text', text: String(ctx.tools.get('no_such_tool') === undefined) }]
+              },
+            }))
+          },
+        }
+      `,
+    })
+    expect(text(await call(ctx, 'probe_unknown', {}))).toBe('true')
+  })
+})

packages/cordis/tool-cordis/tests/tool-cordis.spec.ts

@@ -0,0 +1,49 @@
+import { describe, expect, it } from 'vitest'
+import Loader from '@cordisjs/plugin-loader'
+import * as tool from '../src/index.ts'
+import { setup } from './helpers.ts'
+
+/**
+ * Export-shape and registration surface: the namespace-plugin contract the
+ * real Loader path depends on, the registered tool set, and the Config
+ * validator's defaults and rejections.
+ */
+
+describe('export shape', () => {
+  it('has no default export, and survives the real Loader unwrapExports', () => {
+    // A stray `export default` would make `unwrapExports` (`exports.default ??
+    // exports`) collapse the module to the bare function and DROP `inject`,
+    // crashing at real load (docs/postmortem/0001). Assert directly AND through
+    // the real unwrap so adding `export default apply` fails here.
+    expect('default' in tool).toBe(false)
+    const loader = Object.create(Loader.prototype) as Loader
+    const unwrapped = loader.unwrapExports(tool) as Record<string, unknown>
+    expect(unwrapped).toBe(tool)
+    expect(unwrapped.name).toBe('tool-cordis')
+    expect(unwrapped.inject).toEqual(['tools'])
+    expect(typeof unwrapped.apply).toBe('function')
+    expect(typeof unwrapped.Config).toBe('function')
+  })
+})
+
+describe('tool registration', () => {
+  it('registers the three cordis tools with the documented schemas', async () => {
+    const ctx = await setup()
+    const names = ctx.tools.schemas().map(schema => schema.name)
+    expect(names).toEqual(expect.arrayContaining(['cordis_inspect', 'cordis_mount', 'cordis_unmount']))
+    const inspect = ctx.tools.schemas().find(schema => schema.name === 'cordis_inspect')!
+    const props = (inspect.parameters as { properties: Record<string, { enum?: string[] }> }).properties
+    expect(props.what?.enum).toEqual(['services', 'plugins', 'tools', 'dynamic', 'api', 'events'])
+  })
+})
+
+describe('Config', () => {
+  it('defaults vmTimeoutMs to 5000', () => {
+    expect(new tool.Config()).toEqual({ vmTimeoutMs: 5000 })
+  })
+
+  it('rejects a non-positive vmTimeoutMs at validation time (misconfiguration fails loud)', () => {
+    expect(() => new tool.Config({ vmTimeoutMs: 0 })).toThrow()
+    expect(() => new tool.Config({ vmTimeoutMs: -1 })).toThrow()
+  })
+})

packages/cordis/tool-cordis/tests/unmount-hmr.spec.ts

@@ -0,0 +1,82 @@
+import { afterEach, describe, expect, it, vi } from 'vitest'
+import { Context } from 'cordis'
+import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
+import ToolRegistry from '@deepseek-ai/dsh-tools'
+import * as tool from '../src/index.ts'
+import { call, dummyTool, LISTENER_CODE, REVERSE_TOOL_CODE, setup, text } from './helpers.ts'
+
+/**
+ * Disposal semantics: `cordis_unmount` reaches quiescence before returning,
+ * and disposing the tool-cordis fiber itself (the HMR path) cascades over the
+ * whole dynamic subtree through the ordinary parent→child fiber lifecycle.
+ */
+
+afterEach(() => {
+  vi.restoreAllMocks()
+})
+
+describe('cordis_unmount', () => {
+  it('disposes the mount and its registrations have stopped by the time it returns (quiescence)', async () => {
+    const ctx = await setup()
+    const log = vi.spyOn(console, 'log').mockImplementation(() => {})
+    await call(ctx, 'cordis_mount', { code: LISTENER_CODE })
+
+    ctx.tools.register(dummyTool('trigger_before'))
+    expect(log).toHaveBeenCalledTimes(1)
+
+    const result = await call(ctx, 'cordis_unmount', { id: 'dyn-1' })
+    expect(result.isError).toBe(false)
+    expect(text(result)).toContain('unmounted dyn-1')
+
+    // Immediately after the awaited unmount, the listener must be gone — no
+    // grace period, no eventual consistency.
+    ctx.tools.register(dummyTool('trigger_after'))
+    expect(log).toHaveBeenCalledTimes(1)
+    expect(text(await call(ctx, 'cordis_inspect', { what: 'dynamic' }))).toContain('(no dynamic plugins mounted)')
+  })
+
+  it('unregisters a self-made tool on unmount', async () => {
+    const ctx = await setup()
+    await call(ctx, 'cordis_mount', { code: REVERSE_TOOL_CODE })
+    expect(ctx.tools.get('reverse_text')).toBeDefined()
+
+    await call(ctx, 'cordis_unmount', { id: 'dyn-1' })
+    expect(ctx.tools.get('reverse_text')).toBeUndefined()
+  })
+
+  it('rejects an unknown id, and a second unmount of the same id', async () => {
+    const ctx = await setup()
+    const unknown = await call(ctx, 'cordis_unmount', { id: 'dyn-99' })
+    expect(unknown.isError).toBe(true)
+    expect(text(unknown)).toContain('no dynamic plugin with id "dyn-99"')
+
+    await call(ctx, 'cordis_mount', { code: LISTENER_CODE })
+    await call(ctx, 'cordis_unmount', { id: 'dyn-1' })
+    const again = await call(ctx, 'cordis_unmount', { id: 'dyn-1' })
+    expect(again.isError).toBe(true)
+  })
+})
+
+describe('HMR safety', () => {
+  it('disposing the tool-cordis fiber cascades over the dynamic subtree and its registrations', async () => {
+    const ctx = new Context()
+    await ctx.plugin(SystemPrompt)
+    await ctx.plugin(ToolRegistry)
+    const fiber = await ctx.plugin(tool)
+
+    const log = vi.spyOn(console, 'log').mockImplementation(() => {})
+    await call(ctx, 'cordis_mount', { code: LISTENER_CODE })
+    await call(ctx, 'cordis_mount', { code: REVERSE_TOOL_CODE })
+    expect(ctx.tools.get('reverse_text')).toBeDefined()
+
+    await fiber.dispose()
+
+    // The whole subtree is gone: the self-made tool, the cordis tools, and the
+    // mounted listener (no log on a fresh tools/change).
+    expect(ctx.tools.get('reverse_text')).toBeUndefined()
+    expect(ctx.tools.get('cordis_mount')).toBeUndefined()
+    const calls = log.mock.calls.length
+    ctx.tools.register(dummyTool('trigger_post_dispose'))
+    expect(log).toHaveBeenCalledTimes(calls)
+  })
+})

packages/cordis/tool-cordis/tsconfig.json

@@ -0,0 +1,27 @@
+{
+  "extends": "../../../tsconfig.base.json",
+  "compilerOptions": {
+    "rootDir": "src",
+    "outDir": "lib/types"
+  },
+  "include": [
+    "src"
+  ],
+  "references": [
+    {
+      "path": "../../../vendor/cosmokit"
+    },
+    {
+      "path": "../../../vendor/cordis"
+    },
+    {
+      "path": "../../../vendor/timer"
+    },
+    {
+      "path": "../../../vendor/schemastery"
+    },
+    {
+      "path": "../../core/tools"
+    }
+  ]
+}

packages/core/agent-core/README.md

@@ -36,11 +36,11 @@ This is the [interface/implementation/consumer seam](../../../docs/rfc/implement
 
 ```ts
 import type { Config } from '@deepseek-ai/dsh-agent-core'
-// { agents?, persona? } — the schema is z.intersect([AgentLoop.Config, SystemPrompt.Config]),
+// { agents?, persona?, toolOrder? } — the schema is z.intersect([AgentLoop.Config, SystemPrompt.Config]),
 // so validation and defaulting can never drift from the owners'.
 ```
 
-The bundle FORWARDS each field to the child that owns it: `agents` to `agent-loop` (default `[]`), so each app supplies its own pre-created agents — a stdio app pre-creates a `main`; the ACP app pre-creates none (it creates agents on demand at `session/new`) — and `persona` to `dsh-system-prompt` (default `''`), the deployment's persona section. Forwarding is exactly why the owners can live in the shared spine even though the apps disagree on what to configure.
+The bundle FORWARDS each field to the child that owns it: `agents` to `agent-loop` (default `[]`), so each app supplies its own pre-created agents — a stdio app pre-creates a `main`; the ACP app pre-creates none (it creates agents on demand at `session/new`) — `persona` to `dsh-system-prompt` (default `''`), the deployment's persona section — and `toolOrder` to `dsh-system-prompt` (absent — lexicographic), the explicit model-facing tool order. Forwarding is exactly why the owners can live in the shared spine even though the apps disagree on what to configure.
 
 ## Why a code bundle, not a shared YAML include
 

packages/core/agent-core/src/index.ts

@@ -60,17 +60,21 @@ export const name = 'agent-core'
 /**
  * Bundle config: each field forwarded verbatim to the child that owns it —
  * `agents` to the agent loop (an app that pre-creates no agents, like the ACP
- * bridge, simply omits it), `persona` to the system-prompt plugin (the
- * deployment's persona section), and `projectInstructions` to the
- * project-instructions plugin. All are optional INPUT here because each owner
- * supplies its own default; this bundle's schema composes the owners' schemas
- * so validation and defaulting can never drift from them.
+ * bridge, simply omits it), `persona` and `toolOrder` to the system-prompt
+ * plugin (the deployment's persona section and the explicit model-facing tool
+ * order), and `projectInstructions` to the project-instructions plugin. Every
+ * field is optional INPUT here because each owner's schema supplies the
+ * default (`[]` / `''` / absent — lexicographic / loader defaults); the schema
+ * is the INTERSECTION of the owners' own schemas, so validation and defaulting
+ * can never drift from them.
  */
 export interface Config {
   /** The agent-loop `agents` list (see dsh-agent-loop's `Config`). */
   agents?: AgentLoopConfig['agents']
   /** The deployment persona (see dsh-system-prompt's `Config`). */
   persona?: SystemPromptConfig['persona']
+  /** The explicit model-facing tool order (see dsh-system-prompt's `Config`). */
+  toolOrder?: SystemPromptConfig['toolOrder']
   /** Project-instruction loader controls; set `false` for hermetic prompts. */
   projectInstructions?: projectInstructions.Config | false
 }
@@ -89,12 +93,12 @@ export const Config = z.intersect([
 /**
  * Load the spine. Each `ctx.plugin(...)` mounts one child of the bundle fiber;
  * `agent-loop` receives the forwarded `agents` list and `system-prompt` the
- * forwarded `persona`. Project-instructions receives its own forwarded config
- * or loads with defaults. Load order is irrelevant (cordis pends each fiber on
- * its `inject` until the services it needs exist), but the listing mirrors the
- * dependency layering for readability: the LLM vocabulary and core registries
- * first, then extension plugins that wrap request/tool seams, then the loop
- * that drives them.
+ * forwarded `persona` and `toolOrder`. Project-instructions receives its own
+ * forwarded config or loads with defaults. Load order is irrelevant (cordis
+ * pends each fiber on its `inject` until the services it needs exist), but the
+ * listing mirrors the dependency layering for readability: the LLM vocabulary
+ * and core registries first, then extension plugins that wrap request/tool
+ * seams, then the loop that drives them.
  */
 export function apply(ctx: Context, config: Config): void {
   ctx.plugin(Timer)
@@ -103,8 +107,13 @@ export function apply(ctx: Context, config: Config): void {
   // The forwarded fields are validated + defaulted by this bundle's intersected
   // schema before apply runs, so the ?? fallbacks only narrow the
   // optional-input TYPES — they mirror the owners' schema defaults, never
-  // introduce different ones.
-  ctx.plugin(SystemPrompt, { persona: config.persona ?? '' })
+  // introduce different ones. toolOrder has no owner-supplied default value —
+  // ABSENT means "lexicographic order" — so it is forwarded conditionally
+  // rather than via ??.
+  ctx.plugin(SystemPrompt, {
+    persona: config.persona ?? '',
+    ...config.toolOrder !== undefined ? { toolOrder: config.toolOrder } : {},
+  })
   ctx.plugin(ToolRegistry)
   ctx.plugin(AgentRegistry)
   ctx.plugin(invariants)

packages/core/agent-core/tests/agent-core.spec.ts

@@ -4,6 +4,7 @@ import { tmpdir } from 'node:os'
 import { describe, expect, it } from 'vitest'
 import { Context } from 'cordis'
 import Loader from '@cordisjs/plugin-loader'
+import { TOOL_ORDER_REST } from '@deepseek-ai/dsh-system-prompt'
 import * as agentCore from '../src/index.ts'
 import { AgentId } from '@deepseek-ai/dsh-agent'
 import { SessionId } from '@deepseek-ai/dsh-session'
@@ -147,6 +148,23 @@ describe('dsh-agent-core bundle', () => {
     }
   })
 
+  it('forwards toolOrder to the system-prompt assembly', async () => {
+    const ctx = await mount({ toolOrder: ['zulu', TOOL_ORDER_REST] })
+    // The bundle's own bash tools pend on the absent `ctx.bash` executor in
+    // this providerless mount, so register two plain tools to order.
+    for (const name of ['alpha', 'zulu']) {
+      ctx.get('tools')!.register({
+        name,
+        description: name,
+        parameters: {},
+        execute: async () => [],
+      })
+    }
+    const assembly = await ctx.get('systemPrompt')!.assemble()
+    expect(assembly.tools.map(tool => tool.name)).toEqual(['zulu', 'alpha'])
+    await ctx.fiber.dispose()
+  })
+
   it('supports direct apply with project instructions disabled and no forwarded agents', async () => {
     const ctx = new Context()
     agentCore.apply(ctx, { projectInstructions: false })

packages/core/agent-core/tests/gen-config-catalog.spec.ts

@@ -0,0 +1,458 @@
+/**
+ * Negative-path tests for the config catalog generator (`scripts/gen-config-catalog.ts`).
+ *
+ * The generated catalog is frozen by a regenerate-and-diff freshness gate, so
+ * the freshness half is exercised by `pnpm run verify-config-catalog` in CI.
+ * What a freshness diff CANNOT prove is that the generator REJECTS malformed
+ * source the way it promises to — an unclassifiable package, an undocumented
+ * config field, a schema key the config type does not declare, or a referenced
+ * type name that resolves nowhere. These tests drive `collectConfigCatalog()`
+ * against synthetic fixture packages to prove each guard fires (and that
+ * well-formed packages classify and extract correctly), mirroring the
+ * negative tests for gen-cordis-catalog. The spec lives in this package
+ * because agent-core is the config-composition plugin (its schema is the
+ * intersection of its children's), the shape the generator's cross-package
+ * folding exists for.
+ */
+
+import { mkdtempSync, mkdirSync, rmSync, writeFileSync } from 'node:fs'
+import { tmpdir } from 'node:os'
+import { join } from 'node:path'
+import { afterEach, describe, expect, it } from 'vitest'
+import { collectConfigCatalog, render } from '../../../../scripts/gen-config-catalog.ts'
+
+/** Write one fixture package (package.json + src files) under a scan root. */
+function writePkg(root: string, dir: string, name: string, files: Record<string, string>): void {
+  const pkgDir = join(root, 'packages', dir)
+  mkdirSync(join(pkgDir, 'src'), { recursive: true })
+  writeFileSync(join(pkgDir, 'package.json'), JSON.stringify({ name }))
+  for (const [rel, text] of Object.entries(files)) writeFileSync(join(pkgDir, rel), text)
+}
+
+const roots: string[] = []
+const makeRoot = (): string => {
+  const root = mkdtempSync(join(tmpdir(), 'config-catalog-'))
+  roots.push(root)
+  return root
+}
+/** One-package fixture: the common case. */
+const make = (files: Record<string, string>, name = '@fix/one'): string => {
+  const root = makeRoot()
+  writePkg(root, 'group/one', name, files)
+  return root
+}
+
+afterEach(() => {
+  while (roots.length) rmSync(roots.pop()!, { recursive: true, force: true })
+})
+
+const DOCUMENTED_CONFIG = `/** Fixture config. */
+export interface Config {
+  /** A knob. */
+  knob?: string
+}
+`
+
+describe('gen-config-catalog classification', () => {
+  it('classifies an apply plugin with a config parameter and extracts the paste', () => {
+    const entries = collectConfigCatalog(make({
+      'src/index.ts': `import type { Context } from 'cordis'
+export const inject = ['tools']
+${DOCUMENTED_CONFIG}
+/** Load. */
+export function apply(ctx: Context, config: Config): void {}
+`,
+    }))
+    expect(entries).toHaveLength(1)
+    expect(entries[0]).toMatchObject({ pkg: '@fix/one', kind: 'config', configTypeName: 'Config', inject: ['tools'] })
+    expect(entries[0]?.pastes?.[0]?.text).toContain('/** A knob. */')
+  })
+
+  it('classifies a default service class, reading its constructor and static inject', () => {
+    const entries = collectConfigCatalog(make({
+      'src/index.ts': `import type { Context } from 'cordis'
+import z from 'schemastery'
+${DOCUMENTED_CONFIG}
+/** Fixture service. */
+export default class Fix {
+  static inject = ['llm']
+  static Config = z.object({ knob: z.string() }) as unknown as z<Config>
+  constructor(ctx: Context, config: Config) {}
+}
+`,
+    }))
+    expect(entries[0]).toMatchObject({ kind: 'config', className: 'Fix', inject: ['llm'], schemaKeys: ['knob'] })
+  })
+
+  it('classifies an abstract default class as a seam', () => {
+    const entries = collectConfigCatalog(make({
+      'src/index.ts': 'export default abstract class FixSeam { abstract run(): void }\n',
+    }))
+    expect(entries[0]).toMatchObject({ kind: 'seam', className: 'FixSeam' })
+  })
+
+  it('classifies a plugin whose apply takes no config as no-config', () => {
+    const entries = collectConfigCatalog(make({
+      'src/index.ts': 'import type { Context } from \'cordis\'\n/** Load. */\nexport function apply(ctx: Context): void {}\n',
+    }))
+    expect(entries[0]?.kind).toBe('no-config')
+  })
+
+  it('classifies a module with neither default export nor apply as a library', () => {
+    const entries = collectConfigCatalog(make({
+      'src/index.ts': 'export const helper = 1\n',
+    }))
+    expect(entries[0]?.kind).toBe('library')
+  })
+
+  it('hard-errors on a package with no entry file', () => {
+    const root = makeRoot()
+    mkdirSync(join(root, 'packages', 'group', 'one'), { recursive: true })
+    writeFileSync(join(root, 'packages', 'group', 'one', 'package.json'), JSON.stringify({ name: '@fix/one' }))
+    expect(() => collectConfigCatalog(root)).toThrow(/entry .* is missing or unreadable/)
+  })
+
+  it('hard-errors on a package.json without a name', () => {
+    const root = makeRoot()
+    mkdirSync(join(root, 'packages', 'group', 'one', 'src'), { recursive: true })
+    writeFileSync(join(root, 'packages', 'group', 'one', 'package.json'), '{}')
+    expect(() => collectConfigCatalog(root)).toThrow(/has no "name"/)
+  })
+})
+
+describe('gen-config-catalog config extraction guards', () => {
+  it('hard-errors on a config field with no JSDoc prose', () => {
+    expect(() => collectConfigCatalog(make({
+      'src/index.ts': `import type { Context } from 'cordis'
+export interface Config {
+  knob?: string
+}
+/** Load. */
+export function apply(ctx: Context, config: Config): void {}
+`,
+    }))).toThrow(/config field 'Config\.knob' .* has no JSDoc prose/)
+  })
+
+  it('hard-errors on an undocumented field nested in a type literal', () => {
+    expect(() => collectConfigCatalog(make({
+      'src/index.ts': `import type { Context } from 'cordis'
+/** Fixture config. */
+export interface Config {
+  /** Entries. */
+  entries: {
+    id: string
+  }[]
+}
+/** Load. */
+export function apply(ctx: Context, config: Config): void {}
+`,
+    }))).toThrow(/config field 'Config\.entries\.id' .* has no JSDoc prose/)
+  })
+
+  it('pastes a package-local type transitively and records external refs', () => {
+    const entries = collectConfigCatalog(make({
+      'src/index.ts': `import type { Context } from 'cordis'
+import type { Mode } from './types.ts'
+import type { Remote } from '@fix/dep'
+/** Fixture config. */
+export interface Config {
+  /** The mode. */
+  mode?: Mode
+  /** The remote. */
+  remote?: Remote
+}
+/** Load. */
+export function apply(ctx: Context, config: Config): void {}
+`,
+      'src/types.ts': '/** Fixture mode. */\nexport type Mode = \'a\' | \'b\'\n',
+    }))
+    expect(entries[0]?.pastes?.map(p => p.source)).toEqual([
+      'packages/group/one/src/index.ts:5',
+      'packages/group/one/src/types.ts:2',
+    ])
+    expect(entries[0]?.refs).toEqual([{ alias: 'Remote', imported: 'Remote', specifier: '@fix/dep' }])
+  })
+
+  it('hard-errors on a referenced type name that resolves nowhere', () => {
+    expect(() => collectConfigCatalog(make({
+      'src/index.ts': `import type { Context } from 'cordis'
+/** Fixture config. */
+export interface Config {
+  /** The ghost. */
+  ghost?: Ghost
+}
+/** Load. */
+export function apply(ctx: Context, config: Config): void {}
+`,
+    }))).toThrow(/references 'Ghost' .* neither declared in the package, imported, nor a known global/)
+  })
+
+  it('hard-errors on a config type imported from another package', () => {
+    expect(() => collectConfigCatalog(make({
+      'src/index.ts': `import type { Context } from 'cordis'
+import type { Config } from '@fix/dep'
+/** Load. */
+export function apply(ctx: Context, config: Config): void {}
+`,
+    }))).toThrow(/config type 'Config' is imported from '@fix\/dep'/)
+  })
+
+  it('hard-errors when one name resolves to two different declarations across the closure', () => {
+    expect(() => collectConfigCatalog(make({
+      'src/index.ts': `import type { Context } from 'cordis'
+import type { A } from './a.ts'
+import type { B } from './b.ts'
+/** Fixture config. */
+export interface Config {
+  /** A. */
+  a?: A
+  /** B. */
+  b?: B
+}
+/** Load. */
+export function apply(ctx: Context, config: Config): void {}
+`,
+      'src/a.ts': '/** First Option. */\nexport interface Option {\n  /** X. */\n  x?: string\n}\n/** A. */\nexport interface A {\n  /** O. */\n  o?: Option\n}\n',
+      'src/b.ts': '/** Second Option. */\nexport interface Option {\n  /** Y. */\n  y?: string\n}\n/** B. */\nexport interface B {\n  /** O. */\n  o?: Option\n}\n',
+    }))).toThrow(/type name 'Option' resolves to two different declarations/)
+  })
+})
+
+describe('gen-config-catalog schema cross-check', () => {
+  it('accepts a chained schema whose keys all appear on the config type', () => {
+    const entries = collectConfigCatalog(make({
+      'src/index.ts': `import type { Context } from 'cordis'
+import z from 'schemastery'
+${DOCUMENTED_CONFIG}
+export const Config: z<Config> = z.object({ knob: z.string() }).default({})
+/** Load. */
+export function apply(ctx: Context, config: Config): void {}
+`,
+    }))
+    expect(entries[0]?.schemaKeys).toEqual(['knob'])
+  })
+
+  it('hard-errors on a schema key the config type does not declare', () => {
+    expect(() => collectConfigCatalog(make({
+      'src/index.ts': `import type { Context } from 'cordis'
+import z from 'schemastery'
+${DOCUMENTED_CONFIG}
+export const Config: z<Config> = z.object({ knob: z.string(), hidden: z.number() })
+/** Load. */
+export function apply(ctx: Context, config: Config): void {}
+`,
+    }))).toThrow(/schema validates key 'hidden' but config type 'Config' declares no such member/)
+  })
+
+  it('hard-errors on a NESTED schema key the config type does not declare', () => {
+    expect(() => collectConfigCatalog(make({
+      'src/index.ts': `import type { Context } from 'cordis'
+import z from 'schemastery'
+/** Fixture config. */
+export interface Config {
+  /** Entries. */
+  entries: {
+    /** Id. */
+    id: string
+  }[]
+}
+export const Config: z<Config> = z.object({ entries: z.array(z.object({ id: z.string(), ghost: z.string() })) })
+/** Load. */
+export function apply(ctx: Context, config: Config): void {}
+`,
+    }))).toThrow(/schema validates key 'entries\[\]\.ghost'/)
+  })
+
+  it('resolves nested keys through a workspace-imported intersection part (re-export chains included)', () => {
+    const root = makeRoot()
+    writePkg(root, 'group/dep', '@fix/dep', {
+      'src/index.ts': 'export * from \'./types.ts\'\n',
+      'src/types.ts': '/** Shared options. */\nexport interface Opts {\n  /** Model. */\n  model?: string\n}\n',
+    })
+    writePkg(root, 'group/one', '@fix/one', {
+      'src/index.ts': `import type { Context } from 'cordis'
+import z from 'schemastery'
+import type { Opts } from '@fix/dep'
+/** Fixture config. */
+export interface Config {
+  /** Entries. */
+  entries: (Opts & {
+    /** Id. */
+    id: string
+  })[]
+}
+export const Config: z<Config> = z.object({ entries: z.array(z.object({ id: z.string(), model: z.string() })) })
+/** Load. */
+export function apply(ctx: Context, config: Config): void {}
+`,
+    })
+    expect(() => collectConfigCatalog(root)).not.toThrow()
+  })
+
+  it('resolves nested keys through a Partial<> wrapper', () => {
+    expect(() => collectConfigCatalog(make({
+      'src/index.ts': `import type { Context } from 'cordis'
+import z from 'schemastery'
+/** Caps. */
+export interface Caps {
+  /** X. */
+  x?: boolean
+}
+/** Fixture config. */
+export interface Config {
+  /** Capabilities. */
+  capabilities?: Partial<Caps>
+}
+export const Config: z<Config> = z.object({ capabilities: z.object({ x: z.boolean() }) })
+/** Load. */
+export function apply(ctx: Context, config: Config): void {}
+`,
+    }))).not.toThrow()
+  })
+
+  it('leaves a nested key under an external (unresolvable) type unreported', () => {
+    expect(() => collectConfigCatalog(make({
+      'src/index.ts': `import type { Context } from 'cordis'
+import z from 'schemastery'
+import type { External } from 'some-external-pkg'
+/** Fixture config. */
+export interface Config {
+  /** Options. */
+  options?: External
+}
+export const Config: z<Config> = z.object({ options: z.object({ whatever: z.string() }) })
+/** Load. */
+export function apply(ctx: Context, config: Config): void {}
+`,
+    }))).not.toThrow()
+  })
+
+  it('folds an intersected workspace schema into the subset check', () => {
+    const root = makeRoot()
+    writePkg(root, 'group/leaf', '@fix/leaf', {
+      'src/index.ts': `import type { Context } from 'cordis'
+import z from 'schemastery'
+/** Leaf config. */
+export interface Config {
+  /** Leaf knob. */
+  leaf?: string
+}
+/** Leaf service. */
+export default class Leaf {
+  static Config = z.object({ leaf: z.string() }) as unknown as z<Config>
+  constructor(ctx: Context, config: Config) {}
+}
+`,
+    })
+    writePkg(root, 'group/bundle', '@fix/bundle', {
+      'src/index.ts': `import type { Context } from 'cordis'
+import z from 'schemastery'
+import Leaf from '@fix/leaf'
+/** Bundle config. */
+export interface Config {
+  /** Forwarded leaf knob. */
+  leaf?: string
+}
+export const Config = z.intersect([Leaf.Config]) as unknown as z<Config>
+/** Load. */
+export function apply(ctx: Context, config: Config): void {}
+`,
+    })
+    const entries = collectConfigCatalog(root)
+    expect(entries.find(e => e.pkg === '@fix/bundle')?.schemaComposes).toEqual(['@fix/leaf'])
+  })
+
+  it('resolves composed nested keys through an indexed-access forwarder', () => {
+    const root = makeRoot()
+    writePkg(root, 'group/leaf', '@fix/leaf', {
+      'src/index.ts': `import type { Context } from 'cordis'
+import z from 'schemastery'
+/** Leaf config. */
+export interface Config {
+  /** Agents. */
+  agents: {
+    /** Id. */
+    id: string
+  }[]
+}
+/** Leaf service. */
+export default class Leaf {
+  static Config = z.object({ agents: z.array(z.object({ id: z.string() })) }) as unknown as z<Config>
+  constructor(ctx: Context, config: Config) {}
+}
+`,
+    })
+    writePkg(root, 'group/bundle', '@fix/bundle', {
+      'src/index.ts': `import type { Context } from 'cordis'
+import z from 'schemastery'
+import Leaf, { type Config as LeafConfig } from '@fix/leaf'
+/** Bundle config forwarding the leaf's agents list. */
+export interface Config {
+  /** Forwarded agents list. */
+  agents?: LeafConfig['agents']
+}
+export const Config = z.intersect([Leaf.Config]) as unknown as z<Config>
+/** Load. */
+export function apply(ctx: Context, config: Config): void {}
+`,
+    })
+    expect(() => collectConfigCatalog(root)).not.toThrow()
+  })
+
+  it('hard-errors when an intersected schema key is missing from the bundle config type', () => {
+    const root = makeRoot()
+    writePkg(root, 'group/leaf', '@fix/leaf', {
+      'src/index.ts': `import type { Context } from 'cordis'
+import z from 'schemastery'
+/** Leaf config. */
+export interface Config {
+  /** Leaf knob. */
+  leaf?: string
+}
+/** Leaf service. */
+export default class Leaf {
+  static Config = z.object({ leaf: z.string() }) as unknown as z<Config>
+  constructor(ctx: Context, config: Config) {}
+}
+`,
+    })
+    writePkg(root, 'group/bundle', '@fix/bundle', {
+      'src/index.ts': `import type { Context } from 'cordis'
+import z from 'schemastery'
+import Leaf from '@fix/leaf'
+/** Bundle config that forgot to declare the forwarded field. */
+export interface Config {
+  /** Unrelated. */
+  other?: string
+}
+export const Config = z.intersect([Leaf.Config]) as unknown as z<Config>
+/** Load. */
+export function apply(ctx: Context, config: Config): void {}
+`,
+    })
+    expect(() => collectConfigCatalog(root)).toThrow(/schema validates key 'leaf' but config type 'Config' declares no such member/)
+  })
+})
+
+describe('gen-config-catalog render', () => {
+  it('renders sections, fences, and the terse classification lists', () => {
+    const root = makeRoot()
+    writePkg(root, 'group/one', '@fix/one', {
+      'src/index.ts': `import type { Context } from 'cordis'
+${DOCUMENTED_CONFIG}
+/** Load. */
+export function apply(ctx: Context, config: Config): void {}
+`,
+    })
+    writePkg(root, 'group/lib', '@fix/lib', { 'src/index.ts': 'export const helper = 1\n' })
+    writePkg(root, 'group/seam', '@fix/seam', {
+      'src/index.ts': 'export default abstract class Seam { abstract run(): void }\n',
+    })
+    const page = render(collectConfigCatalog(root))
+    expect(page).toContain('## `@fix/one`')
+    expect(page).toContain('```ts config-catalog')
+    expect(page).toContain('/** A knob. */')
+    expect(page).toContain('- `@fix/lib` ([`packages/group/lib/src/index.ts`](../packages/group/lib/src/index.ts))')
+    expect(page).toContain('- `@fix/seam` — abstract `Seam`')
+  })
+})

packages/core/agent-loop/README.md

@@ -55,12 +55,15 @@ forever:
     STEP loop:
       drain steering
       assembly = systemPrompt.assemble({agent})  ⟵ renderPrompt(assembly) IS the full prompt
-      await serial agent/pre-step        ⟵ surface mutation (compaction) outside the step
+      prefix ??= waterfall agent/session-prefix   ⟵ once per instance (first step): frozen
+                                                session prefix; on the header, never history
+      await serial agent/pre-step(…, prefix)  ⟵ surface mutation (compaction) outside the step;
+                                                pressure gates see the prefix the request carries
       boundary = session.deriveMessages()   ⟵ reconstruction boundary: same sync frame,
       session('step/start')                     strictly before step/start
       config = waterfall agent/request       ⟵ frozen seed; return a replacement to switch
       session('request/header'[-delta])      ⟵ the header event this request owes the log
-      stream llm.stream(freeze({header..., messages: boundary})) → session('assistant/chunk')
+      stream llm.stream(freeze({header..., messages: prefix+boundary})) → session('assistant/chunk')
       message = waterfall agent/step-result
       session('assistant/message')
       each tool-call: session('tool/call')
@@ -84,7 +87,7 @@ Cancellation: `agent.cancel()` is the single public stop primitive — it clears
 ### What is NOT here
 
