Merge remote-tracking branch 'origin/master' into worktree/agent-loop-testkit

This commit is contained in:
Tianyi Cui
2026-07-17 20:17:27 +08:00
92 changed files with 1411 additions and 178 deletions

View File

@@ -33,7 +33,7 @@ Packages live at `packages/<group>/<pkg>/`; groups are containers, while names r
| [`ui/`](ui/README.md) | Editor/client integration surfaces: ACP bridge, JSON-RPC SDK server, user-approval/user-interaction seams, ask-user tool | Product — stable surface |
| [`examples/`](examples/README.md) | Demo bundles (agent-spine + stdio/ACP/JSON-RPC bins) the leaves load | Support — example infra |
| [`support/`](support/README.md) | Support infrastructure (testkits, invariants, replay, Loader smokes, subagent mock) | Support — lower compatibility expectations |
| [`util/`](util/README.md) | Low-level zero-dependency utilities shared across groups (`Branded<B>`, path helpers, timeout, retention) | Support — small, stable, harness-dep-free |
| [`util/`](util/README.md) | Low-level zero-dependency utilities shared across groups (`Branded<B>`, Harness home/path helpers, timeout, retention) | Support — small, stable, harness-dep-free |
Groups distinguish product API from support infrastructure. New packages join an existing group; a new group updates its README and this table.

View File

@@ -24,7 +24,7 @@ Design surveyed against the bash tools of Claude Code, OpenCode, Codex, and pi;
- **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*`), then `NO_COLOR=1 TERM=dumb PAGER=cat GIT_PAGER=cat` (Codex's hardcoded set) so pagers and ANSI color don't garble results. This scrub is the security control that keeps the harness's *ambient* credentials out of a spawned command. A spec's `env` is merged LAST (after the scrub), so a caller's explicit entry — a value it already holds — wins even on a credential-shaped name. The spec's `stdin`, when supplied, is written to the child and closed; with none supplied, fd 0 is `/dev/null` — the exact pre-seam default, so a command that probes stdin's file type is unaffected. Both `env`/`stdin` are set by in-process plugins (the hooks bridges); the model-facing tool doesn't expose them. See [the bash-stdin-env RFC](../../../docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md).
- **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).
- **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

View File

@@ -100,10 +100,14 @@ export class LocalBashExecutor extends BashExecutor {
timeoutMs,
stdoutMaxBytes,
...request.signal ? { signal: request.signal } : {},
// Explicit environment values are merged after credential scrubbing in run.ts.
// Carry stdin/ordinary env/trusted dshEnv through verbatim — optional,
// no config default. run.ts owns the scrub and merge order.
...request.stdin !== undefined ? { stdin: request.stdin } : {},
...request.env !== undefined ? { env: request.env } : {},
// Local execution carries this override for sandboxing subclasses.
...request.dshEnv !== undefined ? { dshEnv: request.dshEnv } : {},
// Carry a sandbox-mode override through verbatim: this executor never
// confines, so the field is inert here (the seam contract) — a
// sandboxing subclass overrides resolve() to stamp its default instead.
sandboxMode: request.sandboxMode,
}
}
@@ -120,6 +124,7 @@ export class LocalBashExecutor extends BashExecutor {
signal: d.signal,
stdin: spec.stdin,
env: spec.env,
dshEnv: spec.dshEnv,
}, this.internals).done
// Only this executor's timeout reason counts as timedOut; outer deadlines count as aborts.
const timedOut = timeoutOf(d.signal, 'BASH_TIMEOUT') !== undefined
@@ -138,6 +143,7 @@ export class LocalBashExecutor extends BashExecutor {
signal: spec.signal,
stdin: spec.stdin,
env: spec.env,
dshEnv: spec.dshEnv,
}, this.internals)
let stdoutOffset = 0

View File

@@ -11,7 +11,8 @@ import { randomBytes } from 'node:crypto'
import { closeSync, mkdtempSync, openSync, writeSync } from 'node:fs'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import type { CollectedOutput } from '@deepseek-ai/dsh-bash'
import { DSH_ENV_PREFIX } from '@deepseek-ai/dsh-bash'
import type { CollectedOutput, DshEnvironment } from '@deepseek-ai/dsh-bash'
/**
* Model-friendly environment overrides: disable colors, pagers, and
@@ -34,18 +35,33 @@ export const ENV_OVERRIDES = {
export const SENSITIVE_ENV_PATTERN = /KEY|SECRET|TOKEN/i
/**
* Build a child environment by scrubbing credential-shaped ambient variables,
* applying model-friendly overrides, then merging trusted caller entries last.
*
* @param extra - caller-supplied entries merged last; an explicit entry wins even against the scrub and the overrides.
* Build a child environment from scrubbed ambient values, terminal overrides,
* ordinary caller entries, and a managed `DSH_*` snapshot. Ambient managed
* names are removed; ordinary and managed entries reject the other channel's
* namespace before `dshEnv` merges last.
* @param extra - caller entries; `DSH_*` names are rejected.
* @param dshEnv - managed entries; non-`DSH_*` names are rejected.
* @returns the environment to hand to `spawn` for the child process.
*/
export function childEnv(extra?: Record<string, string>): NodeJS.ProcessEnv {
export function childEnv(
extra?: Readonly<Record<string, string>>,
dshEnv?: DshEnvironment,
): NodeJS.ProcessEnv {
const env: NodeJS.ProcessEnv = {}
for (const [key, value] of Object.entries(process.env)) {
if (!SENSITIVE_ENV_PATTERN.test(key)) env[key] = value
if (!SENSITIVE_ENV_PATTERN.test(key) && !key.startsWith(DSH_ENV_PREFIX)) env[key] = value
}
return { ...env, ...ENV_OVERRIDES, ...extra }
for (const key of Object.keys(extra ?? {})) {
if (key.startsWith(DSH_ENV_PREFIX)) {
throw new Error(`ordinary bash env cannot set reserved variable "${key}"; use dshEnv`)
}
}
for (const key of Object.keys(dshEnv ?? {})) {
if (!key.startsWith(DSH_ENV_PREFIX)) {
throw new Error(`managed bash env cannot set ordinary variable "${key}"; use env`)
}
}
return { ...env, ...ENV_OVERRIDES, ...extra, ...dshEnv }
}
/** What to run and under which limits (resolved — no defaults in here). */
@@ -73,12 +89,12 @@ export interface SpawnSpec {
*/
stdin?: string | undefined
/**
* Extra environment entries, merged onto the scrubbed env AFTER the
* credential scrub and the model-friendly overrides (so an explicit entry
* wins). Set by in-process plugins; the model-facing tool does not forward
* model input here.
* Ordinary environment entries merged after the credential scrub and
* terminal overrides. `DSH_*` names are rejected and belong in `dshEnv`.
*/
env?: Record<string, string> | undefined
/** Harness-owned entries; non-`DSH_*` names are rejected before spawn. */
dshEnv?: DshEnvironment | undefined
}
/**
@@ -280,7 +296,7 @@ export function runBash(spec: SpawnSpec, internals: RunInternals = {}): RunningB
}
// Keep absent stdin as /dev/null; literal tuples preserve non-null output types.
const env = childEnv(spec.env)
const env = childEnv(spec.env, spec.dshEnv)
const child: ChildProcessByStdio<Writable | null, Readable, Readable> = spec.stdin !== undefined
? 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 })

View File

@@ -127,21 +127,28 @@ describe('LocalBashExecutor.run', () => {
await expect(bash.run(bash.resolve({ command: 'true', workdir: '/nonexistent-dsh' }))).rejects.toThrow(/ENOENT/)
})
it('resolve() carries stdin/env onto the spec, and run() threads them to the command', async () => {
it('resolve() carries stdin/env/dshEnv onto the spec, and run() threads them to the command', async () => {
const { bash } = await setup()
const spec = bash.resolve({ command: 'cat; echo "[$DSH_SEAM_VAR]"', stdin: 'piped\n', env: { DSH_SEAM_VAR: 'env-ok' } })
// resolve() keeps the stdin/env fields verbatim (optional, no default).
const spec = bash.resolve({
command: 'cat; echo "[$SEAM_VAR][$DSH_SEAM_VAR]"',
stdin: 'piped\n',
env: { SEAM_VAR: 'env-ok' },
dshEnv: { DSH_SEAM_VAR: 'dsh-ok' },
})
// resolve() keeps the optional input/environment fields verbatim.
expect(spec.stdin).toBe('piped\n')
expect(spec.env).toEqual({ DSH_SEAM_VAR: 'env-ok' })
expect(spec.env).toEqual({ SEAM_VAR: 'env-ok' })
expect(spec.dshEnv).toEqual({ DSH_SEAM_VAR: 'dsh-ok' })
const result = await bash.run(spec)
expect(result.stdout.text).toBe('piped\n[env-ok]\n')
expect(result.stdout.text).toBe('piped\n[env-ok][dsh-ok]\n')
})
it('resolve() omits stdin/env when the request supplies neither', async () => {
it('resolve() omits stdin/env/dshEnv when the request supplies none', async () => {
const { bash } = await setup()
const spec = bash.resolve({ command: 'true' })
expect('stdin' in spec).toBe(false)
expect('env' in spec).toBe(false)
expect('dshEnv' in spec).toBe(false)
})
})
@@ -160,11 +167,12 @@ describe('LocalBashExecutor.start (background process handles)', () => {
it('threads stdin and extra env into a background process', async () => {
const { bash } = await setup()
const proc = bash.start(bash.resolve({
command: 'cat; echo "[$DSH_BG_VAR]"',
command: 'cat; echo "[$BG_VAR][$DSH_BG_VAR]"',
stdin: 'bg-stdin\n',
env: { DSH_BG_VAR: 'bg-env' },
env: { BG_VAR: 'bg-env' },
dshEnv: { DSH_BG_VAR: 'bg-dsh-env' },
}))
const output = await readUntil(proc, '[bg-env]')
const output = await readUntil(proc, '[bg-env][bg-dsh-env]')
expect(output).toContain('bg-stdin')
await proc.done
expect(proc.exitCode).toBe(0)

View File

@@ -2,6 +2,7 @@ import { mkdtempSync, readFileSync, statSync } from 'node:fs'
import { tmpdir } from 'node:os'
import { dirname, join } from 'node:path'
import { describe, expect, it, vi } from 'vitest'
import type { DshEnvironment } from '@deepseek-ai/dsh-bash'
import { killGroup, OutputCollector, runBash } from '../src/run.ts'
import type { RunningBash } from '../src/run.ts'
@@ -198,19 +199,19 @@ describe('stdin and extra env (set by in-process plugins)', () => {
expect(piped.stdout.text).toBe('socket\n')
})
it('merges extra env entries onto the scrubbed environment', async () => {
const result = await runBash(spec('echo "$DSH_EXTRA_ONE/$DSH_EXTRA_TWO"', {
env: { DSH_EXTRA_ONE: 'alpha', DSH_EXTRA_TWO: 'beta' },
it('merges ordinary extra env entries onto the scrubbed environment', async () => {
const result = await runBash(spec('echo "$EXTRA_ONE/$EXTRA_TWO"', {
env: { EXTRA_ONE: 'alpha', EXTRA_TWO: 'beta' },
})).done
expect(result.stdout.text).toBe('alpha/beta\n')
})
it('an explicit extra env entry overrides the model-friendly override and the scrub', async () => {
// TERM is a model-friendly OVERRIDE (dumb); an explicit extra entry wins.
// DSH_OVERRIDE_KEY matches the credential scrub pattern, yet an explicit
// EXPLICIT_OVERRIDE_KEY matches the credential scrub pattern, yet an explicit
// entry is still honored — the scrub only drops AMBIENT process.env creds.
const result = await runBash(spec('echo "$TERM/$DSH_OVERRIDE_KEY"', {
env: { TERM: 'xterm-256color', DSH_OVERRIDE_KEY: 'explicit-wins' },
const result = await runBash(spec('echo "$TERM/$EXPLICIT_OVERRIDE_KEY"', {
env: { TERM: 'xterm-256color', EXPLICIT_OVERRIDE_KEY: 'explicit-wins' },
})).done
expect(result.stdout.text).toBe('xterm-256color/explicit-wins\n')
})
@@ -363,13 +364,13 @@ describe('abort edge cases', () => {
})
describe('environment and spill-file hardening', () => {
it('scrubs credential-shaped env vars from child processes', async () => {
it('scrubs credential-shaped and ambient DSH env vars from child processes', async () => {
process.env.DSH_TEST_API_KEY = 'super-secret'
process.env.DSH_TEST_TOKEN = 'also-secret'
process.env.DSH_TEST_PLAIN = 'visible'
try {
const result = await runBash(spec('echo "[${DSH_TEST_API_KEY:-absent}|${DSH_TEST_TOKEN:-absent}|${DSH_TEST_PLAIN:-absent}]"')).done
expect(result.stdout.text.trim()).toBe('[absent|absent|visible]')
expect(result.stdout.text.trim()).toBe('[absent|absent|absent]')
} finally {
delete process.env.DSH_TEST_API_KEY
delete process.env.DSH_TEST_TOKEN
@@ -377,6 +378,29 @@ describe('environment and spill-file hardening', () => {
}
})
it('injects only the current trusted DSH environment after scrubbing ambient values', async () => {
process.env.DSH_STALE = 'old-value'
try {
const result = await runBash(spec('echo "[${DSH_STALE:-absent}|$DSH_SHELL|$DSH_SESSION_ID]"', {
dshEnv: { DSH_SHELL: '1', DSH_SESSION_ID: 'current-session' },
})).done
expect(result.stdout.text.trim()).toBe('[absent|1|current-session]')
} finally {
delete process.env.DSH_STALE
}
})
it('rejects DSH variables on the ordinary env channel', () => {
expect(() => runBash(spec('true', { env: { DSH_WRONG_CHANNEL: 'bad' } })))
.toThrow(/DSH_WRONG_CHANNEL.*dshEnv/)
})
it('rejects ordinary variables on the managed env channel', () => {
const invalid = { PATH: '/wrong-channel' } as unknown as DshEnvironment
expect(() => runBash(spec('true', { dshEnv: invalid })))
.toThrow(/managed bash env.*PATH.*use env/)
})
it('creates spill files with owner-only permissions and random names', async () => {
const result = await runBash(
spec('for i in $(seq 1 200); do printf "line-%04d\\n" $i; done', { stdoutMaxBytes: 500, stderrMaxBytes: 500 }),

