Merge branch 'codex/goal-commands' into codex/ralph-tool

# Conflicts:
#	examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md
#	examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json
#	examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md
#	examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json
#	examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md
#	examples/acp-agent/tests/snapshots/model-switching/tool-schemas.expected.json
#	examples/acp-agent/tests/snapshots/permission-switching/tool-schemas.expected.json
#	examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json
#	examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json
#	examples/acp-agent/tests/snapshots/workspace-edit/system-prompt.expected.md
#	examples/acp-agent/tests/snapshots/workspace-edit/tool-schemas.expected.json
#	scripts/gen-tool-catalog.ts

packages/bash/bash-sandbox/README.md

@@ -1,6 +1,6 @@
 # @deepseek-ai/dsh-bash-sandbox
 
-Sandbox-consuming implementation of the [`@deepseek-ai/dsh-bash`](../bash/) executor seam. Load it **instead of** `@deepseek-ai/dsh-bash-local`, together with a [`ctx.sandbox`](../../sandbox/sandbox/) provider (e.g. [`@deepseek-ai/dsh-sandbox-local`](../../sandbox/sandbox-local/)) — no alternate tool plugin is needed; `dsh-tool-bash` detects the executor's `sandboxMode` capability and adds the escalation fields.
+Sandbox-consuming implementation of the [`@deepseek-ai/dsh-bash`](../bash/) executor seam. Load it **instead of** `@deepseek-ai/dsh-bash-local`, together with a [`ctx.sandbox`](../../sandbox/sandbox/) provider (e.g. [`@deepseek-ai/dsh-sandbox-local`](../../sandbox/sandbox-local/)) and a [`ctx.sandboxPolicy`](../../sandbox/sandbox-policy/) (which owns the default mode + workspace root, shared with the sandboxed filesystem) — no alternate tool plugin is needed; `dsh-tool-bash` detects the executor's `sandboxMode` capability and adds the escalation fields.
 
 The package root exports the default and named `SandboxBashExecutor` plugin plus its `Config`; quoting and result-classification helpers stay internal.
 
@@ -16,7 +16,7 @@ Semantics:
 
 - **Denials are result facts.** A failed run whose stderr carries the selected backend's own denial dialect — the signatures the provider stamps on every wrap (EROFS text under bwrap, EACCES under Landlock, EPERM under Seatbelt) — is reported as `BashRunResult.sandbox.denied: true` (conservative classification, read from the collected stderr tail); every CONFINED run also carries the mode it executed under (`result.sandbox.mode`) and the provider's enforcement completeness (`result.sandbox.enforcement`: `full`, or `partial` on an older Landlock ABI).
 - **Runner failures are sandbox failures, never command failures.** Foreground execution throws `SANDBOX_UNAVAILABLE`; a settled background process stamps `process.sandbox.runnerFailed`, which the bash producer renders through generic `task_output`. Spawn failures also pass through settlement, so confined background handles retain their mode/enforcement facts and release per-process accounting.
-- **Config-time default, per-call policy.** The DEFAULT mode is fixed by this entry's config for the executor's lifetime; `resolve()` stamps it onto every spec, and an explicit request-level `sandboxMode` override — set by the tool layer only for a call whose wider mode a human granted through `ctx.approval` ([the sandbox Agent Note § Escalation](../../../.agents/notes/implemented/feature/2026-07-06-sandbox.md)) — makes THAT call run, classify, and report under its own mode while every neighbor keeps the default (background facts are stamped per task at settle). The capability fact `ctx.bash.sandboxMode` reports the configured default so the tool layer advertises escalation only when this executor is mounted. The model learns of the sandbox only through result facts — the static bash tool description explains the denial marker; there is no current-mode statement in the system prompt.
+- **Deployment default, per-call policy.** The DEFAULT mode + workspace root are owned by [`ctx.sandboxPolicy`](../../sandbox/sandbox-policy/) (one home both enforcing families read), not this executor's config; `resolve()` stamps the default onto every spec, and an explicit request-level `sandboxMode` override — set by the tool layer only for a call whose wider mode a human granted through `ctx.approval` ([the sandbox Agent Note § Escalation](../../../.agents/notes/implemented/feature/2026-07-06-sandbox.md)) — makes THAT call run, classify, and report under its own mode while every neighbor keeps the default (background facts are stamped per task at settle). The capability fact `ctx.bash.sandboxMode` reports the configured default so the tool layer advertises escalation only when this executor is mounted. The model learns of the sandbox only through result facts — the static bash tool description explains the denial marker; there is no current-mode statement in the system prompt.
 - **File effects only.** Network and process visibility are deliberately not restricted — the mode vocabulary does not pretend to cover what the backend does not enforce.
 - Process mechanics (spawn, process-group kills, output collection/spill, background handles, credential scrub) are inherited from [`dsh-bash-local`](../bash-local/); runner selection lives in [`dsh-sandbox-local`](../../sandbox/sandbox-local/).
 
@@ -25,11 +25,13 @@ Deny-only at the seam: a denial is a reported fact, and this executor never nego
 ```yaml
 - id: sandbox
   name: '@deepseek-ai/dsh-sandbox-local'
-- id: bash
-  name: '@deepseek-ai/dsh-bash-sandbox'
+- id: sandbox-policy
+  name: '@deepseek-ai/dsh-sandbox-policy'
   config:
     mode: read-only
     workspaceRoot: !!js process.cwd()
+- id: bash
+  name: '@deepseek-ai/dsh-bash-sandbox'
 ```
 
 The keyless consumer-integration proofs are `tests/bwrap.e2e.ts`, `tests/landlock.e2e.ts`, and `tests/seatbelt.e2e.ts` (the real provider + real runner driven through `ctx.bash`, world-verified, each self-skipping where its runner is absent); see [the acp-agent example's default composition](../../../examples/acp-agent/) for the runnable demo.

packages/bash/bash-sandbox/package.json

@@ -25,16 +25,15 @@
     "@deepseek-ai/dsh-bash": "^0.0.1",
     "@deepseek-ai/dsh-bash-local": "^0.0.1",
     "@deepseek-ai/dsh-sandbox": "^0.0.1",
+    "@deepseek-ai/dsh-sandbox-policy": "^0.0.1",
     "cordis": "^4.0.0-rc.7"
   },
-  "dependencies": {
-    "schemastery": "^3.18.0"
-  },
   "devDependencies": {
     "@deepseek-ai/dsh-bash": "workspace:^",
     "@deepseek-ai/dsh-bash-local": "workspace:^",
     "@deepseek-ai/dsh-sandbox": "workspace:^",
     "@deepseek-ai/dsh-sandbox-local": "workspace:^",
+    "@deepseek-ai/dsh-sandbox-policy": "workspace:^",
     "node-addon-landlock-run": "0.0.0-test.0",
     "cordis": "^4.0.0-rc.7"
   }

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

@@ -7,52 +7,39 @@
  * @module @deepseek-ai/dsh-bash-sandbox
  */
 
-import { resolve } from 'node:path'
 import { Context } from 'cordis'
-import z from 'schemastery'
 import type { BashExecRequest, BashExecSpec, BashProcess, BashRunResult } from '@deepseek-ai/dsh-bash'
 import { SandboxUnavailableError } from '@deepseek-ai/dsh-sandbox'
 import type { ConfinedSandboxMode, SandboxEnforcement, SandboxMode } from '@deepseek-ai/dsh-sandbox'
+import type {} from '@deepseek-ai/dsh-sandbox-policy'
 import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
 import type { Config as LocalConfig } from '@deepseek-ai/dsh-bash-local'
 import { classifyDenial, classifyRunnerFailure, matchesSignature, shellQuote } from './helpers.ts'
 
 /**
- * Plugin config: the local executor's knobs plus the sandbox policy. All
- * optional — `static Config` supplies the defaults (`mode: 'read-only'` is the
- * fail-safe default; an example that wants a workspace-writable agent opts in
- * explicitly). The runner choice is not configured here: which platform
- * backend confines the command is the `ctx.sandbox` provider's config.
+ * Plugin config: the local executor's knobs, verbatim. The sandbox policy —
+ * the default mode and the `workspace-write` boundary root — is NOT here: it
+ * lives on `ctx.sandboxPolicy` (`@deepseek-ai/dsh-sandbox-policy`), the one
+ * home both enforcing families read, so bash and fs can never confine to
+ * different roots. The runner choice is likewise the `ctx.sandbox` provider's
+ * config, not this executor's.
  */
-export interface Config extends LocalConfig {
-  /** File-sandbox mode commands run under (default: `read-only`). */
-  mode?: SandboxMode
-  /**
-   * Root directory `workspace-write` mode may write under (default: the
-   * executor's default working directory — `cwd`, else `process.cwd()`).
-   */
-  workspaceRoot?: string
-}
+export type Config = LocalConfig
 
 /**
  * Registers as `ctx.bash` in place of the local executor and requires a
- * `ctx.sandbox` provider; the tool layer is unchanged. The configured mode is
- * the fallback, while a session override or approved one-shot escalation may
- * select each call's mode. The prompt does not state the standing mode;
- * `result.sandbox` reports the mode and enforcement actually used.
+ * `ctx.sandbox` provider plus `ctx.sandboxPolicy`; the tool layer is
+ * unchanged. The policy default (mode + workspace root) is the fallback,
+ * while a session override or approved one-shot escalation may select each
+ * call's mode. The prompt does not state the standing mode; `result.sandbox`
+ * reports the mode and enforcement actually used.
  */
 export class SandboxBashExecutor extends LocalBashExecutor {
-  static inject = ['sandbox']
+  static inject = ['sandbox', 'sandboxPolicy']
 
-  // The sandbox-specific fields intersect the local executor's Config as an
-  // inline schema call: the config catalog walks `static Config` statically.
-  static override Config: z<Config> = z.intersect([
-    LocalBashExecutor.Config,
-    z.object({
-      mode: z.union(['read-only', 'workspace-write', 'danger-full-access'] as const).default('read-only'),
-      workspaceRoot: z.string(),
-    }),
-  ])
+  // No own Config: the sandbox default (mode + workspaceRoot) moved to
+  // ctx.sandboxPolicy, so this executor inherits LocalBashExecutor's Config
+  // verbatim (the config catalog walks the inherited static).
 
   private readonly mode: SandboxMode
   private readonly workspaceRoot: string
@@ -71,9 +58,11 @@ export class SandboxBashExecutor extends LocalBashExecutor {
 
   constructor(ctx: Context, config: Config) {
     super(ctx, config)
-    // Schemastery fills mode before construction; workspaceRoot and cwd retain runtime fallbacks.
-    this.mode = config.mode as SandboxMode
-    this.workspaceRoot = resolve(config.workspaceRoot ?? config.cwd ?? process.cwd())
+    // The sandbox default (mode + workspaceRoot) is the one shared policy home
+    // both enforcing families read; injecting sandboxPolicy guarantees it is
+    // constructed first. workspaceRoot arrives already resolved absolute.
+    this.mode = ctx.sandboxPolicy.defaultMode
+    this.workspaceRoot = ctx.sandboxPolicy.workspaceRoot
   }
 
   /** The configured default mode — the capability fact the tool layer reads. */

packages/bash/bash-sandbox/tests/bwrap.e2e.ts

@@ -6,6 +6,7 @@ import { join } from 'node:path'
 import { afterEach, describe, expect, it } from 'vitest'
 import { Context } from 'cordis'
 import { LocalSandboxProvider } from '@deepseek-ai/dsh-sandbox-local'
+import { SandboxPolicyService } from '@deepseek-ai/dsh-sandbox-policy'
 import { bwrapProfileArgs } from '@deepseek-ai/dsh-sandbox-local/src/profiles.ts'
 import { SandboxBashExecutor } from '@deepseek-ai/dsh-bash-sandbox'
 
@@ -40,7 +41,8 @@ async function tempDir(base: string): Promise<string> {
 async function sandboxedBash(workspace: string, mode: 'read-only' | 'workspace-write'): Promise<SandboxBashExecutor> {
   ctx = new Context()
   await ctx.plugin(LocalSandboxProvider, {})
-  await ctx.plugin(SandboxBashExecutor, { mode, cwd: workspace, workspaceRoot: workspace, timeoutMs: 30_000 })
+  await ctx.plugin(SandboxPolicyService, { mode, workspaceRoot: workspace })
+  await ctx.plugin(SandboxBashExecutor, { cwd: workspace, timeoutMs: 30_000 })
   return ctx.bash as SandboxBashExecutor
 }
 

packages/bash/bash-sandbox/tests/landlock.e2e.ts

@@ -7,6 +7,7 @@ import { afterEach, describe, expect, it } from 'vitest'
 import { Context } from 'cordis'
 import { launcherPath } from 'node-addon-landlock-run'
 import { LocalSandboxProvider } from '@deepseek-ai/dsh-sandbox-local'
+import { SandboxPolicyService } from '@deepseek-ai/dsh-sandbox-policy'
 import { SandboxBashExecutor } from '@deepseek-ai/dsh-bash-sandbox'
 
 /**
@@ -45,7 +46,8 @@ async function sandboxedBash(workspace: string, mode: 'read-only' | 'workspace-w
   ctx = new Context()
   await ctx.plugin(LocalSandboxProvider, {})
   ;(ctx.sandbox as LocalSandboxProvider).internals = { probeBwrap: () => false }
-  await ctx.plugin(SandboxBashExecutor, { mode, cwd: workspace, workspaceRoot: workspace, timeoutMs: 30_000 })
+  await ctx.plugin(SandboxPolicyService, { mode, workspaceRoot: workspace })
+  await ctx.plugin(SandboxBashExecutor, { cwd: workspace, timeoutMs: 30_000 })
   return ctx.bash as SandboxBashExecutor
 }
 

packages/bash/bash-sandbox/tests/sandbox.spec.ts

@@ -12,7 +12,8 @@ import { describe, expect, it, vi } from 'vitest'
 import { Context } from 'cordis'
 import type { BashRunResult, CollectedOutput } from '@deepseek-ai/dsh-bash'
 import { SANDBOX_UNAVAILABLE, SandboxProvider, SandboxUnavailableError } from '@deepseek-ai/dsh-sandbox'
-import type { ConfinedArgv, SandboxPolicy } from '@deepseek-ai/dsh-sandbox'
+import type { ConfinedArgv, SandboxMode, SandboxPolicy } from '@deepseek-ai/dsh-sandbox'
+import { SandboxPolicyService } from '@deepseek-ai/dsh-sandbox-policy'
 import { SandboxBashExecutor } from '@deepseek-ai/dsh-bash-sandbox'
 import { classifyDenial, classifyRunnerFailure, shellQuote } from '../src/helpers.ts'
 import type { Config } from '@deepseek-ai/dsh-bash-sandbox'
@@ -39,7 +40,11 @@ const passthrough = (argv: readonly string[]): ConfinedArgv =>
  * Boot a context with a recording fake `ctx.sandbox` (behavior injectable
  * per test) and the executor under test on top of it.
  */
-async function setup(config: Config = {}, behavior: (argv: readonly string[], policy: SandboxPolicy) => ConfinedArgv = passthrough) {
+async function setup(
+  config: { mode?: SandboxMode; workspaceRoot?: string } & Config = {},
+  behavior: (argv: readonly string[], policy: SandboxPolicy) => ConfinedArgv = passthrough,
+) {
+  const { mode, workspaceRoot, ...execConfig } = config
   const calls: ConfineCall[] = []
   class FakeSandboxProvider extends SandboxProvider {
     confine(argv: readonly string[], policy: SandboxPolicy): ConfinedArgv {
@@ -49,7 +54,11 @@ async function setup(config: Config = {}, behavior: (argv: readonly string[], po
   }
   const ctx = new Context()
   await ctx.plugin(FakeSandboxProvider)
-  await ctx.plugin(SandboxBashExecutor, { graceMs: 200, ...config })
+  await ctx.plugin(SandboxPolicyService, {
+    ...mode !== undefined ? { mode } : {},
+    ...workspaceRoot !== undefined ? { workspaceRoot } : {},
+  })
+  await ctx.plugin(SandboxBashExecutor, { graceMs: 200, ...execConfig })
   const bash = ctx.bash as SandboxBashExecutor
   bash.internals = { spillDir }
   return { ctx, bash, calls }
@@ -84,14 +93,14 @@ describe('the provider hand-off', () => {
     expect(result.sandbox).toEqual({ mode: 'read-only', denied: false, enforcement: 'full' })
   })
 
-  it('workspace-write rides the policy, workspaceRoot falling back to cwd when not configured', async () => {
-    const { bash, calls } = await setup({ mode: 'workspace-write', cwd: tmpdir() })
+  it('workspace-write rides the policy, workspaceRoot falling back to process.cwd() when not configured', async () => {
+    const { bash, calls } = await setup({ mode: 'workspace-write' })
     const result = await bash.run(bash.resolve({ command: 'true' }))
     expect(result.sandbox).toEqual({ mode: 'workspace-write', denied: false, enforcement: 'full' })
-    expect(calls[0]?.policy).toEqual({ mode: 'workspace-write', workspaceRoot: resolve(tmpdir()) })
+    expect(calls[0]?.policy).toEqual({ mode: 'workspace-write', workspaceRoot: resolve(process.cwd()) })
   })
 
-  it('an explicit workspaceRoot wins over cwd', async () => {
+  it('an explicit workspaceRoot on the policy wins', async () => {
     const { calls, bash } = await setup({ mode: 'workspace-write', workspaceRoot: '/ws', cwd: tmpdir() })
     await bash.run(bash.resolve({ command: 'true' }))
     expect(calls[0]?.policy.workspaceRoot).toBe(resolve('/ws'))

packages/bash/bash-sandbox/tests/seatbelt.e2e.ts

@@ -6,6 +6,7 @@ import { join } from 'node:path'
 import { afterEach, describe, expect, it } from 'vitest'
 import { Context } from 'cordis'
 import { LocalSandboxProvider } from '@deepseek-ai/dsh-sandbox-local'
+import { SandboxPolicyService } from '@deepseek-ai/dsh-sandbox-policy'
 import { seatbeltProfileArgs } from '@deepseek-ai/dsh-sandbox-local/src/profiles.ts'
 import { SandboxBashExecutor } from '@deepseek-ai/dsh-bash-sandbox'
 
@@ -39,7 +40,8 @@ async function sandboxedBash(workspace: string, mode: 'read-only' | 'workspace-w
   ctx = new Context()
   await ctx.plugin(LocalSandboxProvider, {})
   ;(ctx.sandbox as LocalSandboxProvider).internals = { probeBwrap: () => false, probeLandlock: () => 'unusable' }
-  await ctx.plugin(SandboxBashExecutor, { mode, cwd: workspace, workspaceRoot: workspace, timeoutMs: 30_000 })
+  await ctx.plugin(SandboxPolicyService, { mode, workspaceRoot: workspace })
+  await ctx.plugin(SandboxBashExecutor, { cwd: workspace, timeoutMs: 30_000 })
   return ctx.bash as SandboxBashExecutor
 }
 

packages/bash/bash-sandbox/tsconfig.json

@@ -14,9 +14,6 @@
     {
       "path": "../../../vendor/cordis"
     },
-    {
-      "path": "../../../vendor/schemastery"
-    },
     {
       "path": "../../util/brand"
     },
@@ -26,6 +23,9 @@
     {
       "path": "../../sandbox/sandbox"
     },
+    {
+      "path": "../../sandbox/sandbox-policy"
+    },
     {
       "path": "../../bash/bash"
     },

packages/bash/bash/README.md

@@ -29,7 +29,7 @@ Implementations subclass `BashExecutor` and implement the abstract methods. Disp
 
 `BashExecRequest` (command, workdir?, timeoutMs?, stdoutMaxBytes?, signal?, stdin?, env?, dshEnv?, sandboxMode?) resolves to `BashExecSpec` (command, workdir, timeoutMs, stdoutMaxBytes, signal?, stdin?, env?, dshEnv?, sandboxMode) before execution. `stdoutMaxBytes` is a trusted foreground-run capture budget for consumers that must parse complete bounded stdout; the model-facing bash tool does not expose it. `sandboxMode` is optional on the request and required-but-nullable on the resolved spec: it carries an approved one-shot escalation or the session's standing override; a sandboxing executor stamps its configured default when absent, while a non-sandboxing executor carries the field and confines nothing.
 
-The seam also owns the per-session mode override vocabulary: the log-only `'bash/sandbox-mode'` session event, the pure `effectiveSandboxMode(events)` fold, and the `setSandboxMode(session, mode)` write path. `run()` returns `BashRunResult`; `start()` returns `BashProcess`, whose incremental read and kill methods are adapted by `dsh-tool-bash` into a generic task registration. A sandboxing executor stamps `BashSandboxInfo` on foreground results and settled process handles. See `src/types.ts` and [core-data-structures/bash.md](../../../docs/core-data-structures/bash.md).
+The per-session sandbox-mode override vocabulary (the `'sandbox/mode'` event, the `effectiveSandboxMode(events)` fold, and the `setSandboxMode(session, mode)` write path) is NOT here — it is policy state shared by every enforcing family, owned by [`@deepseek-ai/dsh-sandbox-policy`](../../sandbox/sandbox-policy/). `run()` returns `BashRunResult`; `start()` returns `BashProcess`, whose incremental read and kill methods are adapted by `dsh-tool-bash` into a generic task registration. A sandboxing executor stamps `BashSandboxInfo` on foreground results and settled process handles. See `src/types.ts` and [core-data-structures/bash.md](../../../docs/core-data-structures/bash.md).
 
 `stdin` and ordinary `env` are set by in-process plugins (the hooks bridges, native plugins) to feed a hook command its JSON payload and `CLAUDE_PROJECT_DIR`/`CLAUDE_PLUGIN_ROOT` values. `dshEnv` is a separate trusted overlay restricted by type to managed keys; the exported `DSH_ENV_PREFIX` is the single source for that namespace, its `DshEnvironmentKey` template type, executor scrubbing, registry validation, derived built-in names, and model guidance. Model bash uses the current snapshot collected by `ctx.bashEnv`. Implementations remove inherited managed keys, reject those names in ordinary `env`, then merge `dshEnv`, so an omitted current fact cannot fall back to stale ambient state. The model-facing tool exposes none of these as parameters. All three remain optional on the resolved spec; absent means no input/overlay. See [the bash-stdin-env Agent Note](../../../.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md) and [the session environment Agent Note](../../../.agents/notes/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md).
 

packages/bash/bash/package.json

@@ -23,12 +23,10 @@
   "license": "BSD-3-Clause",
   "peerDependencies": {
     "@deepseek-ai/dsh-sandbox": "^0.0.1",
-    "@deepseek-ai/dsh-session": "^0.0.1",
     "cordis": "^4.0.0-rc.7"
   },
   "devDependencies": {
     "@deepseek-ai/dsh-sandbox": "workspace:^",
-    "@deepseek-ai/dsh-session": "workspace:^",
     "cordis": "^4.0.0-rc.7"
   }
 }

packages/bash/bash/src/index.ts

@@ -10,7 +10,6 @@ import type { SandboxMode } from '@deepseek-ai/dsh-sandbox'
 import type { BashExecRequest, BashExecSpec, BashProcess, BashRunResult } from './types.ts'
 
 export { DSH_ENV_PREFIX } from './types.ts'
-export { SANDBOX_MODES, effectiveSandboxMode, setSandboxMode } from './session-mode.ts'
 export type {
   BashExecRequest,
   BashExecSpec,

packages/bash/bash/src/session-mode.ts

@@ -1,52 +0,0 @@
-/**
- * Per-session sandbox-mode override stored as log-only events. Folding the log
- * isolates sessions and survives replay; the tool stamps the override onto
- * each call unless an approved one-shot escalation outranks it, and the
- * executor default applies when neither exists. The model receives neither the
- * event nor a standing-mode notice; denial results name the effective mode.
- * @module dsh-bash/session-mode
- */
-
-import type { Session, SessionEvent } from '@deepseek-ai/dsh-session'
-import type { SandboxMode } from '@deepseek-ai/dsh-sandbox'
-
-declare module '@deepseek-ai/dsh-session' {
-  interface SessionEventMap {
-    /**
-     * Durable log-only sandbox-mode override; never a surface event or model
-     * message. Execution and ACP option reporting fold the latest event through
-     * {@link effectiveSandboxMode} without adding a prompt notice.
-     */
-    'bash/sandbox-mode': { mode: SandboxMode }
-  }
-}
-
-/** Every {@link SandboxMode}, for option advertisement and runtime validation of untrusted mode strings. */
-export const SANDBOX_MODES: readonly SandboxMode[] = ['read-only', 'workspace-write', 'danger-full-access']
-
-/**
- * The session's sandbox-mode override: the last `bash/sandbox-mode` event in
- * the log, or undefined when the session never switched and callers should use
- * the executor default. Replay needs no separate catch-up state.
- * @param events - session events in log order (other event types are skipped).
- * @returns the mode of the last switch event, or undefined without one.
- */
-export function effectiveSandboxMode(events: readonly SessionEvent[]): SandboxMode | undefined {
-  for (let index = events.length - 1; index >= 0; index -= 1) {
-    const event = events[index] as SessionEvent
-    if (event.type === 'bash/sandbox-mode') return event.data.mode
-  }
-  return undefined
-}
-
-/**
- * Append one `bash/sandbox-mode` event as the only override write path.
- * Execution and ACP option reporting fold it on read; prompt assembly does not
- * consume it.
- * @param session - the session the override belongs to.
- * @param mode - the mode every subsequent bash call in this session runs
- *   under (until the next switch).
- */
-export function setSandboxMode(session: Session, mode: SandboxMode): void {
-  session.append('bash/sandbox-mode', { mode })
-}

packages/bash/bash/tsconfig.json

@@ -16,9 +16,6 @@
     },
     {
       "path": "../../sandbox/sandbox"
-    },
-    {
-      "path": "../../core/session"
     }
   ]
 }

packages/bash/tool-bash/package.json

@@ -23,15 +23,16 @@
   "license": "BSD-3-Clause",
   "peerDependencies": {
     "@deepseek-ai/dsh-agent": "^0.0.1",
-    "@deepseek-ai/dsh-user-approval": "^0.0.1",
     "@deepseek-ai/dsh-bash": "^0.0.1",
     "@deepseek-ai/dsh-home": "^0.0.1",
     "@deepseek-ai/dsh-llm": "^0.0.1",
     "@deepseek-ai/dsh-session-persistence": "^0.0.1",
     "@deepseek-ai/dsh-sandbox": "^0.0.1",
+    "@deepseek-ai/dsh-sandbox-policy": "^0.0.1",
     "@deepseek-ai/dsh-system-prompt": "^0.0.1",
     "@deepseek-ai/dsh-tasks": "^0.0.1",
     "@deepseek-ai/dsh-tools": "^0.0.1",
+    "@deepseek-ai/dsh-user-approval": "^0.0.1",
     "cordis": "^4.0.0-rc.7"
   },
   "dependencies": {
@@ -47,6 +48,7 @@
     "@deepseek-ai/dsh-home": "workspace:^",
     "@deepseek-ai/dsh-llm": "workspace:^",
     "@deepseek-ai/dsh-sandbox": "workspace:^",
+    "@deepseek-ai/dsh-sandbox-policy": "workspace:^",
     "@deepseek-ai/dsh-session": "workspace:^",
     "@deepseek-ai/dsh-session-persistence": "workspace:^",
     "@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^",
@@ -54,6 +56,7 @@
     "@deepseek-ai/dsh-tasks": "workspace:^",
     "@deepseek-ai/dsh-tool-tasks": "workspace:^",
     "@deepseek-ai/dsh-tools": "workspace:^",
+    "@deepseek-ai/dsh-user-approval": "workspace:^",
     "cordis": "^4.0.0-rc.7"
   }
 }

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

@@ -15,12 +15,13 @@ import { defineTool } from '@deepseek-ai/dsh-tools'
 import type { GenericCallView, TerminalCallView, ToolExecution, ToolResult, ToolResultView } from '@deepseek-ai/dsh-tools'
 import type { Agent } from '@deepseek-ai/dsh-agent'
 import type {} from '@deepseek-ai/dsh-session-persistence'
-import { assertNever } from '@deepseek-ai/dsh-llm'
 import type {} from '@deepseek-ai/dsh-system-prompt'
 import type {} from '@deepseek-ai/dsh-tasks'
 import type {} from '@deepseek-ai/dsh-user-approval'
 import type { SandboxMode } from '@deepseek-ai/dsh-sandbox'
-import { DSH_ENV_PREFIX, effectiveSandboxMode } from '@deepseek-ai/dsh-bash'
+import { ESCALATION_TARGETS, approveEscalation, validateEscalationArgs } from '@deepseek-ai/dsh-sandbox'
+import { effectiveSandboxMode } from '@deepseek-ai/dsh-sandbox-policy'
+import { DSH_ENV_PREFIX } from '@deepseek-ai/dsh-bash'
 import type { DshEnvironment, DshEnvironmentKey } from '@deepseek-ai/dsh-bash'
 import { DSH_HOME_ENV, resolveDshHome } from '@deepseek-ai/dsh-home'
 import { processOutcome } from './background.ts'
@@ -226,24 +227,11 @@ function validateBashArgs(args: BashToolArgs): void {
   if (args.timeoutMs !== undefined && (!Number.isFinite(args.timeoutMs) || args.timeoutMs <= 0)) {
     throw new Error(`invalid timeoutMs: expected a positive number, got ${JSON.stringify(args.timeoutMs)}`)
   }
-  if (args.sandbox_permissions !== undefined && args.justification === undefined) {
-    throw new Error('invalid escalation: sandbox_permissions requires a justification')
-  }
-  if (args.justification !== undefined && args.sandbox_permissions === undefined) {
-    throw new Error('invalid escalation: justification is only valid together with sandbox_permissions')
-  }
-  if (args.justification !== undefined && args.justification.trim().length === 0) {
-    throw new Error('invalid justification: expected a non-empty sentence')
-  }
+  // The escalation pairing (sandbox_permissions ⇔ justification, non-empty) is
+  // the shared rule both enforcing families validate identically.
+  validateEscalationArgs(args.sandbox_permissions, args.justification)
 }
 
-const WIDER_MODES: Record<string, readonly SandboxMode[]> = {
-  'read-only': ['workspace-write', 'danger-full-access'],
-  'workspace-write': ['danger-full-access'],
-}
-
-const ESCALATION_TARGETS: readonly SandboxMode[] = ['workspace-write', 'danger-full-access']
-
 function bashDescription(backgroundEnabled: boolean, escalationModes: readonly SandboxMode[]): string {
   const background = backgroundEnabled
     ? 'Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`.'
@@ -346,35 +334,32 @@ export function apply(ctx: Context, config: Config = {}): void {
   const sessionOverride = (exec: ToolExecution): SandboxMode | undefined =>
     defaultMode === undefined || exec.agent === undefined ? undefined : effectiveSandboxMode(exec.agent.session.events)
 
-  const approveEscalation = async (mode: string, justification: string, exec: ToolExecution): Promise<SandboxMode> => {
+  /**
+   * Resolve a sandbox-escalation request through `ctx.approval` BEFORE
+   * anything executes, delegating the shared fail-closed sequence (strict
+   * widening, channel resolution, outcome mapping) to
+   * {@link approveEscalation}. This tool contributes only the composition
+   * guard (the fields are unadvertised without a sandboxing executor, yet
+   * schema validation checks advertised keys only, so an unadvertised
+   * `sandbox_permissions` still reaches execute) and the approval ingredients
+   * — the seam is consumed opportunistically (`ctx.get`) so a deployment
+   * without it degrades per call.
+   */
+  const approveBashEscalation = (mode: string, justification: string, exec: ToolExecution): Promise<SandboxMode> => {
     if (escalationModes.length === 0) {
       throw new Error('sandbox_permissions is not available in this composition (no sandboxing executor to escalate)')
     }
     const effectiveMode = (sessionOverride(exec) ?? defaultMode) as SandboxMode
-    if (!(WIDER_MODES[effectiveMode] ?? []).includes(mode as SandboxMode)) {
-      throw new Error(`sandbox escalation to "${mode}" is not strictly wider than this call's current "${effectiveMode}" mode`)
-    }
-    const approval = ctx.get('approval')
-    if (approval === undefined) {
-      throw new Error(`sandbox escalation to "${mode}" requires approval, but no approval service is composed`)
-    }
-    if (exec.agent === undefined) {
-      throw new Error(`sandbox escalation to "${mode}" requires approval, but the call has no agent to route it through`)
-    }
-    const outcome = await approval.request({
-      agent: exec.agent,
-      toolName: 'bash',
-      callId: exec.callId,
-      reason: `escalate sandbox to ${mode}: ${justification}`,
-      ...exec.signal ? { signal: exec.signal } : {},
-    })
-    switch (outcome) {
-      case 'allowed-once': return mode as SandboxMode
-      case 'rejected': throw new Error(`the user rejected escalating this command to "${mode}"`)
-      case 'cancelled': throw new Error(`approval for escalating to "${mode}" was cancelled`)
-      case 'unavailable': throw new Error(`sandbox escalation to "${mode}" requires approval, but no approval channel is available`)
-      default: return assertNever(outcome, 'ApprovalOutcome')
-    }
+    return approveEscalation(
+      { requestedMode: mode, justification, effectiveMode, subject: 'command' },
+      {
+        approver: ctx.get('approval'),
+        agent: exec.agent,
+        callId: exec.callId,
+        toolName: 'bash',
+        ...exec.signal ? { signal: exec.signal } : {},
+      },
+    )
   }
 
   // Cross-call guidance belongs in the prompt rather than one-call schema prose.
@@ -417,7 +402,7 @@ export function apply(ctx: Context, config: Config = {}): void {
       validateBashArgs(args)
       // Description is display metadata; workdir defaults to the caller's session.
       const sandboxMode = args.sandbox_permissions !== undefined && args.justification !== undefined
-        ? await approveEscalation(args.sandbox_permissions, args.justification, exec)
+        ? await approveBashEscalation(args.sandbox_permissions, args.justification, exec)
         : sessionOverride(exec)
       const workdir = resolveWorkdir(args.workdir, exec)
       const dshEnv = bashEnv.collect(exec)

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

@@ -6,6 +6,7 @@
 
 import type { BashProcessRead, BashRunResult, BashSandboxInfo, CollectedOutput } from '@deepseek-ai/dsh-bash'
 import type { SandboxMode } from '@deepseek-ai/dsh-sandbox'
+import { escalationHintMarker, sandboxDenialMarker } from '@deepseek-ai/dsh-sandbox'
 
 /** Append the truncation notice (with the full-output spill path) to a stream's text. */
 function streamText(output: CollectedOutput): string {
@@ -42,10 +43,10 @@ export function renderResult(
   const markers: string[] = []
   // Keep the exit marker last because parseExitStatus anchors there.
   if (result.sandbox?.denied) {
-    markers.push(`[sandbox: file access denied under ${result.sandbox.mode} mode]`)
+    markers.push(sandboxDenialMarker(result.sandbox.mode))
     // Hint only when the composition exposes escalation, before the final exit marker.
     if (escalationModes.length > 0) {
-      markers.push('[sandbox: escalation available — retry this exact command once with sandbox_permissions (the narrowest wider mode that suffices) + justification; the approval prompt asks the user]')
+      markers.push(escalationHintMarker('command'))
     }
   }
   // A command may trap SIGTERM and exit 0 after timeout; still report interruption.
@@ -84,9 +85,9 @@ export function renderProcessRead(
   if (sandbox?.runnerFailed) {
     notices.push(`[sandbox: the sandbox runner itself failed under ${sandbox.mode} mode — the command did not run; this is a sandbox problem, not a command failure]`)
   } else if (sandbox?.denied) {
-    notices.push(`[sandbox: file access denied under ${sandbox.mode} mode]`)
+    notices.push(sandboxDenialMarker(sandbox.mode))
     if (escalationModes.length > 0) {
-      notices.push('[sandbox: escalation available — retry this exact command once with sandbox_permissions (the narrowest wider mode that suffices) + justification; the approval prompt asks the user]')
+      notices.push(escalationHintMarker('command'))
     }
   }
   if (notices.length === 0) return read.delta

packages/bash/tool-bash/tests/tools.spec.ts

@@ -181,7 +181,7 @@ async function setupSandboxed(withApproval = false) {
 
 function sandboxAgent(mode?: 'read-only' | 'workspace-write' | 'danger-full-access', ctx?: Context): Agent {
   const events: Array<{ type: string; data?: Record<string, unknown> }> = [{ type: 'turn/start' }]
-  if (mode !== undefined) events.push({ type: 'bash/sandbox-mode', data: { mode } })
+  if (mode !== undefined) events.push({ type: 'sandbox/mode', data: { mode } })
   const id = SessionId('sandbox-session')
   return {
     id,
@@ -553,7 +553,7 @@ describe('sandbox escalation through the generic task producer', () => {
 
     const malformed = sandboxAgent()
     ;(malformed.session.events as unknown as Array<{ type: string; data: { mode: string } }>).push({
-      type: 'bash/sandbox-mode',
+      type: 'sandbox/mode',
       data: { mode: 'unknown-mode' },
     })
     expect(text(await call(ctx, 'bash', escalate, malformed))).toContain('not strictly wider')
@@ -610,7 +610,7 @@ describe('sandbox escalation through the generic task producer', () => {
     const { ctx } = await setupSandboxed(true)
     ctx.approval.request = () => Promise.resolve('rogue' as ApprovalOutcome)
     const result = await call(ctx, 'bash', escalate, sandboxAgent())
-    expect(text(result)).toContain('unreachable variant in ApprovalOutcome')
+    expect(text(result)).toContain('unreachable variant in EscalationOutcome')
   })
 })
 

packages/bash/tool-bash/tsconfig.json

@@ -46,6 +46,9 @@
     },
     {
       "path": "../../sandbox/sandbox"
+    },
+    {
+      "path": "../../sandbox/sandbox-policy"
     }
   ]
 }

