Merge origin/master into codex/truncated-design

This commit is contained in:
Dudu-0223
2026-07-17 18:21:54 +08:00
1057 files changed
+42961 -18526

No files matched your search

+22 -134
View File
@@ -1,34 +1,23 @@
/**
* The bash executor seam (`ctx.bash`): an abstract service defining WHAT a
* bash backend does — run commands, manage background tasks — without saying
* HOW. Implementations subclass {@link BashExecutor} and register themselves
* as the `bash` service; `@deepseek-ai/dsh-bash-local` (local subprocesses)
* is the first. Future implementations swap in sandboxes, containers, or
* remote exec servers without touching the tool schemas that consume them
* (`@deepseek-ai/dsh-tool-bash`).
*
* The split mirrors the LLM seam (`LlmService`/`LlmAdapter`) and the
* surveyed agents: pi hides execution behind a `BashOperations` interface
* (local shell / SSH / VM backends), Codex behind an exec-server protocol.
*
* The `ctx.bash` executor seam for foreground commands and background process
* handles. Task ids, ownership, polling, and notices belong to
* `@deepseek-ai/dsh-tasks`, keeping executors independent of sessions.
* @module @deepseek-ai/dsh-bash
*/
import { Context, Service } from 'cordis'
import type { SandboxMode } from '@deepseek-ai/dsh-sandbox'
import type { BashExecRequest, BashExecSpec, BashRunResult, BashTask, BashTaskId, BashTaskListener, BashTaskRead, OwnerToken } from './types.ts'
import type { BashExecRequest, BashExecSpec, BashProcess, BashRunResult } from './types.ts'
export { BashTaskId, OwnerToken } from './types.ts'
export { SANDBOX_MODES, effectiveSandboxMode, setSandboxMode } from './session-mode.ts'
export type {
BashExecRequest,
BashExecSpec,
BashProcess,
BashProcessRead,
BashProcessStatus,
BashRunResult,
BashSandboxInfo,
BashTask,
BashTaskListener,
BashTaskRead,
BashTaskStatus,
CollectedOutput,
} from './types.ts'
@@ -44,58 +33,32 @@ declare module 'cordis' {
* implementation per context; loading a second throws, which is cordis'
* standard duplicate-service behavior).
*
* Semantics every implementation must honor:
* - {@link run} REJECTS only for infrastructure failures (unusable workdir,
* missing shell, pre-aborted signal). Nonzero exits, timeout kills, and
* abort kills RESOLVE with a descriptive {@link BashRunResult} — reporting
* a failed command is the tool layer's job, not an exception.
* Implementations must honor these semantics:
* - {@link run} rejects only for infrastructure failures. Nonzero exits,
* timeout kills, and abort kills resolve with a {@link BashRunResult}.
* - {@link start} returns immediately; no timeout applies to background
* tasks (callers stop them via {@link kill} or the spec's AbortSignal).
* Completion must fire the {@link onTaskDone} listeners exactly once per
* task, and must NOT fire after the service is disposed.
* - {@link readOutput} is incremental: consecutive reads never re-deliver
* output. Implementations bound their buffers; reads that lost data flag
* `lossy` and point at full-stream spill files when available.
* - Disposal kills every running task and awaits their exit (no orphan
* processes survive `fiber.dispose()`).
* processes. `done` settles at process close and never rejects; spawn
* failures settle as `killed` with the error on stderr.
* - {@link BashProcess.readOutput} is incremental: consecutive reads never
* repeat output. Lossy reads report truncation and available spill files.
* - Disposal kills all running background processes and awaits their exit.