View File

@@ -27,11 +27,11 @@ Implementations subclass `BashExecutor` and implement the abstract methods. Disp
## Vocabulary
`BashExecRequest` (command, workdir?, timeoutMs?, stdoutMaxBytes?, signal?, stdin?, env?, sandboxMode?) resolves to `BashExecSpec` (command, workdir, timeoutMs, stdoutMaxBytes, signal?, stdin?, env?, 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.
`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).
`stdin` and `env` are set by in-process plugins (the hooks bridges, native plugins) to feed a hook command its JSON payload on stdin and its `CLAUDE_PROJECT_DIR`/`CLAUDE_PLUGIN_ROOT` env. The model-facing `dsh-tool-bash` tool does not expose them as parameters — a model already has equivalent power through shell syntax (`FOO=bar cmd`, a heredoc), so they would be redundant tool params. This is not a security boundary: the implementation's credential scrub (not these fields) is what keeps the harness's ambient secrets out of a spawned command. They are plain optionals on the resolved spec; a missing value means "none". See [the bash-stdin-env RFC](../../../docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.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).
## Model Experience

View File

@@ -9,6 +9,7 @@ import { Context, Service } from 'cordis'
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,
@@ -19,6 +20,8 @@ export type {
BashRunResult,
BashSandboxInfo,
CollectedOutput,
DshEnvironment,
DshEnvironmentKey,
} from './types.ts'
declare module 'cordis' {

View File

@@ -6,6 +6,15 @@
import type { SandboxEnforcement, SandboxMode } from '@deepseek-ai/dsh-sandbox'
/** Namespace prefix reserved for DeepSeek Harness-managed child environment facts. */
export const DSH_ENV_PREFIX = 'DSH_' as const
/** One environment key inside the managed {@link DSH_ENV_PREFIX} namespace. */
export type DshEnvironmentKey = `${typeof DSH_ENV_PREFIX}${string}`
/** Trusted DeepSeek Harness variables for one bash execution. */
export type DshEnvironment = Readonly<Record<DshEnvironmentKey, string>>
/**
* Sandbox facts for one run, present iff a sandboxing executor handled it.
* Facts are reported independently of process exit status so callers can
@@ -52,15 +61,20 @@ export interface BashExecRequest {
*/
stdin?: string | undefined
/**
* Extra environment entries for the command, merged AFTER the
* implementation's credential scrub (so an explicit entry here is honored even
* when its name matches the scrub pattern — the caller named a value it holds,
* not the harness's ambient secret). Set by in-process plugins (the hooks
* bridges set `CLAUDE_PROJECT_DIR`, `CLAUDE_PLUGIN_ROOT`, …); the model-facing
* bash tool does not expose it as a parameter (a model that needs an env var
* uses shell syntax like `FOO=bar cmd`).
* Ordinary environment entries for the command, merged after the credential
* scrub. `DSH_*` is reserved for {@link dshEnv} and implementations reject it
* here. Set by in-process plugins (the hooks bridges set
* `CLAUDE_PROJECT_DIR`, `CLAUDE_PLUGIN_ROOT`, …); the model-facing bash tool
* does not expose it as a parameter.
*/
env?: Record<string, string> | undefined
/**
* Harness-owned `DSH_*` variables for this execution. Executors discard
* ambient `DSH_*` entries before merging this snapshot, so an unavailable
* current fact cannot inherit a stale value from the harness process, and
* reject non-`DSH_*` names supplied through this managed channel.
*/
dshEnv?: DshEnvironment | undefined
/** Explicit per-call sandbox mode override. */
sandboxMode?: SandboxMode | undefined
}
@@ -84,10 +98,14 @@ export interface BashExecSpec {
/** Bytes to write to stdin before closing it; absent means no stdin. */
stdin?: string | undefined
/**
* Extra environment entries, merged after credential scrubbing so explicit
* values win; absent means no extra entries.
* Ordinary environment entries carried through from
* {@link BashExecRequest.env}. `DSH_*` remains reserved for {@link dshEnv}.
* OPTIONAL on the spec for the same reason as `stdin`: absent means no
* ordinary extra environment.
*/
env?: Record<string, string> | undefined
/** Managed `DSH_*` snapshot; implementations reject ordinary names. */
dshEnv?: DshEnvironment | undefined
/** Resolved sandbox mode; ignored by executors that do not confine. */
sandboxMode: SandboxMode | undefined
}

View File

@@ -24,6 +24,29 @@ The plugin also contributes the `tool:bash` prompt section (order 105): check th
`command`, `workdir`, and `timeoutMs` are resolved against the executor's config defaults via `ctx.bash.resolve()` before execution, so the executor seam (`BashExecSpec`) receives explicit `workdir`/`timeoutMs` values. The workdir default is applied in the tool layer (from the calling agent's `session.header.cwd`) BEFORE `resolve()` — the per-session cwd must come from `exec.agent`, since N sessions share one executor; only when no session cwd is available does the executor fall back to its own config / `process.cwd()`.
### Managed shell environment
Every foreground and background model bash call receives a newly collected trusted `DSH_*` environment. `DSH_HOME` is the absolute Harness home resolved by [`@deepseek-ai/dsh-home`](../../util/home/README.md) (`dshHome` config, then ambient `$DSH_HOME`, then `~/.dsh`) and `DSH_SHELL=1` identifies the managed child. Agent calls additionally receive `DSH_SESSION_ID=agent.session.header.id`; when the active persistence seam locates a JSONL artifact they also receive `DSH_SESSION_JSONL=<absolute target path>`. The JSONL path is a location hint: it may not exist before the first flush or contain the current buffered turn, and it is not an authorization credential.
`ctx.bashEnv` owns collection. Other plugins can register an effect-scoped contributor with a stable name, declared keys/descriptions, and `resolve(execution: ToolExecution)`; duplicate ownership and undeclared runtime keys fail loudly, while `list()` enumerates declarations without executing providers. Harness built-ins reserve `DSH_HOME`, `DSH_SHELL`, and `DSH_SESSION_ID`; tool-bash's persistence translator owns `DSH_SESSION_JSONL` by reading the backend-neutral `sessionPersistence.locate()` seam.
```ts
import type { Context } from 'cordis'
import type {} from '@deepseek-ai/dsh-tool-bash'
export const inject = ['bashEnv']
export function apply(ctx: Context): void {
ctx.bashEnv.register({
name: 'deployment-region',
variables: { DSH_DEPLOYMENT_REGION: { description: 'Current deployment region.' } },
resolve: execution => execution.agent === undefined ? {} : { DSH_DEPLOYMENT_REGION: 'cn-north' },
})
}
```
The overlay is computed from the current `ToolExecution` and passed through the dedicated `BashExecRequest.dshEnv` channel. The local executor removes all inherited `DSH_*` before merging that snapshot, so nested harnesses and concurrent parent/child agents cannot leak stale identities. `process.env` is never modified. The tool description teaches the generic `$DSH_*` convention rather than naming persistence-specific variables or adding a permanent system-prompt section.
Result text contains stdout, an optional `[stderr]` section, then applicable sandbox-denial, timeout, signal, exit-code, and truncation markers. Timeout is reported independently of final exit status; nonzero exit remains a model-interpreted result rather than `isError`. Truncation links a safe complete spill file or reports it unavailable. Only infrastructure failures such as spawn errors and aborts produce `isError`.
When `run_in_background` is true, this plugin preflights `ctx.tasks.start()` before spawning, registers the calling agent as owner, and adapts the returned `BashProcess` handle into generic cancel/done/incremental-output hooks. The task runtime owns ids, cross-session isolation, completion notices, waiting, and disposal cleanup; this plugin only maps bash exit/sandbox facts into task output and outcome detail. `enableRunInBackground: false` removes the parameter and rejects a forced background call at execution time.
@@ -34,7 +57,7 @@ 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`, and `env`, used by trusted in-process plugins. This tool does **not** expose or forward them: it builds requests from named command/workdir/timeout/signal/sandbox fields only. This is not a trust boundary; the local executor's ambient credential scrub is the security control.
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).
## Permissions and escalation

View File

@@ -25,7 +25,9 @@
"@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-system-prompt": "^0.0.1",
"@deepseek-ai/dsh-tasks": "^0.0.1",
@@ -42,9 +44,12 @@
"@deepseek-ai/dsh-user-approval": "workspace:^",
"@deepseek-ai/dsh-bash": "workspace:^",
"@deepseek-ai/dsh-bash-local": "workspace:^",
"@deepseek-ai/dsh-home": "workspace:^",
"@deepseek-ai/dsh-llm": "workspace:^",
"@deepseek-ai/dsh-sandbox": "workspace:^",
"@deepseek-ai/dsh-session": "workspace:^",
"@deepseek-ai/dsh-session-persistence": "workspace:^",
"@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^",
"@deepseek-ai/dsh-system-prompt": "workspace:^",
"@deepseek-ai/dsh-tasks": "workspace:^",
"@deepseek-ai/dsh-tool-tasks": "workspace:^",

View File

@@ -8,34 +8,203 @@
* @module @deepseek-ai/dsh-tool-bash
*/
import type { Context } from 'cordis'
import { Service, type Context } from 'cordis'
import z from 'schemastery'
import { isAbsolute, resolve as resolvePath } from 'node:path'
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 { effectiveSandboxMode } from '@deepseek-ai/dsh-bash'
import { DSH_ENV_PREFIX, effectiveSandboxMode } 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'
import { parseExitStatus, renderProcessRead, renderResult } from './render.ts'
declare module 'cordis' {
interface Context {
bashEnv: BashEnvRegistry
}
}
export const name = 'tool-bash'
export const inject = ['tools', 'bash', 'systemPrompt']
/** Configures whether the model may background commands. */
/** Configuration for the bash tool and its managed child environment. */
export interface Config {
/** Expose `run_in_background` (default true); disabled calls are also rejected. */
enableRunInBackground?: boolean
/** DeepSeek Harness home directory exposed as `DSH_HOME`; defaults to `$DSH_HOME` or `~/.dsh`. */
dshHome?: string
}
/** Runtime configuration schema for the bash tool plugin. */
export const Config: z<Config> = z.object({
enableRunInBackground: z.boolean().default(true),
dshHome: z.string(),
})
/** Model-visible metadata for one managed `DSH_*` environment variable. */
export interface BashEnvVariable {
/** Concise description of the environment fact represented by the variable. */
description: string
}
/**
* A plugin contribution to the managed environment of each model bash call.
* Declared keys make ownership conflicts detectable before the first command;
* `resolve` computes only the values available for the current execution.
*/
export interface BashEnvContributor {
/** Stable contributor name used in diagnostics and duplicate detection. */
name: string
/** Complete set of `DSH_*` keys this contributor may return. */
variables: Readonly<Record<DshEnvironmentKey, BashEnvVariable>>
/**
* Resolve this contributor's available values for one tool execution.
* @param execution - the bash tool execution and its optional calling agent.
* @returns a partial map containing only keys declared in {@link variables}.
*/
resolve(execution: ToolExecution): Readonly<Partial<Record<DshEnvironmentKey, string>>>
}
/** An enumerable declaration returned by {@link BashEnvRegistry.list}. */
export interface BashEnvVariableInfo extends BashEnvVariable {
/** Contributor that owns the variable. */
contributor: string
/** Declared `DSH_*` environment variable name. */
key: DshEnvironmentKey
}
const DSH_SHELL_KEY = `${DSH_ENV_PREFIX}SHELL` as const
const DSH_SESSION_ID_KEY = `${DSH_ENV_PREFIX}SESSION_ID` as const
const DSH_SESSION_JSONL_KEY = `${DSH_ENV_PREFIX}SESSION_JSONL` as const
const RESERVED_BASH_ENV_KEYS = new Set<DshEnvironmentKey>([
DSH_HOME_ENV,
DSH_SHELL_KEY,
DSH_SESSION_ID_KEY,
])
const BASH_ENV_KEY_SUFFIX = /^[A-Z][A-Z0-9_]*$/
/**
* Registry (`ctx.bashEnv`) for trusted, per-execution `DSH_*` variables.
* The namespace is rebuilt for every model bash call: ambient `DSH_*` values
* are discarded by the executor, then the registry's current snapshot is
* injected. Built-in shell facts remain owned by the registry itself while
* plugins can register additional, enumerable facts with effect-scoped
* disposal.
*/
export class BashEnvRegistry extends Service {
private readonly contributors = new Map<string, BashEnvContributor>()
private readonly keyOwners = new Map<DshEnvironmentKey, string>()
private readonly dshHome: string
/**
* Create and install the `ctx.bashEnv` service.
* @param ctx - Cordis context that owns the service and registrations.
* @param config - home-directory configuration for the built-in variables.
*/
constructor(ctx: Context, config: Config = {}) {
super(ctx, 'bashEnv')
this.dshHome = resolveDshHome(config.dshHome)
}
/**
* Register one environment contributor. Names and keys are unique; built-in
* keys are reserved. Registration is disposed with the calling plugin fiber.
* @param contributor - declared key ownership and per-execution resolver.
* @returns the disposer that unregisters the contribution.
*/
register(contributor: BashEnvContributor): () => void {
const dispose = this.ctx.effect(function* (this: BashEnvRegistry) {
if (contributor.name.trim().length === 0) {
throw new Error('bash env contributor name must be non-empty')
}
if (this.contributors.has(contributor.name)) {
throw new Error(`bash env contributor "${contributor.name}" is already registered`)
}
const variables = Object.entries(contributor.variables) as [DshEnvironmentKey, BashEnvVariable][]
for (const [key, variable] of variables) {
if (!key.startsWith(DSH_ENV_PREFIX)
|| !BASH_ENV_KEY_SUFFIX.test(key.slice(DSH_ENV_PREFIX.length))) {
throw new Error(`bash env contributor "${contributor.name}" declared invalid key "${key}"`)
}
if (RESERVED_BASH_ENV_KEYS.has(key)) {
throw new Error(`bash env contributor "${contributor.name}" cannot own reserved key "${key}"`)
}
if (variable.description.trim().length === 0) {
throw new Error(`bash env contributor "${contributor.name}" must describe "${key}"`)
}
const owner = this.keyOwners.get(key)
if (owner !== undefined) {
throw new Error(`bash env key "${key}" is already owned by contributor "${owner}"; contributor "${contributor.name}" cannot also own it`)
}
}
this.contributors.set(contributor.name, contributor)
for (const [key] of variables) this.keyOwners.set(key, contributor.name)
yield () => {
this.contributors.delete(contributor.name)
for (const [key] of variables) this.keyOwners.delete(key)
}
}.bind(this), 'bashEnv.register()')
return () => void dispose()
}
/**
* Build the trusted `DSH_*` snapshot for one bash tool execution.
* @param execution - the current tool execution.
* @returns an immutable environment overlay containing built-ins and current contributions.
*/
collect(execution: ToolExecution): DshEnvironment {
const values: Record<DshEnvironmentKey, string> = {
[DSH_HOME_ENV]: this.dshHome,
[DSH_SHELL_KEY]: '1',
}
if (execution.agent !== undefined) {
values[DSH_SESSION_ID_KEY] = execution.agent.session.header.id
}
for (const contributor of [...this.contributors.values()].sort((left, right) => left.name.localeCompare(right.name))) {
const resolved = contributor.resolve(execution)
for (const [rawKey, value] of Object.entries(resolved)) {
const key = rawKey as DshEnvironmentKey
if (!Object.hasOwn(contributor.variables, key)) {
throw new Error(`bash env contributor "${contributor.name}" returned undeclared key "${key}"`)
}
if (typeof value !== 'string') {
throw new Error(`bash env contributor "${contributor.name}" returned a non-string value for "${key}"`)
}
values[key] = value
}
}
return Object.freeze(Object.fromEntries(Object.entries(values).sort(([left], [right]) => left.localeCompare(right))))
}
// TODO(bash-env-list-builtins): Include registry-owned built-ins before diagnostics,
// prompt, or UI code treats list() as an exhaustive environment catalog.
/**
* Enumerate plugin-contributed variables without executing their resolvers.
* @returns declarations sorted by environment variable name.
*/
list(): BashEnvVariableInfo[] {
return [...this.contributors.values()]
.flatMap(contributor => Object.entries(contributor.variables).map(([key, variable]) => ({
contributor: contributor.name,
description: variable.description,
key: key as DshEnvironmentKey,
})))
.sort((left, right) => left.key.localeCompare(right.key))
}
}
/** Parsed tool args; execute validates value constraints absent from SchemaSpec. */
interface BashToolArgs {
command: string
@@ -82,6 +251,7 @@ function bashDescription(backgroundEnabled: boolean, escalationModes: readonly S
const base = 'Execute a bash command (`bash -c`) and return its stdout/stderr. '
+ 'Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — '
+ 'pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. '
+ `Current harness environment facts are exposed through managed \`$${DSH_ENV_PREFIX}*\` variables; inspect them when needed. `
+ 'Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way. '
+ 'Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. '
+ background
@@ -153,7 +323,22 @@ function resolveWorkdir(modelWorkdir: string | undefined, exec: { agent?: Agent
return modelWorkdir
}
export function apply(ctx: Context, config: Config): void {
export function apply(ctx: Context, config: Config = {}): void {
const bashEnv = new BashEnvRegistry(ctx, config)
bashEnv.register({
name: 'session-persistence',
variables: {
[DSH_SESSION_JSONL_KEY]: {
description: 'Absolute target path of the current session JSONL when the active persistence backend provides one.',
},
},
resolve(execution) {
const agent = execution.agent
if (agent === undefined) return {}
const location = ctx.get('sessionPersistence')?.locate(agent.session.header)
return location?.kind === 'jsonl' ? { [DSH_SESSION_JSONL_KEY]: location.path } : {}
},
})
const backgroundEnabled = config.enableRunInBackground ?? true
const defaultMode = ctx.bash.sandboxMode
const escalationModes: readonly SandboxMode[] = defaultMode === undefined ? [] : ESCALATION_TARGETS
@@ -235,10 +420,12 @@ export function apply(ctx: Context, config: Config): void {
? await approveEscalation(args.sandbox_permissions, args.justification, exec)
: sessionOverride(exec)
const workdir = resolveWorkdir(args.workdir, exec)
const dshEnv = bashEnv.collect(exec)
const request = {
command: args.command,
...workdir !== undefined ? { workdir } : {},
...args.timeoutMs !== undefined ? { timeoutMs: args.timeoutMs } : {},
dshEnv,
...sandboxMode !== undefined ? { sandboxMode } : {},
}
if (args.run_in_background === true) {