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

@@ -129,10 +129,12 @@ describe('WorkerCodeRuntime — budgets and containment (real workers)', () => {
   }, 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 })
+    // Keep the binding delay above the compute allowance while leaving enough
+    // headroom for worker bootstrap on loaded CI hosts.
+    const { runtime } = await setup({ computeMs: 1_000, maxWallMs: 30_000 })
     const result = await runtime.run({
       program: 'return await tools.slow({})',
-      bindings: tools({ slow: () => new Promise(resolve => setTimeout(() => { resolve('slow-done') }, 700)) }),
+      bindings: tools({ slow: () => new Promise(resolve => setTimeout(() => { resolve('slow-done') }, 1_500)) }),
     })
     expect(result.error).toBeUndefined()
     expect(result.value).toBe('slow-done')

packages/compact/README.md

@@ -1,11 +1,12 @@
 # compact/ — compaction capability family
 
-A three-package capability seam (see [capability seams](../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md)): an abstract compaction interface, a backend that summarizes, and the model-facing tool that consumes it. The interface and a first backend (`compact-basic/`) exist; the consumer tool is deferred. All **product** packages.
+A compaction capability family (see [capability seams](../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md)): an abstract interface, a summarizing backend, a model-free tool-result pruning companion, and a deferred model-facing consumer. All **product** packages.
 
 | Package | Role | ctx key |
 |---|---|---|
 | `compact/` | Abstract compaction seam (interface + `compact/*` events + `CompactionResult`) | `ctx.compact` |
 | `compact-basic/` | A backend: `ctx.tokenMeter` pressure + token-budget retention + `llm.stream()` summarization | (registers `ctx.compact`) |
+| `compact-tool-result-prune/` | Optional model-free head/middle/tail rewriting before summary compaction | `ctx.toolResultPrune` |
 | `tool-compact/` (deferred) | Model-facing `/compact` tool over `ctx.compact` | (registers on `ctx.tools`) |
 
-The interface lives at `compact/compact/`, the backend at `compact/compact-basic/`. Unlike the bash seam, it depends on `dsh-session` and `dsh-llm` — its verbs are defined over a `Session` and its output is the `ContentBlock` vocabulary, so the contract cannot be expressed without naming them. That deviation from the "interface depends only on cordis" guidance is intentional and recorded in the [compaction capability-seam Agent Note](../../.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md). Token measurement is a reusable LLM-family service rather than a `CompactService` method; a template- or model-backed compactor can replace `compact-basic` without changing the meter or callers.
+The interface lives at `compact/compact/`, the backend at `compact/compact-basic/`, and deterministic pruning at `compact/compact-tool-result-prune/`. Unlike the bash seam, the interface depends on `dsh-session` and `dsh-llm` because its verbs are defined over a `Session` and its output uses `ContentBlock`. That deviation is recorded in the [compaction capability-seam Agent Note](../../.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md). Token measurement remains a reusable LLM-family service; a template- or model-backed compactor can replace `compact-basic` without changing the meter, pruner, or callers.

packages/compact/compact-basic/README.md

@@ -9,13 +9,14 @@ This is the implementation tier of the compaction capability — see the [interf
 This backend owns the compaction policy:
 
 - **Measurement** — the singleton `ctx.tokenMeter` prices the latest canonical logged envelope and current surface at one consumed-log revision. Post-step pressure therefore includes the actual system prompt, tools, prefix, routing, assistant completion, tool results, buffered context, and steering.
-- **Retention** — compact the oldest whole surface units while preserving a recent tail and balanced tool-call/result cuts through the [`dsh-compact` boundary helpers](../compact/README.md#tool-pairing-boundaries). Turn boundaries do not protect old steps inside a runaway turn. An open indivisible tail declines until it closes; a single unit larger than the budget remains out of scope.
+- **Model-free pruning** — after pressure or canonical overflow qualifies, the optional [`ctx.toolResultPrune`](../compact-tool-result-prune/README.md) service rewrites oversized tool results before range selection. Compact-basic remeasures through `ctx.tokenMeter`, skips summarization when pressure becomes safe, and otherwise summarizes the pruned surface. Below-pressure post-step checks never prune.
+- **Retention** — compact the oldest whole surface units while preserving a recent tail and balanced tool-call/result cuts through the [`dsh-compact` boundary helpers](../compact/README.md#tool-pairing-boundaries). Turn boundaries do not protect old steps inside a runaway turn. An open indivisible tail declines until it closes. The optional pruner can repair an oversized closed tool unit when its text-bearing result is the removable bulk; indivisible non-tool units and non-prunable tool remainders remain out of scope.
 - **Convergence** — retry head-checkpoint compaction up to `compactionRetries`; reject a summary that does not shrink its source, and throw if retries cannot return below threshold.
 - **Summarization** — a direct `llm/stream` call uses the configured provider/model pair and cap, falling back to the latest logged request target and then the agent target, without running the loop-only `agent/request` seam. The input transcript preserves non-text blocks as tagged placeholders; only returned text enters the checkpoint, excluding reasoning and tool calls that would leak private reasoning or create an orphaned call.
 - **Framing** — the replacement user message marks established checkpoint context with `<compacted-summary>` tags. The raw summary remains on the provenance event, and later automatic cycles merge the prior checkpoint.
 - **Lifecycle** — `compactRegion()` mutates `agent.session` and records its start, summary, replacement, and end. The serial `agent/post-step` listener checks pressure after successful output and tool work are durable but before `step/end`. Canonical provider overflow is handled through `agent/request-error` after the failed step closes.
-- **Overflow recovery** — below-threshold overflow bypasses normal retention and attempts one maximal balanced head reduction while leaving the newest indivisible unit. Retry is authorized only when `surface.replaceGeneration` advances; no range, no replacement, recovery failure, an exhausted cap, cancellation, or an unknown/noncanonical error preserves the original provider failure.
-- **Failure handling** — an unmatched `compact/start` is an inert crash marker because no replacement landed. A region failure records an error end and leaves the surface unchanged. Operational post-step failures warn and continue; overflow-recovery failure preserves the original provider error.
+- **Overflow recovery** — below-threshold overflow bypasses normal retention, prunes, then attempts one maximal balanced head reduction while leaving the newest indivisible unit. Retry is authorized whenever `surface.replaceGeneration` advances, including when pruning lands before later summary work throws. No replacement, an exhausted cap, cancellation, or an unknown/noncanonical error preserves the original provider failure.
+- **Failure handling** — an unmatched `compact/start` is an inert crash marker because no summary replacement landed. A region failure records an error end; the surface remains unchanged unless pruning already landed. Operational post-step failures warn and continue, while overflow-recovery failure preserves the original provider error only when no earlier replacement advanced the surface. Cancellation remains authoritative after any progress.
 
 The protected `summarize()` method is the sole subclass hook. A template- or remote-summarizer subclass can override it while pressure, retention, provenance, shrink validation, and shadowed-token accounting stay on `ctx.tokenMeter`. The hook returns the summary blocks together with the call envelope it used (`{ summary, provider, model, maxTokens? }`), which is logged on `compact/summary`.
 