*/
export abstract class BashExecutor extends Service {
private listeners = new Set<BashTaskListener>()
private listenersClosed = false
constructor(ctx: Context) {
super(ctx, 'bash')
ctx.effect(() => () => {
// Close the listener registry before subclass teardown so late task
// completions (e.g. from kills issued during dispose) stay silent.
this.listenersClosed = true
this.listeners.clear()
}, 'bash listener teardown')
}
/**
* The sandbox mode this executor confines commands under BY DEFAULT, or
* `undefined` when it does not sandbox at all — the capability fact the
* tool and ACP layers read to advertise sandbox controls honestly. The
* getter proves a sandboxing executor is mounted and supplies its fallback
* mode; a session override may make the effective mode narrower or wider,
* so strict escalation widening is checked per call rather than encoded in
* this default-relative capability fact. The base class reports
* `undefined`; a sandboxing implementation overrides the getter.
* @returns the configured default mode of a sandboxing executor;
* `undefined` for an executor that never confines.
* The sandbox mode this executor applies by default, or `undefined` when it
* does not sandbox commands.
* @returns the configured default sandbox mode, when supported.
*/
get sandboxMode(): SandboxMode | undefined {
return undefined
}
/**
* Resolve a caller's {@link BashExecRequest} into a fully-specified
* {@link BashExecSpec}, applying this implementation's config defaults and
* caps (working directory, default/max timeout). Consumers (tool layer)
* call this, then pass the result to {@link run}/{@link start} — keeping
* defaulting in the implementation that owns the config while the seam type
* stays explicit (no hidden `?? default` inside run/start).
* Apply implementation-owned defaults and caps to a request before execution.
* @param request - the caller's request; omitted fields get this
* implementation's defaults, capped fields are clamped.
* @returns the fully-specified spec to hand to {@link run}/{@link start}.
@@ -111,86 +74,11 @@ export abstract class BashExecutor extends Service {
abstract run(spec: BashExecSpec): Promise<BashRunResult>
/**
* Start a background task and return its handle immediately.
* Start a background process and return its handle immediately.
* @param spec - a resolved spec from {@link resolve}, never a raw request.
* @returns the live task handle; completion fires {@link onTaskDone}.
* @returns the live process handle (reads, kill, quiescence promise).
*/
abstract start(spec: BashExecSpec): BashTask
/**
* Look up a background task by id.
* @param id - the task id to look up.
* @returns the tracked task, or undefined for an id this executor never issued.
*/
abstract get(id: BashTaskId): BashTask | undefined
/**
* The opaque OWNER token recorded for a background task at {@link start}
* (from the {@link BashExecSpec}'s `owner`), or `undefined` for an unknown id
* OR a known-but-ownerless task. The executor stores and returns the token
* verbatim — it never interprets it; the access POLICY (who may read/kill a
* task) lives in the consumer (`@deepseek-ai/dsh-tool-bash`), which compares
* `ownerOf(id)` to the caller's token. Collapsing unknown-id and
* known-but-unowned into the same `undefined` is fine: the consumer's access
* gate treats `undefined` as "open", and a genuinely unknown id then fails
* loudly at the subsequent {@link readOutput}/{@link kill} ("unknown task").
* Storing ownership in the executor (disposed with ITS fiber) — not in the
* tool plugin — is what makes ownership survive a `tool-bash` HMR reload.
* @param id - the background task id to look up ownership for.
* @returns the token recorded at start, verbatim; undefined for an unknown
* id or a known-but-ownerless task.
*/
abstract ownerOf(id: BashTaskId): OwnerToken | undefined
/**
* All tracked background tasks (insertion order).
* @returns every task this executor started, running or finished.
*/
abstract list(): BashTask[]
/**
* Read output produced since the previous read. Throws for unknown ids.
* @param id - the task to read from.
* @returns the incremental read; consecutive reads never re-deliver output.
*/
abstract readOutput(id: BashTaskId): BashTaskRead
/**
* Kill a running background task. Returns false when it had already
* finished (no-op). Throws for unknown ids.
* @param id - the task to kill.
* @returns true when this call killed it, false when it had already finished.
*/
abstract kill(id: BashTaskId): boolean
/**
* Register a background-task completion listener (disposed with the
* calling fiber). Listeners never fire after this service is disposed.
* @param listener - called exactly once per task completion.
* @returns the disposer that unregisters the listener.
