feat(bash): generalize managed shell environment

This commit is contained in:
Yichen Jiang
2026-07-12 15:41:42 +08:00
parent acdbe7b828
commit df9617aaff
40 files changed
+790 -197

No files matched your search

+1 -1
View File
@@ -22,7 +22,7 @@ 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. 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/namespace scrub** — start with `process.env` minus credential-shaped vars (`*KEY*`/`*SECRET*`/`*TOKEN*`) and every `DSH_*`, then apply `NO_COLOR=1 TERM=dumb PAGER=cat GIT_PAGER=cat`. Ordinary spec `env` is merged next and may restore caller-held credential-shaped values, but is rejected if it tries to set reserved `DSH_*`; the trusted spec `dshEnv` snapshot is merged last. This keeps ambient secrets out and prevents a nested/previous harness identity from surviving when the current registry omits it. The spec's `stdin`, when supplied, is written to the child and closed; with none supplied, fd 0 is `/dev/null`. 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).
- **Background tasks** — `start()` returns immediately, no timeout applies (Claude Code detaches timeouts when backgrounding), `readOutput()` is incremental with whole-stream byte offsets, and disposal kills everything. The spec's opaque `owner` token is stored on the tracked task and returned by `ownerOf(id)` — the executor never interprets it (the consumer's access policy does), and because it lives with the task here it survives a `tool-bash` HMR reload.
## Sandboxing
+5 -2
View File
@@ -126,10 +126,11 @@ export class LocalBashExecutor extends BashExecutor {
workdir: request.workdir ?? this.config.cwd ?? process.cwd(),
timeoutMs,
...request.signal ? { signal: request.signal } : {},
// Carry stdin/env through verbatim — optional, no config default (absent
// means none). env merges AFTER the scrub 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 } : {},
...request.dshEnv !== undefined ? { dshEnv: request.dshEnv } : {},
// Carry the owner through verbatim (required-but-nullable on the spec):
// the executor never interprets it — the consumer's access policy does.
owner: request.owner,
@@ -153,6 +154,7 @@ export class LocalBashExecutor extends BashExecutor {
signal: d.signal,
stdin: spec.stdin,
env: spec.env,
dshEnv: spec.dshEnv,
}, this.internals).done
// Classify the FIRST abort reason: a BASH_TIMEOUT TimeoutReason means our
// timeout cut the command short; any other abort — an upstream cancel, or a
@@ -179,6 +181,7 @@ export class LocalBashExecutor extends BashExecutor {
signal: spec.signal,
stdin: spec.stdin,
env: spec.env,
dshEnv: spec.dshEnv,
}, this.internals)
const id = BashTaskId(`bash-${this.nextTaskId++}`)
+27 -21
View File
@@ -27,7 +27,7 @@ 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 type { CollectedOutput, DshEnvironment } from '@deepseek-ai/dsh-bash'
/**
* Model-friendly environment overrides: disable colors, pagers, and
@@ -50,27 +50,33 @@ export const ENV_OVERRIDES = {
export const SENSITIVE_ENV_PATTERN = /KEY|SECRET|TOKEN/i
/**
* `process.env` minus credential-shaped vars, plus the model-friendly
* overrides, plus any caller-supplied `extra` entries.
* Build a child environment from scrubbed ambient values, terminal overrides,
* ordinary caller entries, and a trusted managed `DSH_*` snapshot.
*
* Layering matters: the scrub drops `process.env` credentials, then
* `ENV_OVERRIDES` forces the model-friendly terminal vars, then `extra` is
* merged LAST so an explicit caller entry wins even when its name matches the
* scrub pattern (the scrub is the control that stops the HARNESS's ambient
* credentials leaking into a spawned command; a caller that explicitly sets a
* var named a value it already holds, not that ambient secret). `extra` is set
* by in-process plugins (the hooks bridges), not the model — `dsh-tool-bash`
* builds its request from named fields only and does not forward model input
* here (see its README, § "The tool builds its request from named args only").
