Coder/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'master' into codex/reject-credentialed-search-redirects

Browse Source
This commit is contained in:
Tianyi Cui
2026-07-20 18:20:47 +08:00
committed by GitHub
parent efdaad2797 09bcaaa66d
commit eab5699fd4
775 changed files with 17289 additions and 10274 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
packages/AGENTS.md
View File

@@ -6,9 +6,9 @@ These package-specific rules supplement the repo-wide [conventions](../AGENTS.md
- **Optional services use `ctx.get(name)`.** Reserve `ctx.<name>` for declared injections; the property proxy is topology-sensitive, while strict `ctx.get` reads the global service store ([postmortem](../docs/postmortem/0001-acp-default-export-drops-inject.md)).
- **Product-visible plugins require a non-unit REAL-composition test.** Hand-built `ctx.plugin(...)` suites are insufficient. Boot test-only `cordis.yml` through the Loader and app/process; mock only external/nondeterministic boundaries and assert model-visible, durable, or user-visible output. Keep opt-ins out of shipped defaults. [Policy](../docs/testing.md).
- **Typed same-process service and plugin calls are contracts, not serialization boundaries.** Prefer readonly borrowed values; materialize or defensively validate only at parser/config, queued, model/tool JSON, durable/file, worker, process, or wire boundaries.
- **Initiator-owned private chains derive, then capture.** Under `ctx.agents.withInitiator()`, recover the Agent at each orchestration entry, derive `agent.session`, and let operation-local helpers close over it. Keep `Agent` and `Session` explicit at lifecycle, session-log, service, authority, worker/process, persistence, and wire interfaces; do not widen a leaf helper from `Session` to `Context` merely to hide a parameter ([rationale](../docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md)).
- **Initiator-owned private chains derive, then capture.** Under `ctx.agents.withInitiator()`, recover the Agent at each orchestration entry, derive `agent.session`, and let operation-local helpers close over it. Keep `Agent` and `Session` explicit at lifecycle, session-log, service, authority, worker/process, persistence, and wire interfaces; do not widen a leaf helper from `Session` to `Context` merely to hide a parameter ([rationale](../.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.md)).
- **Represent one asynchronous operation with one lifecycle controller or transaction.** Separate readiness, cancellation, disposal, reservation, or sentinel state requires an independent owner or settlement boundary; otherwise fold it while preserving rollback, callback containment, and quiescence.
- **Shape capability interfaces around all current consumers.** Keep tool-schema, Loader, UI, transport, and backend-specific behavior in the consumer or adapter; do not let one consumer dictate the interface ([capability-seam rationale](../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md)).
- **Shape capability interfaces around all current consumers.** Keep tool-schema, Loader, UI, transport, and backend-specific behavior in the consumer or adapter; do not let one consumer dictate the interface ([capability-seam rationale](../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md)).
- **Require a current owner and need.** Tie each abstraction, state machine, option, defensive copy, and compatibility path to a current contract or production consumer, and keep behavior in its owning plugin or service.
- **Require evidence for public choices.** Configurability does not justify an unsupported default, public operation set, format, or imported external concept. Use current-consumer evidence or relevant prior art; otherwise require an explicit value or defer the choice.
- **Write model-facing contracts from the model's perspective.** Prompts, tool schemas, results, and diagnostics contain only task-relevant concepts, not UI, transport, or implementation vocabulary. Pin stable model-visible text verbatim and dynamic behavior through snapshots or end-to-end coverage.
@@ -23,4 +23,4 @@ Naming notes:
- Tests live at package level under `tests/`, not `src/__tests__/`.
- A package's README and JSDoc are part of the change: altered behavior (config keys, defaults, error codes, wire fields) updates them in the same commit. `doc-sync` gates what it can; apply [dsh-prose-standard](../.agents/skills/dsh-prose-standard/SKILL.md) for complete, concise prose and verify accuracy against code.
- Package READMEs document model, token, and KV-cache effects using the [canonical Model Experience format](../docs/cookbook/adding-a-package.md#4-write-the-package-readme).
- Package READMEs put durable consumer gaps and non-obvious maintainer constraints under `## Known Limitations and Deferred Work`; ordinary cleanup stays in its TODO or RFC. Packages with none use a justified [allowlist entry](../scripts/verify-package-readme-limitations.ts) ([rationale](../docs/rfc/implemented/process/2026-07-10-readme-known-limitations-gate.md)).
- Package READMEs put durable consumer gaps and non-obvious maintainer constraints under `## Known Limitations and Deferred Work`; ordinary cleanup stays in its TODO or Agent Note. Packages with none use a justified [allowlist entry](../scripts/verify-package-readme-limitations.ts) ([rationale](../.agents/notes/implemented/process/2026-07-10-readme-known-limitations-gate.md)).

4
packages/README.md
View File

@@ -25,7 +25,7 @@ Packages live at `packages/<group>/<pkg>/`; groups are containers, while names r
| [`todo/`](todo/README.md) | Todo/planning family: the model-facing `todo_write` tool | Product — stable surface |
| [`timeout/`](timeout/README.md) | Tool-call timeout policy: the `tools/execute` deadline enforcer | Product — stable surface |
| [`guard/`](guard/README.md) | Loop-hygiene guards: advisory repeat-call reminders | Product — stable surface |
| [`cordis/`](cordis/README.md) | Self-referential runtime toolset: inspect the live runtime's plugins and services, mount/unmount model-written plugins ([design](../docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md)) | Product — stable surface |
| [`cordis/`](cordis/README.md) | Self-referential runtime toolset: inspect the live runtime's plugins and services, mount/unmount model-written plugins ([design](../.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md)) | Product — stable surface |
| [`hooks/`](hooks/README.md) | Hook bridges + the shared Claude Code / Codex wire-protocol library | Product — stable surface |
| [`session-persistence/`](session-persistence/README.md) | Persistence capability family: the seam + JSONL/SQLite backends | Product — stable surface |
| [`session-query/`](session-query/README.md) | Session retrieval: logical corpus, bounded reads, lineage, and event relationships | Product — stable surface |
@@ -41,6 +41,6 @@ Groups distinguish product API from support infrastructure. New packages join an
The dependency graph is generated: [docs/module-graph.md](../docs/module-graph.md) (`pnpm run gen-module-graph`, freshness-gated in CI).
The rule it must obey: **extension plugins depend on interfaces, never on the concrete loop.** `dsh-agent-loop` is swappable — UI/hook/tool plugins keep working against the `dsh-agent` vocabulary if the loop is replaced. The sanctioned exception is a **composition/bundle** package like `dsh-agent-spine-demo`, whose whole job is to assemble the concrete spine: it depends on `dsh-agent-loop` (and the other concrete spine plugins) on purpose. The rule constrains plugins that EXTEND the system, not the bundle that COMPOSES it. A swappable capability splits into interface / implementation / consumer packages (the bash trio is the template — see [capability seams](../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md)).
The rule it must obey: **extension plugins depend on interfaces, never on the concrete loop.** `dsh-agent-loop` is swappable — UI/hook/tool plugins keep working against the `dsh-agent` vocabulary if the loop is replaced. The sanctioned exception is a **composition/bundle** package like `dsh-agent-spine-demo`, whose whole job is to assemble the concrete spine: it depends on `dsh-agent-loop` (and the other concrete spine plugins) on purpose. The rule constrains plugins that EXTEND the system, not the bundle that COMPOSES it. A swappable capability splits into interface / implementation / consumer packages (the bash trio is the template — see [capability seams](../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md)).
Package READMEs cover purpose, APIs, extension points, and [Model Experience](../docs/cookbook/adding-a-package.md#4-write-the-package-readme) unless on the model-agnostic [omission allowlist](../scripts/verify-package-readme-model-experience.ts). They also carry `## Known Limitations and Deferred Work` or use its [allowlist](../scripts/verify-package-readme-limitations.ts).

2
packages/bash/README.md
View File

@@ -1,6 +1,6 @@
# bash/ — bash capability family
The canonical three-package capability seam (see [capability seams](../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md)): an abstract executor interface, concrete implementations, and the model-facing tool that consumes it. All **product** packages.
The canonical three-package capability seam (see [capability seams](../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md)): an abstract executor interface, concrete implementations, and the model-facing tool that consumes it. All **product** packages.
| Package | Role | ctx key |
|---|---|---|