View File

@@ -0,0 +1,190 @@
import { homedir } from 'node:os'
import { join, resolve } from 'node:path'
import { afterEach, describe, expect, it, vi } from 'vitest'
import { Context } from 'cordis'
import { CallId } from '@deepseek-ai/dsh-llm'
import type { Agent } from '@deepseek-ai/dsh-agent'
import type { ToolExecution } from '@deepseek-ai/dsh-tools'
import { BashEnvRegistry } from '@deepseek-ai/dsh-tool-bash'
afterEach(() => vi.unstubAllEnvs())
function execution(sessionId?: string): ToolExecution {
return {
token: Symbol('bash-env-test') as ToolExecution['token'],
callId: CallId('bash-env-call'),
name: 'bash',
arguments: { command: 'true' },
...(sessionId === undefined
? {}
: { agent: { session: { header: { version: 0, id: sessionId, createdAt: 0 } } } as Agent }),
}
}
describe('BashEnvRegistry', () => {
it('collects unconditional shell facts and the current agent session id', () => {
const ctx = new Context()
const registry = new BashEnvRegistry(ctx, { dshHome: './test-dsh-home' })
expect(registry.collect(execution())).toEqual({
DSH_HOME: resolve('./test-dsh-home'),
DSH_SHELL: '1',
})
expect(registry.collect(execution('session-a'))).toEqual({
DSH_HOME: resolve('./test-dsh-home'),
DSH_SESSION_ID: 'session-a',
DSH_SHELL: '1',
})
})
it('resolves DSH_HOME from the ambient override or the user-home default', () => {
vi.stubEnv('DSH_HOME', './ambient-dsh-home')
const fromEnvironment = new BashEnvRegistry(new Context())
expect(fromEnvironment.collect(execution()).DSH_HOME).toBe(resolve('./ambient-dsh-home'))
vi.stubEnv('DSH_HOME', undefined)
const fromDefault = new BashEnvRegistry(new Context())
expect(fromDefault.collect(execution()).DSH_HOME).toBe(join(homedir(), '.dsh'))
})
it('collects declared contributor variables and omits unavailable values', () => {
const ctx = new Context()
const registry = new BashEnvRegistry(ctx, { dshHome: './test-dsh-home' })
registry.register({
name: 'optional-session-fact',
variables: {
DSH_SESSION_OPTIONAL: { description: 'Optional session-scoped test fact.' },
},
resolve: exec => exec.agent === undefined ? {} : { DSH_SESSION_OPTIONAL: exec.agent.session.header.id },
})
registry.register({
name: 'always-available-fact',
variables: {
DSH_ALWAYS_AVAILABLE: { description: 'Always-available test fact.' },
},
resolve: () => ({ DSH_ALWAYS_AVAILABLE: 'yes' }),
})
expect(registry.collect(execution())).not.toHaveProperty('DSH_SESSION_OPTIONAL')
expect(registry.collect(execution()).DSH_ALWAYS_AVAILABLE).toBe('yes')
expect(registry.collect(execution('session-b')).DSH_SESSION_OPTIONAL).toBe('session-b')
expect(registry.list()).toEqual([
{
contributor: 'always-available-fact',
description: 'Always-available test fact.',
key: 'DSH_ALWAYS_AVAILABLE',
},
{
contributor: 'optional-session-fact',
description: 'Optional session-scoped test fact.',
key: 'DSH_SESSION_OPTIONAL',
},
])
})
it('rejects duplicate variable ownership at registration time', () => {
const ctx = new Context()
const registry = new BashEnvRegistry(ctx, { dshHome: './test-dsh-home' })
registry.register({
name: 'first',
variables: { DSH_SHARED: { description: 'First owner.' } },
resolve: () => ({ DSH_SHARED: 'first' }),
})
expect(() => registry.register({
name: 'second',
variables: { DSH_SHARED: { description: 'Second owner.' } },
resolve: () => ({ DSH_SHARED: 'second' }),
})).toThrow(/DSH_SHARED.*first.*second|DSH_SHARED.*second.*first/)
})
it('rejects duplicate contributor names and malformed declarations', () => {
const registry = new BashEnvRegistry(new Context(), { dshHome: './test-dsh-home' })
registry.register({
name: 'declared',
variables: { DSH_DECLARED: { description: 'Declared fact.' } },
resolve: () => ({}),
})
expect(() => registry.register({
name: 'declared',
variables: { DSH_ANOTHER: { description: 'Another fact.' } },
resolve: () => ({}),
})).toThrow(/already registered/)
expect(() => registry.register({
name: ' ',
variables: { DSH_BLANK_NAME: { description: 'Blank owner.' } },
resolve: () => ({}),
})).toThrow(/name must be non-empty/)
expect(() => registry.register({
name: 'invalid-key',
variables: { dsh_invalid: { description: 'Invalid key.' } } as unknown as Record<'DSH_INVALID', { description: string }>,
resolve: () => ({}),
})).toThrow(/invalid key/)
expect(() => registry.register({
name: 'reserved-key',
variables: { DSH_HOME: { description: 'Reserved key.' } },
resolve: () => ({}),
})).toThrow(/reserved key/)
expect(() => registry.register({
name: 'blank-description',
variables: { DSH_BLANK_DESCRIPTION: { description: ' ' } },
resolve: () => ({}),
})).toThrow(/must describe/)
})
it('rejects undeclared variables returned by a contributor', () => {
const ctx = new Context()
const registry = new BashEnvRegistry(ctx, { dshHome: './test-dsh-home' })
registry.register({
name: 'drifted-provider',
variables: { DSH_DECLARED: { description: 'Declared fact.' } },
resolve: () => ({ DSH_UNDECLARED: 'bad' }),
})
expect(() => registry.collect(execution())).toThrow(/drifted-provider.*DSH_UNDECLARED/)
})
it('rejects non-string values returned by a contributor', () => {
const registry = new BashEnvRegistry(new Context(), { dshHome: './test-dsh-home' })
registry.register({
name: 'wrong-value-type',
variables: { DSH_STRING: { description: 'String fact.' } },
resolve: () => ({ DSH_STRING: 42 }) as unknown as Record<'DSH_STRING', string>,
})
expect(() => registry.collect(execution())).toThrow(/wrong-value-type.*non-string.*DSH_STRING/)
})
it('removes an effect-scoped contributor when its plugin is disposed', async () => {
const ctx = new Context()
const registry = new BashEnvRegistry(ctx, { dshHome: './test-dsh-home' })
const fiber = await ctx.plugin({
inject: ['bashEnv'],
apply(inner: Context) {
inner.bashEnv.register({
name: 'temporary',
variables: { DSH_TEMPORARY: { description: 'Temporary fact.' } },
resolve: () => ({ DSH_TEMPORARY: 'present' }),
})
},
})
expect(registry.collect(execution()).DSH_TEMPORARY).toBe('present')
await fiber.dispose()
expect(registry.collect(execution())).not.toHaveProperty('DSH_TEMPORARY')
})
it('returns an explicit contributor disposer', () => {
const registry = new BashEnvRegistry(new Context(), { dshHome: './test-dsh-home' })
const dispose = registry.register({
name: 'explicit-disposal',
variables: { DSH_EXPLICIT_DISPOSAL: { description: 'Explicitly disposed fact.' } },
resolve: () => ({ DSH_EXPLICIT_DISPOSAL: 'present' }),
})
expect(registry.collect(execution()).DSH_EXPLICIT_DISPOSAL).toBe('present')
dispose()
expect(registry.collect(execution())).not.toHaveProperty('DSH_EXPLICIT_DISPOSAL')
})
})

View File

@@ -1,6 +1,10 @@
import { describe, expect, it } from 'vitest'
import { afterEach, describe, expect, it, vi } from 'vitest'
import { Context } from 'cordis'
import type { SessionEvent } from '@deepseek-ai/dsh-session'
import { existsSync, mkdtempSync, readFileSync, rmSync } from 'node:fs'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session'
import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
import { AgentId } from '@deepseek-ai/dsh-agent'
import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit'
@@ -16,18 +20,25 @@ import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent
* (tool/call + tool/result session events, the generic `ctx.tasks` runtime,
* agent.inject completion notices).
*/
async function harness(adapter: MockAdapter) {
async function harness(adapter: MockAdapter, sessionRoot?: string, dshHome?: string) {
const ctx = new Context()
await mountAgentLoopTestDependencies(ctx)
if (sessionRoot !== undefined) await ctx.plugin(SessionPersistenceJsonl, { root: sessionRoot })
await ctx.plugin(AgentLoop, { agents: [] })
await ctx.plugin(TaskService)
await ctx.plugin(ToolTasks)
await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 })
await ctx.plugin(ToolBash)
await ctx.plugin(ToolBash, dshHome === undefined ? {} : { dshHome })
ctx.llm.registerAdapter(['mock'], adapter)
return ctx
}
const dirs: string[] = []
afterEach(() => {
vi.unstubAllEnvs()
for (const dir of dirs.splice(0)) rmSync(dir, { recursive: true, force: true })
})
function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
return new Promise((resolve) => {
const dispose = ctx.on('agent/status', (subject, status) => {
@@ -75,6 +86,39 @@ async function pollUntil(predicate: () => boolean, timeoutMs = 5_000): Promise<v
}
describe('bash tool through the agent loop', () => {
it('first-turn bash receives session identity before the lazy JSONL file materializes', async () => {
const root = mkdtempSync(join(tmpdir(), 'dsh-bash-session-env-'))
dirs.push(root)
const dshHome = join(root, 'dsh-home')
vi.stubEnv('DSH_STALE_PARENT', 'stale')
const adapter = new MockAdapter([
toolCallResponse('call-1', 'bash', {
command: 'printf \'%s\\n%s\\n%s\\n%s\\n%s\\n\' "$DSH_HOME" "$DSH_SHELL" "$DSH_SESSION_ID" "$DSH_SESSION_JSONL" "${DSH_STALE_PARENT-unset}"; if [ -e "$DSH_SESSION_JSONL" ]; then printf \'present\\n\'; else printf \'absent\\n\'; fi',
description: 'inspect session environment',
}),
textResponse('Session environment inspected.'),
])
const ctx = await harness(adapter, root, dshHome)
const handle = await ctx.agents.create({
agentId: AgentId('session-env'),
sessionId: SessionId('session-env-id'),
agentOptions: { model: 'mock' },
})
const agent = handle.agent as ReactLoopAgent
const location = ctx.sessionPersistence.locate(agent.session.header)
expect(location?.kind).toBe('jsonl')
agent.send([{ type: 'text', text: 'inspect the current session' }])
await waitForIdle(ctx, agent)
const result = findEvent(events(agent), 'tool/result')
expect(resultText(result)).toBe(`${dshHome}\n1\nsession-env-id\n${location?.path}\nunset\nabsent\n`)
expect(existsSync(location!.path)).toBe(true)
const header = JSON.parse(readFileSync(location!.path, 'utf8').split('\n')[0]!) as { type: string; id: string }
expect(header).toMatchObject({ type: 'session', id: 'session-env-id' })
await handle.dispose()
})
it('foreground: model calls bash, sees the result, replies', async () => {
const adapter = new MockAdapter([
toolCallResponse('call-1', 'bash', { command: 'echo integration-ok', description: 'test command' }, 'Running it.'),