* @param extra - caller-supplied entries merged last; an explicit entry wins even against the scrub and the overrides.
* Ambient credentials and all ambient `DSH_*` are removed first;
* `ENV_OVERRIDES` then forces model-friendly terminal values, ordinary `extra`
* follows, and `dshEnv` merges last. Ordinary `extra` may restore a
* credential-shaped name whose value the caller already holds, but cannot set
* the managed namespace. `dsh-tool-bash` builds both channels from trusted
* named fields and never forwards model-provided environment objects.
* @param extra - ordinary caller-supplied entries; `DSH_*` names are rejected.
* @param dshEnv - trusted managed `DSH_*` entries for the current execution.
* @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[key] = value
}
return { ...env, ...ENV_OVERRIDES, ...extra }
for (const key of Object.keys(extra ?? {})) {
if (key.startsWith('DSH_')) {
throw new Error(`ordinary bash env cannot set reserved variable "${key}"; use dshEnv`)
}
}
return { ...env, ...ENV_OVERRIDES, ...extra, ...dshEnv }
}
/** What to run and under which limits (resolved — no defaults in here). */
@@ -96,12 +102,12 @@ 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 `DSH_*` entries merged after ambient `DSH_*` removal. */
dshEnv?: DshEnvironment | undefined
}
/**
@@ -346,7 +352,7 @@ export function runBash(spec: SpawnSpec, internals: RunInternals = {}): RunningB
// typed `spawn` overload infer non-null stdout/stderr, which the
// `ChildProcessByStdio` annotation captures (stdin `Writable | null`; stdout/
// stderr the non-null `Readable` the collectors attach to without a cast).
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 })
+18 -10
View File
@@ -136,21 +136,28 @@ 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][$DSH_SEAM_VAR]"',
stdin: 'piped\n',
env: { SEAM_VAR: 'env-ok' },
dshEnv: { DSH_SEAM_VAR: 'dsh-ok' },
})
// resolve() keeps the optional input/environment fields verbatim.
expect(spec.stdin).toBe('piped\n')
expect(spec.env).toEqual({ DSH_SEAM_VAR: 'env-ok' })
expect(spec.env).toEqual({ SEAM_VAR: 'env-ok' })
expect(spec.dshEnv).toEqual({ DSH_SEAM_VAR: 'dsh-ok' })
const result = await bash.run(spec)
expect(result.stdout.text).toBe('piped\n[env-ok]\n')
expect(result.stdout.text).toBe('piped\n[env-ok][dsh-ok]\n')
})
it('resolve() omits stdin/env when the request supplies neither', async () => {
it('resolve() omits stdin/env/dshEnv when the request supplies none', async () => {
const { bash } = await setup()
const spec = bash.resolve({ command: 'true' })
expect('stdin' in spec).toBe(false)
expect('env' in spec).toBe(false)
expect('dshEnv' in spec).toBe(false)
})
})
@@ -177,14 +184,15 @@ describe('LocalBashExecutor background tasks', () => {
await Promise.all([first.done, second.done])
})
it('threads stdin and extra env into a background task', async () => {
it('threads stdin, ordinary env, and managed env into a background task', async () => {
const { bash } = await setup()
const task = bash.start(bash.resolve({
command: 'cat; echo "[$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 read = await readUntil(bash, task.id, '[bg-env]')
const read = await readUntil(bash, task.id, '[bg-env][bg-dsh-env]')
expect(read.delta).toContain('bg-stdin')
await task.done
expect(task.exitCode).toBe(0)
+25 -8
View File
@@ -201,19 +201,19 @@ 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')
})
@@ -361,13 +361,13 @@ describe('abort edge cases', () => {
})
describe('review fixes: env scrubbing and spill 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}|${DSH_TEST_PLAIN:-absent}]"')).done
expect(result.stdout.text.trim()).toBe('[absent|absent|visible]')
expect(result.stdout.text.trim()).toBe('[absent|absent|absent]')
} finally {
delete process.env.DSH_TEST_API_KEY
delete process.env.DSH_TEST_TOKEN
@@ -375,6 +375,23 @@ describe('review fixes: env scrubbing and spill hardening', () => {
}
})
it('injects only the current trusted DSH environment after scrubbing ambient values', async () => {
process.env.DSH_STALE = 'old-value'
try {