13
packages/bash/bash-local/README.md
View File

@@ -1,6 +1,6 @@
# @deepseek-ai/dsh-bash-local
Local-subprocess implementation of the `@deepseek-ai/dsh-bash` executor seam: `LocalBashExecutor` spawns `bash -c <command>` per call in its own process group, collects bounded output with full-stream spill files, and escalates kills SIGTERM→SIGKILL across the whole group.
Local-subprocess implementation of the `@deepseek-ai/dsh-bash` executor seam: `LocalBashExecutor` spawns `bash -c <command>` per call in its own process group, collects bounded output with size-limited full-stream spill files, and escalates kills SIGTERM→SIGKILL across the whole group.
The package root exports the default and named `LocalBashExecutor` plugin plus its `Config`; subprocess plumbing stays internal to the implementation package.
@@ -14,7 +14,8 @@ The package root exports the default and named `LocalBashExecutor` plugin plus i
timeoutMs: 120000 # default foreground timeout
maxTimeoutMs: 600000 # cap for per-call overrides
maxOutputBytes: 64000 # per-stream in-memory cap; overflow spills to disk
graceMs: 3000 # SIGTERM→SIGKILL escalation grace on kills
maxSpillBytes: 67108864 # per-stream full-output spill cap
graceMs: 3000 # kill escalation and post-exit pipe-drain grace
```
## Behavior (and where it came from)
@@ -22,9 +23,9 @@ The package root exports the default and named `LocalBashExecutor` plugin plus i
Design surveyed against the bash tools of Claude Code, OpenCode, Codex, and pi; the notable choices:
- **Spawn per call, no shell state** — every call is a fresh non-login `bash -c` (deterministic; no rc files). All four surveyed tools spawn per call. `XXX(stateful-shell)` in `src/run.ts` records the two proven stateful designs (Claude Code's cwd-only persistence; Codex's PTY exec sessions) for when real workflows demand them.
- **Process-group kills with escalation** — children are spawned `detached` (own process group); kills send SIGTERM to the group, then SIGKILL after the `graceMs` grace (default 3s — OpenCode's escalation; pipelines and subshells die with the parent). ESRCH is tolerated; daemons that re-parent away from the group can still survive — same caveat as the surveyed tools.
- **Tail-keep truncation + spill files** — output beyond `maxOutputBytes` keeps the in-memory TAIL (errors/results cluster at the end — pi/OpenCode rationale) while the FULL stream is appended to a temp file whose path is reported when available. A foreground `BashExecRequest.stdoutMaxBytes` can raise stdout's capture budget for one trusted caller; stderr and background tasks still use `maxOutputBytes`. If the final spill close reports a delayed writeback failure, the executor still returns the tail but withholds the path rather than advertising a possibly incomplete file.
- **Model-friendly env + credential scrub** — `process.env` minus credential-shaped vars (`*KEY*`/`*SECRET*`/`*TOKEN*`) and all ambient `DSH_*` names, then `NO_COLOR=1 TERM=dumb PAGER=cat GIT_PAGER=cat` (Codex's hardcoded set) so pagers and ANSI color don't garble results. A spec's ordinary `env` is merged after the scrub but rejects `DSH_*`; managed `dshEnv` rejects ordinary names and merges last, preventing stale nested-harness identity. Supplied stdin is written and closed; otherwise fd 0 is `/dev/null`. See the [stdin/env RFC](../../../docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md) and [managed environment RFC](../../../docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md).
- **Process-group kills with escalation** — children are spawned `detached` (own process group); kills send SIGTERM to the group, then SIGKILL after the `graceMs` grace (default 3s — OpenCode's escalation; pipelines and subshells die with the parent). After the main shell exits, inherited stdout/stderr pipes receive the same bounded drain grace so a surviving descendant cannot hold the command open indefinitely. ESRCH is tolerated; daemons that re-parent away from the group can still survive — same caveat as the surveyed tools.
- **Tail-keep truncation + bounded spill files** — output beyond `maxOutputBytes` keeps the in-memory TAIL (errors/results cluster at the end — pi/OpenCode rationale) while the FULL stream is appended to a temp file whose path is reported when available. A foreground `BashExecRequest.stdoutMaxBytes` can raise stdout's capture budget for one trusted caller; stderr and background tasks still use `maxOutputBytes`. A stream larger than `maxSpillBytes` discards its now-incomplete spill and returns only the marked truncated tail. If the final spill close reports a delayed writeback failure, the executor likewise withholds the path rather than advertising an incomplete file.
- **Model-friendly env + credential scrub** — `process.env` minus credential-shaped vars (`*KEY*`/`*SECRET*`/`*TOKEN*`) and all ambient `DSH_*` names, then `NO_COLOR=1 TERM=dumb PAGER=cat GIT_PAGER=cat` (Codex's hardcoded set) so pagers and ANSI color don't garble results. A spec's ordinary `env` is merged after the scrub but rejects `DSH_*`; managed `dshEnv` rejects ordinary names and merges last, preventing stale nested-harness identity. Supplied stdin is written and closed; otherwise fd 0 is `/dev/null`. See the [stdin/env Agent Note](../../../.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md) and [managed environment Agent Note](../../../.agents/notes/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md).
- **Background processes** — `start()` returns a live `BashProcess` handle immediately, no timeout applies (Claude Code detaches timeouts when backgrounding), the handle's `readOutput()` is incremental with whole-stream byte offsets, and disposal kills every running process and awaits its exit. Everything task-shaped (ids, ownership, polling, notices) lives in the generic [`ctx.tasks` runtime](../../tasks/tasks/README.md), which the tool layer registers the handle with — this executor never sees a session or a registry.
## Model Experience
@@ -41,6 +42,6 @@ No direct invalidation; the named consumer owns any request-prefix changes.
- **No persistent shell or PTY** — every call starts a fresh non-login `bash -c`; cwd-only persistence and interactive terminal sessions remain deferred until a real workflow requires them.
- **POSIX-only** — the `bash` binary, detached process groups, group kills, and SIGTERM→SIGKILL escalation are hardcoded; Windows is unsupported.
- **The credential scrub is a name heuristic** — `*KEY*`/`*SECRET*`/`*TOKEN*` only; differently-named secrets (e.g. `*PASSWORD*`) pass through, and a whitelist for over-scrubbed vars is noted future work.
- **Spill files are never deleted** — full-output recovery files (and the private per-process spill dir) accumulate under the OS tmpdir until something external cleans them.
- **Completed spill files are not deleted** — bounded full-output recovery files (and the private per-process spill dir) accumulate under the OS tmpdir until something external cleans them; oversize incomplete spills are discarded and deletion is attempted immediately, but a cleanup failure can leave a bounded file behind.
The raw process handling lives in `src/run.ts`; `src/index.ts` is the service wiring.

10
packages/bash/bash-local/src/index.ts
View File

@@ -10,7 +10,7 @@ import z from 'schemastery'
import { BashExecutor } from '@deepseek-ai/dsh-bash'
import type { BashExecRequest, BashExecSpec, BashProcess, BashProcessRead, BashRunResult } from '@deepseek-ai/dsh-bash'
import { clampTimeout, deadline, timeoutOf } from '@deepseek-ai/dsh-timeout'
import { DEFAULT_GRACE_MS, runBash } from './run.ts'
import { DEFAULT_GRACE_MS, DEFAULT_MAX_SPILL_BYTES, runBash } from './run.ts'
import type { RunInternals, RunningBash } from './run.ts'
/** Plugin config (all optional — `static Config` supplies the defaults). */
@@ -23,7 +23,9 @@ export interface Config {
maxTimeoutMs?: number
/** Per-stream in-memory output cap; overflow spills to a temp file. */
maxOutputBytes?: number
/** Grace period between the SIGTERM and the SIGKILL escalation on a kill. */
/** Per-stream spill-file cap; larger streams retain only their in-memory tail. */
maxSpillBytes?: number
/** Grace period for kill escalation and for inherited pipes after shell exit. */
graceMs?: number
}
@@ -46,6 +48,7 @@ export class LocalBashExecutor extends BashExecutor {
timeoutMs: z.number().default(120_000),
maxTimeoutMs: z.number().default(600_000),
maxOutputBytes: z.number().default(64_000),
maxSpillBytes: z.number().default(DEFAULT_MAX_SPILL_BYTES),
graceMs: z.number().default(DEFAULT_GRACE_MS),
})
@@ -64,6 +67,7 @@ export class LocalBashExecutor extends BashExecutor {
assertPositiveFinite('timeoutMs', this.config.timeoutMs)
assertPositiveFinite('maxTimeoutMs', this.config.maxTimeoutMs)
assertPositiveFinite('maxOutputBytes', this.config.maxOutputBytes)
assertPositiveFinite('maxSpillBytes', this.config.maxSpillBytes)
assertPositiveFinite('graceMs', this.config.graceMs)
ctx.effect(() => async () => {
// Await closure so even a TERM-trapping child cannot outlive the fiber.
@@ -120,6 +124,7 @@ export class LocalBashExecutor extends BashExecutor {
cwd: spec.workdir,
stdoutMaxBytes: spec.stdoutMaxBytes,
stderrMaxBytes: this.config.maxOutputBytes,
maxSpillBytes: this.config.maxSpillBytes,
graceMs: this.config.graceMs,
signal: d.signal,
stdin: spec.stdin,
@@ -139,6 +144,7 @@ export class LocalBashExecutor extends BashExecutor {
cwd: spec.workdir,
stdoutMaxBytes: this.config.maxOutputBytes,
stderrMaxBytes: this.config.maxOutputBytes,
maxSpillBytes: this.config.maxSpillBytes,
graceMs: this.config.graceMs,
signal: spec.signal,
stdin: spec.stdin,

75
packages/bash/bash-local/src/run.ts
View File

@@ -8,7 +8,7 @@
import { type ChildProcessByStdio, spawn } from 'node:child_process'
import type { Readable, Writable } from 'node:stream'
import { randomBytes } from 'node:crypto'
import { closeSync, mkdtempSync, openSync, writeSync } from 'node:fs'
import { closeSync, mkdtempSync, openSync, unlinkSync, writeSync } from 'node:fs'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { DSH_ENV_PREFIX } from '@deepseek-ai/dsh-bash'
@@ -72,7 +72,9 @@ export interface SpawnSpec {
stdoutMaxBytes: number
/** Stderr in-memory cap; overflow spills to disk (tail kept in memory). */
stderrMaxBytes: number
/** Grace period between the SIGTERM and the SIGKILL escalation on a kill. */
/** Per-stream spill-file cap; larger streams retain only their in-memory tail. */
maxSpillBytes: number
/** Grace period for kill escalation and for inherited pipes after shell exit. */
graceMs: number
/**
* Abort signal — kills the process group when it fires. The executor owns
@@ -119,6 +121,9 @@ export interface RunInternals {
/** Default SIGTERM→SIGKILL grace period (the `graceMs` config; matches OpenCode's 3s). */
export const DEFAULT_GRACE_MS = 3_000
/** Default per-stream spill cap (the `maxSpillBytes` config). */
export const DEFAULT_MAX_SPILL_BYTES = 64 * 1024 * 1024
let spillCounter = 0
let defaultSpillDir: string | undefined
@@ -133,9 +138,9 @@ function privateSpillDir(): string {
}
/**
* Collects one stream with a bounded in-memory tail. The FULL stream is
* always recoverable: on first overflow a spill file is created and every
* chunk (including those already collected) is appended there.
* Collects one stream with a bounded in-memory tail. On first overflow a
* spill file is created and every chunk (including those already collected)
* is appended there while the full stream remains within `maxSpillBytes`.
*
* Tail-keep rationale (pi/OpenCode): errors and final results cluster at the
* end of command output; the spill file covers the head.
@@ -146,11 +151,13 @@ export class OutputCollector {
private dropped = false
private spillFd: number | undefined
private spillFile: string | undefined
private spillDisabled = false
/** Total bytes ever pushed (not just retained). */
private total = 0
constructor(
private readonly maxBytes: number,
private readonly maxSpillBytes: number,
private readonly label: string,
private readonly spillDir: string,
) {}
@@ -166,7 +173,7 @@ export class OutputCollector {
push(chunk: Buffer): void {
this.total += chunk.length
const overflows = this.bytes + chunk.length > this.maxBytes
if (overflows || this.spillFd !== undefined) this.spillAll(chunk)
if (!this.spillDisabled && (overflows || this.spillFd !== undefined)) this.spillAll(chunk)
this.chunks.push(chunk)
this.bytes += chunk.length
while (this.bytes > this.maxBytes && this.chunks.length > 1) {
@@ -188,6 +195,10 @@ export class OutputCollector {
/** Open the spill file lazily and append `chunk` (and any prior chunks once). */
private spillAll(chunk: Buffer): void {
if (this.total > this.maxSpillBytes) {
this.discardSpill()
return
}
if (this.spillFd === undefined) {
// Random suffix + O_EXCL + no-follow-equivalent ('wx' fails on any
// existing path, symlink or not) + owner-only mode: defeats spill-path
@@ -202,6 +213,30 @@ export class OutputCollector {
writeSync(this.spillFd, chunk)
}
/** Stop spilling and remove the file once it can no longer hold the complete stream. */
private discardSpill(): void {
const fd = this.spillFd
const file = this.spillFile
this.spillFd = undefined
this.spillFile = undefined
this.spillDisabled = true
if (fd !== undefined) {
try {
closeSync(fd)
} catch {
// Retain the descriptor so finalize can retry the failed close.
this.spillFd = fd
}
}
if (file !== undefined) {
try {
unlinkSync(file)
} catch {
// A failed unlink leaves at most maxSpillBytes behind, never an unbounded file.
}
}
}
/**
* Incremental read in whole-stream byte coordinates: returns everything
* pushed since `fromByte`. When `fromByte` has already slid out of the
@@ -301,8 +336,8 @@ export function runBash(spec: SpawnSpec, internals: RunInternals = {}): RunningB
? spawn('bash', ['-c', spec.command], { cwd: spec.cwd, env, stdio: ['pipe', 'pipe', 'pipe'], detached: true })
: spawn('bash', ['-c', spec.command], { cwd: spec.cwd, env, stdio: ['ignore', 'pipe', 'pipe'], detached: true })
const stdout = new OutputCollector(spec.stdoutMaxBytes, 'stdout', spillDir)
const stderr = new OutputCollector(spec.stderrMaxBytes, 'stderr', spillDir)
const stdout = new OutputCollector(spec.stdoutMaxBytes, spec.maxSpillBytes, 'stdout', spillDir)
const stderr = new OutputCollector(spec.stderrMaxBytes, spec.maxSpillBytes, 'stderr', spillDir)
child.stdout.on('data', (chunk: Buffer) => { stdout.push(chunk) })
child.stderr.on('data', (chunk: Buffer) => { stderr.push(chunk) })
@@ -328,12 +363,13 @@ export function runBash(spec: SpawnSpec, internals: RunInternals = {}): RunningB
}
const done = new Promise<SpawnOutcome>((resolve, reject) => {
child.on('error', (error) => {
// No meaningful close outcome follows a spawn failure.
cleanup()
reject(error)
})
child.on('close', (exitCode, signal) => {
let settled = false
let pipeDrainTimer: NodeJS.Timeout | undefined
const settle = (exitCode: number | null, signal: NodeJS.Signals | null): void => {
if (settled) return
settled = true
child.stdout.destroy()
child.stderr.destroy()
cleanup()
resolve({
exitCode,
@@ -341,9 +377,20 @@ export function runBash(spec: SpawnSpec, internals: RunInternals = {}): RunningB
stdout: stdout.finalize(),
stderr: stderr.finalize(),
})
}
child.on('error', (error) => {
// No meaningful close outcome follows a spawn failure.
settled = true
cleanup()
reject(error)
})
child.on('exit', (exitCode, signal) => {
pipeDrainTimer = setTimeout(() => { settle(exitCode, signal) }, spec.graceMs)
})
child.on('close', settle)
function cleanup(): void {
if (graceTimer !== undefined) clearTimeout(graceTimer)
if (pipeDrainTimer !== undefined) clearTimeout(pipeDrainTimer)
spec.signal?.removeEventListener('abort', onAbort)
}
})

1
packages/bash/bash-local/tests/executor.spec.ts
View File

@@ -66,6 +66,7 @@ describe('LocalBashExecutor.run', () => {
await expect(setup({ timeoutMs: Number.NaN })).rejects.toThrow(/timeoutMs/)
await expect(setup({ maxTimeoutMs: 0 })).rejects.toThrow(/maxTimeoutMs/)
await expect(setup({ maxOutputBytes: -1 })).rejects.toThrow(/maxOutputBytes/)
await expect(setup({ maxSpillBytes: 0 })).rejects.toThrow(/maxSpillBytes/)
await expect(setup({ graceMs: 0 })).rejects.toThrow(/graceMs/)
const { bash } = await setup()

77
packages/bash/bash-local/tests/run.spec.ts
View File

@@ -1,4 +1,4 @@
import { mkdtempSync, readFileSync, statSync } from 'node:fs'