 Everything that goes beyond "call the model, run the tools, repeat" belongs to plugins listening on the event taxonomy:
-- Hooks: `agent/session-start`, `agent/prompt-submit`, `agent/pre-step`, `agent/request`, `agent/step-result`, `tools/pre-execute`, `tools/post-execute`, `agent/turn-continuation`
+- Hooks: `agent/session-start`, `agent/prompt-submit`, `agent/pre-step`, `agent/request`, `agent/session-prefix`, `agent/step-result`, `tools/pre-execute`, `tools/post-execute`, `agent/turn-continuation`
 - Compaction: `agent/pre-step`
 - Sandbox, permission, plan mode: `tools/pre-execute` (deny/ask gate), `tools/post-execute`
 - Sub-agents: implemented outside the loop as `ctx.subagents` providers; in-process providers use `ctx.agents.create()` and owned `AgentHandle` teardown, while child streaming/progress and background/poll collection remain deferred.

packages/core/agent-loop/src/agent.ts

@@ -22,6 +22,10 @@ import { isTurnOpen, lastTurnNumber, runLoop } from './loop.ts'
  * the agent/* event taxonomy — plugins never need this class.
  */
 export class ReactLoopAgent implements Agent {
+  /**
+   * The queued + steering FIFOs behind {@link send}/{@link steer}. Public so
+   * the driver loop can drain it; {@link cancel} clears it wholesale.
+   */
   readonly inbox = new Inbox()
 
   private _status: AgentStatus = 'idle'
@@ -256,6 +260,8 @@ export class ReactLoopAgent implements Agent {
    * promise (unblocking the idle wait), releases any `whenIdle` waiters, and
    * aborts the current request if any. The returned `agent.done` promise
    * resolves once the loop exits.
+   * @returns the disposer — idempotent and infallible (it runs inside the
+   *   fiber's LIFO disposal chain, where a throw would skip later disposers).
    */
   start(): () => void {
     this.done = runLoop(this.ctx, this, {

packages/core/agent-loop/src/inbox.ts

@@ -24,30 +24,47 @@ export class Inbox {
   private steeringMessages: InboxMessage[] = []
   private wakeup: (() => void) | undefined
 
-  /** Resolves when a queued message arrives (used by the idle loop). */
+  /** True while queued messages are pending — read by the idle wait's fast path and the loop's turn-start checks. */
   get hasQueued(): boolean {
     return this.queuedMessages.length > 0
   }
 
+  /** True while steering messages are pending — read by `cancel()`'s arm gate and the loop's stop-override check. */
   get hasSteering(): boolean {
     return this.steeringMessages.length > 0
   }
 
+  /**
+   * Add a message to the queued FIFO and wake a parked {@link waitForQueued}.
+   * @param message - the message to queue for the next turn start.
+   */
   enqueue(message: InboxMessage): void {
     this.queuedMessages.push(message)
     this.wakeup?.()
   }
 
+  /**
+   * Add a message to the steering FIFO. Deliberately no wakeup: steering is
+   * drained between steps of a running turn, never by the idle wait —
+   * `Agent.steer()` on an idle agent falls back to `send()` instead.
+   * @param message - the message to inject between steps of the running turn.
+   */
   steer(message: InboxMessage): void {
     this.steeringMessages.push(message)
   }
 
-  /** Drain all queued messages (turn start). */
+  /**
+   * Drain all queued messages (turn start).
+   * @returns the drained messages in arrival order; the queued FIFO is left empty.
+   */
   drainQueued(): InboxMessage[] {
     return this.queuedMessages.splice(0)
   }
 
-  /** Drain all steering messages (between steps). */
+  /**
+   * Drain all steering messages (between steps).
+   * @returns the drained messages in arrival order; the steering FIFO is left empty.
+   */
   drainSteering(): InboxMessage[] {
     return this.steeringMessages.splice(0)
   }
@@ -62,7 +79,12 @@ export class Inbox {
     this.steeringMessages.length = 0
   }
 
-  /** Wait until a queued message arrives or `cancel` resolves. */
+  /**
+   * Wait until a queued message arrives or `cancel` resolves.
+   * @param cancel - a promise whose resolution abandons the wait without a
+   *   message (the driver loop passes the agent's disposed promise so a parked
+   *   loop can exit).
+   */
   waitForQueued(cancel: Promise<void>): Promise<void> {
     if (this.hasQueued) return Promise.resolve()
     const { promise, resolve } = Promise.withResolvers<void>()

packages/core/agent-loop/src/index.ts

@@ -29,9 +29,14 @@ declare module 'cordis' {
   }
 }
 
+/**
+ * Plugin config: the agents to create — or resume, via `resumeSessionId` —
+ * declaratively at startup, so a cordis.yml deployment needs no code.
+ */
 export interface Config {
   /** Agents created from configuration at startup. */
   agents: (AgentOptions & {
+    /** Agent id to register under; also seeds the fresh per-run session id (`${id}-session-<uuid>`). */
     id: AgentId
     /**
      * If set, the config agent RESUMES this persisted session id instead of