*/
onTaskDone(listener: BashTaskListener): () => void {
const dispose = this.ctx.effect(() => {
this.listeners.add(listener)
return () => this.listeners.delete(listener)
}, 'bash.onTaskDone()')
return () => void dispose()
}
/** For implementations: notify listeners that `task` completed. Listener
* exceptions are contained (logged) — one bad listener must not reject
* `BashTask.done` or starve the listeners after it. */
protected notifyTaskDone(task: BashTask): void {
if (this.listenersClosed) return
for (const listener of this.listeners) {
try {
listener(task)
} catch (error: unknown) {
// Listener bugs are reported, never propagated into task.done.
console.error('bash onTaskDone listener threw:', error)
}
}
}
abstract start(spec: BashExecSpec): BashProcess
}
export default BashExecutor
+13 -26
View File
@@ -1,17 +1,9 @@
/**
* Per-session sandbox-mode override: the session log as the store. A runtime
* switch (an ACP `session/set_config_option`, a test scenario) is recorded as
* one `bash/sandbox-mode` event on the session it applies to;
* `effective = fold(events) ?? the executor's configured default`, so an
* override survives restart by replay, two sessions can never see each
* other's state, and there is no external config store. The event is
* log-only (the `approval/*` precedent): the model learns the mode from the
* prompt section and the boundary notices in `@deepseek-ai/dsh-tool-bash`,
* never from the event itself. EXECUTION honors the fold in the tool layer —
* it stamps the effective mode onto each call's `BashExecRequest.sandboxMode`
* (weakest-precedence: an escalation grant for the call outranks it) — the
* executor itself stays a config-fixed default plus per-call overrides.
*
* Per-session sandbox-mode override stored as log-only events. Folding the log
* isolates sessions and survives replay; the tool stamps the override onto
* each call unless an approved one-shot escalation outranks it, and the
* executor default applies when neither exists. The model receives neither the
* event nor a standing-mode notice; denial results name the effective mode.
* @module dsh-bash/session-mode
*/
@@ -21,12 +13,9 @@ import type { SandboxMode } from '@deepseek-ai/dsh-sandbox'
declare module '@deepseek-ai/dsh-session' {
interface SessionEventMap {
/**
* The session's sandbox mode was switched — log-only (like `approval/*`;
* NOT a surface event, carries no `surfaceOp`): durable and replayable,
* never in the model transcript. The LAST such event is the session's
* override ({@link effectiveSandboxMode}); who asked for it is derivable
* from position (an event after the log's last `request/header*` was a
* runtime switch by the user; see the tool layer's narrator).
* Durable log-only sandbox-mode override; never a surface event or model
* message. Execution and ACP option reporting fold the latest event through
* {@link effectiveSandboxMode} without adding a prompt notice.
*/
'bash/sandbox-mode': { mode: SandboxMode }
}
@@ -37,9 +26,8 @@ export const SANDBOX_MODES: readonly SandboxMode[] = ['read-only', 'workspace-wr
/**
* The session's sandbox-mode override: the last `bash/sandbox-mode` event in
* the log, or undefined when the session never switched (callers apply the
* executor's configured default). The pure fold — resume needs no catch-up
* machinery because replaying the log IS the state.
* the log, or undefined when the session never switched and callers should use
* the executor default. Replay needs no separate catch-up state.
* @param events - session events in log order (other event types are skipped).
* @returns the mode of the last switch event, or undefined without one.
*/
@@ -52,10 +40,9 @@ export function effectiveSandboxMode(events: readonly SessionEvent[]): SandboxMo
}
/**
* THE write path for a session's sandbox-mode override: appends exactly one
* `bash/sandbox-mode` event — the switch IS its event; nothing mutates mode
* state out of band. Takes effect on the session's next bash call and next
* prompt assembly (the consumers fold on every read).
* Append one `bash/sandbox-mode` event as the only override write path.
* Execution and ACP option reporting fold it on read; prompt assembly does not
* consume it.
* @param session - the session the override belongs to.
* @param mode - the mode every subsequent bash call in this session runs
* under (until the next switch).