import { mkdtempSync, readFileSync, statSync, unlinkSync } from 'node:fs'
import { tmpdir } from 'node:os'
import { dirname, join } from 'node:path'
import { describe, expect, it, vi } from 'vitest'
@@ -6,7 +6,10 @@ import type { DshEnvironment } from '@deepseek-ai/dsh-bash'
import { killGroup, OutputCollector, runBash } from '../src/run.ts'
import type { RunningBash } from '../src/run.ts'
const { failNextClose } = vi.hoisted(() => ({ failNextClose: { value: false } }))
const { failNextClose, failNextUnlink } = vi.hoisted(() => ({
failNextClose: { value: false },
failNextUnlink: { value: false },
}))
vi.mock('node:fs', async (importOriginal) => {
const actual = await importOriginal<typeof import('node:fs')>()
return {
@@ -18,6 +21,13 @@ vi.mock('node:fs', async (importOriginal) => {
}
actual.closeSync(fd)
},
unlinkSync(path: Parameters<typeof actual.unlinkSync>[0]): void {
if (failNextUnlink.value) {
failNextUnlink.value = false
throw Object.assign(new Error('simulated EIO on unlink'), { code: 'EIO' })
}
actual.unlinkSync(path)
},
}
})
@@ -29,6 +39,7 @@ function spec(command: string, overrides: Partial<Parameters<typeof runBash>[0]>
cwd: process.cwd(),
stdoutMaxBytes: 64_000,
stderrMaxBytes: 64_000,
maxSpillBytes: 64 * 1024 * 1024,
graceMs: 3_000,
...overrides,
}
@@ -173,6 +184,22 @@ describe('runBash', () => {
const result = await running.done
expect(result.signal).toBe('SIGTERM')
})
it('bounds inherited-pipe draining after the shell exits', async () => {
const pidFile = join(spillDir, `pipe-holder-${Date.now()}.pid`)
const started = Date.now()
const running = runBash(spec(`sleep 60 & echo $! > ${pidFile}; echo shell-done`, { graceMs: 100 }))
const descendant = await waitForPidFile(pidFile)
try {
const result = await running.done
expect(Date.now() - started).toBeLessThan(1_000)
expect(result.exitCode).toBe(0)
expect(result.stdout.text).toBe('shell-done\n')
} finally {
process.kill(descendant, 'SIGKILL')
await waitGone(descendant)
}
})
})
describe('stdin and extra env (set by in-process plugins)', () => {
@@ -282,7 +309,7 @@ describe('output truncation and spill', () => {
describe('OutputCollector', () => {
it('keeps the tail of a single oversized chunk', () => {
const collector = new OutputCollector(10, 'test', spillDir)
const collector = new OutputCollector(10, 100, 'test', spillDir)
collector.push(Buffer.from('0123456789abcdef'))
const out = collector.finalize()
expect(out.text).toBe('6789abcdef')
@@ -291,7 +318,7 @@ describe('OutputCollector', () => {
})
it('readFrom returns increments and flags lossy reads', () => {
const collector = new OutputCollector(10, 'test', spillDir)
const collector = new OutputCollector(10, 100, 'test', spillDir)
collector.push(Buffer.from('aaaaa'))
const first = collector.readFrom(0)
expect(first.text).toBe('aaaaa')
@@ -312,7 +339,7 @@ describe('OutputCollector', () => {
})
it('contains close failures and drops the spill path', () => {
const collector = new OutputCollector(4, 'closefail', spillDir)
const collector = new OutputCollector(4, 100, 'closefail', spillDir)
collector.push(Buffer.from('aaaa'))
collector.push(Buffer.from('bbbb'))
expect(collector.readFrom(0).spillPath).toBeDefined()
@@ -326,6 +353,46 @@ describe('OutputCollector', () => {
expect(out!.truncated).toBe(true)
expect(out!.spillPath).toBeUndefined()
})
it('discards a spill that exceeds its configured cap', () => {
const collector = new OutputCollector(4, 8, 'bounded', spillDir)
collector.push(Buffer.from('aaaa'))
collector.push(Buffer.from('bbbb'))
const spillPath = collector.readFrom(0).spillPath!
expect(readFileSync(spillPath, 'utf8')).toBe('aaaabbbb')
collector.push(Buffer.from('c'))
collector.push(Buffer.from('dddd'))
const out = collector.finalize()
expect(out.text).toBe('dddd')
expect(out.truncated).toBe(true)
expect(out.spillPath).toBeUndefined()
expect(() => readFileSync(spillPath)).toThrow()
})
it('does not create a spill when the first overflowing chunk exceeds the cap', () => {
const collector = new OutputCollector(4, 4, 'no-spill', spillDir)
collector.push(Buffer.from('abcdefgh'))
const out = collector.finalize()
expect(out.text).toBe('efgh')
expect(out.truncated).toBe(true)
expect(out.spillPath).toBeUndefined()
})
it('contains cleanup failures while disabling an oversize spill', () => {
const collector = new OutputCollector(4, 8, 'cleanup-fail', spillDir)
collector.push(Buffer.from('aaaa'))
collector.push(Buffer.from('bbbb'))
const spillPath = collector.readFrom(0).spillPath!
failNextClose.value = true
failNextUnlink.value = true
expect(() => { collector.push(Buffer.from('c')) }).not.toThrow()
expect(failNextClose.value).toBe(false)
expect(failNextUnlink.value).toBe(false)
expect(collector.finalize().spillPath).toBeUndefined()
unlinkSync(spillPath)
})
})
describe('killGroup', () => {

10
packages/bash/bash-sandbox/README.md
View File

@@ -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 RFC § Escalation](../../../docs/rfc/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.

5
packages/bash/bash-sandbox/package.json
View File

@@ -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"
}

55
packages/bash/bash-sandbox/src/index.ts
View File

@@ -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. */

4
packages/bash/bash-sandbox/tests/bwrap.e2e.ts
View File

@@ -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
}

4
packages/bash/bash-sandbox/tests/landlock.e2e.ts
View File

@@ -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
}

23
packages/bash/bash-sandbox/tests/sandbox.spec.ts
View File

@@ -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'))

4
packages/bash/bash-sandbox/tests/seatbelt.e2e.ts
View File

@@ -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
}

6
packages/bash/bash-sandbox/tsconfig.json
View File

@@ -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"
},

6
packages/bash/bash/README.md
View File

@@ -29,9 +29,9 @@ 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 RFC](../../../docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md) and [the session environment RFC](../../../docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.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).
## Model Experience
@@ -44,4 +44,4 @@ No direct invalidation; the named consumer owns any request-prefix changes.
## Known Limitations and Deferred Work
- **No interactive-input vocabulary** — `stdin` is written once at spawn and closed; the seam has no channel to feed a running task and no PTY session concept.
- **Foreground timeouts are always executor-owned** — a caller-owned-deadline mode on the seam is explicitly deferred by [the tool-call timeout-policy RFC](../../../docs/rfc/implemented/architecture/2026-07-07-tool-call-timeout-policy.md).
- **Foreground timeouts are always executor-owned** — a caller-owned-deadline mode on the seam is explicitly deferred by [the tool-call timeout-policy Agent Note](../../../.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.md).

2
packages/bash/bash/package.json
View File

@@ -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"
}
}

1
packages/bash/bash/src/index.ts
View File

@@ -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,

52
packages/bash/bash/src/session-mode.ts
View File

@@ -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 })
}

2
packages/bash/bash/src/types.ts
View File

@@ -131,7 +131,7 @@ export interface BashRunResult {
* short. Mutually exclusive with {@link aborted}: one fused deadline drives
* both the timeout and the caller's cancellation, so a timeout and an abort
* racing before process close report the single first-abort cause, not both
* (see the [timeout-library RFC](../../../../docs/rfc/implemented/architecture/2026-07-06-timeout-deadline-library.md)).
* (see the [timeout-library Agent Note](../../../../.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.md)).
*/
timedOut: boolean
/**

3
packages/bash/bash/tsconfig.json
View File

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

8
packages/bash/tool-bash/README.md
View File

@@ -57,17 +57,17 @@ The tool owns its `presentCall`/`presentResult` render intent. A foreground call
## The tool builds its request from named args only
The `BashExecRequest` seam carries optional `stdoutMaxBytes`, `stdin`, ordinary `env`, and managed `dshEnv`, used by trusted in-process plugins and this tool's environment registry. The model-facing tool exposes none of `stdoutMaxBytes`, `stdin`, or `env`: it builds requests from named command/workdir/timeout/signal/sandbox fields plus the registry-collected `dshEnv`. Extra model keys are ignored and cannot replace managed values. Shell syntax provides equivalent command-level behavior, while the local executor scrubs ambient credentials and stale `DSH_*` values. See the [stdin/env RFC](../../../docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md).
The `BashExecRequest` seam carries optional `stdoutMaxBytes`, `stdin`, ordinary `env`, and managed `dshEnv`, used by trusted in-process plugins and this tool's environment registry. The model-facing tool exposes none of `stdoutMaxBytes`, `stdin`, or `env`: it builds requests from named command/workdir/timeout/signal/sandbox fields plus the registry-collected `dshEnv`. Extra model keys are ignored and cannot replace managed values. Shell syntax provides equivalent command-level behavior, while the local executor scrubs ambient credentials and stale `DSH_*` values. See the [stdin/env Agent Note](../../../.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md).
## Permissions and escalation
Commands run with the executor's full authority unless a sandboxing executor ([`dsh-bash-sandbox`](../bash-sandbox/)) confines them — the deny-only sandbox reports denials as result facts, rendered here as the denial marker; per-call allow/deny/ask policy is the `tools/pre-execute` waterfall (see docs/architecture.md).
Escalating bash calls resolve `ctx.approval` before execution. `allowed-once` applies the requested mode only to that call; rejection, cancellation, unavailability, or missing approval context executes nothing and returns a distinct error. On a real denial, the model may retry the same command once in the same turn with the narrowest sufficient mode and justification; the approval prompt itself is the consent step. Escalation is never speculative, and a disabled or rejected approval is final. The [sandbox RFC](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md) owns the rationale.
Escalating bash calls resolve `ctx.approval` before execution. `allowed-once` applies the requested mode only to that call; rejection, cancellation, unavailability, or missing approval context executes nothing and returns a distinct error. On a real denial, the model may retry the same command once in the same turn with the narrowest sufficient mode and justification; the approval prompt itself is the consent step. Escalation is never speculative, and a disabled or rejected approval is final. The [sandbox Agent Note](../../../.agents/notes/implemented/feature/2026-07-06-sandbox.md) owns the rationale.
## Per-session mode switching
For sandboxing executors, each call resolves mode as one-shot escalation, then session override, then executor default. Non-sandboxing and agent-less calls carry no session override. Neither the prompt nor a switch notice announces the standing mode; denial results report the effective mode when the boundary matters. See the [`dsh-bash` fold](../bash/README.md) and [sandbox switching contract](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md).
For sandboxing executors, each call resolves mode as one-shot escalation, then session override, then executor default. Non-sandboxing and agent-less calls carry no session override. Neither the prompt nor a switch notice announces the standing mode; denial results report the effective mode when the boundary matters. See the [`dsh-bash` fold](../bash/README.md) and [sandbox switching contract](../../../.agents/notes/implemented/feature/2026-07-06-sandbox.md).
## Model Experience
@@ -150,5 +150,5 @@ Append-only; newly visible content follows the reusable request prefix and does
## Known Limitations and Deferred Work
- **Replay exit pills parse from result text** — output whose final line happens to be exactly `[exit code: N]` / `[killed by signal: …]` shows a wrong pill on session replay; a display-only known residual.
- **The `bash` tool opts out of `timeout-policy` budgets** — it keeps the executor-owned `BASH_TIMEOUT` path, per [the tool-call timeout-policy RFC](../../../docs/rfc/implemented/architecture/2026-07-07-tool-call-timeout-policy.md).
- **The `bash` tool opts out of `timeout-policy` budgets** — it keeps the executor-owned `BASH_TIMEOUT` path, per [the tool-call timeout-policy Agent Note](../../../.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.md).
- **Background processes have no executor timeout** — callers must use `task_kill`, or rely on owner/service disposal, when work no longer matters.

5
packages/bash/tool-bash/package.json
View File

@@ -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"
}
}

73
packages/bash/tool-bash/src/index.ts
View File

@@ -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)

9
packages/bash/tool-bash/src/render.ts
View File

@@ -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

10
packages/bash/tool-bash/tests/tools.spec.ts
View File

@@ -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,
@@ -287,7 +287,7 @@ describe('bash tool', () => {
})
// Type and required-key violations are rejected by the harness
// (defineTool validates against the SchemaSpec — the arg-validation RFC) before execute.
// (defineTool validates against the SchemaSpec — the arg-validation Agent Note) before execute.
it.each([
[{}, /missing required property "command"/],
[{ command: 42, description: 'd' }, /"command" must be a string/],
@@ -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')
})
})
@@ -946,7 +946,7 @@ describe('the model-facing bash tool builds its request from named args only (no
* model input into the post-scrub `env` merge or per-run capture budget — NOT
* to defend a trust boundary
* (the credential scrub in dsh-bash-local is the security control; see the
* bash-stdin-env RFC). Foreground `run()` returns a canned result; `start()`
* bash-stdin-env Agent Note). Foreground `run()` returns a canned result; `start()`
* hands back an already-settled fake handle so the task registration completes.
*/
class RecordingBashExecutor extends BashExecutor {

3
packages/bash/tool-bash/tsconfig.json
View File

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

2
packages/code-runtime/README.md
View File

@@ -1,6 +1,6 @@
# code-runtime/ — code-execution capability family
The code-execution capability seam (see [capability seams](../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md)): an abstract runtime interface for executing one model-written program against host-provided async bindings, capturing what it printed and returned. The consumer is the tool registry's [Code Mode](../core/tools/README.md) (`tools: { mode: code }` — the `run_code` tool and the generated TypeScript SDK); design in the [Code Mode RFC](../../docs/rfc/implemented/feature/2026-06-15-code-mode.md). **Product** packages.
The code-execution capability seam (see [capability seams](../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md)): an abstract runtime interface for executing one model-written program against host-provided async bindings, capturing what it printed and returned. The consumer is the tool registry's [Code Mode](../core/tools/README.md) (`tools: { mode: code }` — the `run_code` tool and the generated TypeScript SDK); design in the [Code Mode Agent Note](../../.agents/notes/implemented/feature/2026-06-15-code-mode.md). **Product** packages.
| Package | Role | ctx key |
|---|---|---|

2
packages/code-runtime/code-runtime-worker/README.md
View File

@@ -1,6 +1,6 @@
# @deepseek-ai/dsh-code-runtime-worker
Worker-thread implementation of the [`@deepseek-ai/dsh-code-runtime`](../code-runtime/README.md) seam: `WorkerCodeRuntime` runs each program in ONE fresh Node `worker_threads.Worker` — TypeScript in, type-stripped host-side, bindings bridged over the message port, `{ value, logs, error? }` out. **Containment, not a security boundary**: trust posture is bash-equivalent by design (the [Code Mode RFC](../../../docs/rfc/implemented/feature/2026-06-15-code-mode.md) § Trust posture), with containment bash does not have — separate isolate, empty environment, heap cap, hard termination.