View File

@@ -10,6 +10,8 @@ import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry from '@deepseek-ai/dsh-tools'
import AgentRegistry from '@deepseek-ai/dsh-agent'
import type { Agent } from '@deepseek-ai/dsh-agent'
import SessionStore from '@deepseek-ai/dsh-session'
import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
import TaskService from '@deepseek-ai/dsh-tasks'
import * as ToolTasks from '@deepseek-ai/dsh-tool-tasks'
import ApprovalService from '@deepseek-ai/dsh-user-approval'
@@ -931,6 +933,8 @@ describe('tool-owned UI presentation (presentCall / presentResult)', () => {
})
describe('the model-facing bash tool builds its request from named args only (no {...args} forward)', () => {
const recordingDshHome = join(spillDir, 'dsh-home')
/**
* Records every {@link BashExecRequest} the consumer hands to `resolve()`, so a
* test can assert what the model-facing tool DID and DID NOT forward. The `bash`
@@ -956,6 +960,7 @@ describe('the model-facing bash tool builds its request from named args only (no
...request.signal ? { signal: request.signal } : {},
...request.stdin !== undefined ? { stdin: request.stdin } : {},
...request.env !== undefined ? { env: request.env } : {},
...request.dshEnv !== undefined ? { dshEnv: request.dshEnv } : {},
sandboxMode: request.sandboxMode,
}
}
@@ -977,18 +982,126 @@ describe('the model-facing bash tool builds its request from named args only (no
}
}
async function setupRecording() {
async function setupRecording(withJsonl = false) {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
if (withJsonl) {
await ctx.plugin(SessionStore)
await ctx.plugin(SessionPersistenceJsonl, { root: join(spillDir, 'jsonl') })
}
await ctx.plugin(TaskService)
await ctx.plugin(ToolTasks)
await ctx.plugin(RecordingBashExecutor)
await ctx.plugin(ToolBash)
await ctx.plugin(ToolBash, { dshHome: recordingDshHome })
return { ctx, bash: ctx.bash as RecordingBashExecutor }
}
it('describes the managed harness environment namespace to the model', async () => {
const { ctx } = await setupRecording()
const description = ctx.tools.get('bash')?.description ?? ''
expect(description).toContain('$DSH_*')
expect(description).not.toContain('DSH_SESSION_JSONL')
})
it('injects the session id and JSONL target path into a foreground request', async () => {
const { ctx, bash } = await setupRecording(true)
const agent = registerFakeAgent(ctx, 'request-fg', () => undefined)
const path = ctx.sessionPersistence.locate(agent.session.header)?.path
await ctx.tools.execute({
callId: CallId('session-env-fg'),
name: 'bash',
arguments: { command: 'true', description: 'run command' },
agent,
})
expect(bash.requests[0]?.dshEnv).toEqual({
DSH_HOME: recordingDshHome,
DSH_SESSION_ID: 'request-fg',
DSH_SESSION_JSONL: path,
DSH_SHELL: '1',
})
})
it('injects the same trusted variables into a background request without forwarding model env', async () => {
const { ctx, bash } = await setupRecording(true)
const agent = registerFakeAgent(ctx, 'request-bg', () => undefined)
const path = ctx.sessionPersistence.locate(agent.session.header)?.path
await ctx.tools.execute({
callId: CallId('session-env-bg'),
name: 'bash',
arguments: {
command: 'sleep 1',
description: 'run command',
run_in_background: true,
env: { DSH_SESSION_ID: 'spoofed', DSH_SESSION_JSONL: '/tmp/spoofed' },
},
agent,
})
expect(bash.requests[0]?.env).toBeUndefined()
expect(bash.requests[0]?.dshEnv).toEqual({
DSH_HOME: recordingDshHome,
DSH_SESSION_ID: 'request-bg',
DSH_SESSION_JSONL: path,
DSH_SHELL: '1',
})
})
it('injects built-ins and the stable session id when no JSONL locator is available', async () => {
const { ctx, bash } = await setupRecording()
const agent = registerFakeAgent(ctx, 'request-id-only', () => undefined)
const ambient = process.env.DSH_SESSION_ID
await ctx.tools.execute({
callId: CallId('session-env-id-only'),
name: 'bash',
arguments: { command: 'true', description: 'run command' },
agent,
})
expect(bash.requests[0]?.dshEnv).toEqual({
DSH_HOME: recordingDshHome,
DSH_SESSION_ID: 'request-id-only',
DSH_SHELL: '1',
})
expect(process.env.DSH_SESSION_ID).toBe(ambient)
})
it('keeps parent and child agent session environments isolated', async () => {
const { ctx, bash } = await setupRecording(true)
const parent = registerFakeAgent(ctx, 'request-parent', () => undefined)
const child = registerFakeAgent(ctx, 'request-child', () => undefined)
for (const [callId, agent] of [['parent', parent], ['child', child]] as const) {
await ctx.tools.execute({
callId: CallId(`session-env-${callId}`),
name: 'bash',
arguments: { command: 'true', description: 'run command' },
agent,
})
}
expect(bash.requests.map(request => request.dshEnv)).toEqual([
{
DSH_HOME: recordingDshHome,
DSH_SESSION_ID: 'request-parent',
DSH_SESSION_JSONL: ctx.sessionPersistence.locate(parent.session.header)?.path,
DSH_SHELL: '1',
},
{
DSH_HOME: recordingDshHome,
DSH_SESSION_ID: 'request-child',
DSH_SESSION_JSONL: ctx.sessionPersistence.locate(child.session.header)?.path,
DSH_SHELL: '1',
},
])
expect(bash.requests[0]?.dshEnv?.DSH_SESSION_JSONL).not.toBe(bash.requests[1]?.dshEnv?.DSH_SESSION_JSONL)
})
it('does not forward trusted-only fields even when the model includes them as extra arguments', async () => {
const { ctx, bash } = await setupRecording()
// Unknown `env` and `stdin` keys are ignored by the schema and named request construction.

View File

@@ -26,9 +26,15 @@
{
"path": "../../core/agent"
},
{
"path": "../../session-persistence/session-persistence"
},
{
"path": "../../bash/bash"
},
{
"path": "../../util/home"
},
{
"path": "../../tasks/tasks"
},

View File

@@ -91,6 +91,15 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [
'abstract start(spec: BashExecSpec): BashProcess',
],
},
{
key: 'bashEnv',
summary: 'Registry (`ctx.bashEnv`) for trusted, per-execution `DSH_*` variables.',
methods: [
'register(contributor: BashEnvContributor): () => void',
'collect(execution: ToolExecution): DshEnvironment',
'list(): BashEnvVariableInfo[]',
],
},
{
key: 'codeRuntime',
summary: 'Registers one `ctx.codeRuntime` implementation.',
@@ -150,6 +159,7 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [
key: 'sessionPersistence',
summary: 'Durable append-only session storage.',
methods: [
'abstract locate(meta: SessionHeader): SessionLocation | undefined',
'abstract create(meta: SessionHeader): Promise<void>',
'abstract append(id: SessionId, events: readonly SessionEvent[]): Promise<void>',
'abstract load(id: SessionId): Promise<{ meta: SessionHeader; events: SessionEvent[] }>',
@@ -575,13 +585,25 @@ export const TYPE_API: readonly TypeApiEntry[] = [
name: 'AssembledSection',
declaration: 'export interface AssembledSection {\n name: string;\n text: string;\n}',
},
{
name: 'BashEnvContributor',
declaration: 'export interface BashEnvContributor {\n name: string;\n variables: Readonly<Record<DshEnvironmentKey, BashEnvVariable>>;\n resolve(execution: ToolExecution): Readonly<Partial<Record<DshEnvironmentKey, string>>>;\n}',
},
{
name: 'BashEnvVariable',
declaration: 'export interface BashEnvVariable {\n description: string;\n}',
},
{
name: 'BashEnvVariableInfo',
declaration: 'export interface BashEnvVariableInfo extends BashEnvVariable {\n contributor: string;\n key: DshEnvironmentKey;\n}',
},
{
name: 'BashExecRequest',
declaration: 'export interface BashExecRequest {\n command: string;\n workdir?: string | undefined;\n timeoutMs?: number | undefined;\n stdoutMaxBytes?: number | undefined;\n signal?: AbortSignal | undefined;\n stdin?: string | undefined;\n env?: Record<string, string> | undefined;\n sandboxMode?: SandboxMode | undefined;\n}',
declaration: 'export interface BashExecRequest {\n command: string;\n workdir?: string | undefined;\n timeoutMs?: number | undefined;\n stdoutMaxBytes?: number | undefined;\n signal?: AbortSignal | undefined;\n stdin?: string | undefined;\n env?: Record<string, string> | undefined;\n dshEnv?: DshEnvironment | undefined;\n sandboxMode?: SandboxMode | undefined;\n}',
},
{
name: 'BashExecSpec',
declaration: 'export interface BashExecSpec {\n command: string;\n workdir: string;\n timeoutMs: number;\n stdoutMaxBytes: number;\n signal?: AbortSignal | undefined;\n stdin?: string | undefined;\n env?: Record<string, string> | undefined;\n sandboxMode: SandboxMode | undefined;\n}',
declaration: 'export interface BashExecSpec {\n command: string;\n workdir: string;\n timeoutMs: number;\n stdoutMaxBytes: number;\n signal?: AbortSignal | undefined;\n stdin?: string | undefined;\n env?: Record<string, string> | undefined;\n dshEnv?: DshEnvironment | undefined;\n sandboxMode: SandboxMode | undefined;\n}',
},
{
name: 'BashProcess',
@@ -679,6 +701,14 @@ export const TYPE_API: readonly TypeApiEntry[] = [
name: 'DiffResultView',
declaration: 'export interface DiffResultView {\n card: \'diff\';\n title?: string;\n diffs: FileDiff[];\n}',
},
{
name: 'DshEnvironment',
declaration: 'export type DshEnvironment = Readonly<Record<DshEnvironmentKey, string>>;',
},
{
name: 'DshEnvironmentKey',
declaration: 'export type DshEnvironmentKey = `${typeof DSH_ENV_PREFIX}${string}`;',
},
{
name: 'FileDiff',
declaration: 'export interface FileDiff {\n path: string;\n oldText: string | null;\n newText: string;\n}',
@@ -875,6 +905,10 @@ export const TYPE_API: readonly TypeApiEntry[] = [
name: 'SessionLineageTrace',
declaration: 'export type SessionLineageTrace = {\n target: SessionRecord;\n ancestors: SessionRecord[];\n descendants: SessionLineageNode[];\n} & ({\n complete: true;\n root: SessionRecord;\n} | {\n complete: false;\n unresolvedParentId: SessionId;\n});',
},
{
name: 'SessionLocation',
declaration: 'export interface SessionLocation {\n readonly kind: string;\n readonly path: string;\n}',
},
{
name: 'SessionRecord',
declaration: 'export interface SessionRecord {\n header: SessionHeader;\n live: boolean;\n persisted: boolean;\n}',

View File

@@ -28,6 +28,7 @@ Because the package wires no logger entry, an ACP leaf has **nothing to get wron
| `model` | (required) | the per-session agent template the bridge creates agents from |
| `persona` | — | the deployment persona template (may reference `{{model}}`/`{{cwd}}`), routed to `dsh-system-prompt` |
| `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` |
| `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` |

View File

@@ -38,6 +38,8 @@ export interface Config {
toolOrder?: string[]
/** Tool-registry config — its presentation `mode` (forwarded through agent-spine-demo; see dsh-tools). */
tools?: ToolsConfig
/** DeepSeek Harness home directory exposed to bash and used for local skill discovery. */
dshHome?: string
/** Directory the JSONL session backend writes under. Defaults to `./.sessions`. */
persistenceRoot?: string
/** Controls automatic AGENTS.md/CLAUDE.md loading; configure a byte budget or set `false`. */
@@ -61,6 +63,7 @@ export const Config: z<Config> = z.object({
// schemastery's native [] default would read as an invalid configured list.
toolOrder: z.array(z.string()).default(undefined as unknown as string[]),
tools: ToolRegistry.Config,
dshHome: z.string(),
// TODO(single-default-literal): share this schema default and the defensive
// apply() fallback through one named constant while retaining both boundaries.
persistenceRoot: z.string().default('./.sessions'),

View File

@@ -118,8 +118,9 @@ describe('dsh-acp-demo composition', () => {
})
})
it('forwards skill config into agent-spine-demo', async () => {
const ctx = await mount({ model: 'mock', persona: 'hi', skills: await isolatedSkillsConfig(6), workspaceContext: false })
it('forwards skill config and dshHome into agent-spine-demo', async () => {
const skills = await isolatedSkillsConfig(6)
const ctx = await mount({ model: 'mock', persona: 'hi', dshHome: skills.local!.dshHome!, skills, workspaceContext: false })
ctx.skills.register({ name: 'acp-skill', description: 'ACP skill', source: 'runtime', content: 'body' })
expect(JSON.stringify(await composePrefix(ctx))).toContain('- `acp-skill`: ACP...')
await ctx.fiber.dispose()

View File

@@ -42,11 +42,11 @@ This is the [interface/implementation/consumer seam](../../../docs/rfc/implement
```ts
import type { Config } from '@deepseek-ai/dsh-agent-spine-demo'
// { agents?, persona?, toolOrder?, tools?, skills?, workspaceContext, toolBash?, toolTasks? }
// { agents?, persona?, toolOrder?, tools?, dshHome?, skills?, workspaceContext, toolBash?, toolTasks? }
// workspaceContext requires { maxBytes } or false; the other owner schemas supply defaults.
```
The bundle FORWARDS each field to the child that owns it: `agents` to `agent-loop` (default `[]`), so each app supplies its own pre-created agents — a stdio app pre-creates a `main`; the ACP app pre-creates none (it creates agents on demand at `session/new`) — `persona` 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. `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` to `agent-loop` (default `[]`), so each app supplies its own pre-created agents — a stdio app pre-creates a `main`; the ACP app pre-creates none (it creates agents on demand at `session/new`) — `persona` 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.
## Why a code bundle, not a shared YAML include

View File

@@ -26,6 +26,7 @@
"@deepseek-ai/dsh-agent": "^0.0.1",
"@deepseek-ai/dsh-agent-loop": "^0.0.1",
"@deepseek-ai/dsh-invariants": "^0.0.1",
"@deepseek-ai/dsh-home": "^0.0.1",
"@deepseek-ai/dsh-llm": "^0.0.1",
"@deepseek-ai/dsh-workspace-context": "^0.0.1",
"@deepseek-ai/dsh-session": "^0.0.1",
@@ -45,6 +46,7 @@
"@deepseek-ai/dsh-agent-loop": "workspace:^",
"@deepseek-ai/dsh-fs-local": "workspace:^",
"@deepseek-ai/dsh-invariants": "workspace:^",
"@deepseek-ai/dsh-home": "workspace:^",
"@deepseek-ai/dsh-llm": "workspace:^",
"@deepseek-ai/dsh-workspace-context": "workspace:^",
"@deepseek-ai/dsh-session": "workspace:^",