@@ -50,7 +51,7 @@ export function apply(ctx: Context): void {
 }
 ```
 
-Loading the plugin registers `ctx.compact`. With `auto: true` (the default) it compacts automatically under token pressure; a consumer (a future `/compact` tool) can also call `ctx.compact.compactIfNeeded(...)` or `ctx.compact.compactRegion(...)` directly.
+Loading the plugin registers `ctx.compact`. Add [`dsh-compact-tool-result-prune`](../compact-tool-result-prune/README.md) as a sibling before this plugin to enable the optional model-free pass. With `auto: true` (the default) it compacts automatically under token pressure; a consumer (a future `/compact` tool) can also call `ctx.compact.compactIfNeeded(...)` or `ctx.compact.compactRegion(...)` directly.
 
 ## Model Experience
 
@@ -58,7 +59,7 @@ Loading the plugin registers `ctx.compact`. With `auto: true` (the default) it c
 
 #### What the model sees
 
-After a successful step crosses the threshold, the next request receives the checkpoint preamble below, a blank line, `<compacted-summary>`, the data-dependent summary, and `</compacted-summary>`. Overflow recovery rebuilds the immediate retry from that replacement. This one checkpoint replaces the selected older range and is followed by the retained recent units.
+After a successful step crosses the threshold, oversized tool results are first rewritten when the optional pruner is loaded. If summarization remains necessary, the next request receives the checkpoint preamble below, a blank line, `<compacted-summary>`, the data-dependent summary, and `</compacted-summary>`. Overflow recovery rebuilds the immediate retry from whatever replacement advanced the surface. A checkpoint replaces the selected older range and is followed by the retained recent units.
 
 ##### Conversation checkpoint preamble
 
@@ -68,7 +69,7 @@ This is an automatically generated checkpoint condensing an earlier span of the
 
 #### Token effect
 
-The replacement reduces future input history rather than appending a second copy. The summary remains until a later compaction replaces it; one oversized indivisible unit can still exceed the budget.
+Model-free pruning can avoid the auxiliary call entirely; otherwise it reduces that call's transcript before the summary replaces an older range. The replacement reduces future input history rather than appending a second copy. A summary remains until a later compaction replaces it, while an indivisible non-tool unit can still exceed the budget.
 
 #### KV Cache effect
 
@@ -144,7 +145,7 @@ Prefix-stable for auxiliary calls while this instruction and the summarizer rout
 
 - **Meter accuracy follows the fixed heuristic** — missing reusable provider usage falls back to character count plus structural overhead rather than exact tokenization.
 - **Overflow classification is adapter-maintained** — provider wording can change; both DeepSeek adapters normalize currently recognized context-limit failures to `CONTEXT_WINDOW_EXCEEDED`.
-- **Single-unit and envelope-only overflow remain outside surface compaction** — recovery cannot split one indivisible message/tool unit or shrink system/tools/prefix.
+- **Some indivisible-unit and envelope-only overflow remains outside surface compaction** — recovery cannot shrink system/tools/prefix, split an indivisible non-tool node, or repair a tool unit whose non-prunable remainder still exceeds the window. The optional pruner can shrink text-bearing tool-result bulk inside an otherwise indivisible pair.
 - **`compactRegion` requires an open turn** — a manual call on a fully-closed session throws ("no open turn") rather than compacting.
-- **Summarization failure fails closed with full, over-budget history** — including truncation at the summarization `maxTokens`, which hidden reasoning tokens can consume; the auto path logs a warning and proceeds.
+- **Summarization failure preserves the latest durable surface** — before any replacement, the auto path logs a warning and proceeds with full over-budget history. If pruning already landed, a later summarization failure proceeds from that durable pruned surface. Summarization truncation at `maxTokens`, which hidden reasoning tokens can consume, follows the same rule.
 - **The summarization call has no transcript-snapshot coverage** — `dsh-llm-replay` derives calls from `assistant/chunk` events, so this chunk-less direct `ctx.llm.stream()` call cannot replay (named deferred replay infrastructure in [the seam Agent Note](../../../.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md)).

packages/compact/compact-basic/package.json

@@ -27,8 +27,14 @@
     "@deepseek-ai/dsh-llm": "^0.0.1",
     "@deepseek-ai/dsh-session": "^0.0.1",
     "@deepseek-ai/dsh-token-meter": "^0.0.1",
+    "@deepseek-ai/dsh-compact-tool-result-prune": "^0.0.1",
     "cordis": "^4.0.0-rc.7"
   },
+  "peerDependenciesMeta": {
+    "@deepseek-ai/dsh-compact-tool-result-prune": {
+      "optional": true
+    }
+  },
   "dependencies": {
     "schemastery": "^3.18.0"
   },
@@ -43,6 +49,7 @@
     "@deepseek-ai/dsh-llm": "workspace:^",
     "@deepseek-ai/dsh-session": "workspace:^",
     "@deepseek-ai/dsh-token-meter": "workspace:^",
+    "@deepseek-ai/dsh-compact-tool-result-prune": "workspace:^",
     "@deepseek-ai/dsh-tools": "workspace:^",
     "cordis": "^4.0.0-rc.7"
   }

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

@@ -12,6 +12,8 @@ import type { Session } from '@deepseek-ai/dsh-session'
 import { CONTEXT_WINDOW_EXCEEDED_CODE, assertNever } from '@deepseek-ai/dsh-llm'
 import type { ContentBlock } from '@deepseek-ai/dsh-llm'
 import type { Agent } from '@deepseek-ai/dsh-agent'
+// Type-only: makes the optional sibling service available to `ctx.get()`.
+import type {} from '@deepseek-ai/dsh-compact-tool-result-prune'
 import { resolveConfig } from './config.ts'
 import { compactSurfaceRegion, selectCompactableRange } from './region.ts'
 import { summarizeWithLlm } from './summarizer.ts'
@@ -98,22 +100,35 @@ export class BasicCompactService extends CompactService {
         || retryAttempt >= this.config.maxOverflowRetries
         || signal.aborted) return next()
 
-      let generation: number
+      const generation = agent.session.surface.replaceGeneration
       let result: CompactionResult | null
       try {
-        generation = agent.session.surface.replaceGeneration
         result = await this.compactIfNeeded(agent, 'context-overflow', signal)
       } catch (recoveryError: unknown) {
         const message = recoveryError instanceof Error ? recoveryError.message : String(recoveryError)
+        // A model-free prune can land before later summary work fails. That
+        // durable reduction is sufficient retry proof; do not discard it just
+        // because the optional second phase threw. Cancellation still wins.
+        // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition -- signal can abort while recovery is awaited.
+        if (!signal.aborted && agent.session.surface.replaceGeneration > generation) {
+          ctx.logger.warn(
+            `context-overflow compaction failed after durable surface progress: ${message}; `
+            + 'retrying from the replacement surface',
+          )
+          return { action: 'retry' }
+        }
         ctx.logger.warn(
-          `context-overflow compaction failed: ${message}; preserving the original request error`,
+          // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition -- signal can abort while recovery is awaited.
+          `context-overflow compaction failed: ${message}; ${signal.aborted
+            ? 'cancellation prevents retry'
+            : 'preserving the original request error'}`,
         )
         return next()
       }
       // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition -- signal can abort while compaction is awaited.
-      if (signal.aborted || result === null
+      if (signal.aborted
         || agent.session.surface.replaceGeneration <= generation) return next()
-      logResult(result, 'context overflow recovery')
+      if (result !== null) logResult(result, 'context overflow recovery')
       return { action: 'retry' }
     })
   }
@@ -142,7 +157,7 @@ export class BasicCompactService extends CompactService {
    * @param agent - agent whose latest durable routed request is measured.
    * @param trigger - normal post-step pressure or context-overflow recovery.
    * @param signal - live turn cancellation signal forwarded to summarization.
-   * @returns the latest compaction result, or `null` when no check/work applies.
+   * @returns the latest summary compaction result, or `null` when no summary ran.
    */
   override async compactIfNeeded(
     agent: Agent,
@@ -152,22 +167,34 @@ export class BasicCompactService extends CompactService {
     const model = routedModel(agent.session)
     if (model === undefined) return null
     const meter = this.ctx.tokenMeter
+    const threshold = Math.floor(meter.contextWindow * this.config.thresholdRatio)
+    let measurement = meter.measure(agent.session)
     switch (trigger) {
-      case 'context-overflow': {
-        const measurement = meter.measure(agent.session)
-        const range = selectCompactableRange(agent.session, measurement, 0)
-        if (range === null) return null
-        return this.compactRegion(range.start, range.end, agent, signal)
-      }
+      case 'context-overflow':
+        break
       case 'pressure':
+        if (measurement.totalTokens < threshold) return null
         break
       /* v8 ignore next -- closed-union exhaustiveness guard */
       default:
         assertNever(trigger, 'compaction trigger')
     }
 
-    const threshold = Math.floor(meter.contextWindow * this.config.thresholdRatio)
-    let measurement = meter.measure(agent.session)
+    // Pruning is optional so compact-basic remains independently composable.
+    // Once either trigger qualifies, land the model-free pass before choosing
+    // a summary range, then remeasure through the singleton replay fold.
+    const prune = this.ctx.get('toolResultPrune')
+    if (prune !== undefined) {
+      prune.pruneSession(agent.session)
+      measurement = meter.measure(agent.session)
+    }
+
+    if (trigger === 'context-overflow') {
+      const range = selectCompactableRange(agent.session, measurement, 0)
+      if (range === null) return null
+      return this.compactRegion(range.start, range.end, agent, signal)
+    }
+
     if (measurement.totalTokens < threshold) return null
 
     let result: CompactionResult | null = null

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

@@ -10,6 +10,7 @@ import LlmService, { CallId, CONTEXT_WINDOW_EXCEEDED_CODE, LlmAdapter } from '@d
 import type { ContentBlock, GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm'
 import { Session, SessionId } from '@deepseek-ai/dsh-session'
 import TokenMeterService from '@deepseek-ai/dsh-token-meter'
+import ToolResultPruneService from '@deepseek-ai/dsh-compact-tool-result-prune'
 import type { Agent } from '@deepseek-ai/dsh-agent'
 
 const SIGNAL = new AbortController().signal
@@ -97,6 +98,43 @@ function toolConversation(): Session {
   return session
 }
 
+/** One closed routed tool step followed by an open turn for rewrite events. */
+function oversizedToolResult(chars = 3_000, withCompactablePrompt = false): Session {
+  const session = new Session(SessionId(`oversized-tool-${chars}`))
+  const callId = CallId('oversized')
+  session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
+  if (withCompactablePrompt) {
+    session.append('user/message', {
+      content: [{ type: 'text', text: 'older history '.repeat(200) }],
+      source: { kind: 'user' },
+    }, { surfaceOp: 'append' })
+  }
+  session.append('step/start', { turn: 1, step: 1 })
+  session.append('request/header', {
+    header: { config: { provider: MODEL, model: MODEL } },
+    reason: 'initial',
+  })
+  session.append('assistant/message', {
+    turn: 1,
+    step: 1,
+    content: [{ type: 'tool-call', id: callId, name: 'bash', arguments: '{}' }],
+    provenance: { provider: MODEL, model: MODEL },
+  }, { surfaceOp: 'append' })
+  session.append('tool/call', { turn: 1, step: 1, callId, name: 'bash', arguments: '{}' })
+  session.append('tool/result', {
+    turn: 1,
+    step: 1,
+    callId,
+    content: [{ type: 'text', text: 'X'.repeat(chars) }],
+    isError: false,
+    meta: { presentation: 'preserved' },
+  }, { surfaceOp: 'append' })
+  session.append('step/end', { turn: 1, step: 1 })
+  session.append('turn/end', { turn: 1, reason: { kind: 'completed' } })
+  session.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } })
+  return session
+}
+
 class TestCompactService extends BasicCompactService {
   summary: ContentBlock[] = [{ type: 'text', text: 'small checkpoint' }]
   summaryProvider = 'summary-provider'
@@ -416,6 +454,78 @@ describe('pressure measurement and retention', () => {
   })
 })
 
+describe('optional model-free tool-result pruning', () => {
+  const pruneConfig = { thresholdChars: 100, headChars: 20, tailChars: 10 }
+
+  it('does not prune a below-pressure session opportunistically', async () => {
+    const ctx = createContext(10_000)
+    const prune = new ToolResultPruneService(ctx, pruneConfig)
+    const compact = new TestCompactService(ctx, {
+      auto: false,
+      thresholdRatio: 0.8,
+      retainTokens: 100,
+    })
+    const session = oversizedToolResult()
+    const pruneSession = vi.spyOn(prune, 'pruneSession')
+
+    expect(await compactIfNeeded(compact, session)).toBeNull()
+    expect(pruneSession).not.toHaveBeenCalled()
+    expect(compact.calls).toHaveLength(0)
+    expect(session.surface.replaceGeneration).toBe(0)
+  })
+
+  it('skips LLM summarization when pruning alone clears pressure', async () => {
+    const ctx = createContext(1_000)
+    void new ToolResultPruneService(ctx, pruneConfig)
+    const compact = new TestCompactService(ctx, {
+      auto: false,
+      thresholdRatio: 0.5,
+      retainTokens: 50,
+    })
+    const session = oversizedToolResult()
+
+    expect(ctx.tokenMeter.measure(session).totalTokens).toBeGreaterThanOrEqual(500)
+    expect(await compactIfNeeded(compact, session)).toBeNull()
+    expect(ctx.tokenMeter.measure(session).totalTokens).toBeLessThan(500)
+    expect(compact.calls).toHaveLength(0)
+    expect(session.surface.replaceGeneration).toBe(1)
+  })
+
+  it('summarizes the pruned surface when pruning is insufficient', async () => {
+    const ctx = createContext(2_000)
+    void new ToolResultPruneService(ctx, pruneConfig)
+    const compact = new TestCompactService(ctx, {
+      auto: false,
+      thresholdRatio: 0.5,
+      retainTokens: 50,
+    })
+    const session = toolConversation()
+
+    expect(await compactIfNeeded(compact, session)).not.toBeNull()
+    expect(compact.calls).toHaveLength(1)
+    expect(compact.calls[0]!.text).toContain('tool result middle pruned')
+    expect(compact.calls[0]!.text).not.toContain('result 1 '.repeat(300))
+  })
+
+  it('retains the original compact-basic behavior without the optional plugin', async () => {
+    const ctx = createContext(2_000)
+    const compact = new TestCompactService(ctx, {
+      auto: false,
+      thresholdRatio: 0.5,
+      retainTokens: 50,
+    })
+    const session = oversizedToolResult(3_000, true)
+
+    expect(await compactIfNeeded(compact, session)).not.toBeNull()
+    expect(compact.calls).toHaveLength(1)
+    const original = session.events.find(event => event.type === 'tool/result')
+    expect(original?.type === 'tool/result' && original.data.content[0])
+      .toEqual({ type: 'text', text: 'X'.repeat(3_000) })
+    expect(session.events.filter(event =>
+      event.type === 'tool/result' && event.surfaceOp !== 'append')).toHaveLength(0)
+  })
+})
+
 describe('compaction region transaction', () => {
   it('lands a framed, replayable checkpoint with exact pricing provenance', async () => {
     const compact = service()
@@ -876,6 +986,89 @@ describe('automatic listener and loader composition', () => {
     expect(session.surface.nodes).toContain(retainedSeq)
   })
 
+  it('authorizes overflow retry when pruning alone advances an indivisible surface', async () => {
+    const ctx = createContext(10_000)
+    void new ToolResultPruneService(ctx, {
+      thresholdChars: 100,
+      headChars: 20,
+      tailChars: 10,
+    })
+    const compact = new TestCompactService(ctx, {
+      thresholdRatio: 1,
+      retainTokens: 900,
+    })
+    const session = oversizedToolResult()
+
+    expect(await recover(ctx, agent(session, MODEL), overflow())).toEqual({ action: 'retry' })
+    expect(session.surface.replaceGeneration).toBe(1)
+    expect(session.events.some(event => event.type === 'compact/summary')).toBe(false)
+    expect(compact.calls).toHaveLength(0)
+  })
+
+  it('continues overflow recovery with summarization on the pruned surface', async () => {
+    const ctx = createContext(10_000)
+    void new ToolResultPruneService(ctx, {
+      thresholdChars: 100,
+      headChars: 20,
+      tailChars: 10,
+    })
+    const compact = new TestCompactService(ctx, {
+      thresholdRatio: 1,
+      retainTokens: 900,
+    })
+    const session = toolConversation()
+
+    expect(await recover(ctx, agent(session, MODEL), overflow())).toEqual({ action: 'retry' })
+    expect(session.events.some(event => event.type === 'compact/summary')).toBe(true)
+    expect(compact.calls).toHaveLength(1)
+    expect(compact.calls[0]!.text).toContain('tool result middle pruned')
+  })
+
+  it('retries from a durable prune when later overflow summarization throws', async () => {
+    const ctx = createContext(10_000)
+    const warnings: string[] = []
+    ctx.logger.warn = ((message: string) => void warnings.push(message)) as typeof ctx.logger.warn
+    void new ToolResultPruneService(ctx, {
+      thresholdChars: 100,
+      headChars: 20,
+      tailChars: 10,
+    })
+    const compact = new TestCompactService(ctx, {
+      thresholdRatio: 1,
+      retainTokens: 900,
+    })
+    compact.error = new Error('summary unavailable after prune')
+    const session = oversizedToolResult(3_000, true)
+
+    expect(await recover(ctx, agent(session, MODEL), overflow())).toEqual({ action: 'retry' })
+    expect(session.surface.replaceGeneration).toBe(1)
+    expect(session.events.filter(event => event.type === 'tool/result')).toHaveLength(2)
+    expect(session.events.findLast(event => event.type === 'compact/end')?.data)
+      .toMatchObject({ error: 'summary unavailable after prune' })
+    expect(warnings).toContainEqual(expect.stringContaining('retrying from the replacement surface'))
+  })
+
+  it('lets cancellation win when summary throws after a durable prune', async () => {
+    const ctx = createContext(10_000)
+    const controller = new AbortController()
+    void new ToolResultPruneService(ctx, {
+      thresholdChars: 100,
+      headChars: 20,
+      tailChars: 10,
+    })
+    const compact = new TestCompactService(ctx, {
+      thresholdRatio: 1,
+      retainTokens: 900,
+    })
+    compact.mutateDuringSummary = () => { controller.abort('cancelled during summary') }
+    compact.error = new Error('summary cancelled after prune')
+    const session = oversizedToolResult(3_000, true)
+
+    expect(await recover(ctx, agent(session, MODEL), overflow(), 0, controller.signal))
+      .toEqual({ action: 'fail' })
+    expect(session.surface.replaceGeneration).toBe(1)
+  })
+
   it('preserves the newest whole tool-call/result pair during forced overflow compaction', async () => {
     const ctx = createContext()
     void new TestCompactService(ctx, {

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

@@ -9,6 +9,7 @@ import Include from '@cordisjs/plugin-include'
 import LlmService from '@deepseek-ai/dsh-llm'
 import TokenMeterService from '@deepseek-ai/dsh-token-meter'
 import BasicCompactService from '@deepseek-ai/dsh-compact-basic'
+import ToolResultPruneService from '@deepseek-ai/dsh-compact-tool-result-prune'
 
 let root: string | undefined
 let context: Context | undefined
@@ -32,6 +33,7 @@ async function loadYaml(lines: readonly string[]): Promise<Context> {
   const modules = new Map<string, unknown>([
     ['@deepseek-ai/dsh-llm', LlmService],
     ['@deepseek-ai/dsh-token-meter', TokenMeterService],
+    ['@deepseek-ai/dsh-compact-tool-result-prune', ToolResultPruneService],
     ['@deepseek-ai/dsh-compact-basic', BasicCompactService],
   ])
   context.loader.internal = {
@@ -50,12 +52,17 @@ async function loadYaml(lines: readonly string[]): Promise<Context> {
 }
 
 describe('real Loader composition', () => {
-  it('loads the flat token-meter and compact-basic YAML shape', async () => {
+  it('loads the shipped token-meter, pruning, and compact-basic YAML order', async () => {
     const loaded = await loadYaml([
       "- name: '@deepseek-ai/dsh-llm'",
       "- name: '@deepseek-ai/dsh-token-meter'",
       '  config:',
       '    contextWindow: 4096',
+      "- name: '@deepseek-ai/dsh-compact-tool-result-prune'",
+      '  config:',
+      '    thresholdChars: 100',
+      '    headChars: 20',
+      '    tailChars: 10',
       "- name: '@deepseek-ai/dsh-compact-basic'",
       '  config:',
       '    thresholdRatio: 0.5',
@@ -68,6 +75,7 @@ describe('real Loader composition', () => {
       .map(entry => entry.options.name)
     expect(unloaded).toEqual([])
     expect(loaded.tokenMeter.contextWindow).toBe(4096)
+    expect(loaded.get('toolResultPrune')).toBeInstanceOf(ToolResultPruneService)
     expect(loaded.get('compact')).toBeInstanceOf(BasicCompactService)
     expect((loaded.compact as BasicCompactService).config).toMatchObject({
       thresholdRatio: 0.5,

packages/compact/compact-basic/tsconfig.json

@@ -13,6 +13,7 @@
     { "path": "../../llm/token-meter" },
     { "path": "../../core/session" },
     { "path": "../../core/agent" },
-    { "path": "../compact" }
+    { "path": "../compact" },
+    { "path": "../compact-tool-result-prune" }
   ]
 }

packages/compact/compact-tool-result-prune/README.md

@@ -0,0 +1,60 @@
+# @deepseek-ai/dsh-compact-tool-result-prune
+
+The replay-safe model-free pruning service (`ctx.toolResultPrune`). It rewrites over-budget `tool/result` surface nodes to a bounded head, a fixed omission marker, and a bounded tail while retaining the full original event in the append-only session log.
+
+This is a concrete companion to [`dsh-compact-basic`](../compact-basic/README.md), not a compaction backend or model-facing tool. Compact-basic reads it through optional `ctx.get('toolResultPrune')`, so either package remains independently composable.
+
+## Service API
+
+`pruneSession(session)` scans one stable snapshot of the current surface. Every over-budget tool result is replaced by one newly appended `tool/result` carrying `{ surfaceOp: { op: 'replace', start: originalSeq, end: originalSeq }, sourceEventSeqs: [originalSeq] }`. The replacement spreads the complete original data and changes only `content`, preserving `turn`, `step`, `callId`, error fields, `meta`, and later data additions. The original event remains available for persistence, replay, and exact-log inspection.
+
+The method throws synchronously when the session rejects a replacement. Replacements committed earlier in the pass remain durable.
+
+`measureContent(blocks)` counts Unicode code points in `text` blocks. `pruneContent(blocks)` returns the bounded replacement or `null` when content is already within the threshold. Non-text blocks are retained at their original relative positions; text slicing never splits a UTF-16 surrogate pair, though it can split a multi-code-point grapheme cluster.
+
+Every emitted result has exactly the configured head budget, fixed marker, and tail budget in text code points, is no larger than `thresholdChars`, and is strictly smaller than the triggering input. A second pass therefore emits no replacement.
+
+## Config
+
+Unrecognized keys fail at plugin construction. Resolved config is detached and deeply immutable.
+
+| Key | Required | Meaning |
+|---|---|---|
+| `thresholdChars` | no (default `8192`) | Prune when combined text exceeds this many Unicode code points. |
+| `headChars` | no (default `4096`) | Leading Unicode code points retained. |
+| `tailChars` | no (default `1024`) | Trailing Unicode code points retained. |
+
+All values are integers; the threshold is positive and head/tail are non-negative. `headChars + marker + tailChars` must fit within `thresholdChars`, so a valid configuration can prune every over-budget result without growth or repeated rewriting.
+
+## Usage
+
+```ts
+import type { Context } from 'cordis'
+import ToolResultPruneService from '@deepseek-ai/dsh-compact-tool-result-prune'
+
+export function apply(ctx: Context): void {
+  ctx.plugin(ToolResultPruneService)
+}
+```
+
+## Model Experience
+
+### Pruned tool result
+
+#### What the model sees
+
+Once a compaction trigger qualifies, future requests see the retained head, `\n\n[... tool result middle pruned ...]\n\n`, and retained tail in place of the removed text. Rich blocks keep their order. The model does not see a second copy of the original.
+
+#### Token effect
+
+Each rewritten tool result has at most `thresholdChars` text code points. Pruning itself makes no model call; compact-basic skips summarization when the remeasured request falls below pressure, otherwise the summarizer reads the pruned surface.
+
+#### KV Cache effect
+
+Replacing an earlier result invalidates reuse from the first changed token. The pruned prefix is eligible for reuse while its route, envelope, and preceding history remain identical.
+
+## Known Limitations and Deferred Work
+
+- **Character budgets are not token budgets** — provider token density varies, so `ctx.tokenMeter` remains the authority for deciding whether pruning relieved request pressure.
+- **Pruning is syntactic** — it retains the beginning and end without interpreting which middle lines are semantically important.
+- **Grapheme clusters can split** — code-point slicing protects surrogate pairs but does not perform locale-aware grapheme segmentation.

packages/compact/compact-tool-result-prune/package.json

@@ -0,0 +1,40 @@
+{
+  "name": "@deepseek-ai/dsh-compact-tool-result-prune",
+  "description": "Replay-safe model-free head/middle/tail pruning for tool-result surface nodes",
+  "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-llm": "^0.0.1",
+    "@deepseek-ai/dsh-session": "^0.0.1",
+    "cordis": "^4.0.0-rc.7"
+  },
+  "dependencies": {
+    "schemastery": "^3.18.0"
+  },
+  "devDependencies": {
+    "@cordisjs/plugin-include": "workspace:^",
+    "@cordisjs/plugin-loader": "workspace:^",
+    "@deepseek-ai/dsh-invariants": "workspace:^",
+    "@deepseek-ai/dsh-llm": "workspace:^",
+    "@deepseek-ai/dsh-session": "workspace:^",
+    "cordis": "^4.0.0-rc.7"
+  }
+}

packages/compact/compact-tool-result-prune/src/config.ts

@@ -0,0 +1,77 @@
+/** Configuration resolution for deterministic tool-result pruning. */
+
+import { deepFreeze } from '@deepseek-ai/dsh-llm'
+import type { ResolvedConfig, ToolResultPruneConfig } from './types.ts'
+
+/** Fixed marker substituted for every removed middle span. */
+export const PRUNE_MARKER = '\n\n[... tool result middle pruned ...]\n\n'
+
+/** Low-friction defaults for coding-agent tool output. */
+export const DEFAULTS: ResolvedConfig = deepFreeze({
+  thresholdChars: 8192,
+  headChars: 4096,
+  tailChars: 1024,
+})
+
+const CONFIG_KEYS: ReadonlySet<string> = new Set([
+  'thresholdChars',
+  'headChars',
+  'tailChars',
+])
+
+/**
+ * Count Unicode code points without splitting surrogate pairs.
+ * @param text - text to measure.
+ * @returns the Unicode code-point count.
+ */
+export function codePointLength(text: string): number {
+  return Array.from(text).length
+}
+
+/**
+ * Resolve and validate pruning budgets.
+ * @param config - raw plugin configuration.
+ * @returns a detached deeply immutable configuration.
+ */
+export function resolveConfig(config: ToolResultPruneConfig = {}): ResolvedConfig {
+  for (const key of Object.keys(config)) {
+    if (!CONFIG_KEYS.has(key)) {
+      throw new Error(
+        `ToolResultPruneConfig: unknown key "${key}" `
+        + '(allowed: thresholdChars, headChars, tailChars)',
+      )
+    }
+  }
+
+  const resolved: ResolvedConfig = {
+    thresholdChars: config.thresholdChars ?? DEFAULTS.thresholdChars,
+    headChars: config.headChars ?? DEFAULTS.headChars,
+    tailChars: config.tailChars ?? DEFAULTS.tailChars,
+  }
+  assertPositiveInteger('thresholdChars', resolved.thresholdChars)
+  assertNonNegativeInteger('headChars', resolved.headChars)
+  assertNonNegativeInteger('tailChars', resolved.tailChars)
+
+  const emittedChars = resolved.headChars
+    + codePointLength(PRUNE_MARKER)
+    + resolved.tailChars
+  if (emittedChars > resolved.thresholdChars) {
+    throw new Error(
+      `ToolResultPruneConfig: headChars + marker + tailChars (${emittedChars}) `
+      + `must be at most thresholdChars (${resolved.thresholdChars})`,
+    )
+  }
+  return deepFreeze(structuredClone(resolved))
+}
+
+function assertPositiveInteger(name: string, value: number): void {
+  if (!Number.isInteger(value) || value <= 0) {
+    throw new Error(`ToolResultPruneConfig: ${name} (${value}) must be a positive integer`)
+  }
+}
+
+function assertNonNegativeInteger(name: string, value: number): void {
+  if (!Number.isInteger(value) || value < 0) {
+    throw new Error(`ToolResultPruneConfig: ${name} (${value}) must be a non-negative integer`)
+  }
+}

packages/compact/compact-tool-result-prune/src/index.ts

@@ -0,0 +1,159 @@
+/**
+ * Replay-safe, model-free tool-result pruning service.
+ *
+ * @module @deepseek-ai/dsh-compact-tool-result-prune
+ */
+
+import { Context, Service } from 'cordis'
+import z from 'schemastery'
+import type { ContentBlock } from '@deepseek-ai/dsh-llm'
+import type { Session, SessionEvent } from '@deepseek-ai/dsh-session'
+import { codePointLength, DEFAULTS, PRUNE_MARKER, resolveConfig } from './config.ts'
+import type {
+  PrunedEntry,
+  PruneResult,
+  ResolvedConfig,
+  ToolResultPruneConfig,
+} from './types.ts'
+
+export { codePointLength, DEFAULTS, PRUNE_MARKER, resolveConfig } from './config.ts'
+export type {
+  PrunedEntry,
+  PruneResult,
+  ResolvedConfig,
+  ToolResultPruneConfig,
+} from './types.ts'
+
+declare module 'cordis' {
+  interface Context {
+    toolResultPrune: ToolResultPruneService
+  }
+}
+
+interface SnapshotCandidate {
+  readonly seq: number
+  readonly event: SessionEvent<'tool/result'>
+}
+
+/** Deterministic head/middle/tail pruning for current tool-result surface nodes. */
+export class ToolResultPruneService extends Service {
+  static Config: z<ToolResultPruneConfig> = z.object({
+    thresholdChars: z.number().step(1).min(1).default(DEFAULTS.thresholdChars),
+    headChars: z.number().step(1).min(0).default(DEFAULTS.headChars),
+    tailChars: z.number().step(1).min(0).default(DEFAULTS.tailChars),
+  })
+
+  /** Resolved and immutable character budgets. */
+  readonly config: ResolvedConfig
+
+  constructor(ctx: Context, config: ToolResultPruneConfig = {}) {
+    super(ctx, 'toolResultPrune')
+    this.config = resolveConfig(config)
+  }
+
+  /**
+   * Measure text content in Unicode code points; non-text blocks cost zero.
+   * @param blocks - tool-result content to measure.
+   * @returns total Unicode code points across text blocks.
+   */
+  measureContent(blocks: readonly ContentBlock[]): number {
+    let chars = 0
+    for (const block of blocks) {
+      if (block.type === 'text') chars += codePointLength(block.text)
+    }
+    return chars
+  }
+
+  /**
+   * Replace an over-budget text middle while retaining rich-block order.
+   * Text slicing is by Unicode code point, not UTF-16 code unit, so a retained
+   * boundary cannot split a surrogate pair. Grapheme clusters may still split.
+   * @param blocks - original tool-result content.
+   * @returns pruned content, or `null` when the text is within budget.
+   */
+  pruneContent(blocks: readonly ContentBlock[]): ContentBlock[] | null {
+    const totalChars = this.measureContent(blocks)
+    if (totalChars <= this.config.thresholdChars) return null
+
+    const removedStart = this.config.headChars
+    const removedEnd = totalChars - this.config.tailChars
+    const pruned: ContentBlock[] = []
+    let consumed = 0
+    let markerInserted = false
+
+    for (const block of blocks) {
+      if (block.type !== 'text') {
+        pruned.push(block)
+        continue
+      }
+
+      const points = Array.from(block.text)
+      const blockStart = consumed
+      const blockEnd = blockStart + points.length
+      const headEnd = Math.min(points.length, Math.max(0, removedStart - blockStart))
+      const tailStart = Math.min(points.length, Math.max(0, removedEnd - blockStart))
+      const intersectsRemoved = blockStart < removedEnd && blockEnd > removedStart
+      const marker = intersectsRemoved && !markerInserted ? PRUNE_MARKER : ''
+      if (marker.length > 0) markerInserted = true
+      const text = points.slice(0, headEnd).join('')
+        + marker
+        + points.slice(tailStart).join('')
+      if (text.length > 0) pruned.push({ ...block, text })
+      consumed = blockEnd
+    }
+
+    /* v8 ignore next -- totalChars > threshold and valid budgets guarantee a removed text span. */
+    if (!markerInserted) throw new Error('tool-result prune: failed to locate the removed text span')
+    const charsAfter = this.measureContent(pruned)
+    /* v8 ignore next -- config validation fixes the emitted head + marker + tail budget. */
+    if (charsAfter > this.config.thresholdChars || charsAfter >= totalChars) {
+      throw new Error('tool-result prune: replacement must be smaller and within threshold')
+    }
+    return pruned
+  }
+
+  /**
+   * Prune every over-budget tool result from one stable current-surface snapshot.
+   * Each replacement preserves the complete event data except for `content`,
+   * and points at the shadowed node for durable provenance and replay.
+   * @param session - session whose current surface is rewritten.
+   * @returns landed replacements and aggregate Unicode-code-point savings.
+   * @throws when the session rejects a replacement; replacements committed
+   * earlier in the pass remain durable.
+   */
+  pruneSession(session: Session): PruneResult {
+    const candidates: SnapshotCandidate[] = []
+    for (const seq of [...session.surface.nodes]) {
+      const event = session.events[seq]
+      /* v8 ignore next -- surface seqs are validated contiguous log references. */
+      if (event?.type === 'tool/result') candidates.push({ seq, event })
+    }
+
+    const pruned: PrunedEntry[] = []
+    let charsRemoved = 0
+    for (const { seq, event } of candidates) {
+      const content = this.pruneContent(event.data.content)
+      if (content === null) continue
+      const charsBefore = this.measureContent(event.data.content)
+      const charsAfter = this.measureContent(content)
+      const replacement = session.append('tool/result', {
+        ...event.data,
+        content,
+      }, {
+        surfaceOp: { op: 'replace', start: seq, end: seq },
+        sourceEventSeqs: [seq],
+      })
+      pruned.push({
+        originalSeq: seq,
+        replacementSeq: replacement.seq,
+        callId: event.data.callId,
+        charsBefore,
+        charsAfter,
+      })
+      charsRemoved += charsBefore - charsAfter
+    }
+    return { pruned, charsRemoved }
+  }
+}
+
+export default ToolResultPruneService

packages/compact/compact-tool-result-prune/src/types.ts

@@ -0,0 +1,40 @@
+import type { CallId } from '@deepseek-ai/dsh-llm'
+
+/** Character-budget policy for deterministic tool-result pruning. */
+export interface ToolResultPruneConfig {
+  /** Prune when total text exceeds this many Unicode code points. Defaults to `8192`. */
+  thresholdChars?: number
+  /** Maximum leading Unicode code points retained. Defaults to `4096`. */
+  headChars?: number
+  /** Maximum trailing Unicode code points retained. Defaults to `1024`. */
+  tailChars?: number
+}
+
+/** Validated, detached, deeply immutable pruning configuration. */
+export interface ResolvedConfig {
+  readonly thresholdChars: number
+  readonly headChars: number
+  readonly tailChars: number
+}
+
+/** Provenance and size accounting for one landed surface replacement. */
+export interface PrunedEntry {
+  /** Full-fidelity tool-result event shadowed by the replacement. */
+  readonly originalSeq: number
+  /** Newly appended pruned tool-result event. */
+  readonly replacementSeq: number
+  /** Tool call shared by the original and replacement. */
+  readonly callId: CallId
+  /** Original text size in Unicode code points. */
+  readonly charsBefore: number
+  /** Replacement text size in Unicode code points. */
+  readonly charsAfter: number
+}
+
+/** Aggregate outcome of one stable-surface pruning pass. */
+export interface PruneResult {
+  /** Replacements in the snapshotted surface order. */
+  readonly pruned: readonly PrunedEntry[]
+  /** Total Unicode code points removed across replacements. */
+  readonly charsRemoved: number
+}

packages/compact/compact-tool-result-prune/tests/loader-composition.spec.ts

@@ -0,0 +1,67 @@
+import { mkdtemp, rm, writeFile } from 'node:fs/promises'
+import { tmpdir } from 'node:os'
+import { join } from 'node:path'
+import { pathToFileURL } from 'node:url'
+import { afterEach, describe, expect, it } from 'vitest'
+import { Context } from 'cordis'
+import Loader from '@cordisjs/plugin-loader'
+import Include from '@cordisjs/plugin-include'
+import ToolResultPruneService from '@deepseek-ai/dsh-compact-tool-result-prune'
+
+let root: string | undefined
+let context: Context | undefined
+
+afterEach(async () => {
+  await context?.fiber.dispose()
+  context = undefined
+  if (root !== undefined) await rm(root, { recursive: true, force: true })
+  root = undefined
+})
+
+describe('compact-tool-result-prune real Loader composition', () => {
+  it('loads and resolves the flat YAML plugin shape', async () => {
+    root = await mkdtemp(join(tmpdir(), 'dsh-compact-tool-result-prune-loader-'))
+    const configPath = join(root, 'cordis.yml')
+    await writeFile(configPath, [
+      "- name: '@deepseek-ai/dsh-compact-tool-result-prune'",
+      '  config:',
+      '    thresholdChars: 100',
+      '    headChars: 20',
+      '    tailChars: 10',
+      '',
+    ].join('\n'))
+
+    context = new Context()
+    context.baseUrl = pathToFileURL(root).href + '/'
+    await context.plugin(Loader)
+    context.loader.builtins.include = Include
+    context.loader.internal = {
+      version: 'v2',
+      async import(specifier: string) {
+        if (specifier !== '@deepseek-ai/dsh-compact-tool-result-prune') {
+          throw new Error(`unexpected Loader import: ${specifier}`)
+        }
+        return ToolResultPruneService
+      },
+    } as unknown as NonNullable<typeof context.loader.internal>
+    await context.loader.create({
+      name: 'cordis:include',
+      config: { path: pathToFileURL(configPath).href },
+    })
+    await context.loader.await()
+
+    expect(context.get('toolResultPrune')).toBeInstanceOf(ToolResultPruneService)
+    expect(context.toolResultPrune.config).toEqual({
+      thresholdChars: 100,
+      headChars: 20,
+      tailChars: 10,
+    })
+  })
+
+  it('rejects stale config after plugin schema normalization', async () => {
+    context = new Context()
+    await expect(context.plugin(ToolResultPruneService, {
+      maxChars: 100,
+    } as never)).rejects.toThrow(/unknown key "maxChars"/)
+  })
+})

packages/compact/compact-tool-result-prune/tests/tool-result-prune.spec.ts

@@ -0,0 +1,239 @@
+import { describe, expect, it } from 'vitest'
+import { Context } from 'cordis'
+import { CallId } from '@deepseek-ai/dsh-llm'
+import type { ContentBlock } from '@deepseek-ai/dsh-llm'
+import SessionStore, { Session, SessionId } from '@deepseek-ai/dsh-session'
+import type { SurfaceEvent } from '@deepseek-ai/dsh-session'
+import * as Invariants from '@deepseek-ai/dsh-invariants'
+import ToolResultPruneService, {
+  codePointLength,
+  DEFAULTS,
+  PRUNE_MARKER,
+  resolveConfig,
+} from '@deepseek-ai/dsh-compact-tool-result-prune'
+import type { ToolResultPruneConfig } from '@deepseek-ai/dsh-compact-tool-result-prune'
+
+const MODEL = 'test-model'
+const SMALL: ToolResultPruneConfig = {
+  thresholdChars: 50,
+  headChars: 4,
+  tailChars: 3,
+}
+
+function service(config: ToolResultPruneConfig = SMALL): ToolResultPruneService {
+  return new ToolResultPruneService(new Context(), config)
+}
+
+function appendToolStep(
+  session: Session,
+  turn: number,
+  call: string,
+  content: ContentBlock[],
+  extra: Record<string, unknown> = {},
+): number {
+  const callId = CallId(call)
+  session.append('turn/start', {
+    turn,
+    trigger: { kind: 'message', source: { kind: 'user' } },
+  })
+  session.append('step/start', { turn, step: 1 })
+  session.append('assistant/message', {
+    turn,
+    step: 1,
+    content: [{ type: 'tool-call', id: callId, name: 'bash', arguments: '{}' }],
+    provenance: { provider: MODEL, model: MODEL },
+  }, { surfaceOp: 'append' })
+  session.append('tool/call', { turn, step: 1, callId, name: 'bash', arguments: '{}' })
+  const result = session.append('tool/result', {
+    turn,
+    step: 1,
+    callId,
+    content,
+    isError: false,
+    ...extra,
+  }, { surfaceOp: 'append' })
+  session.append('step/end', { turn, step: 1 })
+  session.append('turn/end', { turn, reason: { kind: 'completed' } })
+  return result.seq
+}
+
+describe('tool-result pruning configuration', () => {
+  it('resolves detached immutable defaults and partial overrides', () => {
+    const raw = { thresholdChars: 100, headChars: 20, tailChars: 10 }
+    const resolved = resolveConfig(raw)
+    raw.headChars = 1
+    expect(resolved).toEqual({ thresholdChars: 100, headChars: 20, tailChars: 10 })
+    expect(Object.isFrozen(resolved)).toBe(true)
+    expect(DEFAULTS).toEqual({ thresholdChars: 8192, headChars: 4096, tailChars: 1024 })
+    expect(Object.isFrozen(DEFAULTS)).toBe(true)
+  })
+
+  it('rejects stale keys, invalid scalars, and an output budget above threshold', () => {
+    const bad = [
+      [{ thresholdChars: 0 }, /thresholdChars .* positive integer/],
+      [{ headChars: -1 }, /headChars .* non-negative integer/],
+      [{ tailChars: 1.5 }, /tailChars .* non-negative integer/],
+      [{ thresholdChars: 50, headChars: 20, tailChars: 20 }, /headChars \+ marker \+ tailChars/],
+      [{ threshold: 10 }, /unknown key "threshold"/],
+    ] as Array<[unknown, RegExp]>
+    for (const [config, pattern] of bad) {
+      expect(() => resolveConfig(config as ToolResultPruneConfig)).toThrow(pattern)
+    }