const result = await runBash(spec('echo "[${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('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', { maxOutputBytes: 500 }),
+2 -2
View File
@@ -30,8 +30,8 @@ Implementations subclass `BashExecutor`, implement the abstract methods, and cal
## Vocabulary
`BashExecRequest` (command, workdir?, timeoutMs?, signal?, stdin?, env?, owner?, sandboxMode?) resolves to `BashExecSpec` (command, workdir, timeoutMs, signal?, stdin?, env?, owner, sandboxMode) before execution; `owner` and `sandboxMode` are optional on the request and **required-but-nullable** on the resolved spec, so a forgotten one is a visible `undefined` rather than a silently-absent property. `sandboxMode` is the explicit per-call sandbox-policy input: an escalation grant a human just issued ([the sandbox RFC § Escalation](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md), which outranks) or the session's standing override ([the sandbox RFC § Per-session mode switching](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md)); a sandboxing executor's `resolve()` stamps its configured default when the request carries none, and a non-sandboxing executor carries the field verbatim and confines nothing.
`BashExecRequest` (command, workdir?, timeoutMs?, signal?, stdin?, env?, dshEnv?, owner?, sandboxMode?) resolves to `BashExecSpec` (command, workdir, timeoutMs, signal?, stdin?, env?, dshEnv?, owner, sandboxMode) before execution; `owner` and `sandboxMode` are optional on the request and **required-but-nullable** on the resolved spec, so a forgotten one is a visible `undefined` rather than a silently-absent property. `sandboxMode` is the explicit per-call sandbox-policy input: an escalation grant a human just issued ([the sandbox RFC § Escalation](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md), which outranks) or the session's standing override ([the sandbox RFC § Per-session mode switching](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md)); a sandboxing executor's `resolve()` stamps its configured default when the request carries none, and a non-sandboxing executor carries the field verbatim and confines nothing.
The seam also owns the per-session mode override vocabulary (the sandbox RFC § Per-session mode switching): the log-only `'bash/sandbox-mode'` session event, the pure fold `effectiveSandboxMode(events)` (last event wins; `undefined` means "apply the executor default"), and THE write path `setSandboxMode(session, mode)` — the session log is the store, so an override survives restart by replay and two sessions can never see each other's mode. Writers must respect turn-enclosure: the ACP bridge anchors an idle switch at the next turn rather than appending between turns. The task id (`BashTaskId`) and the `owner` token (`OwnerToken`) are [branded](../../util/brand) — `OwnerToken` is a DISTINCT brand from `SessionId` (the seam never imports `dsh-session`; the `dsh-tool-bash` consumer is the single boundary that casts its `SessionId` into one). `run()` returns `BashRunResult` (exitCode, signal, timedOut, aborted, timeoutMs, stdout/stderr as `CollectedOutput`) and `start()`/`readOutput()` use `BashTask`/`BashTaskRead` for the background side. A sandboxing executor additionally stamps `sandbox` result facts on results and settled tasks (`BashSandboxInfo`: the mode it executed under, the conservative `denied` classification, and — for confined modes — the backend's `enforcement` completeness); the mode/enforcement vocabulary is owned by the [`dsh-sandbox`](../../sandbox/sandbox/) seam, and the facts are documented in [core-data-structures/bash.md](../../../docs/core-data-structures/bash.md). See `src/types.ts` for the full contracts.
`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 (unlike `owner`'s required-but-nullable): a missing one means "none", the safe default. 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 `DSH_*` keys; model bash uses it for the current snapshot collected by `ctx.bashEnv`. Implementations remove inherited `DSH_*`, 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).