packages/core/agent-loop/src/loop.ts

@@ -157,13 +157,17 @@ export interface LoopHandle {
  *       drain steering → session('steering/message')  ⟵ catches late steering
  *       assembly = ctx.systemPrompt.assemble({agent}) ⟵ waterfall system-prompt/assemble; renderPrompt
  *                                                        (persona section + {{variables}}) IS the full prompt
- *       await ctx.serial('agent/pre-step')            ⟵ surface mutation (compaction) OUTSIDE the step
+ *       prefix ??= waterfall agent/session-prefix     ⟵ once per loop instance (first step): frozen
+ *                                                        session prefix; logged on the header, never
+ *                                                        session history
+ *       await ctx.serial('agent/pre-step', …, prefix) ⟵ surface mutation (compaction) OUTSIDE the step;
+ *                                                        pressure gates see the prefix the request carries
  *       boundary = session.deriveMessages()           ⟵ the reconstruction boundary: snapshot in the
  *       session('step/start')                            same sync frame, strictly before step/start
  *       config = waterfall agent/request(config)      ⟵ frozen seed; a returned replacement switches
  *       session('request/header'|'request/header-delta')  ⟵ the header event this request owes the
  *                                                        log (initial/resume anchor, delta, fallback)
- *       req = freeze({header..., messages: boundary, sessionId, signal})
+ *       req = freeze({header..., messages: prefix+boundary, sessionId, signal})
  *       stream ctx.llm.stream(req)                    ⟵ waterfall llm/stream (raw chunks, frozen req)
  *         session('assistant/chunk')
  *       msg = waterfall agent/step-result             ⟵ BEFORE the log append, so the
@@ -185,6 +189,9 @@ export interface LoopHandle {
  *     re-enqueue leftover steering as queued          ⟵ steering is never stranded
  *   idle (emit agent/status) unless more queued
  * ```
+ * @param ctx - the plugin context the loop reaches events (agent/…, session/flush) and services (systemPrompt, llm, tools) through.
+ * @param agent - the agent this invocation drives for its whole lifetime (its inbox, session, and options).
+ * @param handle - the bridge to the agent's mutable state: status/abort setters plus the disposal and cancel-marker reads.
  */
 export async function runLoop(ctx: Context, agent: ReactLoopAgent, handle: LoopHandle): Promise<void> {
   // Per-instance transmission bookkeeping: whether THIS loop instance has
@@ -469,6 +476,50 @@ async function runTurn(
         break
       }
 
+      // Compose the session prefix ONCE per loop instance, lazily before the
+      // instance's first pre-step: request-only messages placed in front of
+      // the ENTIRE derived history on every request this instance sends. It
+      // MUST precede the pre-step seam so compaction gates on THIS instance's
+      // prefix — reading a previous instance's logged prefix would let a
+      // resumed/forked instance whose contributor grew skip compaction and
+      // ship an over-window first request. The result is deep-cloned
+      // (decoupled from listener-held references), deep-frozen, and cached on
+      // the transmission bookkeeping, so reuse is structural — the prefix
+      // cannot change mid-session and the provider prefix cache holds by
+      // construction (resume = a new instance = a recompose, anchored by its
+      // 'resume' snapshot). The prefix is not session history — the header
+      // event in runStep is its only durable record
+      // (EpochHeader.messagePrefix). The frozen empty seed serves both the
+      // listener chain and the no-listener fallback: a contribution is a
+      // RETURNED extension of `await next()`, never an in-place push. This
+      // runs OUTSIDE the step, before the boundary snapshot: a composing
+      // listener's session append lands before the boundary and joins the
+      // CURRENT request.
+      if (transmission.sessionPrefix === undefined) {
+        const emptyPrefix: Message[] = deepFreeze([])
+        const composed = await ctx.waterfall(
+          'agent/session-prefix', agent, emptyPrefix, abort.signal,
+          () => Promise.resolve(emptyPrefix),
+        )
+
+        // Interruption landing during prefix composition: mirror the assembly
+        // window above — drop the about-to-start step without running the
+        // seam, and DISCARD the composition instead of caching it. An
+        // abort-aware listener may have returned a degraded fallback under
+        // the firing signal; committing it would ship a prefix no request
+        // ever used (and no header ever logged) on this instance's next real
+        // request. The next turn recomposes under a live signal — the cache
+        // only ever holds a fully composed prefix. The cache-hit path needs
+        // no such check: nothing awaits between the assembly check above and
+        // the pre-step seam.
+        if (handle.isCancelled() || handle.isDisposed()) {
+          handle.setAbort(undefined)
+          reason = handle.isDisposed() ? { kind: 'disposed' } : { kind: 'aborted', reason: handle.cancelReason() }
+          break
+        }
+        transmission.sessionPrefix = deepFreeze(structuredClone(composed))
+      }
+
       // Pre-step surface-mutation checkpoint (compaction), fired OUTSIDE the
       // step: after `turn/start` (and the prior step's close) but before
       // `step/start`, so a compaction's log-only `compact/*` records and its
@@ -479,8 +530,10 @@ async function runTurn(
       // concurrent listeners cannot interleave their `session.append`s. A
       // throwing listener escapes to the outer catch, which closes the (not-yet-
       // open) step as a no-op and ends the turn via failTurn — a broken
-      // pre-step plugin ends the turn, not the loop.
-      await ctx.serial('agent/pre-step', agent, turn, step, fullSystemPrompt, abort.signal)
+      // pre-step plugin ends the turn, not the loop. The composed session
+      // prefix rides along so token-pressure listeners count everything the
+      // request will actually carry.
+      await ctx.serial('agent/pre-step', agent, turn, step, fullSystemPrompt, transmission.sessionPrefix, abort.signal)
 
       // Interruption landing during the pre-step seam: do not open an empty step.
       if (handle.isCancelled() || handle.isDisposed()) {
@@ -671,11 +724,12 @@ function drainSteering(agent: ReactLoopAgent, turn: number): boolean {
 }
 
 /** One step: build the request from the boundary snapshot + the step's
- * header → log the header event the request owes → stream model → record →
- * execute tools. The caller assembles the system prompt, fires the
- * `agent/pre-step` seam, snapshots the derivation, and opens the step BEFORE
- * calling this, so `boundaryMessages` is exactly the surface prefix at
- * step/start and already reflects any compaction. */
+ * header → compose the session prefix if this instance has none yet → log
+ * the header event the request owes → stream model → record → execute
+ * tools. The caller assembles the
+ * system prompt, fires the `agent/pre-step` seam, snapshots the derivation,
+ * and opens the step BEFORE calling this, so `boundaryMessages` is exactly
+ * the surface prefix at step/start and already reflects any compaction. */
 async function runStep(
   ctx: Context,
   agent: ReactLoopAgent,
@@ -715,22 +769,30 @@ async function runStep(
     throw new Error(`agent "${agent.id}" has no model: set AgentOptions.model or supply one via the agent/request waterfall`)
   }
 
+  // The session prefix was composed (once per instance) before this step's
+  // pre-step seam — the caller guarantees it, so the cache is always set here.
+  // eslint-disable-next-line @typescript-eslint/no-non-null-assertion -- runTurn composes the prefix before every runStep call
+  const sessionPrefix = transmission.sessionPrefix!
+
   // The request header (the log's request/header* vocabulary): canonical form,
-  // recorded before dispatch so the log always explains the request.
+  // recorded before dispatch so the log always explains the request —
+  // including the session prefix, which no other event carries.
   const header = canonicalHeader({
     config,
     ...system ? { system } : {},
     ...assembly.tools.length > 0 ? { tools: assembly.tools } : {},
+    ...sessionPrefix.length > 0 ? { messagePrefix: sessionPrefix } : {},
   })
   recordRequestHeader(session, transmission, header)
 
   // Build and freeze: the request is a pure function of (boundary snapshot,
   // logged header) — llm/stream listeners and adapters read it, mutation
   // throws. sessionId + frozen is the loop-built marker the dev invariant
-  // keys on.
+  // keys on. Message order: header.messagePrefix, then the boundary
+  // snapshot — the reconstruction equation the invariant recomputes.
   const request: GenerateOptions = deepFreeze({
     model: header.config.model,
-    messages: boundaryMessages,
+    messages: [...header.messagePrefix ?? [], ...boundaryMessages],
     ...header.system !== undefined ? { system: header.system } : {},
     ...header.tools !== undefined ? { tools: header.tools } : {},
     ...header.config.temperature !== undefined ? { temperature: header.config.temperature } : {},
@@ -877,7 +939,11 @@ function withoutToolCalls(message: Message): Message {
   return { ...message, content: message.content.filter(block => block.type !== 'tool-call') }
 }
 
-/** The last turn number in a (possibly seeded) session log, or 0. */
+/**
+ * The last turn number in a (possibly seeded) session log, or 0.
+ * @param session - the session whose log is scanned for the latest `turn/start`.
+ * @returns the latest `turn/start`'s turn number, or 0 when the log has none (the next turn is this plus one).
+ */
 export function lastTurnNumber(session: Session): number {
   const lastStart = session.events.findLast(event => event.type === 'turn/start')
   return lastStart?.data.turn ?? 0
@@ -891,6 +957,8 @@ export function lastTurnNumber(session: Session): number {
  * returns to idle), so status is not a reliable open-turn signal. Used by
  * `inject()` to choose between appending into an open turn vs. wrapping the
  * injection in its own one-shot turn (the turn-enclosure RFC).
+ * @param session - the session whose log is inspected.
+ * @returns true when the log's last turn boundary is a `turn/start` with no matching `turn/end` yet.
  */
 export function isTurnOpen(session: Session): boolean {
   const last = session.events.findLast(e => e.type === 'turn/start' || e.type === 'turn/end')

packages/core/agent-loop/src/request-log.ts

@@ -12,14 +12,26 @@
 
 import { diffHeader, headerEquals, applyHeaderDelta } from '@deepseek-ai/dsh-session'
 import type { EpochHeader, Session } from '@deepseek-ai/dsh-session'
+import type { Message } from '@deepseek-ai/dsh-llm'
 
 /** Per-loop-instance bookkeeping: whether THIS instance has logged a header yet. */
 export interface TransmissionLog {
   /** True once this loop instance appended its anchoring `request/header` snapshot. */
   loggedHeader: boolean
+  /**
+   * The instance's composed session prefix (the `agent/session-prefix`
+   * waterfall's deep-frozen product), cached on the instance's first
+   * request-building step and reused verbatim for every request it sends —
+   * the structural guarantee that the prefix never changes mid-session.
+   * `undefined` until composed.
+   */
+  sessionPrefix?: Message[]
 }
 
-/** Fresh bookkeeping for a newly-started loop instance. */
+/**
+ * Fresh bookkeeping for a newly-started loop instance.
+ * @returns state with `loggedHeader` false, so the instance's first request appends an anchoring snapshot.
+ */
 export function createTransmissionLog(): TransmissionLog {
   return { loggedHeader: false }
 }
@@ -58,7 +70,7 @@ export function recordRequestHeader(session: Session, state: TransmissionLog, he
   const baseline = session.requestHeader()!
   if (headerEquals(baseline, header)) return
   const delta = diffHeader(baseline, header)
-  /* v8 ignore next -- headerEquals false ⟹ diffHeader defined: both compare the same three parts */
+  /* v8 ignore next -- headerEquals false ⟹ diffHeader defined: both compare the same four parts */
   if (delta === undefined) return
   if (headerEquals(applyHeaderDelta(baseline, delta), header)) {
     session.append('request/header-delta', delta)

packages/core/agent-loop/tests/cancel.spec.ts

@@ -12,7 +12,7 @@
 
 import { describe, expect, it } from 'vitest'
 import { Context } from 'cordis'
-import LlmService from '@deepseek-ai/dsh-llm'
+import LlmService, { type Message } from '@deepseek-ai/dsh-llm'
 import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session'
 import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
 import ToolRegistry from '@deepseek-ai/dsh-tools'
@@ -166,6 +166,103 @@ describe('Agent.cancel()', () => {
     expect(reasons.length).toBe(2)
   })
 
+  it('cancel from inside the agent/session-prefix waterfall drops the step (prefix-composition window)', async () => {
+    const adapter = new MockAdapter([textResponse('should not stream')])
+    const ctx = await harness(adapter)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+
+    // Prefix composition runs before the pre-step seam on the instance's first
+    // step; a cancel landing inside it must drop the about-to-start step
+    // without running the seam or the model.
+    let streamed = false
+    ctx.on('session/event', (_s, event) => { if (event.type === 'assistant/chunk') streamed = true })
+    ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next) => {
+      agent.cancel('from prefix composition')
+      return next()
+    })
+
+    const reasons: TurnEndReason[] = []
+    ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
+
+    send(agent, 'go')
+    await waitForIdle(ctx, agent)
+
+    expect(streamed).toBe(false)
+    expect(reasons).toEqual([{ kind: 'aborted', reason: 'from prefix composition' }])
+  })
+
+  it('disposal from inside the agent/session-prefix waterfall ends the turn disposed (prefix-composition window)', async () => {
+    const adapter = new MockAdapter([textResponse('should not stream')])
+    const ctx = new Context()
+    await ctx.plugin(LlmService)
+    await ctx.plugin(SessionStore)
+    await ctx.plugin(SystemPrompt)
+    await ctx.plugin(ToolRegistry)
+    await ctx.plugin(AgentRegistry)
+    await ctx.plugin(AgentLoop, { agents: [] })
+    ctx.llm.registerAdapter(['mock'], adapter)
+
+    const handle = ctx.agents.create({
+      agentId: AgentId('a-dispose-prefix'),
+      sessionId: SessionId('dispose-prefix-session'),
+      agentOptions: { model: 'mock' },
+    })
+    const agent = handle.agent as ReactLoopAgent
+
+    let disposalDone: Promise<void> | undefined
+    let streamed = false
+    ctx.on('session/event', (_s, event) => { if (event.type === 'assistant/chunk') streamed = true })
+    ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next) => {
+      disposalDone = handle.dispose()
+      return next()
+    })
+
+    send(agent, 'go')
+    await new Promise(resolve => setTimeout(resolve, 0))
+    await disposalDone
+    await agent.done
+
+    // No step opened, no model call ran, and the turn closed disposed.
+    expect(streamed).toBe(false)
+    expect(adapter.requests).toHaveLength(0)
+    const turnEnd = agent.session.events.findLast(e => e.type === 'turn/end')
+    expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason).toEqual({ kind: 'disposed' })
+  })
+
+  it('a cancel-interrupted prefix composition is discarded: the next send recomposes and ships the fresh prefix (stale-cache guard)', async () => {
+    const adapter = new MockAdapter([textResponse('reply')])
+    const ctx = await harness(adapter)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+
+    // The first composition is interrupted mid-waterfall and — like an
+    // abort-aware listener bailing on a firing signal — contributes nothing.
+    // Caching that degraded result would silently strip the prefix from every
+    // later request of this instance; the loop must discard it and recompose
+    // on the next send, and the SECOND composition's value must be what the
+    // wire and the header log carry.
+    const opener: Message = { role: 'user', content: [{ type: 'text', text: 'fresh opener' }] }
+    let compositions = 0
+    ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next): Promise<Message[]> => {
+      compositions += 1
+      if (compositions === 1) {
+        agent.cancel('mid-composition')
+        return next()
+      }
+      return [opener, ...await next()]
+    })
+
+    send(agent, 'dropped')
+    await waitForIdle(ctx, agent)
+    send(agent, 'real prompt')
+    await waitForIdle(ctx, agent)
+
+    expect(compositions).toBe(2)
+    expect(adapter.requests).toHaveLength(1)
+    expect(adapter.requests[0]?.messages[0]).toEqual(opener)
+    const headerEvent = agent.session.events.find(e => e.type === 'request/header')
+    expect(headerEvent?.type === 'request/header' && headerEvent.data.header.messagePrefix).toEqual([opener])
+  })
+
   it('cancel from a synchronous turn/start session-event listener drops the step (step-start window)', async () => {
     const adapter = new MockAdapter([textResponse('should not stream')])
     const ctx = await harness(adapter)

packages/core/agent-loop/tests/interception.spec.ts

@@ -1,6 +1,6 @@
 import { describe, expect, it } from 'vitest'
 import { Context } from 'cordis'
-import LlmService, { CallId } from '@deepseek-ai/dsh-llm'
+import LlmService, { CallId, type Message } from '@deepseek-ai/dsh-llm'
 import SessionStore, { type SessionEvent, type TurnEndReason } from '@deepseek-ai/dsh-session'
 import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
 import ToolRegistry, { defineTool, type PostToolDecision, type PreToolDecision } from '@deepseek-ai/dsh-tools'
@@ -310,6 +310,162 @@ describe('agent/session-start', () => {
   })
 })
 
+describe('agent/session-prefix', () => {
+  it('composes once per loop instance and fronts every request; the header records it; history stays untouched', async () => {
+    const adapter = new MockAdapter([
+      toolCallResponse('c1', 'echo', { text: 'ping' }),
+      textResponse('done'),
+      textResponse('again'),
+    ])
+    const ctx = await harness(adapter)
+    ctx.tools.register(defineTool({
+      name: 'echo', description: 'echo', parameters: { text: { type: 'string' } },
+      async execute(args) { return [{ type: 'text', text: String(args.text) }] },
+    }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+
+    const reminder: Message = { role: 'user', content: [{ type: 'text', text: '<system-reminder>catalog</system-reminder>' }] }
+    let composed = 0
+    ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next): Promise<Message[]> => {
+      composed += 1
+      return [...await next(), reminder]
+    })
+
+    send(agent, 'go')
+    await waitForIdle(ctx, agent)
+    send(agent, 'next turn')
+    await waitForIdle(ctx, agent)
+
+    // Three requests (two turns), ONE composition: the frozen product is
+    // reused verbatim, so the prefix cannot drift mid-session.
+    expect(adapter.requests).toHaveLength(3)
+    expect(composed).toBe(1)
+    for (const request of adapter.requests) {
+      expect(request.messages[0]).toEqual(reminder)
+    }
+    // The anchoring snapshot is the prefix's durable record — and the ONLY
+    // header event: reuse means no request/header-delta ever.
+    const headerEvents = events(agent).filter(e => e.type === 'request/header' || e.type === 'request/header-delta')
+    expect(headerEvents).toHaveLength(1)
+    expect(headerEvents[0]?.type === 'request/header' && headerEvents[0].data.header.messagePrefix).toEqual([reminder])
+    // Never session history: the derivation starts at the real user prompt.
+    expect(agent.session.deriveMessages()[0]).toEqual({ role: 'user', content: [{ type: 'text', text: 'go' }] })
+  })
+
+  it('composes before the first pre-step and hands the prefix to the seam (pressure gates see the real value)', async () => {
+    const adapter = new MockAdapter([textResponse('ok')])
+    const ctx = await harness(adapter)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+
+    const reminder: Message = { role: 'user', content: [{ type: 'text', text: 'opener' }] }
+    const order: string[] = []
+    ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next): Promise<Message[]> => {
+      order.push('compose')
+      return [reminder, ...await next()]
+    })
+    const seen: (readonly Message[])[] = []
+    ctx.on('agent/pre-step', (_agent, _turn, _step, _system, sessionPrefix) => {
+      order.push('pre-step')
+      seen.push(sessionPrefix)
+    })
+
+    send(agent, 'hi')
+    await waitForIdle(ctx, agent)
+
+    // Composition precedes the pre-step seam, and the seam receives THIS
+    // instance's composed prefix — a token-pressure gate (compaction) counts
+    // what the request will actually carry, never a stale logged prefix.
+    expect(order).toEqual(['compose', 'pre-step'])
+    expect(seen[0]).toEqual([reminder])
+  })
+
+  it('the canonical prepend pattern composes contributions in registration order', async () => {
+    const adapter = new MockAdapter([textResponse('ok')])
+    const ctx = await harness(adapter)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+
+    // Both listeners use the canonical `[mine, ...await next()]` prepend: the
+    // waterfall unwinds innermost-first (the second listener's array is built
+    // first), so prepending puts the FIRST-registered contribution first.
+    ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next): Promise<Message[]> => {
+      return [{ role: 'user', content: [{ type: 'text', text: 'first' }] }, ...await next()]
+    })
+    ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next): Promise<Message[]> => {
+      return [{ role: 'user', content: [{ type: 'text', text: 'second' }] }, ...await next()]
+    })
+
+    send(agent, 'hi')
+    await waitForIdle(ctx, agent)
+
+    const texts = adapter.requests[0]!.messages.map(m => m.content[0]?.type === 'text' ? m.content[0].text : '')
+    expect(texts).toEqual(['first', 'second', 'hi'])
+  })
+
+  it('with no contributions the header omits messagePrefix and the request is the bare derivation', async () => {
+    const adapter = new MockAdapter([textResponse('ok')])
+    const ctx = await harness(adapter)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+
+    // A listener that delegates without contributing — the canonical no-op.
+    ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next) => next())
+
+    send(agent, 'hi')
+    await waitForIdle(ctx, agent)
+
+    const headerEvent = events(agent).find(e => e.type === 'request/header')
+    expect(headerEvent?.type === 'request/header' && 'messagePrefix' in headerEvent.data.header).toBe(false)
+    expect(adapter.requests[0]!.messages).toEqual([{ role: 'user', content: [{ type: 'text', text: 'hi' }] }])
+  })
+
+  it('the frozen seed rejects in-place mutation — a contribution is a returned extension', async () => {
+    const adapter = new MockAdapter([textResponse('ok')])
+    const ctx = await harness(adapter)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+
+    let mutationError: unknown
+    ctx.on('agent/session-prefix', async (_agent, prefix, _signal, next): Promise<Message[]> => {
+      try {
+        prefix.push({ role: 'user', content: [{ type: 'text', text: 'smuggled' }] })
+      } catch (error: unknown) {
+        mutationError = error
+      }
+      return next()
+    })
+
+    send(agent, 'hi')
+    await waitForIdle(ctx, agent)
+
+    expect(mutationError).toBeInstanceOf(TypeError)
+    expect(adapter.requests[0]!.messages).toEqual([{ role: 'user', content: [{ type: 'text', text: 'hi' }] }])
+  })
+
+  it('mutating a listener-held reference after composition cannot alter later requests (the cache is a frozen clone)', async () => {
+    const adapter = new MockAdapter([
+      toolCallResponse('c1', 'echo', { text: 'ping' }),
+      textResponse('done'),
+    ])
+    const ctx = await harness(adapter)
+    ctx.tools.register(defineTool({
+      name: 'echo', description: 'echo', parameters: { text: { type: 'string' } },
+      async execute(args) { return [{ type: 'text', text: String(args.text) }] },
+    }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+
+    const held: Message = { role: 'user', content: [{ type: 'text', text: 'v1' }] }
+    ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next): Promise<Message[]> => [...await next(), held])
+
+    send(agent, 'go')
+    await waitForIdle(ctx, agent)
+
+    // The listener mutates the object it contributed AFTER composition; the
+    // cached prefix is a deep-frozen clone, so step 2's request is unchanged.
+    held.content = [{ type: 'text', text: 'v2' }]
+    expect(adapter.requests[1]!.messages[0]).toEqual({ role: 'user', content: [{ type: 'text', text: 'v1' }] })
+    expect(events(agent).filter(e => e.type === 'request/header-delta')).toHaveLength(0)
+  })
+})
+
+
 describe('agent/turn-continuation (ContinuationDecision)', () => {
   it('a continue decision with a reason records next-step steering in the same turn', async () => {
     const adapter = new MockAdapter([textResponse('step 1 no tools'), textResponse('step 2')])

packages/core/agent-loop/tests/tool-order.spec.ts

@@ -0,0 +1,117 @@
+/**
+ * Loop-level tool-order determinism: the request/header event — and therefore
+ * the frozen request the adapter receives — carries the assembly's canonical
+ * tool order (system-prompt's `toolOrder` config, or lexicographic name
+ * order), regardless of the order tool plugins happened to register in.
+ * Registration order is a plugin-load artifact (concurrent dynamic imports
+ * race), so nothing downstream of the registry may depend on it.
+ */
+
+import { describe, expect, it } from 'vitest'
+import { Context } from 'cordis'
+import LlmService from '@deepseek-ai/dsh-llm'
+import SessionStore, { foldRequestHeader } from '@deepseek-ai/dsh-session'
+import SystemPrompt, { TOOL_ORDER_REST } from '@deepseek-ai/dsh-system-prompt'
+import type { Config as SystemPromptConfig } from '@deepseek-ai/dsh-system-prompt'
+import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools'
+import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent'
+import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
+import { MockAdapter, textResponse } from './mock-adapter.ts'
+
+async function harness(adapter: MockAdapter, toolOrder?: SystemPromptConfig['toolOrder']) {
+  const ctx = new Context()
+  await ctx.plugin(LlmService)
+  await ctx.plugin(SessionStore)
+  await ctx.plugin(SystemPrompt, { persona: 'stable base', ...toolOrder !== undefined ? { toolOrder } : {} })
+  await ctx.plugin(ToolRegistry)
+  await ctx.plugin(AgentRegistry)
+  await ctx.plugin(AgentLoop, { agents: [] })
+  ctx.llm.registerAdapter(['mock'], adapter)
+  return ctx
+}
+
+function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
+  return new Promise((resolve) => {
+    const dispose = ctx.on('agent/status', (subject, status) => {
+      if (subject === agent && status === 'idle') {
+        dispose()
+        resolve()
+      }
+    })
+  })
+}
+
+function registerNamed(ctx: Context, name: string) {
+  ctx.tools.register(defineTool({
+    name,
+    description: `the ${name} tool`,
+    parameters: {},
+    async execute() {
+      return [{ type: 'text', text: name }]
+    },
+  }))
+}
+
+/** Run one text-only turn and return the harness context + agent. */
+async function runTurn(registrationOrder: string[], toolOrder?: SystemPromptConfig['toolOrder']) {
+  const adapter = new MockAdapter([textResponse('done')])
+  const ctx = await harness(adapter, toolOrder)
+  for (const name of registrationOrder) registerNamed(ctx, name)
+  const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+  agent.send([{ type: 'text', text: 'go' }])
+  await waitForIdle(ctx, agent)
+  return { ctx, agent, adapter }
+}
+
+describe('loop-level canonical tool order', () => {
+  it('logs the request/header with tools in canonical order, not registration order', async () => {
+    const { agent, adapter } = await runTurn(['zulu', 'alpha', 'mike'])
+    const header = foldRequestHeader(agent.session.events)
+    expect(header?.tools?.map(tool => tool.name)).toEqual(['alpha', 'mike', 'zulu'])
+    // The dispatched request is built FROM the logged header (whose tools the
+    // assembly already canonicalized) and reaches the adapter deep-frozen —
+    // the marker the reconstruction invariant keys on.
+    expect(adapter.requests[0]?.tools?.map(tool => tool.name)).toEqual(['alpha', 'mike', 'zulu'])
+    expect(Object.isFrozen(adapter.requests[0])).toBe(true)
+    expect(adapter.requests[0]?.sessionId).toBe(agent.session.id)
+  })
+
+  it('produces the same header order for any registration order', async () => {
+    const first = await runTurn(['alpha', 'mike', 'zulu'])
+    const second = await runTurn(['zulu', 'mike', 'alpha'])
+    const names = (run: typeof first) => foldRequestHeader(run.agent.session.events)?.tools?.map(tool => tool.name)
+    expect(names(first)).toEqual(['alpha', 'mike', 'zulu'])
+    expect(names(second)).toEqual(names(first))
+  })
+
+  it('honors a configured toolOrder in the logged header and the dispatched request', async () => {
+    const { agent, adapter } = await runTurn(['alpha', 'zulu', 'mike'], ['zulu', TOOL_ORDER_REST])
+    const header = foldRequestHeader(agent.session.events)
+    expect(header?.tools?.map(tool => tool.name)).toEqual(['zulu', 'alpha', 'mike'])
+    expect(adapter.requests[0]?.tools?.map(tool => tool.name)).toEqual(['zulu', 'alpha', 'mike'])
+    expect(Object.isFrozen(adapter.requests[0])).toBe(true)
+  })
+
+  it('fails the turn — no model request — when toolOrder names an unregistered tool', async () => {
+    // The assemble rejection escapes to runTurn's outer catch: the open turn
+    // closes with an `error` reason (agent/error mirrors it), no step opens,
+    // no request/header is logged, the adapter never sees a request, and the
+    // agent returns to idle — a misconfigured deployment fails every turn
+    // deterministically instead of silently reordering nothing.
+    const adapter = new MockAdapter([textResponse('never sent')])
+    const ctx = await harness(adapter, ['ghost', TOOL_ORDER_REST])
+    registerNamed(ctx, 'alpha')
+    const errors: Error[] = []
+    ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+    expect(adapter.requests).toHaveLength(0)
+    expect(errors.map(e => e.message)).toEqual(['toolOrder lists unregistered tool "ghost"; registered tools: alpha'])
+    expect(foldRequestHeader(agent.session.events)).toBeUndefined()
+    const end = agent.session.events.find(e => e.type === 'turn/end')
+    expect(end?.type === 'turn/end' && end.data.reason).toMatchObject({ kind: 'error', step: 1 })
+    // The turn is balanced (turn/start → turn/end) with no step events inside.
+    expect(agent.session.events.some(e => e.type === 'step/start')).toBe(false)
+  })
+})

packages/core/agent/README.md

@@ -43,8 +43,9 @@ Turn and step boundaries are NOT mirrored as `agent/*` emits: a consumer that ne
 
 - `agent/session-start` (emit) — fired once before the first turn; a listener seeds context via `agent.inject()` (it cannot veto startup).
 - `agent/prompt-submit` — decide what happens to one drained queued message before it becomes a `user/message`: `PromptDecision` = `allow` (optionally rewriting the prompt `content` or attaching `additionalContext`) or `block` (drop it; a batch whose every prompt is blocked opens a zero-step turn that ends `rejected`). Maps onto Claude Code's `UserPromptSubmit`.
-- `agent/pre-step` (serial) — mutate the session surface before the step opens and history is derived (compaction). Fires after `turn/start` and before `step/start`, so a listener's appended events land outside the step.
+- `agent/pre-step` (serial) — mutate the session surface before the step opens and history is derived (compaction). Fires after `turn/start` and before `step/start`, so a listener's appended events land outside the step; carries the assembled system prompt and the instance's composed session prefix so a token-pressure gate counts everything the request will carry.
 - `agent/request` — shape the call config before the model call: a frozen `LlmCallConfig` seed in, a replacement out (model switching, sampling overrides). Content is not shapeable here — every request is a pure function of the session log ([reconstructability RFC](../../../docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md)); the loop logs whatever config the request actually uses as a `request/header*` event
+- `agent/session-prefix` — compose the session prefix: request-only messages placed in front of the ENTIRE derived history on every request. Fired ONCE per loop instance, lazily before its first pre-step (so pressure gates see this instance's real prefix, never a previous instance's logged one); the composed result is deep-frozen, recorded as `EpochHeader.messagePrefix` on the anchoring `request/header` snapshot, and reused verbatim afterwards — the prefix cannot change mid-session, so the provider prefix cache holds by construction (resume = a new instance = a recompose, attributably anchored by its `'resume'` snapshot). The home for session-stable openers that must not become durable history (a skills catalog, an AGENTS.md digest); `deriveMessages()` never returns it. Content that CHANGES mid-session belongs in the append-only history channels instead — `agent.inject()`, `tools/post-execute` `additionalContext`, prompt-submit `additionalContext` — each a durable `context/message` paid once and prefix-cached thereafter
 - `agent/step-result` — post-process the assembled assistant message before tool dispatch (validates what the log records)
 - `agent/turn-continuation` — override the continue/stop decision via `ContinuationDecision` = `{action:'stop'}` or `{action:'continue', reason?}` (a `continue` `reason` is recorded as next-step steering in the same turn — the typed `/goal` pattern). Force-continue `/loop`, force-stop budget guard.
 