+  })
+})
+
+describe('ToolResultPruneService content transform', () => {
+  it('measures text code points only and skips content within threshold', () => {
+    const prune = service()
+    const blocks = [
+      { type: 'text', text: 'a😀b' },
+      { type: 'reasoning', text: 'not measured' },
+    ] satisfies ContentBlock[]
+    expect(prune.measureContent(blocks)).toBe(3)
+    expect(prune.pruneContent(blocks)).toBeNull()
+    expect(codePointLength('a😀b')).toBe(3)
+  })
+
+  it('keeps configured head and tail without splitting surrogate pairs', () => {
+    const prune = service()
+    const result = prune.pruneContent([{ type: 'text', text: '😀'.repeat(60) }])
+    expect(result).toEqual([{
+      type: 'text',
+      text: `${'😀'.repeat(4)}${PRUNE_MARKER}${'😀'.repeat(3)}`,
+    }])
+    expect(prune.measureContent(result!)).toBeLessThanOrEqual(50)
+    expect(result![0]).toMatchObject({ type: 'text' })
+    expect((result![0] as { text: string }).text).not.toContain('\uFFFD')
+  })
+
+  it('preserves non-text blocks and their relative ordering across removed text', () => {
+    const prune = service()
+    const reasoning: ContentBlock = { type: 'reasoning', text: 'private-rich-block' }
+    const call: ContentBlock = {
+      type: 'tool-call',
+      id: CallId('nested'),
+      name: 'nested',
+      arguments: '{}',
+    }
+    const result = prune.pruneContent([
+      { type: 'text', text: 'A'.repeat(40) },
+      reasoning,
+      { type: 'text', text: 'B'.repeat(30) },
+      call,
+      { type: 'text', text: 'C'.repeat(30) },
+    ])
+    expect(result).toEqual([
+      { type: 'text', text: `AAAA${PRUNE_MARKER}` },
+      reasoning,
+      call,
+      { type: 'text', text: 'CCC' },
+    ])
+    expect(prune.measureContent(result!)).toBeLessThanOrEqual(50)
+  })
+
+  it('supports zero-sized head and tail while still shrinking', () => {
+    const prune = service({
+      thresholdChars: codePointLength(PRUNE_MARKER),
+      headChars: 0,
+      tailChars: 0,
+    })
+    const result = prune.pruneContent([{ type: 'text', text: 'x'.repeat(100) }])
+    expect(result).toEqual([{ type: 'text', text: PRUNE_MARKER }])
+    expect(prune.measureContent(result!)).toBe(prune.config.thresholdChars)
+  })
+})
+
+describe('ToolResultPruneService session transaction', () => {
+  it('prunes a stable snapshot, preserves all data, and records provenance', () => {
+    const session = new Session(SessionId('preserve'))
+    const originalSeq = appendToolStep(session, 1, 'one', [{
+      type: 'text',
+      text: 'x'.repeat(100),
+    }], {
+      isError: true,
+      error: { name: 'ExitError', code: 'EXIT_1' },
+      meta: { diff: ['a', 'b'] },
+      futureField: { nested: true },
+    })
+    session.append('turn/start', {
+      turn: 2,
+      trigger: { kind: 'message', source: { kind: 'user' } },
+    })
+
+    const result = service().pruneSession(session)
+    expect(result.pruned).toHaveLength(1)
+    expect(result.charsRemoved).toBeGreaterThan(0)
+    const entry = result.pruned[0]!
+    expect(entry).toMatchObject({ originalSeq, callId: CallId('one'), charsBefore: 100 })
+    expect(entry.charsAfter).toBeLessThanOrEqual(50)
+
+    const original = session.events[originalSeq]!
+    const replacement = session.events[entry.replacementSeq]! as SurfaceEvent
+    expect(original).toMatchObject({
+      type: 'tool/result',
+      data: { content: [{ type: 'text', text: 'x'.repeat(100) }] },
+    })
+    expect(replacement).toMatchObject({
+      type: 'tool/result',
+      data: {
+        turn: 1,
+        step: 1,
+        callId: CallId('one'),
+        isError: true,
+        error: { name: 'ExitError', code: 'EXIT_1' },
+        meta: { diff: ['a', 'b'] },
+        futureField: { nested: true },
+      },
+      surfaceOp: { op: 'replace', start: originalSeq, end: originalSeq },
+      sourceEventSeqs: [originalSeq],
+    })
+    expect(session.surface.nodes).not.toContain(originalSeq)
+  })
+
+  it('prunes multiple results, skips short ones, and converges in one pass', () => {
+    const session = new Session(SessionId('multiple'))
+    appendToolStep(session, 1, 'a', [{ type: 'text', text: 'A'.repeat(100) }])
+    appendToolStep(session, 2, 'b', [{ type: 'text', text: 'short' }])
+    appendToolStep(session, 3, 'c', [{ type: 'text', text: 'C'.repeat(80) }])
+    session.append('turn/start', {
+      turn: 4,
+      trigger: { kind: 'message', source: { kind: 'user' } },
+    })
+    const prune = service()
+    const first = prune.pruneSession(session)
+    const second = prune.pruneSession(session)
+    expect(first.pruned.map(entry => entry.callId)).toEqual([CallId('a'), CallId('c')])
+    expect(first.charsRemoved).toBe(
+      first.pruned.reduce((sum, entry) => sum + entry.charsBefore - entry.charsAfter, 0),
+    )
+    expect(second).toEqual({ pruned: [], charsRemoved: 0 })
+  })
+
+  it('replays to the identical pruned model messages', () => {
+    const session = new Session(SessionId('replay'))
+    appendToolStep(session, 1, 'a', [{ type: 'text', text: 'A'.repeat(100) }])
+    session.append('turn/start', {
+      turn: 2,
+      trigger: { kind: 'message', source: { kind: 'user' } },
+    })
+    service().pruneSession(session)
+    const replay = new Session(session.id, [...session.events])
+    expect(replay.deriveMessages()).toEqual(session.deriveMessages())
+    expect(replay.surface.replaceGeneration).toBe(session.surface.replaceGeneration)
+  })
+
+  it('runs under real invariants between closed steps but not outside a turn', async () => {
+    const ctx = new Context()
+    await ctx.plugin(SessionStore)
+    await ctx.plugin(Invariants)
+    const prune = new ToolResultPruneService(ctx, SMALL)
+    const session = ctx.sessions.create(SessionId('invariants'))
+    appendToolStep(session, 1, 'a', [{ type: 'text', text: 'A'.repeat(100) }])
+    expect(() => prune.pruneSession(session)).toThrow(/outside any open turn/)
+    session.append('turn/start', {
+      turn: 2,
+      trigger: { kind: 'message', source: { kind: 'user' } },
+    })
+    expect(() => prune.pruneSession(session)).not.toThrow()
+  })
+})

packages/compact/compact-tool-result-prune/tsconfig.json

@@ -0,0 +1,15 @@
+{
+  "extends": "../../../tsconfig.base.json",
+  "compilerOptions": {
+    "rootDir": "src",
+    "outDir": "lib/types"
+  },
+  "include": ["src"],
+  "references": [
+    { "path": "../../../vendor/cosmokit" },
+    { "path": "../../../vendor/cordis" },
+    { "path": "../../../vendor/schemastery" },
+    { "path": "../../llm/llm" },
+    { "path": "../../core/session" }
+  ]
+}

packages/compact/compact/README.md

@@ -38,7 +38,7 @@ The private per-session cache is keyed by `session.surface.replaceGeneration` an
 1. appends `compact/start` (log-only) — acquires the lock,
 2. summarizes the range,
 3. appends `compact/summary` (log-only) — provenance: summary, range, shadowed seqs, token count, and provider/model call envelope,
-4. appends a single `user/message` with `surfaceOp: { op: 'replace', start, end }` carrying the summary — **the only surface mutation**,
+4. appends a single `user/message` with `surfaceOp: { op: 'replace', start, end }` carrying the summary — **the only surface mutation in this operation**,
 5. appends `compact/end` (log-only) — releases the lock.
 
 The surface mutation (step 4) sits **inside** the lock bracket: `compact/end` is the last event, so the lock is never released before the mutation lands. A crash between `compact/start` and `compact/end` therefore leaves a detectable orphaned lock (a `compact/start` with no matching `compact/end`) rather than a `compact/end` that falsely claims compaction finished while the surface was never shadowed.
@@ -90,5 +90,5 @@ No conversation-cache invalidation. A consumer's auxiliary request can reuse onl
 ## Known Limitations and Deferred Work
 
 - **No model-facing consumer tier yet** — `@deepseek-ai/dsh-tool-compact` (the `/compact` tool) is deferred; compaction is reachable only via direct `ctx.compact` calls or a backend's auto listener.
-- **Single-unit overflow is out of contract** — one indivisible unit (a closed tool pair or a large pasted `user/message`) alone exceeding the budget cannot be compacted.
+- **Some single-unit overflow is out of contract** — balanced summary compaction cannot split one indivisible unit. The optional pruning companion can still repair a closed tool pair when text-bearing tool-result bulk is removable; a large non-tool node or a tool unit whose non-prunable remainder is oversized cannot be compacted.
 - **An envelope that alone approaches the window is not surface-compaction work** — compaction shrinks derived history, never the system prompt, tools, or session prefix.

packages/context/workspace-context/README.md

@@ -42,7 +42,7 @@ These instructions apply to work under `packages/app`. Use them as guidance when
 
 A same-file edit starts with `Updated instructions from: <path>` and says to use the new content instead of the previously loaded content. A candidate switch additionally names the old path. When no candidate remains, the message is `Instructions removed: <path>` followed by `The previously loaded instructions from this file no longer apply.` Literal `</system-reminder>` text inside an instruction file is escaped so file content cannot close the plugin-owned frame.
 
-The core `context/message` envelope is disabled for these messages because the plugin already owns the complete `<system-reminder>` framing. This is caller-selected with `envelope: 'raw'`; ordinary injected context still receives the canonical `<context source="...">` envelope.
+The plugin owns the complete `<system-reminder>` framing, and every `context/message` (from this plugin or any other) reaches the model verbatim as a user-role message with no wrapping.
 
 ## State And Refresh
 

packages/context/workspace-context/src/index.ts

@@ -92,7 +92,6 @@ export function apply(ctx: Context, config: Config): void {
     if (update !== undefined) {
       agent.inject(update.context.content, {
         source: update.context.source,
-        envelope: update.context.envelope,
         meta: update.context.meta,
       })
       applyInstructionVersionUpdates(agent.session, update.versionUpdates, instructionVersions)

packages/context/workspace-context/src/render.ts

@@ -163,6 +163,12 @@ function buildInstructionText(
 ): string {
   const marker = markerText(maxBytes, omitted, truncated)
   const body = [marker, style.intro, ...files.map(file => style.section(file))].filter(block => block.length > 0)
+  // Caller-owned framing: the plugin bakes the complete `<system-reminder>`
+  // frame into the message content. The session surface projects context
+  // verbatim and does not wrap it, so any framing must live here in the
+  // producer's content (the pattern a future `meta`-driven renderer would
+  // generalize — see the deferred note in
+  // ../../../../.agents/notes/implemented/simplification/2026-07-20-unwrap-injected-content-envelopes.md).
   return [SYSTEM_REMINDER_OPEN, body.join('\n\n'), SYSTEM_REMINDER_CLOSE].join('\n')
 }
 

packages/context/workspace-context/src/state.ts

@@ -61,9 +61,8 @@ export interface ReconciledInstructionContext {
   versionUpdates: InstructionVersionUpdate[]
 }
 
-/** Plugin-owned raw context with required replay metadata. */
+/** Plugin-owned context with required replay metadata. */
 export interface WorkspaceHookContext extends HookContext {
-  envelope: 'raw'
   meta: JsonValue
 }
 
@@ -76,7 +75,7 @@ function workspaceContextHook(text: string, changes: WorkspaceInstructionChange[
     ...change.digest !== undefined ? { digest: change.digest } : {},
   }))
   const meta: JsonValue = { kind: 'workspace-instructions', version: 1, changes: serializedChanges }
-  return { content: [{ type: 'text', text }], source: PLUGIN_SOURCE, envelope: 'raw', meta }
+  return { content: [{ type: 'text', text }], source: PLUGIN_SOURCE, meta }
 }
 
 /**

packages/context/workspace-context/tests/workspace-context.spec.ts

@@ -173,7 +173,6 @@ function stubAgent(cwd?: string, seed: SessionEvent[] = []): Agent {
       session.append('context/message', {
         content,
         source: options?.source ?? { kind: 'user' },
-        ...options?.envelope !== undefined ? { envelope: options.envelope } : {},
         ...options?.meta !== undefined ? { meta: options.meta } : {},
       }, { surfaceOp: 'append' })
     },
@@ -202,7 +201,6 @@ function workspaceChangeContext(scope: string, digest: string): HookContext {
   return {
     content: [{ type: 'text', text: `instructions for ${scope}` }],
     source: { kind: 'plugin', plugin: 'workspace-context' },
-    envelope: 'raw',
     meta: {
       kind: 'workspace-instructions',
       version: 1,
@@ -217,7 +215,6 @@ function appendAdditionalContexts(agent: Agent, result: { additionalContexts?: H
     lastSeq = agent.session.append('context/message', {
       content: context.content,
       source: context.source,
-      ...context.envelope !== undefined ? { envelope: context.envelope } : {},
       ...context.meta !== undefined ? { meta: context.meta } : {},
     }, { surfaceOp: 'append' }).seq
   }
@@ -1695,7 +1692,6 @@ describe('dynamic nested workspace context injection', () => {
 
       expect(result.isError).toBe(false)
       expect(workspaceContextOf(result)?.source).toEqual({ kind: 'plugin', plugin: 'workspace-context' })
-      expect(workspaceContextOf(result)?.envelope).toBe('raw')
       expect(workspaceContextOf(result)?.meta).toMatchObject({
         kind: 'workspace-instructions',
         version: 1,
@@ -2461,7 +2457,6 @@ describe('dynamic nested workspace context injection', () => {
       expect(blocksText(result.content)).toBe('downstream replacement')
       expect(result.additionalContexts).toHaveLength(2)
       expect(workspaceContextOf(result)?.source).toEqual({ kind: 'plugin', plugin: 'workspace-context' })
-      expect(workspaceContextOf(result)?.envelope).toBe('raw')
       expect(workspaceContextOf(result)?.meta).toMatchObject({
         kind: 'workspace-instructions',
         changes: [{ action: 'set', scope: 'pkg', path: 'pkg/AGENTS.md' }],
@@ -2474,7 +2469,8 @@ describe('dynamic nested workspace context injection', () => {
       })
       const agent = stubAgent(root)
       appendAdditionalContexts(agent, result)
-      expect(blocksText(agent.session.deriveMessages()[1]?.content)).toContain('<context source="plugin">\ndownstream context\n</context>')
+      expect(blocksText(agent.session.deriveMessages()[1]?.content)).toContain('downstream context')
+      expect(blocksText(agent.session.deriveMessages()[1]?.content)).not.toContain('<context source=')
     } finally {
       await rm(root, { recursive: true, force: true })
       await rm(home, { recursive: true, force: true })
@@ -2807,7 +2803,6 @@ describe('workspace context pending state', () => {
     const otherWorkspaceEvent = agent.session.append('context/message', {
       content: otherContext.content,
       source: otherContext.source,
-      ...otherContext.envelope !== undefined ? { envelope: otherContext.envelope } : {},
       ...otherContext.meta !== undefined ? { meta: otherContext.meta } : {},
     }, { surfaceOp: 'append' })
     observeInstructionSessionEvent(agent.session, otherWorkspaceEvent, pending, versions)
@@ -2817,7 +2812,6 @@ describe('workspace context pending state', () => {
     const confirmed = agent.session.append('context/message', {
       content: context.content,
       source: context.source,
-      ...context.envelope !== undefined ? { envelope: context.envelope } : {},
       ...context.meta !== undefined ? { meta: context.meta } : {},
     }, { surfaceOp: 'append' })
     observeInstructionSessionEvent(agent.session, confirmed, pending, versions)

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

@@ -263,12 +263,12 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [
         jsDoc: '/**\n * List direct children of a directory in stable name order. Returns resolved\n * child targets plus cheap metadata only; never reads file contents.\n * @param target - the resolved directory target.\n * @param signal - aborts the listing.\n * @returns one entry per direct child, in stable name order.\n */',
       },
       {
-        signature: 'abstract writeText(target: FsTarget, content: string, expected?: FsWriteIntent, signal?: AbortSignal): Promise<FsWriteOutcome>',
-        jsDoc: '/**\n * Atomically create or replace UTF-8 text. `expected` guards intent and\n * staleness; omission allows unconditional overwrite.\n * @param target - the resolved target to write.\n * @param content - the full new file content.\n * @param expected - the write intent guarding the write; omit for unconditional.\n * @param signal - aborts before the atomic rename takes effect.\n * @returns the outcome, including the version the write produced.\n */',
+        signature: 'abstract writeText( target: FsTarget, content: string, expected?: FsWriteIntent, signal?: AbortSignal, sandboxMode?: SandboxMode, ): Promise<FsWriteOutcome>',
+        jsDoc: '/**\n * Atomically create or replace UTF-8 text. `expected` guards intent and\n * staleness; omission allows unconditional overwrite.\n * @param target - the resolved target to write.\n * @param content - the full new file content.\n * @param expected - the write intent guarding the write; omit for unconditional.\n * @param signal - aborts before the atomic rename takes effect.\n * @param sandboxMode - the per-call sandbox mode this write runs under; a\n *   sandboxing backend fences the write by it, the bare backend ignores it.\n *   Omit to leave the backend its own default.\n * @returns the outcome, including the version the write produced.\n */',
       },
       {
-        signature: 'abstract editText(target: FsTarget, edit: FsEditRequest, expected?: { version: FsVersion }, signal?: AbortSignal): Promise<FsEditOutcome>',
-        jsDoc: '/**\n * Atomically edit literal text. When supplied, the version guard is checked\n * before matching so stale content reports `FS_STALE_VERSION`; omission edits\n * the current content without a freshness precondition.\n * @param target - the resolved target to edit.\n * @param edit - the literal search/replace request.\n * @param expected - the version guard; omit for an unconditional edit.\n * @param signal - aborts before the atomic rename takes effect.\n * @returns the outcome, including the version the edit produced.\n */',
+        signature: 'abstract editText( target: FsTarget, edit: FsEditRequest, expected?: { version: FsVersion }, signal?: AbortSignal, sandboxMode?: SandboxMode, ): Promise<FsEditOutcome>',
+        jsDoc: '/**\n * Atomically edit literal text. When supplied, the version guard is checked\n * before matching so stale content reports `FS_STALE_VERSION`; omission edits\n * the current content without a freshness precondition.\n * @param target - the resolved target to edit.\n * @param edit - the literal search/replace request.\n * @param expected - the version guard; omit for an unconditional edit.\n * @param signal - aborts before the atomic rename takes effect.\n * @param sandboxMode - the per-call sandbox mode this edit runs under; a\n *   sandboxing backend fences the edit by it, the bare backend ignores it.\n *   Omit to leave the backend its own default.\n * @returns the outcome, including the version the edit produced.\n */',
       },
     ],
   },
@@ -368,6 +368,11 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [
       },
     ],
   },
+  {
+    key: 'sandboxPolicy',
+    summary: 'The sandbox-policy service (`ctx.sandboxPolicy`).',
+    methods: [],
+  },
   {
     key: 'sessionPersistence',
     summary: 'Durable append-only session storage.',
@@ -426,7 +431,7 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [
     methods: [
       {
         signature: 'create(id?: SessionId, options?: CreateSessionOptions): Session',
-        jsDoc: '/**\n * Create a session owned by the calling fiber: disposing that fiber stops\n * event notification and removes the session from the store. `options.seed`\n * populates the session with a copy of those events (replay/fork);\n * `options.meta` attaches creation metadata (validated absolute `cwd`,\n * `parentSession` lineage) as the immutable {@link SessionHeader} (the store\n * fills `version`/`id`/`createdAt`).\n *\n * For an agent whose session must be torn down IN ORDER with its loop (so the\n * loop\'s final flush is captured before the store attachment ends), do NOT use this\n * — fold the session lifecycle into the agent\'s own effect via\n * {@link prepare} + {@link enter} + {@link announce} (see\n * `dsh-agent-loop`\'s creation transaction).\n *\n * @param id - the session id; omitted, the store mints `session-<n>`.\n * @param options - seed events and/or creation metadata for the header.\n * @returns the live session, already entered and announced.\n * @throws if a session with `id` already exists, metadata is not a plain\n *   lossless-JSON record with valid scalar fields, or `meta.cwd` is a\n *   non-absolute path (storage backends key directories off it).\n */',
+        jsDoc: '/**\n * Create a session owned by the calling fiber: disposing that fiber stops\n * event notification and removes the session from the store. `options.seed`\n * populates the session with a copy of those events (replay/fork);\n * `options.meta` attaches creation metadata (validated absolute `cwd`, seed\n * and parent lineage, and delegation depth) as the immutable\n * {@link SessionHeader} (the store fills `version`/`id`/`createdAt`).\n *\n * For an agent whose session must be torn down IN ORDER with its loop (so the\n * loop\'s final flush is captured before the store attachment ends), do NOT use this\n * — fold the session lifecycle into the agent\'s own effect via\n * {@link prepare} + {@link enter} + {@link announce} (see\n * `dsh-agent-loop`\'s creation transaction).\n *\n * @param id - the session id; omitted, the store mints `session-<n>`.\n * @param options - seed events and/or creation metadata for the header.\n * @returns the live session, already entered and announced.\n * @throws if a session with `id` already exists, metadata is not a plain\n *   lossless-JSON record with valid scalar fields, or `meta.cwd` is a\n *   non-absolute path (storage backends key directories off it).\n */',
       },
       {
         signature: 'prepare(id?: SessionId, options?: CreateSessionOptions): Session',
@@ -586,6 +591,24 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [
       },
     ],
   },
+  {
+    key: 'toolResultPrune',
+    summary: 'Deterministic head/middle/tail pruning for current tool-result surface nodes.',
+    methods: [
+      {
+        signature: 'measureContent(blocks: readonly ContentBlock[]): number',
+        jsDoc: '/**\n * Measure text content in Unicode code points; non-text blocks cost zero.\n * @param blocks - tool-result content to measure.\n * @returns total Unicode code points across text blocks.\n */',
+      },
+      {
+        signature: 'pruneContent(blocks: readonly ContentBlock[]): ContentBlock[] | null',
+        jsDoc: '/**\n * Replace an over-budget text middle while retaining rich-block order.\n * Text slicing is by Unicode code point, not UTF-16 code unit, so a retained\n * boundary cannot split a surrogate pair. Grapheme clusters may still split.\n * @param blocks - original tool-result content.\n * @returns pruned content, or `null` when the text is within budget.\n */',
+      },
+      {
+        signature: 'pruneSession(session: Session): PruneResult',
+        jsDoc: '/**\n * Prune every over-budget tool result from one stable current-surface snapshot.\n * Each replacement preserves the complete event data except for `content`,\n * and points at the shadowed node for durable provenance and replay.\n * @param session - session whose current surface is rewritten.\n * @returns landed replacements and aggregate Unicode-code-point savings.\n * @throws when the session rejects a replacement; replacements committed\n * earlier in the pass remain durable.\n */',
+      },
+    ],
+  },
   {
     key: 'tools',
     summary: 'Tool registry and execution pipeline.',
@@ -723,8 +746,8 @@ export const EVENT_API: readonly EventApiEntry[] = [
     name: 'agent/prompt-submit',
     mode: 'waterfall',
     signature: '\'agent/prompt-submit\'(this: Scoped<Agent>, agent: Agent, content: ContentBlock[], source: MessageSource, next: () => Promise<PromptDecision>): Promise<PromptDecision>',
-    jsDoc: '/**\n * Allow, rewrite, or block one drained prompt before it becomes a user\n * message. Call `next()` for the unchanged default.\n * @param agent - the agent draining its inbox.\n * @param content - the drained message\'s blocks, as queued.\n * @param source - the message\'s resolved source.\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.\n * @mode waterfall\n */',
-    summary: 'Allow, rewrite, or block one drained prompt before it becomes a user message.',
+    jsDoc: '/**\n * Allow, rewrite, or block one claimed prompt before it becomes a user\n * message. Call `next()` for the unchanged default.\n * @param agent - the agent whose turn claimed the message.\n * @param content - the claimed message\'s blocks, as queued.\n * @param source - the message\'s resolved source.\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.\n * @mode waterfall\n */',
+    summary: 'Allow, rewrite, or block one claimed prompt before it becomes a user message.',
   },
   {
     name: 'agent/queued',
@@ -1173,13 +1196,9 @@ export const TYPE_API: readonly TypeApiEntry[] = [
     name: 'ContentBlockType',
     declaration: 'export type ContentBlockType = keyof ContentBlockMap;',
   },
-  {
-    name: 'ContextEnvelope',
-    declaration: 'export type ContextEnvelope = \'context\' | \'raw\';',
-  },
   {
     name: 'CreateAgentOptions',
-    declaration: 'export interface CreateAgentOptions {\n    readonly sessionId: SessionId;\n    readonly meta?: {\n        readonly cwd?: string;\n        readonly parentSession?: SessionId;\n        readonly seedLength?: number;\n    };\n    readonly seed?: readonly SessionEvent[];\n    readonly agentOptions?: AgentOptions;\n    readonly signal?: AbortSignal;\n    readonly setup?: (agentCtx: Context) => Promise<void> | void;\n}',
+    declaration: 'export interface CreateAgentOptions {\n    readonly sessionId: SessionId;\n    readonly meta?: {\n        readonly cwd?: string;\n        readonly parentSession?: SessionId;\n        readonly seedLength?: number;\n        readonly delegationDepth?: number;\n    };\n    readonly seed?: readonly SessionEvent[];\n    readonly agentOptions?: AgentOptions;\n    readonly signal?: AbortSignal;\n    readonly setup?: (agentCtx: Context) => Promise<void> | void;\n}',
   },
   {
     name: 'CreateGoalRequest',
@@ -1187,7 +1206,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [
   },
   {
     name: 'CreateSessionOptions',
-    declaration: 'export interface CreateSessionOptions {\n    readonly seed?: readonly SessionEvent[];\n    readonly meta?: {\n        readonly cwd?: string;\n        readonly parentSession?: SessionId;\n        readonly createdAt?: number;\n        readonly seedLength?: number;\n    };\n}',
+    declaration: 'export interface CreateSessionOptions {\n    readonly seed?: readonly SessionEvent[];\n    readonly meta?: {\n        readonly cwd?: string;\n        readonly parentSession?: SessionId;\n        readonly createdAt?: number;\n        readonly seedLength?: number;\n        readonly delegationDepth?: number;\n    };\n}',
   },
   {
     name: 'DiffCallView',
@@ -1311,11 +1330,11 @@ export const TYPE_API: readonly TypeApiEntry[] = [
   },
   {
     name: 'HookContext',
-    declaration: 'export interface HookContext {\n    content: ContentBlock[];\n    source: MessageSource;\n    envelope?: ContextEnvelope;\n    meta?: JsonValue;\n}',
+    declaration: 'export interface HookContext {\n    content: ContentBlock[];\n    source: MessageSource;\n    meta?: JsonValue;\n}',
   },
   {
     name: 'InjectOptions',
-    declaration: 'export interface InjectOptions extends SendOptions {\n    envelope?: ContextEnvelope;\n    meta?: JsonValue;\n}',
+    declaration: 'export interface InjectOptions extends SendOptions {\n    meta?: JsonValue;\n}',
   },
   {
     name: 'JsonValue',
@@ -1361,6 +1380,14 @@ export const TYPE_API: readonly TypeApiEntry[] = [
     name: 'PromptSection',
     declaration: 'export interface PromptSection {\n    readonly name: string;\n    readonly order: number;\n    readonly text: string | ((context: AssembleContext) => string);\n}',
   },
+  {
+    name: 'PrunedEntry',
+    declaration: 'export interface PrunedEntry {\n    readonly originalSeq: number;\n    readonly replacementSeq: number;\n    readonly callId: CallId;\n    readonly charsBefore: number;\n    readonly charsAfter: number;\n}',
+  },
+  {
+    name: 'PruneResult',
+    declaration: 'export interface PruneResult {\n    readonly pruned: readonly PrunedEntry[];\n    readonly charsRemoved: number;\n}',
+  },
   {
     name: 'ReasoningBlock',
     declaration: 'export interface ReasoningBlock {\n    type: \'reasoning\';\n    text: string;\n}',
@@ -1399,7 +1426,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [
   },
   {
     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        envelope?: ContextEnvelope;\n        meta?: JsonValue;\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        provenance: AssistantProvenance;\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; /* …truncated — full shape in source */',
+    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        meta?: JsonValue;\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        provenance: AssistantProvenance;\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         /* …truncated — full shape in source */',
   },
   {
     name: 'SessionEventReadRequest',
@@ -1435,7 +1462,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [
   },
   {
     name: 'SessionHeader',
-    declaration: 'export interface SessionHeader {\n    readonly version: number;\n    readonly id: SessionId;\n    readonly createdAt: number;\n    readonly cwd?: string;\n    readonly parentSession?: SessionId;\n    readonly seedLength?: number;\n}',
+    declaration: 'export interface SessionHeader {\n    readonly version: number;\n    readonly id: SessionId;\n    readonly createdAt: number;\n    readonly cwd?: string;\n    readonly parentSession?: SessionId;\n    readonly seedLength?: number;\n    readonly delegationDepth?: number;\n}',
   },
   {
     name: 'SessionId',

packages/core/agent-loop/README.md

@@ -46,7 +46,9 @@ Configured agents start automatically. A model call requires both `provider` and
 
 ### Internal concrete driver
 
-The concrete `Agent` class, its `Inbox`, `runLoop`, and instance-bound publication/start controls are package-internal. The package root exports only the plugin/service/config contract, and the package exports map exposes no `./src/*` escape hatch; lifecycle owners create agents through `ctx.agents` rather than naming, constructing, or starting driver internals. The concrete `send()`, running `steer()`, and open-turn `inject()` materialize content plus resolved source once as detached, deeply frozen lossless JSON; malformed data throws before enqueue or append. An injection that arrives while the current step executes assistant tool calls stays in a FIFO until the batch settles; successful batches place it after the complete result batch, and interrupted batches drain it before the turn closes. One prepared session can be claimed by only one concrete driver, and everything observable happens through session events and the `agent/*` event taxonomy.
+The concrete `Agent` class, its `Inbox`, `runLoop`, and instance-bound publication/start controls are package-internal. The package root exports only the plugin/service/config contract, and the package exports map exposes no `./src/*` escape hatch; lifecycle owners create agents through `ctx.agents` rather than naming, constructing, or starting driver internals. One prepared session can be claimed by only one concrete driver, and everything observable happens through session events and the `agent/*` event taxonomy.
+
+Each concrete `send()` materializes content plus resolved source once as a detached, deeply frozen lossless-JSON FIFO item. If claimed, it is the sole ordinary message in its turn; a successor waits for the preceding ordinary turn's checkpoint to settle, while cancellation, disposal, or a pre-start failure may drop it without a turn. Running `steer()` enters the steering FIFO: an open turn records it at the next steering checkpoint before a request or continuation decision, but policy can still stop before another step; steering left after turn close and its checkpoint becomes later queued input unless terminal turn policy, cancellation, or disposal discards it. Open-turn `inject()` uses the same accepted-value boundary but defers in a FIFO while the current step executes assistant tool calls; successful batches place it after all results, and interrupted batches drain it before turn close. Malformed data throws before enqueue or append.
 
 ### Loop lifecycle (`loop.ts`)
 

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

@@ -252,7 +252,6 @@ export class ReactLoopAgent implements Agent {
     const context = {
       content,
       source,
-      ...options?.envelope !== undefined ? { envelope: options.envelope } : {},
       ...options?.meta !== undefined ? { meta: options.meta } : {},
     }
     if (isTurnOpen(this.session)) {
@@ -403,7 +402,7 @@ export class ReactLoopAgent implements Agent {
       cancelReason: () => this.cancelReason,
       clearCancel: () => { this.cancelRequested = false },
       withToolBatch: run => this.withToolBatch(run),
-      // Pre-step cancellation re-parks without emitting a status transition.
+      // Pre-start cancellation settles queued-work waiters before publishing idle.
       settleIdle: () => { this.settleIdleWaiters() },
     }))
   }

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

@@ -15,7 +15,7 @@ export interface InboxMessage {
 }
 
 /**
- * Per-agent inbox: a queued FIFO (drained at turn start) and a steering FIFO
+ * Per-agent inbox: a queued FIFO (dequeued once per turn start) and a steering FIFO
  * (drained between steps of a running turn). Purely an in-memory mechanism of
  * the loop — the public surface is `Agent.send()` / `Agent.steer()`.
  */
@@ -54,11 +54,11 @@ export class Inbox {
   }
 
   /**
-   * Drain all queued messages (turn start).
-   * @returns the drained messages in arrival order; the queued FIFO is left empty.
+   * Remove the oldest queued message for one turn start.
+   * @returns the oldest message, or `undefined` when the queued FIFO is empty.
    */
-  drainQueued(): InboxMessage[] {
-    return this.queuedMessages.splice(0)
+  dequeueQueued(): InboxMessage | undefined {
+    return this.queuedMessages.shift()
   }
 
   /**
@@ -72,7 +72,7 @@ export class Inbox {
   /**
    * Discard all pending messages (queued + steering) without delivering them —
    * used by `cancel()`, which drops un-started work rather than draining it into
-   * a turn. Unlike `drainQueued`/`drainSteering`, the messages are thrown away.
+   * a turn. Unlike `dequeueQueued`/`drainSteering`, the messages are thrown away.
    */
   clear(): void {
     this.queuedMessages.length = 0

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

@@ -620,12 +620,7 @@ export class AgentLoop extends Service implements AgentFactory {
       transaction.assertActive()
       const session = this.runtime.ctx.sessions.prepare(options.resumeSessionId, {
         seed: loaded.events,
-        meta: {
-          createdAt: loaded.meta.createdAt,
-          ...loaded.meta.cwd === undefined ? {} : { cwd: loaded.meta.cwd },
-          ...loaded.meta.parentSession === undefined ? {} : { parentSession: loaded.meta.parentSession },
-          ...loaded.meta.seedLength === undefined ? {} : { seedLength: loaded.meta.seedLength },
-        },
+        meta: loaded.meta,
       })
       const agent = transaction.prepare(agentOptions, session, this.maxParallelToolCalls)
       await transaction.waitFor(options.setup?.(agent.ctx))

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

@@ -91,16 +91,16 @@ export interface LoopHandle {
   cancelReason(): string
   /** Clear the cancel marker (called once per iteration after the turn returns). */
   clearCancel(): void
-  /** Settle idle waiters when pre-running cancellation skips a turn, without emitting `agent/status`. */
+  /** Settle idle waiters before pre-running cancellation publishes idle. */
   settleIdle(): void
   /** Run an active tool-call batch, accepting post-tool context into the FIFO drained before settlement. */
   readonly withToolBatch: <T>(run: (acceptContext: (context: HookContext) => void) => Promise<T>) => Promise<T>
 }
 
 /**
- * Drive queued batches as durable turns until disposal. Plugin failures end the
- * current turn without terminating the driver. The caller establishes the
- * `ctx.agents.withInitiator()` boundary before entry; package-private
+ * Drive queued messages as independent durable turns until disposal. Plugin
+ * failures end the current turn without terminating the driver. The caller
+ * establishes the `ctx.agents.withInitiator()` boundary before entry; package-private
  * orchestration recovers that exact Agent and captures its Session locally.
  * @param ctx - the plugin context the loop reaches its initiating Agent,
  * events (agent/…, session/flush), and services (systemPrompt, llm, tools)
@@ -118,20 +118,35 @@ export async function runLoop(ctx: Context, handle: LoopHandle): Promise<void> {
   const events = agentEvents(ctx, agent)
 
   while (!handle.isDisposed()) {
-    await handle.inbox.waitForQueued(handle.disposed)
-    if (handle.isDisposed()) break
-
-    // Cancellation between wake and `running` skips only the cancelled work;
-    // a replacement prompt still runs and owns the eventual idle transition.
+    // An idle listener can enqueue and cancel replacement work before the next
+    // wait is installed. Consume that empty marker before parking the driver.
     if (handle.isCancelled()) {
       handle.clearCancel()
       if (!handle.inbox.hasQueued) {
         handle.settleIdle()
+        handle.setStatus('idle')
+        continue
+      }
+    }
+
+    await handle.inbox.waitForQueued(handle.disposed)
+    if (handle.isDisposed()) break
+
+    // Cancellation between wake and `running` skips only the cancelled work;
+    // a replacement prompt still runs before the eventual idle transition.
+    if (handle.isCancelled()) {
+      handle.clearCancel()
+      if (!handle.inbox.hasQueued) {
+        // Settle before publishing idle: the already-idle path has no status
+        // transition, while an idle listener can register waiters for new work.
+        handle.settleIdle()
+        handle.setStatus('idle')
         continue
       }
     }
 
     handle.setStatus('running')
+    if (handle.isDisposed()) break
 
     // A synchronous `running` listener can cancel before `runTurn`; balance the
     // status only when no replacement prompt was queued by that listener.
@@ -182,12 +197,11 @@ async function runTurn(
     return messages.length > 0
   }
 
-  // Drain before opening the turn, but append only after `turn/start`.
-  const queued = handle.inbox.drainQueued()
-  const first = queued[0]
+  // Claim one queued message before opening its turn, but append it only after `turn/start`.
+  const message = handle.inbox.dequeueQueued()
   /* v8 ignore next 3 -- invariant guard: runLoop only calls runTurn when hasQueued */
-  if (!first) throw new Error('runTurn invariant violated: no queued message at turn start')
-  const trigger: TurnTrigger = { kind: 'message', source: first.source }
+  if (!message) throw new Error('runTurn invariant violated: no queued message at turn start')
+  const trigger: TurnTrigger = { kind: 'message', source: message.source }
 
   let reason: TurnEndReason = { kind: 'completed' }
   let step = 0
@@ -226,56 +240,36 @@ async function runTurn(
     // matter what throws below; the catch + closeTurn guarantee it. A pre-commit
     // veto leaves no turn/start in the log and therefore owes no turn/end.
     session.append('turn/start', { turn, trigger })
-    // Each drained queued message runs the `agent/prompt-submit` waterfall before
-    // it becomes a `user/message` — a hook can rewrite the prompt or block it.
+    // The claimed message runs the `agent/prompt-submit` waterfall before it
+    // becomes a `user/message` — a hook can rewrite the prompt or block it.
     // Recorded INSIDE the turn (after turn/start) so every event is turn-enclosed;
     // turn/end is now owed, so a throwing prompt-submit listener (the waterfall
     // throws) is caught below and the turn still closes.
-    let anyAllowed = false
-    // Seeded with a floor (only observable if the batch were empty, which
-    // runTurn never allows — it is called with ≥1 queued message); each `block`
-    // decision carries a required `reason` and overwrites it, so a fully-blocked
-    // batch always reports the last vetoing reason.
-    let lastBlockReason = 'prompt blocked by hook'
-    for (const message of queued) {
-      const decision = await events.waterfall(
-        'agent/prompt-submit', message.content, message.source,
-        () => Promise.resolve<PromptDecision>({ kind: 'allow' }),
-      )
-      if (decision.kind === 'block') {
-        lastBlockReason = decision.reason
-        // Record the veto durably: `PromptDecision.reason` is the durable record
-        // of why a prompt was blocked, but a fully-blocked batch's `rejected`
-        // turn/end only preserves the LAST reason, and a MIXED batch (this prompt
-        // blocked, another allowed) does not end `rejected` at all — so without
-        // this append a blocked prompt would vanish from the log whenever any
-        // sibling prompt is allowed. `prompt/blocked` sits in the open turn in
-        // place of the `user/message` this prompt would have become.
-        session.append('prompt/blocked', { content: message.content, source: message.source, reason: decision.reason })
-        continue
-      }
-      anyAllowed = true
+    const promptDecision = await events.waterfall(
+      'agent/prompt-submit', message.content, message.source,
+      () => Promise.resolve<PromptDecision>({ kind: 'allow' }),
+    )
+    if (promptDecision.kind === 'block') {
+      session.append('prompt/blocked', { content: message.content, source: message.source, reason: promptDecision.reason })
+      reason = { kind: 'rejected', reason: promptDecision.reason }