+1
View File
@@ -30,6 +30,7 @@ export type {
BashTaskRead,
BashTaskStatus,
CollectedOutput,
DshEnvironment,
} from './types.ts'
declare module 'cordis' {
+20 -12
View File
@@ -12,6 +12,9 @@ import type { SandboxEnforcement, SandboxMode } from '@deepseek-ai/dsh-sandbox'
/** Identifies one background task within an executor (generated `bash-N`). */
export type BashTaskId = Branded<'BashTaskId'>
/** Trusted DeepSeek Harness variables for one bash execution. */
export type DshEnvironment = Readonly<Record<`DSH_${string}`, string>>
/**
* Brand a string as a {@link BashTaskId}.
* @param id - the raw task-id string (the executor generates `bash-N`).
@@ -106,15 +109,19 @@ 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.
*/
dshEnv?: DshEnvironment | undefined
/**
* Opaque OWNER token for a background task — the consumer's isolation key
* (the tool layer passes the owning agent's `session.header.id`). The
@@ -163,13 +170,14 @@ export interface BashExecSpec {
*/
stdin?: string | undefined
/**
* Extra environment entries, carried through verbatim from
* {@link BashExecRequest.env} and merged by the implementation AFTER its
* credential scrub (an explicit entry wins even when its name matches the
* scrub pattern). OPTIONAL on the spec for the same reason as `stdin` — no
* config default, absent means "no extra env".
* 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
/** Trusted `DSH_*` snapshot carried through from {@link BashExecRequest.dshEnv}. */
dshEnv?: DshEnvironment | undefined
/**
* Opaque owner token, REQUIRED-but-nullable (mirrors `workdir`/`timeoutMs`
* being required on the resolved spec): {@link BashExecutor.resolve} carries
+19 -4
View File
@@ -22,11 +22,26 @@ The plugin also contributes the `tool:bash` prompt section (order 105) — the c
`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()`.
### Session identity environment
### Managed shell environment
Every foreground and background call made for an agent receives `DSH_SESSION_ID=agent.session.header.id`. When the active persistence backend locates a JSONL artifact, the call also receives `DSH_SESSION_JSONL=<absolute target path>`; absent persistence and non-file backends still provide the id but omit the JSONL variable. The path is a location hint: lazy materialization means it may not exist on the first turn, and during an open turn it can omit buffered events that have not reached `session/flush`. Neither value is an authorization credential.
Every foreground and background model bash call receives a newly collected trusted `DSH_*` environment. `DSH_HOME` is the absolute Harness home (`dshHome` config, then ambient `$DSH_HOME`, then `~/.dsh`) and `DSH_SHELL=1` identifies the managed child. Agent calls additionally receive `DSH_SESSION_ID=agent.session.header.id`; when the active persistence seam locates a JSONL artifact they also receive `DSH_SESSION_JSONL=<absolute target path>`. The JSONL path is a location hint: it may not exist before the first flush or contain the current buffered turn, and it is not an authorization credential.
The overlay is computed from `ToolExecution.agent` for each call and passed through `BashExecRequest.env`; `process.env` is never modified, so concurrent parent/child agents keep separate values. The tool description names both variables so the model can inspect them without a permanent system-prompt section.
`ctx.bashEnv` owns collection. Other plugins can register an effect-scoped contributor with a stable name, declared keys/descriptions, and `resolve(execution: ToolExecution)`; duplicate ownership and undeclared runtime keys fail loudly, while `list()` enumerates declarations without executing providers. Harness built-ins reserve `DSH_HOME`, `DSH_SHELL`, and `DSH_SESSION_ID`; tool-bash's persistence translator owns `DSH_SESSION_JSONL` by reading the backend-neutral `sessionPersistence.locate()` seam.