packages/core/agent/src/types.ts

@@ -17,7 +17,8 @@
  *   consumer that wants the live transcript subscribes here.
  * - **`agent/*`** (this module) — the LIVE runtime surface. Always carries the
  *   live `Agent`. Two shapes: INTERCEPTION seams (the `agent/prompt-submit`/
- *   `agent/request`/`agent/step-result`/`agent/turn-continuation` waterfalls and
+ *   `agent/request`/`agent/session-prefix`/`agent/step-result`/
+ *   `agent/turn-continuation` waterfalls and
  *   the serial `agent/pre-step`) that mutate/veto, and TRANSIENT emits
  *   (`agent/status`, `agent/error`, `agent/created`/
  *   `agent/disposed`, `agent/queued`, `agent/session-start`)
@@ -50,7 +51,11 @@ import type {} from '@deepseek-ai/dsh-system-prompt'
 /** Identifies one live agent in the registry. */
 export type AgentId = Branded<'AgentId'>
 
-/** Brand a string as an {@link AgentId}. */
+/**
+ * Brand a string as an {@link AgentId}.
+ * @param id - the raw agent id string.
+ * @returns the same string, branded (a compile-time cast — no runtime cost).
+ */
 export function AgentId(id: string): AgentId {
   return id as AgentId
 }
@@ -80,10 +85,22 @@ export interface AgentOptions {
   model?: string
 }
 
+/**
+ * Options for {@link Agent.send}/{@link Agent.steer}/{@link Agent.inject}. An
+ * absent `source` resolves to `{ kind: 'user' }`, so a plugin supplying content
+ * must label itself here or its message is recorded as a user prompt (see
+ * {@link HookContext} on why that label is load-bearing).
+ */
 export interface SendOptions {
   source?: MessageSource
 }
 
+/**
+ * An agent's lifecycle state, emitted on every transition as `agent/status`:
+ * `idle` (parked, waiting for queued work), `running` (a turn is in progress),
+ * `disposed` (terminal — no transition leaves it, and `send`/`steer`/`inject`
+ * throw).
+ */
 export type AgentStatus = 'idle' | 'running' | 'disposed'
 
 /**
@@ -316,21 +333,28 @@ declare module 'cordis' {
      * value; this event is typed and documented as `void`, so listeners must not
      * return a semantic veto value. `fullSystemPrompt` is the assembled prompt a
      * listener needs to measure pressure (the system prompt counts toward the
-     * budget). `signal` cancels any in-flight work a listener starts (e.g. a
+     * budget), and `sessionPrefix` is the instance's composed
+     * {@link agent/session-prefix} product for the same reason — every request
+     * carries it in front of the derived history, and it is composed BEFORE
+     * this seam fires precisely so a pressure gate counts the prefix the
+     * request will actually send (never a stale logged one). `signal` cancels
+     * any in-flight work a listener starts (e.g. a
      * summarization model call).
      * @param agent - the agent about to open the step.
      * @param turn - the already-open turn this step belongs to.
      * @param step - the number of the step about to start.
      * @param fullSystemPrompt - the assembled prompt, for measuring token pressure.
+     * @param sessionPrefix - the instance's frozen session prefix, for the same measurement.
      * @param signal - aborts in-flight listener work when the turn is torn down.
      * @mode serial
      */
-    // TODO: `fullSystemPrompt` is a smell on a generic per-step seam — compaction
-    // is its only consumer, so a wide event carries a string just one listener
+    // TODO: `fullSystemPrompt`/`sessionPrefix` are a smell on a generic
+    // per-step seam — compaction
+    // is their only consumer, so a wide event carries payloads just one listener
     // reads. Revisit if no second consumer appears: e.g. hand listeners a lazy
     // prompt provider, or move token-pressure measurement behind a
     // compaction-specific seam instead of the shared pre-step checkpoint.
-    'agent/pre-step'(agent: Agent, turn: number, step: number, fullSystemPrompt: string, signal: AbortSignal): Promise<void> | void
+    'agent/pre-step'(agent: Agent, turn: number, step: number, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal): Promise<void> | void
     /**
      * Waterfall: decide what happens to ONE drained queued message before it
      * becomes a `user/message` — allow (optionally rewriting the prompt bytes or
@@ -351,8 +375,9 @@ declare module 'cordis' {
      * ALL a listener shapes here: every request is a pure function of the
      * session log (the reconstructability RFC), so model-visible content
      * flows through the log channels — `inject()`, steering, prompt-submit
-     * `additionalContext`, prompt sections via `system-prompt/assemble` —
-     * never through request mutation, and the loop records whatever config
+     * `additionalContext`, prompt sections via `system-prompt/assemble`, or
+     * the header-logged session prefix via {@link agent/session-prefix}
+     * — never through request mutation, and the loop records whatever config
      * the request actually uses as a `request/header*` event before dispatch.
      * The step's messages are already snapshotted when this fires (the
      * `step/start` boundary): an `inject()` from a listener here lands in the
@@ -367,6 +392,53 @@ declare module 'cordis' {
      * @mode waterfall
      */
     'agent/request'(agent: Agent, turn: number, step: number, config: LlmCallConfig, next: () => Promise<LlmCallConfig>): Promise<LlmCallConfig>
+    /**
+     * Waterfall: compose the SESSION PREFIX — request-only messages placed in
+     * front of the ENTIRE derived history (directly after the provider's
+     * system slot) on every request this loop instance sends. Fired ONCE per
+     * loop instance, lazily before its first step's {@link agent/pre-step}
+     * seam — BEFORE the pre-step so a token-pressure gate (compaction) counts
+     * the prefix this instance will actually send, never a previous
+     * instance's logged one. The composed
+     * result is deep-frozen, recorded as `EpochHeader.messagePrefix` on the
+     * instance's anchoring `'initial'`/`'resume'` header snapshot, and reused
+     * verbatim for every subsequent request — never recomputed mid-session,
+     * so the provider prefix cache holds by construction (a process restart
+     * or `ctx.agents.resume()` is a new instance: it recomposes, and any
+     * drift lands attributably on the `'resume'` snapshot). Composition runs
+     * outside the step, before the boundary snapshot: a composing listener's
+     * session append joins the CURRENT request's derived history. A
+     * composition interrupted by a cancel/dispose landing inside the
+     * waterfall is discarded — never cached, logged, or sent — and the next
+     * turn recomposes under a live signal, so an abort-aware listener's
+     * degraded fallback cannot leak into later requests.
+     *
+     * This is the home for session-stable openers the model must always see
+     * but that must NOT become durable history — a skills catalog, an
+     * AGENTS.md digest, a workspace baseline: `Session.deriveMessages()`
+     * never returns the prefix, and the header events are its only durable
+     * record, so the request stays reconstructable from the log. Content
+     * that CHANGES mid-session belongs in the append-only history channels
+     * instead — `agent.inject()`, a `tools/post-execute` decision's
+     * `additionalContext`, prompt-submit `additionalContext` — each a
+     * durable `context/message` paid once and prefix-cached thereafter.
+     *
+     * The seed is a frozen empty list; a contributing listener returns a NEW
+     * array — never an in-place push. The canonical contribution is a
+     * PREPEND, `[mine, ...await next()]`: the waterfall unwinds
+     * innermost-first (the LAST-registered listener's `next()` resolves
+     * first), so prepending yields registration order on the wire, and every
+     * plugin using it composes deterministically. The append form
+     * `[...await next(), mine]` is legal but places a contribution AFTER
+     * every later-registered plugin's — reverse registration order when all
+     * contributors append. Call `next()` to
+     * delegate, or return a list without it to short-circuit.
+     * @param agent - the agent whose session prefix is being composed.
+     * @param prefix - the frozen empty seed; return an extended replacement to contribute.
+     * @param signal - aborts in-flight listener work (e.g. a discovery scan) when the step is torn down.
+     * @mode waterfall
+     */
+    'agent/session-prefix'(agent: Agent, prefix: Message[], signal: AbortSignal, next: () => Promise<Message[]>): Promise<Message[]>
     /**
      * Waterfall: post-process the assembled assistant {@link Message} before
      * tool dispatch (validation, content rewriting, …).

packages/core/agent/tests/verify-export-jsdoc.spec.ts

@@ -0,0 +1,555 @@
+/**
+ * Negative-path tests for the export-surface JSDoc gate
+ * (`scripts/verify-export-jsdoc.ts`).
+ *
+ * The gate's positive half runs against the real tree in CI (`pnpm run
+ * verify-export-jsdoc`, part of doc-sync). What that run cannot prove is that
+ * the walk REJECTS an undocumented surface the way it promises to — and that
+ * every deliberate exemption (heritage members, plugin-protocol slots,
+ * constructors, overload implementations, augmentation bodies, re-exports)
+ * actually holds. These tests drive `collectExportJsdocViolations()` against
+ * synthetic fixture packages, mirroring the gen-cordis-catalog negative
+ * tests.
+ */
+
+import { mkdirSync, mkdtempSync, rmSync, writeFileSync } from 'node:fs'
+import { tmpdir } from 'node:os'
+import { dirname, join } from 'node:path'
+import { afterEach, describe, expect, it } from 'vitest'
+import { collectExportJsdocViolations } from '../../../../scripts/verify-export-jsdoc.ts'
+
+const roots: string[] = []
+
+afterEach(() => {
+  while (roots.length) rmSync(roots.pop()!, { recursive: true, force: true })
+})
+
+/** Write fixture files under `packages/group/fix/src/` and return the scan root. */
+function fixture(files: Record<string, string>): string {
+  const root = mkdtempSync(join(tmpdir(), 'export-jsdoc-'))
+  roots.push(root)
+  for (const [rel, content] of Object.entries(files)) {
+    const abs = join(root, 'packages', 'group', 'fix', 'src', rel)
+    mkdirSync(dirname(abs), { recursive: true })
+    writeFileSync(abs, content)
+  }
+  return root
+}
+
+/** Single-file fixture shorthand: the content becomes `src/index.ts`. */
+const make = (content: string): string => fixture({ 'index.ts': content })
+
+describe('verify-export-jsdoc functions and consts', () => {
+  it('accepts a fully documented surface', () => {
+    expect(collectExportJsdocViolations(make(`
+/**
+ * Add one to a count.
+ * @param n - the count to bump.
+ * @returns the count plus one.
+ */
+export function bump(n: number): number { return n + 1 }
+
+/**
+ * Fire-and-forget (void needs no @returns).
+ * @param flag - whether to arm.
+ */
+export function poke(flag: boolean): void { void flag }
+
+/** The default retry budget. */
+export const RETRIES = 3
+
+/**
+ * Halve a count.
+ * @param n - the count to halve.
+ * @returns the count halved.
+ */
+export const halve = (n: number): number => n / 2
+`))).toEqual([])
+  })
+
+  it('flags an exported function with no JSDoc at all', () => {
+    expect(collectExportJsdocViolations(make(
+      'export function bare(): void {}\n',
+    ))).toEqual([expect.stringMatching(/exported function 'bare' .* has no JSDoc\./)])
+  })
+
+  it('flags a missing @param and a missing @returns', () => {
+    const violations = collectExportJsdocViolations(make(
+      '/** Docs without tags. */\nexport function f(x: number): number { return x }\n',
+    ))
+    expect(violations).toEqual([
+      expect.stringMatching(/exported function 'f' .* is missing @param x\./),
+      expect.stringMatching(/exported function 'f' .* is missing @returns \(return type: number\)\./),
+    ])
+  })
+
+  it('flags an unannotated (inferred) return type', () => {
+    expect(collectExportJsdocViolations(make(
+      '/**\n * Docs.\n * @param x - value.\n */\nexport function f(x: number) { return x }\n',
+    ))).toEqual([expect.stringMatching(/no return type annotation/)])
+  })
+
+  it('flags tags-only JSDoc with no description prose', () => {
+    expect(collectExportJsdocViolations(make(
+      '/**\n * @param x - value.\n */\nexport function f(x: number): void {}\n',
+    ))).toEqual([expect.stringMatching(/no description prose above its block tags/)])
+  })
+
+  it('flags a stale @param and a binding-pattern parameter', () => {
+    const violations = collectExportJsdocViolations(make(
+      '/**\n * Docs.\n * @param ghost - not real.\n */\nexport function f({ a }: { a: number }): void {}\n',
+    ))
+    expect(violations).toEqual([
+      expect.stringMatching(/parameter '\{ a \}' is a binding pattern; the export surface needs simple identifier parameters/),
+      expect.stringMatching(/@param ghost does not match any parameter \(stale tag\?\)/),
+    ])
+  })
+
+  it('exempts a `this` receiver annotation from @param', () => {
+    expect(collectExportJsdocViolations(make(
+      '/**\n * Docs.\n * @param x - value.\n */\nexport function f(this: object, x: number): void {}\n',
+    ))).toEqual([])
+  })
+
+  it('waives @returns for a declarator-annotated const but not an unannotated one', () => {
+    expect(collectExportJsdocViolations(make(`
+type Fn = (x: number) => number
+/**
+ * Uses the named signature.
+ * @param x - value.
+ */
+export const good: Fn = x => x
+/**
+ * No signature anywhere.
+ * @param x - value.
+ */
+export const bad = (x: number) => x
+`))).toEqual([expect.stringMatching(/exported const 'bad' .* has no return type annotation/)])
+  })
+
+  it('requires description prose on a non-function const', () => {
+    expect(collectExportJsdocViolations(make(
+      'export const LIMIT = 10\n',
+    ))).toEqual([expect.stringMatching(/exported const 'LIMIT' .* has no JSDoc\./)])
+  })
+})
+
+describe('verify-export-jsdoc type-level exports', () => {
+  it('requires description prose on interfaces, type aliases, and enums', () => {
+    const violations = collectExportJsdocViolations(make(
+      'export interface I { a: number }\nexport type T = number\nexport enum E { A }\n',
+    ))
+    expect(violations).toEqual([
+      expect.stringMatching(/exported interface 'I' .* has no JSDoc\./),
+      expect.stringMatching(/exported type 'T' .* has no JSDoc\./),
+      expect.stringMatching(/exported enum 'E' .* has no JSDoc\./),
+    ])
+  })
+
+  it('skips `declare module` augmentation bodies (the cordis gate owns them)', () => {
+    expect(collectExportJsdocViolations(make(
+      "declare module 'cordis' {\n  interface Events {\n    'fix/x'(): void\n  }\n}\nexport {}\n",
+    ))).toEqual([])
+  })
+})
+
+describe('verify-export-jsdoc export forms', () => {
+  it('resolves an `export { … }` list to the local declaration', () => {
+    expect(collectExportJsdocViolations(make(
+      'function f(): void {}\nexport { f }\n',
+    ))).toEqual([expect.stringMatching(/exported function 'f' .* has no JSDoc\./)])
+  })
+
+  it('does not treat a never-exported sibling declarator as surface (review round 2)', () => {
+    // `export { publicValue }` resolves to the whole variable statement; only
+    // the named declarator is surface — the gate must not demand JSDoc for
+    // the private sibling sharing the statement.
+    expect(collectExportJsdocViolations(make(
+      '/** The public knob. */\nconst publicValue = 1, privateHelper = 2\nexport { publicValue }\nvoid privateHelper\n',
+    ))).toEqual([])
+  })
+
+  it('unions declarators across multiple export lists over one statement (review round 2)', () => {
+    // Two lists each name one declarator of the same undocumented statement:
+    // both are surface (deduplicating on first resolution would drop `b`),
+    // while the never-exported `c` stays out.
+    const violations = collectExportJsdocViolations(make(
+      'const a = 1, b = 2, c = 3\nexport { a }\nexport { b }\nvoid c\n',
+    ))
+    expect(violations).toEqual([
+      expect.stringMatching(/exported const 'a' .* has no JSDoc\./),
+      expect.stringMatching(/exported const 'b' .* has no JSDoc\./),
+    ])
+  })
+
+  it('scopes a default-export identifier to its own declarator (review round 2)', () => {
+    // `export default` of an identifier reaches the statement through the
+    // same name lookup as an export list; the sibling stays private.
+    expect(collectExportJsdocViolations(make(
+      '/** The app entry. */\nconst app = 1, scratch = 2\nexport default app\nvoid scratch\n',
+    ))).toEqual([])
+  })
+
+  it('reports a re-exported module once, at its defining file', () => {
+    const violations = collectExportJsdocViolations(fixture({
+      'index.ts': "export * from './other.ts'\n",
+      'other.ts': 'export function f(): void {}\n',
+    }))
+    expect(violations).toEqual([expect.stringMatching(/other\.ts:1\) has no JSDoc\./)])
+  })
+
+  it('exempts overload implementations when the signatures are documented', () => {
+    expect(collectExportJsdocViolations(make(`
+/**
+ * From a number.
+ * @param x - the number.
+ * @returns its text.
+ */
+export function f(x: number): string
+/**
+ * From a flag.
+ * @param x - the flag.
+ * @returns its text.
+ */
+export function f(x: boolean): string
+export function f(x: number | boolean): string { return String(x) }
+`))).toEqual([])
+  })
+})
+
+describe('verify-export-jsdoc classes', () => {
+  it('flags an undocumented class, method, property, and accessor', () => {
+    const violations = collectExportJsdocViolations(make(`
+export class C {
+  state = 1
+  get view(): number { return this.state }
+  run(x: number): number { return x }
+}
+`))
+    expect(violations).toEqual([
+      expect.stringMatching(/exported class 'C' .* has no JSDoc\./),
+      expect.stringMatching(/exported class property 'C.state' .* has no JSDoc\./),
+      expect.stringMatching(/exported class accessor 'C.view' .* has no JSDoc\./),
+      expect.stringMatching(/exported class method 'C.run' .* has no JSDoc\./),
+    ])
+  })
+
+  it('exempts members declared by an extends/implements heritage type', () => {
+    expect(collectExportJsdocViolations(make(`
+/** Seam. */
+export abstract class Base {
+  /**
+   * Do it.
+   * @param x - input.
+   * @returns output.
+   */
+  abstract run(x: number): number
+}
+/** Iface. */
+export interface Sized {
+  /** Byte size. */
+  size: number
+}
+/** Impl. */
+export class Impl extends Base implements Sized {
+  size = 0
+  run(x: number): number { return x }
+}
+`))).toEqual([])
+  })
+
+  it('skips private/protected/#private members and constructors', () => {
+    expect(collectExportJsdocViolations(make(`
+/** Documented. */
+export class C {
+  #secret = 1
+  private hidden(): void {}
+  protected hook(): void {}
+  constructor(x: number) { void x }
+}
+`))).toEqual([])
+  })
+
+  it('exempts plugin-protocol statics but checks other statics', () => {
+    const violations = collectExportJsdocViolations(make(`
+/** Plugin. */
+export class C {
+  static Config = { a: 1 }
+  static inject = ['bash']
+  static reusable = true
+  static other = 1
+}
+`))
+    expect(violations).toEqual([expect.stringMatching(/exported class property 'C.other' .* has no JSDoc\./)])
+  })
+
+  it("covers a set accessor by the getter's doc", () => {
+    expect(collectExportJsdocViolations(make(`
+/** Documented. */
+export class C {
+  /** The current width. */
+  get width(): number { return 1 }
+  set width(_v: number) {}
+}
+`))).toEqual([])
+  })
+})
+
+describe('verify-export-jsdoc plugin protocol and namespaces', () => {
+  it('exempts top-level plugin-protocol exports', () => {
+    expect(collectExportJsdocViolations(make(`
+export const name = 'fix'
+export const inject = ['bash']
+export const reusable = true
+export const Config = { parse: true }
+export function apply(): void {}
+`))).toEqual([])
+  })
+
+  it('recurses into namespaces with qualified names and honors the merge idiom', () => {
+    const violations = collectExportJsdocViolations(make(`
+/** The plugin class. */
+export class Fix {}
+export namespace Fix {
+  export interface Config { a: number }
+}
+export namespace Loose {
+  export const x = 1
+}
+`))
+    expect(violations).toEqual([
+      expect.stringMatching(/exported interface 'Fix.Config' .* has no JSDoc\./),
+      expect.stringMatching(/exported namespace 'Loose' .* has no JSDoc\./),
+      expect.stringMatching(/exported const 'Loose.x' .* has no JSDoc\./),
+    ])
+  })
+})
+
+describe('verify-export-jsdoc fail-closed forms (review round 1)', () => {
+  it('checks the function contract on a non-identifier default export', () => {
+    expect(collectExportJsdocViolations(make(
+      '/** Doubles. */\nexport default (x: number): number => x * 2\n',
+    ))).toEqual([
+      expect.stringMatching(/default export .* is missing @param x\./),
+      expect.stringMatching(/default export .* is missing @returns \(return type: number\)\./),
+    ])
+    expect(collectExportJsdocViolations(make(
+      '/**\n * Doubles.\n * @param x - the input.\n * @returns twice the input.\n */\nexport default (x: number): number => x * 2\n',
+    ))).toEqual([])
+  })
+
+  it('treats an inline function-type annotation as the surface signature', () => {
+    expect(collectExportJsdocViolations(make(
+      '/** Maps a number. */\nexport declare const f: (x: number) => number\n',
+    ))).toEqual([
+      expect.stringMatching(/exported const 'f' .* is missing @param x\./),
+      expect.stringMatching(/exported const 'f' .* is missing @returns \(return type: number\)\./),
+    ])
+    expect(collectExportJsdocViolations(make(
+      '/**\n * Maps a number.\n * @param x - the input.\n * @returns the mapped value.\n */\nexport const f: (x: number) => number = v => v\n',
+    ))).toEqual([])
+  })
+
+  it('recurses into an ambient declare namespace where members export implicitly', () => {
+    expect(collectExportJsdocViolations(make(
+      'export declare namespace N {\n  function f(x: number): number\n}\n',
+    ))).toEqual([
+      expect.stringMatching(/exported namespace 'N' .* has no JSDoc\./),
+      expect.stringMatching(/exported function 'N.f' .* has no JSDoc\./),
+    ])
+  })
+
+  it('requires an export-import alias to document itself (its target may be unwalked)', () => {
+    expect(collectExportJsdocViolations(make(
+      '/** Holder. */\nexport namespace N {\n  /** The value. */\n  export const x = 1\n}\nexport import y = N.x\n',
+    ))).toEqual([expect.stringMatching(/exported alias 'y' .* has no JSDoc\./)])
+    expect(collectExportJsdocViolations(make(
+      'namespace N {\n  export const x = 1\n}\n/** Alias surfacing the internal counter. */\nexport import y = N.x\n',
+    ))).toEqual([])
+  })
+
+  it('refuses an export-import alias to a callable, class, or namespace target', () => {
+    const refusal = /exported alias 'g' .* aliases a callable, class, or namespace target/
+    expect(collectExportJsdocViolations(make(
+      'namespace N {\n  export function f(x: number): number { return x }\n}\n/** Alias. */\nexport import g = N.f\n',
+    ))).toEqual([expect.stringMatching(refusal)])
+    expect(collectExportJsdocViolations(make(
+      'namespace N {\n  export class C {\n    run(x: number): number { return x }\n  }\n}\n/** Alias. */\nexport import g = N.C\n',
+    ))).toEqual([expect.stringMatching(refusal)])
+    expect(collectExportJsdocViolations(make(
+      'namespace N {\n  export namespace Sub {\n    export function f(x: number): number { return x }\n  }\n}\n/** Alias. */\nexport import g = N.Sub\n',
+    ))).toEqual([expect.stringMatching(refusal)])
+  })
+
+  it('classifies wrapped function initializers and default exports (parens, satisfies)', () => {
+    expect(collectExportJsdocViolations(make(
+      'type Fn = (x: number) => number\n/** Wrapped. */\nexport const f = (((x: number): number => x)) satisfies Fn\n',
+    ))).toEqual([
+      expect.stringMatching(/exported const 'f' .* is missing @param x\./),
+      expect.stringMatching(/exported const 'f' .* is missing @returns \(return type: number\)\./),
+    ])
+    expect(collectExportJsdocViolations(make(
+      'type Fn = (x: number) => number\n/** Wrapped. */\nexport default (((x: number): number => x * 2) satisfies Fn)\n',
+    ))).toEqual([
+      expect.stringMatching(/default export .* is missing @param x\./),
+      expect.stringMatching(/default export .* is missing @returns \(return type: number\)\./),
+    ])
+  })
+
+  it('treats a single-call-signature type literal as the surface signature', () => {
+    expect(collectExportJsdocViolations(make(
+      '/** Maps. */\nexport declare const f: { (x: number): number }\n',
+    ))).toEqual([
+      expect.stringMatching(/exported const 'f' .* is missing @param x\./),
+      expect.stringMatching(/exported const 'f' .* is missing @returns \(return type: number\)\./),
+    ])
+  })
+
+  it('refuses a hybrid callable type literal instead of narrowing the check', () => {
+    expect(collectExportJsdocViolations(make(
+      '/** Hybrid. */\nexport declare const f: { (x: number): number; flush: () => void }\n',
+    ))).toEqual([expect.stringMatching(/exported const 'f'.*callable type literal is not gate-classifiable; extract a named type/)])
+  })
+
+  it('refuses an export-equals assignment instead of failing open', () => {
+    expect(collectExportJsdocViolations(make(
+      'const x = 1\nexport = x\n',
+    ))).toEqual([expect.stringMatching(/export-equals assignment .* is not a gate-supported export form/)])
+  })
+})
+
+describe('verify-export-jsdoc heritage refinement (review round 1)', () => {
+  it('requires @param for parameters the base member never names', () => {
+    const violations = collectExportJsdocViolations(make(`
+/** Seam. */
+export abstract class Base {
+  /**
+   * Do it.
+   * @param x - input.
+   * @returns output.
+   */
+  abstract run(x: number): number
+}
+/** Impl. */
+export class Impl extends Base {
+  override run(x: number, verbose?: boolean): number { return verbose ? x : -x }
+}
+`))
+    expect(violations).toEqual([expect.stringMatching(/exported class method 'Impl.run' .* is missing @param verbose\./)])
+  })
+
+  it('does not exempt a public override of a protected-only base member', () => {
+    expect(collectExportJsdocViolations(make(`
+/** Seam. */
+export abstract class Base {
+  /** Subclass hook. */
+  protected hook(): void {}
+}
+/** Impl. */
+export class Impl extends Base {
+  override hook(): void {}
+}
+`))).toEqual([expect.stringMatching(/exported class method 'Impl.hook' .* has no JSDoc\./)])
+  })
+
+  it('treats an underscore-prefixed rename of a base parameter as the same parameter', () => {
+    expect(collectExportJsdocViolations(make(`
+/** Seam. */
+export abstract class Base {
+  /**
+   * Load it.
+   * @param cwd - the working directory to scope the lookup.
+   * @returns the loaded value.
+   */
+  abstract load(cwd: string): number
+}
+/** Impl (ignores cwd). */
+export class Impl extends Base {
+  load(_cwd: string): number { return 1 }
+}
+`))).toEqual([])
+  })
+
+  it('flags a binding-pattern parameter an override adds beyond the base', () => {
+    expect(collectExportJsdocViolations(make(`
+/** Seam. */
+export abstract class Base {
+  /**
+   * Do it.
+   * @param x - input.
+   * @returns output.
+   */
+  abstract run(x: number): number
+}
+/** Impl. */
+export class Impl extends Base {
+  override run(x: number, { verbose }: { verbose?: boolean } = {}): number { return verbose ? x : -x }
+}
+`))).toEqual([expect.stringMatching(/exported class method 'Impl.run' .* is a binding pattern/)])
+  })
+
+  it('revives the @returns duty when an override grows a concrete result over a void base', () => {
+    const voidBase = `
+/** Seam. */
+export abstract class Base {
+  /** Do it (fire-and-forget). */
+  abstract run(): void
+}
+`
+    expect(collectExportJsdocViolations(make(`${voidBase}
+/** Impl. */
+export class Impl extends Base {
+  override run(): number { return 1 }
+}
+`))).toEqual([expect.stringMatching(/exported class method 'Impl.run' .* is missing @returns \(return type: number\)\./)])
+    expect(collectExportJsdocViolations(make(`${voidBase}
+/** Impl. */
+export class Impl extends Base {
+  /**
+   * Do it and count.
+   * @returns how many were done.
+   */
+  override run(): number { return 1 }
+}
+`))).toEqual([])
+  })
+
+  it('classifies an unannotated override return over a void base via the checker', () => {
+    const voidBase = `
+/** Seam. */
+export abstract class Base {
+  /** Do it (fire-and-forget). */
+  abstract run(): void
+}
+`
+    expect(collectExportJsdocViolations(make(`${voidBase}
+/** Impl. */
+export class Impl extends Base {
+  override run() { return 1 }
+}
+`))).toEqual([expect.stringMatching(/exported class method 'Impl.run' .* non-void result its heritage declaration does not document/)])
+    expect(collectExportJsdocViolations(make(`${voidBase}
+/** Impl (faithful void, no annotation needed). */
+export class Impl extends Base {
+  override run() {}
+}
+`))).toEqual([])
+  })
+
+  it('keeps the full exemption when the base return already carries the @returns duty', () => {
+    expect(collectExportJsdocViolations(make(`
+/** Seam. */
+export abstract class Base {
+  /**
+   * Count things.
+   * @returns the count.
+   */
+  abstract run(): number
+}
+/** Impl. */
+export class Impl extends Base {
+  override run(): number { return 1 }
+}
+`))).toEqual([])
+  })
+})

packages/core/session/README.md

@@ -9,6 +9,7 @@ Creates and holds event-sourced `Session` instances. Persistence is intentionall
 ### Public API
 
 - `ctx.sessions.create(id?: SessionId, options?: { seed?: SessionEvent[]; meta?: { cwd?: string; parentSession?: SessionId; createdAt?: number; seedLength?: number } }): Session` — Create a session. `options.seed` replays/forks an existing event log; `options.meta` attaches creation metadata (validated absolute `cwd`, `parentSession` lineage, seed boundary) as the immutable `SessionHeader`. The store fills `version`/`id` and defaults `createdAt` to now; a caller reconstructing a persisted session passes the original `createdAt` and persisted `seedLength` to preserve them. Disposed with the calling fiber.
+- `ctx.sessions.fork(source, boundary?, childSessionId?): Session` — Resolve a live session object or id, select a seed through the inclusive `boundary` event seq (default: current last event), require that boundary to be `turn/end`, and create a live child session with lineage metadata.
 - `ctx.sessions.get(id: SessionId): Session | undefined`
 - `ctx.sessions.list(): Session[]`
 
@@ -50,11 +51,11 @@ Plain class (not a Cordis Service). Create via `ctx.sessions.create()`.
 
 ### Request-header reconstruction (`request-header.ts`)
 
-The `request/header` (full `EpochHeader` snapshot with a `RequestHeaderReason`) and `request/header-delta` (system line-trim / name-keyed tools delta / whole config) events make the request envelope logged session state, so every conversation request is a pure function of the log. The pure trio reconstructs it: `foldRequestHeader(events)` folds a log (or any prefix) into the header in force; `diffHeader(prev, next)` encodes a change (undefined when equal); `applyHeaderDelta(prev, delta)` replays one. Writer contract: every logged delta is round-trip-verified (`apply(prev, delta)` deep-equals the new header) with a `'fallback'` snapshot when the encoding cannot express the change (a pure tool reordering), so folding never needs error recovery on a well-formed log. `canonicalHeader` pins the one representation of absence (empty system/tools ≡ absent fields).
+The `request/header` (full `EpochHeader` snapshot with a `RequestHeaderReason`) and `request/header-delta` (system line-trim / name-keyed tools delta / whole config / whole session prefix) events make the request envelope logged session state, so every conversation request is a pure function of the log. The pure trio reconstructs it: `foldRequestHeader(events)` folds a log (or any prefix) into the header in force; `diffHeader(prev, next)` encodes a change (undefined when equal); `applyHeaderDelta(prev, delta)` replays one. Writer contract: every logged delta is round-trip-verified (`apply(prev, delta)` deep-equals the new header) with a `'fallback'` snapshot when the encoding cannot express the change (a pure tool reordering), so folding never needs error recovery on a well-formed log. `canonicalHeader` pins the one representation of absence (empty system/tools/messagePrefix ≡ absent fields; a delta's EMPTY prefix array encodes the transition back to absence). `EpochHeader.messagePrefix` is the durable record of the `agent/session-prefix` waterfall's product — composed once per loop instance, the request is `messagePrefix + derived history`, and `deriveMessages()` never returns it.
 
 ### Session event vocabulary (`types.ts`)
 
-The append-only log's event types, enumerated member by member — payloads, surface badges, provenance — in the generated [persistence log event catalog](../../../docs/persistence-catalog/log-events.md). Token usage rides on `assistant/message.usage`; an operational error's step is on `turn/end.reason` for `kind: 'error'`.
+The append-only log's event types, enumerated member by member — payloads, surface badges, provenance — in the generated [persistence log event catalog](../../../docs/persistence-catalog.md). Token usage rides on `assistant/message.usage`; an operational error's step is on `turn/end.reason` for `kind: 'error'`.
 
 Merge-extensible via `SessionEventMap` — a plugin declaration-merges its own types (the compaction seam's `compact/*`, the hook bridges' `hook/*`); merged members appear in the same catalog.
 
@@ -72,9 +73,9 @@ Every `SessionEvent` carries two optional top-level fields (structural metadata)
 ### Extension points
 
 - Persistence plugins: subscribe to `session/event` (write-behind) and drain on `session/flush` (awaited) and fiber dispose. A durable backend reads the log and reloads it into a live session; the metadata seam (`SessionHeader`, `session.header`) is what such a backend stores beside the log.