Worker-thread implementation of the [`@deepseek-ai/dsh-code-runtime`](../code-runtime/README.md) seam: `WorkerCodeRuntime` runs each program in ONE fresh Node `worker_threads.Worker` — TypeScript in, type-stripped host-side, bindings bridged over the message port, `{ value, logs, error? }` out. **Containment, not a security boundary**: trust posture is bash-equivalent by design (the [Code Mode Agent Note](../../../.agents/notes/implemented/feature/2026-06-15-code-mode.md) § Trust posture), with containment bash does not have — separate isolate, empty environment, heap cap, hard termination.
## Config

6
packages/code-runtime/code-runtime-worker/tests/runtime.spec.ts
View File

@@ -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')

4
packages/code-runtime/code-runtime/README.md
View File

@@ -2,7 +2,7 @@
The **code-execution seam**: an abstract `CodeRuntime` service (`ctx.codeRuntime`) defining WHAT a code runtime does — run one model-written program against a set of host-provided async bindings and report `{ value, logs, error? }` — without saying HOW.
This package is the interface third of the capability (the bash trio is the template — see [capability seams](../../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md)): implementations subclass `CodeRuntime` and register the service; the consumer is the tool registry's Code Mode, which generates the model-facing SDK and bridges tool dispatch — both specified in the [Code Mode RFC](../../../docs/rfc/implemented/feature/2026-06-15-code-mode.md), whose first implementation is a Node worker-thread backend. The runtime knows nothing about tools or sessions: it is handed named async functions and a program string, and everything tool-shaped stays with the consumer.
This package is the interface third of the capability (the bash trio is the template — see [capability seams](../../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md)): implementations subclass `CodeRuntime` and register the service; the consumer is the tool registry's Code Mode, which generates the model-facing SDK and bridges tool dispatch — both specified in the [Code Mode Agent Note](../../../.agents/notes/implemented/feature/2026-06-15-code-mode.md), whose first implementation is a Node worker-thread backend. The runtime knows nothing about tools or sessions: it is handed named async functions and a program string, and everything tool-shaped stays with the consumer.
## Service API (`ctx.codeRuntime`)
@@ -29,5 +29,5 @@ No direct invalidation; the named consumer owns any request-prefix changes.
## Known Limitations and Deferred Work
- **`run()` is one-shot** — `logs` arrive only on the resolved `CodeRunResult`; the seam exposes no streaming-log or progress surface for a live program's output.
- **A persistent REPL-style kernel is recorded future work** — the no-state-between-runs contract stands until a persistent-kernel backend brings its own logging story ([Code Mode RFC](../../../docs/rfc/implemented/feature/2026-06-15-code-mode.md)).
- **A persistent REPL-style kernel is recorded future work** — the no-state-between-runs contract stands until a persistent-kernel backend brings its own logging story ([Code Mode Agent Note](../../../.agents/notes/implemented/feature/2026-06-15-code-mode.md)).
- **Only the worker-thread backend ships** — `'process'`/`'container'` are declared well-known `isolation` values with no implementation; a hard security boundary awaits a container backend.

5
packages/compact/README.md
View File

@@ -1,11 +1,12 @@
# compact/ — compaction capability family
A three-package capability seam (see [capability seams](../../docs/rfc/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 RFC](../../docs/rfc/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.

21
packages/compact/compact-basic/README.md
View File

@@ -2,20 +2,21 @@
The **basic compaction backend**: a `BasicCompactService` implementing the `@deepseek-ai/dsh-compact` seam with reusable `ctx.tokenMeter` pressure, token-budget retention, and summarization as a direct one-shot `ctx.llm.stream()` call (interceptable at `llm/stream`).
This is the implementation tier of the compaction capability — see the [interface package](../compact/README.md) for the seam and the [capability-seam RFC](../../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md) for the design.
This is the implementation tier of the compaction capability — see the [interface package](../compact/README.md) for the seam and the [capability-seam Agent Note](../../../.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md) for the design.
## What it owns
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.
- **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 RFC](../../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md)).
- **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)).

7
packages/compact/compact-basic/package.json
View File

@@ -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"
}

55
packages/compact/compact-basic/src/index.ts
View File

@@ -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

193
packages/compact/compact-basic/tests/compact-basic.spec.ts
View File

@@ -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, {

10
packages/compact/compact-basic/tests/loader-composition.spec.ts
View File

@@ -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,

3
packages/compact/compact-basic/tsconfig.json
View File

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

60
packages/compact/compact-tool-result-prune/README.md Normal file
View File

@@ -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.

40
packages/compact/compact-tool-result-prune/package.json Normal file
View File

@@ -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"
}
}

77
packages/compact/compact-tool-result-prune/src/config.ts Normal file
View File

@@ -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`)
}
}

159
packages/compact/compact-tool-result-prune/src/index.ts Normal file
View File

@@ -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

40
packages/compact/compact-tool-result-prune/src/types.ts Normal file
View File

@@ -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
}

67
packages/compact/compact-tool-result-prune/tests/loader-composition.spec.ts Normal file
View File

@@ -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"/)
})
})

239
packages/compact/compact-tool-result-prune/tests/tool-result-prune.spec.ts Normal file
View File

@@ -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()
})
})

15
packages/compact/compact-tool-result-prune/tsconfig.json Normal file
View File

@@ -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" }
]
}

6
packages/compact/compact/README.md
View File

@@ -10,7 +10,7 @@ This package is the interface tier of the compaction capability, split so each c
| `@deepseek-ai/dsh-compact-basic` | a backend: `ctx.tokenMeter` pressure + token-budget retention + `llm.stream()` summarization |
| `@deepseek-ai/dsh-tool-compact` (deferred) | the model-facing `/compact` tool over `ctx.compact` |
Unlike the bash seam, this interface depends on `@deepseek-ai/dsh-session` and `@deepseek-ai/dsh-llm` — the contract's verbs are defined over a `Session` and its output is the `ContentBlock` vocabulary, so they cannot be expressed without naming those packages. That deviation from the "interface depends only on cordis" guidance is intentional and recorded in the [compaction capability-seam RFC](../../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md).
Unlike the bash seam, this interface depends on `@deepseek-ai/dsh-session` and `@deepseek-ai/dsh-llm` — the contract's verbs are defined over a `Session` and its output is the `ContentBlock` vocabulary, so they cannot be expressed without naming those packages. 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).
## Service API (`ctx.compact`)
@@ -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.

2
packages/compact/compact/src/index.ts
View File

@@ -3,7 +3,7 @@
* compact and replace a history range with one summary node by subclassing
* {@link CompactService}. This interface necessarily depends on session and LLM
* vocabulary; the rationale is in the
* [compaction RFC](../../../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md).
* [compaction Agent Note](../../../../.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md).
* @module @deepseek-ai/dsh-compact
*/

4
packages/compact/compact/src/types.ts
View File

@@ -3,7 +3,7 @@
* Those declaration-merged events are log-only lock/provenance markers, not
* surface events; a separate replacement `user/message` carries the summary.
* Backend packages own configuration and retention policy; see
* `docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md`.
* `.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md`.
* @module @deepseek-ai/dsh-compact/types
*/
@@ -30,7 +30,7 @@ declare module '@deepseek-ai/dsh-session' {
* The model that wrote the summary — the summarize call's envelope,
* reported by the backend that made the call, logged so the one-shot
* request is reconstructable from log + code and "which model wrote
* this summary" has a durable answer (the reconstructability RFC).
* this summary" has a durable answer (the reconstructability Agent Note).
*/
model: string
/** The generation cap the summarize call sent, when one applied. */

2
packages/context/README.md
View File

@@ -7,4 +7,4 @@ Product plugins that add model-visible request context without defining a tool o
| `time-context/` | Durable per-step current time and elapsed-time context | (none) |
| `workspace-context/` | `AGENTS.md`/`CLAUDE.md` workspace context loader | (listens on `agent/session-prefix` + `tools/post-execute`) |
The [`workspace-context` decision record](../../docs/rfc/implemented/feature/2026-06-24-workspace-context.md) explains its per-agent/session isolation and lifecycle split.
The [`workspace-context` decision record](../../.agents/notes/implemented/feature/2026-06-24-workspace-context.md) explains its per-agent/session isolation and lifecycle split.

2
packages/context/time-context/README.md
View File

@@ -1,6 +1,6 @@
# @deepseek-ai/dsh-time-context
Opt-in durable context with the current zoned time and elapsed time sampled during model-request preparation. `dsh-agent-spine-demo` and shipped examples do not mount it. Decision record: [the durable time-context RFC](../../../docs/rfc/implemented/feature/2026-07-16-durable-per-step-time-context.md).
Opt-in durable context with the current zoned time and elapsed time sampled during model-request preparation. `dsh-agent-spine-demo` and shipped examples do not mount it. Decision record: [the durable time-context Agent Note](../../../.agents/notes/implemented/feature/2026-07-16-durable-per-step-time-context.md).
## Config

2
packages/context/workspace-context/README.md
View File

@@ -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

1
packages/context/workspace-context/src/index.ts
View File

@@ -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)

6
packages/context/workspace-context/src/render.ts
View File

@@ -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')
}

5
packages/context/workspace-context/src/state.ts
View File

@@ -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 }
}
/**

10
packages/context/workspace-context/tests/workspace-context.spec.ts
View File

@@ -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)

2
packages/cordis/README.md
View File

@@ -1,6 +1,6 @@
# packages/cordis — the self-referential runtime toolset
Model-facing tools over the live cordis runtime the agent itself runs inside: inspect the loaded plugins and service surface, mount model-written plugins, and dispose them again. Design home: [the toolset RFC](../../docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md).
Model-facing tools over the live cordis runtime the agent itself runs inside: inspect the loaded plugins and service surface, mount model-written plugins, and dispose them again. Design home: [the toolset Agent Note](../../.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md).
| Package | Role | ctx key |
|---|---|---|

4
packages/cordis/tool-cordis/README.md
View File

@@ -1,6 +1,6 @@
# @deepseek-ai/dsh-tool-cordis
The self-referential cordis toolset: three model-facing tools over the live runtime the agent runs inside. Design home — sandbox semantics, mount lifecycle, cross-mount composition, the generated API catalog, standing decisions: [the toolset RFC](../../../docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md).
The self-referential cordis toolset: three model-facing tools over the live runtime the agent runs inside. Design home — sandbox semantics, mount lifecycle, cross-mount composition, the generated API catalog, standing decisions: [the toolset Agent Note](../../../.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md).
## What it does
@@ -12,7 +12,7 @@ Exact model-facing schemas: [the generated tool catalog](../../../docs/tool-cata
## Trust stance
The sandbox isolates globals but is not a security boundary. Node globals are absent or redirect to Cordis services such as `ctx.fs`, `ctx.web`, and `ctx.bash`, and writes to `globalThis` stay local, but host-realm helpers make escape possible. Mounted plugins receive a façade without framework internals, yet its allowed services affect the live runtime. Treat this toolset like bash access; see the [design and trust stance](../../../docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md).
The sandbox isolates globals but is not a security boundary. Node globals are absent or redirect to Cordis services such as `ctx.fs`, `ctx.web`, and `ctx.bash`, and writes to `globalThis` stay local, but host-realm helpers make escape possible. Mounted plugins receive a façade without framework internals, yet its allowed services affect the live runtime. Treat this toolset like bash access; see the [design and trust stance](../../../.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md).
## Config

55
packages/cordis/tool-cordis/src/api-catalog.ts
View File

@@ -241,12 +241,12 @@ 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 */',
},
],
},
@@ -304,6 +304,11 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [
},
],
},
{
key: 'sandboxPolicy',
summary: 'The sandbox-policy service (`ctx.sandboxPolicy`).',
methods: [],
},
{
key: 'sessionPersistence',
summary: 'Durable append-only session storage.',
@@ -522,6 +527,24 @@ 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.',
@@ -652,8 +675,8 @@ 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',
@@ -750,7 +773,7 @@ export const EVENT_API: readonly EventApiEntry[] = [
name: 'llm/stream',
mode: 'waterfall',
signature: '\'llm/stream\'(this: LlmService, options: GenerateOptions, next: () => AsyncIterable<StreamChunk>): AsyncIterable<StreamChunk>',
jsDoc: '/**\n * Waterfall around every streaming model call (retry, replay, routing).\n * Bound to the {@link LlmService}; call `next()` to reach the resolved\n * adapter\'s stream, or yield your own chunks to short-circuit.\n * @param options - the full request. A LOOP-built request arrives\n * deep-frozen (mutation throws): its content is a pure function of the\n * session log (the reconstructability RFC), so listeners read it, never\n * rewrite it. A hand-built one-shot (compaction summarize) is the\n * caller\'s own object and stays mutable here.\n * @mode waterfall\n */',
jsDoc: '/**\n * Waterfall around every streaming model call (retry, replay, routing).\n * Bound to the {@link LlmService}; call `next()` to reach the resolved\n * adapter\'s stream, or yield your own chunks to short-circuit.\n * @param options - the full request. A LOOP-built request arrives\n * deep-frozen (mutation throws): its content is a pure function of the\n * session log (the reconstructability Agent Note), so listeners read it, never\n * rewrite it. A hand-built one-shot (compaction summarize) is the\n * caller\'s own object and stays mutable here.\n * @mode waterfall\n */',
summary: 'Waterfall around every streaming model call (retry, replay, routing).',
},
{
@@ -1068,10 +1091,6 @@ 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}',