+49 -162
View File
@@ -1,85 +1,24 @@
/**
* Execution vocabulary for the bash executor seam. Types only — the abstract
* service lives in `./index.ts`, implementations in sibling packages
* (`@deepseek-ai/dsh-bash-local` first).
*
* Execution types for the bash executor seam. Background task semantics belong
* to `@deepseek-ai/dsh-tasks`; this seam exposes only process handles.
* @module dsh-bash/types
*/
import type { Branded } from '@deepseek-ai/dsh-brand'
import type { SandboxEnforcement, SandboxMode } from '@deepseek-ai/dsh-sandbox'
/** Identifies one background task within an executor (generated `bash-N`). */
export type BashTaskId = Branded<'BashTaskId'>
/**
* Brand a string as a {@link BashTaskId}.
* @param id - the raw task-id string (the executor generates `bash-N`).
* @returns the same string, branded; no validation is performed.
*/
export function BashTaskId(id: string): BashTaskId {
return id as BashTaskId
}
/**
* A background task's opaque isolation key — the CONSUMER's owner identity, not
* the bash seam's. The executor stores and returns it verbatim and never
* interprets it; the access policy lives in the consumer (`dsh-tool-bash`),
* which is the single boundary that casts its own id vocabulary into one. A
* DISTINCT brand (not a `SessionId` alias) keeps the seam decoupled — a
* sandboxed/remote executor inherits no session dependency.
*/
export type OwnerToken = Branded<'OwnerToken'>
/**
* Brand a string as an {@link OwnerToken}. Only the consuming boundary
* (`dsh-tool-bash`) should cast its own id vocabulary in — see the type's doc.
* @param id - the consumer's raw owner identity (the tool layer passes the owning agent's session id).
* @returns the same string, branded; no validation is performed.
*/
export function OwnerToken(id: string): OwnerToken {
return id as OwnerToken
}
/**
* Sandbox facts for one foreground run — present on {@link BashRunResult} iff
* a sandboxing executor ran the command (an unsandboxed executor reports no
* `sandbox` field at all). Reported independently of `exitCode`/`signal`
* (orthogonal outcomes), so a caller can tell "the command failed on its own"
* from "the sandbox blocked a file operation". The mode/enforcement
* vocabulary lives on the `@deepseek-ai/dsh-sandbox` seam; this shape is the
* bash seam's result-fact carrier for it.
* Sandbox facts for one run, present iff a sandboxing executor handled it.
* Facts are reported independently of process exit status so callers can
* distinguish command failures from policy denials and runner failures.
*/
export interface BashSandboxInfo {
/** The mode the command actually ran under. */
mode: SandboxMode
/**
* True when the executor classifies this run's failure as the sandbox
* denying a file operation. The classification is CONSERVATIVE (a failed
* exit whose stderr carries a filesystem-permission signature) and reads
* the COLLECTED stderr — the bounded in-memory tail per
* {@link CollectedOutput} semantics, so a signature that survives only in a
* spill file is missed toward `denied: false`. A plain command failure
* keeps `denied: false` even under a sandboxed mode.
*/
/** Whether the sandbox denied a file operation. */
denied: boolean
/**
* How completely the runner enforced `mode`'s file effects — see
* {@link SandboxEnforcement}. Absent exactly when `mode` is
* `danger-full-access`: nothing is confined, so there is no enforcement to
* report.
*/
/** How completely the selected runner enforced the requested mode. */
enforcement?: SandboxEnforcement
/**
* True when the executor classifies this failure as the SANDBOX RUNNER
* itself failing (missing binary, refused profile, fail-closed refusal
* before exec) — the command NEVER RAN; this is a sandbox failure, not a
* task failure, and it outranks `denied` (a runner's own error text can
* contain denial words). Only ever stamped on settled BACKGROUND tasks: a
* foreground run surfaces the same condition as the thrown
* `SANDBOX_UNAVAILABLE` error instead (the foreground path has an error
* channel; a settled task's facts are its only channel).