-- Replay/fork: `ctx.sessions.create(id, { seed })` seeds a new session with an existing event log. The surface rebuilds deterministically from `surfaceOp` markers in the seeded events. The seed is validated to the SAME invariants `append` enforces — including that every surface-eligible event (`SurfaceEventType`) carries a `surfaceOp` marker — so a marker-less message event is rejected at construction rather than silently vanishing from `deriveMessages()` (the surface is the sole derivation path) on resume.
+- Replay/fork: `ctx.sessions.create(id, { seed })` seeds a new session with an existing event log. The surface rebuilds deterministically from `surfaceOp` markers in the seeded events. The seed is validated to the SAME always-on invariants `append` enforces — contiguous seqs, JSON-serializable data, and required `surfaceOp` markers on surface-eligible events — so marker-less message events are rejected at construction rather than silently vanishing from `deriveMessages()`. Broader turn-enclosure checks stay in `dsh-invariants` and persistence repair. Ordinary live-session forks use `ctx.sessions.fork(source, boundary?, childSessionId?)`, where `boundary` is the inclusive source event seq to fork through.
 - Compaction: the `dsh-compact-basic` plugin appends a `user/message` with `surfaceOp: { op: 'replace', start, end }` to shadow old surface nodes behind a summary checkpoint.
 
 ### What is NOT here (TODO)
 
-- **Session branching/tree** (pi-style entry tree) — deferred unless needed beyond seed-based forking.
+- **Session branching/tree** (pi-style entry tree) — deferred unless needed beyond boundary-based `fork()`.

packages/core/session/src/index.ts

@@ -153,10 +153,15 @@ export class Session {
     this.header = header ?? { version: SESSION_FORMAT_VERSION, id, createdAt: Date.now() }
   }
 
+  /**
+   * The append-only event log, exposed live by reference (readonly-typed, not
+   * a snapshot): later appends are visible through the same array.
+   */
   get events(): readonly SessionEvent[] {
     return this.log
   }
 
+  /** The next event's sequence number — always the log length (the `seq = log.length` contiguity contract). */
   get seq(): number {
     return this.log.length
   }
@@ -175,6 +180,9 @@ export class Session {
    *   declare how it joins the surface, the sole source of derived history) and
    *   rejected by the compiler for non-surface types like `turn/start` or
    *   `assistant/chunk`.
+   * @returns the logged event — its assigned `seq`/`time` plus the SNAPSHOT of
+   *   `data` that entered the log, so reading `event.data` back sees the logged
+   *   value, never the caller's still-mutable input.
    * @throws if `data` is not losslessly JSON-serializable (BigInt, function,
    *   symbol, undefined, non-finite number, circular ref, or an exotic object
    *   like Map/Set/Date). The event log is the durable source of truth, so this
@@ -362,6 +370,32 @@ export class Session {
   }
 }
 
+/** A fork source: either the live session object or its live store id. */
+export type SessionForkSource = Session | SessionId
+
+/**
+ * Rejection codes for session forking: the fork source id is unknown to the
+ * live store (`SESSION_NOT_FOUND`) or names a session object that is not the
+ * store's live instance (`SESSION_NOT_LIVE`); the requested child id is
+ * already taken (`SESSION_ALREADY_EXISTS`); the boundary is not a contiguous
+ * existing seq (`INVALID_BOUNDARY`); or the boundary event is not a
+ * `turn/end` — a fork must cut on a closed turn (`OPEN_TURN`).
+ */
+export type SessionForkErrorCode =
+  | 'SESSION_NOT_FOUND'
+  | 'SESSION_NOT_LIVE'
+  | 'SESSION_ALREADY_EXISTS'
+  | 'INVALID_BOUNDARY'
+  | 'OPEN_TURN'
+
+/** Typed error for session fork rejections. */
+export class SessionForkError extends Error {
+  constructor(message: string, public readonly code: SessionForkErrorCode) {
+    super(message)
+    this.name = 'SessionForkError'
+  }
+}
+
 /**
  * In-memory session store (`ctx.sessions`).
  *
@@ -496,6 +530,92 @@ export class SessionStore extends Service {
   list(): Session[] {
     return [...this.store.values()]
   }
+
+  /**
+   * Create a live child session from a turn-enclosed prefix of a live source.
+   * `boundary` is an inclusive source event seq; omitted means the source's
+   * current last event. A non-empty selected slice must end at `turn/end`.
+   *
+   * @param source - Live source session object or id.
+   * @param boundary - Inclusive source event seq to fork through; omitted means
+   *   the source's current last event, and omitted on an empty source forks an
+   *   empty child.
+   * @param childSessionId - Optional child session id; omitted delegates to
+   *   `SessionStore`'s id policy.
+   * @returns The created live child session.
+   */
+  fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId): Session {
+    if (childSessionId !== undefined && this.get(childSessionId) !== undefined) {
+      throw new SessionForkError(`session "${childSessionId}" already exists`, 'SESSION_ALREADY_EXISTS')
+    }
+    const liveSource = this._resolveForkSource(source)
+    const seed = this._forkSeed(liveSource, boundary)
+    return this.create(childSessionId, {
+      seed,
+      meta: {
+        ...liveSource.header.cwd !== undefined ? { cwd: liveSource.header.cwd } : {},
+        parentSession: liveSource.id,
+        seedLength: seed.length,
+      },
+    })
+  }
+
+  private _forkSeed(session: Session, requestedBoundary: number | undefined): SessionEvent[] {
+    const events = session.events
+    const lastEvent = events.at(-1)
+    let boundary: number
+    if (requestedBoundary !== undefined) {
+      boundary = requestedBoundary
+    } else {
+      if (lastEvent === undefined) return []
+      boundary = lastEvent.seq
+    }
+    if (!Number.isSafeInteger(boundary) || boundary < 0) {
+      throw new SessionForkError(
+        `fork boundary for session "${session.id}" must be a non-negative safe integer, got ${String(boundary)}`,
+        'INVALID_BOUNDARY',
+      )
+    }
+    if (boundary >= events.length) {
+      const lastSeq = events.at(-1)?.seq
+      throw new SessionForkError(
+        `fork boundary ${boundary} does not exist in session "${session.id}" (last seq: ${lastSeq ?? 'none'})`,
+        'INVALID_BOUNDARY',
+      )
+    }
+
+    const boundaryEvent = events[boundary]
+    if (boundaryEvent === undefined || boundaryEvent.seq !== boundary) {
+      throw new SessionForkError(
+        `fork boundary ${boundary} does not match a contiguous event seq in session "${session.id}"`,
+        'INVALID_BOUNDARY',
+      )
+    }
+    if (boundaryEvent.type !== 'turn/end') {
+      throw new SessionForkError(
+        `fork boundary ${boundary} in session "${session.id}" must be turn/end, got ${boundaryEvent.type}`,
+        'OPEN_TURN',
+      )
+    }
+
+    return events.slice(0, boundary + 1).map(event => structuredClone(event))
+  }
+
+  private _resolveForkSource(source: SessionForkSource): Session {
+    if (typeof source === 'string') {
+      const session = this.get(source)
+      if (session === undefined) throw new SessionForkError(`session "${source}" not found`, 'SESSION_NOT_FOUND')
+      return session
+    }
+
+    const live = this.get(source.id)
+    if (live === undefined) {
+      throw new SessionForkError(`session "${source.id}" not found`, 'SESSION_NOT_FOUND')
+    }
+    if (live !== source) throw new SessionForkError(`session "${source.id}" is not the live store instance`, 'SESSION_NOT_LIVE')
+    return source
+  }
+
 }
 
 export default SessionStore

packages/core/session/src/json.ts

@@ -40,6 +40,10 @@ export type JsonValue = null | boolean | number | string | JsonValue[] | { [key:
  * hiding under a symbol/non-enumerable key cannot make the round-trip lossy.
  * Getters are invoked during the check (again as `JSON.stringify` would), so the
  * contract is for plain data records, not objects with side-effecting accessors.
+ * @param value - the candidate event data to test.
+ * @param seen - objects on the current descent path, for circular-reference
+ *   detection; the recursion threads it — callers omit it.
+ * @returns true when `value` survives a JSON round-trip losslessly.
  */
 export function isJsonValue(value: unknown, seen: Set<object> = new Set()): boolean {
   if (value === null) return true

packages/core/session/src/repair.ts

@@ -54,6 +54,8 @@ import type { SessionEvent } from './types.ts'
  * Only the LAST turn can be open: the invariants plugin guarantees a `turn/end`
  * before any later `turn/start`, so an interior open turn is impossible in a
  * valid committed log. Likewise at most one step is open within that turn.
+ * @param events - the loaded durable log to scan (a valid committed prefix, possibly with a crash tail).
+ * @returns the synthetic closer events to append after `events`, in order; empty when the log is already balanced.
  */
 export function interruptedTurnClosers(events: readonly SessionEvent[]): SessionEvent[] {
   let openTurn: number | null = null

packages/core/session/src/request-header.ts

@@ -13,15 +13,23 @@
  */
 
 import { callConfigEquals } from '@deepseek-ai/dsh-llm'
-import type { LlmCallConfig, ToolSchema } from '@deepseek-ai/dsh-llm'
+import type { LlmCallConfig, Message, ToolSchema } from '@deepseek-ai/dsh-llm'
 import type { EpochHeader, SessionEvent, SystemDelta, ToolsDelta } from './types.ts'
 
+/** The `request/header-delta` payload shape: each present field amends the folded header. */
+type HeaderDelta = {
+  system?: SystemDelta
+  tools?: ToolsDelta
+  config?: LlmCallConfig
+  messagePrefix?: Message[]
+}
+
 /**
- * Normalize a header to canonical form: an empty system prompt and an empty
- * tool list become ABSENT fields, matching how requests are built (both
- * request-build spreads skip empty values). Diff, fold, and comparison all
- * operate on canonical headers, so "no system prompt" has exactly one
- * representation.
+ * Normalize a header to canonical form: an empty system prompt, an empty
+ * tool list, and an empty session prefix become ABSENT fields, matching how
+ * requests are built (the request-build spreads skip empty values). Diff,
+ * fold, and comparison all operate on canonical headers, so "no system
+ * prompt" (and "no session prefix") has exactly one representation.
  * @param header - the header to normalize (not mutated).
  * @returns the canonical header.
  */
@@ -30,6 +38,7 @@ export function canonicalHeader(header: EpochHeader): EpochHeader {
     config: header.config,
     ...header.system !== undefined && header.system.length > 0 ? { system: header.system } : {},
     ...header.tools !== undefined && header.tools.length > 0 ? { tools: header.tools } : {},
+    ...header.messagePrefix !== undefined && header.messagePrefix.length > 0 ? { messagePrefix: header.messagePrefix } : {},
   }
 }
 
@@ -109,37 +118,46 @@ function applyTools(prev: readonly ToolSchema[], delta: ToolsDelta): ToolSchema[
  * writer's round-trip guard runs (`applyHeaderDelta(prev, delta)` must equal
  * the intended header) and the loop runs to skip logging an unchanged header.
  * Tools compare per-schema IN ORDER (canonical JSON), so a pure reordering is
- * correctly unequal.
+ * correctly unequal; the session prefix compares as canonical JSON (both
+ * sides come from the same build path, so key order matches when the values
+ * do).
  * @param a - one canonical header.
  * @param b - the other.
- * @returns whether config, system, and tools (in order) all match.
+ * @returns whether config, system, tools (in order), and the session prefix all match.
  */
 export function headerEquals(a: EpochHeader, b: EpochHeader): boolean {
   if (!callConfigEquals(a.config, b.config) || a.system !== b.system) return false
+  if (!sameMessages(a.messagePrefix, b.messagePrefix)) return false
   const at = a.tools ?? []
   const bt = b.tools ?? []
   return at.length === bt.length && at.every((tool, i) => sameSchema(tool, bt[i] as ToolSchema))
 }
 
+/** Canonical JSON equality over session-prefix arrays; absence equals the empty array. */
+function sameMessages(a: readonly Message[] | undefined, b: readonly Message[] | undefined): boolean {
+  return JSON.stringify(a ?? []) === JSON.stringify(b ?? [])
+}
+
 /**
  * Compute the `request/header-delta` payload between two canonical headers,
  * or undefined when they are equal. The caller MUST round-trip the result
  * ({@link applyHeaderDelta} on `prev` deep-equals `next`) before logging it —
  * the encoding cannot express every change (a pure tool reordering) — and
  * fall back to a full `request/header` snapshot when the check fails.
+ * The session prefix is replaced whole (small advisory content, not worth
+ * diffing); an empty replacement array encodes the transition to "none".
  * @param prev - the folded header the log currently implies.
  * @param next - the header the next request will actually use.
  * @returns the delta payload, or undefined when nothing changed.
  */
-export function diffHeader(
-  prev: EpochHeader, next: EpochHeader,
-): { system?: SystemDelta; tools?: ToolsDelta; config?: LlmCallConfig } | undefined {
-  const delta: { system?: SystemDelta; tools?: ToolsDelta; config?: LlmCallConfig } = {}
+export function diffHeader(prev: EpochHeader, next: EpochHeader): HeaderDelta | undefined {
+  const delta: HeaderDelta = {}
   if (prev.system !== next.system) delta.system = diffSystem(prev.system, next.system)
   const prevTools = prev.tools ?? []
   const nextTools = next.tools ?? []
   if (JSON.stringify(prevTools) !== JSON.stringify(nextTools)) delta.tools = diffTools(prevTools, nextTools)
   if (!callConfigEquals(prev.config, next.config)) delta.config = next.config
+  if (!sameMessages(prev.messagePrefix, next.messagePrefix)) delta.messagePrefix = next.messagePrefix ?? []
   return Object.keys(delta).length > 0 ? delta : undefined
 }
 
@@ -151,15 +169,15 @@ export function diffHeader(
  * @param delta - the logged delta payload.
  * @returns the canonical header after the delta.
  */
-export function applyHeaderDelta(
-  prev: EpochHeader, delta: { system?: SystemDelta; tools?: ToolsDelta; config?: LlmCallConfig },
-): EpochHeader {
+export function applyHeaderDelta(prev: EpochHeader, delta: HeaderDelta): EpochHeader {
   const system = delta.system !== undefined ? applySystem(prev.system, delta.system) : prev.system
   const tools = delta.tools !== undefined ? applyTools(prev.tools ?? [], delta.tools) : prev.tools
+  const messagePrefix = delta.messagePrefix ?? prev.messagePrefix
   return canonicalHeader({
     config: delta.config ?? prev.config,
     ...system !== undefined ? { system } : {},
     ...tools !== undefined ? { tools } : {},
+    ...messagePrefix !== undefined ? { messagePrefix } : {},
   })
 }
 

packages/core/session/src/surface.ts

@@ -29,6 +29,8 @@ const SURFACE_EVENT_TYPES = new Set<string>([
  * surface-eligible event that is MISSING its mandatory marker (e.g. validating
  * a seed/load log); use {@link isSurfaceEvent} to narrow to a fully-formed
  * {@link SurfaceEvent} with `surfaceOp` present.
+ * @param type - the event type string to test.
+ * @returns true when the type is one of the five message-producing types.
  */
 export function isSurfaceEligibleType(type: string): boolean {
   return SURFACE_EVENT_TYPES.has(type)
@@ -38,6 +40,8 @@ export function isSurfaceEligibleType(type: string): boolean {
  * Narrow a {@link SessionEvent} to {@link SurfaceEvent}: checks that the
  * event's `type` is surface-eligible AND that `surfaceOp` is present.
  * The narrowed type has mandatory {@link SurfaceOp}.
+ * @param event - the event to narrow.
+ * @returns true when the event is surface-eligible and carries its `surfaceOp` marker.
  */
 export function isSurfaceEvent(event: SessionEvent): event is SurfaceEvent {
   if (!SURFACE_EVENT_TYPES.has(event.type)) return false

packages/core/session/src/tool-pairing.ts

@@ -74,6 +74,12 @@ function nodeDelta(event: SessionEvent): number {
  * surface successor (`SurfaceNode.next`), or `null` when `end` is the tail —
  * for the cut after `end`.
  *
+ * @param nodes - the surface linked list in head→tail order.
+ * @param events - the session log each node's `seq` indexes into.
+ * @param beforeSeq - names the cut (the node it sits immediately before);
+ *   `null` — or any seq not on the surface — means the after-tail cut.
+ * @returns true when every `tool-call` before the cut is answered before it
+ *   (the unanswered-call depth at the cut is zero).
  * @throws if the surface prefix drives the unanswered-call depth negative — a
  *   `tool/result` with no preceding open `tool-call` on the surface. That is a
  *   corrupt surface (a structural invariant violation), surfaced loudly here

packages/core/session/src/types.ts

@@ -1,10 +1,14 @@
 import type { Branded } from '@deepseek-ai/dsh-brand'
-import type { CallId, ContentBlock, LlmCallConfig, MessageSource, StreamChunk, TokenUsage, ToolSchema } from '@deepseek-ai/dsh-llm'
+import type { CallId, ContentBlock, LlmCallConfig, Message, MessageSource, StreamChunk, TokenUsage, ToolSchema } from '@deepseek-ai/dsh-llm'
 
 /** Identifies one session in the store (and its persistence artifacts). */
 export type SessionId = Branded<'SessionId'>
 
-/** Brand a string as a {@link SessionId}. */
+/**
+ * Brand a string as a {@link SessionId}.
+ * @param id - the raw session id string.
+ * @returns the same string, branded (a compile-time cast — no runtime cost).
+ */
 export function SessionId(id: string): SessionId {
   return id as SessionId
 }
@@ -102,6 +106,7 @@ export interface TurnTriggerMap {
   injection: { kind: 'injection'; source: MessageSource }
 }
 
+/** The union over {@link TurnTriggerMap} — what started a turn; plugins extend it by merging variants into the map. */
 export type TurnTrigger = TurnTriggerMap[keyof TurnTriggerMap]
 
 /**
@@ -156,6 +161,7 @@ export interface TurnEndReasonMap {
   interrupted: { kind: 'interrupted' }
 }
 
+/** The union over {@link TurnEndReasonMap} — why a turn ended; plugins extend it by merging variants into the map. */
 export type TurnEndReason = TurnEndReasonMap[keyof TurnEndReasonMap]
 
 /**
@@ -177,14 +183,15 @@ export interface TodoItem {
 }
 
 /**
- * The request header: everything about an LLM request besides its message
- * content — the call configuration plus the rendered system prompt and tool
- * schemas. Logged session state (the reconstructability RFC): a
+ * The request header: everything about an LLM request besides its derived
+ * message history — the call configuration plus the rendered system prompt,
+ * tool schemas, and the session prefix. Logged session state (the
+ * reconstructability RFC): a
  * {@link SessionEventMap} `request/header` snapshot installs one, a
  * `request/header-delta` amends it, and folding those events over the log
  * (`foldRequestHeader`) reconstructs the header any request was built under.
- * Canonical form: an empty system prompt and an empty tool list are ABSENT
- * fields, matching how requests are built.
+ * Canonical form: an empty system prompt, an empty tool list, and an empty
+ * prefix are ABSENT fields, matching how requests are built.
  */
 export interface EpochHeader {
   /** The conversation's call configuration (model + sampling scalars). */
@@ -193,6 +200,14 @@ export interface EpochHeader {
   system?: string
   /** Assembled tool schemas; absent for a tool-less request. */
   tools?: ToolSchema[]
+  /**
+   * The session prefix: request-only messages sent BEFORE the entire derived
+   * history (the `agent/session-prefix` waterfall's product, composed once
+   * per loop instance and reused for every request it sends). Not session
+   * history — `deriveMessages()` never returns it — so the header is its
+   * only durable record; absent when the instance composed none.
+   */
+  messagePrefix?: Message[]
 }
 
 /**
@@ -350,17 +365,24 @@ export interface SessionEventMap {
   'request/header': { header: EpochHeader; reason: RequestHeaderReason }
   /**
    * Amendment to the folded {@link EpochHeader}: at least one of a
-   * {@link SystemDelta}, a {@link ToolsDelta}, or a whole replacement
-   * {@link LlmCallConfig} (four scalars — not worth diffing). Appended by the
+   * {@link SystemDelta}, a {@link ToolsDelta}, a whole replacement
+   * {@link LlmCallConfig} (four scalars — not worth diffing), or a whole
+   * replacement session prefix (`messagePrefix` — small advisory content,
+   * replaced whole; an EMPTY array encodes the transition to "none",
+   * mirroring the canonical form's absent field — the loop never produces
+   * one in practice: the prefix is composed once per instance and anchored
+   * by that instance's snapshot, so this arm exists for codec totality).
+   * Appended by the
    * loop inside the step, before dispatch, when the header for this request
    * differs from the fold of the log so far; the writer verifies
    * `applyHeaderDelta(previous, delta)` reproduces the new header exactly and
    * falls back to a `'fallback'` `request/header` snapshot when it cannot, so
    * a logged delta ALWAYS round-trips. NOT a {@link SurfaceEventType}.
    */
-  'request/header-delta': { system?: SystemDelta; tools?: ToolsDelta; config?: LlmCallConfig }
+  'request/header-delta': { system?: SystemDelta; tools?: ToolsDelta; config?: LlmCallConfig; messagePrefix?: Message[] }
 }
 
+/** The appendable event-type keys of {@link SessionEventMap}, plugin-merged extensions included. */
 export type SessionEventType = keyof SessionEventMap
 
 /**

packages/core/session/tests/fork.spec.ts

@@ -0,0 +1,240 @@
+import { describe, expect, it } from 'vitest'
+import { Context } from 'cordis'
+import { CallId } from '@deepseek-ai/dsh-llm'
+import SessionStore, { Session, SessionForkError, SessionId } from '@deepseek-ai/dsh-session'
+import type { SessionEvent, TurnEndReason } from '@deepseek-ai/dsh-session'
+
+async function setup(): Promise<{ ctx: Context; sessions: SessionStore }> {
+  const ctx = new Context()
+  await ctx.plugin(SessionStore)
+  return { ctx, sessions: ctx.sessions }
+}
+
+function appendClosedTurn(
+  session: Session,
+  turn: number,
+  text = `hello ${turn}`,
+  reason: TurnEndReason = { kind: 'completed' },
+): void {
+  session.append('turn/start', { turn, trigger: { kind: 'message', source: { kind: 'user' } } })
+  session.append('user/message', {
+    content: [{ type: 'text', text }],
+    source: { kind: 'user' },
+  }, { surfaceOp: 'append' })
+  session.append('turn/end', { turn, reason })
+}
+
+function appendOpenTurn(session: Session, turn: number): void {
+  session.append('turn/start', { turn, trigger: { kind: 'message', source: { kind: 'user' } } })
+  session.append('user/message', {
+    content: [{ type: 'text', text: `open ${turn}` }],
+    source: { kind: 'user' },
+  }, { surfaceOp: 'append' })
+}
+
+function firstUserMessage(events: readonly SessionEvent[]): SessionEvent<'user/message'> {
+  const event = events.find((e): e is SessionEvent<'user/message'> => e.type === 'user/message')
+  if (event === undefined) throw new Error('missing user/message')
+  return event
+}
+
+function lastSeq(session: Session): number {
+  const event = session.events.at(-1)
+  if (event === undefined) throw new Error('missing last event')
+  return event.seq
+}
+
+describe('SessionStore.fork', () => {
+  it('forks an empty live session as an empty child with lineage metadata', async () => {
+    const { ctx, sessions } = await setup()
+    const source = ctx.sessions.create(SessionId('empty-parent'), { meta: { cwd: '/workspace' } })
+
+    const child = sessions.fork(source, undefined, SessionId('empty-child'))
+
+    expect(child.events).toEqual([])
+    expect(child.header).toMatchObject({
+      id: SessionId('empty-child'),
+      cwd: '/workspace',
+      parentSession: SessionId('empty-parent'),
+      seedLength: 0,
+    })
+  })
+
+  it('forks the latest completed boundary by default and deep-clones seed events', async () => {
+    const { ctx, sessions } = await setup()
+    const source = ctx.sessions.create(SessionId('parent'), { meta: { cwd: '/workspace' } })
+    appendClosedTurn(source, 1, 'hello')
+
+    const child = sessions.fork(SessionId('parent'), undefined, SessionId('child'))
+
+    expect(child.events).toEqual(source.events)
+    expect(child.events).not.toBe(source.events)
+    expect(child.events[1]).not.toBe(source.events[1])
+    firstUserMessage(child.events).data.content[0] = { type: 'text', text: 'child mutation' }
+    expect(firstUserMessage(source.events).data.content).toEqual([{ type: 'text', text: 'hello' }])
+    expect(child.header).toMatchObject({
+      id: SessionId('child'),
+      cwd: '/workspace',
+      parentSession: SessionId('parent'),
+      seedLength: source.events.length,
+    })
+  })
+
+  it('forks from an earlier turn boundary even when the source currently has an open tail', async () => {
+    const { ctx, sessions } = await setup()
+    const source = ctx.sessions.create(SessionId('parent'), { meta: { cwd: '/workspace' } })
+    appendClosedTurn(source, 1, 'first')
+    const firstBoundary = lastSeq(source)
+    appendClosedTurn(source, 2, 'second')
+    appendOpenTurn(source, 3)
+
+    const child = sessions.fork(source, firstBoundary, SessionId('child-from-first'))
+
+    expect(child.events).toEqual(source.events.slice(0, firstBoundary + 1))
+    expect(child.header.seedLength).toBe(firstBoundary + 1)
+    expect(child.deriveMessages()).toEqual([{ role: 'user', content: [{ type: 'text', text: 'first' }] }])
+  })
+
+  it('accepts every turn/end reason as an explicit fork boundary', async () => {
+    const { ctx, sessions } = await setup()
+    const reasons: TurnEndReason[] = [
+      { kind: 'completed' },
+      { kind: 'aborted', reason: 'cancelled by user' },
+      { kind: 'error', step: 1, message: 'model failed', code: 'MODEL' },
+      { kind: 'disposed' },
+      { kind: 'max-tokens' },
+      { kind: 'interrupted' },
+    ]
+
+    for (const reason of reasons) {
+      const source = ctx.sessions.create(SessionId(`parent-${reason.kind}`))
+      appendClosedTurn(source, 1, reason.kind, reason)
+
+      const child = sessions.fork(source, lastSeq(source), SessionId(`child-${reason.kind}`))
+
+      expect(child.events.at(-1)?.type).toBe('turn/end')
+      expect(child.header.seedLength).toBe(source.events.length)
+    }
+  })
+
+  it('rejects invalid boundaries before creating a child', async () => {
+    const { ctx, sessions } = await setup()
+    const empty = ctx.sessions.create(SessionId('empty'))
+    expect(() => sessions.fork(empty, 0, SessionId('empty-child')))
+      .toThrow(new SessionForkError('fork boundary 0 does not exist in session "empty" (last seq: none)', 'INVALID_BOUNDARY'))
+    expect(ctx.sessions.get(SessionId('empty-child'))).toBeUndefined()
+
+    const source = ctx.sessions.create(SessionId('parent'))
+    appendClosedTurn(source, 1)
+    expect(() => sessions.fork(source, -1, SessionId('negative')))
+      .toThrow(/non-negative safe integer/)
+    expect(() => sessions.fork(source, 0.5, SessionId('fraction')))
+      .toThrow(/non-negative safe integer/)
+    expect(() => sessions.fork(source, Number.MAX_SAFE_INTEGER + 1, SessionId('unsafe')))
+      .toThrow(/non-negative safe integer/)
+    expect(() => sessions.fork(source, source.seq, SessionId('past-end')))
+      .toThrow(new SessionForkError(`fork boundary ${source.seq} does not exist in session "parent" (last seq: ${source.seq - 1})`, 'INVALID_BOUNDARY'))
+  })
+
+  it('rejects a corrupted live source whose array index no longer matches event seq', async () => {
+    const { ctx, sessions } = await setup()
+    const source = ctx.sessions.create(SessionId('corrupt-parent'))
+    appendClosedTurn(source, 1)
+    const mutableLog = (source as unknown as { log: SessionEvent[] }).log
+    mutableLog[2] = { ...mutableLog[2]!, seq: 99 }
+
+    expect(() => sessions.fork(source, 2, SessionId('corrupt-child')))
+      .toThrow(new SessionForkError('fork boundary 2 does not match a contiguous event seq in session "corrupt-parent"', 'INVALID_BOUNDARY'))
+    expect(ctx.sessions.get(SessionId('corrupt-child'))).toBeUndefined()
+  })
+
+  it('rejects an unknown live session id', async () => {
+    const { sessions } = await setup()
+
+    expect(() => sessions.fork(SessionId('missing')))
+      .toThrow(new SessionForkError('session "missing" not found', 'SESSION_NOT_FOUND'))
+  })
+
+  it('rejects a detached Session object that is not live in ctx.sessions', async () => {
+    const { sessions } = await setup()
+    const detached = new Session(SessionId('detached'))
+
+    expect(() => sessions.fork(detached))
+      .toThrow(new SessionForkError('session "detached" not found', 'SESSION_NOT_FOUND'))
+  })
+
+  it('rejects a stale Session object whose id is live on a different instance', async () => {
+    const { ctx, sessions } = await setup()
+    ctx.sessions.create(SessionId('same-id'))
+    const stale = new Session(SessionId('same-id'))
+
+    expect(() => sessions.fork(stale))
+      .toThrow(new SessionForkError('session "same-id" is not the live store instance', 'SESSION_NOT_LIVE'))
+  })
+
+  it('rejects selected slices whose boundary is inside an open turn', async () => {
+    const { ctx, sessions } = await setup()
+    const cases: [string, (session: Session) => number][] = [
+      ['turn/start', (session) => {
+        session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
+        return lastSeq(session)
+      }],
+      ['step/start', (session) => {
+        session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
+        session.append('step/start', { turn: 1, step: 1 })
+        return lastSeq(session)
+      }],
+      ['user/message', (session) => {
+        session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
+        session.append('user/message', { content: [{ type: 'text', text: 'open' }], source: { kind: 'user' } }, { surfaceOp: 'append' })
+        return lastSeq(session)
+      }],
+      ['assistant/message', (session) => {
+        session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
+        session.append('step/start', { turn: 1, step: 1 })
+        session.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'partial' }] }, { surfaceOp: 'append' })
+        return lastSeq(session)
+      }],
+      ['tool/call', (session) => {
+        const callId = CallId('call-open')
+        session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
+        session.append('step/start', { turn: 1, step: 1 })
+        session.append('assistant/message', {
+          turn: 1,
+          step: 1,
+          content: [{ type: 'tool-call', id: callId, name: 'bash', arguments: '{}' }],
+        }, { surfaceOp: 'append' })
+        session.append('tool/call', { turn: 1, step: 1, callId, name: 'bash', arguments: '{}' })
+        return lastSeq(session)
+      }],
+    ]
+
+    for (const [lastType, build] of cases) {
+      const source = ctx.sessions.create(SessionId(`open-${lastType}`))
+      const boundary = build(source)
+
+      expect(() => sessions.fork(source, boundary))
+        .toThrow(new SessionForkError(`fork boundary ${boundary} in session "open-${lastType}" must be turn/end, got ${lastType}`, 'OPEN_TURN'))
+    }
+  })
+
+  it('rejects a child session id that is already live with a typed fork error', async () => {
+    const { ctx, sessions } = await setup()
+    const source = ctx.sessions.create(SessionId('parent'))
+    appendClosedTurn(source, 1)
+    ctx.sessions.create(SessionId('child'))
+
+    expect(() => sessions.fork(source, undefined, SessionId('child')))
+      .toThrow(new SessionForkError('session "child" already exists', 'SESSION_ALREADY_EXISTS'))
+  })
+
+  it('rejects a duplicate child session id before validating the boundary', async () => {
+    const { ctx, sessions } = await setup()
+    const source = ctx.sessions.create(SessionId('open-parent'))
+    source.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
+    ctx.sessions.create(SessionId('child'))
+
+    expect(() => sessions.fork(source, undefined, SessionId('child')))
+      .toThrow(new SessionForkError('session "child" already exists', 'SESSION_ALREADY_EXISTS'))
+  })
+})

packages/core/session/tests/request-header.spec.ts

@@ -8,9 +8,9 @@
  */
 
 import { describe, expect, it } from 'vitest'
-import { Session, SessionId, applyHeaderDelta, canonicalHeader, diffHeader, foldRequestHeader } from '@deepseek-ai/dsh-session'
+import { Session, SessionId, applyHeaderDelta, canonicalHeader, diffHeader, foldRequestHeader, headerEquals } from '@deepseek-ai/dsh-session'
 import type { EpochHeader, SessionEvent } from '@deepseek-ai/dsh-session'
-import type { ToolSchema } from '@deepseek-ai/dsh-llm'
+import type { Message, ToolSchema } from '@deepseek-ai/dsh-llm'
 
 const CONFIG = { model: 'm' }
 
@@ -18,6 +18,10 @@ function tool(name: string, description = 'd'): ToolSchema {
   return { name, description, parameters: { type: 'object' } }
 }
 
+function msg(text: string): Message {
+  return { role: 'user', content: [{ type: 'text', text }] }
+}
+
 /** Round-trip helper: diff must reproduce `next` from `prev` exactly. */
 function roundTrip(prev: EpochHeader, next: EpochHeader): ReturnType<typeof diffHeader> {
   const delta = diffHeader(prev, next)
@@ -103,6 +107,48 @@ describe('diffHeader / applyHeaderDelta', () => {
   })
 })
 
+describe('the session prefix (messagePrefix)', () => {
+  it('canonicalHeader normalizes an empty prefix to an absent field', () => {
+    expect(canonicalHeader({ config: CONFIG, messagePrefix: [] })).toEqual({ config: CONFIG })
+    const full = canonicalHeader({ config: CONFIG, messagePrefix: [msg('p')] })
+    expect(full.messagePrefix).toEqual([msg('p')])
+  })
+
+  it('headerEquals treats absence and empty as one representation, content differences as unequal', () => {
+    expect(headerEquals(canonicalHeader({ config: CONFIG }), { config: CONFIG, messagePrefix: [] })).toBe(true)
+    expect(headerEquals({ config: CONFIG, messagePrefix: [msg('a')] }, { config: CONFIG, messagePrefix: [msg('b')] })).toBe(false)
+    expect(headerEquals({ config: CONFIG, messagePrefix: [msg('a')] }, { config: CONFIG })).toBe(false)
+  })
+
+  it('replaces a changed prefix whole and leaves untouched parts alone', () => {
+    const prev = canonicalHeader({ config: CONFIG, system: 'keep', messagePrefix: [msg('old')] })
+    const next = canonicalHeader({ config: CONFIG, system: 'keep', messagePrefix: [msg('new'), msg('more')] })