@@ -1170,11 +1189,11 @@ 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',
@@ -1220,6 +1239,14 @@ 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}',
@@ -1258,7 +1285,7 @@ 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',

2
packages/cordis/tool-cordis/src/index.ts
View File

@@ -26,7 +26,7 @@ export interface Config {
/**
* Milliseconds the SYNCHRONOUS portion of mount code may run in the vm
* before evaluation is aborted (default 5000). An async body escapes this
* bound — see docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md for the trust stance.
* bound — see .agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md for the trust stance.
*/
vmTimeoutMs?: number
}

8
packages/core/agent-loop/README.md
View File

@@ -19,7 +19,7 @@ Each agent and its session share one caller-chosen `SessionId`, assumed globally
`AgentLoop` also implements the `AgentFactory` seam and registers itself via `ctx.agents.setFactory(this)`, so plugins create/resume agents through `ctx.agents` (the interface):
- `ctx.agents.create({ sessionId, meta?, seed?, agentOptions?, setup?, signal? }): Promise<AgentHandle>` — programmatic create under the caller-supplied shared id. It awaits the unpublished setup transaction before returning; `meta` carries cwd/lineage/seed-boundary metadata and `seed` reconstructs a forked child prefix after the session boundary validates and snapshots the durable values. `signal` applies only until this promise settles. The resolved [`AgentHandle`](../agent/README.md) owns exact teardown.
- `ctx.agents.resume({ resumeSessionId, agentOptions?, setup?, signal? }): Promise<AgentHandle>` — load a persisted session via `ctx.sessionPersistence` ([session persistence](../../../docs/rfc/implemented/architecture/2026-06-14-session-persistence.md)), register the agent under that same id, reconstruct its history, then await setup against a fresh unpublished agent scope before rollback-covered publication. Turn numbering and derived history continue from the loaded log. Requires a session-persistence backend (NOT hard-injected — non-persistent demos still work; `resume` rejects with a clear error when persistence is absent). `signal` is creation-only. Returns an `AgentHandle`.
- `ctx.agents.resume({ resumeSessionId, agentOptions?, setup?, signal? }): Promise<AgentHandle>` — load a persisted session via `ctx.sessionPersistence` ([session persistence](../../../.agents/notes/implemented/architecture/2026-06-14-session-persistence.md)), register the agent under that same id, reconstruct its history, then await setup against a fresh unpublished agent scope before rollback-covered publication. Turn numbering and derived history continue from the loaded log. Requires a session-persistence backend (NOT hard-injected — non-persistent demos still work; `resume` rejects with a clear error when persistence is absent). `signal` is creation-only. Returns an `AgentHandle`.
The config-driven `ctx.agentLoop.create()` path keeps its agent owned by the loop fiber (it discards the handle). For a programmatic agent, the handle holder is the only consumer-facing teardown capability; AgentLoop provider unload is the independent structural teardown edge, not another handle exposed to application code.
@@ -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`)
@@ -114,7 +116,7 @@ Append-only; each synthetic result follows the reusable request prefix and does
## Known Limitations and Deferred Work
- **Classification is unary** — calls whose safety depends on comparing siblings or resources must remain exclusive ([rationale](../../../docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md)).
- **Classification is unary** — calls whose safety depends on comparing siblings or resources must remain exclusive ([rationale](../../../.agents/notes/implemented/feature/2026-07-10-parallel-tool-call-execution.md)).
- **Config labels are fresh by default** — omitting `sessionId` creates a fresh `${id}-session-<uuid>` on every startup; exact resume-or-create behavior requires an explicit stable `sessionId`, while `resumeSessionId` requires existing persisted history.
- **Config agents have no per-agent persona field or setup hook** — they use the deployment persona; scoped persona/tool composition is available only through the programmatic `ctx.agents.create()` / `resume()` factory options.
- **No built-in turn budget** — the default continuation is `continue` whenever a step had tool calls or steering; bounding a runaway turn requires an `agent/turn-continuation` force-stop plugin.

3
packages/core/agent-loop/src/agent.ts
View File

@@ -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)) {
@@ -398,7 +397,7 @@ 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() },
}))
}

12
packages/core/agent-loop/src/inbox.ts
View File

@@ -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

94
packages/core/agent-loop/src/loop.ts
View File

@@ -1,7 +1,7 @@
/**
* Drives one agent across queued durable turns. Turn failures are contained so
* later work can run; the session log, not this driver, owns conversation state.
* See docs/rfc/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md.
* See .agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md.
* @module dsh-agent-loop/loop
*/
@@ -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

193
packages/core/agent-loop/tests/cancel.spec.ts
View File

@@ -79,7 +79,8 @@ 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.
@@ -91,6 +92,35 @@ 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)
@@ -110,7 +140,162 @@ 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' })
@@ -121,10 +306,14 @@ 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 () => {

40
packages/core/agent-loop/tests/contract-regressions.spec.ts
View File

@@ -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 () => {

18
packages/core/agent-loop/tests/coverage-edges.spec.ts
View File

@@ -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 () => {
@@ -235,7 +245,7 @@ describe('disposed vs aborted branching', () => {
})
})
describe('structured tool error propagation (the runtime-validation RFC, part 2)', () => {
describe('structured tool error propagation (the runtime-validation Agent Note, part 2)', () => {
it('forwards a tool HarnessError onto the tool/result session event', async () => {
const { HarnessError } = await import('@deepseek-ai/dsh-llm')
// First model turn calls the tool; second turn (after the tool result is

10
packages/core/agent-loop/tests/inbox.spec.ts
View File

@@ -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', () => {

55
packages/core/agent-loop/tests/interception.spec.ts
View File

@@ -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' }]
},
}))

204
packages/core/agent-loop/tests/loop.spec.ts
View File

@@ -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 () => {

43
packages/core/agent-loop/tests/properties.spec.ts
View File

@@ -1,6 +1,6 @@
/**
* Property-based tests for the agent loop's inbox/turn scheduling (the
* property-testing RFC). Deterministic by construction: schedules are driven
* property-testing Agent Note). Deterministic by construction: schedules are driven
* through the `agent/status` settle signal (no wall-clock sleeps), so a flake
* is a finding, not timing noise.
*
@@ -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()
}

2
packages/core/agent-loop/tests/request-cache.e2e.ts
View File

@@ -14,7 +14,7 @@ import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
* multi-step tool turn (plus a follow-up turn) against the live DeepSeek API must report
* `cacheReadTokens > 0` on every request after the first — the adapter maps the provider's
* `prompt_cache_hit_tokens`, and the per-step usage recorded on `assistant/message` events is
* the production observable for cache behavior (the reconstructability RFC's measurement
* the production observable for cache behavior (the reconstructability Agent Note's measurement
* layer: prefix stability is corollary #1). Mocks establish append-extension;
* this key-gated test establishes a real provider cache hit.
*/

2
packages/core/agent-loop/tests/resume.spec.ts
View File

@@ -75,7 +75,7 @@ function throwUnknown(value: unknown): never {
throw value
}
describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
describe('the session-persistence Agent Note: AgentLoop factory create/resume', () => {
it('normalizes a non-Error resume publication failure for rollback and rethrows it', async () => {
const sessionId = SessionId('unknown-resume-failure-s')
const root = await persistSession(sessionId)

18
packages/core/agent/README.md
View File

@@ -26,7 +26,7 @@ The scoped-registration surface: `Agent.ctx` is the agent's scope context (`dsh-
- `ctx.agents.withInitiator(agent, operation)` — run with one exact Agent and preserve the operation's exact synchronous value or Promise.
- `ctx.agents.withoutInitiator(operation)` — hide an inherited initiator for unrelated process-local work.
The scope carries the `Agent` itself and is process-local. Ambient presence is neither liveness proof nor authorization; explicit Agent fields remain authoritative at service, worker, process, persistence, and wire boundaries. Teardown rejects new boundaries, lets injected dependents and returned-Promise boundaries drain, then disables the underlying `AsyncLocalStorage`; unreturned work remains owned by the subsystem that detached it. If a boundary's inherited async chain starts an owning Cordis fiber's unload, that nested boundary chain is released from the drain so the unload cannot wait on itself; its continuations observe the disposed service after teardown. The [initiator-scope decision](../../../docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md) owns the detailed boundary and teardown contract.
The scope carries the `Agent` itself and is process-local. Ambient presence is neither liveness proof nor authorization; explicit Agent fields remain authoritative at service, worker, process, persistence, and wire boundaries. Teardown rejects new boundaries, lets injected dependents and returned-Promise boundaries drain, then disables the underlying `AsyncLocalStorage`; unreturned work remains owned by the subsystem that detached it. If a boundary's inherited async chain starts an owning Cordis fiber's unload, that nested boundary chain is released from the drain so the unload cannot wait on itself; its continuations observe the disposed service after teardown. The [initiator-scope decision](../../../.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.md) owns the detailed boundary and teardown contract.
#### Factory seam (creation)
@@ -34,7 +34,7 @@ Agent *creation* is provided by the plugin implementing `AgentFactory` (`dsh-age
- `ctx.agents.setFactory(factory: AgentFactory): () => void` — register the creation factory (the loop calls this on construction). Throws on a second factory; the slot clears on dispose.
- `ctx.agents.create(options: CreateAgentOptions): Promise<AgentHandle>` — create a session and agent, await optional setup while unpublished, then publish through final `SessionStore.enter()` and `AgentRegistry.enter()` checks. Concurrent same-ID creation is unsupported: more than one operation may prepare, but only one can enter; every loser rolls its private scope/session/driver back. An optional creation-only `signal` cancels unpublished setup and is detached before the handle is returned; later cancellation uses `handle.dispose()` or `agent.cancel()`. Publication is rollback-covered and every delivered creation edge is paired during rollback. Rejects if no factory is registered.
- `ctx.agents.resume(options: ResumeAgentOptions): Promise<AgentHandle>` — load a persisted session ([session persistence](../../../docs/rfc/implemented/architecture/2026-06-14-session-persistence.md)), mint a fresh unpublished agent scope, await optional setup, and use the same final-entry publication sequence. Its optional `signal` is likewise creation-only. Rejects if no factory is registered or session persistence is unconfigured.
- `ctx.agents.resume(options: ResumeAgentOptions): Promise<AgentHandle>` — load a persisted session ([session persistence](../../../.agents/notes/implemented/architecture/2026-06-14-session-persistence.md)), mint a fresh unpublished agent scope, await optional setup, and use the same final-entry publication sequence. Its optional `signal` is likewise creation-only. Rejects if no factory is registered or session persistence is unconfigured.
`AgentHandle = { agent: Agent; dispose(): Promise<void> }`. The disposer is a **consumer capability** — no observer holding the bare registry entry can tear the agent down. The caller fiber and the registered factory provider are structural co-owners: caller unload enforces structured ownership, while factory unload must stop old instances because their scoped dependency surface belongs to that provider. `dispose()` from any owner reaches one memoized quiescence boundary: it stops the loop, `await`s its exit plus every outstanding idle-injection flush (not just the `disposed` status flip), unregisters the agent, removes its session from the store, and finally unwinds its scoped world. This order captures every agent-started `session/flush` before the session is detached and keeps scoped listeners alive through those checkpoints. `ctx.agents.get(id)` still returns a bare `Agent`; the ACP bridge and in-process subagent backends hold consumer handles, while config-created agents are already owned by the loop fiber.
@@ -44,9 +44,9 @@ Agent *creation* is provided by the plugin implementing `AgentFactory` (`dsh-age
The lifecycle edges have two important local caveats. `agent/created` runs after scoped setup and after both session and agent registry entries exist. Setup is trusted composition-only code; the immediately following non-vetoing `agent/session-start` notification is the first supported startup injection point. `agent/disposed` always means the exact agent has left the registry. AgentLoop emits it after its driver is quiescent, while ordered teardown may still be detaching the session and unwinding the scope; custom agents registered directly own any stronger driver-ordering contract themselves.
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. The full rationale for scoped dispatch and terminal settlement is in the [agent-scope runtime-design RFC](../../../docs/rfc/implemented/architecture/2026-07-12-agent-scope-runtime-design.md#three-execution-boundaries-are-deliberately-one-way).
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. 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. 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](../../../docs/rfc/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. 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: clears the queued + steering FIFOs, aborts the in-flight step, and drops a turn about to start (the pre-step window) so a queued-but-not-started prompt never runs. A UI/ACP `session/cancel` maps to this. The single public stop primitive. Idle with nothing pending → a safe no-op.
- `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()`.
@@ -103,6 +105,6 @@ Prefix-stable while an agent's scoped registrations are unchanged. Setup or relo
- **Ambient identity may outlive liveness** — consumers still check `agent.status`, cancellation, and the owning capability contract before lifecycle-sensitive work.
- **Inter-agent channels beyond delegation** — shared state, streaming child output, and background/poll semantics remain outside the current synchronous `ctx.subagents` seam.
- **`agent/session-start` cannot gate startup** — it remains a synchronous, veto-less notification; async composition that must finish before publication belongs in the factory's `setup(agentCtx)` transaction instead.
- **No public step-only abort** — `cancel()` clears ALL pending work (queued + steering + in-flight); an abort that preserves queued prompts returns only with a named consumer ([stop-surface RFC](../../../docs/rfc/implemented/simplification/2026-06-20-public-agent-stop-surface.md)).
- **No public step-only abort** — `cancel()` clears ALL pending work (queued + steering + in-flight); an abort that preserves queued prompts returns only with a named consumer ([stop-surface Agent Note](../../../.agents/notes/implemented/simplification/2026-06-20-public-agent-stop-surface.md)).