```ts
import type { Context } from 'cordis'
import type {} from '@deepseek-ai/dsh-tool-bash'
export function apply(ctx: Context): void {
ctx.bashEnv.register({
name: 'deployment-region',
variables: { DSH_DEPLOYMENT_REGION: { description: 'Current deployment region.' } },
resolve: execution => execution.agent === undefined ? {} : { DSH_DEPLOYMENT_REGION: 'cn-north' },
})
}
```
The overlay is computed from the current `ToolExecution` and passed through the dedicated `BashExecRequest.dshEnv` channel. The local executor removes all inherited `DSH_*` before merging that snapshot, so nested harnesses and concurrent parent/child agents cannot leak stale identities. `process.env` is never modified. The tool description teaches the generic `$DSH_*` convention rather than naming persistence-specific variables or adding a permanent system-prompt section.
Result text: stdout, then a `[stderr]` section, then status markers — `[sandbox: file access denied under <mode> mode]` when a sandboxing executor classified the failure as a policy denial (reported first so `[exit code: N]` stays the last line; the static description tells the model a denial is policy, not a command bug, and forbids retrying around it), `[timed out after Nms]` whenever the executor's timer fired (reported independently of how the process ended, so a command that traps SIGTERM and exits 0 still shows it), `[killed by signal: …]` for a signal death, `[exit code: N]` for a non-zero exit (reported, **not** `isError`: the model decides how to react), and `[output truncated; full output: <path>]` when the tail was kept and a safe spill file is available. If the executor knows output was dropped but cannot safely advertise a complete spill file, the path is reported as `(unavailable)`. Only infrastructure failures (spawn errors, aborts) surface as `isError` results.
@@ -52,7 +67,7 @@ When a background task finishes, a short notice is injected into the owning agen
## The tool builds its request from named args only
The `BashExecRequest` seam carries optional `stdin` and `env`, used by trusted consumers. This tool does **not** expose them as model parameters: it builds the request from named schema fields and adds only the session overlay above, so model-supplied `env`/`stdin` keys are ignored and cannot replace the trusted values. This is not a trust boundary — a model already has equivalent power through shell syntax (`FOO=bar cmd`, a heredoc), and the real defense against leaking ambient secrets is `dsh-bash-local`'s credential scrub. Regression guards assert extra model fields never enter the request while the trusted overlay still does. See [the bash-stdin-env RFC](../../../docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md).
The `BashExecRequest` seam carries optional `stdin` and ordinary `env` for in-process consumers plus the harness-owned `dshEnv` channel above. This tool does **not** expose any of them as model parameters: it builds the request from named schema fields, so model-supplied `env`/`stdin` keys are ignored and cannot replace the managed values. A model already has equivalent command-local power through shell syntax (`FOO=bar cmd`, a heredoc); ambient-secret protection comes from `dsh-bash-local`'s credential scrub, while `dshEnv` ownership prevents stale or spoofed Harness context. See [the bash-stdin-env RFC](../../../docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md).
## Permissions and escalation
+3
View File
@@ -32,6 +32,9 @@
"@deepseek-ai/dsh-tools": "^0.0.1",
"cordis": "^4.0.0-rc.6"
},
"dependencies": {
"schemastery": "^3.18.0"
},
"devDependencies": {
"@deepseek-ai/dsh-agent": "workspace:^",
"@deepseek-ai/dsh-agent-loop": "workspace:^",
+192 -24
View File
@@ -55,8 +55,10 @@
* @module @deepseek-ai/dsh-tool-bash
*/
import type { Context } from 'cordis'
import { isAbsolute, resolve as resolvePath } from 'node:path'
import { Service, type Context } from 'cordis'
import z from 'schemastery'
import { homedir } from 'node:os'
import { isAbsolute, join, 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'
@@ -69,11 +71,178 @@ import type {} from '@deepseek-ai/dsh-system-prompt'
import type {} from '@deepseek-ai/dsh-user-approval'
import type { SandboxMode } from '@deepseek-ai/dsh-sandbox'
import { BashTaskId, OwnerToken, effectiveSandboxMode } from '@deepseek-ai/dsh-bash'
import type { BashRunResult, BashTask, CollectedOutput } from '@deepseek-ai/dsh-bash'
import type { BashRunResult, BashTask, CollectedOutput, DshEnvironment } from '@deepseek-ai/dsh-bash'
declare module 'cordis' {
interface Context {
bashEnv: BashEnvRegistry
}
}
export const name = 'tool-bash'
export const inject = ['tools', 'bash', 'systemPrompt']
/** Configuration for the bash tool and its managed child environment. */
export interface Config {
/** DeepSeek Harness home directory exposed as `DSH_HOME`; defaults to `$DSH_HOME` or `~/.dsh`. */
dshHome?: string
}
/** Runtime configuration schema for the bash tool plugin. */
export const Config: z<Config> = z.object({
dshHome: z.string(),
})
/** Model-visible metadata for one managed `DSH_*` environment variable. */
export interface BashEnvVariable {
/** Concise description of the environment fact represented by the variable. */
description: string
}
/**
* A plugin contribution to the managed environment of each model bash call.