+    const delta = roundTrip(prev, next)
+    expect(delta).toEqual({ messagePrefix: [msg('new'), msg('more')] })
+  })
+
+  it('round-trips a prefix gained from a bare header and lost back to one (empty array encodes absence)', () => {
+    const none = canonicalHeader({ config: CONFIG })
+    const some = canonicalHeader({ config: CONFIG, messagePrefix: [msg('p')] })
+    const gained = roundTrip(none, some)
+    expect(gained).toEqual({ messagePrefix: [msg('p')] })
+    const lost = roundTrip(some, none)
+    expect(lost).toEqual({ messagePrefix: [] })
+  })
+
+  it('folds prefix deltas over the log like any other header amendment', () => {
+    const session = new Session(SessionId('fold-prefix'))
+    session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
+    const first = canonicalHeader({ config: CONFIG, messagePrefix: [msg('catalog v1')] })
+    session.append('request/header', { header: first, reason: 'initial' })
+    const second = canonicalHeader({ config: CONFIG, messagePrefix: [msg('catalog v2')] })
+    session.append('request/header-delta', diffHeader(first, second)!)
+    expect(foldRequestHeader(session.events)).toEqual(second)
+    session.append('request/header-delta', diffHeader(second, canonicalHeader({ config: CONFIG }))!)
+    expect(foldRequestHeader(session.events)).toEqual({ config: CONFIG })
+  })
+})
+
 describe('foldRequestHeader', () => {
   function headerEvents(session: Session): readonly SessionEvent[] {
     return session.events

packages/core/session/tests/session.spec.ts

@@ -61,8 +61,10 @@ describe('Session', () => {
 
   it('replays identically from a seeded event log', () => {
     const original = new Session(SessionId('s3'))
+    original.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
     original.append('user/message', { content: [{ type: 'text', text: 'q' }], source: { kind: 'user' } }, { surfaceOp: 'append' })
     original.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'a' }] }, { surfaceOp: 'append' })
+    original.append('turn/end', { turn: 1, reason: { kind: 'completed' } })
 
     const replayed = new Session(SessionId('s3-replay'), [...original.events])
     expect(replayed.deriveMessages()).toEqual(original.deriveMessages())
@@ -423,7 +425,9 @@ describe('todo/write event', () => {
 
   it('round-trips through a seeded replay identically (durable, no surfaceOp needed)', () => {
     const original = new Session(SessionId('t4'))
+    original.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
     original.append('todo/write', { todos: [{ content: 'only', status: 'completed' }] })
+    original.append('turn/end', { turn: 1, reason: { kind: 'completed' } })
     // Seeding a non-surface event with no surfaceOp must not throw.
     const replayed = new Session(SessionId('t4-replay'), [...original.events])
     expect(replayed.events.findLast(e => e.type === 'todo/write')!.data.todos)

packages/core/system-prompt/README.md

@@ -7,15 +7,16 @@ System prompt assembly registry. Plugins contribute ordered text sections, tool-
 | Key | Default | Meaning |
 |---|---|---|
 | `persona` | `''` | The deployment persona: the ONE deployment-authored prompt fragment, rendered as the order-0 `deployment:persona` section and shared by every agent in the context (subagents included). A template — complete `{{…}}` groups are interpreted strictly against the registered variables (the shipped loop registers `{{model}}`/`{{cwd}}`), with no escape syntax for literal braces yet. Empty ⇒ the section is dropped at render. |
+| `toolOrder` | — | Explicit model-facing tool order, as a list of `ToolSchema.name`s with one `'<unlisted-tools>'` rest entry (`TOOL_ORDER_REST`): listed tools take their listed position, unlisted tools land at the rest entry in lexicographic name order. Absent ⇒ plain lexicographic name order. Applied to the collected tools BEFORE the `system-prompt/assemble` waterfall — like the sections' `order` sort, it canonicalizes what the registry contributed (registration order is a plugin-load artifact), and a waterfall listener that mutates the list owns the determinism of what it emits. Misconfiguration fails loud: a list without exactly one rest entry, or with duplicates, throws at load; a listed name with no registered tool rejects every `assemble()`; a tool provider returning the reserved rest-entry name also rejects. Under the shipped loop the turn fails before any model request. Why a central list and not per-plugin weights: [Explicit model-facing tool order](../../../docs/rfc/implemented/feature/2026-07-06-explicit-tool-order.md). |
 
 ## Service: `SystemPrompt` (ctx key: `systemPrompt`)
 
 ### Public API
 
 - `ctx.systemPrompt.section(section: PromptSection): () => void` Contribute a section. Duplicate names throw. Disposed with the calling fiber.
-- `ctx.systemPrompt.tools(provider: () => ToolSchema[]): () => void` Contribute tool schemas (evaluated at each assembly). Disposed with the calling fiber.
+- `ctx.systemPrompt.tools(provider: () => ToolSchema[]): () => void` Contribute tool schemas (evaluated at each assembly). A provider must not return a schema named `TOOL_ORDER_REST`; that name is reserved for `toolOrder`'s rest entry. Disposed with the calling fiber.
 - `ctx.systemPrompt.variable(name: string, provider: (context) => string | undefined): () => void` Contribute a prompt variable, referenced from section text as `{{name}}`. Duplicate or unreferenceable names throw; `undefined` means "no value for this assembly". Disposed with the calling fiber.
-- `ctx.systemPrompt.assemble(context?: AssembleContext): Promise<PromptAssembly>` Assemble the prompt for one caller. Runs through the `system-prompt/assemble` waterfall.
+- `ctx.systemPrompt.assemble(context?: AssembleContext): Promise<PromptAssembly>` Assemble the prompt for one caller. Runs through the `system-prompt/assemble` waterfall. Rejects when a configured `toolOrder` names a tool no provider contributed, or when a provider returns the reserved rest-entry name.
 
 ### Events
 

packages/core/system-prompt/src/index.ts

@@ -88,7 +88,8 @@ export interface AssembledSection {
  *
  * Tool schemas are part of the assembly by design: "what the model is told it
  * can do" is one coherent thing managed here, even though adapters transmit
- * `tools` as a separate wire field rather than prompt text.
+ * `tools` as a separate wire field rather than prompt text. They arrive in
+ * the canonical model-facing order (see {@link Config.toolOrder}).
  *
  * `variables` carries every registered prompt variable resolved against this
  * assembly's context — key present means registered, `undefined` value means
@@ -110,6 +111,71 @@ const VARIABLE_NAME = /^[a-z][a-z0-9_]*$/
 /** A complete `{{...}}` reference group at the scan position (validated after). */
 const GROUP_AT = /^\{\{([^{}]*)\}\}/
 
+/**
+ * The rest entry for {@link Config.toolOrder}: the position where registered
+ * tools not named in the list are inserted (in lexicographic name order).
+ * Reserved: collected tool schemas using this name are rejected before
+ * ordering, so the marker can never collide with a real model-facing tool.
+ */
+export const TOOL_ORDER_REST = '<unlisted-tools>'
+
+/**
+ * Validate a configured tool-order list's shape at service construction:
+ * the {@link TOOL_ORDER_REST} rest entry exactly once, no duplicate names.
+ * Returns the list (or undefined when unconfigured); throws otherwise,
+ * failing the service at load — a bad order config must never reach an
+ * assembly. Whether every listed name matches a registered tool is checked
+ * at each assembly instead ({@link orderTools}): tool plugins register after
+ * this service constructs, so the tool set does not exist yet here.
+ */
+function validateToolOrder(toolOrder: string[] | undefined): string[] | undefined {
+  if (toolOrder === undefined) return undefined
+  const seen = new Set<string>()
+  for (const name of toolOrder) {
+    if (seen.has(name)) throw new Error(`toolOrder lists "${name}" more than once`)
+    seen.add(name)
+  }
+  if (!seen.has(TOOL_ORDER_REST)) {
+    throw new Error(`toolOrder must contain the "${TOOL_ORDER_REST}" rest entry (where unlisted tools are inserted)`)
+  }
+  return toolOrder
+}
+
+/**
+ * Order collected tool schemas by the validated policy: with no configured
+ * list, plain lexicographic name order; with one, listed names take their
+ * listed position and every unlisted tool lands at the
+ * {@link TOOL_ORDER_REST} rest entry in lexicographic name order. A listed
+ * name with no collected tool throws — misconfiguration fails loud, and this
+ * is the earliest moment the registered tool set exists to check against
+ * (tool plugins register after the service constructs, so load time is too
+ * early): the assembly rejects, failing the caller's turn before any model
+ * request. Never drops a tool, and both sorts are stable, so tools sharing a
+ * name keep their collection order.
+ */
+function orderTools(tools: ToolSchema[], toolOrder: string[] | undefined): ToolSchema[] {
+  const reserved = tools.find(tool => tool.name === TOOL_ORDER_REST)
+  if (reserved !== undefined) {
+    throw new Error(`tool provider returned reserved tool name "${TOOL_ORDER_REST}" (reserved for toolOrder's rest entry)`)
+  }
+  if (toolOrder === undefined) return tools.sort(compareToolNames)
+  const registered = new Set(tools.map(tool => tool.name))
+  const unknown = toolOrder.filter(name => name !== TOOL_ORDER_REST && !registered.has(name))
+  if (unknown.length > 0) {
+    throw new Error(`toolOrder lists unregistered tool${unknown.length > 1 ? 's' : ''} ${unknown.map(name => `"${name}"`).join(', ')}; registered tools: ${[...registered].sort().join(', ') || '(none)'}`)
+  }
+  const listed = new Set(toolOrder)
+  const rest = tools.filter(tool => !listed.has(tool.name)).sort(compareToolNames)
+  return toolOrder.flatMap(name =>
+    name === TOOL_ORDER_REST ? rest : tools.filter(tool => tool.name === name))
+}
+
+/** Lexicographic (code-unit) name comparison — locale-independent, so the order is identical on every machine. */
+function compareToolNames(a: ToolSchema, b: ToolSchema): number {
+  return a.name < b.name ? -1 : a.name > b.name ? 1 : 0
+}
+
+/** Plugin config: the deployment-authored fragment of the system prompt (see {@link Config.persona} for its contract). */
 export interface Config {
   /**
    * The deployment's persona — the ONE deployment-authored fragment of the
@@ -124,6 +190,29 @@ export interface Config {
    * deployment opens with the harness identity alone.
    */
   persona?: string
+  /**
+   * Explicit model-facing tool order, as a list of `ToolSchema.name`s: listed
+   * tools take their listed position, and tools absent from the list are
+   * inserted at the {@link TOOL_ORDER_REST} (`'<unlisted-tools>'`) entry in
+   * lexicographic name order. A configured list must contain the rest entry
+   * exactly once, no duplicate names, and no name without a registered tool —
+   * a misconfigured order blocks work instead of silently reaching a model
+   * request: shape violations throw at load, and an unregistered name rejects
+   * every assembly. `TOOL_ORDER_REST` is reserved for the list marker and may
+   * not be a collected tool name; such a provider output also rejects the
+   * assembly. The single assembly-time validation rejects either failure
+   * before any model request — the earliest moment the registered tool set
+   * exists to check against, since tool plugins register after this service
+   * constructs. When omitted, tools are ordered lexicographically by name.
+   * Applied to the tools
+   * {@link SystemPrompt.assemble} collects, BEFORE the
+   * `system-prompt/assemble` waterfall — like the sections' `order` sort, it
+   * canonicalizes what the registry contributed (registration order is a
+   * plugin-load artifact); a waterfall listener that mutates the tool list
+   * owns the determinism of what it emits. Rationale (and why not per-plugin
+   * weights): docs/rfc/implemented/feature/2026-07-06-explicit-tool-order.md.
+   */
+  toolOrder?: string[]
 }
 
 /**
@@ -138,6 +227,10 @@ export interface Config {
  * while a `}}` still follows (e.g. `{{{model}}}`, `{{a{b}}`) all throw. A
  * lone `{{` with no `}}` anywhere after it is ordinary prose and passes
  * through verbatim. Substituted values are never re-scanned.
+ * @param assembly - the assembly to render (typically the awaited result of
+ *   {@link SystemPrompt.assemble}); only `sections` and `variables` are read.
+ * @returns the full system prompt text; `''` when every section renders empty
+ *   (the caller then sends no system prompt at all).
  */
 export function renderPrompt(assembly: PromptAssembly): string {
   return assembly.sections
@@ -198,14 +291,23 @@ function interpolate(section: AssembledSection, variables: Record<string, string
 export class SystemPrompt extends Service {
   static Config: z<Config> = z.object({
     persona: z.string().default(''),
+    // A schemastery array defaults to [] when omitted, but an omitted
+    // toolOrder must stay absent ("lexicographic order"), not become an
+    // explicitly-configured empty list (which is invalid — it lacks the
+    // rest entry). Forcing the default to undefined keeps the key out of the
+    // validated config; the cast is needed because .default() expects the
+    // array type.
+    toolOrder: z.array(z.string()).default(undefined as unknown as string[]),
   })
 
   private sections: PromptSection[] = []
   private toolProviders: (() => ToolSchema[])[] = []
   private variableProviders = new Map<string, (context: AssembleContext) => string | undefined>()
+  private readonly toolOrder: string[] | undefined
 
   constructor(ctx: Context, public config: Config) {
     super(ctx, 'systemPrompt')
+    this.toolOrder = validateToolOrder(config.toolOrder)
     // The harness-owned openers. They live HERE (not on the loop plugin) so a
     // deployment that swaps in a different loop keeps them: the identity is a
     // harness fact stated ahead of everything, and the persona is the
@@ -261,7 +363,10 @@ export class SystemPrompt extends Service {
   /**
    * Contribute a tool-schema provider that is evaluated at each assembly
    * call (so it can reflect the live registry state). The provider is
-   * removed when the calling fiber is disposed. Emits `system-prompt/change`.
+   * removed when the calling fiber is disposed. A provider must not return a
+   * schema named {@link TOOL_ORDER_REST}; that name is reserved for
+   * {@link Config.toolOrder}'s rest entry and rejects the assembly. Emits
+   * `system-prompt/change`.
    * @param provider - evaluated at every {@link assemble} for fresh schemas.
    * @returns the disposer that removes the provider.
    */
@@ -318,19 +423,28 @@ export class SystemPrompt extends Service {
 
   /**
    * Assemble the current prompt for one caller: section texts are resolved
-   * against `context` and sorted by order, tools collected from all
-   * providers, and every registered variable resolved against `context` into
-   * `assembly.variables`. Tool schemas are deep-cloned because adapters and
-   * request waterfalls may mutate schema objects. Runs through the
-   * `system-prompt/assemble` waterfall, giving listeners the opportunity to
-   * mutate or replace the assembly before it reaches the model. Await the
-   * result before reading the assembly values — waterfall listeners may be
-   * async. Interpolation happens later, in {@link renderPrompt}.
+   * against `context` and sorted by order, tools collected from all providers
+   * and put in the canonical model-facing order ({@link Config.toolOrder}, or
+   * lexicographic name order when unconfigured — provider registration order
+   * is a plugin-load artifact and never reaches the assembly; a configured
+   * order naming a tool no provider contributed rejects the assembly), and every
+   * registered variable resolved against `context` into `assembly.variables`.
+   * Tool schemas are deep-cloned because adapters and request waterfalls may
+   * mutate schema objects. Runs through the `system-prompt/assemble`
+   * waterfall, giving listeners the opportunity to mutate or replace the
+   * assembly before it reaches the model — like the sections' `order` sort,
+   * tool canonicalization happens on the initial assembly, and a listener
+   * owns the determinism of whatever it emits. Await the result before
+   * reading the assembly values — waterfall listeners may be async.
+   * Interpolation happens later, in {@link renderPrompt}.
    * @param context - what this assembly is for (defaults to an empty context;
    *   see {@link AssembleContext}).
    * @returns the assembly after the waterfall has run.
    */
-  assemble(context: AssembleContext = {}): Promise<PromptAssembly> {
+  // async so the misconfigured-toolOrder throw in orderTools surfaces as a
+  // rejection: a Promise-returning method must not throw synchronously
+  // (`assemble().catch(...)` would miss it).
+  async assemble(context: AssembleContext = {}): Promise<PromptAssembly> {
     const variables: Record<string, string | undefined> = {}
     for (const [name, provider] of this.variableProviders) {
       variables[name] = provider(context)
@@ -343,8 +457,10 @@ export class SystemPrompt extends Service {
           text: typeof section.text === 'function' ? section.text(context) : section.text,
         }))
         .sort((a, b) => a.order - b.order),
-      tools: this.toolProviders.flatMap(provider =>
-        provider().map(tool => ({ ...tool, parameters: structuredClone(tool.parameters) }))),
+      tools: orderTools(
+        this.toolProviders.flatMap(provider =>
+          provider().map(tool => ({ ...tool, parameters: structuredClone(tool.parameters) }))),
+        this.toolOrder),
       variables,
     }
     return this.ctx.waterfall(this, 'system-prompt/assemble', assembly, context, () => Promise.resolve(assembly))

packages/core/system-prompt/tests/tool-order.spec.ts

@@ -0,0 +1,115 @@
+import { describe, expect, it } from 'vitest'
+import { Context } from 'cordis'
+import SystemPrompt, { PromptAssembly, TOOL_ORDER_REST } from '@deepseek-ai/dsh-system-prompt'
+import type { ToolSchema } from '@deepseek-ai/dsh-llm'
+
+function tool(name: string, description = name): ToolSchema {
+  return { name, description, parameters: { type: 'object', properties: {} } }
+}
+
+async function mount(config: { persona?: string; toolOrder?: string[] } = {}): Promise<Context> {
+  const ctx = new Context()
+  await ctx.plugin(SystemPrompt, config)
+  return ctx
+}
+
+function names(assembly: PromptAssembly): string[] {
+  return assembly.tools.map(t => t.name)
+}
+
+describe('SystemPrompt tool order', () => {
+  // The ONE place the public constant's value is pinned; everything else
+  // (tests and deployment configs alike) references TOOL_ORDER_REST.
+  it('exports the rest entry as "<unlisted-tools>"', () => {
+    expect(TOOL_ORDER_REST).toBe('<unlisted-tools>')
+  })
+
+  it('assembles tools in lexicographic name order when no toolOrder is configured', async () => {
+    const ctx = await mount()
+    ctx.systemPrompt.tools(() => [tool('charlie'), tool('alpha')])
+    ctx.systemPrompt.tools(() => [tool('bravo')])
+    expect(names(await ctx.systemPrompt.assemble())).toEqual(['alpha', 'bravo', 'charlie'])
+  })
+
+  it('assembles the same order regardless of provider registration order', async () => {
+    const forward = await mount()
+    forward.systemPrompt.tools(() => [tool('alpha')])
+    forward.systemPrompt.tools(() => [tool('zulu')])
+    const backward = await mount()
+    backward.systemPrompt.tools(() => [tool('zulu')])
+    backward.systemPrompt.tools(() => [tool('alpha')])
+    expect(names(await forward.systemPrompt.assemble())).toEqual(['alpha', 'zulu'])
+    expect(names(await backward.systemPrompt.assemble())).toEqual(['alpha', 'zulu'])
+  })
+
+  it('applies a configured toolOrder: listed positions, rest at the rest entry lexicographically', async () => {
+    const ctx = await mount({ toolOrder: ['todo_write', TOOL_ORDER_REST, 'bash'] })
+    ctx.systemPrompt.tools(() => [tool('bash'), tool('echo_b'), tool('todo_write'), tool('echo_a')])
+    expect(names(await ctx.systemPrompt.assemble())).toEqual(['todo_write', 'echo_a', 'echo_b', 'bash'])
+  })
+
+  it('rejects the assembly when toolOrder names a tool that is not registered (misconfiguration blocks work)', async () => {
+    const ctx = await mount({ toolOrder: ['todo_write', 'ghost', TOOL_ORDER_REST, 'wraith'] })
+    ctx.systemPrompt.tools(() => [tool('bash'), tool('todo_write')])
+    await expect(ctx.systemPrompt.assemble()).rejects.toThrow(
+      'toolOrder lists unregistered tools "ghost", "wraith"; registered tools: bash, todo_write')
+  })
+
+  it('names the single unregistered tool when no tools are registered at all', async () => {
+    const ctx = await mount({ toolOrder: ['ghost', TOOL_ORDER_REST] })
+    await expect(ctx.systemPrompt.assemble()).rejects.toThrow(
+      'toolOrder lists unregistered tool "ghost"; registered tools: (none)')
+  })
+
+  it.each([
+    ['without an explicit toolOrder', undefined],
+    ['with only the rest entry configured', [TOOL_ORDER_REST]],
+  ])('rejects a provider tool named like the reserved rest entry %s', async (_case, toolOrder) => {
+    const ctx = await mount(toolOrder === undefined ? {} : { toolOrder })
+    ctx.systemPrompt.tools(() => [tool(TOOL_ORDER_REST)])
+    await expect(ctx.systemPrompt.assemble()).rejects.toThrow(
+      `tool provider returned reserved tool name "${TOOL_ORDER_REST}"`)
+  })
+
+  it('keeps collection order between tools that share a name (stable sort)', async () => {
+    const ctx = await mount()
+    ctx.systemPrompt.tools(() => [tool('dup', 'first'), tool('anchor'), tool('dup', 'second')])
+    const assembly = await ctx.systemPrompt.assemble()
+    expect(assembly.tools.map(t => t.description)).toEqual(['anchor', 'first', 'second'])
+  })
+
+  it('canonicalizes BEFORE the assemble waterfall: listeners see the ordered list and own their own edits', async () => {
+    const ctx = await mount()
+    ctx.systemPrompt.tools(() => [tool('zulu'), tool('alpha')])
+    let seen: string[] | undefined
+    ctx.on('system-prompt/assemble', function (assembly, _context, next) {
+      seen = assembly.tools.map(t => t.name)
+      // A listener-appended tool is NOT re-sorted — same contract as sections:
+      // canonicalization applies to what the registry contributed, and a
+      // listener owns the determinism of what it emits.
+      assembly.tools.push(tool('aardvark'))
+      return next()
+    })
+    const assembly = await ctx.systemPrompt.assemble()
+    expect(seen).toEqual(['alpha', 'zulu'])
+    expect(names(assembly)).toEqual(['alpha', 'zulu', 'aardvark'])
+  })
+
+  it.each([
+    ['an empty list', []],
+    ['a list without the rest entry', ['bash', 'todo_write']],
+  ])('rejects %s at load (the rest entry is required)', async (_case, toolOrder) => {
+    await expect(new Context().plugin(SystemPrompt, { toolOrder })).rejects.toThrow(`must contain the "${TOOL_ORDER_REST}" rest entry`)
+  })
+
+  it.each([
+    ['a duplicate tool name', ['bash', 'bash', TOOL_ORDER_REST]],
+    ['a duplicate rest entry', [TOOL_ORDER_REST, 'bash', TOOL_ORDER_REST]],
+  ])('rejects %s at load', async (_case, toolOrder) => {
+    await expect(new Context().plugin(SystemPrompt, { toolOrder })).rejects.toThrow('more than once')
+  })
+
+  it('throws from direct construction too', () => {
+    expect(() => new SystemPrompt(new Context(), { toolOrder: ['bash'] })).toThrow('rest entry')
+  })
+})

packages/core/tools/README.md

@@ -1,6 +1,6 @@
 # dsh-tools
 
-Tool registry and execution pipeline. Tool plugins register their schemas and executors; the agent loop executes each call through `tools/pre-execute` (the allow/deny gate) → core dispatch → `tools/post-execute` (inspect/replace the result, attach context).
+Tool registry and execution pipeline. Tool plugins register their schemas and executors; the agent loop executes each call through `tools/pre-execute` (the allow/deny gate) → `tools/execute` (an around-dispatch wrapper for timeout/retry/metrics plugins) → `tools/post-execute` (inspect/replace the result, attach context).
 
 ## Service: `ToolRegistry` (ctx key: `tools`)
 
@@ -8,8 +8,8 @@ Tool registry and execution pipeline. Tool plugins register their schemas and ex
 
 - `ctx.tools.register(definition: ToolDefinition): () => void` Register a tool. Disposed with the calling fiber.
 - `ctx.tools.get(name: string): ToolDefinition | undefined`
-- `ctx.tools.schemas(): ToolSchema[]` Schemas of all registered tools (without the `execute` functions). The shipped tools' schemas are catalogued in [docs/tool-catalog/tools.md](../../../docs/tool-catalog/tools.md), generated by booting each tool plugin and harvesting this method (see [the tool-schema-catalog RFC](../../../docs/rfc/implemented/process/2026-07-02-tool-schema-catalog.md)).
-- `ctx.tools.execute(exec: ToolExecution): Promise<ToolExecutionResult>` Execute one tool call through the `tools/pre-execute` → dispatch → `tools/post-execute` pipeline.
+- `ctx.tools.schemas(): ToolSchema[]` Schemas of all registered tools (without the `execute` functions). The shipped tools' schemas are catalogued in [docs/tool-catalog.md](../../../docs/tool-catalog.md), generated by booting each tool plugin and harvesting this method (see [the tool-schema-catalog RFC](../../../docs/rfc/implemented/process/2026-07-02-tool-schema-catalog.md)).
+- `ctx.tools.execute(exec: ToolExecution): Promise<ToolExecutionResult>` Execute one tool call through the `tools/pre-execute` → `tools/execute` → `tools/post-execute` pipeline.
 
 ### Injected services
 
@@ -20,12 +20,13 @@ Tool registry and execution pipeline. Tool plugins register their schemas and ex
 | Event | Mode | Purpose |
 |---|---|---|
 | `tools/pre-execute` | waterfall | Allow/deny gate BEFORE a tool runs (sandbox, permission, hooks); returns `PreToolDecision` |
+| `tools/execute` | waterfall | Around-dispatch wrapper (timeout, retry, metrics): `(exec, next)` → the dispatched `ToolExecutionResult`; `next()` is dispatch-with-normalization |
 | `tools/post-execute` | waterfall | Inspect/replace the result AFTER a tool runs, attach context; returns `PostToolDecision` |
 | `tools/change` | emit | A tool was registered or unregistered |
 
 ### Key types
 
-- `ToolDefinition` — `ToolSchema` + `execute(args, exec): Promise<ContentBlock[] | { content: ContentBlock[]; meta? }>` (the bare array is the model-facing content; the object form additionally attaches an opaque, JSON-serializable `meta` presentation payload persisted on the `tool/result` event and handed back to `presentResult`), plus optional `presentCall(args)` / `presentResult(args, result)` for tool-owned UI presentation (see below).
+- `ToolDefinition` — `ToolSchema` + `execute(args, exec): Promise<ContentBlock[] | { content: ContentBlock[]; meta? }>` (the bare array is the model-facing content; the object form additionally attaches an opaque, JSON-serializable `meta` presentation payload persisted on the `tool/result` event and handed back to `presentResult`), plus optional `presentCall(args)` / `presentResult(args, result)` for tool-owned UI presentation (see below). It also carries an optional cooperative timeout budget `timeoutMs?: number` (ms) enforced by `@deepseek-ai/dsh-timeout-policy`, never sent to the model.
 - `ToolExecution` — one pending tool call: `{ callId, name, arguments, agent?, signal? }`.
 - `ToolExecutionResult` — outcome: `{ callId, content, isError, error?, additionalContext?, meta? }`. On failure with a `HarnessError`, `error: { name, code }` carries the structured failure class alongside the model-facing text (the loop forwards it onto the `tool/result` session event for retry/sandbox plugins and replay). `additionalContext` (a `HookContext`) ferries any `tools/post-execute` context up to the loop, which buffers it and appends it as a `context/message` after all `tool/result`s in the step. `meta` is the tool's opaque presentation payload from a successful `execute` (the object return form); the loop forwards it onto the `tool/result` session event for result-card rendering.
 - `PreToolDecision` — `{kind:'allow'}` | `{kind:'deny', reason}` | `{kind:'ask', reason?}`. Input rewrite (changing `arguments`) is deliberately NOT offered (it would desync the pre-execution audit/history/UI from what ran — its own proposed RFC); `ask` degrades to `deny` until the permission system lands.
@@ -35,7 +36,7 @@ Tool registry and execution pipeline. Tool plugins register their schemas and ex
 ### Extension points
 
 - Tool plugins call `ctx.tools.register()` — schemas flow into the assembly automatically.
-- `tools/pre-execute` is the allow/deny gate (sandbox, permission, hooks): listeners receive `(exec, next)` and call `next()` to delegate to the default (allow) or return a `PreToolDecision` to short-circuit; a `deny`/`ask` skips dispatch and yields an `isError` result. `tools/post-execute` is the inspect/transform seam: `(exec, result, next)` → a `PostToolDecision` that can replace content, block with feedback, or attach `additionalContext`. Core dispatch sits between them as plain code; the tool body keeps its own try/catch so a thrown tool still reaches `post-execute` as an `isError`. Both follow the typed-Decision idiom shared with the `agent/*` interception seams (see [`dsh-agent`](../agent/README.md)).
+- `tools/pre-execute` is the allow/deny gate (sandbox, permission, hooks): listeners receive `(exec, next)` and call `next()` to delegate to the default (allow) or return a `PreToolDecision` to short-circuit; a `deny`/`ask` skips dispatch and yields an `isError` result. `tools/execute` is the around-dispatch seam (timeout, retry, metrics): listeners receive `(exec, next)` and call `next()` to delegate to core dispatch (returning its `ToolExecutionResult`, optionally wrapped), or return a replacement result to short-circuit dispatch; the base `next()` IS dispatch-with-normalization, so `await next()` already yields an `isError` result for a thrown/unknown tool (never a raw throw). A wrapper mutates `exec` in place before `next()` — e.g. replacing `exec.signal` with a per-call deadline — because cordis `next()` ignores passed arguments. `tools/post-execute` is the inspect/transform seam: `(exec, result, next)` → a `PostToolDecision` that can replace content, block with feedback, or attach `additionalContext`. Core dispatch is the base of the `tools/execute` waterfall; the tool body keeps its own try/catch so a thrown tool still reaches `post-execute` as an `isError`. All follow the typed-Decision idiom shared with the `agent/*` interception seams (see [`dsh-agent`](../agent/README.md)); `@deepseek-ai/dsh-timeout-policy` is the reference `tools/execute` wrapper.
 - MCP servers: one plugin per server, discover tools, call `ctx.tools.register()` with the server's schemas.
 
 ### Typed tool parameter schemas
@@ -71,6 +72,14 @@ A `defineTool` tool also **validates the model-generated arguments against its `
 
 See `defineTool`, `validateArgs`, `ToolArgsError`, `SchemaSpec`, `InferArgs`, and `schemaSpecToJsonSchema` in the public API for details.
 
+`defineTool` also validates an optional `timeoutMs` at definition time when present: it must be a positive finite number, or the helper throws — the budget is attached to the produced `ToolDefinition` (for `@deepseek-ai/dsh-timeout-policy`) and never reaches the model.
+
+### Structured-output schema subset
+
+A separate vocabulary for callers that DEMAND a machine-readable value from an agent — the subagent seam's `SubagentStartRequest.outputSchema` (and, by extension, a workflow's `agent({ schema })`). Unlike `SchemaSpec` (the author-facing DSL for tool parameters), a `StructuredOutputSchema` is an object-rooted **raw JSON Schema subset** as data: it travels verbatim to the model as a forced tool's `parameters`, and the produced value is validated against it.
+
+The subset is deliberately narrow and REJECTS LOUD outside it — accepting a keyword the validator doesn't enforce would validate less than the schema promises (accepted-then-ignored). Supported: single-string `type` (`object`/`array`/`string`/`number`/`integer`/`boolean`/`null`; type arrays rejected), `properties`/`required`/`additionalProperties` (boolean; every `required` key must be declared), `items`, scalar-only `enum`/`const`; annotations (`description`/`title`/`default`/`examples`) are ignored but must still be JSON data. `assertSupportedOutputSchema(schema)` throws `OutputSchemaError` (`code: 'UNSUPPORTED_SCHEMA'`, listing every violation) for anything else; `validateStructuredValue(schema, value)` returns path-qualified violations (empty = valid, total — never throws).
+
 ### Tool-owned UI presentation
 
 A tool owns how ITS calls render in a UI (an editor's tool-call card, a CLI log line) — a UI plugin must NOT special-case tool names. A `ToolDefinition` may declare two optional, pure, display-only methods that return a **`card`-tagged render intent** (a discriminated union — a tool declares its card kind once and a UI bridge switches on `card`):

packages/core/tools/src/index.ts

@@ -1,9 +1,10 @@
 /**
  * Tool registry and execution pipeline. Plugins register tools; the registry
  * feeds schemas into the system prompt, and `execute()` dispatches each call
- * through `tools/pre-execute` (the allow/deny gate) → core dispatch →
- * `tools/post-execute` (inspect/replace the result, attach context) for
- * sandbox, permission, and hook plugins to gate or transform a call.
+ * through `tools/pre-execute` (the allow/deny gate) → `tools/execute` (an
+ * around-dispatch wrapper for timeout/retry/metrics plugins) → `tools/post-execute`
+ * (inspect/replace the result, attach context) for sandbox, permission, and hook
+ * plugins to gate or transform a call.
  *
  * @module @deepseek-ai/dsh-tools
  */
@@ -28,6 +29,16 @@ export {
   type JsonSchemaObject,
 } from './schema.ts'
 
+export {
+  assertSupportedOutputSchema,
+  validateStructuredValue,
+  OutputSchemaError,
+  type StructuredOutputSchema,
+  type StructuredSchemaNode,
+  type StructuredSchemaType,
+  type StructuredScalar,
+} from './json-schema.ts'
+
 // The render-intent vocabulary a tool declares via `presentCall`/`presentResult`