+    } else {
       // `allow.content` REPLACES the prompt bytes (a rewrite); absent keeps them.
-      const content = decision.content ?? message.content
+      const content = promptDecision.content ?? message.content
       session.append('user/message', { content, source: message.source }, { surfaceOp: 'append' })
       // Every `allow.additionalContexts` entry is a separate context/message the
       // next request also sees. The turn is open, so inject() appends each one
-      // into THIS turn without flattening provenance, framing, or metadata.
-      for (const context of decision.additionalContexts ?? []) {
+      // into THIS turn without flattening provenance or metadata.
+      for (const context of promptDecision.additionalContexts ?? []) {
         agent.inject(context.content, {
           source: context.source,
-          ...context.envelope !== undefined ? { envelope: context.envelope } : {},
           ...context.meta !== undefined ? { meta: context.meta } : {},
         })
       }
     }
 
     while (true) {
-      // A fully blocked batch closes its zero-step turn as rejected.
-      if (!anyAllowed) {
-        reason = { kind: 'rejected', reason: lastBlockReason }
-        break
-      }
+      // A blocked prompt closes its zero-step turn as rejected.
+      if (promptDecision.kind === 'block') break
       step += 1
 
       // Steering from the previous round's continuation listeners joins before

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

@@ -106,7 +106,8 @@ describe('Agent.cancel()', () => {
 
     // send() queues synchronously (status still idle, loop microtask not yet
     // resumed). Cancel in that pre-step window: the queued turn must not run.
-    send(agent, 'drop me')
+    send(agent, 'drop me first')
+    send(agent, 'drop me second')
     agent.cancel('pre-step')
 
     // Give the loop a chance to wake and process the cancel.
@@ -118,6 +119,35 @@ describe('Agent.cancel()', () => {
     expect(agent.status).toBe('idle')
   })
 
+  it('disposal from the running notification drops queued work before turn start', async () => {
+    const adapter = new MockAdapter([textResponse('should not run')])
+    const ctx = await harness(adapter)
+    const handle = await ctx.agents.create({
+      sessionId: SessionId('dispose-running-session'),
+      agentOptions: { provider: 'mock', model: 'mock' },
+    })
+    const agent = handle.agent
+
+    const running = Promise.withResolvers<undefined>()
+    let disposalDone: Promise<void> | undefined
+    ctx.on('agent/status', (subject, status) => {
+      if (subject !== agent || status !== 'running') return
+      disposalDone = handle.dispose()
+      running.resolve(undefined)
+    })
+
+    send(agent, 'drop before claim')
+    await running.promise
+    if (disposalDone === undefined) throw new Error('running listener did not start disposal')
+    await disposalDone
+    await driverDone(agent)
+
+    expect(agent.status).toBe('disposed')
+    expect(agent.session.events.some(event => event.type === 'turn/start')).toBe(false)
+    expect(userTexts(agent)).toEqual([])
+    expect(adapter.requests).toHaveLength(0)
+  })
+
   it('a whenIdle() waiter registered BEFORE a pre-step cancel resolves (F1 hang guard)', async () => {
     const adapter = new MockAdapter([textResponse('x')])
     const ctx = await harness(adapter)
@@ -137,7 +167,162 @@ describe('Agent.cancel()', () => {
     expect(agent.status).toBe('idle')
   })
 
-  it('cancel() mid-step aborts the in-flight model call; the turn ends aborted', async () => {
+  it('cancel() between consecutive turns restores idle and leaves idle steer usable', async () => {
+    const adapter = new MockAdapter([textResponse('first reply'), textResponse('steer reply')])
+    const ctx = await harness(adapter)
+    const agent = ctx.agentLoop.create(SessionId('between-turn-cancel'), { provider: 'mock', model: 'mock' })
+
+    let rejectFirstFlush = true
+    ctx.on('session/flush', (session) => {
+      if (session !== agent.session || !rejectFirstFlush) return
+      rejectFirstFlush = false
+      throw new Error('first flush failed')
+    })
+
+    const cancelled = Promise.withResolvers<undefined>()
+    ctx.on('agent/error', (subject, _turn, _step, error) => {
+      if (subject !== agent || error.message !== 'first flush failed') return
+      // The first hop runs before runLoop resumes from runTurn; the second lands
+      // before its resolved waitForQueued continuation checks cancellation.
+      queueMicrotask(() => {
+        queueMicrotask(() => {
+          agent.cancel('between turns')
+          cancelled.resolve(undefined)
+        })
+      })
+    })
+
+    const statuses: string[] = []
+    ctx.on('agent/status', (subject, status) => {
+      if (subject === agent) statuses.push(status)
+    })
+
+    send(agent, 'first')
+    send(agent, 'queued tail')
+    await cancelled.promise
+
+    expect(agent.status).toBe('idle')
+    expect(statuses).toEqual(['running', 'idle'])
+    expect(adapter.requests).toHaveLength(1)
+    expect(agent.session.events.filter(event => event.type === 'turn/start')).toHaveLength(1)
+    expect(userTexts(agent)).toEqual(['first'])
+
+    let idleResolved = false
+    void agent.whenIdle().then(() => { idleResolved = true })
+    await Promise.resolve()
+    expect(idleResolved).toBe(true)
+
+    const idle = waitForIdle(ctx, agent)
+    agent.steer([{ type: 'text', text: 'idle steer' }])
+    await idle
+
+    expect(statuses).toEqual(['running', 'idle', 'running', 'idle'])
+    expect(adapter.requests).toHaveLength(2)
+    expect(userTexts(agent)).toEqual(['first', 'idle steer'])
+  })
+
+  it('an idle-listener replacement keeps whenIdle pending until the replacement turn finishes', async () => {
+    const adapter = new MockAdapter([textResponse('first reply'), textResponse('replacement reply')])
+    const ctx = await harness(adapter)
+    const agent = ctx.agentLoop.create(SessionId('between-turn-idle-listener'), { provider: 'mock', model: 'mock' })
+
+    let rejectFirstFlush = true
+    ctx.on('session/flush', (session) => {
+      if (session !== agent.session || !rejectFirstFlush) return
+      rejectFirstFlush = false
+      throw new Error('first flush failed')
+    })
+
+    ctx.on('agent/error', (subject, _turn, _step, error) => {
+      if (subject !== agent || error.message !== 'first flush failed') return
+      queueMicrotask(() => {
+        queueMicrotask(() => { agent.cancel('between turns') })
+      })
+    })
+
+    const replacementRegistered = Promise.withResolvers<undefined>()
+    let replacementObservation: Promise<{ status: string; requests: number; turns: number }> | undefined
+    ctx.on('agent/status', (subject, status) => {
+      if (subject !== agent || status !== 'idle' || replacementObservation !== undefined) return
+      send(agent, 'replacement')
+      replacementObservation = agent.whenIdle().then(() => ({
+        status: agent.status,
+        requests: adapter.requests.length,
+        turns: agent.session.events.filter(event => event.type === 'turn/start').length,
+      }))
+      replacementRegistered.resolve(undefined)
+    })
+
+    send(agent, 'first')
+    send(agent, 'cancelled tail')
+    await replacementRegistered.promise
+    if (replacementObservation === undefined) throw new Error('idle listener did not register replacement work')
+
+    await expect(replacementObservation).resolves.toEqual({ status: 'idle', requests: 2, turns: 2 })
+    expect(userTexts(agent)).toEqual(['first', 'replacement'])
+  })
+
+  it('idle-listener cancellation settles its waiter without cancelling later work', async () => {
+    const adapter = new MockAdapter([textResponse('first reply'), textResponse('later reply')])
+    const ctx = await harness(adapter)
+    const agent = ctx.agentLoop.create(SessionId('idle-listener-cancel'), { provider: 'mock', model: 'mock' })
+
+    const replacementRegistered = Promise.withResolvers<undefined>()
+    let replacementObservation: Promise<{ status: string; requests: number; turns: number }> | undefined
+    ctx.on('agent/status', (subject, status) => {
+      if (subject !== agent || status !== 'idle' || replacementObservation !== undefined) return
+      send(agent, 'cancelled replacement')
+      replacementObservation = agent.whenIdle().then(() => ({
+        status: agent.status,
+        requests: adapter.requests.length,
+        turns: agent.session.events.filter(event => event.type === 'turn/start').length,
+      }))
+      agent.cancel('idle listener')
+      replacementRegistered.resolve(undefined)
+    })
+
+    send(agent, 'first')
+    await replacementRegistered.promise
+    if (replacementObservation === undefined) throw new Error('idle listener did not register replacement work')
+
+    await expect(Promise.race([
+      replacementObservation,
+      new Promise((_resolve, reject) => setTimeout(() => { reject(new Error('whenIdle hung after idle-listener cancel')) }, 1000)),
+    ])).resolves.toEqual({ status: 'idle', requests: 1, turns: 1 })
+
+    const idle = waitForIdle(ctx, agent)
+    send(agent, 'later')
+    await idle
+    expect(adapter.requests).toHaveLength(2)
+    expect(userTexts(agent)).toEqual(['first', 'later'])
+  })
+
+  it('replacement work queued after idle-listener cancellation still runs', async () => {
+    const adapter = new MockAdapter([textResponse('first reply'), textResponse('replacement reply')])
+    const ctx = await harness(adapter)
+    const agent = ctx.agentLoop.create(SessionId('idle-listener-post-cancel-send'), { provider: 'mock', model: 'mock' })
+
+    const replacementRegistered = Promise.withResolvers<undefined>()
+    let replacementIdle: Promise<void> | undefined
+    ctx.on('agent/status', (subject, status) => {
+      if (subject !== agent || status !== 'idle' || replacementIdle !== undefined) return
+      send(agent, 'cancelled replacement')
+      agent.cancel('idle listener')
+      send(agent, 'surviving replacement')
+      replacementIdle = agent.whenIdle()
+      replacementRegistered.resolve(undefined)
+    })
+
+    send(agent, 'first')
+    await replacementRegistered.promise
+    if (replacementIdle === undefined) throw new Error('idle listener did not register replacement work')
+    await replacementIdle
+
+    expect(adapter.requests).toHaveLength(2)
+    expect(userTexts(agent)).toEqual(['first', 'surviving replacement'])
+  })
+
+  it('cancel() mid-step aborts the active turn and drops every queued tail item', async () => {
     const adapter = new MockAdapter(['hang'])
     const ctx = await harness(adapter)
     const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
@@ -148,10 +333,14 @@ describe('Agent.cancel()', () => {
     send(agent, 'go')
     await new Promise(r => setTimeout(r, 30))
     expect(agent.status).toBe('running')
+    send(agent, 'queued tail')
     agent.cancel('mid-step')
     await waitForIdle(ctx, agent)
 
     expect(reasons).toEqual([{ kind: 'aborted', reason: 'mid-step' }])
+    expect(userTexts(agent)).toEqual(['go'])
+    expect(agent.session.events.filter(event => event.type === 'turn/start')).toHaveLength(1)
+    expect(adapter.requests).toHaveLength(1)
   })
 
   it('cancel() with no reason defaults to "cancelled" when aborting an in-flight step', async () => {

packages/core/agent-loop/tests/contract-regressions.spec.ts

@@ -632,15 +632,20 @@ describe('plugin exceptions are contained', () => {
     expect(agent.status).toBe('idle')
   })
 
-  it('a rejecting session/flush listener is reported but does not kill the agent', async () => {
+  it('a rejecting first-turn flush settles before the queued tail starts', async () => {
     const adapter = new MockAdapter([textResponse('one'), textResponse('two')])
     const ctx = await harness(adapter)
     const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
-    let rejectedOnce = false
-    ctx.on('session/flush', async () => {
-      if (!rejectedOnce) {
-        rejectedOnce = true
+    const firstFlush = Promise.withResolvers<undefined>()
+    const releaseFirstFlush = Promise.withResolvers<undefined>()
+    let flushes = 0
+    ctx.on('session/flush', async (session) => {
+      if (session !== agent.session) return
+      flushes += 1
+      if (flushes === 1) {
+        firstFlush.resolve(undefined)
+        await releaseFirstFlush.promise
         throw new Error('disk full')
       }
     })
@@ -648,18 +653,25 @@ describe('plugin exceptions are contained', () => {
     const errors: Error[] = []
     ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error))
 
+    const idle = waitForIdle(ctx, agent)
     send(agent, 'first')
-    await waitForIdle(ctx, agent)
-    expect(errors.map(e => e.message)).toEqual(['disk full'])
-
     send(agent, 'second')
-    await waitForIdle(ctx, agent)
+
+    await firstFlush.promise
+    expect(adapter.requests).toHaveLength(1)
+    expect(agent.session.events.filter(event => event.type === 'turn/start')).toHaveLength(1)
+
+    releaseFirstFlush.resolve(undefined)
+    await idle
+
+    expect(errors.map(e => e.message)).toEqual(['disk full'])
     expect(adapter.requests).toHaveLength(2)
+    expect(agent.session.events.filter(event => event.type === 'turn/start')).toHaveLength(2)
   })
 })
 
 describe('disposed status is part of the agent/status contract', () => {
-  it('disposing the fiber emits agent/status(disposed) and ends the turn with reason disposed', async () => {
+  it('disposing the fiber ends the active turn and never starts its queued tail', async () => {
     const adapter = new MockAdapter(['hang'])
     const ctx = await harness(adapter)
 
@@ -675,11 +687,19 @@ describe('disposed status is part of the agent/status contract', () => {
 
     send(agent, 'go')
     await new Promise(r => setTimeout(r, 30))
+    send(agent, 'queued tail')
     await fiber.dispose()
     await driverDone(agent)
 
     expect(statuses).toEqual(['running', 'disposed'])
     expect(reasons).toEqual([{ kind: 'disposed' }])
+    expect(agent.session.events.filter(event => event.type === 'turn/start')).toHaveLength(1)
+    const messages = agent.session.events
+      .filter(event => event.type === 'user/message')
+      .flatMap(event => event.data.content)
+      .flatMap(block => block.type === 'text' ? [block.text] : [])
+    expect(messages).toEqual(['go'])
+    expect(adapter.requests).toHaveLength(1)
   })
 
   it('a throwing agent/status listener cannot break disposal or leak the registry entry', async () => {

packages/core/agent-loop/tests/coverage-edges.spec.ts

@@ -146,12 +146,22 @@ describe('toError normalization', () => {
     const errors: Error[] = []
     ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error))
 
-    send(agent, 'go')
+    send(agent, 'fails before turn start')
+    send(agent, 'survives as the next item')
     await waitForIdle(ctx, agent)
     expect(errors).toHaveLength(1)
     expect(errors[0]).toMatchObject({ message: 'naked string error', code: 'UNKNOWN' })
-    expect(adapter.requests).toEqual([])
-    expect(agent.session.events.some(event => event.type === 'turn/start' || event.type === 'turn/end')).toBe(false)
+    expect(adapter.requests).toHaveLength(1)
+    const starts = agent.session.events.filter(event => event.type === 'turn/start')
+    const ends = agent.session.events.filter(event => event.type === 'turn/end')
+    const messages = agent.session.events.filter(event => event.type === 'user/message')
+    expect(starts).toHaveLength(1)
+    expect(starts[0]?.type === 'turn/start' && starts[0].data.turn).toBe(1)
+    expect(ends).toHaveLength(1)
+    expect(messages).toHaveLength(1)
+    expect(messages[0]?.type === 'user/message' && messages[0].data.content).toEqual([
+      { type: 'text', text: 'survives as the next item' },
+    ])
   })
 
   it('normalizes non-Error throws from agent/request waterfall via inline toError in runStep catch', async () => {

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

@@ -8,17 +8,17 @@ function resolverPair() {
 }
 
 describe('Inbox', () => {
-  it('enqueues and drains queued messages in FIFO order', () => {
+  it('dequeues one queued message at a time in FIFO order', () => {
     const inbox = new Inbox()
     inbox.enqueue({ content: [{ type: 'text', text: 'first' }], source: { kind: 'user' } })
     inbox.enqueue({ content: [{ type: 'text', text: 'second' }], source: { kind: 'user' } })
     expect(inbox.hasQueued).toBe(true)
 
-    const drained = inbox.drainQueued()
-    expect(drained).toHaveLength(2)
-    expect(drained[0]!.content[0]).toMatchObject({ text: 'first' })
-    expect(drained[1]!.content[0]).toMatchObject({ text: 'second' })
+    expect(inbox.dequeueQueued()?.content[0]).toMatchObject({ text: 'first' })
+    expect(inbox.hasQueued).toBe(true)
+    expect(inbox.dequeueQueued()?.content[0]).toMatchObject({ text: 'second' })
     expect(inbox.hasQueued).toBe(false)
+    expect(inbox.dequeueQueued()).toBeUndefined()
   })
 
   it('pushes and drains steering messages separately from queued', () => {

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

@@ -99,7 +99,6 @@ describe('agent/prompt-submit', () => {
         additionalContexts: [{
           content: [{ type: 'text', text: '<system-reminder>extra ctx</system-reminder>' }],
           source: { kind: 'plugin', plugin: 'test' },
-          envelope: 'raw',
           meta,
         }],
       }))
@@ -113,7 +112,6 @@ describe('agent/prompt-submit', () => {
     expect(userMsg).toBeDefined()
     expect(ctxMsg?.type === 'context/message' && ctxMsg.data.content).toEqual([{ type: 'text', text: '<system-reminder>extra ctx</system-reminder>' }])
     expect(ctxMsg?.type === 'context/message' && ctxMsg.data.source).toEqual({ kind: 'plugin', plugin: 'test' })
-    expect(ctxMsg?.type === 'context/message' && ctxMsg.data.envelope).toBe('raw')
     expect(ctxMsg?.type === 'context/message' && ctxMsg.data.meta).toEqual(meta)
     const sent = JSON.stringify(adapter.requests[0]!.messages)
     expect(sent).toContain('extra ctx')
@@ -179,9 +177,7 @@ describe('agent/prompt-submit', () => {
     expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason).toEqual({ kind: 'rejected', reason: 'blocked by policy' })
   })
 
-  it('a mixed batch records a prompt/blocked for the vetoed prompt while the allowed one runs', async () => {
-    // Blocking one prompt in a mixed batch must persist its reason even though
-    // the allowed prompt keeps the turn from ending rejected.
+  it('adjacent blocked and allowed prompts keep independent turn outcomes', async () => {
     const adapter = new MockAdapter([textResponse('ran once')])
     const ctx = await harness(adapter)
     const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
@@ -194,13 +190,13 @@ describe('agent/prompt-submit', () => {
     const reasons: TurnEndReason[] = []
     ctx.on('session/event', (_s, event: SessionEvent) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
 
-    // both sends land before the loop drains → one batched turn
+    // Both sends land before the driver wakes, but each remains its own turn.
     send(agent, 'secret')
     send(agent, 'safe')
     await waitForIdle(ctx, agent)
 
     const log = events(agent)
-    // the allowed prompt became a user/message and drove exactly one model call
+    // The allowed prompt became a user/message and drove exactly one model call.
     const userMsgs = log.filter(e => e.type === 'user/message')
     expect(userMsgs).toHaveLength(1)
     expect(userMsgs[0]?.type === 'user/message' && userMsgs[0].data.content).toEqual([{ type: 'text', text: 'safe' }])
@@ -212,12 +208,14 @@ describe('agent/prompt-submit', () => {
       content: [{ type: 'text', text: 'secret' }],
       reason: 'policy: no secrets',
     })
-    // the turn did NOT reject — a sibling was allowed — so the boundary reason
-    // alone would not have preserved the block
-    expect(reasons.some(r => r.kind === 'rejected')).toBe(false)
+    expect(log.filter(e => e.type === 'turn/start')).toHaveLength(2)
+    expect(reasons).toEqual([
+      { kind: 'rejected', reason: 'policy: no secrets' },
+      { kind: 'completed' },
+    ])
   })
 
-  it('a throwing prompt-submit listener ends the turn balanced (error), loop survives', async () => {
+  it('a throwing prompt-submit listener ends its turn balanced while an adjacent message survives', async () => {
     const adapter = new MockAdapter([textResponse('after')])
     const ctx = await harness(adapter)
     const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
@@ -228,20 +226,31 @@ describe('agent/prompt-submit', () => {
       return { kind: 'allow' as const }
     })
     const errors: Error[] = []
+    const reasons: TurnEndReason[] = []
+    const statuses: string[] = []
     ctx.on('agent/error', (_a, _t, _s, error) => void errors.push(error))
+    ctx.on('agent/status', (subject, status) => { if (subject === agent) statuses.push(status) })
+    ctx.on('session/event', (session, event) => {
+      if (session === agent.session && event.type === 'turn/end') reasons.push(event.data.reason)
+    })
 
+    const idle = waitForIdle(ctx, agent)
     send(agent, 'first')
-    await waitForIdle(ctx, agent)
-    expect(errors.map(e => e.message)).toEqual(['prompt hook broke'])
-    // turn balanced
-    const log = events(agent)
-    expect(log.filter(e => e.type === 'turn/start')).toHaveLength(1)
-    expect(log.filter(e => e.type === 'turn/end')).toHaveLength(1)
-
-    // loop survives: a second prompt runs normally
     send(agent, 'second')
-    await waitForIdle(ctx, agent)
-    expect(adapter.requests.length).toBeGreaterThanOrEqual(1)
+    await idle
+    expect(errors.map(e => e.message)).toEqual(['prompt hook broke'])
+    // The failed prompt forms one balanced error turn; the adjacent prompt forms
+    // the following normal turn without an intermediate idle transition.
+    const log = events(agent)
+    expect(log.filter(e => e.type === 'turn/start')).toHaveLength(2)
+    expect(log.filter(e => e.type === 'turn/end')).toHaveLength(2)
+    expect(reasons).toEqual([
+      { kind: 'error', step: 0, message: 'prompt hook broke' },
+      { kind: 'completed' },
+    ])
+    expect(statuses).toEqual(['running', 'idle'])
+    expect(adapter.requests).toHaveLength(1)
+    expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('second')
   })
 })
 
@@ -556,7 +565,6 @@ describe('tool additionalContexts buffering across a step', () => {
         additionalContexts: [{
           content: [{ type: 'text', text: `ctx-${exec.callId}` }],
           source: { kind: 'plugin', plugin: 'p' },
-          envelope: 'raw',
           meta: { callId: exec.callId },
         }],
       }))
@@ -580,7 +588,6 @@ describe('tool additionalContexts buffering across a step', () => {
       .map(b => (b.type === 'text' ? b.text : ''))
     expect(ctxTexts).toEqual(['ctx-c1', 'ctx-c2'])
     const contextEvents = events(agent).filter(e => e.type === 'context/message')
-    expect(contextEvents.map(e => e.type === 'context/message' && e.data.envelope)).toEqual(['raw', 'raw'])
     expect(contextEvents.map(e => e.type === 'context/message' && e.data.meta)).toEqual([{ callId: 'c1' }, { callId: 'c2' }])
   })
 
@@ -591,7 +598,7 @@ describe('tool additionalContexts buffering across a step', () => {
       name: 'composite', description: 'composite', parameters: {},
       async execute(_args, exec) {
         exec.deferContext({ content: [{ type: 'text', text: 'nested-a' }], source: { kind: 'plugin', plugin: 'a' }, meta: { order: 1 } })
-        exec.deferContext({ content: [{ type: 'text', text: 'nested-b' }], source: { kind: 'plugin', plugin: 'b' }, envelope: 'raw', meta: { order: 2 } })
+        exec.deferContext({ content: [{ type: 'text', text: 'nested-b' }], source: { kind: 'plugin', plugin: 'b' }, meta: { order: 2 } })
         return [{ type: 'text', text: 'outer result' }]
       },
     }))

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

@@ -354,14 +354,24 @@ describe('agent loop', () => {
     expect(flat).toContain('change of plans')
   })
 
-  it('steering while idle behaves like send (starts a turn)', async () => {
-    const adapter = new MockAdapter([textResponse('ok')])
+  it('same-tick idle steering inherits one-send-one-turn FIFO behavior', async () => {
+    const adapter = new MockAdapter([textResponse('first'), textResponse('second')])
     const ctx = await harness(adapter)
     const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
-    agent.steer([{ type: 'text', text: 'hello' }])
-    await waitForIdle(ctx, agent)
-    expect(agent.session.events.some(e => e.type === 'user/message')).toBe(true)
+    const idle = waitForIdle(ctx, agent)
+    agent.steer([{ type: 'text', text: 'first idle steer' }])
+    agent.steer([{ type: 'text', text: 'second idle steer' }])
+    await idle
+
+    expect(agent.session.events.filter(event => event.type === 'turn/start')).toHaveLength(2)
+    expect(agent.session.events
+      .filter(event => event.type === 'user/message')
+      .map(event => event.data.content)).toEqual([
+      [{ type: 'text', text: 'first idle steer' }],
+      [{ type: 'text', text: 'second idle steer' }],
+    ])
+    expect(adapter.requests).toHaveLength(2)
   })
 
   it('inject() while idle wraps context in a one-shot turn, visible to the next request', async () => {
@@ -385,10 +395,10 @@ describe('agent loop', () => {
     await waitForIdle(ctx, agent)
     const flat = JSON.stringify(adapter.requests[0]!.messages)
     expect(flat).toContain('file changed: a.ts')
-    expect(flat).toContain('<context source=\\"plugin\\">')
+    expect(flat).not.toContain('<context source=')
   })
 
-  it('inject() can persist raw structured context without the generic context envelope', async () => {
+  it('inject() persists structured context content verbatim with durable hidden meta', async () => {
     const adapter = new MockAdapter([textResponse('ok')])
     const ctx = await harness(adapter)
     const agent = ctx.agentLoop.create(SessionId('raw-context'), { provider: 'mock', model: 'mock' })
@@ -401,14 +411,13 @@ describe('agent loop', () => {
 
     agent.inject([{ type: 'text', text }], {
       source: { kind: 'plugin', plugin: 'workspace-context' },
-      envelope: 'raw',
       meta,
     })
     send(agent, 'go')
     await waitForIdle(ctx, agent)
 
     const contextEvent = agent.session.events.find(event => event.type === 'context/message')
-    expect(contextEvent?.type === 'context/message' && contextEvent.data).toMatchObject({ envelope: 'raw', meta })
+    expect(contextEvent?.type === 'context/message' && contextEvent.data).toMatchObject({ meta })
     const requestText = JSON.stringify(adapter.requests[0]!.messages)
     expect(requestText).toContain('Additional instructions from: pkg/AGENTS.md')
     expect(requestText).not.toContain('<context source=')
@@ -432,7 +441,6 @@ describe('agent loop', () => {
         const first = { type: 'text' as const, text: 'mid-turn notice' }
         agent.inject([first], {
           source: { kind: 'plugin', plugin: 'x' },
-          envelope: 'raw',
           meta,
         })
         first.text = 'mutated after inject'
@@ -458,7 +466,6 @@ describe('agent loop', () => {
     expect(contexts).toHaveLength(2)
     expect(result.seq).toBeLessThan(contexts[0]!.seq)
     expect(contexts[0]?.type === 'context/message' && contexts[0].data).toMatchObject({
-      envelope: 'raw',
       meta,
     })
     expect(contexts.flatMap(event => event.type === 'context/message' ? event.data.content : []))
@@ -925,7 +932,149 @@ describe('agent loop', () => {
     expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason.kind).toBe('completed')
   })
 
-  it('chains queued messages into consecutive turns', async () => {
+  it('keeps same-tick sends in separate turns and checkpoints before the next starts', async () => {
+    const adapter = new MockAdapter([textResponse('first answer'), textResponse('second answer')])
+    const ctx = await harness(adapter)
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
+
+    const firstFlush = Promise.withResolvers<undefined>()
+    const releaseFirstFlush = Promise.withResolvers<undefined>()
+    let flushes = 0
+    ctx.on('session/flush', async (session) => {
+      if (session !== agent.session) return
+      flushes += 1
+      if (flushes === 1) {
+        firstFlush.resolve(undefined)
+        await releaseFirstFlush.promise
+      }
+    })
+
+    const turns: number[] = []
+    ctx.on('session/event', (session, event) => {
+      if (session === agent.session && event.type === 'turn/start') turns.push(event.data.turn)
+    })
+
+    const idle = waitForIdle(ctx, agent)
+    send(agent, 'first message')
+    send(agent, 'second message')
+
+    await firstFlush.promise
+    expect(turns).toEqual([1])
+    expect(adapter.requests).toHaveLength(1)
+
+    releaseFirstFlush.resolve(undefined)
+    await idle
+
+    expect(turns).toEqual([1, 2])
+    expect(flushes).toBe(2)
+    expect(adapter.requests).toHaveLength(2)
+    expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('first answer')
+    expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('second message')
+  })
+
+  it('holds a turn-end listener send behind the closing turn checkpoint', async () => {
+    const adapter = new MockAdapter([textResponse('first answer'), textResponse('second answer')])
+    const ctx = await harness(adapter)
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
+
+    const firstFlush = Promise.withResolvers<undefined>()
+    const releaseFirstFlush = Promise.withResolvers<undefined>()
+    let flushes = 0
+    ctx.on('session/flush', async (session) => {
+      if (session !== agent.session) return
+      flushes += 1
+      if (flushes === 1) {
+        firstFlush.resolve(undefined)
+        await releaseFirstFlush.promise
+      }
+    })
+
+    const turns: number[] = []
+    const statuses: string[] = []
+    ctx.on('agent/status', (subject, status) => {
+      if (subject === agent) statuses.push(status)
+    })
+    ctx.on('session/event', (session, event) => {
+      if (session !== agent.session) return
+      if (event.type === 'turn/start') turns.push(event.data.turn)
+      if (event.type === 'turn/end' && event.data.turn === 1) send(agent, 'turn-end listener message')
+    })
+
+    const idle = waitForIdle(ctx, agent)
+    send(agent, 'first message')
+    await firstFlush.promise
+
+    expect(turns).toEqual([1])
+    expect(adapter.requests).toHaveLength(1)
+
+    releaseFirstFlush.resolve(undefined)
+    await idle
+
+    expect(turns).toEqual([1, 2])
+    expect(statuses).toEqual(['running', 'idle'])
+    expect(adapter.requests).toHaveLength(2)
+    expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('first answer')
+    expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('turn-end listener message')
+  })
+
+  it('keeps a reentrant agent/queued send as the next independent turn', async () => {
+    const adapter = new MockAdapter([textResponse('first'), textResponse('second')])
+    const ctx = await harness(adapter)
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
+
+    let nested = false
+    ctx.on('agent/queued', (subject) => {
+      if (subject !== agent || nested) return
+      nested = true
+      send(agent, 'queued listener message')
+    })
+
+    const idle = waitForIdle(ctx, agent)
+    send(agent, 'outer message')
+    await idle
+
+    const turns = agent.session.events.filter(event => event.type === 'turn/start')
+    const messages = agent.session.events
+      .filter(event => event.type === 'user/message')
+      .map(event => event.data.content)
+    expect(turns).toHaveLength(2)
+    expect(messages).toEqual([
+      [{ type: 'text', text: 'outer message' }],
+      [{ type: 'text', text: 'queued listener message' }],
+    ])
+  })
+
+  it('preserves independent turn sources across an adjacent microtask send', async () => {
+    const adapter = new MockAdapter([textResponse('first'), textResponse('second')])
+    const ctx = await harness(adapter)
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
+
+    const idle = waitForIdle(ctx, agent)
+    agent.send([{ type: 'text', text: 'user message' }])
+    await Promise.resolve()
+    agent.send(
+      [{ type: 'text', text: 'plugin message' }],
+      { source: { kind: 'plugin', plugin: 'test' } },
+    )
+    await idle
+
+    const triggers = agent.session.events
+      .filter(event => event.type === 'turn/start')
+      .map(event => event.data.trigger)
+    const sources = agent.session.events
+      .filter(event => event.type === 'user/message')
+      .map(event => event.data.source)
+    expect(triggers).toEqual([
+      { kind: 'message', source: { kind: 'user' } },
+      { kind: 'message', source: { kind: 'plugin', plugin: 'test' } },
+    ])
+    expect(sources).toEqual([
+      { kind: 'user' },
+      { kind: 'plugin', plugin: 'test' },
+    ])
+  })
+
+  it('keeps a session-listener send after dequeue in the following turn', async () => {
     const adapter = new MockAdapter([textResponse('first'), textResponse('second')])
     const ctx = await harness(adapter)
     const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
@@ -948,6 +1097,37 @@ describe('agent loop', () => {
 
     expect(turns).toEqual([1, 2])
     expect(adapter.requests).toHaveLength(2)
+    expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('first')
+    expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('second message')
+  })
+
+  it('keeps a model-adapter callback send in the following turn', async () => {
+    const agentRef: { current?: Agent } = {}
+    const adapter = new MockAdapter([
+      () => {
+        const agent = agentRef.current
+        if (agent === undefined) throw new Error('model callback ran before agent setup')
+        send(agent, 'model callback message')
+        return textResponse('first')
+      },
+      textResponse('second'),
+    ])
+    const ctx = await harness(adapter)
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
+    agentRef.current = agent
+
+    const idle = waitForIdle(ctx, agent)
+    send(agent, 'outer message')
+    await idle
+
+    const messages = agent.session.events
+      .filter(event => event.type === 'user/message')
+      .map(event => event.data.content)
+    expect(agent.session.events.filter(event => event.type === 'turn/start')).toHaveLength(2)
+    expect(messages).toEqual([
+      [{ type: 'text', text: 'outer message' }],
+      [{ type: 'text', text: 'model callback message' }],
+    ])
   })
 
   it('awaits session/flush at turn end (persistence checkpoint)', async () => {

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

@@ -81,6 +81,21 @@ function turnNumbers(agent: Agent): number[] {
     .map(e => (e.data as { turn: number }).turn)
 }
 
+function turnEndNumbers(agent: Agent): number[] {
+  return agent.session.events
+    .filter(e => e.type === 'turn/end')
+    .map(e => (e.data as { turn: number }).turn)
+}
+
+function userMessageCountsByTurn(agent: Agent): number[] {
+  const counts: number[] = []
+  for (const event of agent.session.events) {
+    if (event.type === 'turn/start') counts.push(0)
+    if (event.type === 'user/message') counts[counts.length - 1]! += 1
+  }
+  return counts
+}
+
 /** Assert a status trace is a legal run: idle/running alternating, ending idle. */
 function assertLegalStatusTrace(trace: string[]): void {
   for (let i = 1; i < trace.length; i++) {
@@ -90,7 +105,7 @@ function assertLegalStatusTrace(trace: string[]): void {
 }
 
 describe('agent loop scheduling properties', () => {
-  it('a synchronous burst loses no message and uses strictly increasing turns', async () => {
+  it('a synchronous burst gives every message its own strictly increasing turn', async () => {
     await fc.assert(fc.asyncProperty(
       fc.array(fc.string({ minLength: 1 }), { minLength: 1, maxLength: 6 }),
       async (texts) => {
@@ -105,8 +120,11 @@ describe('agent loop scheduling properties', () => {
 
           // No message lost: every send appears as a user/message, in order.
           expect(userMessageTexts(agent)).toEqual(texts)
-          // A synchronous burst batches into exactly one turn.
-          expect(turnNumbers(agent)).toEqual([1])
+          // This failure-free fixture maps every item to an independent turn.
+          expect(turnNumbers(agent)).toEqual(texts.map((_, i) => i + 1))
+          expect(turnEndNumbers(agent)).toEqual(texts.map((_, i) => i + 1))
+          expect(userMessageCountsByTurn(agent)).toEqual(texts.map(() => 1))
+          expect(trace).toEqual(['running', 'idle'])
           assertLegalStatusTrace(trace)
         } finally {
           await ctx.fiber.dispose()
@@ -137,9 +155,9 @@ describe('agent loop scheduling properties', () => {
     ), { numRuns: 20, timeout: 2000 })
   })
 
-  it('mixed schedule (send, optionally settle) loses no message and orders turns', async () => {
-    // Each step is a (text, settle?) pair: settle=true awaits idle before the
-    // next send (own turn); settle=false sends in the same tick (batches).
+  it('mixed settled and same-tick sends preserve one turn per message', async () => {
+    // Each step optionally waits for idle before the next send; that scheduling
+    // choice must not change the ordinary message-to-turn mapping.
     const stepArb = fc.record({ text: fc.string({ minLength: 1 }), settle: fc.boolean() })
     await fc.assert(fc.asyncProperty(
       fc.array(stepArb, { minLength: 1, maxLength: 6 }),
@@ -158,14 +176,13 @@ describe('agent loop scheduling properties', () => {
           }
           await lastIdle
 
-          // No message lost or reordered, regardless of batching.
+          // No message is lost or reordered, regardless of driver timing.
           expect(userMessageTexts(agent)).toEqual(steps.map(s => s.text))
-          // Turn numbers are a strictly increasing 1..N prefix (N = turn count).
+          // Every item forms one FIFO-ordered turn containing only that message.
           const turns = turnNumbers(agent)
-          expect(turns).toEqual(turns.map((_, i) => i + 1))
-          // Every message landed in some turn; turns never exceed messages.
-          expect(turns.length).toBeLessThanOrEqual(steps.length)
-          expect(turns.length).toBeGreaterThanOrEqual(1)
+          expect(turns).toEqual(steps.map((_, i) => i + 1))
+          expect(turnEndNumbers(agent)).toEqual(turns)
+          expect(userMessageCountsByTurn(agent)).toEqual(steps.map(() => 1))
         } finally {
           await ctx.fiber.dispose()
         }

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

@@ -411,7 +411,7 @@ describe('the session-persistence Agent Note: AgentLoop factory create/resume',
     await ctx.fiber.dispose()
   })
 
-  it('resume of a forked session preserves the parentSession lineage and seed boundary in the header', async () => {
+  it('resume of a forked session preserves the lineage, seed boundary, and delegation depth in the header', async () => {
     // Lifecycle 1: persist a FORKED session (carries parentSession + seedLength
     // in its header) by creating it with a complete-turn seed — the write path
     // materializes the fork (header + seed) on disk.
@@ -423,7 +423,7 @@ describe('the session-persistence Agent Note: AgentLoop factory create/resume',
     const { ctx: ctx1, root } = await persistentHarness(adapter1)
     const forked = ctx1.sessions.create(SessionId('forked-sess'), {
       seed,
-      meta: { cwd: '/w', parentSession: SessionId('parent-sess'), seedLength: seed.length },
+      meta: { cwd: '/w', parentSession: SessionId('parent-sess'), seedLength: seed.length, delegationDepth: 1 },
     })
     await ctx1.parallel('session/flush', forked)
     await ctx1.fiber.dispose()
@@ -447,6 +447,9 @@ describe('the session-persistence Agent Note: AgentLoop factory create/resume',
     expect(a2.session.header.parentSession).toBe('parent-sess')
     expect(a2.session.header.cwd).toBe('/w')
     expect(a2.session.header.seedLength).toBe(seed.length)
+    // The recursion budget survives resume — a dropped depth would let a
+    // resumed child delegate as if it were top-level.
+    expect(a2.session.header.delegationDepth).toBe(1)
     await ctx2.fiber.dispose()
   })
 

packages/core/agent/README.md

@@ -46,7 +46,7 @@ The lifecycle edges have two important local caveats. `agent/created` runs after
 
 Most interception points are cooperative waterfalls returning seam-specific decisions. `agent/pre-step` and `agent/post-step` are serial checkpoints around a step's durable work, while `agent/request-error` is the failed-model-request recovery waterfall: a retry opens a new numbered step after the failed step closes. `agent/turn-stop` is the terminal serial fold: it runs after ordinary continuation and steering folding, and a returned stop remains in force through turn close and flush so later steering cannot create an extra step or turn. Ordinary queued prompts remain intact. Effective broad cancellation first emits the observe-only `agent/cancel-requested` with its resolved reason, then clears queues and aborts; notification failures are contained and cannot veto the stop. The full rationale for scoped dispatch and terminal settlement is in the [agent-scope runtime-design Agent Note](../../../.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.md#three-execution-boundaries-are-deliberately-one-way).
 
-`PromptDecision.additionalContexts` is an array so every injected context keeps its own source, envelope, and metadata. A `ContinuationDecision` reason is narrower: it becomes a `steering/message`, not a `context/message`, and therefore carries only content and source.
+`PromptDecision.additionalContexts` is an array so every injected context keeps its own source and metadata. A `ContinuationDecision` reason is narrower: it becomes a `steering/message`, not a `context/message`, and therefore carries only content and source.
 
 Turn and step boundaries and the model token stream are durable `session/event` facts rather than mirrored `agent/*` notifications. Consumers read `turn/*`, `step/*`, and `assistant/chunk` from the session feed; tool policy and outcome observation belong to the complete pipeline documented by [`dsh-tools`](../tools/README.md).
 
@@ -54,13 +54,15 @@ Turn and step boundaries and the model token stream are durable `session/event`
 
 The handle every plugin programs against:
 