* Declared keys make ownership conflicts detectable before the first command;
* `resolve` computes only the values available for the current execution.
*/
export interface BashEnvContributor {
/** Stable contributor name used in diagnostics and duplicate detection. */
name: string
/** Complete set of `DSH_*` keys this contributor may return. */
variables: Readonly<Record<`DSH_${string}`, 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<`DSH_${string}`, string>>>
}
/** An enumerable declaration returned by {@link BashEnvRegistry.list}. */
export interface BashEnvVariableInfo extends BashEnvVariable {
/** Contributor that owns the variable. */
contributor: string
/** Declared `DSH_*` environment variable name. */
key: `DSH_${string}`
}
const RESERVED_BASH_ENV_KEYS = new Set<`DSH_${string}`>([
'DSH_HOME',
'DSH_SHELL',
'DSH_SESSION_ID',
])
const BASH_ENV_KEY = /^DSH_[A-Z][A-Z0-9_]*$/
/**
* 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<`DSH_${string}`, string>()
private readonly dshHome: string
/**
* Create and install the `ctx.bashEnv` service.
* @param ctx - Cordis context that owns the service and registrations.
* @param config - home-directory configuration for the built-in variables.
*/
constructor(ctx: Context, config: Config = {}) {
super(ctx, 'bashEnv')
this.dshHome = resolvePath(config.dshHome ?? process.env.DSH_HOME ?? join(homedir(), '.dsh'))
}
/**
* Register one environment contributor. Names and keys are unique; built-in
* keys are reserved. Registration is disposed with the calling plugin fiber.
* @param contributor - declared key ownership and per-execution resolver.
* @returns the disposer that unregisters the contribution.
*/
register(contributor: BashEnvContributor): () => void {
const dispose = this.ctx.effect(function* (this: BashEnvRegistry) {
if (contributor.name.trim().length === 0) {
throw new Error('bash env contributor name must be non-empty')
}
if (this.contributors.has(contributor.name)) {
throw new Error(`bash env contributor "${contributor.name}" is already registered`)
}
const variables = Object.entries(contributor.variables) as [`DSH_${string}`, BashEnvVariable][]
for (const [key, variable] of variables) {
if (!BASH_ENV_KEY.test(key)) {
throw new Error(`bash env contributor "${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<`DSH_${string}`, string> = {
DSH_HOME: this.dshHome,
DSH_SHELL: '1',
}
if (execution.agent !== undefined) {
values.DSH_SESSION_ID = execution.agent.session.header.id
}
for (const contributor of [...this.contributors.values()].sort((left, right) => left.name.localeCompare(right.name))) {
const resolved = contributor.resolve(execution)
for (const [rawKey, value] of Object.entries(resolved)) {
const key = rawKey as `DSH_${string}`
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))))
}
/**
* 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 `DSH_${string}`,
})))
.sort((left, right) => left.key.localeCompare(right.key))
}
}
/**
* Validate the constraints the SchemaSpec can't express. `defineTool` now
* validates parsed args against the SchemaSpec before `execute` runs (the
@@ -168,8 +337,7 @@ function bashDescription(escalationModes: readonly SandboxMode[]): string {
const base = 'Execute a bash command (`bash -c`) and return its stdout/stderr. '
+ 'Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — '
+ 'pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. '
+ 'The current agent session id is available as `$DSH_SESSION_ID`; when JSONL persistence is configured, '
+ '`$DSH_SESSION_JSONL` is its absolute target path and may not exist or contain the current unflushed turn yet. '
+ 'Current harness environment facts are exposed through managed `$DSH_*` 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 (a background task reports the same marker via bash_output once it has finished). '
+ 'Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. '
+ 'Set `run_in_background: true` for long-running commands: the call returns a task id immediately; '
@@ -397,22 +565,6 @@ function resolveWorkdir(modelWorkdir: string | undefined, exec: { agent?: Agent
return modelWorkdir
}
/**
* Build the trusted per-execution session environment. Identity always comes
* from the calling agent's immutable session header; an optional JSONL path
* comes from the active persistence backend's side-effect-free locator. A
* non-agent caller has no current session, so it receives neither variable.