 // lives in its own UI-facing module; re-export it so `@deepseek-ai/dsh-tools`
 // stays the single public surface for consumers (producers + the ACP bridge).
@@ -64,17 +75,37 @@ declare module 'cordis' {
      * @mode waterfall
      */
     'tools/pre-execute'(this: ToolRegistry, exec: ToolExecution, next: () => Promise<PreToolDecision>): Promise<PreToolDecision>
+    /**
+     * Around-dispatch waterfall wrapping the registry's core tool dispatch,
+     * between the `tools/pre-execute` gate and the `tools/post-execute` seam. A
+     * listener receives `(exec, next)`: call `next()` to delegate to dispatch
+     * (returning its {@link ToolExecutionResult}, optionally wrapped), or return a
+     * replacement result without calling `next()` to short-circuit dispatch. The
+     * base `next()` IS the dispatch-with-normalization thunk — a thrown tool (or
+     * unknown tool) is already normalized to an `isError` result by the time a
+     * listener's `await next()` returns, so a wrapper never sees a raw throw from
+     * the tool body. This is the seam a timeout/retry/metrics plugin wraps: it can
+     * mutate `exec` (e.g. replace `exec.signal` with a per-call deadline) BEFORE
+     * `next()` and inspect the result AFTER. (Cordis `next()` ignores any passed
+     * arguments and re-invokes downstream with the shared payload, so a wrapper
+     * mutates `exec` in place rather than passing a new object to `next()`.)
+     * Multiple listeners compose by registration order — an outer one wraps the
+     * inner ones plus dispatch.
+     * @param exec - the allowed call about to dispatch (name, parsed arguments, caller agent, signal).
+     * @mode waterfall
+     */
+    'tools/execute'(this: ToolRegistry, exec: ToolExecution, next: () => Promise<ToolExecutionResult>): Promise<ToolExecutionResult>
     /**
      * Waterfall AFTER a tool runs — where hook plugins inspect the result and
      * accept it (optionally REPLACING the model-facing content, and/or attaching
      * `additionalContext` for the next request) or block it with corrective
      * `feedback` (Claude Code's `PostToolUse`). Listeners receive
      * `(exec, result, next)`: call `next()` to delegate to the default (accept
-     * unchanged), or return a {@link PostToolDecision} to override. The core tool
-     * dispatch sits between the two waterfalls as plain code, all inside
-     * `execute`'s outer try/catch (and the tool body keeps its own inner
-     * try/catch, so a thrown tool still reaches `post-execute` as an `isError`
-     * result).
+     * unchanged), or return a {@link PostToolDecision} to override. Core tool
+     * dispatch runs earlier as the base `next()` of the `tools/execute`
+     * waterfall, all inside `execute`'s outer try/catch (and the tool body keeps
+     * its own inner try/catch, so a thrown tool still reaches `post-execute` as an
+     * `isError` result).
      * @param exec - the call that just ran (name, parsed arguments, caller agent).
      * @param result - the dispatch outcome a listener may accept, replace, or block.
      * @mode waterfall
@@ -107,6 +138,14 @@ export type ToolExecuteReturn = ContentBlock[] | { content: ContentBlock[]; meta
 /** A registered tool: its schema plus the execution function. */
 export interface ToolDefinition extends ToolSchema {
   execute(args: unknown, exec: ToolExecution): Promise<ToolExecuteReturn>
+  /**
+   * Cooperative tool-call timeout budget in milliseconds. Omit for no deadline.
+   * Enforced by `@deepseek-ai/dsh-timeout-policy` (a `tools/execute` wrapper); it
+   * is NEVER sent to the model — `schemas()` whitelists only name/description/
+   * parameters. Declaring it asserts this tool forwards `exec.signal` to a
+   * cooperative implementation that can reach quiescence when the signal aborts.
+   */
+  timeoutMs?: number
   /**
    * Optional: how to present the PENDING state of one call in a UI, derived from
    * the call's `args` (parsed arguments, `unknown` — the tool validates/narrows
@@ -261,7 +300,7 @@ function errorInfo(error: unknown): ToolErrorInfo | undefined {
 
 /**
  * Tool registry (`ctx.tools`): tool plugins register definitions; the agent
- * loop executes calls through the `tools/pre-execute` → dispatch →
+ * loop executes calls through the `tools/pre-execute` → `tools/execute` →
  * `tools/post-execute` pipeline. The registry contributes its schemas into the
  * system-prompt assembly.
  */
@@ -335,18 +374,20 @@ export class ToolRegistry extends Service {
   }
 
   /**
-   * Execute one tool call through the `tools/pre-execute` → dispatch →
-   * `tools/post-execute` pipeline. The two waterfalls are the gate (allow/deny)
-   * and the inspect/transform seam; core dispatch sits between them as plain
-   * code. The whole thing is wrapped in one outer try/catch so a throwing
-   * listener (in either waterfall) becomes an `isError` result instead of
-   * failing the turn; the tool body ALSO keeps its own inner try/catch, so a
-   * thrown tool becomes an `isError` result that `post-execute` listeners can
-   * still inspect. If the tool is not registered, the result is an `isError`
-   * carrying a `UNKNOWN_TOOL` structured error. A thrown {@link HarnessError}
-   * surfaces its `{ name, code }` on the result.
+   * Execute one tool call through the `tools/pre-execute` → `tools/execute`
+   * (around dispatch) → `tools/post-execute` pipeline. `pre-execute` is the gate
+   * (allow/deny), `tools/execute` wraps core dispatch (a timeout/retry/metrics
+   * seam), and `post-execute` is the inspect/transform seam; core dispatch sits
+   * as the base `next()` of the `tools/execute` waterfall. The whole thing is
+   * wrapped in one outer try/catch so a throwing listener (in any waterfall)
+   * becomes an `isError` result instead of failing the turn; the tool body ALSO
+   * keeps its own inner try/catch, so a thrown tool becomes an `isError` result
+   * that `tools/execute` and `post-execute` listeners can still inspect. If the
+   * tool is not registered, the result is an `isError` carrying a `UNKNOWN_TOOL`
+   * structured error. A thrown {@link HarnessError} surfaces its `{ name, code }`
+   * on the result.
    * @param exec - the call to run (name, parsed arguments, caller agent, signal).
-   * @returns the final result after both waterfalls; failures resolve as
+   * @returns the final result after every waterfall; failures resolve as
    *   `isError` results, never rejections.
    */
   async execute(exec: ToolExecution): Promise<ToolExecutionResult> {
@@ -372,23 +413,30 @@ export class ToolRegistry extends Service {
         return await this.postExecute(exec, denied)
       }
 
-      // --- Core dispatch (plain code between the waterfalls). The tool body's
-      // own try/catch turns a throw into an isError result so post-execute can
-      // inspect it; an unknown tool routes through the same catch. ---
-      let result: ToolExecutionResult
-      try {
-        const tool = this.store.get(exec.name)
-        if (!tool) throw new ToolNotFoundError(exec.name)
-        // Normalize the two `execute` return shapes: a bare ContentBlock[] (no
-        // meta) or a { content, meta } object (a tool attaching a private
-        // presentation payload). An array IS the content; the object carries it.
-        const returned = await tool.execute(exec.arguments, exec)
-        const content = Array.isArray(returned) ? returned : returned.content
-        const meta = Array.isArray(returned) ? undefined : returned.meta
-        result = { callId: exec.callId, content, isError: false, ...meta !== undefined ? { meta } : {} }
-      } catch (error: unknown) {
-        result = toolErrorResult(exec.callId, error)
-      }
+      // --- Around-dispatch: tools/execute. The base `next` is the dispatch-
+      // with-normalization thunk — the tool body's own try/catch turns a throw
+      // into an isError result so a wrapper (and post-execute) can inspect it;
+      // an unknown tool routes through the same catch. A `tools/execute` listener
+      // (e.g. a timeout plugin) wraps this thunk: it may mutate `exec` before
+      // delegating and inspect the normalized result after. ---
+      const result = await this.ctx.waterfall(
+        this, 'tools/execute', exec,
+        async (): Promise<ToolExecutionResult> => {
+          try {
+            const tool = this.store.get(exec.name)
+            if (!tool) throw new ToolNotFoundError(exec.name)
+            // Normalize the two `execute` return shapes: a bare ContentBlock[] (no
+            // meta) or a { content, meta } object (a tool attaching a private
+            // presentation payload). An array IS the content; the object carries it.
+            const returned = await tool.execute(exec.arguments, exec)
+            const content = Array.isArray(returned) ? returned : returned.content
+            const meta = Array.isArray(returned) ? undefined : returned.meta
+            return { callId: exec.callId, content, isError: false, ...meta !== undefined ? { meta } : {} }
+          } catch (error: unknown) {
+            return toolErrorResult(exec.callId, error)
+          }
+        },
+      )
 
       return await this.postExecute(exec, result)
     } catch (error: unknown) {

packages/core/tools/src/json-schema.ts

@@ -0,0 +1,345 @@
+/**
+ * Structured-output JSON Schema subset: the vocabulary a caller uses to demand
+ * a machine-readable result from a subagent (`SubagentStartRequest.outputSchema`)
+ * or a workflow `agent()` call.
+ *
+ * This is deliberately NOT full JSON Schema. The schema travels verbatim to the
+ * model as a forced tool's `parameters`, and the value the model produces is
+ * validated here — so every accepted keyword must be one this module actually
+ * enforces. Accepting a keyword we don't enforce would validate less than the
+ * schema promises (accepted-then-ignored), so anything outside the subset is
+ * REJECTED LOUD by {@link assertSupportedOutputSchema} instead. The subset:
+ *
+ * - `type` — a single string (`object`/`array`/`string`/`number`/`integer`/
+ *   `boolean`/`null`); type ARRAYS (`["string","null"]`) are rejected.
+ * - `properties`/`required`/`additionalProperties` (boolean) on objects; every
+ *   `required` key must be declared in `properties`. `additionalProperties`
+ *   absent keeps standard JSON Schema semantics (extra keys allowed).
+ * - `items` on arrays (absent ⇒ any JSON items).
+ * - `enum` (non-empty, scalars only) and `const` (scalar) on scalar types.
+ * - Annotations `description`/`title`/`default`/`examples` are allowed and
+ *   ignored (they constrain nothing), except that they must still be JSON data
+ *   — the schema is serialized onto the wire, so a non-JSON annotation would be
+ *   silently mangled.
+ *
+ * Values checked by {@link validateStructuredValue} are expected to be plain
+ * host-realm JSON data (model tool-call arguments are parsed wire JSON; a
+ * caller holding foreign-realm data materializes it first).
+ *
+ * @module dsh-tools/json-schema
+ */
+
+import { assertNever, HarnessError } from '@deepseek-ai/dsh-llm'
+
+/** The scalar values `enum`/`const` may carry (finite numbers only). */
+export type StructuredScalar = string | number | boolean | null
+
+/** The `type` keywords the subset accepts. */
+export type StructuredSchemaType = 'object' | 'array' | 'string' | 'number' | 'integer' | 'boolean' | 'null'
+
+/**
+ * One node of the structured-output schema subset. Recursive via `properties`
+ * and `items`; see the module doc for the exact keyword semantics.
+ */
+export interface StructuredSchemaNode {
+  type: StructuredSchemaType
+  /** Nested property schemas (`type: 'object'` only). */
+  properties?: Record<string, StructuredSchemaNode>
+  /** Required property names; each must appear in `properties`. */
+  required?: string[]
+  /** `false` rejects undeclared keys; absent/`true` allows them (JSON Schema default). */
+  additionalProperties?: boolean
+  /** Item schema (`type: 'array'` only); absent ⇒ any JSON items. */
+  items?: StructuredSchemaNode
+  /** Allowed values (scalar types only). */
+  enum?: StructuredScalar[]
+  /** The single allowed value (scalar types only). */
+  const?: StructuredScalar
+  /** Annotation, ignored for validation. */
+  description?: string
+  /** Annotation, ignored for validation. */
+  title?: string
+  /** Annotation, ignored for validation (must still be JSON data). */
+  default?: unknown
+  /** Annotation, ignored for validation (must still be JSON data). */
+  examples?: unknown
+}
+
+/** A structured-output schema: an OBJECT-rooted {@link StructuredSchemaNode}. */
+export type StructuredOutputSchema = StructuredSchemaNode & { type: 'object' }
+
+/**
+ * Thrown by {@link assertSupportedOutputSchema} when a schema falls outside the
+ * supported subset. Extends {@link HarnessError} (`code: 'UNSUPPORTED_SCHEMA'`)
+ * so seam code and tool results can route on it; `violations` lists every
+ * offending path, not just the first.
+ */
+export class OutputSchemaError extends HarnessError {
+  /** The individual violation messages, in walk order. */
+  readonly violations: string[]
+
+  constructor(violations: string[]) {
+    super(`unsupported output schema: ${violations.join('; ')}`, 'UNSUPPORTED_SCHEMA')
+    this.name = 'OutputSchemaError'
+    this.violations = violations
+  }
+}
+
+/** The keywords the subset accepts, checked (`constraint`) or ignored (`annotation`). */
+const CONSTRAINT_KEYWORDS = new Set(['type', 'properties', 'required', 'additionalProperties', 'items', 'enum', 'const'])
+const ANNOTATION_KEYWORDS = new Set(['description', 'title', 'default', 'examples'])
+
+const SCHEMA_TYPES: readonly StructuredSchemaType[] = ['object', 'array', 'string', 'number', 'integer', 'boolean', 'null']
+
+/**
+ * Whether a value is a PLAIN JSON object — non-null, non-array, and with a
+ * prototype chain of at most one link (`null`-proto, or any realm's
+ * `Object.prototype`, whose own prototype is `null`). Realm-agnostic on
+ * purpose: a schema materialized in another realm carries THAT realm's
+ * `Object.prototype`, which an identity check would wrongly reject. Exotic
+ * hosts (`Date`, `Map`, class instances) have longer chains and are rejected —
+ * they would serialize lossily (`Date` → string, `Map` → `{}`) instead of
+ * failing loud.
+ */
+function isObjectLike(value: unknown): value is Record<string, unknown> {
+  if (typeof value !== 'object' || value === null || Array.isArray(value)) return false
+  const proto: unknown = Object.getPrototypeOf(value)
+  return proto === null || Object.getPrototypeOf(proto) === null
+}
+
+/** Whether a value is a supported scalar (`enum`/`const` member): string, finite number, boolean, or null. */
+function isStructuredScalar(value: unknown): value is StructuredScalar {
+  return value === null || typeof value === 'string' || typeof value === 'boolean'
+    || (typeof value === 'number' && Number.isFinite(value))
+}
+
+/**
+ * Whether a value is JSON data (annotation payloads only): scalars, arrays, and
+ * object-likes of such values. Realm-agnostic on purpose (no prototype check) —
+ * the schema may have been materialized from another realm; structural JSON-ness
+ * is what the wire needs. Cycles are rejected via `seen`.
+ */
+function isJsonData(value: unknown, seen: Set<object>): boolean {
+  if (isStructuredScalar(value)) return true
+  // The scalar check above already returned for null, so `object` here is a real object.
+  if (typeof value !== 'object') return false
+  if (seen.has(value)) return false
+  seen.add(value)
+  try {
+    if (Array.isArray(value)) return value.every(entry => isJsonData(entry, seen))
+    // A non-plain object (Date, Map, class instance) is NOT JSON data even when
+    // it has no enumerable values — it would serialize lossily, not loudly.
+    if (!isObjectLike(value)) return false
+    return Object.values(value).every(entry => isJsonData(entry, seen))
+  } finally {
+    seen.delete(value)
+  }
+}
+
+/** Collect subset violations for one schema node (recursive walk). */
+function checkSchemaNode(node: unknown, path: string, violations: string[], seen: Set<object>): void {
+  if (!isObjectLike(node)) {
+    violations.push(`${path} must be a schema object`)
+    return
+  }
+  if (seen.has(node)) {
+    violations.push(`${path} is circular`)
+    return
+  }
+  seen.add(node)
+
+  for (const key of Object.keys(node)) {
+    if (CONSTRAINT_KEYWORDS.has(key)) continue
+    if (ANNOTATION_KEYWORDS.has(key)) {
+      if (!isJsonData(node[key], new Set())) violations.push(`${path}.${key} annotation must be JSON data`)
+      continue
+    }
+    violations.push(`${path}.${key} is not a supported keyword (subset: type/properties/required/additionalProperties/items/enum/const + annotations)`)
+  }
+  if (typeof node.description !== 'undefined' && typeof node.description !== 'string') {
+    violations.push(`${path}.description must be a string`)
+  }
+  if (typeof node.title !== 'undefined' && typeof node.title !== 'string') {
+    violations.push(`${path}.title must be a string`)
+  }
+
+  const type = node.type
+  if (typeof type !== 'string' || !(SCHEMA_TYPES as readonly unknown[]).includes(type)) {
+    violations.push(Array.isArray(type)
+      ? `${path}.type must be a single type string (type arrays are not supported)`
+      : `${path}.type must be one of ${SCHEMA_TYPES.join('/')}`)
+    seen.delete(node)
+    return
+  }
+  const schemaType = type as StructuredSchemaType
+
+  // Keywords that only make sense on one type are rejected elsewhere — an
+  // `items` on an object (or `properties` on a string) is a schema-author bug
+  // the subset surfaces rather than ignores.
+  const allowedFor: Record<string, StructuredSchemaType[]> = {
+    properties: ['object'],
+    required: ['object'],
+    additionalProperties: ['object'],
+    items: ['array'],
+    enum: ['string', 'number', 'integer', 'boolean', 'null'],
+    const: ['string', 'number', 'integer', 'boolean', 'null'],
+  }
+  for (const [key, types] of Object.entries(allowedFor)) {
+    if (key in node && !types.includes(schemaType)) {
+      violations.push(`${path}.${key} is not supported on type "${schemaType}"`)
+    }
+  }
+
+  switch (schemaType) {
+    case 'object': {
+      const properties = node.properties
+      if (properties !== undefined) {
+        if (!isObjectLike(properties)) {
+          violations.push(`${path}.properties must be an object of schemas`)
+        } else {
+          for (const [key, child] of Object.entries(properties)) {
+            checkSchemaNode(child, `${path}.properties.${key}`, violations, seen)
+          }
+        }
+      }
+      const required = node.required
+      if (required !== undefined) {
+        if (!Array.isArray(required) || required.some(entry => typeof entry !== 'string')) {
+          violations.push(`${path}.required must be an array of strings`)
+        } else {
+          const declared = isObjectLike(properties) ? properties : {}
+          // The guard above proved every entry is a string.
+          for (const key of required as string[]) {
+            // Own-property check: `in` would let inherited names (`toString`)
+            // satisfy the declared-in-properties contract via the prototype.
+            if (!Object.hasOwn(declared, key)) violations.push(`${path}.required names "${key}" which is not in properties`)
+          }
+        }
+      }
+      if (node.additionalProperties !== undefined && typeof node.additionalProperties !== 'boolean') {
+        violations.push(`${path}.additionalProperties must be a boolean`)
+      }
+      break
+    }
+    case 'array': {
+      if (node.items !== undefined) checkSchemaNode(node.items, `${path}.items`, violations, seen)
+      break
+    }
+    case 'string':
+    case 'number':
+    case 'integer':
+    case 'boolean':
+    case 'null': {
+      const allowed = node.enum
+      if (allowed !== undefined) {
+        if (!Array.isArray(allowed) || allowed.length === 0 || !allowed.every(entry => isStructuredScalar(entry))) {
+          violations.push(`${path}.enum must be a non-empty array of scalars`)
+        }
+      }
+      if ('const' in node && !isStructuredScalar(node.const)) {
+        violations.push(`${path}.const must be a scalar`)
+      }
+      break
+    }
+    /* v8 ignore start -- defensive: schemaType was membership-checked against SCHEMA_TYPES above, so no runtime value reaches here */
+    default:
+      assertNever(schemaType, 'assertSupportedOutputSchema')
+    /* v8 ignore stop */
+  }
+
+  seen.delete(node)
+}
+
+/**
+ * Assert `schema` is a supported {@link StructuredOutputSchema} — object-rooted
+ * and entirely within the enforced subset. Throws {@link OutputSchemaError}
+ * (`UNSUPPORTED_SCHEMA`) listing EVERY violation; returns (and narrows) on
+ * success. Call this at the seam boundary, before any child is created.
+ * @param schema - the caller-supplied schema (unknown until asserted).
+ * @returns nothing — the assertion signature narrows `schema` to
+ * {@link StructuredOutputSchema} in the caller's scope on normal return.
+ */
+export function assertSupportedOutputSchema(schema: unknown): asserts schema is StructuredOutputSchema {
+  const violations: string[] = []
+  checkSchemaNode(schema, 'schema', violations, new Set())
+  if (violations.length === 0 && (schema as StructuredSchemaNode).type !== 'object') {
+    violations.push('schema.type must be "object" (structured output is object-rooted)')
+  }
+  if (violations.length > 0) throw new OutputSchemaError(violations)
+}
+
+/** Collect violations for one value against an (already asserted) schema node. */
+function checkValue(node: StructuredSchemaNode, value: unknown, path: string): string[] {
+  switch (node.type) {
+    case 'object': {
+      if (!isObjectLike(value)) return [`"${path}" must be an object`]
+      const violations: string[] = []
+      const properties = node.properties ?? {}
+      // Own-property discipline throughout: JSON carries own enumerable
+      // properties only, so an inherited `toString` must not satisfy
+      // `required`, dodge `additionalProperties: false`, or be validated as if
+      // the value carried it.
+      for (const key of node.required ?? []) {
+        if (!Object.hasOwn(value, key) || value[key] === undefined) violations.push(`missing required property "${path}.${key}"`)
+      }
+      for (const [key, child] of Object.entries(properties)) {
+        if (!Object.hasOwn(value, key) || value[key] === undefined) continue
+        violations.push(...checkValue(child, value[key], `${path}.${key}`))
+      }
+      if (node.additionalProperties === false) {
+        for (const key of Object.keys(value)) {
+          if (!Object.hasOwn(properties, key)) violations.push(`"${path}.${key}" is not a declared property (additionalProperties: false)`)
+        }
+      }
+      return violations
+    }
+    case 'array': {
+      if (!Array.isArray(value)) return [`"${path}" must be an array`]
+      if (!node.items) return []
+      const items = node.items
+      return value.flatMap((entry, index) => checkValue(items, entry, `${path}[${index}]`))
+    }
+    case 'string': {
+      if (typeof value !== 'string') return [`"${path}" must be a string`]
+      break
+    }
+    case 'number': {
+      if (typeof value !== 'number' || !Number.isFinite(value)) return [`"${path}" must be a finite number`]
+      break
+    }
+    case 'integer': {
+      if (typeof value !== 'number' || !Number.isInteger(value)) return [`"${path}" must be an integer`]
+      break
+    }
+    case 'boolean': {
+      if (typeof value !== 'boolean') return [`"${path}" must be a boolean`]
+      break
+    }
+    case 'null': {
+      if (value !== null) return [`"${path}" must be null`]
+      break
+    }
+    default:
+      return assertNever(node.type, 'validateStructuredValue')
+  }
+  // Scalar constraint checks, shared by every scalar branch above.
+  if (node.enum && !node.enum.includes(value)) {
+    return [`"${path}" must be one of ${JSON.stringify(node.enum)}`]
+  }
+  if ('const' in node && value !== node.const) {
+    return [`"${path}" must be ${JSON.stringify(node.const)}`]
+  }
+  return []
+}
+
+/**
+ * Validate a value against an (already {@link assertSupportedOutputSchema}-
+ * asserted) schema. Returns human-readable, path-qualified violation messages
+ * — empty means valid. Total: never throws, however malformed the value.
+ * @param schema - the asserted schema to check against.
+ * @param value - the candidate value (e.g. parsed tool-call arguments).
+ * @returns every violation found, in walk order (empty = valid).
+ */
+export function validateStructuredValue(schema: StructuredOutputSchema, value: unknown): string[] {
+  return checkValue(schema, value, 'value')
+}

packages/core/tools/src/schema.ts

@@ -155,6 +155,9 @@ export interface JsonSchemaObject {
  * `properties`, `required` array).
  *
  * This is a plain function — no schemastery or other framework dependency.
+ * @param spec - the author-facing per-property schema to convert.
+ * @returns the wire-format JSON Schema; the top-level `required` array is
+ *   omitted entirely when no property is marked required.
  */
 export function schemaSpecToJsonSchema(spec: SchemaSpec): JsonSchemaObject {
   const properties: Record<string, unknown> = {}
@@ -269,6 +272,9 @@ function checkSpec(spec: SchemaSpec, value: unknown, path: string): string[] {
  * keys are allowed (no `additionalProperties: false`); `default` is not
  * applied; an `object`/`array` prop without `properties`/`items` only
  * type-checks; `enum` is membership (strings only).
+ * @param spec - the declared parameter schema to validate against.
+ * @param args - the model-generated arguments, however malformed.
+ * @returns the violation messages in declaration order; empty means valid.
  */
 export function validateArgs(spec: SchemaSpec, args: unknown): string[] {
   return checkSpec(spec, args, '')
@@ -289,6 +295,13 @@ export interface DefineToolOptions<S extends SchemaSpec> {
    * standard JSON Schema at runtime.
    */
   parameters: S
+  /**
+   * Optional cooperative tool-call timeout budget in milliseconds. When given it
+   * must be a positive finite number; it is attached to the produced
+   * {@link ToolDefinition} for `@deepseek-ai/dsh-timeout-policy` to enforce and
+   * is never sent to the model.
+   */
+  timeoutMs?: number
   /**
    * Tool execution function. `args` is typed as {@link InferArgs<S>} — zero
    * casts needed. Returns either a bare {@link ContentBlock}`[]` (model-facing
@@ -340,6 +353,13 @@ export interface DefineToolOptions<S extends SchemaSpec> {
  * Raw JSON-Schema tool definitions (from MCP servers) are still accepted
  * by `ToolRegistry.register()` directly — `defineTool` is sugar for
  * first-party plugin authors.
+ * @param options - the tool's name, description, typed parameter schema,
+ *   execute body, and optional presenters.
+ * @returns a registry-ready {@link ToolDefinition}: its `execute` validates the
+ *   raw args first (throwing {@link ToolArgsError} on mismatch, which the
+ *   registry turns into an isError result), and its presenters validate softly
+ *   (returning undefined on mismatch, since replay may feed them older-schema
+ *   args).
  */
 export function defineTool<S extends SchemaSpec>(options: DefineToolOptions<S>): ToolDefinition {
   // Object-literal execute methods don't use `this`; the reference is safe.
@@ -349,10 +369,14 @@ export function defineTool<S extends SchemaSpec>(options: DefineToolOptions<S>):
   const userPresentCall = options.presentCall
   // eslint-disable-next-line @typescript-eslint/unbound-method
   const userPresentResult = options.presentResult
+  if (options.timeoutMs !== undefined && (!Number.isFinite(options.timeoutMs) || options.timeoutMs <= 0)) {
+    throw new Error(`defineTool(${options.name}): timeoutMs must be a positive finite number`)
+  }
   const tool: ToolDefinition = {
     name: options.name,
     description: options.description,
     parameters: schemaSpecToJsonSchema(options.parameters) as unknown as Record<string, unknown>,
+    ...(options.timeoutMs !== undefined ? { timeoutMs: options.timeoutMs } : {}),
     async execute(args: unknown, exec: ToolExecution): Promise<ToolExecuteReturn> {
       // Validate the model-generated args before the typed body runs. On
       // mismatch we throw ToolArgsError; the registry turns it into an

packages/core/tools/tests/gen-tool-catalog.spec.ts

@@ -35,7 +35,7 @@ describe('gen-tool-catalog collectToolCatalog', () => {
   it('boots every shipped tool package and harvests its model-facing schemas', async () => {
     const catalog = await collectToolCatalog()
     const names = catalog.flatMap(entry => entry.schemas.map(s => s.name)).sort()
-    expect(names).toEqual(['bash', 'bash_kill', 'bash_output', 'edit', 'read', 'subagent', 'todo_write', 'web_fetch', 'web_search', 'write'])
+    expect(names).toEqual(['ask_user_question', 'bash', 'bash_kill', 'bash_output', 'cordis_inspect', 'cordis_mount', 'cordis_unmount', 'edit', 'read', 'subagent', 'todo_write', 'web_fetch', 'web_search', 'write'])
     // Every tool carries a JSON-Schema `parameters` object (what the model sees).
     for (const entry of catalog) {
       for (const schema of entry.schemas) {

packages/core/tools/tests/json-schema.spec.ts

@@ -0,0 +1,304 @@
+import { describe, expect, it } from 'vitest'
+import {
+  assertSupportedOutputSchema,
+  OutputSchemaError,
+  validateStructuredValue,
+  type StructuredOutputSchema,
+} from '../src/json-schema.ts'
+
+/** Assert-and-narrow helper: the asserted schema, typed. */
+function asserted(schema: unknown): StructuredOutputSchema {
+  assertSupportedOutputSchema(schema)
+  return schema
+}
+
+/** The violations OutputSchemaError carries for a bad schema (throws if it passes). */
+function violationsOf(schema: unknown): string[] {
+  try {
+    assertSupportedOutputSchema(schema)
+  } catch (error: unknown) {
+    if (error instanceof OutputSchemaError) return error.violations
+    throw error
+  }
+  throw new Error('expected the schema to be rejected')
+}
+
+describe('assertSupportedOutputSchema', () => {
+  it('accepts a representative subset schema (all supported keywords)', () => {
+    const schema = asserted({
+      type: 'object',
+      description: 'a finding',
+      title: 'Finding',
+      properties: {
+        file: { type: 'string', description: 'path' },
+        line: { type: 'integer' },
+        severity: { type: 'string', enum: ['low', 'high'] },
+        kind: { type: 'string', const: 'bug' },
+        score: { type: 'number' },
+        confirmed: { type: 'boolean' },
+        parent: { type: 'null' },
+        tags: { type: 'array', items: { type: 'string' } },
+        nested: {
+          type: 'object',
+          properties: { x: { type: 'number', default: 3, examples: [1, 2] } },
+          additionalProperties: false,
+        },
+        anything: { type: 'array' },
+      },
+      required: ['file', 'line'],
+      additionalProperties: true,
+    })
+    expect(schema.type).toBe('object')
+  })
+
+  it('rejects a non-object root (scalar/array-rooted schemas)', () => {
+    expect(violationsOf({ type: 'string' })).toEqual(['schema.type must be "object" (structured output is object-rooted)'])
+    expect(violationsOf({ type: 'array', items: { type: 'string' } }))
+      .toContain('schema.type must be "object" (structured output is object-rooted)')
+  })
+
+  it('rejects non-object schema nodes and missing/unknown type', () => {
+    expect(violationsOf('nope')).toEqual(['schema must be a schema object'])
+    expect(violationsOf(null)).toEqual(['schema must be a schema object'])
+    expect(violationsOf([])).toEqual(['schema must be a schema object'])
+    expect(violationsOf({})).toEqual(['schema.type must be one of object/array/string/number/integer/boolean/null'])
+    expect(violationsOf({ type: 'tuple' })[0]).toMatch(/type must be one of/)
+    expect(violationsOf({ type: 'object', properties: { a: 'str' } })).toEqual(['schema.properties.a must be a schema object'])
+  })
+
+  it('rejects type ARRAYS with a dedicated message', () => {
+    expect(violationsOf({ type: ['string', 'null'] }))
+      .toEqual(['schema.type must be a single type string (type arrays are not supported)'])
+  })
+
+  it('rejects unsupported constraint keywords loudly (never accepted-then-ignored)', () => {
+    for (const keyword of ['oneOf', 'anyOf', 'allOf', 'not', 'pattern', 'minimum', 'maxLength', '$ref']) {
+      const bad = violationsOf({ type: 'object', [keyword]: [] })
+      expect(bad.some(v => v.includes(`schema.${keyword} is not a supported keyword`))).toBe(true)
+    }
+  })
+
+  it('reports EVERY violation, not just the first', () => {
+    const bad = violationsOf({
+      type: 'object',
+      pattern: 'x',
+      properties: { a: { type: 'weird' }, b: { type: 'string', minimum: 1 } },
+    })
+    expect(bad.length).toBe(3)
+  })
+
+  it('rejects keywords on the wrong type (items on object, properties on string, enum on object)', () => {
+    expect(violationsOf({ type: 'object', items: { type: 'string' } }))
+      .toEqual(['schema.items is not supported on type "object"'])
+    expect(violationsOf({ type: 'object', properties: { a: { type: 'string', properties: {} } } }))
+      .toEqual(['schema.properties.a.properties is not supported on type "string"'])
+    expect(violationsOf({ type: 'object', enum: [1] }))
+      .toEqual(['schema.enum is not supported on type "object"'])
+    expect(violationsOf({ type: 'object', properties: { a: { type: 'array', const: 1 } } }))
+      .toEqual(['schema.properties.a.const is not supported on type "array"'])
+  })
+
+  it('validates required: must be string[] naming declared properties', () => {
+    expect(violationsOf({ type: 'object', required: 'file' }))
+      .toEqual(['schema.required must be an array of strings'])
+    expect(violationsOf({ type: 'object', required: [1] }))
+      .toEqual(['schema.required must be an array of strings'])
+    expect(violationsOf({ type: 'object', properties: { a: { type: 'string' } }, required: ['b'] }))
+      .toEqual(['schema.required names "b" which is not in properties'])
+    expect(violationsOf({ type: 'object', required: ['a'] }))
+      .toEqual(['schema.required names "a" which is not in properties'])