- **`HookContext` carries exactly one `MessageSource`** — contributions from several plugins merged onto one tool call collapse under one source; mixed provenance is unrepresentable.
- **`SessionStartSource` reserves `'clear'`/`'compact'` with no emitter yet** — only `'startup'`/`'resume'` occur until the driving subsystems land (`TODO(compaction)`).

45
packages/core/agent/src/types.ts
View File

@@ -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 {
@@ -32,17 +32,15 @@ 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'
@@ -50,16 +48,15 @@ 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[] }
@@ -97,15 +94,20 @@ 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
@@ -119,10 +121,11 @@ export interface Agent {
inject(content: ContentBlock[], options?: InjectOptions): void
/**
* Clear queued and steering work, including work waiting to start, and abort
* the active step. 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. 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.
*/
cancel(reason?: string): void
@@ -203,10 +206,10 @@ 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

2
packages/core/scope/README.md
View File

@@ -15,7 +15,7 @@ Scoped registration primitive. `createScope(ctx, key)` creates a tagged Cordis c
## Design contract
The registration context determines both visibility and ownership, preventing a registration from being visible in one scope but disposed with another. Scopes route trusted same-process plugins; they are not sandboxes or authority boundaries. See the [agent-scope RFC](../../../docs/rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md#security-and-authority-are-explicit-non-goals) for rationale and security non-goals.
The registration context determines both visibility and ownership, preventing a registration from being visible in one scope but disposed with another. Scopes route trusted same-process plugins; they are not sandboxes or authority boundaries. See the [agent-scope Agent Note](../../../.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md#security-and-authority-are-explicit-non-goals) for rationale and security non-goals.
Handing out a scoped context hands out the minting plugin's service-resolution surface (resolution walks the minting fiber's dependency chain, not the holder's) — mint it from the plugin whose dependencies the scoped registrations need to resolve.

16
packages/core/session/README.md
View File

@@ -22,7 +22,7 @@ Use the split lifecycle only when teardown must be ordered with another resource
- `enter(session)` performs the collision check, publishes without announcing, and returns an entry-bound idempotent detach. Concurrent same-id preparations are allowed, but only one entry succeeds; a stale detach cannot remove its replacement.
- `announce(session)` emits the single creation edge and rejects repeat or reentrant announcements. Detach during that dispatch is deferred and later emits the paired disposal edge; an unannounced entry emits neither lifecycle edge.
`dsh-agent-loop` uses this split so final loop flush precedes session detach; see the [ownership RFC](../../../docs/rfc/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md).
`dsh-agent-loop` uses this split so final loop flush precedes session detach; see the [ownership Agent Note](../../../.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md).
### Live service events
@@ -32,7 +32,7 @@ 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.
@@ -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 RFC](../../../docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md).
`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`)
@@ -79,7 +79,7 @@ Every `SessionEvent` carries two optional top-level fields (structural metadata)
- 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
@@ -128,6 +128,6 @@ Logging causes no invalidation, and exact reconstruction preserves request-prefi
## Known Limitations and Deferred Work
- **Session branching/tree** (pi-style entry tree) — deferred unless needed beyond boundary-based `fork()`.
- **`fork()` cuts only at closed-turn boundaries of live sessions** — the boundary must be a `turn/end` event and the source must be in the store; forking a persisted-but-unloaded session is excluded from the [fork API](../../../docs/rfc/implemented/feature/2026-06-30-session-store-fork-api.md).
- **`fork()` cuts only at closed-turn boundaries of live sessions** — the boundary must be a `turn/end` event and the source must be in the store; forking a persisted-but-unloaded session is excluded from the [fork API](../../../.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.md).
- **`SESSION_FORMAT_VERSION` stays pinned at `0`** — pre-release, no compatibility implied: a backend rejects any other version, and no migration path exists until the first release ([policy](../../../AGENTS.md)).
- **`TurnEndReasonMap` omits the ACP-named `refusal` / `max_turn_requests` variants** — producer-gated: they land when an adapter or the loop first emits them.

58
packages/core/session/src/index.ts
View File

@@ -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
@@ -228,22 +213,6 @@ 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.
*
@@ -496,7 +465,7 @@ export class Session {
* The per-node pure function {@link deriveMessages} folds over the surface;
* an external reconstructor (or the dev invariant) folds the same function
* over a log prefix's surface to rebuild the exact messages any request was
* built from (the reconstructability RFC). The returned message wrapper is
* built from (the reconstructability Agent Note). The returned message wrapper is
* fresh; its content reuses the logged event's already deep-frozen durable
* data, so changing the wrapper cannot rewrite the log and changing content
* throws.
@@ -509,7 +478,18 @@ 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 +506,6 @@ 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.

39
packages/core/session/src/surface.ts
View File

@@ -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
}
}

31
packages/core/session/src/types.ts
View File

@@ -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'>
@@ -109,8 +106,8 @@ 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 +176,44 @@ 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. */

2
packages/core/session/tests/properties.spec.ts
View File

@@ -1,5 +1,5 @@
/**
* Property-based tests for the Session event log (the property-testing RFC).
* Property-based tests for the Session event log (the property-testing Agent Note).
*
* Generates arbitrary event logs and asserts the derivation invariants the
* agent loop and replay depend on: deriveMessages is deterministic and

11
packages/core/session/tests/session.spec.ts
View File

@@ -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' })

4
packages/core/session/tests/surface.spec.ts
View File

@@ -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' }])
})
})

4
packages/core/system-prompt/README.md
View File

@@ -7,7 +7,7 @@ System prompt assembly registry. Plugins contribute ordered sections, tool schem
| Key | Default | Meaning |
|---|---|---|
| `persona` | `''` | The global deployment-persona default: the ONE config-authored prompt fragment, rendered as the order-0 `deployment:persona` section unless an agent-scoped contribution shadows it. A template — complete `{{…}}` groups are interpreted strictly against the registered variables (the shipped loop registers `{{model}}`/`{{cwd}}`), with no escape syntax for literal braces yet. Empty ⇒ the section is dropped at render. |
| `toolOrder` | — | Explicit model-facing tool order, as a list of `ToolSchema.name`s with one `'<unlisted-tools>'` rest entry (`TOOL_ORDER_REST`): listed tools take their listed position, unlisted tools land at the rest entry in lexicographic name order. Absent ⇒ plain lexicographic name order. Applied to the collected tools BEFORE the `system-prompt/assemble` waterfall — like the sections' `order` sort, it canonicalizes what the registry contributed (registration order is a plugin-load artifact), and a waterfall listener that mutates the list owns the determinism of what it emits. Misconfiguration fails loud: a list without exactly one rest entry, or with duplicates, throws at load; a listed name with no registered tool rejects every `assemble()`; a tool provider returning the reserved rest-entry name also rejects. Under the shipped loop the turn fails before any model request. Why a central list and not per-plugin weights: [Explicit model-facing tool order](../../../docs/rfc/implemented/feature/2026-07-06-explicit-tool-order.md). |
| `toolOrder` | — | Explicit model-facing tool order, as a list of `ToolSchema.name`s with one `'<unlisted-tools>'` rest entry (`TOOL_ORDER_REST`): listed tools take their listed position, unlisted tools land at the rest entry in lexicographic name order. Absent ⇒ plain lexicographic name order. Applied to the collected tools BEFORE the `system-prompt/assemble` waterfall — like the sections' `order` sort, it canonicalizes what the registry contributed (registration order is a plugin-load artifact), and a waterfall listener that mutates the list owns the determinism of what it emits. Misconfiguration fails loud: a list without exactly one rest entry, or with duplicates, throws at load; a listed name with no registered tool rejects every `assemble()`; a tool provider returning the reserved rest-entry name also rejects. Under the shipped loop the turn fails before any model request. Why a central list and not per-plugin weights: [Explicit model-facing tool order](../../../.agents/notes/implemented/feature/2026-07-06-explicit-tool-order.md). |
## Service: `SystemPrompt` (ctx key: `systemPrompt`)
@@ -38,7 +38,7 @@ Merge-extensible: plugins can declare extra fields on `PromptAssembly` and `Asse
- Tool schema providers: `ToolRegistry` registers itself as a tool provider automatically.
- The [`system-prompt/assemble` waterfall](#live-events): cooperatively mutate or replace the assembly per caller.
Design rationale: [the prompt-variables RFC](../../../docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md).
Design rationale: [the prompt-variables Agent Note](../../../.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md).
## Model Experience

20
packages/core/tools/README.md
View File

@@ -16,9 +16,9 @@ tools:
### Public API
- `ctx.tools.register(definition: ToolDefinition): () => void` Register a trusted typed same-process definition. The layer is the calling context's scope: a plain plugin context registers globally; an agent's `agent.ctx` registers for that agent alone, shadowing a same-named global tool there. Duplicate names within one layer throw; non-native modes also reject the reserved `run_code` transport name. `timeoutMs`, when present, must be positive and finite. Disposed with the calling fiber.
- `ctx.tools.restrict(filter)` applies an agent-scoped allow/deny mask to global tools and throws from a plain context. The filter is snapshotted at registration; multiple masks intersect and scope-local tools merge afterwards. Deny masks admit later unnamed globals, while allow masks exclude later names. Unknown, local, or reserved names and empty filters reject. This is live visibility composition, not an authority boundary; see the [scope security non-goal](../../../docs/rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md#security-and-authority-are-explicit-non-goals).
- `ctx.tools.restrict(filter)` applies an agent-scoped allow/deny mask to global tools and throws from a plain context. The filter is snapshotted at registration; multiple masks intersect and scope-local tools merge afterwards. Deny masks admit later unnamed globals, while allow masks exclude later names. Unknown, local, or reserved names and empty filters reject. This is live visibility composition, not an authority boundary; see the [scope security non-goal](../../../.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md#security-and-authority-are-explicit-non-goals).
- `ctx.tools.get(name: string, scope?: ScopeKey): ToolDefinition | undefined` Resolution as one scope sees it (shadowing applied; a restricted-away global reads as absent) — presenters pass the calling agent so the card matches what executed.
- `ctx.tools.schemas(scope?: ScopeKey): ToolSchema[]` Schemas of everything the scope can see (without the `execute` functions). The shipped tools' schemas are catalogued in [docs/tool-catalog.md](../../../docs/tool-catalog.md), generated by booting each tool plugin and harvesting this method (see [the tool-schema-catalog RFC](../../../docs/rfc/implemented/process/2026-07-02-tool-schema-catalog.md)).
- `ctx.tools.schemas(scope?: ScopeKey): ToolSchema[]` Schemas of everything the scope can see (without the `execute` functions). The shipped tools' schemas are catalogued in [docs/tool-catalog.md](../../../docs/tool-catalog.md), generated by booting each tool plugin and harvesting this method (see [the tool-schema-catalog Agent Note](../../../.agents/notes/implemented/process/2026-07-02-tool-schema-catalog.md)).
- `ctx.tools.guard(guard: ToolGuard): () => void` Register a monotonic synchronous execution guard after `tools/pre-execute`: returning a reason denies the call, while `undefined` leaves it unchanged. A plain-context guard applies globally; an `agent.ctx` guard applies only to that agent. Later waterfall listeners cannot turn a guard denial back into permission. Disposed with the calling fiber.
- `ctx.tools.execute(exec)` losslessly snapshots and freezes arguments, assigns an opaque token, runs the complete policy/dispatch/result pipeline, then independently snapshots the authoritative outcome before final observation. Invalid arguments use the same result path without reaching policy or the body; around wrappers may replace only `signal`.
- `ctx.tools.executionMode(exec)` returns `parallel` only when the visible definition's `isConcurrencySafe(exec.arguments)` classifier returns exactly `true`; unknown, hidden, undeclared, invalid, or throwing classifications are exclusive.
@@ -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.
@@ -88,7 +88,7 @@ See `defineTool`, `validateArgs`, `ToolArgsError`, `SchemaSpec`, `InferArgs`, an
Optional `timeoutMs` must be positive and finite; it is policy metadata, not model-visible schema.
Optional `isConcurrencySafe(args)` receives typed, softly validated arguments. Exact `true` permits concurrent dispatch/body execution; invalid input and all other outcomes remain exclusive. Opted-in bodies do not mutate parent-owned state, and shared-state races must commute or fail closed. The [parallel tool-call RFC](../../../docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md) owns the full safety contract.
Optional `isConcurrencySafe(args)` receives typed, softly validated arguments. Exact `true` permits concurrent dispatch/body execution; invalid input and all other outcomes remain exclusive. Opted-in bodies do not mutate parent-owned state, and shared-state races must commute or fail closed. The [parallel tool-call Agent Note](../../../.agents/notes/implemented/feature/2026-07-10-parallel-tool-call-execution.md) owns the full safety contract.
### Structured-output schema subset
@@ -101,19 +101,19 @@ Tools optionally own pure `presentCall()` and `presentResult()` render intents,
- Call views are `{ card: 'generic', title, kind?, rawInput?, content?, locations? }`, `{ card: 'terminal', title, description?, cwd? }`, or `{ card: 'diff', title, diffs, locations? }`.
- Result views are `{ card: 'generic', title?, content? }`, `{ card: 'terminal', title?, output?, exitCode?, signal? }`, or `{ card: 'diff', title?, diffs }`.
Returning `undefined` selects generic fallback. Presenters depend only on their arguments because UIs call them during live streaming and log replay. Result presentation may read JSON-serializable `result.meta`, which persists with the result; `defineTool` soft-validates older logged arguments and falls back instead of crashing replay. `dsh-tool-bash` and `dsh-tool-fs` are the reference implementations; the [render-intent RFC](../../../docs/rfc/implemented/architecture/2026-07-02-tool-render-intent-union.md) owns the rationale.