-- `agent.send(content, options?)` — queue a message; starts a turn when idle. Omitting `options.source` attests direct human input as `{ kind: 'user' }` and may authorize policy consumers, so plugins, schedulers, and other non-human producers provide their own source. Content and resolved source become one detached, deeply frozen lossless-JSON record before `agent/queued` and enqueue; invalid data throws synchronously, and caller or notification-listener in-place mutation cannot change the log or model input (`agent/prompt-submit` still rewrites by returning replacement content).
-- `agent.steer(content, options?)` — steer a running turn (inject between steps); uses the same owned acceptance boundary and behaves like `send` when idle
-- `agent.inject(content, options?)` — accept detached in-session context without running the model; the next request sees its `context/message`. `options.envelope` defaults to the canonical `<context>` framing and may be `'raw'` when the caller owns a complete familiar frame; `options.meta` persists opaque JSON state without rendering it. While a turn is open it joins that turn, deferring FIFO while the current tool batch executes and draining before turn close if execution is interrupted; while idle it is wrapped in a one-shot `injection` turn and durability checkpoint ([the turn-enclosure invariant](../../../.agents/notes/implemented/architecture/2026-06-15-turn-enclosure-invariant.md)).
+- `agent.send(content, options?)` — queue one independent FIFO item. If claimed, that item becomes the sole ordinary message in its turn; a claimed FIFO successor waits for that turn's checkpoint to settle. Broad cancellation, disposal, or a pre-start failure may instead drop it without a turn. Omitting `options.source` attests direct human input as `{ kind: 'user' }` and may authorize policy consumers, so plugins, schedulers, and other non-human producers provide their own source. Content and resolved source become one detached, deeply frozen lossless-JSON record before `agent/queued` and enqueue; invalid data throws synchronously, and caller or notification-listener in-place mutation cannot change the log or model input (`agent/prompt-submit` still rewrites by returning replacement content). The [one-send-one-turn Agent Note](../../../.agents/notes/implemented/simplification/2026-07-17-one-send-one-turn.md) owns the rationale.
+- `agent.steer(content, options?)` — submit steering while the agent is `running`. An open turn records it at the next steering checkpoint before a request or continuation decision; policy can still stop before another step. After turn close and its checkpoint, remaining steering becomes later queued input unless terminal turn policy, cancellation, or disposal discards it. The method uses the same synchronous snapshot-and-validation boundary as `send` and delegates to `send` when idle
+- `agent.inject(content, options?)` — accept detached in-session context without running the model; the next request sees its `context/message` with `content` rendered verbatim as a user-role message. `options.meta` persists opaque JSON state without rendering it. While a turn is open it joins that turn, deferring FIFO while the current tool batch executes and draining before turn close if execution is interrupted; while idle it is wrapped in a one-shot `injection` turn and durability checkpoint ([the turn-enclosure invariant](../../../.agents/notes/implemented/architecture/2026-06-15-turn-enclosure-invariant.md)).
 - `agent.cancel(reason?)` — cancel ALL pending work: an effective call emits `agent/cancel-requested` before it clears the queued + steering FIFOs, aborts the in-flight step, and drops a turn about to start (the pre-step window). Observers may synchronize their own state but cannot veto cancellation. A UI/ACP `session/cancel` maps to this. The single public stop primitive. Idle with nothing pending → a safe no-op with no notification.
 - `agent.whenIdle()` — resolve once the agent reaches quiescence after settling out of `running` (idle → immediately; disposed → awaits the loop exit). A non-owner's quiescence-observation hook: it observes the work settling WITHOUT tearing the agent down. Teardown is separate — a lifecycle owner stops and unregisters via `AgentHandle.dispose()`, which awaits the loop exit directly.
 - `agent.session`, `agent.status`, `agent.options`, `agent.id`
 
+`running` describes a driver-wide drain interval, not proof that a turn is still open; it can cover turn close, the durability checkpoint, and consecutive queued turns.
+
 ### Extension points
 
 - Agent creation: `AgentLoop.create()` is the concrete config-path implementation (in `dsh-agent-loop`), while programmatic consumers create/resume owned agents through `ctx.agents.create()` / `ctx.agents.resume()`. Replace the loop by implementing `Agent` and registering via `ctx.agents.register()`.

packages/core/agent/src/index.ts

@@ -46,15 +46,21 @@ export interface CreateAgentOptions {
   readonly sessionId: SessionId
   /**
    * Session creation metadata: validated absolute `cwd`, `parentSession`
-   * fork lineage, and the `seedLength` seed boundary. Mirrors the
-   * `cwd`/`parentSession`/`seedLength` fields of
+   * fork lineage, the `seedLength` seed boundary, and the `delegationDepth`
+   * recursion budget. Mirrors the
+   * `cwd`/`parentSession`/`seedLength`/`delegationDepth` fields of
    * {@link CreateSessionOptions.meta} in dsh-session (the internal-only
    * `createdAt`, used when reconstructing a persisted session, is deliberately
    * excluded — a factory caller never sets it). This is durable session data,
    * so the session boundary validates and snapshots it before asynchronous
    * setup begins.
    */
-  readonly meta?: { readonly cwd?: string; readonly parentSession?: SessionId; readonly seedLength?: number }
+  readonly meta?: {
+    readonly cwd?: string
+    readonly parentSession?: SessionId
+    readonly seedLength?: number
+    readonly delegationDepth?: number
+  }
   /**
    * Seed events to reconstruct the child session's log from (the fork lineage
    * primitive). When present, the factory creates the session with this event

packages/core/agent/src/types.ts

@@ -8,7 +8,7 @@
 import type { Context } from 'cordis'
 import type { Scoped } from '@deepseek-ai/dsh-scope'
 import type { ContentBlock, LlmCallConfig, Message, MessageSource } from '@deepseek-ai/dsh-llm'
-import type { ContextEnvelope, JsonValue, Session, SessionId } from '@deepseek-ai/dsh-session'
+import type { JsonValue, Session, SessionId } from '@deepseek-ai/dsh-session'
 import type {} from '@deepseek-ai/dsh-system-prompt'
 declare module '@deepseek-ai/dsh-system-prompt' {
   interface AssembleContext {
@@ -35,17 +35,15 @@ export interface SendOptions {
 
 /** Options specific to durable synthetic context injection. */
 export interface InjectOptions extends SendOptions {
-  /** Keep the canonical context tag, or send caller-owned framing verbatim. */
-  envelope?: ContextEnvelope
   /** Opaque JSON state retained in the session event but hidden from the model. */
   meta?: JsonValue
 }
 
 /**
  * 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).
+ * `idle` (parked, waiting for queued work), `running` (the driver is draining
+ * work and may be closing or checkpointing a turn), `disposed` (terminal — no
+ * transition leaves it, and `send`/`steer`/`inject` throw).
  */
 export type AgentStatus = 'idle' | 'running' | 'disposed'
 
@@ -53,16 +51,15 @@ export type AgentStatus = 'idle' | 'running' | 'disposed'
 export interface HookContext {
   content: ContentBlock[]
   source: MessageSource
-  /** Keep the canonical context tag, or use caller-owned framing verbatim. */
-  envelope?: ContextEnvelope
   /** Opaque JSON state retained in the session event but hidden from the model. */
   meta?: JsonValue
 }
 
 /**
  * Prompt interception result. `allow.content` replaces the prompt and each
- * `additionalContexts` entry becomes a separate context message. `block` records a
- * durable `prompt/blocked`; an all-blocked batch ends a zero-step rejected turn.
+ * `additionalContexts` entry becomes a separate context message. `block`
+ * records a durable `prompt/blocked` and ends the claimed prompt's zero-step
+ * turn as rejected.
  */
 export type PromptDecision =
   | { kind: 'allow'; content?: ContentBlock[]; additionalContexts?: HookContext[] }
@@ -100,15 +97,20 @@ export interface Agent {
   readonly ctx: Context
 
   /**
-   * Queue detached, frozen lossless-JSON input; starts a turn when idle.
+   * Queue one detached, frozen lossless-JSON item. If claimed, it is the sole
+   * ordinary message in its FIFO-ordered turn; the next claimed item waits for
+   * that turn's checkpoint.
    * Invalid input throws synchronously before notification or enqueue.
    */
   send(content: ContentBlock[], options?: SendOptions): void
 
   /**
-   * Steer a running turn: content is injected between steps of the current
-   * turn. Uses the same owned-value and synchronous-validation boundary as
-   * {@link send}; when idle, behaves exactly like that method.
+   * Submit steering while the agent is `running`. An open turn records it at
+   * the next steering checkpoint before a request or continuation decision;
+   * policy may stop before another step. After turn close and its checkpoint,
+   * any remainder is queued for a later turn; terminal `agent/turn-stop`,
+   * cancellation, or disposal may discard it. Uses the same synchronous
+   * snapshot-and-validation boundary as {@link send}; when idle, delegates to it.
    */
   steer(content: ContentBlock[], options?: SendOptions): void
 
@@ -122,11 +124,11 @@ export interface Agent {
   inject(content: ContentBlock[], options?: InjectOptions): void
 
   /**
-   * Clear queued and steering work, including work waiting to start, and abort
-   * the active step. An effective call first emits `agent/cancel-requested` with
-   * the resolved reason. The supplied reason is preserved across pre-step and
-   * active cancellation windows, and `whenIdle()` resolves after cancellation
-   * reaches quiescence. Idle cancellation is a no-op and does not arm a later cancel.
+   * Clear all queued and steering work, including items waiting to start, and
+   * abort the active step. An effective call first emits `agent/cancel-requested`
+   * with the resolved reason. That reason is preserved across pre-step and active
+   * cancellation windows, and `whenIdle()` resolves after cancellation reaches
+   * quiescence. Idle cancellation is a no-op and does not arm a later cancel.
    */
   cancel(reason?: string): void
 
@@ -217,10 +219,10 @@ declare module 'cordis' {
      */
     'agent/pre-step'(this: Scoped<Agent>, agent: Agent, turn: number, step: number, signal: AbortSignal): Promise<void> | void
     /**
-     * Allow, rewrite, or block one drained prompt before it becomes a user
+     * Allow, rewrite, or block one claimed prompt before it becomes a user
      * message. Call `next()` for the unchanged default.
-     * @param agent - the agent draining its inbox.
-     * @param content - the drained message's blocks, as queued.
+     * @param agent - the agent whose turn claimed the message.
+     * @param content - the claimed message's blocks, as queued.
      * @param source - the message's resolved source.
      * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
      * @mode waterfall

packages/core/session/README.md

@@ -8,7 +8,7 @@ Creates and holds event-sourced `Session` instances. Persistence is intentionall
 
 ### Public API
 
-- `ctx.sessions.create(id?, { seed?, meta? }?)` validates and detaches durable seed/header data, fills the version and id, defaults `createdAt` to now, publishes the session, and binds it to the calling fiber. Persisted reconstruction supplies its original `createdAt` and `seedLength`.
+- `ctx.sessions.create(id?, { seed?, meta? }?)` validates and detaches durable seed/header data, fills the version and id, defaults `createdAt` to now, publishes the session, and binds it to the calling fiber. Persisted reconstruction supplies its original `createdAt`, `seedLength`, and `delegationDepth`.
 - `ctx.sessions.flush(session)` dispatches the awaited parallel durability checkpoint through the session's captured scope. Every listener starts and the call waits for all to settle before reporting failure; unpublished, detached, and stale objects reject.
 - `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`
@@ -32,13 +32,13 @@ The store pairs announced creation with disposal, publishes post-commit append n
 
 Plain class (not a Cordis Service). Create via `ctx.sessions.create()`.
 
-- `session.append(type, data, opts?)` snapshots and freezes durable data and surface metadata, validates marker shape, provenance, and complete replacement coverage, commits synchronously, then notifies observers with independent failure containment. Reentrant attached-session appends reject, and runtime checks cover widened unions and loaded logs.
+- `session.append(type, data, opts?)` snapshots and freezes durable data and surface metadata, validates marker shape, provenance, complete replacement coverage, and content-only single-result `tool/result` rewrites, commits synchronously, then notifies observers with independent failure containment. Reentrant attached-session appends reject, and runtime checks cover widened unions and loaded logs.
 - `session.deriveMessages()` incrementally projects each new surface entry once and returns a fresh array over shared frozen messages. Assistant projections preserve provider/model provenance and adapter-private replay state. A surface rewrite rebuilds the projection; there is no raw-log fallback.
 - `session.deriveEventMessage(event)` is the canonical per-event projection used by reconstruction and invariants.
 - `session.surface` exposes the readonly `SessionSurface` view owned by the session's single incremental surface manager; `replaceGeneration` changes on every committed rewrite.
 - `session.events` is a cached frozen snapshot invalidated by append; accepted events remain deeply frozen.
 - `session.seq`, `session.id` — current sequence and readonly typed identity.
-- `session.header: SessionHeader` — detached, deep-frozen creation metadata (`version`, `id`, `createdAt`, optional `cwd`/`parentSession`/`seedLength`). Construction validates the durable record and requires its id to match `session.id`.
+- `session.header: SessionHeader` — detached, deep-frozen creation metadata (`version`, `id`, `createdAt`, optional `cwd`/`parentSession`/`seedLength`/`delegationDepth`). Construction validates the durable record and requires its id to match `session.id`.
 
 ### Lossless JSON utilities
 
@@ -49,14 +49,14 @@ Durable values need one accepted representation, not a check followed by a secon
 - `SurfaceOp` — how an event entered the ordered surface: `'append'` (normal tail append) or `{ op: 'replace', start, end }` (replace entries from `start` through `end` inclusive — both must be valid surface seqs; `start === end` replaces one entry). Used by compaction to shadow old events without deleting them.
 - `SurfaceIntent` — `{ surfaceOp: SurfaceOp; sourceEventSeqs?: number[] }`, the required third parameter to `session.append()` for surface-eligible types.
 - `SessionSurface` — the readonly live `nodes` and `replaceGeneration` projection exposed by `session.surface`; candidate validation remains private to `Session`.
-- `foldSurface(events)` — replay the canonical surface contract into detached current event sequences and actual replacement ranges. The same pass rejects non-contiguous seqs, misplaced or malformed metadata, empty or duplicate provenance, non-earlier sources, invalid positional ranges, and replacements that fail to cite every shadowed surface entry; `SurfaceManager` shares the atomic transition while retaining only its incremental sequence cache.
+- `foldSurface(events)` — replay the canonical surface contract into detached current event sequences and actual replacement ranges. The same pass rejects non-contiguous seqs, misplaced or malformed metadata, empty or duplicate provenance, non-earlier sources, invalid positional ranges, replacements that fail to cite every shadowed surface entry, and a `tool/result` replacement that changes anything except one current result's `content`; `SurfaceManager` shares the atomic transition while retaining only its incremental sequence cache.
 - `isSurfaceEvent(event)` / `isSurfaceEligibleType(type)` — the first narrows a `SessionEvent` to a fully formed surface event; the second detects a surface-eligible event missing its marker when validating a seed or loaded log.
 
 ### Request-header reconstruction (`request-header.ts`)
 
 `request/header` records a full canonical snapshot of the non-history request envelope with reason `initial`, `resume`, or `change`. `foldRequestHeader()` selects the latest snapshot; legacy delta events and the removed `fallback` reason are rejected. `messagePrefix` remains separate from derived history. See the [reconstructable-requests Agent Note](../../../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md).
 
-`context/message` defaults to the canonical tagged context projection. A producer may set `envelope: 'raw'` when its `content` already contains the complete model-facing frame, and may attach JSON `meta` for replayable plugin state; metadata remains durable but is excluded from `deriveMessages()`.
+`context/message` renders its `content` verbatim as a user-role message, and may attach JSON `meta` for replayable plugin state; metadata remains durable but is excluded from `deriveMessages()`.
 
 ### Session event vocabulary (`types.ts`)
 
@@ -73,13 +73,13 @@ Every `SessionEvent` carries two optional top-level fields (structural metadata)
 
 ### Metadata types (`types.ts`)
 
-- `SessionHeader` — session metadata written once when published as `Session.header`, where detachment and deep-freezing enforce immutability at runtime: `{ version, id, createdAt, cwd?, parentSession?, seedLength? }`. Persistence loaders may return mutable detached copies of the same data type. Owned here (beside `SessionId`) because `Session.header` is typed by it; persistence backends re-export it rather than own it (which would force a package cycle).
+- `SessionHeader` — session metadata written once when published as `Session.header`, where detachment and deep-freezing enforce immutability at runtime: `{ version, id, createdAt, cwd?, parentSession?, seedLength?, delegationDepth? }`. Persistence loaders may return mutable detached copies of the same data type. Owned here (beside `SessionId`) because `Session.header` is typed by it; persistence backends re-export it rather than own it (which would force a package cycle).
 
 ### 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: `create(id, { seed })` validates and freezes a contiguous current-format log and rebuilds its surface; request headers require provider/model and assistant messages require provider/model provenance. `fork(source, boundary?, childSessionId?)` selects a completed-turn prefix and records lineage.
-- Compaction: the `dsh-compact-basic` plugin appends a `user/message` with `surfaceOp: { op: 'replace', start, end }` to shadow old surface entries behind a summary checkpoint. Tool-pairing boundary policy and its cache belong to the [`dsh-compact` seam](../../compact/compact/README.md), while this package owns ordered surface membership and `replaceGeneration`.
+- Compaction: `dsh-compact-basic` appends a `user/message` replacement for summary checkpoints, while `dsh-compact-tool-result-prune` appends a content-only `tool/result` replacement. Tool-pairing boundary policy and its cache belong to the [`dsh-compact` seam](../../compact/compact/README.md), while this package owns ordered surface membership, replacement validation, and `replaceGeneration`.
 
 ## Model Experience
 
@@ -87,7 +87,7 @@ Every `SessionEvent` carries two optional top-level fields (structural metadata)
 
 #### What the model sees
 
-The model receives projections of `user/message`, `assistant/message`, and `tool/result` surface entries verbatim. A `context/message` is a user-role message containing exactly `<context source="<source-kind>">`, its content blocks, and `</context>`; `steering/message` uses the identical `<steering source="<source-kind>">` / `</steering>` wrapper. Tool calls live inside assistant messages. Chunks, boundaries, usage, hook records, todo records, and other log-only events add no message.
+The model receives projections of `user/message`, `assistant/message`, `tool/result`, `context/message`, and `steering/message` surface entries verbatim: each is a user- or assistant-role message carrying its content blocks unchanged. Tool calls live inside assistant messages. Chunks, boundaries, usage, hook records, todo records, and other log-only events add no message.
 
 #### Token effect
 

packages/core/session/src/index.ts

@@ -11,9 +11,9 @@ import { isAbsolute } from 'node:path'
 import { deepFreeze } from '@deepseek-ai/dsh-llm'
 import { scopeOf, scopeTarget } from '@deepseek-ai/dsh-scope'
 import type { Scoped } from '@deepseek-ai/dsh-scope'
-import type { ContentBlock, Message, MessageSource } from '@deepseek-ai/dsh-llm'
+import type { Message } from '@deepseek-ai/dsh-llm'
 import { SESSION_FORMAT_VERSION, SessionId } from './types.ts'
-import type { ContextEnvelope, CreateSessionOptions, EpochHeader, SessionEvent, SessionEventMap, SessionEventType, SessionHeader, SurfaceIntent, SurfaceEventType } from './types.ts'
+import type { CreateSessionOptions, EpochHeader, SessionEvent, SessionEventMap, SessionEventType, SessionHeader, SurfaceIntent, SurfaceEventType } from './types.ts'
 import { snapshotJsonValue } from './json.ts'
 import { SurfaceManager } from './surface.ts'
 import type { SessionSurface } from './surface.ts'
@@ -80,21 +80,6 @@ declare module 'cordis' {
   }
 }
 
-/**
- * Render injected context as tagged synthetic user-role content, keeping the
- * canonical session vocabulary provider-neutral. Adapter-specific exceptions
- * belong in the adapter.
- */
-function renderTagged(tag: string, content: ContentBlock[], source: MessageSource): ContentBlock[] {
-  const open = `<${tag} source=${JSON.stringify(source.kind)}>`
-  const close = `</${tag}>`
-  return [
-    { type: 'text', text: open },
-    ...content,
-    { type: 'text', text: close },
-  ]
-}
-
 /** Detach, validate, and freeze the creation metadata published by a session. */
 function snapshotSessionHeader(id: SessionId, source?: SessionHeader): SessionHeader {
   const input: unknown = source === undefined
@@ -128,6 +113,10 @@ function snapshotSessionHeader(id: SessionId, source?: SessionHeader): SessionHe
     && (typeof record.seedLength !== 'number' || !Number.isSafeInteger(record.seedLength) || record.seedLength < 0)) {
     throw new Error('session header seedLength must be a non-negative safe integer')
   }
+  if (record.delegationDepth !== undefined
+    && (typeof record.delegationDepth !== 'number' || !Number.isSafeInteger(record.delegationDepth) || record.delegationDepth < 0)) {
+    throw new Error('session header delegationDepth must be a non-negative safe integer')
+  }
   return deepFreeze(record as unknown as SessionHeader)
 }
 
@@ -228,22 +217,6 @@ interface SessionEntry {
 /** Store attachment for the append path; module-private to keep Session store-agnostic publicly. */
 const attachments = new WeakMap<Session, SessionEntry>()
 
-/**
- * Render one context contribution exactly as it will appear in model history.
- * @param content - content blocks supplied by the context producer.
- * @param source - attribution used by the canonical context envelope.
- * @param envelope - canonical tagged framing or caller-owned raw framing.
- * @returns a detached block list ready for the derived model transcript.
- */
-export function renderContextContent(
-  content: ContentBlock[],
-  source: MessageSource,
-  envelope: ContextEnvelope = 'context',
-): ContentBlock[] {
-  const cloned = structuredClone(content)
-  return envelope === 'raw' ? cloned : renderTagged('context', cloned, source)
-}
-
 /**
  * An event-sourced session: an append-only log of {@link SessionEvent}s.
  *
@@ -509,7 +482,18 @@ export class Session {
     // trace/replay data.
 
     switch (event.type) {
-      case 'user/message': {
+      // Injected context and mid-turn steering project identically to a user
+      // prompt: content verbatim, in user role. context's `source`/`meta` and
+      // steering's `turn` are log-only and do not reach the model. Do NOT
+      // re-add per-type framing (e.g. `<context>`/`<steering>`) here: framing is
+      // caller-owned — a producer bakes it into `content`, as workspace-context
+      // does with `<system-reminder>` — or, if reintroduced, must be driven by
+      // the event `meta` map and a dedicated renderer, keeping this projection a
+      // verbatim pass-through. See the deferred design note in
+      // ../../../../.agents/notes/implemented/simplification/2026-07-20-unwrap-injected-content-envelopes.md
+      case 'user/message':
+      case 'context/message':
+      case 'steering/message': {
         return { role: 'user', content: event.data.content }
       }
       case 'assistant/message': {
@@ -526,14 +510,6 @@ export class Session {
           content: [{ type: 'tool-result', toolCallId: callId, content, isError }],
         }
       }
-      case 'context/message': {
-        const { content, source, envelope } = event.data
-        return { role: 'user', content: renderContextContent(content, source, envelope) }
-      }
-      case 'steering/message': {
-        const { content, source } = event.data
-        return { role: 'user', content: renderTagged('steering', content, source) }
-      }
       default:
         // A non-surface event (boundary, chunk, log-only record) projects to
         // no message. Merge-extensible union: no assertNever here.
@@ -586,9 +562,9 @@ export class SessionStore extends Service {
    * Create a session owned by the calling fiber: disposing that fiber stops
    * event notification and removes the session from the store. `options.seed`
    * populates the session with a copy of those events (replay/fork);
-   * `options.meta` attaches creation metadata (validated absolute `cwd`,
-   * `parentSession` lineage) as the immutable {@link SessionHeader} (the store
-   * fills `version`/`id`/`createdAt`).
+   * `options.meta` attaches creation metadata (validated absolute `cwd`, seed
+   * and parent lineage, and delegation depth) as the immutable
+   * {@link SessionHeader} (the store fills `version`/`id`/`createdAt`).
    *
    * For an agent whose session must be torn down IN ORDER with its loop (so the
    * loop's final flush is captured before the store attachment ends), do NOT use this
@@ -650,6 +626,7 @@ export class SessionStore extends Service {
       ...meta?.cwd === undefined ? {} : { cwd: meta.cwd },
       ...meta?.parentSession === undefined ? {} : { parentSession: meta.parentSession },
       ...meta?.seedLength === undefined ? {} : { seedLength: meta.seedLength },
+      ...meta?.delegationDepth === undefined ? {} : { delegationDepth: meta.delegationDepth },
     }
     return new Session(sessionId, seed, header)
   }

packages/core/session/src/surface.ts

@@ -5,6 +5,7 @@
  * @module @deepseek-ai/dsh-session/surface
  */
 
+import { isDeepStrictEqual } from 'node:util'
 import type { SessionEvent, SurfaceEvent, SurfaceEventType, SurfaceOp } from './types.ts'
 
 /** Runtime counterpart of the message-producing event union. */
@@ -187,11 +188,37 @@ function replacementRange(
   }
 }
 
+/** Restrict a tool-result replacement to one current result's content. */
+function assertToolResultRewrite(
+  event: SessionEvent,
+  shadowedSeqs: readonly number[],
+  events: readonly SessionEvent[],
+): void {
+  if (event.type !== 'tool/result') return
+  if (shadowedSeqs.length !== 1) {
+    throw new Error('tool/result surface replacement must rewrite exactly one current node')
+  }
+  for (const originalSeq of shadowedSeqs) {
+    const original = events[originalSeq]
+    if (original?.type !== 'tool/result') {
+      throw new Error('tool/result surface replacement must target a current tool/result')
+    }
+    const originalRest = { ...original.data } as Record<string, unknown>
+    const replacementRest = { ...event.data } as Record<string, unknown>
+    delete originalRest['content']
+    delete replacementRest['content']
+    if (!isDeepStrictEqual(originalRest, replacementRest)) {
+      throw new Error('tool/result surface replacement may change only content')
+    }
+  }
+}
+
 /** Validate one event at its replay boundary and prepare its atomic fold transition. */
 function planSurfaceEvent(
   state: SurfaceFoldState,
   event: SessionEvent,
   expectedSeq: number,
+  events: readonly SessionEvent[],
 ): SurfacePlan | undefined {
   if (event.seq !== expectedSeq) {
     throw new Error(`session event seq ${event.seq} is not contiguous; expected ${expectedSeq}`)
@@ -204,6 +231,7 @@ function planSurfaceEvent(
   }
   const range = replacementRange(state, surfaceOp)
   assertProvenance(event, range.shadowedSeqs)
+  assertToolResultRewrite(event, range.shadowedSeqs, events)
   return {
     kind: 'replace',
     seq: event.seq,
@@ -218,8 +246,9 @@ function applySurfaceEvent(
   state: SurfaceFoldState,
   event: SessionEvent,
   expectedSeq: number,
+  events: readonly SessionEvent[],
 ): SurfaceFoldReplacement | undefined {
-  const plan = planSurfaceEvent(state, event, expectedSeq)
+  const plan = planSurfaceEvent(state, event, expectedSeq, events)
   if (plan?.kind === 'append') {
     state.nodes.push(plan.seq)
   } else if (plan?.kind === 'replace') {
@@ -239,13 +268,13 @@ function applySurfaceEvent(
  * Replay a complete session log through the canonical surface fold.
  * @param events - session events in contiguous seq order.
  * @returns detached current sequences and replacement history.
- * @throws when an event violates surface metadata, provenance, or range rules.
+ * @throws when an event violates surface metadata, provenance, range, or tool-result rewrite rules.
  */
 export function foldSurface(events: readonly SessionEvent[]): SurfaceFoldResult {
   const state = createFoldState()
   const replacements: SurfaceFoldReplacement[] = []
   for (const [index, event] of events.entries()) {
-    const replacement = applySurfaceEvent(state, event, index)
+    const replacement = applySurfaceEvent(state, event, index, events)
     if (replacement !== undefined) replacements.push(replacement)
   }
   return { nodes: [...state.nodes], replacements }
@@ -266,7 +295,7 @@ export class SurfaceManager implements SessionSurface {
    */
   validateNext(event: SessionEvent): void {
     if (this._lastProcessedSeq < this.log.length - 1) this._processDelta()
-    planSurfaceEvent(this._state, event, this.log.length)
+    planSurfaceEvent(this._state, event, this.log.length, this.log)
   }
 
   /** Monotonic count of folded positional replacements. */
@@ -285,7 +314,7 @@ export class SurfaceManager implements SessionSurface {
   private _processDelta(): void {
     for (let i = this._lastProcessedSeq + 1; i < this.log.length; i++) {
       // eslint-disable-next-line @typescript-eslint/no-non-null-assertion -- bounded by the loop condition
-      applySurfaceEvent(this._state, this.log[i]!, i)
+      applySurfaceEvent(this._state, this.log[i]!, i, this.log)
       this._lastProcessedSeq = i
     }
   }

packages/core/session/src/types.ts

@@ -2,9 +2,6 @@ import type { Branded } from '@deepseek-ai/dsh-brand'
 import type { AssistantProvenance, CallId, ContentBlock, LlmCallConfig, Message, MessageSource, StreamChunk, TokenUsage, ToolSchema } from '@deepseek-ai/dsh-llm'
 import type { JsonValue } from './json.ts'
 
-/** Canonical context-tag framing, or caller-owned framing rendered verbatim. */
-export type ContextEnvelope = 'context' | 'raw'
-
 /** Identifies one session in the store (and its persistence artifacts). */
 export type SessionId = Branded<'SessionId'>
 
@@ -50,6 +47,12 @@ export interface SessionHeader {
    * boundary lets resume and replay distinguish parent history from child work.
    */
   readonly seedLength?: number
+  /**
+   * Delegation depth: absent (zero) for a top-level session, parent depth + 1
+   * for a subagent child. Persisted so a recursion budget survives restart and
+   * resume — a runtime-only depth would reset a resumed child to top-level.
+   */
+  readonly delegationDepth?: number
 }
 
 /**
@@ -69,6 +72,7 @@ export interface CreateSessionOptions {
     readonly parentSession?: SessionId
     readonly createdAt?: number
     readonly seedLength?: number
+    readonly delegationDepth?: number
   }
 }
 
@@ -109,8 +113,8 @@ export interface TurnEndReasonMap {
   /** At least one step reached its output-token ceiling, even if a plugin continued the turn. */
   'max-tokens': { kind: 'max-tokens' }
   /**
-   * Policy blocked every prompt before the first step. The zero-step turn still
-   * records a balanced durable boundary and the veto reason.
+   * Policy blocked the turn's claimed prompt before the first step. The
+   * zero-step turn still records a balanced durable boundary and veto reason.
    */
   rejected: { kind: 'rejected'; reason: string }
   /**
@@ -179,40 +183,44 @@ export type RequestHeaderReason = 'initial' | 'resume' | 'change'
  */
 export interface SessionEventMap {
   /**
-   * Opens turn `turn`. `trigger` records what started it — a drained message
-   * batch or an idle-time injection. The turn is the durability/replay
+   * Opens turn `turn`. `trigger` records what started it — one claimed queued
+   * message or an idle-time injection. The turn is the durability/replay
    * boundary: every event sits between a `turn/start` and its matching
    * `turn/end` (the turn-enclosure invariant).
    */
   'turn/start': { turn: number; trigger: TurnTrigger }
   /**
    * Closes turn `turn` with the {@link TurnEndReason} that ended it. The loop
-   * fires the awaited `session/flush` checkpoint at every turn end, so the turn
-   * boundary is also the durable-commit boundary.
+   * awaits `session/flush` after an ordinary turn ends before claiming the next
+   * queued item. Success commits the turn; rejection is reported live and does
+   * not prevent later work.
    */
   'turn/end': { turn: number; reason: TurnEndReason }
   /** Opens step `step` of turn `turn` — one model call plus the tool executions it requested. */
   'step/start': { turn: number; step: number }
   /** Closes step `step` of turn `turn`. */
   'step/end': { turn: number; step: number }
-  /** A user-visible prompt (queued message drained at turn start). */
+  /** A user-visible prompt (the queued message claimed for this turn). */
   'user/message': { content: ContentBlock[]; source: MessageSource }
   /**
    * Durable record of a prompt veto and its reason. It is log-only: the blocked
-   * prompt never enters the model-visible surface, including in a mixed batch.
+   * prompt never enters the model-visible surface, and its turn runs zero steps.
    */
   'prompt/blocked': { content: ContentBlock[]; source: MessageSource; reason: string }
   /**
    * In-session context injection (file-change notices, subdir AGENTS.md,
    * skill content, cron notifications, …). Rendered into the derived history
-   * as synthetic context — NOT a user prompt. `envelope: 'raw'` lets a caller
-   * own the complete model-facing frame; `meta` is durable JSON state omitted
-   * from the model projection.
+   * as a synthetic user-role message carrying `content` verbatim — NOT a
+   * user prompt. `meta` is durable JSON state omitted from the model
+   * projection; it is also the intended channel for any future framing
+   * directive (a producer declares the frame, a dedicated renderer applies it —
+   * see the deferred note in
+   * ../../../../.agents/notes/implemented/simplification/2026-07-20-unwrap-injected-content-envelopes.md),
+   * so the surface keeps projecting `content` verbatim rather than wrapping it.
    */
   'context/message': {
     content: ContentBlock[]
     source: MessageSource
-    envelope?: ContextEnvelope
     meta?: JsonValue
   }
   /** Raw stream chunk — token-level replay fidelity. */

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

@@ -48,7 +48,7 @@ describe('Session', () => {
     expect(structuredClone(turnEnd.data.reason)).toEqual({ kind: 'max-tokens' })
   })
 
-  it('renders context and steering messages as tagged synthetic user content', () => {
+  it('renders context and steering messages as plain user content', () => {
     const session = new Session(SessionId('s2'))
     session.append('context/message', {
       content: [{ type: 'text', text: 'file changed: a.ts' }],
@@ -62,12 +62,12 @@ describe('Session', () => {
 
     const [contextMessage, steeringMessage] = session.deriveMessages()
     expect(contextMessage!.role).toBe('user')
-    expect(contextMessage!.content[0]).toMatchObject({ type: 'text', text: '<context source="plugin">' })
-    expect(contextMessage!.content.at(-1)).toMatchObject({ type: 'text', text: '</context>' })
-    expect(steeringMessage!.content[0]).toMatchObject({ type: 'text', text: '<steering source="user">' })
+    expect(contextMessage!.content).toEqual([{ type: 'text', text: 'file changed: a.ts' }])
+    expect(steeringMessage!.role).toBe('user')
+    expect(steeringMessage!.content).toEqual([{ type: 'text', text: 'focus on tests' }])
   })
 
-  it('renders raw context without a generic envelope while preserving structured metadata', () => {
+  it('keeps context meta durable in the event while hiding it from the projection', () => {
     const session = new Session(SessionId('s2-raw'))
     const meta = {
       kind: 'workspace-instructions',
@@ -77,7 +77,6 @@ describe('Session', () => {
     session.append('context/message', {
       content: [{ type: 'text', text: '<system-reminder>Additional instructions from: pkg/AGENTS.md</system-reminder>' }],
       source: { kind: 'plugin', plugin: 'workspace-context' },
-      envelope: 'raw',
       meta,
     }, { surfaceOp: 'append' })
 
@@ -882,6 +881,19 @@ describe('SessionStore', () => {
     })
   })
 
+  it('attaches delegationDepth from meta to the header', async () => {
+    const ctx = new Context()
+    await ctx.plugin(SessionStore)
+    const session = ctx.sessions.create(SessionId('delegated-child'), {
+      meta: { parentSession: SessionId('parent'), delegationDepth: 2 },
+    })
+    expect(session.header).toMatchObject({
+      id: 'delegated-child',
+      parentSession: 'parent',
+      delegationDepth: 2,
+    })
+  })
+
   it('rejects non-JSON and invalid scalar session metadata', async () => {
     const ctx = new Context()
     await ctx.plugin(SessionStore)
@@ -893,6 +905,9 @@ describe('SessionStore', () => {
       { meta: { seedLength: '1' }, error: /seedLength must be a non-negative safe integer/ },
       { meta: { seedLength: 0.5 }, error: /seedLength must be a non-negative safe integer/ },
       { meta: { seedLength: -1 }, error: /seedLength must be a non-negative safe integer/ },
+      { meta: { delegationDepth: '1' }, error: /delegationDepth must be a non-negative safe integer/ },
+      { meta: { delegationDepth: 0.5 }, error: /delegationDepth must be a non-negative safe integer/ },
+      { meta: { delegationDepth: -1 }, error: /delegationDepth must be a non-negative safe integer/ },
     ]
 
     for (const [index, { meta, error }] of cases.entries()) {

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

@@ -369,8 +369,8 @@ describe('deriveMessages with surface', () => {
     s.append('steering/message', { turn: 1, content: [{ type: 'text', text: 'focus' }], source: { kind: 'user' } }, { surfaceOp: 'append' })
     const messages = s.deriveMessages()
     expect(messages).toHaveLength(2)
-    expect(messages[0]!.content[0]).toMatchObject({ type: 'text', text: '<context source="plugin">' })
-    expect(messages[1]!.content[0]).toMatchObject({ type: 'text', text: '<steering source="user">' })
+    expect(messages[0]!.content).toEqual([{ type: 'text', text: 'file changed' }])
+    expect(messages[1]!.content).toEqual([{ type: 'text', text: 'focus' }])
   })
 })
 

packages/core/tools/README.md

@@ -38,7 +38,7 @@ The live registry pipeline has three transformable waterfalls followed by the ob
 - `ToolExecutionToken` — a fresh branded `Symbol` assigned by the registry. It supports equality correlation only and never crosses a model, log, or worker boundary.
 - `ToolExecution` — the pipeline-owned call: immutable `{ token, callId, name, arguments, agent?, parent? }` identity plus optional operational `signal`, which an around wrapper may add, replace, remove, and restore. A nested call's `parent` is a `ToolExecutionToken`, not an execution object.
 - `ToolRunContext` — the execution passed to a tool body, extending `ToolExecution` with `deferContext(context)`. Composite tools use it to ferry context produced by nested dispatches to the outer result even when the tool later throws; it never injects immediately.
-- `ToolExecutionResult` — losslessly JSON-serializable outcome: `{ content, isError, error?, additionalContexts?, meta? }`. Call identity stays on the immutable `ToolExecution` supplied alongside the result instead of being duplicated on the outcome. The registry materializes and freezes the complete post-policy value before final observation. On failure with a `HarnessError`, `error: { name, code }` carries the structured failure class alongside the model-facing text. `additionalContexts` preserves each deferred or post-execute `HookContext` with its own source, envelope, and durable JSON metadata; the loop buffers the array and appends each entry as a `context/message` after all `tool/result`s in the step.
+- `ToolExecutionResult` — losslessly JSON-serializable outcome: `{ content, isError, error?, additionalContexts?, meta? }`. Call identity stays on the immutable `ToolExecution` supplied alongside the result instead of being duplicated on the outcome. The registry materializes and freezes the complete post-policy value before final observation. On failure with a `HarnessError`, `error: { name, code }` carries the structured failure class alongside the model-facing text. `additionalContexts` preserves each deferred or post-execute `HookContext` with its own source and durable JSON metadata; the loop buffers the array and appends each entry as a `context/message` after all `tool/result`s in the step.
 - `PreToolDecision` — `{kind:'allow'}` | `{kind:'deny', reason}` | `{kind:'ask', reason?}`. Input rewrite is deliberately not offered; `ask` is serviced by [`ctx.approval`](../../ui/user-approval/README.md) when mounted and otherwise degrades to deny.