View File

@@ -25,6 +25,7 @@ import * as workspaceContext from '@deepseek-ai/dsh-workspace-context'
import * as toolSkill from '@deepseek-ai/dsh-tool-skill'
import * as toolTasks from '@deepseek-ai/dsh-tool-tasks'
import AgentLoop, { type Config as AgentLoopConfig } from '@deepseek-ai/dsh-agent-loop'
import { resolveDshHome } from '@deepseek-ai/dsh-home'
export const name = 'agent-spine-demo'
@@ -44,13 +45,14 @@ export interface SkillConfig {
* bridge, simply omits it), `persona` and `toolOrder` to the system-prompt
* plugin (the deployment's persona section and the explicit model-facing tool
* order), the `tools` object to the tool registry (its presentation `mode`),
* `skills` to the skill registry/local provider/tool consumer,
* `workspaceContext` to the workspace-context loader, and
* `toolBash`/`toolTasks` to the model-facing tool plugins this bundle owns.
* Owner schemas supply defaults for optional input; workspace context instead
* requires an explicit byte budget or `false` because it changes model-visible
* input. Producer opt-in stays producer-local: `toolBash` configures bash only;
* independently composed producers keep their own config.
* `dshHome` to bash environment and local skill discovery, `skills` to the
* skill registry/local provider/tool consumer, `workspaceContext` to the
* workspace-context loader, and `toolBash`/`toolTasks` to the model-facing tool
* plugins this bundle owns. Owner schemas supply defaults for optional input;
* workspace context instead requires an explicit byte budget or `false` because
* it changes model-visible input. Producer opt-in stays producer-local:
* `toolBash` configures bash only; independently composed producers keep their
* own config.
*/
export interface Config {
/** The agent-loop `agents` list (see dsh-agent-loop's `Config`). */
@@ -61,6 +63,8 @@ export interface Config {
toolOrder?: SystemPromptConfig['toolOrder']
/** The tool registry's config — its presentation `mode` (see dsh-tools' `Config`). */
tools?: ToolsConfig
/** DeepSeek Harness home directory shared by shell context and local skill discovery. */
dshHome?: string
/** Workspace-context loader controls with an explicit byte budget; set `false` for hermetic prompts. */
workspaceContext: workspaceContext.Config | false
/** Skill registry, local provider, and model-facing consumer config. */
@@ -90,11 +94,12 @@ export const Config = z.intersect([
SystemPrompt.Config,
z.object({
tools: ToolRegistry.Config,
dshHome: z.string(),
skills: SkillConfigSchema,
workspaceContext: z.union([z.const(false), workspaceContext.Config]).required(),
toolBash: ToolBashConfigSchema,
toolTasks: ToolTasksConfigSchema,
}) as unknown as z<Pick<Config, 'tools' | 'skills' | 'workspaceContext' | 'toolBash' | 'toolTasks'>>,
}) as unknown as z<Pick<Config, 'tools' | 'dshHome' | 'skills' | 'workspaceContext' | 'toolBash' | 'toolTasks'>>,
]) as unknown as z<Config>
/**
@@ -107,6 +112,7 @@ export function pickSpineConfig(config: Omit<Config, 'agents'>): Omit<Config, 'a
...config.persona !== undefined ? { persona: config.persona } : {},
...config.toolOrder !== undefined ? { toolOrder: config.toolOrder } : {},
...config.tools !== undefined ? { tools: config.tools } : {},
...config.dshHome !== undefined ? { dshHome: config.dshHome } : {},
workspaceContext: config.workspaceContext,
...config.skills !== undefined ? { skills: config.skills } : {},
...config.toolBash !== undefined ? { toolBash: config.toolBash } : {},
@@ -125,6 +131,13 @@ export function pickSpineConfig(config: Omit<Config, 'agents'>): Omit<Config, 'a
* seams, then the loop that drives them.
*/
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')
}
const dshHome = resolveDshHome(config.dshHome ?? nestedDshHome)
ctx.plugin(Timer)
ctx.plugin(LlmService)
ctx.plugin(SessionStore)
@@ -135,11 +148,11 @@ export function apply(ctx: Context, config: Config): void {
})
ctx.plugin(ToolRegistry, config.tools ?? {})
ctx.plugin(SkillService, config.skills?.registry ?? {})
ctx.plugin(SkillLocal, config.skills?.local ?? {})
ctx.plugin(SkillLocal, Object.assign({}, config.skills?.local, { dshHome }))
ctx.plugin(AgentRegistry)
ctx.plugin(TaskService)
ctx.plugin(invariants)
ctx.plugin(toolBash, config.toolBash ?? {})
ctx.plugin(toolBash, Object.assign({}, config.toolBash, { dshHome }))
if (config.workspaceContext !== false) {
ctx.plugin(workspaceContext, config.workspaceContext)
}

View File

@@ -11,6 +11,7 @@ import { SessionId } from '@deepseek-ai/dsh-session'
import LocalFileSystem from '@deepseek-ai/dsh-fs-local'
import { MockAdapter, textResponse } from '../../../core/agent-loop/tests/mock-adapter.ts'
import { CallId, type Message } from '@deepseek-ai/dsh-llm'
import type { ToolExecution } from '@deepseek-ai/dsh-tools'
declare module '@deepseek-ai/dsh-tasks' {
interface TaskKindMap {
@@ -239,6 +240,39 @@ describe('dsh-agent-spine-demo bundle', () => {
await ctx.fiber.dispose()
})
it('shares top-level dshHome between local skills and the managed bash environment', async () => {
const home = await mkdtemp(join(tmpdir(), 'dsh-agent-core-shared-home-'))
const agentsHome = await mkdtemp(join(tmpdir(), 'dsh-agent-core-shared-agents-'))
await mkdir(join(home, 'skills'), { recursive: true })
await writeFile(join(home, 'skills', 'shared-skill.md'), '---\nname: shared-skill\ndescription: Shared home skill\n---\n\nShared body.\n')
const ctx = await mount({
dshHome: home,
workspaceContext: false,
skills: { local: { agentsHome } },
}, true)
expect((await ctx.skills.list()).map(skill => skill.name)).toEqual(['shared-skill'])
const execution: ToolExecution = {
token: Symbol('agent-core-dsh-home-test') as ToolExecution['token'],
callId: CallId('agent-core-dsh-home'),
name: 'bash',
arguments: { command: 'true' },
}
expect(ctx.bashEnv.collect(execution)).toMatchObject({ DSH_HOME: home, DSH_SHELL: '1' })
await ctx.fiber.dispose()
})
it('rejects conflicting global and nested DSH home directories', () => {
expect(() => {
agentCore.apply(new Context(), {
dshHome: '/global-dsh-home',
workspaceContext: false,
skills: { local: { dshHome: '/nested-dsh-home' } },
})
}).toThrow(/must resolve to the same directory/)
})
it('places workspace instructions before the skill catalog in the session prefix', async () => {
const root = await mkdtemp(join(tmpdir(), 'dsh-agent-spine-demo-prefix-order-'))
try {
@@ -307,6 +341,7 @@ describe('dsh-agent-spine-demo bundle', () => {
persona: 'You are merged.',
toolOrder: ['zulu'],
tools: { mode: 'native' as const },
dshHome: '/tmp/dsh-home',
workspaceContext: false as const,
skills: {},
toolBash: { enableRunInBackground: false },
@@ -317,6 +352,7 @@ describe('dsh-agent-spine-demo bundle', () => {
persona: appConfig.persona,
toolOrder: appConfig.toolOrder,
tools: appConfig.tools,
dshHome: appConfig.dshHome,
workspaceContext: false,
skills: {},
toolBash: appConfig.toolBash,

View File

@@ -50,6 +50,9 @@
{
"path": "../../support/invariants"
},
{
"path": "../../util/home"
},
{
"path": "../../bash/tool-bash"
},

View File

@@ -28,6 +28,7 @@ The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapte
| `model` | (required) | the pre-created `main` agent's model |
| `persona` | — | the deployment persona template (may reference `{{model}}`/`{{cwd}}`), routed to `dsh-system-prompt` |
| `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` |
| `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` |

View File

@@ -43,6 +43,8 @@ export interface Config {
toolOrder?: string[]
/** Tool-registry config — its presentation `mode` (forwarded through agent-spine-demo; see dsh-tools). */
tools?: ToolsConfig
/** DeepSeek Harness home directory exposed to bash and used for local skill discovery. */
dshHome?: string
/** Directory the JSONL session backend writes under. Defaults to `./.sessions`. */
persistenceRoot?: string
/** stdin-chat banner printed once on start. Defaults to `'ready.'`. */
@@ -71,6 +73,7 @@ export const Config: z<Config> = z.object({
// schemastery's native [] default would read as an invalid configured list.
toolOrder: z.array(z.string()).default(undefined as unknown as string[]),
tools: ToolRegistry.Config,
dshHome: z.string(),
// TODO(single-default-literal): share these schema defaults and defensive
// apply() fallbacks through named constants while retaining both boundaries.
persistenceRoot: z.string().default('./.sessions'),

View File

@@ -132,8 +132,9 @@ describe('dsh-stdio-demo app', () => {
await ctx.fiber.dispose()
})
it('forwards skill config into agent-spine-demo', async () => {
const ctx = await mount({ model: 'mock', persona: 'hi', skills: await isolatedSkillsConfig(6), workspaceContext: false })
it('forwards skill config and dshHome into agent-spine-demo', async () => {
const skills = await isolatedSkillsConfig(6)
const ctx = await mount({ model: 'mock', persona: 'hi', dshHome: skills.local!.dshHome!, skills, workspaceContext: false })
ctx.skills.register({ name: 'stdio-skill', description: 'Stdio skill', source: 'runtime', content: 'body' })
expect(JSON.stringify(await composePrefix(ctx))).toContain('- `stdio-skill`: Std...')
await ctx.fiber.dispose()

View File

@@ -46,6 +46,8 @@ The three emit points run detached — no seam awaits a `SessionStart`/`Subagent
The matcher subject is the tool name (`PreToolUse`/`PostToolUse`), the session source (`SessionStart`), or a constant `agent_type` of `general-purpose` (`SubagentStart`/`SubagentStop` — the harness subagent seam carries no per-kind label, so the bridge reports Claude Code's own Task-tool default; a default/`*`/empty `agent_type` matcher fires, a specific-kind matcher does not); `UserPromptSubmit`/`Stop` ignore matchers. Multiple file-configured hooks on one point run **serially, in config order**, and fold most-restrictively (`deny > ask > allow`, see `dsh-hook-protocol`); serial keeps each hook's `hook/invoked`/`hook/result` pair adjacent in the log, and the fold is order-independent for the decision (see the RFC's "run serially, not concurrently" note).
Every agent-scoped stdin payload carries `session_id` and string-shaped `transcript_path`. The bridge resolves the latter through `ctx.sessionPersistence.locate(session.header)` when available and otherwise sends `''`. Lookup does not create or flush the artifact, so a path can be absent before the first turn-end checkpoint or omit the current open turn.
## Context source
Injected context carries an explicit `{ kind: 'plugin', plugin: 'hooks-claude' }` source. `agent.inject()` defaults a missing source to `{ kind: 'user' }`, which would mislabel plugin context as a user prompt — so the bridge always names itself.

View File

@@ -29,6 +29,7 @@
"@deepseek-ai/dsh-hook-protocol": "^0.0.1",
"@deepseek-ai/dsh-llm": "^0.0.1",
"@deepseek-ai/dsh-session": "^0.0.1",
"@deepseek-ai/dsh-session-persistence": "^0.0.1",
"@deepseek-ai/dsh-subagent": "^0.0.1",
"@deepseek-ai/dsh-tools": "^0.0.1",
"cordis": "^4.0.0-rc.7"
@@ -42,6 +43,8 @@
"@deepseek-ai/dsh-hook-protocol": "workspace:^",
"@deepseek-ai/dsh-llm": "workspace:^",
"@deepseek-ai/dsh-session": "workspace:^",
"@deepseek-ai/dsh-session-persistence": "workspace:^",
"@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^",
"@deepseek-ai/dsh-subagent": "workspace:^",
"@deepseek-ai/dsh-tools": "workspace:^",
"cordis": "^4.0.0-rc.7"