Returning `undefined` selects generic fallback. Presenters depend only on their arguments because UIs call them during live streaming and log replay. Result presentation may read JSON-serializable `result.meta`, which persists with the result; `defineTool` soft-validates older logged arguments and falls back instead of crashing replay. `dsh-tool-bash` and `dsh-tool-fs` are the reference implementations; the [render-intent Agent Note](../../../.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md) owns the rationale.
### Code Mode
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 RFC](../../../docs/rfc/implemented/feature/2026-06-15-code-mode.md) and [code-runtime seam](../../code-runtime/README.md). Try `pnpm run demo:code-mode`.
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
The agent loop groups consecutive `parallel` calls into a bounded rolling pool and treats each `exclusive` call as an ordering barrier. Only dispatch/body overlaps; policy, durable results, and context retain model order. Code Mode bindings remain serial. The [parallel tool-call RFC](../../../docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md) owns the shipped declarations and rationale.
The agent loop groups consecutive `parallel` calls into a bounded rolling pool and treats each `exclusive` call as an ordering barrier. Only dispatch/body overlaps; policy, durable results, and context retain model order. Code Mode bindings remain serial. The [parallel tool-call Agent Note](../../../.agents/notes/implemented/feature/2026-07-10-parallel-tool-call-execution.md) owns the shipped declarations and rationale.
## Model Experience
@@ -177,9 +177,9 @@ Append-only; newly visible content follows the reusable request prefix and does
## Known Limitations and Deferred Work
- **Concurrency policy is not an event seam** — `executionMode()` reads the resolved tool definition directly; plugins can only declare a classifier on definitions they own.
- **`tools/pre-execute` deliberately cannot rewrite `exec.arguments`** — logged and rendered args would desync from what ran; the rewrite design is [a proposed RFC](../../../docs/rfc/proposed/feature/2026-06-30-pre-tool-input-rewrite.md).
- **`tools/pre-execute` deliberately cannot rewrite `exec.arguments`** — logged and rendered args would desync from what ran; the rewrite design is [a proposed Agent Note](../../../.agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.md).
- **`defineTool`'s schema DSL is a deliberate subset** — string/number/boolean/object/array with string-only `enum`; `validateArgs` tolerates extra keys and preserves `default` as a model-visible JSON Schema annotation without applying it during validation; dynamic Cordis mounts may supply defaults even though first-party definitions do not, while raw-registered JSON-Schema tools validate their own input.
- **`timeoutMs` on a definition is declarative only** — the registry never enforces deadlines; enforcement requires the `@deepseek-ai/dsh-timeout-policy` wrapper.
- **Code Mode is TypeScript-only and the presentation mode is service-wide** — `mode: code`/`both` rejects prompt assembly unless `ctx.codeRuntime.language === 'typescript'`; scoped restrictions/shadows still choose each agent's visible bindings, but one tool cannot be native-only while another is code-only.
- **Code Mode bindings return text only** — non-text content blocks in a sub-call result collapse to `[<type> content]` placeholders.
- **`run_code` state is fresh per run** — a persistent REPL-style kernel is rejected for the MVP (cross-call state would be invisible to the log); see [the Code Mode RFC](../../../docs/rfc/implemented/feature/2026-06-15-code-mode.md).
- **`run_code` state is fresh per run** — a persistent REPL-style kernel is rejected for the MVP (cross-call state would be invisible to the log); see [the Code Mode Agent Note](../../../.agents/notes/implemented/feature/2026-06-15-code-mode.md).

15
packages/core/tools/src/index.ts
View File

@@ -139,7 +139,7 @@ export interface ToolDefinition extends ToolSchema {
* Opted-in executions must not mutate parent-owned state. Shared state must
* tolerate concurrent dispatch; recorder races are permitted only when they
* commute or fail closed. See the
* [parallel-tool-call RFC](../../../../docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md)
* [parallel-tool-call Agent Note](../../../../.agents/notes/implemented/feature/2026-07-10-parallel-tool-call-execution.md)
* for the full contract.
* @param args - parsed arguments; `defineTool` validates before calling.
* @returns Whether this call may join a parallel group.
@@ -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)
}
}
}

2
packages/core/tools/src/ts-types.ts
View File

@@ -75,7 +75,7 @@ export function jsonSchemaToTs(schema: unknown, indent = 0): string {
}
}
/** The fixed model-facing usage contract rendered above the declarations (see the Code Mode RFC's "What the model sees"). */
/** The fixed model-facing usage contract rendered above the declarations (see the Code Mode Agent Note's "What the model sees"). */
const SDK_INSTRUCTIONS = `## Writing code for run_code
Pass \`run_code\` the body of an async TypeScript function (erasable syntax only — no \`enum\` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:

5
packages/core/tools/tests/code-mode.spec.ts
View File

@@ -13,7 +13,7 @@ import { Session, SessionId } from '@deepseek-ai/dsh-session'
import type { SessionEventMap } from '@deepseek-ai/dsh-session'
/**
* Code Mode unit tier (per the RFC's plan): provider contribution per mode,
* Code Mode unit tier (per the Agent Note's plan): provider contribution per mode,
* misconfiguration rejections, the run_code dispatch bridge (serialization,
* abort, JSON normalization, error mapping, events, quiescence), and HMR
* safety — all against an in-repo fake runtime, exactly the
@@ -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' },
},
])

13
packages/core/tools/tests/gen-tool-catalog.spec.ts
View File

@@ -49,6 +49,19 @@ describe('gen-tool-catalog collectToolCatalog', () => {
expect(bash?.source).toBe('packages/bash/tool-bash/src/index.ts')
})
it('harvests search tools without depending on the generator process PATH', async () => {
const oldPath = process.env.PATH
try {
process.env.PATH = ''
const catalog = await collectToolCatalog()
const search = catalog.find(entry => entry.pkg === '@deepseek-ai/dsh-tool-fs-search')
expect(search?.schemas.map(s => s.name).sort()).toEqual(['glob', 'grep'])
} finally {
if (oldPath === undefined) delete process.env.PATH
else process.env.PATH = oldPath
}
})
it('records the shipped `subagent_fork` alias in a note (config-driven tool name)', async () => {
// `tool-subagent`'s registered name is the load-time `toolName` config, so the shipped
// agents surface this one package as both `subagent` and `subagent_fork`.

4
packages/core/tools/tests/properties.spec.ts
View File

@@ -1,8 +1,8 @@
/**
* Property-based tests for the tool-schema DSL (the property-testing RFC), including
* Property-based tests for the tool-schema DSL (the property-testing Agent Note), including
* the the property-testing ↔ runtime-validation composition composition: generated args that satisfy a SchemaSpec must
* pass validateArgs, and targeted corruptions must be rejected. This closes the
* validator/InferArgs drift risk noted in the arg-validation RFC.
* validator/InferArgs drift risk noted in the arg-validation Agent Note.
*/
import { describe, expect, it } from 'vitest'

9
packages/core/tools/tests/scoped.spec.ts
View File

@@ -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'),
]))
})
})

7
packages/core/tools/tests/tools.spec.ts
View File

@@ -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 () => {
@@ -1174,7 +1173,7 @@ describe('ToolRegistry.get', () => {
})
})
describe('validateArgs (the runtime-validation RFC, part 1)', () => {
describe('validateArgs (the runtime-validation Agent Note, part 1)', () => {
it('returns [] for valid args and is total over malformed input', () => {
const spec = {
path: { type: 'string', required: true },
@@ -1274,7 +1273,7 @@ describe('validateArgs (the runtime-validation RFC, part 1)', () => {
})
})
describe('defineTool validation (the runtime-validation RFC, part 1)', () => {
describe('defineTool validation (the runtime-validation Agent Note, part 1)', () => {
it('returns an isError result with the violations when the model sends bad args', async () => {
const ctx = await setup()
ctx.tools.register(defineTool({

5
packages/examples/acp-demo/README.md
View File

@@ -1,6 +1,6 @@
# @deepseek-ai/dsh-acp-demo
The **ACP server app**: a Cordis app plugin that composes the default agent spine ([`@deepseek-ai/dsh-agent-spine-demo`](../../examples/agent-spine-demo/README.md)) with the front-door cluster an [Agent Client Protocol](../../ui/acp/README.md) server needs, and a `bin` that boots a leaf `cordis.yml` speaking ACP JSON-RPC on stdio.
The **ACP server app**: a Cordis app plugin that composes the default agent spine ([`@deepseek-ai/dsh-agent-spine-demo`](../agent-spine-demo/README.md)) with the front-door cluster an [Agent Client Protocol](../../ui/acp/README.md) server needs, and a `bin` that boots a leaf `cordis.yml` speaking ACP JSON-RPC on stdio.
It is the structured counterpart to [`@deepseek-ai/dsh-stdio-demo`](../stdio-demo/README.md): both consume the same spine, but this one bakes in the OPPOSITE front-door cluster.
@@ -32,12 +32,13 @@ 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` |
| `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

4
packages/examples/acp-demo/src/index.ts
View File

@@ -53,7 +53,7 @@ export interface Config {
skills?: agentCore.SkillConfig
/** Model-facing bash tool config forwarded through agent-core. */
toolBash?: NonNullable<agentCore.Config['toolBash']>
/** Generic background-task control-tool config forwarded through agent-core. */
/** Generic background-task controls forwarded through agent-core; set false to omit their tool surface. */
toolTasks?: NonNullable<agentCore.Config['toolTasks']>
}
@@ -75,7 +75,7 @@ export const Config: z<Config> = z.object({
workspaceContext: z.union([z.const(false), workspaceContext.Config]).required(),
skills: agentCore.SkillConfigSchema,
toolBash: agentCore.ToolBashConfigSchema,
toolTasks: agentCore.ToolTasksConfigSchema,
toolTasks: z.union([z.const(false), agentCore.ToolTasksConfigSchema]),
})
/* jscpd:ignore-end */

8
packages/examples/agent-spine-demo/README.md
View File

@@ -34,9 +34,9 @@ The spine is everything COMMON to every front door. The swappable and front-door
- **the LLM adapter** — the bundle ships the abstract `llm` service; the leaf registers a concrete adapter on `ctx.llm` (`llm-deepseek`, `llm-pi-ai`, `llm-replay`).
- **the bash executor** — the bundle ships `tool-bash` (the consumer schema); the leaf provides `ctx.bash` (`bash-local` or a sandboxed impl).
- **non-local skill providers** — the bundle ships the skill registry, the local filesystem provider, and the `skill` tool; deployments can add other providers such as embedded or remote catalogs as siblings.
- **presentation + per-app infra** — the terminal (`dsh-tui` / `dsh-stdio`) or ACP front door and `hmr`. These form the coupled front-door cluster that the app packages ([`dsh-stdio-demo`](../../examples/stdio-demo/README.md), [`dsh-acp-demo`](../../examples/acp-demo/README.md)) bake in. `timer` is in the spine because it is common and stdout-silent; front doors own stdout and remain outside.
- **presentation + per-app infra** — the terminal (`dsh-tui` / `dsh-stdio`) or ACP front door and `hmr`. These form the coupled front-door cluster that the app packages ([`dsh-stdio-demo`](../stdio-demo/README.md), [`dsh-acp-demo`](../acp-demo/README.md)) bake in. `timer` is in the spine because it is common and stdout-silent; front doors own stdout and remain outside.
This is the [interface/implementation/consumer seam](../../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md) raised to the composition level: the bundle owns the shared spine, the leaf owns the backends, the app package owns the front door.
This is the [interface/implementation/consumer seam](../../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md) raised to the composition level: the bundle owns the shared spine, the leaf owns the backends, the app package owns the front door.
## Config
@@ -46,7 +46,7 @@ import type { Config } from '@deepseek-ai/dsh-agent-spine-demo'
// workspaceContext requires { maxBytes } or false; the other owner schemas supply defaults.
```
The bundle FORWARDS each field to the child that owns it: `agents` and `maxParallelToolCalls` to `agent-loop` (`agents` defaults to `[]`; the cap defaults there), so each app supplies its own pre-created agents — a stdio app pre-creates `main`, while the ACP app creates agents on demand at `session/new`; `persona` and `toolOrder` to `dsh-system-prompt`; `tools` to the tool registry for its presentation mode; `skills.registry`, `skills.local`, and `skills.tool` to the skill registry, local provider, and model-facing consumer; the required `workspaceContext` choice to `dsh-workspace-context` (`{ maxBytes }` enables loading and `false` disables it); and `toolBash`/`toolTasks` to the two model-facing tool plugins the bundle owns. It resolves `dshHome` once through [`@deepseek-ai/dsh-home`](../../util/home/README.md) and forwards that absolute value to tool-bash's managed environment and local skill discovery. An absent top-level `dshHome` adopts `skills.local.dshHome`; supplying both with different resolved paths fails loudly. `toolBash.enableRunInBackground` controls only the bash producer, while `toolTasks` controls generic `task_output` wait bounds; independently loaded producers keep their own config. Workspace instructions register before the skill catalog so their session-prefix message renders first. App packages use `pickSpineConfig()` to copy only these bundle-owned fields.
The bundle FORWARDS each field to the child that owns it: `agents` and `maxParallelToolCalls` to `agent-loop` (`agents` defaults to `[]`; the cap defaults there), so each app supplies its own pre-created agents — a stdio app pre-creates `main`, while the ACP app creates agents on demand at `session/new`; `persona` and `toolOrder` to `dsh-system-prompt`; `tools` to the tool registry for its presentation mode; `skills.registry`, `skills.local`, and `skills.tool` to the skill registry, local provider, and model-facing consumer; the required `workspaceContext` choice to `dsh-workspace-context` (`{ maxBytes }` enables loading and `false` disables it); and `toolBash`/`toolTasks` to the two model-facing tool plugins the bundle owns. Set `skills.enabled: false` to omit both the local provider and model-facing skill tool, and set `toolTasks: false` to retain the task service for foreground producers without exposing `task_output` / `task_list` / `task_kill`. It resolves `dshHome` once through [`@deepseek-ai/dsh-home`](../../util/home/README.md) and forwards that absolute value to tool-bash's managed environment and enabled local skill discovery. An absent top-level `dshHome` adopts `skills.local.dshHome`; supplying both with different resolved paths fails loudly. `toolBash.enableRunInBackground` controls only the bash producer; independently loaded producers keep their own config. Workspace instructions register before the skill catalog so their session-prefix message renders first. App packages use `pickSpineConfig()` to copy only these bundle-owned fields.
## Why a code bundle, not a shared YAML include
@@ -62,5 +62,5 @@ No direct invalidation; the named consumer owns any request-prefix changes.
## Known Limitations and Deferred Work
- **The spine set is fixed in code** — `apply()` mounts every child unconditionally (including `tool-bash`); no config excludes or replaces one, so swapping the loop or dropping a spine member means composing a different bundle.
- **Most of the spine set is fixed in code** — `apply()` always mounts the core services and `tool-bash`; config can omit the bundled skills and task-control tools, but swapping the loop or dropping another spine member means composing a different bundle.
- **`dsh-invariants` mounts unconditionally** — this bundle has no toggle, so every composition using it pays the dev-mode relational assertions; Session's always-on validation and freezing are separate.