 - `PostToolDecision` — `{kind:'accept', content?, additionalContexts?}` (keep the call successful, optionally replacing the model-facing content) | `{kind:'block', feedback, additionalContexts?}` (turn it into an `isError` whose content is the corrective feedback). Accept preserves tool-deferred contexts before decision contexts; block discards tool-deferred contexts and exposes only contexts explicitly supplied by the blocking decision.
 - `ToolGuard` — `(execution) => string | undefined`; the returned string is a final monotonic denial reason evaluated after the reorderable pre-execute waterfall and before dispatch.
@@ -108,7 +108,7 @@ Returning `undefined` selects generic fallback. Presenters depend only on their
 Under `code` or `both`, the registry exposes the reserved `run_code` transport and a deterministic TypeScript SDK for the current scope; only program output re-enters model context. Each JSON-normalized binding re-enters the complete tool pipeline sequentially with logged correlation to the outer call. Denials reject that binding, ordinary side effects are not rolled back, and sub-call `additionalContexts` are deferred through the parent result to preserve call/result adjacency. Run settlement aborts and drains outstanding bindings; failures surface as `CodeRunFailedError`. See the [Code Mode Agent Note](../../../.agents/notes/implemented/feature/2026-06-15-code-mode.md) and [code-runtime seam](../../code-runtime/README.md). Try `pnpm run demo:code-mode`.
 
 - **The SDK section** (`tools:sdk`, order 150): a lazy prompt section regenerating, at each assembly, a `declare const tools: {...}` TypeScript declaration of the calling scope's visible end capabilities (exotic names via quoted keys), plus fixed usage instructions. Deterministic — lexicographic tool order, byte-identical text for an unchanged tool set (prefix-cache-friendly). The codegen (`jsonSchemaToTs`, exported) is total: constructs outside the `defineTool` subset degrade to `unknown`, never throw.
-- **The dispatch bridge** (`run_code`'s execute): every binding call is JSON-normalized before dispatch (a value that does not survive — `BigInt`, circulars — rejects that one call, so the dispatched form and logged form are the same JSON value by construction), serialized through a per-run queue (even `Promise.all` executes underlying calls one at a time in submission order), given the outer execution's opaque token as `parent`, and run through the complete pre-execute → guards → execute → post-execute → result pipeline. A denial reaches the program as a binding rejection, and each sub-call is logged as a `tool/code-dispatch` session event with deterministic id `<parent>:code:<n>`; `deriveMessages()` does not surface that event. Token correlation lets commit-style observers defer an inner success until the final `run_code` result without exposing the live outer execution; ordinary tool side effects are not rolled back. Every sub-call `additionalContexts` entry is deferred through the outer `ToolRunContext` in dispatch order; the loop appends those contexts only after the parent `run_code` result, preserving adjacency and retaining each source/envelope/meta even when the program later fails.
+- **The dispatch bridge** (`run_code`'s execute): every binding call is JSON-normalized before dispatch (a value that does not survive — `BigInt`, circulars — rejects that one call, so the dispatched form and logged form are the same JSON value by construction), serialized through a per-run queue (even `Promise.all` executes underlying calls one at a time in submission order), given the outer execution's opaque token as `parent`, and run through the complete pre-execute → guards → execute → post-execute → result pipeline. A denial reaches the program as a binding rejection, and each sub-call is logged as a `tool/code-dispatch` session event with deterministic id `<parent>:code:<n>`; `deriveMessages()` does not surface that event. Token correlation lets commit-style observers defer an inner success until the final `run_code` result without exposing the live outer execution; ordinary tool side effects are not rolled back. Every sub-call `additionalContexts` entry is deferred through the outer `ToolRunContext` in dispatch order; the loop appends those contexts only after the parent `run_code` result, preserving adjacency and retaining each source/meta even when the program later fails.
 - **Settlement discipline**: the bridge owns a run-scoped abort that follows the outer signal in and fires when the run settles for any reason, so a budget expiry aborts an in-flight sub-tool instead of orphaning it; the bridge then drains its queue BEFORE returning, so every `tool/code-dispatch` lands inside the open turn. A failed run throws `CodeRunFailedError` (`code: 'CODE_RUN_FAILED'`, message = the failure kind + captured logs), which the pipeline converts to a structured `isError` the model self-corrects from.
 
 ### Parallel execution

packages/core/tools/src/index.ts

@@ -235,8 +235,8 @@ export interface ToolExecution extends ToolExecutionInput {
 export interface ToolRunContext extends ToolExecution {
   /**
    * Defer one nested-dispatch context until this tool's final result reaches
-   * the agent loop. Contexts retain their individual source, envelope, and
-   * metadata and are emitted in call order.
+   * the agent loop. Contexts retain their individual source and metadata and
+   * are emitted in call order.
    */
   deferContext(context: HookContext): void
 }
@@ -958,14 +958,19 @@ export class ToolRegistry extends Service {
     // Freeze the remaining mutable signal slot before observers receive the
     // shared WeakMap-keyable execution object.
     Object.freeze(exec)
+    const { name: toolName, callId } = exec
+    const reportFailure = (error: unknown): void => {
+      this.ctx.logger.warn(`tool "${toolName}" (${callId}): tools/result observer failed: ${errorMessage(error)}`)
+    }
     const callbacks = this.ctx.events.dispatch('emit', [
       scopeTarget(this, exec.agent), 'tools/result', exec, result,
     ])
     for (const callback of callbacks) {
       try {
-        callback(exec, result)
+        const returned: unknown = callback(exec, result)
+        void Promise.resolve(returned).catch(reportFailure)
       } catch (error: unknown) {
-        this.ctx.logger.warn(`tool "${exec.name}" (${exec.callId}): tools/result observer failed: ${errorMessage(error)}`)
+        reportFailure(error)
       }
     }
   }

packages/core/tools/tests/code-mode.spec.ts

@@ -487,7 +487,6 @@ describe('the run_code dispatch bridge', () => {
           additionalContexts: [{
             content: [{ type: 'text' as const, text: `context for ${exec.callId}` }],
             source: { kind: 'plugin' as const, plugin: 'test' },
-            envelope: 'raw' as const,
             meta: { callId: exec.callId },
           }],
         })
@@ -505,13 +504,11 @@ describe('the run_code dispatch bridge', () => {
       {
         content: [{ type: 'text', text: 'context for call-1:code:1' }],
         source: { kind: 'plugin', plugin: 'test' },
-        envelope: 'raw',
         meta: { callId: 'call-1:code:1' },
       },
       {
         content: [{ type: 'text', text: 'context for call-1:code:2' }],
         source: { kind: 'plugin', plugin: 'test' },
-        envelope: 'raw',
         meta: { callId: 'call-1:code:2' },
       },
     ])

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

@@ -582,13 +582,18 @@ describe('scoped execution dispatch', () => {
     ctx.on('tools/result', () => {
       throw { toString: () => { throw new Error('coercion trap') } }
     })
+    ctx.on('tools/result', () => Promise.reject(new Error('async observer failure')) as never)
     ctx.on('tools/result', (_exec, result) => { seen.push(result.isError) })
 
     const result = await ctx.tools.execute({ callId: CallId('final'), name: 't', arguments: {}, agent: key })
+    await Promise.resolve()
     expect(result).toMatchObject({ isError: true, content: [{ type: 'text', text: 'outer failure' }] })
     expect(seen).toEqual([true, true])
     expect(dispatchModes).toEqual(['emit'])
-    expect(warn).toHaveBeenCalledOnce()
-    expect(String(warn.mock.calls[0]?.[0])).toContain('<unprintable thrown value>')
+    expect(warn).toHaveBeenCalledTimes(2)
+    expect(warn.mock.calls.map(call => String(call[0]))).toEqual(expect.arrayContaining([
+      expect.stringContaining('<unprintable thrown value>'),
+      expect.stringContaining('async observer failure'),
+    ]))
   })
 })

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

@@ -384,7 +384,7 @@ describe('ToolRegistry', () => {
       parameters: {},
       async execute(_args, exec) {
         exec.deferContext({ content: [{ type: 'text', text: 'nested-1' }], source: { kind: 'plugin', plugin: 'nested-1' }, meta: { n: 1 } })
-        exec.deferContext({ content: [{ type: 'text', text: 'nested-2' }], source: { kind: 'plugin', plugin: 'nested-2' }, envelope: 'raw' })
+        exec.deferContext({ content: [{ type: 'text', text: 'nested-2' }], source: { kind: 'plugin', plugin: 'nested-2' } })
         return [{ type: 'text', text: 'done' }]
       },
     }))
@@ -418,7 +418,6 @@ describe('ToolRegistry', () => {
       { kind: 'plugin', plugin: 'post' },
     ])
     expect(result.additionalContexts?.[0]?.meta).toEqual({ n: 1 })
-    expect(result.additionalContexts?.[1]?.envelope).toBe('raw')
   })
 
   it('keeps deferred contexts when a composite tool throws, but drops them when the outer call is blocked', async () => {

packages/examples/acp-demo/README.md

@@ -34,13 +34,14 @@ Because the package wires no logger entry, an ACP leaf has **nothing to get wron
 | `toolOrder` | — | explicit model-facing tool order (a name list with one `'<unlisted-tools>'` rest entry; absent — lexicographic; an unregistered name fails each turn at prompt assembly), routed to `dsh-system-prompt` |
 | `dshHome` | `$DSH_HOME` or `~/.dsh` | Harness home exposed to model bash and used by local skill discovery |
 | `tools` | `{ mode: 'native' }` | tool-registry presentation config (`native` / `code` / `both`), routed through `dsh-agent-spine-demo` |
+| `workspaceContext` | (required) | workspace-instruction byte budget/config, or `false`; routed to the providerless-safe `dsh-workspace-context` plugin |
 | `skills` | owner defaults | registry-cache, local-provider, and model-facing skill-tool config, routed through `dsh-agent-spine-demo` |
 | `toolBash` | owner defaults | model-facing bash config routed through `dsh-agent-spine-demo`, including bash's producer-local `enableRunInBackground` |
 | `toolTasks` | owner defaults | generic `task_output` wait bounds routed through `dsh-agent-spine-demo` |
 | `goals` | owner defaults | persisted goal-domain and model-tool config; `false` removes the goal stack and `/goal` producer |
 | `persistenceRoot` | `./.sessions` | the JSONL backend's root directory |
 
-The leaf supplies the swappable backends: an LLM adapter (`llm-deepseek` for the real model, `llm-replay` for keyless snapshot replay) and a bash executor.
+The leaf supplies the swappable backends: an LLM adapter (`llm-deepseek` for the real model, `llm-replay` for keyless snapshot replay), a bash executor, and optionally a `ctx.fs` provider. Workspace context becomes a no-op without `ctx.fs`; the shipped [`examples/acp-agent/cordis.yml`](../../../examples/acp-agent/cordis.yml) selects `dsh-sandbox-policy`, `dsh-fs-sandbox`, `dsh-fs-policy`, and `dsh-tool-fs` so baseline instructions and model-facing `read`/`write`/`edit` share one provider, sandbox mode, workspace root, and observed-version policy.
 
 ## The bin
 

packages/examples/agent-spine-demo/src/index.ts

@@ -162,7 +162,7 @@ export function apply(ctx: Context, config: Config): void {
   const nestedDshHome = config.skills?.local?.dshHome
   if (config.dshHome !== undefined && nestedDshHome !== undefined
     && resolveDshHome(config.dshHome) !== resolveDshHome(nestedDshHome)) {
-    throw new Error('agent-core: dshHome and skills.local.dshHome must resolve to the same directory')
+    throw new Error('agent-spine-demo: dshHome and skills.local.dshHome must resolve to the same directory')
   }
   const dshHome = resolveDshHome(config.dshHome ?? nestedDshHome)
 

packages/examples/agent-spine-demo/tests/agent-core.spec.ts

@@ -326,7 +326,7 @@ describe('dsh-agent-spine-demo bundle', () => {
         workspaceContext: false,
         skills: { local: { dshHome: '/nested-dsh-home' } },
       })
-    }).toThrow(/must resolve to the same directory/)
+    }).toThrow('agent-spine-demo: dshHome and skills.local.dshHome must resolve to the same directory')
   })
 
   it('places workspace instructions before the skill catalog in the session prefix', async () => {

packages/examples/stdio-demo/tests/built-bin.e2e.ts

@@ -104,8 +104,8 @@ async function makeConsumer(
   return dir
 }
 
-/** Run the built bin in `cwd` against `configArg` with one stdin line; resolve with stdout/stderr + exit code. */
-function runBuiltBin(cwd: string, configArg: string, line: string): Promise<{ stdout: string; code: number; stderr: string }> {
+/** Run the built bin in `cwd` against `configArg` with piped stdin; resolve with stdout/stderr + exit code. */
+function runBuiltBin(cwd: string, configArg: string, input: string): Promise<{ stdout: string; code: number; stderr: string }> {
   return new Promise((resolve, reject) => {
     // --expose-internals: the cordis Loader resolves bare plugin specifiers via
     // its internal module loader (active only under this flag); demo:echo passes
@@ -128,7 +128,7 @@ function runBuiltBin(cwd: string, configArg: string, line: string): Promise<{ st
     }, 25_000)
     child.on('exit', (code) => { clearTimeout(timer); resolve({ stdout, code: code ?? -1, stderr }) })
     child.on('error', (err) => { clearTimeout(timer); reject(err) })
-    child.stdin.write(`${line}\n`)
+    child.stdin.write(`${input}\n`)
     child.stdin.end()
   })
 }
@@ -167,6 +167,17 @@ describe.skipIf(!existsSync(stdioBin))('dsh-stdio-demo BUILT bin (node lib/bin.j
     expect(code).toBe(0)
   }, 30_000)
 
+  it('runs two synchronously piped lines as two ordinary turns', async () => {
+    consumer = await makeConsumer('TWO-TURNS ready.')
+    const { stdout, code, stderr } = await runBuiltBin(consumer, './cordis.yml', 'first\nsecond')
+    expect(stderr).not.toContain('UNHANDLED')
+    expect(stdout).toContain('[main turn 1]')
+    expect(stdout).toContain('You said: "first"')
+    expect(stdout).toContain('[main turn 2]')
+    expect(stdout).toContain('You said: "second"')
+    expect(code).toBe(0)
+  }, 30_000)
+
   it('boots when optional spill plugins are loaded from a built consumer install', async () => {
     consumer = await makeConsumer(
       'SPILL-OK ready.',

packages/fs/README.md

@@ -6,11 +6,12 @@ The filesystem stack: a provider seam (text IO + atomic mutation with an optiona
 |---|---|---|
 | `fs/` | Provider seam: text IO + atomic mutation primitives (optional version guard); owns the `fs/*` policy events | `ctx.fs` |
 | `fs-local/` | Local-filesystem `FileSystem` implementation | (registers `ctx.fs`) |
+| `fs-sandbox/` | Sandbox-enforcing `FileSystem`: extends `fs-local` and fences write/edit by the per-call sandbox mode (read-only denies, workspace-write contains to the workspace + temp roots), reads pass through | (registers `ctx.fs`) |
 | `fs-policy/` | Policy gate plugin: observed-state + read-before-edit + version-guarded write/edit, via the `fs/*` event gate | (no service — `fs/*` listeners) |
-| `tool-fs/` | Model-facing `read`/`write`/`edit` tools AND the executor (reads via `ctx.fs`, owns read windowing, dispatches `fs/*`) | (registers on `ctx.tools`) |
+| `tool-fs/` | Model-facing `read`/`write`/`edit` tools AND the executor (reads via `ctx.fs`, owns read windowing, dispatches `fs/*`); advertises the sandbox escalation fields when the mounted `ctx.fs` confines | (registers on `ctx.tools`) |
 | `tool-fs-search/` | Model-facing `glob`/`grep` discovery tools when `rg` is available on the bash executor `PATH`, backed by fixed ripgrep commands through `ctx.bash`, NOT by `ctx.fs` provider methods | (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. Discovery (`tool-fs-search/`) deliberately does NOT extend the provider seam: search is a process-backed `rg` workflow on the bash executor, so filesystem backends stay free of a universal search contract; its tools register only when that executor can find `rg`, and its results are follow-up-readable when the bash workdir and the `read` root are the same workspace (the co-located deployment its README documents).
+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 — `fs-sandbox` is the first such replacement (an in-process path fence over the shared sandbox mode; see [the cross-family fs sandbox Agent Note](../../.agents/notes/implemented/feature/2026-07-14-cross-family-fs-sandbox.md)). 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. The mode fence and the read-before-edit gate are orthogonal and compose. Discovery (`tool-fs-search/`) deliberately does NOT extend the provider seam: search is a process-backed `rg` workflow on the bash executor, so filesystem backends stay free of a universal search contract; its tools register only when that executor can find `rg`, and its results are follow-up-readable when the bash workdir and the `read` root are the same workspace (the co-located deployment its README documents).
 
 ## No timeouts on file IO
 

packages/fs/fs-sandbox/README.md

@@ -0,0 +1,33 @@
+# dsh-fs-sandbox — the sandbox-enforcing filesystem backend
+
+`SandboxedFileSystem` extends [`LocalFileSystem`](../fs-local/README.md) and registers as `ctx.fs`. It inherits every text-storage mechanic verbatim (resolve, stat, read/stream, list, the atomic write, the read-match-write edit critical section) and adds only a per-call MODE fence on `writeText`/`editText`. Reads always pass through — every mode permits reading.
+
+Loading it INSTEAD OF `dsh-fs-local`, together with a [`ctx.sandboxPolicy`](../../sandbox/sandbox-policy/README.md), is the whole swap; the model-facing tools (`dsh-tool-fs`) are untouched. Injects `sandboxPolicy` for the default mode and the `workspace-write` boundary root — the SAME policy home bash reads, so the two families never confine to different roots.
+
+## The fence
+
+The per-call mode is the tool-stamped effective mode (session override or escalation grant), falling back to the deployment default:
+
+- `read-only` — denies every mutation with the structured `FS_SANDBOX_DENIED`.
+- `workspace-write` — allows a mutation only when the target canonicalizes under a writable root: the workspace root plus the platform temp areas (`/tmp`, `os.tmpdir()`), the SAME set the Seatbelt profile grants, derived from the one [`writableRoots`](../../sandbox/README.md) function so the fs fence and the bash runner cannot drift. The target is re-canonicalized immediately before delegating, so an ancestor symlink swapped since the tool resolved it is caught.
+- `danger-full-access` — delegates unfenced.
+
+## Threat model: a policy fence, not a kernel boundary
+
+The fence is a check in TRUSTED code over a MODEL-CONTROLLED path — the operations are the seam's own (open, rename), only the target path is untrusted, so canonicalize-then-contain is the complete answer to this surface. This mirrors the `code-runtime` stance: containment, not a security boundary. Kernel-grade isolation of untrusted CODE stays `ctx.bash`'s job ([`dsh-bash-sandbox`](../../bash/bash-sandbox/README.md)). The residual TOCTOU (an ancestor symlink swapped between the containment re-check and the syscall) is narrowed by re-canonicalizing immediately before the write and is accepted for this threat model; a kernel-tight boundary needs `openat2`-class primitives not worth their portability cost here.
+
+A denial is a structured `FsError` (`FS_SANDBOX_DENIED`, carrying the effective mode) — no stderr text inference (unlike bash's kernel denials), because an in-process fence knows exactly what it refused. The model-facing `[sandbox: file access denied under <mode> mode]` marker and the one-approved-wider retry live in the tool layer (`dsh-tool-fs`), exactly as bash's do. See [the cross-family fs sandbox RFC](../../../.agents/notes/implemented/feature/2026-07-14-cross-family-fs-sandbox.md).
+
+## Model Experience
+
+Indirectly, through `dsh-tool-fs`, which renders this backend's `FS_SANDBOX_DENIED` refusals as the `[sandbox: file access denied under <mode> mode]` marker plus the same-turn escalation hint.
+
+#### KV Cache effect
+
+No direct invalidation; the named consumer owns any request-prefix changes.
+
+## Known Limitations and Deferred Work
+
+- **A policy fence, not a kernel boundary** — the check is trusted code over a model-controlled path, so the residual resolve-to-syscall TOCTOU is narrowed (by the in-place re-canonicalization) but not eliminated; adversarial host processes are out of scope. Kernel-grade isolation of untrusted code stays `ctx.bash`'s.
+- **Fence-vs-runner parity is derived, not asserted** — the writable set comes from `writableRoots`, shared with the Seatbelt profile and pinned by a parity test; a runner profile that changed its writable set without that function would drift.
+- **Requires `ctx.sandboxPolicy`** — the backend reads the default mode and workspace root from it and does not confine without it composed.

packages/fs/fs-sandbox/package.json

@@ -0,0 +1,38 @@
+{
+  "name": "@deepseek-ai/dsh-fs-sandbox",
+  "description": "Sandbox-enforcing implementation of the DeepSeek Harness filesystem seam: fences write/edit by the per-call sandbox mode (read-only denies mutation, workspace-write contains it to the workspace + temp roots) while reads pass through",
+  "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-fs": "^0.0.1",
+    "@deepseek-ai/dsh-fs-local": "^0.0.1",
+    "@deepseek-ai/dsh-sandbox": "^0.0.1",
+    "@deepseek-ai/dsh-sandbox-policy": "^0.0.1",
+    "cordis": "^4.0.0-rc.7"
+  },
+  "devDependencies": {
+    "@deepseek-ai/dsh-fs": "workspace:^",
+    "@deepseek-ai/dsh-fs-local": "workspace:^",
+    "@deepseek-ai/dsh-sandbox": "workspace:^",
+    "@deepseek-ai/dsh-sandbox-policy": "workspace:^",
+    "cordis": "^4.0.0-rc.7"
+  }
+}

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

@@ -0,0 +1,157 @@
+/**
+ * `SandboxedFileSystem`: the sandbox-enforcing implementation of the
+ * `@deepseek-ai/dsh-fs` provider seam. It extends `LocalFileSystem` so all
+ * text-storage mechanics — resolve, stat, read/stream, list, the atomic
+ * write and the read-match-write edit critical section — are the local
+ * implementation's, verbatim; this package adds only the per-call MODE fence
+ * on the two mutations. Reads pass through untouched: every mode permits
+ * reading.
+ *
+ * The fence is a policy check in TRUSTED code over a MODEL-CONTROLLED path,
+ * NOT a kernel boundary — the operations are the seam's own (open, rename),
+ * and only the target path is untrusted, so canonicalize-then-contain is the
+ * complete answer to this surface. Kernel-grade isolation of untrusted CODE
+ * stays `ctx.bash`'s job (`@deepseek-ai/dsh-bash-sandbox`). This mirrors the
+ * `code-runtime` stance: containment, not a security boundary. The residual
+ * TOCTOU (an ancestor symlink swapped between the containment re-check and the
+ * syscall) is narrowed by re-canonicalizing immediately before delegating and
+ * is accepted for this threat model.
+ *
+ * Per-call mode: `read-only` denies every mutation; `workspace-write` allows a
+ * mutation only when the target canonicalizes under the workspace root or a
+ * platform temp area (the SAME writable-root set the Seatbelt profile grants,
+ * derived from the one `writableRoots` function so bash and fs cannot drift);
+ * `danger-full-access` delegates unfenced. A denial throws the structured
+ * `FS_SANDBOX_DENIED` — no text inference is needed (unlike bash's kernel
+ * stderr), because an in-process fence knows exactly what it refused. The
+ * escalation retry lives in the tool layer (`@deepseek-ai/dsh-tool-fs`),
+ * exactly as bash's does.
+ *
+ * @module @deepseek-ai/dsh-fs-sandbox
+ */
+
+import { sep } from 'node:path'
+import { Context } from 'cordis'
+import { LocalFileSystem } from '@deepseek-ai/dsh-fs-local'
+import type { Config as LocalConfig } from '@deepseek-ai/dsh-fs-local'
+import { FsError } from '@deepseek-ai/dsh-fs'
+import type { FsEditOutcome, FsEditRequest, FsTarget, FsVersion, FsWriteIntent, FsWriteOutcome } from '@deepseek-ai/dsh-fs'
+import { writableRoots } from '@deepseek-ai/dsh-sandbox'
+import type { SandboxMode } from '@deepseek-ai/dsh-sandbox'
+import type {} from '@deepseek-ai/dsh-sandbox-policy'
+
+/**
+ * Plugin config: the local backend's knobs, verbatim (only `cwd`, the resolve
+ * base for relative paths). The sandbox default (mode + `workspace-write`
+ * boundary root) is NOT here — it lives on `ctx.sandboxPolicy`, the one home
+ * both enforcing families share.
+ */
+export type Config = LocalConfig
+
+/** Whether `path` is `root` itself or lies beneath it (both already canonical). */
+function isUnder(path: string, root: string): boolean {
+  if (path === root) return true
+  const prefix = root.endsWith(sep) ? root : root + sep
+  return path.startsWith(prefix)
+}
+
+/**
+ * Sandbox-enforcing filesystem backend. Registers as `ctx.fs` (loading it
+ * INSTEAD OF `dsh-fs-local`, together with a `ctx.sandboxPolicy`, is the whole
+ * swap — the model-facing tools are untouched). Its configured default mode is
+ * the fallback exposed by {@link sandboxMode}; `dsh-tool-fs` folds a session's
+ * `sandbox/mode` override and stamps the effective mode onto each mutation,
+ * while an approved escalation may stamp a strictly wider mode for one call.
+ */
+export class SandboxedFileSystem extends LocalFileSystem {
+  static inject = ['sandboxPolicy']
+
+  private readonly defaultMode: SandboxMode
+  /**
+   * The canonical roots a `workspace-write` mutation may land under, computed
+   * once (the workspace root and platform temp areas are fixed for the
+   * provider's lifetime): the same set {@link writableRoots} gives every
+   * enforcement dialect, so the fs fence and the bash runner agree.
+   */
+  private readonly writableRoots: string[]
+
+  constructor(ctx: Context, config: Config) {
+    super(ctx, config)
+    this.defaultMode = ctx.sandboxPolicy.defaultMode
+    this.writableRoots = writableRoots({ mode: 'workspace-write', workspaceRoot: ctx.sandboxPolicy.workspaceRoot })
+  }
+
+  /** The deployment default mode — the capability fact the tool layer reads to advertise escalation. */
+  override get sandboxMode(): SandboxMode {
+    return this.defaultMode
+  }
+
+  /**
+   * Fence the write by the per-call mode, then delegate to the inherited
+   * atomic write. See {@link checkedTarget}.
+   * @param target - the resolved target to write.
+   * @param content - the full new file content.
+   * @param expected - the write intent guarding the write; omit for unconditional.
+   * @param signal - aborts before the atomic rename takes effect.
+   * @param sandboxMode - the per-call mode; omit to use the deployment default.
+   * @returns the write outcome from the inherited backend.
+   */
+  override async writeText(
+    target: FsTarget,
+    content: string,
+    expected?: FsWriteIntent,
+    signal?: AbortSignal,
+    sandboxMode?: SandboxMode,
+  ): Promise<FsWriteOutcome> {
+    return super.writeText(await this.checkedTarget(target, sandboxMode), content, expected, signal)
+  }
+
+  /**
+   * Fence the edit by the per-call mode, then delegate to the inherited
+   * atomic edit. See {@link checkedTarget}.
+   * @param target - the resolved target to edit.
+   * @param edit - the literal search/replace request.
+   * @param expected - the version guard; omit for an unconditional edit.
+   * @param signal - aborts before the atomic rename takes effect.
+   * @param sandboxMode - the per-call mode; omit to use the deployment default.
+   * @returns the edit outcome from the inherited backend.
+   */
+  override async editText(
+    target: FsTarget,
+    edit: FsEditRequest,
+    expected?: { version: FsVersion },
+    signal?: AbortSignal,
+    sandboxMode?: SandboxMode,
+  ): Promise<FsEditOutcome> {
+    return super.editText(await this.checkedTarget(target, sandboxMode), edit, expected, signal)
+  }
+
+  /**
+   * Enforce the per-call mode against `target` and return the EXACT target the
+   * mutation must use, so the checked identity is the mutated one (no
+   * check-here-write-there TOCTOU). `read-only` denies; `workspace-write`
+   * re-canonicalizes NOW (`resolve` realpaths the deepest existing ancestor,
+   * reflecting a concurrently swapped symlink), requires containment under a
+   * writable root, and returns THAT fresh target; `danger-full-access` returns
+   * the caller's target unfenced. Throws the structured `FS_SANDBOX_DENIED` on
+   * refusal — the tool layer maps it to the model-facing `[sandbox: …]` marker
+   * and the escalation hint.
+   */
+  private async checkedTarget(target: FsTarget, sandboxMode?: SandboxMode): Promise<FsTarget> {
+    const mode = sandboxMode ?? this.defaultMode
+    if (mode === 'danger-full-access') return target
+    if (mode === 'read-only') {
+      throw new FsError(`cannot write "${target.displayPath}": file access denied under read-only mode`, 'FS_SANDBOX_DENIED')
+    }
+    // workspace-write: containment on the FRESH canonical path (catches a
+    // symlink ancestor swapped since the tool resolved this target), and the
+    // mutation delegates with THIS fresh target — never the stale one.
+    const fresh = await this.resolve(target.displayPath)
+    if (!this.writableRoots.some(root => isUnder(fresh.targetKey, root))) {
+      throw new FsError(`cannot write "${target.displayPath}": file access denied under workspace-write mode`, 'FS_SANDBOX_DENIED')
+    }
+    return fresh
+  }
+}
+
+export default SandboxedFileSystem

packages/fs/fs-sandbox/tests/fs-sandbox.spec.ts

@@ -0,0 +1,237 @@
+/**
+ * Tests for the sandbox-enforcing filesystem backend: the per-call mode fence
+ * on write/edit (read-only denies, workspace-write contains, danger-full-access
+ * passes through), reads always passing through, the capability fact, and the
+ * containment matrix — `..` traversal, absolute paths outside, and symlink
+ * escapes (a symlinked directory inside the workspace pointing out, and a new
+ * file created under one). The fence is exercised on a real filesystem: a
+ * denied write leaves no file on disk.
+ */
+
+import { afterEach, beforeEach, describe, expect, it } from 'vitest'
+import { mkdir, mkdtemp, readFile, rm, symlink, writeFile } from 'node:fs/promises'
+import { existsSync } from 'node:fs'
+import { homedir, tmpdir } from 'node:os'
+import { join } from 'node:path'
+import { Context } from 'cordis'
+import { FsError, FsTargetKey } from '@deepseek-ai/dsh-fs'
+import type { FsTarget } from '@deepseek-ai/dsh-fs'
+import SandboxPolicyService from '@deepseek-ai/dsh-sandbox-policy'
+import type { SandboxMode } from '@deepseek-ai/dsh-sandbox'
+import { SandboxedFileSystem } from '@deepseek-ai/dsh-fs-sandbox'
+
+let base: string
+let workspace: string
+let outside: string
+let ctx: Context
+let fs: SandboxedFileSystem
+let fiber: Awaited<ReturnType<Context['plugin']>>
+
+async function boot(mode: SandboxMode): Promise<void> {
+  ctx = new Context()
+  await ctx.plugin(SandboxPolicyService, { mode, workspaceRoot: workspace })
+  fiber = await ctx.plugin(SandboxedFileSystem, { cwd: workspace })
+  fs = ctx.fs as SandboxedFileSystem
+}
+
+beforeEach(async () => {
+  // Base under HOME, deliberately NOT tmpdir: `workspace-write` grants /tmp and
+  // os.tmpdir() (parity with the bash runner), so an "outside" dir under tmpdir
+  // would be legitimately writable. Sibling dirs under HOME are outside every
+  // grant, so containment failures are real denials. (The bwrap e2e roots its
+  // workspaces under HOME for the same reason.)
+  base = await mkdtemp(join(homedir(), '.dsh-fssbx-'))
+  workspace = join(base, 'ws')
+  outside = join(base, 'out')
+  await mkdir(workspace)
+  await mkdir(outside)
+})
+afterEach(async () => {
+  await fiber?.dispose()
+  await rm(base, { recursive: true, force: true })
+})
+
+/** Resolve a path through the backend and return its target. */
+function target(path: string): Promise<FsTarget> {
+  return fs.resolve(path)
+}
+
+describe('the capability fact', () => {
+  it('reports the deployment default mode (what the tool layer advertises against)', async () => {
+    await boot('workspace-write')
+    expect(fs.sandboxMode).toBe('workspace-write')
+  })
+})
+
+describe('read-only', () => {
+  beforeEach(() => boot('read-only'))
+
+  it('denies write, leaving no file on disk', async () => {
+    const path = join(workspace, 'denied.txt')
+    await expect(fs.writeText(await target(path), 'x')).rejects.toMatchObject({ code: 'FS_SANDBOX_DENIED' })
+    expect(existsSync(path)).toBe(false)
+  })
+
+  it('denies edit of an existing file (the content is unchanged)', async () => {
+    const path = join(workspace, 'file.txt')
+    await writeFile(path, 'original')
+    await expect(fs.editText(await target(path), { oldString: 'original', newString: 'changed', replaceAll: false }))
+      .rejects.toMatchObject({ code: 'FS_SANDBOX_DENIED' })
+    expect(await readFile(path, 'utf8')).toBe('original')
+  })
+
+  it('allows reads (every mode permits reading)', async () => {
+    const path = join(workspace, 'readable.txt')
+    await writeFile(path, 'hello')
+    expect(await fs.readText(await target(path))).toBe('hello')
+  })
+})
+
+describe('workspace-write containment', () => {
+  beforeEach(() => boot('workspace-write'))
+
+  it('a write under the workspace lands', async () => {
+    const path = join(workspace, 'nested', 'ok.txt')
+    const outcome = await fs.writeText(await target(path), 'inside')
+    expect(outcome.operation).toBe('create')
+    expect(await readFile(path, 'utf8')).toBe('inside')
+  })
+
+  it('a write to the platform temp area lands (parity with the bash runner grant)', async () => {
+    const path = join(await mkdtemp(join(tmpdir(), 'dsh-fssbx-tmp-')), 'temp.txt')
+    await fs.writeText(await target(path), 'temp')
+    expect(await readFile(path, 'utf8')).toBe('temp')
+  })
+
+  it('an absolute path outside the workspace is denied, no file created', async () => {
+    const path = join(outside, 'escape.txt')
+    await expect(fs.writeText(await target(path), 'x')).rejects.toMatchObject({ code: 'FS_SANDBOX_DENIED' })
+    expect(existsSync(path)).toBe(false)
+  })
+
+  it('a `..` traversal out of the workspace is denied', async () => {
+    const path = join(workspace, '..', 'sibling-escape.txt')
+    await expect(fs.writeText(await target(path), 'x')).rejects.toMatchObject({ code: 'FS_SANDBOX_DENIED' })
+    expect(existsSync(join(workspace, '..', 'sibling-escape.txt'))).toBe(false)
+  })
+
+  it('a symlinked directory inside the workspace pointing OUT is denied (canonicalized before containment)', async () => {
+    // workspace/link -> outside ; writing workspace/link/f.txt would land in outside/f.txt.
+    await symlink(outside, join(workspace, 'link'))
+    const path = join(workspace, 'link', 'f.txt')
+    await expect(fs.writeText(await target(path), 'x')).rejects.toMatchObject({ code: 'FS_SANDBOX_DENIED' })
+    expect(existsSync(join(outside, 'f.txt'))).toBe(false)
+  })
+
+  it('a NEW file created under a symlinked-out directory is denied (deepest-ancestor realpath)', async () => {
+    await symlink(outside, join(workspace, 'link'))
+    const path = join(workspace, 'link', 'newdir', 'deep.txt')
+    await expect(fs.writeText(await target(path), 'x')).rejects.toMatchObject({ code: 'FS_SANDBOX_DENIED' })
+    expect(existsSync(join(outside, 'newdir'))).toBe(false)
+  })
+
+  it('an edit outside the workspace is denied; the original is untouched', async () => {
+    const path = join(outside, 'file.txt')
+    await writeFile(path, 'original')
+    await expect(fs.editText(await target(path), { oldString: 'original', newString: 'x', replaceAll: false }))
+      .rejects.toMatchObject({ code: 'FS_SANDBOX_DENIED' })
+    expect(await readFile(path, 'utf8')).toBe('original')
+  })
+
+  it('an edit inside the workspace lands', async () => {
+    const path = join(workspace, 'edit.txt')
+    await writeFile(path, 'original')
+    const outcome = await fs.editText(await target(path), { oldString: 'original', newString: 'changed', replaceAll: false })
+    expect(outcome.after).toBe('changed')
+    expect(await readFile(path, 'utf8')).toBe('changed')
+  })
+
+  it('mutates the freshly checked identity, not a stale outside targetKey (TOCTOU direction)', async () => {
+    // A target whose displayPath is inside the workspace but whose targetKey is
+    // a STALE outside path — as if an ancestor symlink pointed out at the tool's
+    // resolve() and was swapped in before the write. The fence re-resolves
+    // displayPath (now inside) AND delegates with that fresh target, so the byte
+    // lands inside and the stale outside path is never written.
+    const insidePath = join(workspace, 'landed.txt')
+    const staleTarget: FsTarget = { displayPath: insidePath, targetKey: FsTargetKey(join(outside, 'escaped.txt')) }
+    await fs.writeText(staleTarget, 'inside')
+    expect(await readFile(insidePath, 'utf8')).toBe('inside')
+    expect(existsSync(join(outside, 'escaped.txt'))).toBe(false)
+  })
+
+  it('the workspace root itself passes the fence (path equal to a writable root), failing only on file type', async () => {
+    // isUnder's path-equals-root branch: the fence allows the root, and the
+    // write then fails because the root is a directory, not a regular file.
+    await expect(fs.writeText(await target(workspace), 'x')).rejects.toMatchObject({ code: 'FS_NOT_REGULAR_FILE' })
+  })
+})
+
+describe('workspace-write with the filesystem root as the workspace (a root ending in the path separator)', () => {
+  it('grants writes anywhere: containment against `/` allows any absolute path', async () => {
+    // A degenerate but valid config — workspaceRoot '/'. It exercises isUnder's
+    // separator-suffixed-root branch: `/` already ends in the separator, so the
+    // prefix stays `/` and every absolute path is contained.
+    const rootCtx = new Context()
+    await rootCtx.plugin(SandboxPolicyService, { mode: 'workspace-write', workspaceRoot: '/' })
+    const rootFiber = await rootCtx.plugin(SandboxedFileSystem, { cwd: workspace })
+    const rootFs = rootCtx.fs as SandboxedFileSystem
+    try {
+      const path = join(base, 'anywhere.txt') // under HOME, outside /tmp — allowed only via the `/` root
+      await rootFs.writeText(await rootFs.resolve(path), 'anywhere')
+      expect(await readFile(path, 'utf8')).toBe('anywhere')
+    } finally {
+      await rootFiber.dispose()
+    }
+  })
+})
+
+describe('danger-full-access', () => {
+  beforeEach(() => boot('danger-full-access'))
+
+  it('writes anywhere, unfenced', async () => {
+    const path = join(outside, 'free.txt')
+    await fs.writeText(await target(path), 'free')
+    expect(await readFile(path, 'utf8')).toBe('free')
+  })
+})
+
+describe('the per-call mode override (escalation)', () => {
+  it('a workspace-write stamp on a read-only default lets a contained write land for that call only', async () => {
+    await boot('read-only')
+    const path = join(workspace, 'escalated.txt')
+    // Default read-only would deny; the per-call workspace-write stamp allows it (contained).
+    await fs.writeText(await target(path), 'granted', undefined, undefined, 'workspace-write')
+    expect(await readFile(path, 'utf8')).toBe('granted')
+    // A neighboring plain call still runs under the read-only default.
+    await expect(fs.writeText(await target(join(workspace, 'plain.txt')), 'x'))
+      .rejects.toMatchObject({ code: 'FS_SANDBOX_DENIED' })
+  })
+
+  it('a danger-full-access stamp bypasses the fence for that call', async () => {
+    await boot('read-only')
+    const path = join(outside, 'granted-full.txt')
+    await fs.writeText(await target(path), 'full', undefined, undefined, 'danger-full-access')
+    expect(await readFile(path, 'utf8')).toBe('full')
+  })
+})
+
+describe('registration and HMR safety', () => {
+  it('registers as ctx.fs and unregisters cleanly from a child fiber', async () => {
+    await boot('workspace-write')
+    expect(ctx.fs).toBeInstanceOf(SandboxedFileSystem)
+    await fiber.dispose()
+    expect(ctx.get('fs')).toBeUndefined()
+    // Re-mount below the disposed one to prove no lingering registration.
+    fiber = await ctx.plugin(SandboxedFileSystem, { cwd: workspace })
+    expect(ctx.fs).toBeInstanceOf(SandboxedFileSystem)
+  })
+})
+
+describe('FsError identity', () => {
+  it('the denial is a structured FsError distinct from a host permission error', async () => {
+    await boot('read-only')
+    const error = await fs.writeText(await target(join(workspace, 'x.txt')), 'x').catch((e: unknown) => e)
+    expect(error).toBeInstanceOf(FsError)
+    expect((error as FsError).code).toBe('FS_SANDBOX_DENIED')
+  })
+})

packages/fs/fs-sandbox/tsconfig.json

@@ -0,0 +1,30 @@
+{
+  "extends": "../../../tsconfig.base.json",
+  "compilerOptions": {
+    "rootDir": "src",
+    "outDir": "lib/types"
+  },
+  "include": [
+    "src"
+  ],
+  "references": [
+    {
+      "path": "../../../vendor/cosmokit"
+    },
+    {
+      "path": "../../../vendor/cordis"
+    },
+    {
+      "path": "../fs"
+    },
+    {
+      "path": "../fs-local"
+    },
+    {
+      "path": "../../sandbox/sandbox"
+    },
+    {
+      "path": "../../sandbox/sandbox-policy"
+    }
+  ]
+}

packages/fs/fs/package.json

@@ -24,11 +24,13 @@
   "peerDependencies": {
     "@deepseek-ai/dsh-brand": "^0.0.1",
     "@deepseek-ai/dsh-llm": "^0.0.1",
+    "@deepseek-ai/dsh-sandbox": "^0.0.1",
     "cordis": "^4.0.0-rc.7"
   },
   "devDependencies": {
     "@deepseek-ai/dsh-brand": "workspace:^",
     "@deepseek-ai/dsh-llm": "workspace:^",
+    "@deepseek-ai/dsh-sandbox": "workspace:^",
     "cordis": "^4.0.0-rc.7"
   }
 }

packages/fs/fs/src/index.ts

@@ -7,6 +7,7 @@
  */
 
 import { Context, Service } from 'cordis'
+import type { SandboxMode } from '@deepseek-ai/dsh-sandbox'
 import type {
   FsDirEntry,
   FsEditOutcome,
@@ -82,6 +83,23 @@ export abstract class FileSystem extends Service {
     super(ctx, 'fs')
   }
 
+  /**
+  /**
+   * The sandbox mode this backend enforces on mutations BY DEFAULT, or
+   * `undefined` when it does not confine at all — the capability fact the tool
+   * layer reads to advertise the escalation fields honestly (mirrors
+   * `BashExecutor.sandboxMode`). The base class and the bare local backend
+   * report `undefined`; a sandboxing backend (`@deepseek-ai/dsh-fs-sandbox`)
+   * overrides it with the deployment default. A session override may make the