*/
function sessionEnvironment(ctx: Context, exec: { agent?: Agent }): Record<string, string> | undefined {
const agent = exec.agent
if (agent === undefined) return undefined
const env: Record<string, string> = { DSH_SESSION_ID: agent.session.header.id }
const location = ctx.get('sessionPersistence')?.locate(agent.session.header)
if (location?.kind === 'jsonl') env.DSH_SESSION_JSONL = location.path
return env
}
/** Status line for background task reads. */
function statusLine(task: BashTask): string {
switch (task.status) {
@@ -422,7 +574,23 @@ function statusLine(task: BashTask): string {
}
}
export function apply(ctx: Context): void {
export function apply(ctx: Context, config: Config = {}): void {
const bashEnv = new BashEnvRegistry(ctx, config)
bashEnv.register({
name: 'session-persistence',
variables: {
DSH_SESSION_JSONL: {
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: location.path } : {}
},
})
// The bash tools' cross-call HABIT, which the per-tool descriptions cannot
// carry (they describe one call each): the exit-code marker is only useful
// if the model actually checks it every time.
@@ -614,13 +782,13 @@ export function apply(ctx: Context): void {
// session runs in its own workspace (see resolveWorkdir); an explicit
// model workdir still wins.
const workdir = resolveWorkdir(args.workdir, exec)
const env = sessionEnvironment(ctx, exec)
const dshEnv = bashEnv.collect(exec)
const request = {
command: args.command,
...workdir !== undefined ? { workdir } : {},
...args.timeoutMs !== undefined ? { timeoutMs: args.timeoutMs } : {},
...exec.signal ? { signal: exec.signal } : {},
...env !== undefined ? { env } : {},
dshEnv,
...sandboxMode !== undefined ? { sandboxMode } : {},
}
if (args.run_in_background === true) {
@@ -0,0 +1,189 @@
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 {
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')
})
})
@@ -1,4 +1,4 @@
import { afterEach, describe, expect, it } from 'vitest'
import { afterEach, describe, expect, it, vi } from 'vitest'
import { Context } from 'cordis'
import { existsSync, mkdtempSync, readFileSync, rmSync } from 'node:fs'
import { tmpdir } from 'node:os'
@@ -21,7 +21,7 @@ import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent
* through the agent loop, exercising the same seams a live model would
* (tool/call + tool/result session events, agent.inject notifications).