+  })
+
+  it('validates additionalProperties must be boolean and enum/const must be scalars', () => {
+    expect(violationsOf({ type: 'object', additionalProperties: {} }))
+      .toEqual(['schema.additionalProperties must be a boolean'])
+    expect(violationsOf({ type: 'object', properties: { a: { type: 'string', enum: [] } } }))
+      .toEqual(['schema.properties.a.enum must be a non-empty array of scalars'])
+    expect(violationsOf({ type: 'object', properties: { a: { type: 'string', enum: [{}] } } }))
+      .toEqual(['schema.properties.a.enum must be a non-empty array of scalars'])
+    expect(violationsOf({ type: 'object', properties: { a: { type: 'string', enum: 'x' } } }))
+      .toEqual(['schema.properties.a.enum must be a non-empty array of scalars'])
+    expect(violationsOf({ type: 'object', properties: { a: { type: 'number', enum: [Number.NaN] } } }))
+      .toEqual(['schema.properties.a.enum must be a non-empty array of scalars'])
+    expect(violationsOf({ type: 'object', properties: { a: { type: 'string', const: {} } } }))
+      .toEqual(['schema.properties.a.const must be a scalar'])
+  })
+
+  it('rejects non-string description/title and non-JSON annotation payloads', () => {
+    expect(violationsOf({ type: 'object', description: 7 }))
+      .toEqual(['schema.description must be a string'])
+    expect(violationsOf({ type: 'object', title: 7 }))
+      .toEqual(['schema.title must be a string'])
+    expect(violationsOf({ type: 'object', default: () => 1 }))
+      .toEqual(['schema.default annotation must be JSON data'])
+    expect(violationsOf({ type: 'object', examples: [undefined] }))
+      .toEqual(['schema.examples annotation must be JSON data'])
+    expect(violationsOf({ type: 'object', examples: [Number.POSITIVE_INFINITY] }))
+      .toEqual(['schema.examples annotation must be JSON data'])
+    // A cyclic annotation payload is caught by the JSON-data walk.
+    const cyclicAnnotation: Record<string, unknown> = {}
+    cyclicAnnotation.self = cyclicAnnotation
+    expect(violationsOf({ type: 'object', default: cyclicAnnotation }))
+      .toEqual(['schema.default annotation must be JSON data'])
+    // Object/array annotations that ARE JSON data pass.
+    asserted({ type: 'object', default: { a: [1, 'x', null, true] } })
+  })
+
+  it('rejects a circular schema instead of recursing forever', () => {
+    const node: Record<string, unknown> = { type: 'object' }
+    node.properties = { self: node }
+    expect(violationsOf(node)).toEqual(['schema.properties.self is circular'])
+  })
+
+  it('accepts the same subschema object reused in two SIBLING positions (a DAG, not a cycle)', () => {
+    const leaf = { type: 'string' }
+    asserted({ type: 'object', properties: { a: leaf, b: leaf } })
+  })
+
+  it('required cannot be satisfied by INHERITED names — `toString` is not a declared property', () => {
+    // `'toString' in {}` is true via Object.prototype; the declared-property
+    // contract must be an own-property check.
+    expect(violationsOf({ type: 'object', properties: {}, required: ['toString'] }))
+      .toEqual(['schema.required names "toString" which is not in properties'])
+  })
+
+  it('rejects exotic host objects where the subset expects plain JSON structure', () => {
+    // A Map as `properties` has no own enumerable entries: structurally it
+    // would read as "no properties" and serialize to {} — lossy, not loud.
+    expect(violationsOf({ type: 'object', properties: new Map() }))
+      .toEqual(['schema.properties must be an object of schemas'])
+    // A Date node is not a schema object even though Object.values(date) is [].
+    expect(violationsOf({ type: 'object', properties: { at: new Date(0) } }))
+      .toEqual(['schema.properties.at must be a schema object'])
+  })
+
+  it('rejects exotic annotation payloads that would serialize lossily', () => {
+    expect(violationsOf({ type: 'object', default: new Date(0) }))
+      .toEqual(['schema.default annotation must be JSON data'])
+    expect(violationsOf({ type: 'object', examples: [new Map()] }))
+      .toEqual(['schema.examples annotation must be JSON data'])
+  })
+})
+
+describe('validateStructuredValue', () => {
+  const schema = asserted({
+    type: 'object',
+    properties: {
+      file: { type: 'string' },
+      line: { type: 'integer' },
+      score: { type: 'number' },
+      confirmed: { type: 'boolean' },
+      parent: { type: 'null' },
+      severity: { type: 'string', enum: ['low', 'high'] },
+      kind: { type: 'string', const: 'bug' },
+      tags: { type: 'array', items: { type: 'string' } },
+      free: { type: 'array' },
+      nested: { type: 'object', properties: { x: { type: 'number' } }, required: ['x'], additionalProperties: false },
+    },
+    required: ['file'],
+  })
+
+  it('accepts a fully valid value (empty violations)', () => {
+    expect(validateStructuredValue(schema, {
+      file: 'a.ts', line: 3, score: 0.5, confirmed: true, parent: null,
+      severity: 'high', kind: 'bug', tags: ['x'], free: [1, { any: true }], nested: { x: 1 },
+    })).toEqual([])
+  })
+
+  it('reports missing required and wrong root type', () => {
+    expect(validateStructuredValue(schema, {})).toEqual(['missing required property "value.file"'])
+    expect(validateStructuredValue(schema, 'nope')).toEqual(['"value" must be an object'])
+    expect(validateStructuredValue(schema, [])).toEqual(['"value" must be an object'])
+  })
+
+  it('type-checks every scalar branch with path-qualified messages', () => {
+    expect(validateStructuredValue(schema, { file: 1 })).toEqual(['"value.file" must be a string'])
+    expect(validateStructuredValue(schema, { file: 'a', line: 1.5 })).toEqual(['"value.line" must be an integer'])
+    expect(validateStructuredValue(schema, { file: 'a', line: 'x' })).toEqual(['"value.line" must be an integer'])
+    expect(validateStructuredValue(schema, { file: 'a', score: 'x' })).toEqual(['"value.score" must be a finite number'])
+    expect(validateStructuredValue(schema, { file: 'a', score: Number.NaN })).toEqual(['"value.score" must be a finite number'])
+    expect(validateStructuredValue(schema, { file: 'a', confirmed: 'yes' })).toEqual(['"value.confirmed" must be a boolean'])
+    expect(validateStructuredValue(schema, { file: 'a', parent: 0 })).toEqual(['"value.parent" must be null'])
+  })
+
+  it('enforces enum membership and const equality', () => {
+    expect(validateStructuredValue(schema, { file: 'a', severity: 'mid' }))
+      .toEqual(['"value.severity" must be one of ["low","high"]'])
+    expect(validateStructuredValue(schema, { file: 'a', kind: 'feature' }))
+      .toEqual(['"value.kind" must be "bug"'])
+  })
+
+  it('checks arrays per index; an items-less array accepts anything', () => {
+    expect(validateStructuredValue(schema, { file: 'a', tags: 'x' })).toEqual(['"value.tags" must be an array'])
+    expect(validateStructuredValue(schema, { file: 'a', tags: ['ok', 2] })).toEqual(['"value.tags[1]" must be a string'])
+    expect(validateStructuredValue(schema, { file: 'a', free: [{ deep: [1] }, null] })).toEqual([])
+  })
+
+  it('recurses into nested objects: required + additionalProperties: false', () => {
+    expect(validateStructuredValue(schema, { file: 'a', nested: {} }))
+      .toEqual(['missing required property "value.nested.x"'])
+    expect(validateStructuredValue(schema, { file: 'a', nested: { x: 1, y: 2 } }))
+      .toEqual(['"value.nested.y" is not a declared property (additionalProperties: false)'])
+    expect(validateStructuredValue(schema, { file: 'a', nested: 3 }))
+      .toEqual(['"value.nested" must be an object'])
+  })
+
+  it('a required key present-but-undefined counts as missing', () => {
+    expect(validateStructuredValue(schema, { file: undefined })).toEqual(['missing required property "value.file"'])
+  })
+
+  it('inherited properties satisfy nothing: required, additionalProperties, and recursion are own-property only', () => {
+    // required: ['toString'] must NOT be satisfied by Object.prototype.toString.
+    expect(validateStructuredValue(
+      asserted({ type: 'object', properties: { toString: { type: 'string' } }, required: ['toString'] }),
+      {},
+    )).toEqual(['missing required property "value.toString"'])
+    // additionalProperties: false must flag an OWN `toString` key even though
+    // `'toString' in properties` is true via the prototype.
+    expect(validateStructuredValue(
+      asserted({ type: 'object', additionalProperties: false }),
+      { toString: 1 },
+    )).toEqual(['"value.toString" is not a declared property (additionalProperties: false)'])
+    // A declared property the value does NOT carry must not be validated
+    // against the value's INHERITED member (constructor is a function on
+    // every plain object's prototype, not a carried property).
+    expect(validateStructuredValue(
+      asserted({ type: 'object', properties: { constructor: { type: 'string' } } }),
+      {},
+    )).toEqual([])
+  })
+
+  it('a non-plain object value is not an object in the JSON sense', () => {
+    expect(validateStructuredValue(asserted({ type: 'object' }), new Date(0)))
+      .toEqual(['"value" must be an object'])
+  })
+
+  it('collects multiple violations across branches in one pass', () => {
+    expect(validateStructuredValue(schema, { line: 'x', severity: 'mid' })).toEqual([
+      'missing required property "value.file"',
+      '"value.line" must be an integer',
+      '"value.severity" must be one of ["low","high"]',
+    ])
+  })
+
+  it('null-typed const/enum work through the scalar path', () => {
+    const nullish = asserted({ type: 'object', properties: { a: { type: 'null', const: null } } })
+    expect(validateStructuredValue(nullish, { a: null })).toEqual([])
+  })
+
+  it('rejects a non-object properties value in the schema walk', () => {
+    expect(violationsOf({ type: 'object', properties: [] }))
+      .toEqual(['schema.properties must be an object of schemas'])
+  })
+
+  it('an object schema without properties/required only type-checks its value', () => {
+    const bare = asserted({ type: 'object' })
+    expect(validateStructuredValue(bare, { any: ['thing'] })).toEqual([])
+    expect(validateStructuredValue(bare, 7)).toEqual(['"value" must be an object'])
+  })
+
+  it('validateStructuredValue throws on a type the assert would never let through (assertNever backstop)', () => {
+    const forged = { type: 'tuple' } as unknown as StructuredOutputSchema
+    expect(() => validateStructuredValue(forged, 1)).toThrow(/tuple/)
+  })
+})

packages/core/tools/tests/tools.spec.ts

@@ -5,6 +5,7 @@ import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
 import ToolRegistry, {
   defineTool, schemaSpecToJsonSchema, validateArgs, ToolArgsError, ToolNotFoundError,
   type InferArgs, type SchemaSpec, type PreToolDecision, type PostToolDecision,
+  type ToolExecution, type ToolExecutionResult,
 } from '@deepseek-ai/dsh-tools'
 
 async function setup() {
@@ -62,6 +63,17 @@ describe('ToolRegistry', () => {
     expect(schema.execute).toBeUndefined()
   })
 
+  it('schemas() excludes timeoutMs — the budget must never reach the model', async () => {
+    const ctx = await setup()
+    ctx.tools.register(defineTool({
+      name: 'budgeted', description: 'has a budget', parameters: {}, timeoutMs: 5_000,
+      async execute() { return [{ type: 'text' as const, text: 'ok' }] },
+    }))
+    const schema = ctx.tools.schemas().find(s => s.name === 'budgeted')
+    expect(schema).toBeDefined()
+    expect('timeoutMs' in (schema as object)).toBe(false)
+  })
+
   it('executes a tool and returns its content', async () => {
     const ctx = await setup()
     ctx.tools.register(echoTool)
@@ -272,6 +284,151 @@ describe('ToolRegistry', () => {
     expect(order).toEqual(['pre:before', 'pre:after', 'post:before', 'post:after'])
   })
 
+  it('runs tools/execute after an allowed pre-execute, around dispatch, and before post-execute', async () => {
+    const ctx = await setup()
+    const order: string[] = []
+    ctx.tools.register(defineTool({
+      name: 'traced',
+      description: 'echo',
+      parameters: { text: { type: 'string' } },
+      async execute(args) {
+        order.push('dispatch')
+        return [{ type: 'text' as const, text: args.text ?? '' }]
+      },
+    }))
+
+    ctx.on('tools/pre-execute', async (_exec, next) => { order.push('pre'); return next() })
+    ctx.on('tools/execute', async (_exec: ToolExecution, next: () => Promise<ToolExecutionResult>): Promise<ToolExecutionResult> => {
+      order.push('execute:before')
+      const result = await next()
+      order.push('execute:after')
+      return result
+    })
+    ctx.on('tools/post-execute', async (_exec, _result, next) => { order.push('post'); return next() })
+
+    const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'traced', arguments: { text: 'hi' } })
+    expect(result).toEqual({ callId: CallId('c1'), content: [{ type: 'text', text: 'hi' }], isError: false })
+    // The around seam wraps dispatch; pre gates before it, post runs over its result.
+    expect(order).toEqual(['pre', 'execute:before', 'dispatch', 'execute:after', 'post'])
+  })
+
+  it('a pre-execute deny short-circuits before tools/execute (the seam never runs)', async () => {
+    const ctx = await setup()
+    ctx.tools.register(echoTool)
+
+    let entered = false
+    ctx.on('tools/pre-execute', async (_exec, _next): Promise<PreToolDecision> => ({ kind: 'deny', reason: 'nope' }))
+    ctx.on('tools/execute', async (_exec: ToolExecution, next: () => Promise<ToolExecutionResult>): Promise<ToolExecutionResult> => {
+      entered = true
+      return next()
+    })
+
+    const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'echo', arguments: { text: 'hi' } })
+    expect(result.isError).toBe(true)
+    expect(result.content[0]).toMatchObject({ text: 'Error: nope' })
+    expect(entered).toBe(false) // a denied call never enters the around-dispatch seam
+  })
+
+  it('a thrown tool is normalized to an isError result BEFORE a tools/execute listener sees next()', async () => {
+    const ctx = await setup()
+    ctx.tools.register({
+      ...echoTool,
+      name: 'boom',
+      async execute() { throw new HarnessError('kaboom', 'BOOM') },
+    })
+
+    let seen: { isError: boolean; error?: unknown } | undefined
+    ctx.on('tools/execute', async (_exec: ToolExecution, next: () => Promise<ToolExecutionResult>): Promise<ToolExecutionResult> => {
+      const result = await next()
+      // The base next() IS dispatch-with-normalization: the wrapper sees the
+      // normalized isError result, never a raw throw from the tool body.
+      seen = { isError: result.isError, error: result.error }
+      return result
+    })
+
+    const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'boom', arguments: {} })
+    expect(seen).toEqual({ isError: true, error: { name: 'HarnessError', code: 'BOOM' } })
+    expect(result.isError).toBe(true)
+    expect(result.content[0]).toMatchObject({ text: 'Error: kaboom' })
+  })
+
+  it('a thrown tool normalized inside tools/execute still reaches post-execute', async () => {
+    const ctx = await setup()
+    ctx.tools.register({
+      ...echoTool,
+      name: 'boom',
+      async execute() { throw new Error('exploded') },
+    })
+
+    let postSaw: boolean | undefined
+    ctx.on('tools/execute', async (_exec: ToolExecution, next: () => Promise<ToolExecutionResult>): Promise<ToolExecutionResult> => next())
+    ctx.on('tools/post-execute', async (_exec, result, next) => {
+      postSaw = result.isError
+      return next()
+    })
+
+    const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'boom', arguments: {} })
+    expect(postSaw).toBe(true) // the normalized isError still flows through post-execute
+    expect(result.isError).toBe(true)
+    expect(result.content[0]).toMatchObject({ text: 'Error: exploded' })
+  })
+
+  it('a tools/execute listener can replace exec.signal for the dispatched tool (deadline pattern)', async () => {
+    const ctx = await setup()
+    let seenSignal: AbortSignal | undefined
+    ctx.tools.register({
+      ...echoTool,
+      name: 'signal-probe',
+      async execute(_args, exec) {
+        seenSignal = exec.signal
+        return [{ type: 'text' as const, text: 'ok' }]
+      },
+    })
+
+    const upstream = new AbortController().signal
+    const replacement = new AbortController().signal
+    ctx.on('tools/execute', async (exec: ToolExecution, next: () => Promise<ToolExecutionResult>): Promise<ToolExecutionResult> => {
+      expect(exec.signal).toBe(upstream)
+      // Cordis next() ignores passed arguments, so a wrapper mutates exec in
+      // place (the documented "mutate the shared object, then delegate" idiom).
+      exec.signal = replacement
+      return next()
+    })
+
+    await ctx.tools.execute({ callId: CallId('c1'), name: 'signal-probe', arguments: {}, signal: upstream })
+    expect(seenSignal).toBe(replacement) // dispatch saw the wrapper's replacement, not the upstream
+  })
+
+  it('a tools/execute listener can short-circuit dispatch by returning a result without next()', async () => {
+    const ctx = await setup()
+    let dispatched = false
+    ctx.tools.register({
+      ...echoTool,
+      name: 'never-runs',
+      async execute() { dispatched = true; return [] },
+    })
+
+    ctx.on('tools/execute', async (exec: ToolExecution, _next: () => Promise<ToolExecutionResult>): Promise<ToolExecutionResult> =>
+      ({ callId: exec.callId, content: [{ type: 'text', text: 'short-circuited' }], isError: false }))
+
+    const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'never-runs', arguments: {} })
+    expect(dispatched).toBe(false) // returning without next() skips core dispatch
+    expect(result.content[0]).toMatchObject({ text: 'short-circuited' })
+  })
+
+  it('returns an isError result when a tools/execute listener throws', async () => {
+    const ctx = await setup()
+    ctx.tools.register(echoTool)
+    ctx.on('tools/execute', async () => { throw new Error('wrapper broke') })
+
+    const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'echo', arguments: { text: 'hi' } })
+    expect(result).toEqual({
+      callId: CallId('c1'),
+      content: [{ type: 'text', text: 'Error: wrapper broke' }],
+      isError: true,
+    })
+  })
+
   it('returns an isError result when a tools/pre-execute listener throws', async () => {
     const ctx = await setup()
     ctx.tools.register(echoTool)
@@ -989,6 +1146,38 @@ describe('defineTool validation (the runtime-validation RFC, part 1)', () => {
     const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'raw', arguments: {} })
     expect(result.isError).toBe(false)
   })
+
+  it('attaches a positive-finite timeoutMs to the definition', () => {
+    const tool = defineTool({
+      name: 'x', description: 'd', parameters: {}, timeoutMs: 30_000,
+      async execute() { return [{ type: 'text' as const, text: 'ok' }] },
+    })
+    expect(tool.timeoutMs).toBe(30_000)
+  })
+
+  it('omits timeoutMs when not declared', () => {
+    const tool = defineTool({
+      name: 'x', description: 'd', parameters: {},
+      async execute() { return [{ type: 'text' as const, text: 'ok' }] },
+    })
+    expect(tool.timeoutMs).toBeUndefined()
+  })
+
+  it('throws when timeoutMs is zero or negative', () => {
+    const make = (ms: number) => defineTool({
+      name: 'x', description: 'd', parameters: {}, timeoutMs: ms,
+      async execute() { return [{ type: 'text' as const, text: 'ok' }] },
+    })
+    expect(() => make(0)).toThrow('timeoutMs must be a positive finite number')
+    expect(() => make(-5)).toThrow('positive finite number')
+  })
+
+  it('throws when timeoutMs is non-finite', () => {
+    expect(() => defineTool({
+      name: 'x', description: 'd', parameters: {}, timeoutMs: Infinity,
+      async execute() { return [{ type: 'text' as const, text: 'ok' }] },
+    })).toThrow('positive finite number')
+  })
 })
 
 describe('defineTool presentation (presentCall / presentResult)', () => {

packages/fs/README.md

@@ -10,3 +10,7 @@ The filesystem stack: a provider seam (text IO + atomic mutation with an optiona
 | `tool-fs/` | Model-facing `read`/`write`/`edit` tools AND the executor (reads via `ctx.fs`, owns read windowing, dispatches `fs/*`) | (registers on `ctx.tools`) |
 
 The interface lives at `fs/fs/`. A sandboxed, remote, or project-scoped filesystem backend can replace `fs-local` without touching the seam, the policy gate, or the model-facing tool schemas. The policy (`fs-policy/`) is a plugin that participates only through the `fs/*` event gate, not a service the tool injects — so dropping it gracefully loses the policy and leaves the unconstrained bare provider rather than breaking the tool. A deployment that loads `tool-fs/` is expected to also load it.
+
+## No timeouts on file IO
+
+`read`/`write`/`edit` take **no** `timeoutMs`, and the provider seam arms no deadline — unlike bash and web, which consume [`@deepseek-ai/dsh-timeout`](../util/timeout/README.md). A local syscall is best-effort-abortable at most: a timeout could not force an in-progress `fsync`/`rename` to stop, so a deadline here would be a knob that cannot deliver on its promise. Adding one would also be an implicit default in the exact place explicit-over-implicit forbids. Both reference agents (Claude Code, Codex) leave file IO untimed for the same reason; cancellation still propagates through the tool-execution signal for best-effort abort at syscall boundaries.

packages/fs/fs-local/src/fsio.ts

@@ -137,6 +137,9 @@ export interface LocalDirEntry {
  * and intermediate directories are created by the write. Two input paths
  * reaching the same file via symlinks share one key. Falls back to the absolute
  * path only when no ancestor (not even the filesystem root) can be resolved.
+ * @param cwd - base directory a relative `path` resolves against.
+ * @param path - absolute or relative path; empty/whitespace-only throws `FS_NOT_FOUND`.
+ * @returns the absolute display path plus the realpath-derived stable target key.
  */
 export async function resolveLocalTarget(cwd: string, path: string): Promise<LocalTarget> {
   if (path.trim().length === 0) throw new FsError('file_path must be a non-empty string', 'FS_NOT_FOUND')
@@ -197,7 +200,11 @@ async function probeStats(absolutePath: string, readStats: (path: string) => Pro
   }
 }
 
-/** Probe a path for its version, mode, type, and size. Null if absent. */
+/**
+ * Probe a path for its version, mode, type, and size. Null if absent.
+ * @param absolutePath - the path to stat (typically a target key; symlinks are followed).
+ * @returns the metadata, or null when the path — or a parent segment — does not exist.
+ */
 export async function probe(absolutePath: string): Promise<PathInfo | null> {
   const info = await probeStats(absolutePath, stat)
   if (!info) return null
@@ -231,6 +238,9 @@ async function resolveListedChildTarget(parent: LocalTarget, name: string): Prom
  * List direct children of a directory in stable name order. Each child includes
  * a resolved target plus stat metadata when still available; file contents are
  * never read.
+ * @param target - the resolved directory to list; a missing or non-directory target throws.
+ * @param signal - aborts the listing, checked between children (`FS_ABORTED`).
+ * @returns one entry per direct child, sorted by name.
  */
 export async function listDirectory(target: LocalTarget, signal?: AbortSignal): Promise<LocalDirEntry[]> {
   throwIfAborted(signal, 'list')
@@ -321,6 +331,9 @@ async function statRegularFile(target: LocalTarget, verb: 'read', signal?: Abort
 /**
  * Read a whole regular UTF-8 text file into a single decoded string. Rejects
  * non-regular files, invalid UTF-8, and NUL-byte binary samples.
+ * @param target - the resolved file to read.
+ * @param signal - aborts the read (`FS_ABORTED`).
+ * @returns the full decoded text, byte-for-byte (no normalization).
  */
 export async function readWholeText(target: LocalTarget, signal?: AbortSignal): Promise<string> {
   await statRegularFile(target, 'read', signal)
@@ -336,6 +349,9 @@ export async function readWholeText(target: LocalTarget, signal?: AbortSignal):
  * Stream a whole regular UTF-8 text file as decoded text chunks. Same text
  * semantics as {@link readWholeText} (regular-file check, binary/NUL rejection,
  * cross-chunk UTF-8 decoding), but never holds the whole file in memory.
+ * @param target - the resolved file to stream.
+ * @param signal - aborts the stream, including between chunks (`FS_ABORTED`).
+ * @returns decoded text chunks in file order; chunk boundaries carry no meaning.
  */
 export async function* streamWholeText(target: LocalTarget, signal?: AbortSignal): AsyncIterable<string> {
   await statRegularFile(target, 'read', signal)
@@ -383,6 +399,11 @@ async function removeStagingDirOrThrow(stagingDir: string, originalError: unknow
  * (`0o700`) staging directory, fsync, optionally chmod to the final mode while
  * still private, then rename over the target. `mode` (when given) preserves an
  * existing file's permissions across the replace.
+ * @param absolutePath - the final destination (typically a target key); missing parent dirs are created.
+ * @param content - the full UTF-8 text to write.
+ * @param mode - final file mode applied before the rename (an existing file's, to preserve permissions); undefined leaves `0o600`.
+ * @param signal - aborts the write (`FS_ABORTED`); checked before the rename, so the target is never left torn.
+ * @param internals - test seam for pinning temp names and observing the staged file.
  */
 export async function writeFileAtomic(
   absolutePath: string,
@@ -440,6 +461,12 @@ export async function writeFileAtomic(
 /** Line ending style detected before LF normalization. */
 export type LineEndings = 'LF' | 'CRLF'
 
+/**
+ * Collapse CRLF to LF — the canonical in-memory form every edit/diff basis
+ * uses. Lone `\r` bytes (not followed by `\n`) are left untouched.
+ * @param content - decoded text in whatever line-ending style the file had.
+ * @returns the text with every `\r\n` pair replaced by `\n`.
+ */
 function normalizeLineEndings(content: string): string {
   return content.replaceAll('\r\n', '\n')
 }
@@ -451,6 +478,14 @@ function detectLineEndings(raw: string): LineEndings {
   return crlfCount > lfCount ? 'CRLF' : 'LF'
 }
 
+/**
+ * Convert LF-normalized content back to the line-ending style detected at read
+ * time, for write-back. `LF` returns the content unchanged; `CRLF` re-normalizes
+ * first so an already-CRLF sequence is never doubled to `\r\r\n`.
+ * @param content - the LF-normalized (edited) text.
+ * @param lineEndings - the original file's style, as detected by {@link readForEdit}.
+ * @returns the text in the original file's line-ending style.
+ */
 function restoreLineEndings(content: string, lineEndings: LineEndings): string {
   return lineEndings === 'LF' ? content : normalizeLineEndings(content).split('\n').join('\r\n')
 }
@@ -469,6 +504,10 @@ function countOccurrences(content: string, needle: string): number {
 /**
  * Read and decode a file for editing: rejects binaries, returns LF-normalized
  * content plus the original line-ending style for write-back.
+ * @param absolutePath - the file to read (typically a target key).
+ * @param displayPath - the caller-facing path used in error messages.
+ * @param signal - aborts the read (`FS_ABORTED`).
+ * @returns the LF-normalized content and the detected style to restore on write-back.
  */
 export async function readForEdit(
   absolutePath: string,
@@ -490,6 +529,9 @@ export async function readForEdit(
  * prior bytes, so an undiffable prior file simply yields no contextual-hunk basis
  * (the caller treats `null` the same as an absent file: the result renders a
  * whole-file diff rather than an applied hunk).
+ * @param absolutePath - the file to read (typically a target key); it must exist.
+ * @param signal - aborts the read (`FS_ABORTED`).
+ * @returns the LF-normalized text, or null for a binary or non-UTF-8 file.
  */
 export async function readTextForDiff(absolutePath: string, signal?: AbortSignal): Promise<string | null> {
   const buffer = await readFileAbortable(absolutePath, 'read', signal)
@@ -508,6 +550,12 @@ export async function readTextForDiff(absolutePath: string, signal?: AbortSignal
  * `FS_EDIT_NOT_FOUND` on empty `oldString` or zero matches and
  * `FS_AMBIGUOUS_EDIT` on multiple matches when `replaceAll` is false. Returns
  * the edited content (still LF-normalized) and the replacement count.
+ * @param content - the current file content, already LF-normalized.
+ * @param oldString - literal text to find; CRLF inside it is normalized to LF before matching.
+ * @param newString - literal replacement text, normalized the same way.
+ * @param replaceAll - replace every match instead of requiring exactly one.
+ * @param displayPath - the caller-facing path used in error messages.
+ * @returns the edited LF-normalized content plus how many occurrences were replaced.
  */
 export function applyLiteralEdit(
   content: string,

packages/fs/fs-local/src/index.ts

@@ -77,6 +77,7 @@ export class LocalFileSystem extends FileSystem {
     cwd: z.string().default(process.cwd()),
   })
 
+  /** Validated config (schemastery applied the defaults before construction). */
   readonly config: ResolvedConfig
   /** Test seam forwarded to fsio (force streaming path, pin temp names). */
   internals: FsIoInternals = {}

packages/fs/fs/src/types.ts

@@ -29,7 +29,12 @@ import type { Branded } from '@deepseek-ai/dsh-brand'
  */
 export type FsTargetKey = Branded<'FsTargetKey'>
 
-/** Brand a string as an {@link FsTargetKey}. */
+/**
+ * Brand a string as an {@link FsTargetKey}. For backend use only — a consumer
+ * never manufactures a key, it receives one from `resolve()`.
+ * @param key - the backend's raw key string (the local backend passes a realpath).
+ * @returns the same string, branded; no validation is performed.
+ */
 export function FsTargetKey(key: string): FsTargetKey {
   return key as FsTargetKey
 }
@@ -42,7 +47,12 @@ export function FsTargetKey(key: string): FsTargetKey {
  */
 export type FsVersion = Branded<'FsVersion'>
 
-/** Brand a string as an {@link FsVersion}. */
+/**
+ * Brand a string as an {@link FsVersion}. For backend use only — a consumer
+ * never manufactures a version, it receives one from `stat`/write/edit outcomes.
+ * @param v - the backend's raw version string (the local backend derives it from mtime+size).
+ * @returns the same string, branded; no validation is performed.
+ */
 export function FsVersion(v: string): FsVersion {
   return v as FsVersion
 }

packages/fs/tool-fs/src/diff.ts

@@ -40,6 +40,10 @@ export type FsDiffMeta = { diffs: FileDiff[] }
  * (a pure insertion) reports `oldText: null` (nothing to diff against), mirroring
  * the call-time card's new-file convention. The unified-diff "\ No newline at end
  * of file" markers are dropped — they annotate the patch, not file content.
+ * @param path - the path stamped on every produced diff (the model-facing `file_path`; the bridge relativizes it).
+ * @param before - the file text before the change (the backend's LF-normalized diff basis).
+ * @param after - the file text after the change, on the same basis.
+ * @returns one diff per applied hunk, in file order; empty when the texts are identical.
  */
 export function computeHunkDiffs(path: string, before: string, after: string): FileDiff[] {
   const patch = structuredPatch('', '', before, after, undefined, undefined, { context: DIFF_CONTEXT })
@@ -83,6 +87,8 @@ function isFileDiff(value: unknown): value is FileDiff {
  * it validates defensively rather than trusting the payload — a bad `meta` yields
  * `undefined`, and the caller decides the fallback (edit → the generic result
  * rendering; write → an args-derived whole-file diff), never a thrown presenter.
+ * @param meta - the opaque `tool/result` meta payload (live or replayed from the session log).
+ * @returns the validated non-empty hunk list, or undefined for an absent/empty/malformed payload.
  */
 export function diffsFromMeta(meta: unknown): FileDiff[] | undefined {
   if (typeof meta !== 'object' || meta === null || Array.isArray(meta)) return undefined

packages/fs/tool-fs/src/edit.ts

@@ -29,7 +29,13 @@ interface EditInput {
   replaceAll: boolean
 }
 
-/** Validate value constraints the schema DSL can't express. */
+/**
+ * Validate value constraints the schema DSL can't express: a non-blank
+ * `file_path`, a non-empty `old_string`, and `old_string !== new_string`
+ * (an equal pair would be a guaranteed no-op edit).
+ * @param args - the schema-validated raw tool arguments.
+ * @returns the camelCased input with `replace_all` defaulted to false.
+ */
 export function parseEditArgs(args: { file_path: string; old_string: string; new_string: string; replace_all?: boolean }): EditInput {
   if (args.file_path.trim().length === 0) throw new Error('file_path must be a non-empty string')
   if (args.old_string.length === 0) throw new Error('old_string must be a non-empty string')
@@ -42,14 +48,22 @@ export function parseEditArgs(args: { file_path: string; old_string: string; new
   }
 }
 
-/** Format an edit success (single-match or replace-all) as a Claude-style model-facing message. */
+/**
+ * Format an edit success (single-match or replace-all) as a Claude-style model-facing message.
+ * @param displayPath - the backend-resolved path shown to the model.
+ * @param replaceAll - selects the all-occurrences wording over the single-replacement one.
+ * @returns the confirmation sentence the model sees as the tool result.
+ */
 export function formatEditOutput(displayPath: string, replaceAll: boolean): string {
   return replaceAll
     ? `The file ${displayPath} has been updated. All occurrences were successfully replaced.`
     : `The file ${displayPath} has been updated successfully.`
 }
 
-/** Register the `edit` tool and its system-prompt guidance. */
+/**
+ * Register the `edit` tool and its system-prompt guidance.
+ * @param ctx - the plugin context; registrations are effects scoped to it, and execution uses its `fs` service.
+ */
 export function applyEditTool(ctx: Context): void {
   ctx.systemPrompt.section({
     name: 'tool:edit',