+   * effective mode narrower or wider, so strict escalation widening is checked
+   * per call rather than encoded in this default-relative fact.
+   * @returns the configured default mode of a sandboxing backend; `undefined`
+   *   for a backend that never confines.
+   */
+  get sandboxMode(): SandboxMode | undefined {
+    return undefined
+  }
+
   /**
    * Resolve a model/plugin-supplied path into a stable {@link FsTarget}. May perform I/O (a
    * remote/sandboxed backend may need a round-trip to map a path to a stable identity), hence
@@ -152,9 +170,18 @@ export abstract class FileSystem extends Service {
    * @param content - the full new file content.
    * @param expected - the write intent guarding the write; omit for unconditional.
    * @param signal - aborts before the atomic rename takes effect.
+   * @param sandboxMode - the per-call sandbox mode this write runs under; a
+   *   sandboxing backend fences the write by it, the bare backend ignores it.
+   *   Omit to leave the backend its own default.
    * @returns the outcome, including the version the write produced.
    */
-  abstract writeText(target: FsTarget, content: string, expected?: FsWriteIntent, signal?: AbortSignal): Promise<FsWriteOutcome>
+  abstract writeText(
+    target: FsTarget,
+    content: string,
+    expected?: FsWriteIntent,
+    signal?: AbortSignal,
+    sandboxMode?: SandboxMode,
+  ): Promise<FsWriteOutcome>
 
   /**
    * Atomically edit literal text. When supplied, the version guard is checked
@@ -164,9 +191,18 @@ export abstract class FileSystem extends Service {
    * @param edit - the literal search/replace request.
    * @param expected - the version guard; omit for an unconditional edit.
    * @param signal - aborts before the atomic rename takes effect.
+   * @param sandboxMode - the per-call sandbox mode this edit runs under; a
+   *   sandboxing backend fences the edit by it, the bare backend ignores it.
+   *   Omit to leave the backend its own default.
    * @returns the outcome, including the version the edit produced.
    */
-  abstract editText(target: FsTarget, edit: FsEditRequest, expected?: { version: FsVersion }, signal?: AbortSignal): Promise<FsEditOutcome>
+  abstract editText(
+    target: FsTarget,
+    edit: FsEditRequest,
+    expected?: { version: FsVersion },
+    signal?: AbortSignal,
+    sandboxMode?: SandboxMode,
+  ): Promise<FsEditOutcome>
 }
 
 export default FileSystem

packages/fs/fs/src/types.ts

@@ -168,6 +168,7 @@ export type FsErrorCode =
   | 'FS_NOT_TEXT'
   | 'FS_NOT_REGULAR_FILE'
   | 'FS_PERMISSION_DENIED'
+  | 'FS_SANDBOX_DENIED'
   | 'FS_IO_ERROR'
   | 'FS_STALE_VERSION'
   | 'FS_NOT_OBSERVED'

packages/fs/fs/tsconfig.json

@@ -9,6 +9,7 @@
     { "path": "../../../vendor/cosmokit" },
     { "path": "../../../vendor/cordis" },
     { "path": "../../util/brand" },
-    { "path": "../../llm/llm" }
+    { "path": "../../llm/llm" },
+    { "path": "../../sandbox/sandbox" }
   ]
 }

packages/fs/tool-fs/package.json

@@ -28,9 +28,12 @@
   "peerDependencies": {
     "@deepseek-ai/dsh-fs": "^0.0.1",
     "@deepseek-ai/dsh-llm": "^0.0.1",
+    "@deepseek-ai/dsh-sandbox": "^0.0.1",
+    "@deepseek-ai/dsh-sandbox-policy": "^0.0.1",
     "@deepseek-ai/dsh-session": "^0.0.1",
     "@deepseek-ai/dsh-system-prompt": "^0.0.1",
     "@deepseek-ai/dsh-tools": "^0.0.1",
+    "@deepseek-ai/dsh-user-approval": "^0.0.1",
     "cordis": "^4.0.0-rc.7"
   },
   "devDependencies": {
@@ -42,9 +45,12 @@
     "@deepseek-ai/dsh-fs-local": "workspace:^",
     "@deepseek-ai/dsh-llm": "workspace:^",
     "@deepseek-ai/dsh-llm-deepseek": "workspace:^",
+    "@deepseek-ai/dsh-sandbox": "workspace:^",
+    "@deepseek-ai/dsh-sandbox-policy": "workspace:^",
     "@deepseek-ai/dsh-session": "workspace:^",
     "@deepseek-ai/dsh-system-prompt": "workspace:^",
     "@deepseek-ai/dsh-tools": "workspace:^",
+    "@deepseek-ai/dsh-user-approval": "workspace:^",
     "cordis": "^4.0.0-rc.7"
   }
 }

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

@@ -13,6 +13,7 @@ import type {} from '@deepseek-ai/dsh-fs'
 import type {} from '@deepseek-ai/dsh-system-prompt'
 import { computeHunkDiffs, diffsFromMeta, type FsDiffMeta } from './diff.ts'
 import { sessionResolveOptions } from './session-cwd.ts'
+import type { FsSandboxSurface } from './sandbox.ts'
 
 /** Validated `edit` arguments after defaulting. */
 interface EditInput {
@@ -22,6 +23,20 @@ interface EditInput {
   replaceAll: boolean
 }
 
+/**
+ * The `edit` tool's validated argument shape: the base parameters plus the two
+ * escalation fields, advertised only under a confining `ctx.fs` (absent from
+ * the schema otherwise, so the validator rejects them before `execute`).
+ */
+interface EditToolArgs {
+  file_path: string
+  old_string: string
+  new_string: string
+  replace_all?: boolean
+  sandbox_permissions?: string
+  justification?: string
+}
+
 /**
  * Validate value constraints the schema DSL can't express: a non-blank
  * `file_path`, a non-empty `old_string`, and `old_string !== new_string`
@@ -56,8 +71,9 @@ export function formatEditOutput(displayPath: string, replaceAll: boolean): stri
 /**
  * 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.
+ * @param sandbox - the shared sandbox-escalation surface (advertisement, mode stamping, denial mapping).
  */
-export function applyEditTool(ctx: Context): void {
+export function applyEditTool(ctx: Context, sandbox: FsSandboxSurface): void {
   ctx.systemPrompt.section({
     name: 'tool:edit',
     order: 102,
@@ -72,20 +88,31 @@ export function applyEditTool(ctx: Context): void {
       old_string: { type: 'string', required: true, description: 'Literal text to replace. Must match exactly.' },
       new_string: { type: 'string', required: true, description: 'Literal replacement text. Use an empty string to delete the match.' },
       replace_all: { type: 'boolean', description: 'Replace all matches. Defaults to false; when false, old_string must appear exactly once.' },
+      ...sandbox.escalationModes.length > 0 ? sandbox.schemaFields() : {},
     },
-    async execute(args, exec): Promise<{ content: ContentBlock[]; meta?: FsDiffMeta }> {
+    async execute(args: EditToolArgs, exec): Promise<{ content: ContentBlock[]; meta?: FsDiffMeta }> {
       const input = parseEditArgs(args)
+      // Resolve the per-call sandbox mode (escalation grant > session override
+      // > backend default) BEFORE anything executes.
+      const sandboxMode = await sandbox.stampMode('edit', args, exec)
       const target = await ctx.fs.resolve(input.filePath, sessionResolveOptions(exec))
       // Single-slot decision: the policy plugin returns { version: vObserved } or
       // throws FS_NOT_OBSERVED; the bare default is undefined (unconditional edit).
       // No stat — the bare default never manufactures a version basis.
       const intent = await ctx.waterfall('fs/edit-intent', target, exec, () => undefined)
-      const outcome = await ctx.fs.editText(
-        target,
-        { oldString: input.oldString, newString: input.newString, replaceAll: input.replaceAll },
-        intent,
-        exec.signal,
-      )
+      let outcome
+      try {
+        outcome = await ctx.fs.editText(
+          target,
+          { oldString: input.oldString, newString: input.newString, replaceAll: input.replaceAll },
+          intent,
+          exec.signal,
+          sandboxMode,
+        )
+      } catch (error: unknown) {
+        // A sandbox denial becomes the shared [sandbox: …] marker; any other error passes through.
+        throw sandbox.mapError(error, sandboxMode)
+      }
       // Record the observed version (a no-op when no policy plugin listens).
       ctx.emit('fs/observed', target, outcome.version, exec)
       // An edit necessarily changes content, so result metadata carries at least one applied hunk.

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

@@ -7,10 +7,12 @@
 
 import type { Context } from 'cordis'
 import z from 'schemastery'
+import type {} from '@deepseek-ai/dsh-user-approval'
 import { applyReadTool, READ_LIMIT, STREAM_MIN_SIZE } from './read.ts'
 import { applyWriteTool } from './write.ts'
 import { applyEditTool } from './edit.ts'
 import { READ_MAX_BYTES, READ_MAX_LINE_LENGTH } from './read-render.ts'
+import { FsSandboxSurface } from './sandbox.ts'
 
 /** Cordis plugin name used by loader diagnostics. */
 export const name = 'tool-fs'
@@ -61,6 +63,10 @@ export function apply(ctx: Context, config: Config): void {
     maxBytes: resolved.readMaxBytes,
     streamMinSize: resolved.readStreamMinSize,
   })
-  applyWriteTool(ctx)
-  applyEditTool(ctx)
+  // One escalation surface shared by both mutating tools: advertisement gating,
+  // per-call mode stamping, and denial-marker mapping, all keyed off whether
+  // the mounted ctx.fs confines (ctx.fs.sandboxMode).
+  const sandbox = new FsSandboxSurface(ctx)
+  applyWriteTool(ctx, sandbox)
+  applyEditTool(ctx, sandbox)
 }

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

@@ -0,0 +1,135 @@
+/**
+ * The sandbox-escalation surface shared by the `write` and `edit` tools: the
+ * per-call mode stamp, the advertised escalation fields, and the denial-marker
+ * mapping — all delegating the vocabulary and the fail-closed approval
+ * sequence to `@deepseek-ai/dsh-sandbox` (the same pieces `@deepseek-ai/dsh-tool-bash`
+ * uses), so bash and fs escalate identically. Built ONCE per plugin from
+ * `ctx.fs.sandboxMode` (the capability fact — is a confining backend mounted?)
+ * and shared by both mutating tools.
+ *
+ * @module @deepseek-ai/dsh-tool-fs/sandbox
+ */
+
+import type { Context } from 'cordis'
+import type { ToolExecution } from '@deepseek-ai/dsh-tools'
+import type { SandboxMode } from '@deepseek-ai/dsh-sandbox'
+import { ESCALATION_TARGETS, approveEscalation, escalationHintMarker, sandboxDenialMarker, validateEscalationArgs } from '@deepseek-ai/dsh-sandbox'
+import { effectiveSandboxMode } from '@deepseek-ai/dsh-sandbox-policy'
+import { FsError } from '@deepseek-ai/dsh-fs'
+
+/** The two escalation arguments a mutating tool may carry (advertised only under a confining backend). */
+export interface FsEscalationArgs {
+  sandbox_permissions?: string
+  justification?: string
+}
+
+/** The schema fields for the escalation arguments, spread into a tool's `parameters` when a confining backend is mounted. */
+export interface EscalationSchemaFields {
+  sandbox_permissions: { type: 'string'; enum: string[]; description: string }
+  justification: { type: 'string'; description: string }
+}
+
+/**
+ * The filesystem escalation surface: advertisement gating, per-call mode
+ * stamping (folding the session's `sandbox/mode` override), the one-approved
+ * wider retry, and denial-marker mapping. A pure product of `ctx` at plugin
+ * apply time.
+ */
+export class FsSandboxSurface {
+  /** The escalation targets this composition advertises (`[]` when no confining backend is mounted). */
+  readonly escalationModes: readonly SandboxMode[]
+  /** The backend's default mode, or `undefined` when `ctx.fs` does not confine. */
+  private readonly defaultMode: SandboxMode | undefined
+
+  constructor(private readonly ctx: Context) {
+    this.defaultMode = ctx.fs.sandboxMode
+    this.escalationModes = this.defaultMode === undefined ? [] : ESCALATION_TARGETS
+  }
+
+  /**
+   * The escalation schema fields for a mutating tool's `parameters`. Call it
+   * only under a confining backend (guard on {@link escalationModes}); the
+   * enum pins the closed target vocabulary, the strict-wider check happens per
+   * call at execution.
+   * @returns the two escalation parameter specs.
+   */
+  schemaFields(): EscalationSchemaFields {
+    return {
+      sandbox_permissions: {
+        type: 'string',
+        enum: [...this.escalationModes],
+        description: 'The wider sandbox mode this file operation needs. Only valid as a one-shot retry '
+          + 'of an operation the sandbox just denied; requires justification and user approval.',
+      },
+      justification: {
+        type: 'string',
+        description: 'Required with sandbox_permissions: one sentence for the user explaining '
+          + 'why this exact file operation needs the wider access.',
+      },
+    }
+  }
+
+  /**
+   * The session's standing mode override for an ordinary (non-escalating)
+   * call — the `sandbox/mode` fold of the calling agent's log. Undefined for a
+   * non-confining backend and for agent-less callers.
+   */
+  private sessionOverride(exec: ToolExecution): SandboxMode | undefined {
+    if (this.defaultMode === undefined || exec.agent === undefined) return undefined
+    return effectiveSandboxMode(exec.agent.session.events)
+  }
+
+  /**
+   * The mode to STAMP onto this mutation: an approved escalation grant (a
+   * strictly wider retry resolved through `ctx.approval` before anything
+   * executes), else the session's standing override, else `undefined` (the
+   * backend applies its own default). Validates the escalation argument
+   * pairing first.
+   * @param toolName - the mutating tool's name, for the approval audit trail.
+   * @param args - the call's escalation arguments.
+   * @param exec - the tool-execution context (agent, callId, signal).
+   * @returns the mode to pass to the mutation, or undefined for the backend default.
+   */
+  async stampMode(toolName: string, args: FsEscalationArgs, exec: ToolExecution): Promise<SandboxMode | undefined> {
+    validateEscalationArgs(args.sandbox_permissions, args.justification)
+    if (args.sandbox_permissions === undefined || args.justification === undefined) {
+      return this.sessionOverride(exec)
+    }
+    if (this.escalationModes.length === 0) {
+      throw new Error('sandbox_permissions is not available in this composition (no sandboxing filesystem to escalate)')
+    }
+    const effectiveMode = (this.sessionOverride(exec) ?? this.defaultMode) as SandboxMode
+    return approveEscalation(
+      { requestedMode: args.sandbox_permissions, justification: args.justification, effectiveMode, subject: 'operation' },
+      {
+        approver: this.ctx.get('approval'),
+        agent: exec.agent,
+        callId: exec.callId,
+        toolName,
+        ...exec.signal ? { signal: exec.signal } : {},
+      },
+    )
+  }
+
+  /**
+   * Map a thrown provider error for the model: a `FS_SANDBOX_DENIED` becomes a
+   * `FsError` whose text is the shared `[sandbox: …]` denial marker plus the
+   * same-turn escalation hint, so a policy denial reads identically to bash's
+   * WHILE keeping the structured `FS_SANDBOX_DENIED` code — `ToolRegistry`
+   * populates `result.error` only for `HarnessError` instances, so a plain
+   * `Error` would strip the code retry/observers key off. Any other error
+   * passes through unchanged. A `FS_SANDBOX_DENIED` only arises under a
+   * confining backend, which always advertises the escalation fields, so the
+   * hint always applies here.
+   * @param error - the error thrown by the mutation.
+   * @param stampedMode - the mode stamped onto the call (names the mode in the marker).
+   * @returns the error to throw — the marker `FsError` for a sandbox denial, else the original.
+   */
+  mapError(error: unknown, stampedMode: SandboxMode | undefined): unknown {
+    if (!(error instanceof FsError) || error.code !== 'FS_SANDBOX_DENIED') return error
+    // A FS_SANDBOX_DENIED only arises under a confining backend, so defaultMode
+    // (hence the resolved mode) is defined here.
+    const mode = (stampedMode ?? this.defaultMode) as SandboxMode
+    return new FsError(`${sandboxDenialMarker(mode)}\n${escalationHintMarker('operation')}`, 'FS_SANDBOX_DENIED', { cause: error })
+  }
+}

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

@@ -14,6 +14,7 @@ import type {} from '@deepseek-ai/dsh-fs'
 import type {} from '@deepseek-ai/dsh-system-prompt'
 import { computeHunkDiffs, diffsFromMeta, type FsDiffMeta } from './diff.ts'
 import { sessionResolveOptions } from './session-cwd.ts'
+import type { FsSandboxSurface } from './sandbox.ts'
 
 /**
  * Validate value constraints the schema DSL can't express: only a non-blank
@@ -41,11 +42,24 @@ ${verb} file
 </content>`
 }
 
+/**
+ * The `write` tool's validated argument shape: the base parameters plus the
+ * two escalation fields, advertised only under a confining `ctx.fs` (absent
+ * from the schema otherwise, so the validator rejects them before `execute`).
+ */
+interface WriteToolArgs {
+  file_path: string
+  content: string
+  sandbox_permissions?: string
+  justification?: string
+}
+
 /**
  * Register the `write` tool and its system-prompt guidance.
  * @param ctx - the plugin context; registrations are effects scoped to it, and execution uses its `fs` service.
+ * @param sandbox - the shared sandbox-escalation surface (advertisement, mode stamping, denial mapping).
  */
-export function applyWriteTool(ctx: Context): void {
+export function applyWriteTool(ctx: Context, sandbox: FsSandboxSurface): void {
   ctx.systemPrompt.section({
     name: 'tool:write',
     order: 101,
@@ -58,14 +72,26 @@ export function applyWriteTool(ctx: Context): void {
     parameters: {
       file_path: { type: 'string', required: true, description: 'Path to write, resolved by the filesystem backend.' },
       content: { type: 'string', required: true, description: 'Full UTF-8 text content to write.' },
+      ...sandbox.escalationModes.length > 0 ? sandbox.schemaFields() : {},
     },
-    async execute(args, exec): Promise<{ content: ContentBlock[]; meta?: FsDiffMeta }> {
+    async execute(args: WriteToolArgs, exec): Promise<{ content: ContentBlock[]; meta?: FsDiffMeta }> {
       const input = parseWriteArgs(args)
+      // Resolve the per-call sandbox mode (escalation grant > session override
+      // > backend default) BEFORE anything executes; an escalating call
+      // resolves approval here and throws its distinct text on any non-grant.
+      const sandboxMode = await sandbox.stampMode('write', args, exec)
       const target = await ctx.fs.resolve(input.filePath, sessionResolveOptions(exec))
       // Single-slot decision: the policy plugin produces createIfAbsent/
       // replaceIfVersion; the bare default is undefined (unconditional). No stat.
       const intent = await ctx.waterfall('fs/write-intent', target, exec, () => undefined)
-      const outcome = await ctx.fs.writeText(target, input.content, intent, exec.signal)
+      let outcome: FsWriteOutcome
+      try {
+        outcome = await ctx.fs.writeText(target, input.content, intent, exec.signal, sandboxMode)
+      } catch (error: unknown) {
+        // A sandbox denial becomes the shared [sandbox: …] marker (the model
+        // recognizes it from bash); any other error passes through.
+        throw sandbox.mapError(error, sandboxMode)
+      }
       // Record the observed version (a no-op when no policy plugin listens).
       ctx.emit('fs/observed', target, outcome.version, exec)
       // Overwrites carry applied hunks. Creates have no prior text, so result presentation uses

packages/fs/tool-fs/tests/tools.spec.ts

@@ -24,6 +24,8 @@ import * as ToolFs from '@deepseek-ai/dsh-tool-fs'
 import { STREAM_MIN_SIZE } from '../src/read.ts'
 import { formatReadOutput } from '../src/read-render.ts'
 import type { FileReadOutcome } from '../src/read-render.ts'
+import ApprovalService from '@deepseek-ai/dsh-user-approval'
+import type { SandboxMode } from '@deepseek-ai/dsh-sandbox'
 
 /** An in-memory fake provider; a test can arm a rejection on any primitive. */
 class FakeFs extends FileSystem {
@@ -580,3 +582,163 @@ describe('read caps are plugin config', () => {
     expect('default' in ToolFs).toBe(false)
   })
 })
+
+describe('sandbox escalation surface (write/edit)', () => {
+  /** A confining fake `ctx.fs`: reports a default mode, records the per-call mode stamped, and can arm a sandbox denial. */
+  class SandboxingFakeFs extends FakeFs {
+    stamped: (SandboxMode | undefined)[] = []
+    override get sandboxMode(): SandboxMode {
+      return 'workspace-write'
+    }
+    override async writeText(
+      target: FsTarget,
+      content: string,
+      expected?: FsWriteIntent,
+      _signal?: AbortSignal,
+      sandboxMode?: SandboxMode,
+    ): Promise<FsWriteOutcome> {
+      this.stamped.push(sandboxMode)
+      return super.writeText(target, content, expected)
+    }
+    override async editText(
+      target: FsTarget,
+      edit: FsEditRequest,
+      expected?: { version: FsVersion },
+      _signal?: AbortSignal,
+      sandboxMode?: SandboxMode,
+    ): Promise<FsEditOutcome> {
+      this.stamped.push(sandboxMode)
+      return super.editText(target, edit, expected)
+    }
+  }
+
+  async function setupConfining(opts: { approval?: boolean } = {}) {
+    const ctx = new Context()
+    await ctx.plugin(SystemPrompt)
+    await ctx.plugin(ToolRegistry)
+    await ctx.plugin(SandboxingFakeFs)
+    await ctx.plugin(FsPolicy)
+    if (opts.approval === true) await ctx.plugin(ApprovalService)
+    await ctx.plugin(ToolFs)
+    return { ctx, fs: ctx.fs as SandboxingFakeFs }
+  }
+
+  /** A fake agent whose session records appends (the approval audit surface), mid-turn, carrying the given events for the fold. */
+  function escalationAgent(events: Array<{ type: string; data?: Record<string, unknown> }> = []): object {
+    return {
+      id: 'agent-fs-esc',
+      session: {
+        header: { version: 0, id: 'sess-fs-esc', createdAt: 0 },
+        events: [{ type: 'turn/start' }, ...events],
+        append: (type: string, data: Record<string, unknown>) => { events.push({ type, data }) },
+      },
+    }
+  }
+
+  function fsSchema(ctx: Context, name: 'write' | 'edit') {
+    const schema = ctx.tools.schemas().find(s => s.name === name)
+    if (!schema) throw new Error(`${name} tool not registered`)
+    return schema as unknown as { parameters: { properties: Record<string, { enum?: string[] }> } }
+  }
+
+  it('advertises no escalation fields under a non-confining backend', async () => {
+    const { ctx } = await setup()
+    expect(ctx.fs.sandboxMode).toBeUndefined()
+    for (const name of ['write', 'edit'] as const) {
+      const props = fsSchema(ctx, name).parameters.properties
+      expect(props['sandbox_permissions']).toBeUndefined()
+      expect(props['justification']).toBeUndefined()
+    }
+  })
+
+  it('advertises the closed target vocabulary on write and edit under a confining backend', async () => {
+    const { ctx } = await setupConfining()
+    for (const name of ['write', 'edit'] as const) {
+      const props = fsSchema(ctx, name).parameters.properties
+      expect(props['sandbox_permissions']?.enum).toEqual(['workspace-write', 'danger-full-access'])
+      expect(props['justification']).toBeDefined()
+    }
+  })
+
+  it('a plain write stamps nothing (backend default) and no session override folds without one', async () => {
+    const { ctx, fs } = await setupConfining()
+    await call(ctx, 'write', { file_path: 'a.txt', content: 'x' }, escalationAgent())
+    expect(fs.stamped).toEqual([undefined])
+  })
+
+  it('a standing session override folds onto the stamp', async () => {
+    const { ctx, fs } = await setupConfining()
+    await call(ctx, 'write', { file_path: 'a.txt', content: 'x' }, escalationAgent([{ type: 'sandbox/mode', data: { mode: 'read-only' } }]))
+    expect(fs.stamped).toEqual(['read-only'])
+  })
+
+  it('a denied write maps to the shared marker plus the escalation hint (isError)', async () => {
+    const { ctx, fs } = await setupConfining()
+    fs.rejectWith = new FsError('denied', 'FS_SANDBOX_DENIED')
+    const result = await call(ctx, 'write', { file_path: 'a.txt', content: 'x' }, escalationAgent())
+    expect(result.isError).toBe(true)
+    expect(text(result)).toContain('[sandbox: file access denied under workspace-write mode]')
+    expect(text(result)).toContain('retry this exact operation once with sandbox_permissions')
+  })
+
+  it('a non-FS_SANDBOX_DENIED provider error passes through unchanged', async () => {
+    const { ctx, fs } = await setupConfining()
+    fs.rejectWith = new FsError('boom', 'FS_IO_ERROR')
+    const result = await call(ctx, 'write', { file_path: 'a.txt', content: 'x' }, escalationAgent())
+    expect(result.isError).toBe(true)
+    expect(text(result)).toContain('boom')
+    expect(text(result)).not.toContain('[sandbox:')
+  })
+
+  it('an approved escalation stamps the granted mode onto that write', async () => {
+    const { ctx, fs } = await setupConfining({ approval: true })
+    ctx.on('approval/request', () => Promise.resolve('allowed-once' as const))
+    // Pass a signal so the escalation ask forwards it to the approval request
+    // (the request rides the tool-execution abort signal).
+    await ctx.tools.execute({
+      callId: CallId('call-fs-esc-grant'),
+      name: 'write',
+      arguments: { file_path: 'a.txt', content: 'x', sandbox_permissions: 'danger-full-access', justification: 'the test needs it' },
+      agent: escalationAgent() as never,
+      signal: new AbortController().signal,
+    })
+    expect(fs.stamped).toEqual(['danger-full-access'])
+  })
+
+  it('a rejected escalation fails closed with its own text and never mutates', async () => {
+    const { ctx, fs } = await setupConfining({ approval: true })
+    ctx.on('approval/request', () => Promise.resolve('rejected' as const))
+    const result = await call(ctx, 'edit', { file_path: 'a.txt', old_string: 'x', new_string: 'y', sandbox_permissions: 'danger-full-access', justification: 'the test needs it' }, escalationAgent())
+    expect(result.isError).toBe(true)
+    expect(text(result)).toContain('the user rejected escalating this operation to "danger-full-access"')
+    expect(fs.stamped).toEqual([])
+  })
+
+  it('escalation without an approval service fails closed', async () => {
+    const { ctx } = await setupConfining()
+    const result = await call(ctx, 'write', { file_path: 'a.txt', content: 'x', sandbox_permissions: 'danger-full-access', justification: 'why' }, escalationAgent())
+    expect(result.isError).toBe(true)
+    expect(text(result)).toContain('no approval service is composed')
+  })
+
+  it('escalation with an approval service but no agent fails closed', async () => {
+    const { ctx } = await setupConfining({ approval: true })
+    const result = await call(ctx, 'write', { file_path: 'a.txt', content: 'x', sandbox_permissions: 'danger-full-access', justification: 'why' })
+    expect(result.isError).toBe(true)
+    expect(text(result)).toContain('no agent to route it through')
+  })
+
+  it('rejects the escalation argument pairing (one field without the other)', async () => {
+    const { ctx } = await setupConfining()
+    const missing = await call(ctx, 'write', { file_path: 'a.txt', content: 'x', sandbox_permissions: 'workspace-write' }, escalationAgent())
+    expect(missing.isError).toBe(true)
+    expect(text(missing)).toContain('sandbox_permissions requires a justification')
+  })
+
+  it('sandbox_permissions under a non-confining backend fails closed (unadvertised field still reaches execute)', async () => {
+    const { ctx } = await setup()
+    const result = await call(ctx, 'write', { file_path: 'a.txt', content: 'x', sandbox_permissions: 'workspace-write', justification: 'why' }, escalationAgent())
+    expect(result.isError).toBe(true)
+    expect(text(result)).toContain('not available in this composition')
+  })
+})

packages/fs/tool-fs/tsconfig.json

@@ -13,6 +13,9 @@
     { "path": "../../core/tools" },
     { "path": "../../core/system-prompt" },
     { "path": "../fs" },
-    { "path": "../fs-policy" }
+    { "path": "../fs-policy" },
+    { "path": "../../sandbox/sandbox" },
+    { "path": "../../sandbox/sandbox-policy" },
+    { "path": "../../ui/user-approval" }
   ]
 }

packages/goal/command-goal/tests/command-goal.spec.ts

@@ -33,7 +33,6 @@ function appendInjection(session: Session, content: ContentBlock[], options?: In
   session.append('context/message', {
     content,
     source,
-    ...options?.envelope === undefined ? {} : { envelope: options.envelope },
     ...options?.meta === undefined ? {} : { meta: options.meta },
   }, { surfaceOp: 'append' })
   session.append('turn/end', { turn, reason: { kind: 'completed' } })

packages/goal/goal/README.md

@@ -19,7 +19,7 @@ Event-sourced same-session goal state. The service retains one current completio
 
 At most one goal is current. Creation produces an active revision-one goal and arms it. A non-complete goal must be edited, transitioned, or cleared; a completed goal may be replaced by a globally fresh id. Edits retain phase, blocker reason, and activation. Pause, completion, blocking, and clear disarm activation. A block records a policy-owned lower-kebab-case code plus a normalized free-form explanation; provider limits, configured budgets, execution errors, and requests for human input all use this one durable phase rather than multiplying lifecycle states. Resume accepts a stopped phase or a disarmed active goal only while the configured round cap has remaining capacity; it clears any former blocker reason. An active armed goal rejects the redundant operation.
 
-Every non-clear mutation appends a complete versioned snapshot through `agent.inject()`; clear appends a revisioned tombstone. The raw `context/message`, its `{ kind: 'goal' }` source, and its metadata must agree exactly. Replay rejects malformed shapes, source/content drift, discontinuous revisions, illegal lifecycle transitions, non-monotonic per-goal timestamps, and non-sequential goal rounds. Mutation timestamps clamp against the preceding goal update when wall time moves backward.
+Every non-clear mutation appends a complete versioned snapshot through `agent.inject()`; clear appends a revisioned tombstone. The `context/message` content projected verbatim to the model, its `{ kind: 'goal' }` source, and its metadata must agree exactly. Replay rejects malformed shapes, source/content drift, discontinuous revisions, illegal lifecycle transitions, non-monotonic per-goal timestamps, and non-sequential goal rounds. Mutation timestamps clamp against the preceding goal update when wall time moves backward.
 
 Injection may append immediately or wait in an active tool-batch FIFO. The service overlays accepted pending changes in memory and reconciles each exact payload when it enters the log, so consecutive model-tool mutations see their own latest revisions without treating an unlogged cache as durable state. Reentrant append observers see each accepted mutation exactly once, and incremental replay retains its cursor at the first corrupt event. `goal/changed` fires after the append or enqueue succeeds; listener failures are contained.
 

packages/goal/goal/src/fold.ts

@@ -325,8 +325,7 @@ export function decodeGoalEvent(event: ContextMessageEvent): GoalChangeMeta | un
   if (source === undefined || source.goalId !== ref.id || source.revision !== ref.revision || source.round !== 0) {
     throw new Error(`goal change at session event ${event.seq} has mismatched source attribution`)
   }
-  if (event.data.envelope !== 'raw'
-    || JSON.stringify(event.data.content) !== JSON.stringify(renderGoalChange(change))) {
+  if (JSON.stringify(event.data.content) !== JSON.stringify(renderGoalChange(change))) {
     throw new Error(`goal change at session event ${event.seq} has mismatched model-visible content`)
   }
   return change

packages/goal/goal/src/index.ts

@@ -497,7 +497,6 @@ export class GoalService extends Service {
     try {
       agent.inject(renderGoalChange(change), {
         source: { kind: 'goal', goalId: ref.id, revision: ref.revision, round: 0 },
-        envelope: 'raw',
         meta,
       })
     } catch (error: unknown) {

packages/goal/goal/src/render.ts

@@ -6,7 +6,7 @@ import type { GoalChangeMeta } from './types.ts'
 /**
  * Render a complete goal snapshot or clear tombstone without hidden prose.
  * @param change - durable goal change metadata.
- * @returns the single raw context block logged for model reconstruction.
+ * @returns the single context block logged and projected verbatim for model reconstruction.
  */
 export function renderGoalChange(change: GoalChangeMeta): ContentBlock[] {
   const payload = change.operation === 'clear'

packages/goal/goal/tests/goal.e2e.ts

@@ -117,7 +117,6 @@ describe('goal domain through a real cordis.yml and stdio process', () => {
         maxGoalRounds: 7,
       },
     })
-    expect(context.data.envelope).toBe('raw')
     expect(context.data.content).toEqual(renderGoalChange(change))
     expect(JSON.stringify(context)).not.toContain('activation')
     expect(events.filter(event => event.type === 'user/message'

packages/goal/goal/tests/goal.spec.ts

@@ -38,7 +38,6 @@ function appendInjection(session: Session, content: ContentBlock[], options?: In
   const context = {
     content,
     source,
-    ...options?.envelope === undefined ? {} : { envelope: options.envelope },
     ...options?.meta === undefined ? {} : { meta: options.meta },
   }
   const last = session.events.at(-1)
@@ -111,7 +110,7 @@ function appendRound(session: Session, ref: GoalRef, round: number): void {
 }
 
 describe('GoalService creation and replay', () => {
-  it('applies the configured default and writes one balanced raw context snapshot', async () => {
+  it('applies the configured default and writes one balanced verbatim context snapshot', async () => {
     vi.useFakeTimers()
     vi.setSystemTime(1_700_000_000_000)
     const { ctx, agent, session } = await harness({ defaultMaxGoalRounds: 17 })
@@ -136,7 +135,6 @@ describe('GoalService creation and replay', () => {
     const context = session.events[1]
     expect(context?.type).toBe('context/message')
     if (context?.type !== 'context/message') throw new Error('expected goal context')
-    expect(context.data.envelope).toBe('raw')
     expect(context.data.source).toEqual({ kind: 'goal', goalId: goal.id, revision: 1, round: 0 })
     const change = decodeGoalChange(context.data.meta)
     if (change === undefined) throw new Error('expected decoded goal change')
@@ -520,7 +518,7 @@ describe('GoalService mutations', () => {
     const turn = nextTurn(session)
     session.append('turn/start', { turn, trigger: { kind: 'injection', source } })
     session.append('context/message', {
-      content: renderGoalChange(change), source, envelope: 'raw', meta: change as never,
+      content: renderGoalChange(change), source, meta: change as never,
     }, { surfaceOp: 'append' })
     session.append('turn/end', { turn, reason: { kind: 'completed' } })
 
@@ -551,12 +549,10 @@ describe('GoalService mutations', () => {
     }
     appendInjection(session, renderGoalChange(change), {
       source: { kind: 'goal', goalId: change.goal.id, revision: 1, round: 0 },
-      envelope: 'raw',
       meta: change as never,
     })
     appendInjection(session, [{ type: 'text', text: 'corrupt' }], {
       source: { kind: 'goal', goalId: change.goal.id, revision: 2, round: 0 },
-      envelope: 'raw',
       meta: { ...change, operation: 'edit', extra: true } as never,
     })
 
@@ -588,7 +584,7 @@ describe('goal replay validation', () => {
   function appendChange(
     session: Session,
     change: GoalChangeMeta,
-    overrides: { content?: ContentBlock[]; source?: MessageSource; envelope?: 'raw' } = {},
+    overrides: { content?: ContentBlock[]; source?: MessageSource } = {},
   ): void {
     const source = overrides.source ?? {
       kind: 'goal',
@@ -601,13 +597,12 @@ describe('goal replay validation', () => {
     session.append('context/message', {
       content: overrides.content ?? renderGoalChange(change),
       source,
-      envelope: overrides.envelope ?? 'raw',
       meta: change as never,
     }, { surfaceOp: 'append' })
     session.append('turn/end', { turn, reason: { kind: 'completed' } })
   }
 
-  function oneChange(change: GoalChangeMeta, overrides: { content?: ContentBlock[]; source?: MessageSource; envelope?: 'raw' } = {}) {
+  function oneChange(change: GoalChangeMeta, overrides: { content?: ContentBlock[]; source?: MessageSource } = {}) {
     const session = new Session(SessionId(`validation-${Math.random()}`))
     appendChange(session, change, overrides)
     return session.events
@@ -797,7 +792,7 @@ describe('goal replay validation', () => {
     const turn = nextTurn(session)
     session.append('turn/start', { turn, trigger: { kind: 'injection', source } })
     session.append('context/message', {
-      content: [{ type: 'text', text: 'missing' }], source, envelope: 'raw',
+      content: [{ type: 'text', text: 'missing' }], source,
     }, { surfaceOp: 'append' })
     session.append('turn/end', { turn, reason: { kind: 'completed' } })
     expect(() => foldGoal(session.events)).toThrow('lacks goal change metadata')
@@ -836,21 +831,13 @@ describe('goal replay validation', () => {
     })).toThrow('positive safe integer')
   })
 
-  it('rejects source, content, and envelope drift from the durable metadata', () => {
+  it('rejects source and content drift from the durable metadata', () => {
     const change = snapshotChange()
     expect(() => foldGoal(oneChange(change, { source: { kind: 'plugin', plugin: 'wrong' } }))).toThrow('mismatched source')
     expect(() => foldGoal(oneChange(change, {
       source: { kind: 'goal', goalId: change.goal.id, revision: 1, round: -1 },
     }))).toThrow('source is invalid')
     expect(() => foldGoal(oneChange(change, { content: [{ type: 'text', text: 'wrong' }] }))).toThrow('model-visible content')
-    const events = oneChange(change)
-    const context = events.find(event => event.type === 'context/message')
-    if (context?.type !== 'context/message') throw new Error('expected context')
-    const altered = structuredClone(events)
-    const clonedContext = altered.find(event => event.type === 'context/message')
-    if (clonedContext?.type !== 'context/message') throw new Error('expected cloned context')
-    delete (clonedContext.data as { envelope?: string }).envelope
-    expect(() => foldGoal(altered)).toThrow('model-visible content')
   })
 
   it('folds a clear tombstone after a snapshot', () => {
@@ -867,7 +854,7 @@ describe('goal replay validation', () => {
     const turn = nextTurn(session)
     session.append('turn/start', { turn, trigger: { kind: 'injection', source } })
     session.append('context/message', {
-      content: renderGoalChange(clear), source, envelope: 'raw', meta: clear as never,
+      content: renderGoalChange(clear), source, meta: clear as never,
     }, { surfaceOp: 'append' })
     session.append('turn/end', { turn, reason: { kind: 'completed' } })
     expect(foldGoal(session.events)).toEqual({

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

@@ -36,7 +36,6 @@ function stubAgent(rawId: string, supplied?: Session): StubAgent {
       session.append('context/message', {
         content,
         source,
-        ...options?.envelope === undefined ? {} : { envelope: options.envelope },
         ...options?.meta === undefined ? {} : { meta: options.meta },
       }, { surfaceOp: 'append' })
     },

packages/guard/repeat-tool-guard/README.md

@@ -30,7 +30,7 @@ The chain key is `(tool name, canonical arguments)` — canonicalization is a de
 
 ## Reminder delivery
 
-Reminders ride the post-execute decision's `additionalContexts` (source `{kind: 'plugin', plugin: 'repeat-tool-guard'}`), never a `content` replacement: the `tool/result` event stays the tool's own output for audit. The loop buffers the context and appends it as a `context/message` after the step's tool results, which the session renders as the tagged synthetic-user envelope — so the reminder is model-visible, source-attributed, and reconstructable from the session log with no new session event. The guard always delegates via `next()` and prepends its reminder to the downstream decision's context array (both variants — a blocked call still gets the nudge); every entry retains its own source, envelope, and metadata.
+Reminders ride the post-execute decision's `additionalContexts` (source `{kind: 'plugin', plugin: 'repeat-tool-guard'}`), never a `content` replacement: the `tool/result` event stays the tool's own output for audit. The loop buffers the context and appends it as a `context/message` after the step's tool results, which the session renders as a plain synthetic user message — so the reminder is model-visible, source-attributed, and reconstructable from the session log with no new session event. The guard always delegates via `next()` and prepends its reminder to the downstream decision's context array (both variants — a blocked call still gets the nudge); every entry retains its own source and metadata.
 
 ## Testing
 

packages/guard/repeat-tool-guard/src/index.ts

@@ -140,7 +140,7 @@ function validateThresholds(values: number[]): number[] {
 
 /**
  * Prepend the guard's reminder while preserving every downstream context's
- * source, envelope, and metadata.
+ * source and metadata.
  */
 function prependContext(ours: HookContext, theirs: HookContext[] | undefined): HookContext[] {
   return [ours, ...theirs ?? []]

packages/hooks/hooks-claude/tests/coverage-cases.ts

@@ -508,7 +508,6 @@ export function defineCoverageCases(group: CoverageGroup): void {
         additionalContexts: [{
           content: [{ type: 'text' as const, text: 'from-downstream' }],
           source: { kind: 'plugin' as const, plugin: 'policy' },
-          envelope: 'raw' as const,
           meta: { owner: 'policy' },
         }],
       }))
@@ -527,7 +526,6 @@ export function defineCoverageCases(group: CoverageGroup): void {
         { kind: 'plugin', plugin: 'hooks-claude' },
         { kind: 'plugin', plugin: 'policy' },
       ])
-      expect(contexts[1]?.type === 'context/message' && contexts[1].data.envelope).toBe('raw')
       expect(contexts[1]?.type === 'context/message' && contexts[1].data.meta).toEqual({ owner: 'policy' })
     })
 
@@ -561,7 +559,6 @@ export function defineCoverageCases(group: CoverageGroup): void {
         additionalContexts: [{
           content: [{ type: 'text' as const, text: 'downstream-note' }],
           source: { kind: 'plugin' as const, plugin: 'policy' },
-          envelope: 'raw' as const,
           meta: { owner: 'policy' },
         }],
       }))
@@ -574,7 +571,6 @@ export function defineCoverageCases(group: CoverageGroup): void {
         { kind: 'plugin', plugin: 'hooks-claude' },
         { kind: 'plugin', plugin: 'policy' },
       ])
-      expect(contexts[1]?.type === 'context/message' && contexts[1].data.envelope).toBe('raw')
       expect(contexts[1]?.type === 'context/message' && contexts[1].data.meta).toEqual({ owner: 'policy' })
     })