View File

@@ -14,6 +14,7 @@ import type { Context } from 'cordis'
import z from 'schemastery'
import type { Agent, ContinuationDecision, HookContext, PromptDecision } from '@deepseek-ai/dsh-agent'
import type { ContentBlock, MessageSource } from '@deepseek-ai/dsh-llm'
import type {} from '@deepseek-ai/dsh-session-persistence'
import type { PostToolDecision, PreToolDecision, ToolExecution, ToolExecutionResult } from '@deepseek-ai/dsh-tools'
import {
appendHookInvoked,
@@ -197,7 +198,7 @@ export function apply(ctx: Context, config: Config): void {
// may miss the first request.
// TODO(session-start-gating): add a startup gate before promising first-turn delivery.
ctx.on('agent/session-start', (agent, source) => {
detached.track(runPoint('SessionStart', source, sessionStartPayload(agent, source), { agent, signal: detached.signal })
detached.track(runPoint('SessionStart', source, sessionStartPayload(ctx, agent, source), { agent, signal: detached.signal })
.then((merged) => {
const context = contextFrom(merged)
if (context) agent.inject(context.content, { source: context.source })
@@ -211,7 +212,7 @@ export function apply(ctx: Context, config: Config): void {
// matcher subject (CC ignores matchers for this event). ---
ctx.on('agent/prompt-submit', async (agent, content, _source, next): Promise<PromptDecision> => {
const turn = lastTurn(agent)
const merged = await runPoint('UserPromptSubmit', '', promptPayload(agent, content), { agent, turn })
const merged = await runPoint('UserPromptSubmit', '', promptPayload(ctx, agent, content), { agent, turn })
if (merged.decision === 'deny') {
return { kind: 'block', reason: merged.reason ?? 'blocked by UserPromptSubmit hook' }
}
@@ -230,7 +231,7 @@ export function apply(ctx: Context, config: Config): void {
// --- PreToolUse → PreToolDecision. Matcher subject is the tool name. ---
ctx.on('tools/pre-execute', async (exec, next): Promise<PreToolDecision> => {
const turn = lastTurn(exec.agent)
const merged = await runPoint('PreToolUse', exec.name, preToolPayload(exec), { ...exec.agent ? { agent: exec.agent } : {}, turn, ...exec.signal ? { signal: exec.signal } : {} })
const merged = await runPoint('PreToolUse', exec.name, preToolPayload(ctx, exec), { ...exec.agent ? { agent: exec.agent } : {}, turn, ...exec.signal ? { signal: exec.signal } : {} })
if (merged.decision === 'deny') return { kind: 'deny', reason: merged.reason ?? 'blocked by PreToolUse hook' }
if (merged.decision === 'ask') return { kind: 'ask', ...merged.reason !== undefined ? { reason: merged.reason } : {} }
return next()
@@ -239,7 +240,7 @@ export function apply(ctx: Context, config: Config): void {
// --- PostToolUse → PostToolDecision. Matcher subject is the tool name. ---
ctx.on('tools/post-execute', async (exec, result, next): Promise<PostToolDecision> => {
const turn = lastTurn(exec.agent)
const merged = await runPoint('PostToolUse', exec.name, postToolPayload(exec, result), { ...exec.agent ? { agent: exec.agent } : {}, turn, ...exec.signal ? { signal: exec.signal } : {} })
const merged = await runPoint('PostToolUse', exec.name, postToolPayload(ctx, exec, result), { ...exec.agent ? { agent: exec.agent } : {}, turn, ...exec.signal ? { signal: exec.signal } : {} })
const context = contextFrom(merged)
if (merged.decision === 'deny') {
return { kind: 'block', feedback: [{ type: 'text', text: merged.reason ?? 'blocked by PostToolUse hook' }], ...context ? { additionalContexts: [context] } : {} }
@@ -261,7 +262,7 @@ export function apply(ctx: Context, config: Config): void {
// A blocking Stop hook forces continuation with its reason.
// TODO(stop-loop-guard): cap consecutive forced continuations; hooks must self-limit meanwhile.
ctx.on('agent/turn-continuation', async (agent, turn, _default, next): Promise<ContinuationDecision> => {
const merged = await runPoint('Stop', '', stopPayload(agent), { agent, turn })
const merged = await runPoint('Stop', '', stopPayload(ctx, agent), { agent, turn })
if (merged.decision === 'deny') {
// A blocking Stop hook forces continuation.
const text = merged.reason ?? 'continue: blocked by Stop hook'
@@ -274,7 +275,7 @@ export function apply(ctx: Context, config: Config): void {
// use the live child's workspace and the generic agent-type matcher subject.
ctx.on('subagent/start', (info) => {
const child = ctx.get('agents')?.get(info.id)
detached.track(runPoint('SubagentStart', SUBAGENT_TYPE, subagentPayload('SubagentStart', info, child), { ...child ? { agent: child } : {}, signal: detached.signal })
detached.track(runPoint('SubagentStart', SUBAGENT_TYPE, subagentPayload(ctx, 'SubagentStart', info, child), { ...child ? { agent: child } : {}, signal: detached.signal })
.then((merged) => {
const context = contextFrom(merged)
if (context && child) child.inject(context.content, { source: context.source })
@@ -286,7 +287,7 @@ export function apply(ctx: Context, config: Config): void {
// `.then` before the tool caller's `await run.result` disposes it) so the hook runs in the
// child's cwd, not the server default.
const child = ctx.get('agents')?.get(info.id)
detached.track(runPoint('SubagentStop', SUBAGENT_TYPE, subagentPayload('SubagentStop', info, child), { ...child ? { agent: child } : {}, signal: detached.signal }))
detached.track(runPoint('SubagentStop', SUBAGENT_TYPE, subagentPayload(ctx, 'SubagentStop', info, child), { ...child ? { agent: child } : {}, signal: detached.signal }))
})
}
@@ -316,28 +317,31 @@ function blocksToText(content: ContentBlock[]): string {
return content.filter((b): b is Extract<ContentBlock, { type: 'text' }> => b.type === 'text').map(b => b.text).join('')
}
function base(agent: Agent | undefined, event: string): Record<string, unknown> {
function base(ctx: Context, agent: Agent | undefined, event: string): Record<string, unknown> {
return {
session_id: agent?.session.header.id ?? '',
transcript_path: agent === undefined
? ''
: ctx.get('sessionPersistence')?.locate(agent.session.header)?.path ?? '',
cwd: agent?.session.header.cwd ?? process.cwd(),
hook_event_name: event,
}
}
function sessionStartPayload(agent: Agent, source: string): Record<string, unknown> {
return { ...base(agent, 'SessionStart'), source }
function sessionStartPayload(ctx: Context, agent: Agent, source: string): Record<string, unknown> {
return { ...base(ctx, agent, 'SessionStart'), source }
}
function promptPayload(agent: Agent, content: ContentBlock[]): Record<string, unknown> {
return { ...base(agent, 'UserPromptSubmit'), prompt: blocksToText(content) }
function promptPayload(ctx: Context, agent: Agent, content: ContentBlock[]): Record<string, unknown> {
return { ...base(ctx, agent, 'UserPromptSubmit'), prompt: blocksToText(content) }
}
function preToolPayload(exec: ToolExecution): Record<string, unknown> {
return { ...base(exec.agent, 'PreToolUse'), tool_name: exec.name, tool_input: exec.arguments, tool_use_id: exec.callId }
function preToolPayload(ctx: Context, exec: ToolExecution): Record<string, unknown> {
return { ...base(ctx, exec.agent, 'PreToolUse'), tool_name: exec.name, tool_input: exec.arguments, tool_use_id: exec.callId }
}
function postToolPayload(exec: ToolExecution, result: ToolExecutionResult): Record<string, unknown> {
return { ...base(exec.agent, 'PostToolUse'), tool_name: exec.name, tool_input: exec.arguments, tool_use_id: exec.callId, tool_response: blocksToText(result.content) }
function postToolPayload(ctx: Context, exec: ToolExecution, result: ToolExecutionResult): Record<string, unknown> {
return { ...base(ctx, exec.agent, 'PostToolUse'), tool_name: exec.name, tool_input: exec.arguments, tool_use_id: exec.callId, tool_response: blocksToText(result.content) }
}
function stopPayload(agent: Agent): Record<string, unknown> {
return { ...base(agent, 'Stop'), stop_hook_active: false }
function stopPayload(ctx: Context, agent: Agent): Record<string, unknown> {
return { ...base(ctx, agent, 'Stop'), stop_hook_active: false }
}
/**
* Build a SubagentStart/SubagentStop payload from the CC base (the child's
@@ -345,9 +349,9 @@ function stopPayload(agent: Agent): Record<string, unknown> {
* fields. `agent_type` is the CC-default {@link SUBAGENT_TYPE}; `stop_hook_active`
* is present on SubagentStop only (the loop-guard flag, always false this cut).
*/
function subagentPayload(event: 'SubagentStart' | 'SubagentStop', info: { id: string }, child: Agent | undefined): Record<string, unknown> {
function subagentPayload(ctx: Context, event: 'SubagentStart' | 'SubagentStop', info: { id: string }, child: Agent | undefined): Record<string, unknown> {
return {
...base(child, event),
...base(ctx, child, event),
agent_id: info.id,
agent_type: SUBAGENT_TYPE,
...event === 'SubagentStop' ? { stop_hook_active: false } : {},

View File

@@ -1,9 +1,10 @@
import { afterEach, describe, expect, it, vi } from 'vitest'
import { mkdtempSync, rmSync, writeFileSync, chmodSync, existsSync } from 'node:fs'
import { mkdtempSync, rmSync, writeFileSync, chmodSync, existsSync, readFileSync } from 'node:fs'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { Context } from 'cordis'
import type { SessionEvent } from '@deepseek-ai/dsh-session'
import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
import { defineTool } from '@deepseek-ai/dsh-tools'
import { AgentId } from '@deepseek-ai/dsh-agent'
import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
@@ -26,10 +27,11 @@ function hooks(d: string, h: unknown): string {
writeFileSync(join(d, 'hooks.json'), JSON.stringify({ hooks: h })); return join(d, 'hooks.json')
}
type HarnessOpts = { pluginRoot?: string; projectDir?: string; stderrSummaryMaxChars?: number }
type HarnessOpts = { pluginRoot?: string; projectDir?: string; stderrSummaryMaxChars?: number; sessionRoot?: string }
async function harness(configPath: string, adapter: MockAdapter, opts: HarnessOpts = {}): Promise<Context> {
const ctx = new Context()
await mountAgentLoopTestDependencies(ctx)
if (opts.sessionRoot !== undefined) await ctx.plugin(SessionPersistenceJsonl, { root: opts.sessionRoot })
await ctx.plugin(AgentLoop, { agents: [] })
await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 })
await ctx.plugin(HooksClaude, { configPath, ...opts })
@@ -51,6 +53,28 @@ async function waitFor(predicate: () => boolean, timeout = 5000, interval = 10):
}
describe('hooks-claude coverage — config option arms + substitution + skip warning', () => {
it('uses the persistence locator for transcript_path and an empty string without one', async () => {
async function capture(sessionRoot?: string): Promise<{ payload: { transcript_path: string }; expected: string | undefined }> {
const d = dir()
const cap = join(d, 'payload')
const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'capture.sh', `#!/usr/bin/env bash\ncat > "${cap}"\n`) }] }] })
const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')])
const ctx = await harness(path, adapter, { ...sessionRoot !== undefined ? { sessionRoot } : {} })
ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } }))
const agent = ctx.agentLoop.create(AgentId('transcript'), { model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
return {
payload: JSON.parse(readFileSync(cap, 'utf8')) as { transcript_path: string },
expected: ctx.get('sessionPersistence')?.locate(agent.session.header)?.path,
}
}
const located = await capture(dir())
expect(located.payload.transcript_path).toBe(located.expected)
expect((await capture()).payload.transcript_path).toBe('')
}, 15_000) // Two real agent/hook subprocess loops need loaded pre-push runner headroom.
it('honors pluginRoot + projectDir substitution and warns on a skipped non-command hook', async () => {
const d = dir()
// ${CLAUDE_PLUGIN_ROOT} resolves to d; the script writes its own cwd-independent marker.

View File

@@ -29,6 +29,9 @@
{
"path": "../../core/session"
},
{
"path": "../../session-persistence/session-persistence"
},
{
"path": "../../subagent/subagent"
},

View File

@@ -48,6 +48,8 @@ The hooks themselves run in the agent's session workspace: for the agent-scoped
A tool call's payload carries the real `tool_name` (the same value the matcher tests) and Codex's `tool_input: { command }` shape (the `command` arg when present, else `''`). The matcher subject is the tool name (`PreToolUse`/`PostToolUse`) or the session source (`SessionStart`); `UserPromptSubmit`/`Stop` ignore matchers.
Every agent-scoped stdin payload carries `session_id` and `transcript_path`. The bridge resolves the latter through `ctx.sessionPersistence.locate(session.header)` when available and otherwise sends `null`, preserving the Codex `string | null` shape. Lookup does not create or flush the artifact, so a path can be absent before the first turn-end checkpoint or omit the current open turn.
`SessionStart` — the one emit point — runs detached; each run chain is tracked, and disposing the bridge aborts a still-running hook process, then drains the continuation before the dispose resolves (`createDetachedRuns` in `dsh-hook-protocol`).
## Context source

View File

@@ -29,6 +29,7 @@
"@deepseek-ai/dsh-hook-protocol": "^0.0.1",
"@deepseek-ai/dsh-llm": "^0.0.1",
"@deepseek-ai/dsh-session": "^0.0.1",
"@deepseek-ai/dsh-session-persistence": "^0.0.1",
"@deepseek-ai/dsh-tools": "^0.0.1",
"cordis": "^4.0.0-rc.7"
},
@@ -41,6 +42,8 @@
"@deepseek-ai/dsh-hook-protocol": "workspace:^",
"@deepseek-ai/dsh-llm": "workspace:^",
"@deepseek-ai/dsh-session": "workspace:^",
"@deepseek-ai/dsh-session-persistence": "workspace:^",
"@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^",
"@deepseek-ai/dsh-tools": "workspace:^",
"cordis": "^4.0.0-rc.7"
}