22
packages/examples/agent-spine-demo/src/index.ts
View File

@@ -31,6 +31,8 @@ export const name = 'agent-spine-demo'
/** Skill bundle config forwarded to the registry, local provider, and model-facing consumer. */
export interface SkillConfig {
/** Mount the bundled local skill provider and model-facing skill tool (default true). */
enabled?: boolean
/** Registry-level discovery cache settings. */
registry?: SkillRegistryConfig
/** Local filesystem skill provider settings. */
@@ -73,12 +75,13 @@ export interface Config {
skills?: SkillConfig
/** Model-facing bash tool config, including this producer's background opt-in. */
toolBash?: toolBash.Config
/** Generic background-task control-tool wait bounds. */
toolTasks?: toolTasks.Config
/** Generic background-task controls; set false to keep the task service without model-facing task tools. */
toolTasks?: toolTasks.Config | false
}
/** The skill config schema exported for app packages that forward `skills`. */
export const SkillConfigSchema: z<SkillConfig> = z.object({
enabled: z.boolean().default(true),
registry: SkillService.Config,
local: SkillLocal.Config,
tool: toolSkill.Config,
@@ -100,7 +103,7 @@ export const Config = z.intersect([
skills: SkillConfigSchema,
workspaceContext: z.union([z.const(false), workspaceContext.Config]).required(),
toolBash: ToolBashConfigSchema,
toolTasks: ToolTasksConfigSchema,
toolTasks: z.union([z.const(false), ToolTasksConfigSchema]),
}) as unknown as z<Pick<Config, 'tools' | 'dshHome' | 'skills' | 'workspaceContext' | 'toolBash' | 'toolTasks'>>,
]) as unknown as z<Config>
@@ -137,7 +140,7 @@ 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)
@@ -150,8 +153,11 @@ export function apply(ctx: Context, config: Config): void {
...config.toolOrder !== undefined ? { toolOrder: config.toolOrder } : {},
})
ctx.plugin(ToolRegistry, config.tools ?? {})
ctx.plugin(SkillService, config.skills?.registry ?? {})
ctx.plugin(SkillLocal, Object.assign({}, config.skills?.local, { dshHome }))
const skillsEnabled = config.skills?.enabled ?? true
if (skillsEnabled) {
ctx.plugin(SkillService, config.skills?.registry ?? {})
ctx.plugin(SkillLocal, Object.assign({}, config.skills?.local, { dshHome }))
}
ctx.plugin(AgentRegistry)
ctx.plugin(TaskService)
ctx.plugin(invariants)
@@ -161,8 +167,8 @@ export function apply(ctx: Context, config: Config): void {
}
// Both plugins prepend session-prefix messages. Registration order is the
// rendered order, so workspace instructions must precede the skill catalog.
ctx.plugin(toolSkill, config.skills?.tool ?? {})
ctx.plugin(toolTasks, config.toolTasks ?? {})
if (skillsEnabled) ctx.plugin(toolSkill, config.skills?.tool ?? {})
if (config.toolTasks !== false) ctx.plugin(toolTasks, config.toolTasks ?? {})
ctx.plugin(AgentLoop, {
agents: config.agents ?? [],
...config.maxParallelToolCalls !== undefined ? { maxParallelToolCalls: config.maxParallelToolCalls } : {},

23
packages/examples/agent-spine-demo/tests/agent-core.spec.ts
View File

@@ -280,7 +280,7 @@ 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 () => {
@@ -344,6 +344,21 @@ describe('dsh-agent-spine-demo bundle', () => {
await ctx.fiber.dispose()
})
it('can omit skills and model-facing task controls for a foreground-only deployment', async () => {
const ctx = await mount({
workspaceContext: false,
skills: { enabled: false },
toolBash: { enableRunInBackground: false },
toolTasks: false,
}, true)
expect(ctx.tools.schemas().map(tool => tool.name)).toEqual(['bash'])
expect(ctx.get('skills')).toBeUndefined()
expect(ctx.get('tasks')).toBeDefined()
await ctx.fiber.dispose()
})
it('picks shared spine config without leaking front-door fields', () => {
const appConfig = {
model: 'front-door-only',
@@ -352,9 +367,9 @@ describe('dsh-agent-spine-demo bundle', () => {
tools: { mode: 'native' as const },
dshHome: '/tmp/dsh-home',
workspaceContext: false as const,
skills: {},
skills: { enabled: false },
toolBash: { enableRunInBackground: false },
toolTasks: { waitTimeoutMs: 7, maxWaitTimeoutMs: 11 },
toolTasks: false as const,
}
expect(agentCore.pickSpineConfig(appConfig)).toEqual({
@@ -363,7 +378,7 @@ describe('dsh-agent-spine-demo bundle', () => {
tools: appConfig.tools,
dshHome: appConfig.dshHome,
workspaceContext: false,
skills: {},
skills: appConfig.skills,
toolBash: appConfig.toolBash,
toolTasks: appConfig.toolTasks,
})

2
packages/examples/cli-demo/src/index.ts
View File

@@ -61,7 +61,7 @@ export const Config: z<Config> = z.object({
toolOrder: z.array(z.string()).default(undefined as unknown as string[]),
tools: ToolRegistry.Config,
toolBash: agentCore.ToolBashConfigSchema,
toolTasks: agentCore.ToolTasksConfigSchema,
toolTasks: z.union([z.const(false), agentCore.ToolTasksConfigSchema]),
workspaceContext: z.union([z.const(false), workspaceContext.Config]).required(),
})
/* jscpd:ignore-end */

15
packages/examples/cli-demo/tests/cli-demo.spec.ts
View File

@@ -146,6 +146,21 @@ describe('dsh-cli-demo app composition', () => {
expect(wait).toHaveBeenCalledWith(id, 7, undefined, undefined)
})
it('accepts false to keep task services without model-facing task controls', async () => {
const ctx = await mount({
provider: 'mock',
model: 'mock',
skills: { enabled: false },
toolTasks: false,
workspaceContext: false,
})
expect(ctx.get('tasks')).toBeDefined()
expect(ctx.get('tools')?.get('task_output')).toBeUndefined()
expect(ctx.get('tools')?.get('task_list')).toBeUndefined()
expect(ctx.get('tools')?.get('task_kill')).toBeUndefined()
})
it('exposes the Loader-safe namespace plugin shape and schema', () => {
expect(cliDemo.name).toBe('cli-demo')
expect(cliDemo.Config).toBeDefined()

Some files were not shown because too many files have changed in this diff Show More