*/
async function harness(adapter: MockAdapter, sessionRoot?: string) {
async function harness(adapter: MockAdapter, sessionRoot?: string, dshHome?: string) {
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(SessionStore)
@@ -31,13 +31,16 @@ async function harness(adapter: MockAdapter, sessionRoot?: string) {
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [] })
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(() => { for (const dir of dirs.splice(0)) rmSync(dir, { recursive: true, force: true }) })
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) => {
@@ -79,14 +82,16 @@ 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\' "$DSH_SESSION_ID" "$DSH_SESSION_JSONL"; if [ -e "$DSH_SESSION_JSONL" ]; then printf \'present\\n\'; else printf \'absent\\n\'; fi',
command: 'printf \'%s\\n%s\\n%s\\n%s\\n%s\\n\' "$DSH_HOME" "$DSH_SHELL" "$DSH_SESSION_ID" "$DSH_SESSION_JSONL" "${DSH_STALE_PARENT-unset}"; if [ -e "$DSH_SESSION_JSONL" ]; then printf \'present\\n\'; else printf \'absent\\n\'; fi',
description: 'inspect session environment',
}),
textResponse('Session environment inspected.'),
])
const ctx = await harness(adapter, root)
const ctx = await harness(adapter, root, dshHome)
const handle = ctx.agents.create({
agentId: AgentId('session-env'),
sessionId: SessionId('session-env-id'),
@@ -100,7 +105,7 @@ describe('bash tool through the agent loop', () => {
await waitForIdle(ctx, agent)
const result = findEvent(events(agent), 'tool/result')
expect(resultText(result)).toBe(`session-env-id\n${location?.path}\nabsent\n`)
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' })
+27 -11
View File
@@ -892,6 +892,8 @@ 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`
@@ -899,7 +901,7 @@ describe('the model-facing bash tool builds its request from named args only (no
* model that power), so it must build its request from named args only and
* never spread unknown tool-call keys into it. This guard's job is to catch a
* future refactor that blindly forwards `...args` — which would silently thread
* model input into the post-scrub `env` merge — NOT to defend a trust boundary
* model input into the ordinary `env` channel — NOT to defend a trust boundary
* (the credential scrub in dsh-bash-local is the security control; see the
* bash-stdin-env RFC). Foreground `run()` returns a canned result; `start()` is
* unused here.
@@ -915,6 +917,7 @@ 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 } : {},
owner: request.owner,
sandboxMode: request.sandboxMode,
}
@@ -943,15 +946,15 @@ describe('the model-facing bash tool builds its request from named args only (no
await ctx.plugin(SessionPersistenceJsonl, { root: join(spillDir, 'jsonl') })
}
await ctx.plugin(RecordingBashExecutor)
await ctx.plugin(ToolBash)
await ctx.plugin(ToolBash, { dshHome: recordingDshHome })
return { ctx, bash: ctx.bash as RecordingBashExecutor }
}
it('describes the trusted session variables to the model', async () => {
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_SESSION_ID')
expect(description).toContain('DSH_SESSION_JSONL')
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 () => {
@@ -966,9 +969,11 @@ describe('the model-facing bash tool builds its request from named args only (no
agent,
})
expect(bash.requests[0]?.env).toEqual({
expect(bash.requests[0]?.dshEnv).toEqual({
DSH_HOME: recordingDshHome,
DSH_SESSION_ID: 'request-fg',
DSH_SESSION_JSONL: path,
DSH_SHELL: '1',
})
})
@@ -989,13 +994,16 @@ describe('the model-facing bash tool builds its request from named args only (no
agent,
})
expect(bash.requests[0]?.env).toEqual({
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 only the stable session id when no JSONL locator is available', async () => {
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
@@ -1007,7 +1015,11 @@ describe('the model-facing bash tool builds its request from named args only (no
agent,
})
expect(bash.requests[0]?.env).toEqual({ DSH_SESSION_ID: 'request-id-only' })
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)
})
@@ -1025,17 +1037,21 @@ describe('the model-facing bash tool builds its request from named args only (no
})
}
expect(bash.requests.map(request => request.env)).toEqual([
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]?.env?.DSH_SESSION_JSONL).not.toBe(bash.requests[1]?.env?.DSH_SESSION_JSONL)
expect(bash.requests[0]?.dshEnv?.DSH_SESSION_JSONL).not.toBe(bash.requests[1]?.dshEnv?.DSH_SESSION_JSONL)
})
it('does not forward env/stdin even when the model includes them as extra arguments', async () => {