View File

@@ -17,6 +17,7 @@ import type { Context } from 'cordis'
import z from 'schemastery'
import type { Agent, ContinuationDecision, HookContext, PromptDecision } from '@deepseek-ai/dsh-agent'
import type { ContentBlock, MessageSource } from '@deepseek-ai/dsh-llm'
import type {} from '@deepseek-ai/dsh-session-persistence'
import type { PostToolDecision, PreToolDecision, ToolExecution, ToolExecutionResult } from '@deepseek-ai/dsh-tools'
import {
appendHookInvoked,
@@ -172,7 +173,7 @@ export function apply(ctx: Context, config: Config): void {
// hook may miss the first request.
// TODO(session-start-gating): add a startup gate before promising first-turn delivery.
ctx.on('agent/session-start', (agent, source) => {
detached.track(runPoint('SessionStart', source, { ...base(agent, 'SessionStart', model), source }, { agent, plainStdoutAsContext: true, signal: detached.signal })
detached.track(runPoint('SessionStart', source, { ...base(ctx, agent, 'SessionStart', model), source }, { agent, plainStdoutAsContext: true, signal: detached.signal })
.then((merged) => {
const context = contextFrom(merged)
if (context) agent.inject(context.content, { source: context.source })
@@ -184,7 +185,7 @@ export function apply(ctx: Context, config: Config): void {
// UserPromptSubmit → PromptDecision. Codex supports block, not allow or ask.
ctx.on('agent/prompt-submit', async (agent, content, _source, next): Promise<PromptDecision> => {
const turn = lastTurn(agent)
const merged = await runPoint('UserPromptSubmit', '', { ...turnBase(agent, 'UserPromptSubmit', model), prompt: blocksToText(content) }, { agent, turn, plainStdoutAsContext: true })
const merged = await runPoint('UserPromptSubmit', '', { ...turnBase(ctx, agent, 'UserPromptSubmit', model), prompt: blocksToText(content) }, { agent, turn, plainStdoutAsContext: true })
/* jscpd:ignore-start */
if (merged.decision === 'deny') return { kind: 'block', reason: merged.reason ?? 'blocked by UserPromptSubmit hook' }
// Context alone is not a veto: DELEGATE so a later prompt-submit listener can
@@ -202,7 +203,7 @@ export function apply(ctx: Context, config: Config): void {
// PreToolUse → PreToolDecision. Codex blocks only (no allow/ask honored).
ctx.on('tools/pre-execute', async (exec, next): Promise<PreToolDecision> => {
const turn = lastTurn(exec.agent)
const merged = await runPoint('PreToolUse', exec.name, preToolPayload(exec, model), { ...exec.agent ? { agent: exec.agent } : {}, turn, ...exec.signal ? { signal: exec.signal } : {} })
const merged = await runPoint('PreToolUse', exec.name, preToolPayload(ctx, exec, model), { ...exec.agent ? { agent: exec.agent } : {}, turn, ...exec.signal ? { signal: exec.signal } : {} })
/* jscpd:ignore-end */
if (merged.decision === 'deny') return { kind: 'deny', reason: merged.reason ?? 'blocked by PreToolUse hook' }
return next()
@@ -212,7 +213,7 @@ export function apply(ctx: Context, config: Config): void {
ctx.on('tools/post-execute', async (exec, result, next): Promise<PostToolDecision> => {
const turn = lastTurn(exec.agent)
/* jscpd:ignore-start */
const merged = await runPoint('PostToolUse', exec.name, postToolPayload(exec, result, model), { ...exec.agent ? { agent: exec.agent } : {}, turn, ...exec.signal ? { signal: exec.signal } : {} })
const merged = await runPoint('PostToolUse', exec.name, postToolPayload(ctx, exec, result, model), { ...exec.agent ? { agent: exec.agent } : {}, turn, ...exec.signal ? { signal: exec.signal } : {} })
const context = contextFrom(merged)
if (merged.decision === 'deny') {
return { kind: 'block', feedback: [{ type: 'text', text: merged.reason ?? 'blocked by PostToolUse hook' }], ...context ? { additionalContexts: [context] } : {} }
@@ -236,7 +237,7 @@ export function apply(ctx: Context, config: Config): void {
// avoid continuing the same turn indefinitely. It is always false here, so an
// unconditionally blocking hook force-continues every step until it self-limits.
ctx.on('agent/turn-continuation', async (agent, turn, _default, next): Promise<ContinuationDecision> => {
const merged = await runPoint('Stop', '', { ...turnBase(agent, 'Stop', model), stop_hook_active: false, last_assistant_message: null }, { agent, turn })
const merged = await runPoint('Stop', '', { ...turnBase(ctx, agent, 'Stop', model), stop_hook_active: false, last_assistant_message: null }, { agent, turn })
/* jscpd:ignore-end */
if (merged.decision === 'deny') {
// A blocking Stop hook forces continuation; a block with no reason (exit 2,
@@ -270,10 +271,12 @@ function blocksToText(content: ContentBlock[]): string {
/* jscpd:ignore-end */
/** Base fields on every Codex payload (no turn_id). */
function base(agent: Agent | undefined, event: string, model: string): Record<string, unknown> {
function base(ctx: Context, agent: Agent | undefined, event: string, model: string): Record<string, unknown> {
return {
session_id: agent?.session.header.id ?? '',
transcript_path: null,
transcript_path: agent === undefined
? null
: ctx.get('sessionPersistence')?.locate(agent.session.header)?.path ?? null,
cwd: agent?.session.header.cwd ?? process.cwd(),
hook_event_name: event,
model,
@@ -282,8 +285,8 @@ function base(agent: Agent | undefined, event: string, model: string): Record<st
}
/** Base + turn_id, for the turn-scoped events (PreToolUse/PostToolUse/UserPromptSubmit/Stop). */
function turnBase(agent: Agent | undefined, event: string, model: string): Record<string, unknown> {
return { ...base(agent, event, model), turn_id: String(lastTurn(agent)) }
function turnBase(ctx: Context, agent: Agent | undefined, event: string, model: string): Record<string, unknown> {
return { ...base(ctx, agent, event, model), turn_id: String(lastTurn(agent)) }
}
/** Extract a `command` string from a tool call's parsed arguments, else ''. */
@@ -295,14 +298,14 @@ function commandOf(args: unknown): string {
return ''
}
function preToolPayload(exec: ToolExecution, model: string): Record<string, unknown> {
function preToolPayload(ctx: Context, exec: ToolExecution, model: string): Record<string, unknown> {
// `tool_name` is the REAL tool name (matching the `exec.name` matcher subject);
// a hardcoded constant would disagree with what the matcher tests and make a
// config's tool matcher never fire. `tool_input` keeps Codex's `{ command }`
// shape (its shell payload), derived from the call's `command` arg when present.
return { ...turnBase(exec.agent, 'PreToolUse', model), tool_name: exec.name, tool_input: { command: commandOf(exec.arguments) }, tool_use_id: exec.callId }
return { ...turnBase(ctx, exec.agent, 'PreToolUse', model), tool_name: exec.name, tool_input: { command: commandOf(exec.arguments) }, tool_use_id: exec.callId }
}
function postToolPayload(exec: ToolExecution, result: ToolExecutionResult, model: string): Record<string, unknown> {
return { ...turnBase(exec.agent, 'PostToolUse', model), tool_name: exec.name, tool_input: { command: commandOf(exec.arguments) }, tool_use_id: exec.callId, tool_response: blocksToText(result.content) }
function postToolPayload(ctx: Context, exec: ToolExecution, result: ToolExecutionResult, model: string): Record<string, unknown> {
return { ...turnBase(ctx, exec.agent, 'PostToolUse', model), tool_name: exec.name, tool_input: { command: commandOf(exec.arguments) }, tool_use_id: exec.callId, tool_response: blocksToText(result.content) }
}

View File

@@ -4,6 +4,7 @@ import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { Context } from 'cordis'
import type { SessionEvent } from '@deepseek-ai/dsh-session'
import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
import { defineTool } from '@deepseek-ai/dsh-tools'
import { AgentId } from '@deepseek-ai/dsh-agent'
import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
@@ -22,9 +23,11 @@ function hooks(d: string, h: unknown): string {
writeFileSync(join(d, 'hooks.json'), JSON.stringify({ hooks: h })); return join(d, 'hooks.json')
}
async function harness(configPath: string, adapter: MockAdapter, opts: { stderrSummaryMaxChars?: number } = {}): Promise<Context> {
type HarnessOpts = { stderrSummaryMaxChars?: number; sessionRoot?: string }
async function harness(configPath: string, adapter: MockAdapter, opts: HarnessOpts = {}): Promise<Context> {
const ctx = new Context()
await mountAgentLoopTestDependencies(ctx)
if (opts.sessionRoot !== undefined) await ctx.plugin(SessionPersistenceJsonl, { root: opts.sessionRoot })
await ctx.plugin(AgentLoop, { agents: [] })
await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 })
await ctx.plugin(HooksCodex, { configPath, model: 'm', ...opts })
@@ -46,6 +49,28 @@ async function waitFor(predicate: () => boolean, timeout = 5000, interval = 10):
}
describe('hooks-codex coverage — decision mapping paths', () => {
it('uses the persistence locator for transcript_path and null without one', async () => {
async function capture(sessionRoot?: string): Promise<{ payload: { transcript_path: string | null }; expected: string | undefined }> {
const d = dir()
const cap = join(d, 'payload')
const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'capture.sh', `#!/usr/bin/env bash\ncat > "${cap}"\n`) }] }] })
const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')])
const ctx = await harness(path, adapter, { ...sessionRoot !== undefined ? { sessionRoot } : {} })
ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } }))
const agent = ctx.agentLoop.create(AgentId('transcript'), { model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
return {
payload: JSON.parse(readFileSync(cap, 'utf8')) as { transcript_path: string | null },
expected: ctx.get('sessionPersistence')?.locate(agent.session.header)?.path,
}
}
const located = await capture(dir())
expect(located.payload.transcript_path).toBe(located.expected)
expect((await capture()).payload.transcript_path).toBeNull()
}, 15_000) // Two real agent/hook subprocess loops need loaded pre-push runner headroom.
it('UserPromptSubmit block (exit 2) → rejected turn; default reason on empty stderr', async () => {
const d = dir()
hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'b.sh', '#!/usr/bin/env bash\nexit 2\n') }] }] })

View File

@@ -29,6 +29,9 @@
{
"path": "../../core/session"
},
{
"path": "../../session-persistence/session-persistence"
},
{
"path": "../../llm/llm"
},

View File

@@ -19,6 +19,8 @@ The JSONL durable session-persistence backend — a concrete `SessionPersistence
|---|---|---|
| `root` | `string` (required) | Root directory for all session files. **No default** — a `process.cwd()` default would scatter files as the process's cwd changes (bash calls, subprocesses). |
`locate(meta)` returns `{ kind: 'jsonl', path }` using the resolved absolute root and the same cwd-bucket/id encoding as materialization. It performs no filesystem I/O: the target can be returned before the file exists, and an existing file contains only the last flushed prefix.
## Durability and crash semantics
- **Lazy materialization.** `create(meta)` writes nothing; on the first `append`, the backend writes and `fsync`s a temporary file, publishes it without overwrite via a hard link, then `fsync`s the directory. A created-but-never-appended session leaves nothing on disk and is absent from `list`.

View File

@@ -1,7 +1,8 @@
/**
* JSONL durable session-persistence backend. It stores a header and contiguous
* events in one append-only file per session, and delegates orchestration to
* {@link PersistenceCoordinator}.
* {@link PersistenceCoordinator}. Its side-effect-free locator returns the
* absolute per-session log target before materialization.
* @module @deepseek-ai/dsh-session-persistence-jsonl
*/
@@ -12,7 +13,7 @@ import { dirname, resolve } from 'node:path'
import { randomBytes } from 'node:crypto'
import {
SessionPersistence, PersistenceCoordinator,
type PersistenceBackend, type StoredPrefix,
type PersistenceBackend, type SessionLocation, type StoredPrefix,
} from '@deepseek-ai/dsh-session-persistence'
import type { SessionEvent, SessionId, SessionHeader } from '@deepseek-ai/dsh-session'
import {
@@ -68,6 +69,11 @@ export class SessionPersistenceJsonl extends SessionPersistence implements Persi
/* jscpd:ignore-start */
// --- SessionPersistence service surface (delegated to the coordinator) ---
/** Resolve the absolute target path without touching the filesystem. */
locate(meta: SessionHeader): SessionLocation {
return { kind: 'jsonl', path: logPath(this.root, meta.cwd, meta.id) }
}
create(meta: SessionHeader): Promise<void> {
return this.coordinator.create(meta)
}

View File

@@ -2,7 +2,7 @@ import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest'
import { Context } from 'cordis'
import { appendFile, mkdtemp, mkdir, rm, readFile, writeFile, readdir, stat } from 'node:fs/promises'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { isAbsolute, join, relative, resolve } from 'node:path'
import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
import type { Session, SessionEvent, SessionHeader } from '@deepseek-ai/dsh-session'
import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
@@ -112,6 +112,19 @@ describe('SessionPersistenceJsonl: format helpers', () => {
it('encodeSegment rejects an empty id', () => {
expect(() => encodeSegment('')).toThrow(/empty/)
})
it('resolves a relative custom root before locating a session', async () => {
const absoluteRoot = await freshRoot()
const ctx = new Context()
await ctx.plugin(SessionStore)
const fiber = await ctx.plugin(SessionPersistenceJsonl, { root: relative(process.cwd(), absoluteRoot) })
const m = meta('relative-location', '/work')
expect(ctx.sessionPersistence.locate(m)).toEqual({
kind: 'jsonl',
path: logPath(resolve(absoluteRoot), '/work', m.id),
})
await fiber.dispose()
})
})
describe('SessionPersistenceJsonl: durability and crash semantics', () => {
@@ -126,8 +139,13 @@ describe('SessionPersistenceJsonl: durability and crash semantics', () => {
it('lazy materialization: create() writes no file until the first append', async () => {
const m = meta('lazy', '/work')
const location = ctx.sessionPersistence.locate(m)
expect(location).toEqual({ kind: 'jsonl', path: logPath(root, '/work', m.id) })
expect(isAbsolute(location!.path)).toBe(true)
await ctx.sessionPersistence.create(m)
// nothing on disk yet
// locate() is a pure target-path calculation: neither it nor create()
// materializes a file before the first append.
const dir = sessionDir(root, '/work')
await expect(stat(logPath(root, '/work', m.id))).rejects.toThrow()
expect((await ctx.sessionPersistence.list()).map(h => h.id)).not.toContain(m.id)
@@ -139,6 +157,26 @@ describe('SessionPersistenceJsonl: durability and crash semantics', () => {
void dir
})
it('keeps the same location on resume and gives a fork its own location', async () => {
const parent = meta('location-parent', '/work')
const parentLocation = ctx.sessionPersistence.locate(parent)
await ctx.sessionPersistence.create(parent)
await ctx.sessionPersistence.append(parent.id, oneTurnLog())
const loaded = await ctx.sessionPersistence.load(parent.id)
expect(ctx.sessionPersistence.locate(loaded.meta)).toEqual(parentLocation)
const child = {
...loaded.meta,
id: SessionId('location-child'),
parentSession: parent.id,
seedLength: loaded.events.length,
}
const childLocation = ctx.sessionPersistence.locate(child)
expect(childLocation?.path).not.toBe(parentLocation?.path)
expect(childLocation).toEqual({ kind: 'jsonl', path: logPath(root, '/work', child.id) })
})
it('round-trip is byte-identical (incl. assistant/chunk verbatim)', async () => {
const m = meta('chunks')
const log: SessionEvent[] = [

View File

@@ -2,6 +2,8 @@
A SQLite durable session-persistence backend — a second `SessionPersistence` implementation ([session persistence](../../../docs/rfc/implemented/architecture/2026-06-14-session-persistence.md)), built to validate that the abstract seam and the shared `runPersistenceContract` suite are genuinely backend-agnostic. It satisfies the SAME contract as `dsh-session-persistence-jsonl` (append-only, contiguous-seq, lazy materialization, interrupted-turn close on load), expressed over `node:sqlite` rows instead of file bytes.
`locate(meta)` returns `undefined`: all sessions share one database, so there is no honest independent per-session transcript path.
> **TODO:** this backend talks to `node:sqlite` directly. If a cordis database service (`cordis/db` / a `@cordisjs` SQL driver plugin) is adopted, route through that instead of holding a raw `DatabaseSync` here — the contract surface (`SessionPersistence`) would not change, only the storage driver.
## Storage model

View File

@@ -1,7 +1,8 @@
/**
* SQLite durable session-persistence backend. It maps each session header and
* event to rows, and delegates write-path orchestration to
* {@link PersistenceCoordinator}.
* {@link PersistenceCoordinator}. It has no independent per-session artifact,
* so its locator returns `undefined`.
* @module @deepseek-ai/dsh-session-persistence-sqlite
*/
@@ -12,7 +13,7 @@ import { mkdir } from 'node:fs/promises'
import { dirname, resolve } from 'node:path'
import {
SessionPersistence, PersistenceCoordinator,
type PersistenceBackend, type StoredPrefix,
type PersistenceBackend, type SessionLocation, type StoredPrefix,
} from '@deepseek-ai/dsh-session-persistence'
import type { SessionEvent, SurfaceEventType, SessionId, SessionHeader } from '@deepseek-ai/dsh-session'
import {
@@ -95,6 +96,11 @@ export class SessionPersistenceSqlite extends SessionPersistence implements Pers
// --- SessionPersistence service surface (delegated to the coordinator) ---
/** SQLite has one database, not an independent local artifact per session. */
locate(_meta: SessionHeader): SessionLocation | undefined {
return undefined
}
create(meta: SessionHeader): Promise<void> {
return this.coordinator.create(meta)
}

View File

@@ -153,6 +153,12 @@ describe('scanRows', () => {
})
describe('SessionPersistenceSqlite: durability and crash semantics', () => {
it('has no independent per-session log location', async () => {
const { ctx, dispose } = await backend()
expect(ctx.sessionPersistence.locate(meta('sqlite-location'))).toBeUndefined()
await dispose()
})
it('an interrupted turn (rows after the last turn/end) is PRESERVED and closed during load', async () => {
const path = await freshDbPath()
const m = meta('crash')

View File

@@ -8,6 +8,7 @@ The persisted unit IS the existing `SessionEvent` (event-sourced model — the l
| Method | Contract |
|---|---|
| `locate(meta): SessionLocation \| undefined` | Resolve an absolute per-session artifact target without I/O or materialization. Backends without an independent local artifact return `undefined`. |
| `create(meta): Promise<void>` | Register a new session's metadata. MAY defer the physical write until the first `append` (lazy materialization). |
| `append(id, events): Promise<void>` | Durably persist a batch (from the `session/flush` drain). Append-only; first event `seq` == stored next-seq after any repair; rejects non-JSON-serializable data naming the offending type. |
| `load(id): Promise<{ meta; events }>` | Reload meta + log. Preserves an interrupted (unclosed) final turn and closes it with synthetic closers — an error `tool/result` per unanswered `tool-call`, then `step/end?`+`turn/end {interrupted}` (a turn can be huge — never truncated); only a torn tail fragment is dropped. Events contiguous (`events[i].seq === i`); rejects a committed-region gap/parse error or unknown `version`. |
@@ -24,6 +25,8 @@ The persisted unit IS the existing `SessionEvent` (event-sourced model — the l
`PersistenceCoordinator` owns per-id state, write-behind buffers and serialization, the `session/event``session/flush` drain, lazy materialization, crash-tail repair, session adoption, and quiescent disposal. A first-party backend composes one, implements the small `PersistenceBackend` storage hook interface, and delegates its four public service methods. JSONL and SQLite therefore share lifecycle correctness while retaining different storage primitives; see the [coordinator RFC](../../../docs/rfc/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md).
The side-effect-free `locate` query remains backend-owned because it describes storage topology rather than write orchestration.
The `PersistenceBackend<TornMarker>` hooks (the only seam between the coordinator and storage):
| Hook | Role |
@@ -44,9 +47,9 @@ Import `runPersistenceContract` from `tests/contract.ts` (the public-API contrac
Three backends run these suites: an in-memory reference (in `tests/`), `dsh-session-persistence-jsonl` (append-only file log) and `dsh-session-persistence-sqlite` (`node:sqlite`, each `SessionEvent` one row `(session_id, seq, type, time, data, source_event_seqs, surface_op)`). All passing the same contract + coordinator suite is the proof that the seam is genuinely backend-agnostic — lazy materialization, crash-tail-on-load, and contiguous-seq hold identically over file bytes and over a transactional store.
## Metadata types
## Metadata and location types
Re-exported from `dsh-session`: `SessionHeader` (immutable session metadata: `version`, `id`, `createdAt`, `cwd?`, `parentSession?`, `seedLength?`).
Re-exported from `dsh-session`: `SessionHeader` (immutable session metadata: `version`, `id`, `createdAt`, `cwd?`, `parentSession?`, `seedLength?`). `SessionLocation` is `{ readonly kind: string; readonly path: string }`; its path is an absolute backend target, not proof that the artifact exists or contains an unflushed turn.
## Model Experience

View File

@@ -21,6 +21,18 @@ declare module 'cordis' {
}
}
/**
* A backend-resolved, per-session local artifact location. The path is an
* absolute target path and can name an artifact that has not materialized yet.
* Consumers must treat it as a location hint, never as an authorization token.
*/
export interface SessionLocation {
/** Backend-specific artifact kind, for example `jsonl`. */
readonly kind: string
/** Absolute path to this session's backend-owned artifact. */
readonly path: string
}
/**
* Durable append-only session storage. Implementations preserve contiguous,
* losslessly JSON-serializable events; {@link append} resolves only after
@@ -32,6 +44,15 @@ export abstract class SessionPersistence extends Service {
super(ctx, 'sessionPersistence')
}
/**
* Resolve this backend's independent local artifact for a session without
* reading, creating, flushing, or otherwise materializing it. Backends such
* as SQLite that do not own one artifact per session return `undefined`.
* @param meta - the immutable session header whose artifact is requested.
* @returns the backend-specific absolute location, when one exists.
*/
abstract locate(meta: SessionHeader): SessionLocation | undefined
/**
* Register a new session's metadata. A backend MAY defer the physical write
* until the first {@link append} (lazy materialization), in which case a

View File

@@ -41,6 +41,10 @@ class MemoryPersistence extends SessionPersistence implements PersistenceBackend
// --- service surface (delegated to the coordinator) ---
locate(_meta: SessionHeader): undefined {
return undefined
}
create(m: SessionHeader): Promise<void> {
return this.coordinator.create(m)
}

View File

@@ -34,6 +34,10 @@ class TestPersistence extends SessionPersistence {
this.afterList = undefined
}
locate(_meta: SessionHeader): undefined {
return undefined
}
create(meta: SessionHeader): Promise<void> {
TestPersistence.entries.set(meta.id, { meta: structuredClone(meta), events: [] })
return Promise.resolve()

View File

@@ -44,6 +44,10 @@ class TracePersistence extends SessionPersistence {
this.afterList = undefined
}
locate(_meta: SessionHeader): undefined {
return undefined
}
create(meta: SessionHeader): Promise<void> {
TracePersistence.entries.set(meta.id, { meta: structuredClone(meta), events: [] })
return Promise.resolve()

View File

@@ -12,7 +12,7 @@ Requires `ctx.skills` (`inject: ['skills']`).
| Field | Default | Meaning |
|---|---|---|
| `dshHome` | `$DSH_HOME` or `~/.dsh` | DeepSeek Harness config root; scans `skills` under this directory. |
| `dshHome` | `$DSH_HOME` or `~/.dsh` | DeepSeek Harness config root resolved by [`@deepseek-ai/dsh-home`](../../util/home/README.md); scans `skills` under this directory. |
| `agentsHome` | `$DSH_AGENTS_HOME` or `~/.agents` | Shared agent config root scanned for compatible skills. |
| `customSkillDirs` | `[]` | Additional local skill roots scanned after project roots and before user roots. |

View File

@@ -23,6 +23,7 @@
"license": "BSD-3-Clause",
"peerDependencies": {
"@deepseek-ai/dsh-fs": "^0.0.1",
"@deepseek-ai/dsh-home": "^0.0.1",
"@deepseek-ai/dsh-skill": "^0.0.1",
"cordis": "^4.0.0-rc.7"
},
@@ -32,6 +33,7 @@
},
"devDependencies": {
"@deepseek-ai/dsh-fs": "workspace:^",
"@deepseek-ai/dsh-home": "workspace:^",
"@deepseek-ai/dsh-skill": "workspace:^",
"cordis": "^4.0.0-rc.7"
}

View File

@@ -17,6 +17,7 @@ import z from 'schemastery'
import type Schema from 'schemastery'
import { parse as parseYaml } from 'yaml'
import type { FileSystem, FsDirEntry, FsTarget } from '@deepseek-ai/dsh-fs'
import { resolveDshHome } from '@deepseek-ai/dsh-home'
import {
isSkillName,
type SkillCandidate,
@@ -92,7 +93,7 @@ export class LocalSkillProvider implements SkillProvider {
private readonly customSkillDirs: string[]
constructor(private readonly ctx: Context, config: Config = {}) {
this.dshHome = resolve(config.dshHome ?? process.env.DSH_HOME ?? join(homedir(), '.dsh'))
this.dshHome = resolveDshHome(config.dshHome)
this.agentsHome = resolve(config.agentsHome ?? process.env.DSH_AGENTS_HOME ?? join(homedir(), '.agents'))
this.customSkillDirs = (config.customSkillDirs ?? []).map(root => resolve(root))
}

View File

@@ -9,6 +9,7 @@
{ "path": "../../../vendor/cosmokit" },
{ "path": "../../../vendor/cordis" },
{ "path": "../../../vendor/schemastery" },
{ "path": "../../util/home" },
{ "path": "../../fs/fs" },
{ "path": "../skill" }
]

View File

@@ -5,12 +5,15 @@ Zero-dependency primitives shared across the other groups. A package lands here
| Package | Role |
|---|---|
| `brand/` | The type-only `Branded<B>` nominal-typing primitive (no runtime code, no harness deps) |
| `home/` | Canonical `DSH_HOME` resolution from explicit config, environment, or `~/.dsh` (no harness deps) |
| `paths/` | Shared filesystem path constants and helpers for harness user data |
| `timeout/` | The timing/classification half of a timeout — `clampTimeout`/`deadline`/`timeoutOf`/`TimeoutReason` (pure functions, no harness deps); termination stays in each capability |
| `retention/` | Bounded model-facing output — `ItemRetainer`/`TextRetainer` + neutral notice helpers (pure, no harness deps); business semantics stay in each tool |
`dsh-brand` is the canonical case: it owns ONLY the `Branded<B>` helper, so a capability package can brand the ids it owns (`dsh-tasks`'s `TaskId`, `dsh-session`'s `SessionId`, …) by depending on `dsh-brand` alone, without pulling in an unrelated package just to reach `Branded`.
`dsh-home` gives every package the same configurable Harness home without assigning that cross-cutting fact to bash, skills, or a composition bundle. It resolves an explicit value before `$DSH_HOME`, falls back to `~/.dsh`, and returns an absolute path without caching, creating, or mutating anything.
`dsh-timeout` follows the same shape for the timeout family: `dsh-bash` and `dsh-web-fetch-local` each fuse a caller's cancellation with a deadline and later classify "timed out" vs "cancelled" by depending on `dsh-timeout` alone. It deliberately owns only the timing/classification half — the *termination* (SIGKILL a process group, tear down a fetch socket) stays in each capability, because no shared layer can own every capability's kill (see [the timeout-library RFC](../../docs/rfc/implemented/architecture/2026-07-06-timeout-deadline-library.md)).
`dsh-retention` is the same split for bounded tool output: a tool (`glob`/`grep`/`bash`/`web_fetch`/`web_search`) feeds items or text into a retainer and gets back what it kept and exactly what it omitted — while grouping, exit codes, provider errors, and recovery prose stay tool-owned. It deliberately owns only the retention mechanic; `truncated` is a budget fact, never an "incomplete inspection" state (see [the retention-library RFC](../../docs/rfc/implemented/architecture/2026-07-06-tool-result-retention-library.md)).

View File

@@ -0,0 +1,17 @@
# @deepseek-ai/dsh-home
`@deepseek-ai/dsh-home` is the single owner of DeepSeek Harness home-directory resolution. `resolveDshHome(configured?)` returns an absolute path using this precedence:
1. The explicit `configured` path.
2. The `DSH_HOME` environment variable.
3. The `.dsh` directory under the current user's home directory.
The resolver reads its inputs at call time. It does not cache a result, create the directory, or mutate `process.env`; consumers keep ownership of their own configuration fields and pass the configured value when resolving the shared home.
## Model Experience
Indirectly, through `dsh-tool-bash`, which exposes the resolved path to model bash as `DSH_HOME` without adding a prompt section.
## Known Limitations and Deferred Work
- **Resolution only** — the resolver makes a path absolute but does not create it, check access, or canonicalize symlinks; each consumer owns those filesystem decisions.

View File

@@ -0,0 +1,30 @@
{
"name": "@deepseek-ai/dsh-home",
"description": "Canonical DeepSeek Harness home-directory resolver",
"version": "0.0.1",
"private": true,
"type": "module",
"main": "lib/index.js",
"types": "lib/types/index.d.ts",
"exports": {
".": {
"types": "./lib/types/index.d.ts",
"default": "./lib/index.js"
},
"./src/*": "./src/*",
"./package.json": "./package.json"
},
"files": [
"lib/index.js",
"lib/types/**/*.d.ts",
"lib/types/**/*.d.ts.map",
"src"
],
"license": "BSD-3-Clause",
"peerDependencies": {
"cordis": "^4.0.0-rc.6"
},
"devDependencies": {
"cordis": "^4.0.0-rc.6"
}
}

View File

@@ -0,0 +1,23 @@
/**
* Canonical DeepSeek Harness home-directory resolution.
*
* @module @deepseek-ai/dsh-home
*/
import { homedir } from 'node:os'
import { join, resolve } from 'node:path'
const DEFAULT_DSH_HOME_DIRNAME = '.dsh'
/** Environment variable that overrides the default Harness home directory. */
export const DSH_HOME_ENV = 'DSH_HOME' as const
/**
* Resolve the DeepSeek Harness home directory without caching or mutating the environment.
*
* @param configured - Optional configured path, which takes precedence over the environment.
* @returns The absolute configured path, `$DSH_HOME`, or `~/.dsh`, in that order.
*/
export function resolveDshHome(configured?: string): string {
return resolve(configured ?? process.env[DSH_HOME_ENV] ?? join(homedir(), DEFAULT_DSH_HOME_DIRNAME))
}

View File

@@ -0,0 +1,26 @@
import { homedir } from 'node:os'
import { join, resolve } from 'node:path'
import { afterEach, describe, expect, it, vi } from 'vitest'
import { DSH_HOME_ENV, resolveDshHome } from '@deepseek-ai/dsh-home'
afterEach(() => vi.unstubAllEnvs())
describe('resolveDshHome', () => {
it('prefers an explicit configured path and resolves it absolutely', () => {
vi.stubEnv(DSH_HOME_ENV, './environment-home')
expect(resolveDshHome('./configured-home')).toBe(resolve('./configured-home'))
})
it('uses DSH_HOME when no configured path is supplied', () => {
vi.stubEnv(DSH_HOME_ENV, './environment-home')
expect(resolveDshHome()).toBe(resolve('./environment-home'))
})
it('defaults to the .dsh directory under the user home', () => {
vi.stubEnv(DSH_HOME_ENV, undefined)
expect(resolveDshHome()).toBe(join(homedir(), '.dsh'))
})
})

View File

@@ -0,0 +1,9 @@
{
"extends": "../../../tsconfig.base.json",
"compilerOptions": {
"rootDir": "src",
"outDir": "lib/types"
},
"include": ["src"],
"references": []
}