*/
/** Whether the sandbox runner failed before the command could run. */
runnerFailed?: boolean
}
@@ -122,38 +61,14 @@ export interface BashExecRequest {
* uses shell syntax like `FOO=bar cmd`).
*/
env?: Record<string, string> | 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
* executor stores it on the task and exposes it via {@link BashExecutor.ownerOf};
* the executor itself NEVER interprets it (no access policy lives in the
* seam — that is the consumer's job). Absent for foreground runs and for an
* ownerless background start (a non-agent caller).
*/
owner?: OwnerToken | undefined
/**
* Explicit per-call sandbox-policy input, overriding the executor's
* configured default mode for THIS call. Never a silent default: a
* consumer sets it only from an explicit policy source — an
* `'allowed-once'` grant a human just issued through `ctx.approval` (the
* escalation flow in the sandbox RFC § Escalation, which outranks), or the
* session's standing override folded from its own `bash/sandbox-mode`
* events (the sandbox RFC § Per-session mode switching — the user's recorded per-session
* choice). A sandboxing executor confines THIS call under the given mode;
* a non-sandboxing executor carries the field and confines nothing (the
* tool layer stamps neither escalation nor overrides without a sandboxing
* executor — see {@link BashExecutor.sandboxMode}).
*/
/** Explicit per-call sandbox mode override. */
sandboxMode?: SandboxMode | undefined
}
/**
* A fully-resolved execution SPEC — exactly what {@link BashExecutor.run} /
* {@link BashExecutor.start} act on. `workdir` and `timeoutMs` are REQUIRED:
* defaulting and capping already happened in {@link BashExecutor.resolve}, so
* the executor never hides a `?? config` fallback (explicit > implicit). For
* background tasks, `start()` ignores `timeoutMs` (background runs have no
* timeout) — the field is still required because the type is shared.
* A resolved execution spec. {@link BashExecutor.resolve} fills and caps the
* required fields; {@link BashExecutor.start} ignores `timeoutMs` because
* background processes have no executor timeout.
*/
export interface BashExecSpec {
command: string
@@ -166,40 +81,14 @@ export interface BashExecSpec {
stdoutMaxBytes: number
/** Abort signal — implementations kill the command when it fires. */
signal?: AbortSignal | undefined
/**
* Bytes to write to the command's stdin (then close it), carried through
* verbatim from {@link BashExecRequest.stdin}. OPTIONAL on the resolved spec
* (unlike `owner`): it has no config default, so a missing one means "no
* stdin" — the safe, ordinary case — not a silent footgun, so it stays a
* plain optional rather than required-but-nullable (see the request field).
*/
/** Bytes to write to stdin before closing it; absent means no stdin. */
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".
* Extra environment entries, merged after credential scrubbing so explicit
* values win; absent means no extra entries.
*/
env?: Record<string, string> | undefined
/**
* Opaque owner token, REQUIRED-but-nullable (mirrors `workdir`/`timeoutMs`
* being required on the resolved spec): {@link BashExecutor.resolve} carries
* the request's `owner` through, defaulting a missing one to `undefined`. A
* required field makes a forgotten owner a VISIBLE `undefined` rather than a
* silently-absent property that yields an unowned (cross-session-readable)
* task. `start()` stores it; `run()` (foreground) ignores it.
*/
owner: OwnerToken | undefined
/**
* The sandbox mode this call executes under, REQUIRED-but-nullable for the
* same visibility reason as `owner`. A sandboxing executor's `resolve()`
* stamps the effective mode (the request's explicit override, else its
* configured default) so `run()`/`start()` read the spec, never the config;
* a non-sandboxing executor carries the request value through verbatim and
* ignores it (`undefined` under such an executor means what its README says:
* unconfined execution).
*/
/** Resolved sandbox mode; ignored by executors that do not confine. */
sandboxMode: SandboxMode | undefined
}
@@ -237,43 +126,15 @@ export interface BashRunResult {
timeoutMs: number
stdout: CollectedOutput
stderr: CollectedOutput
/**
* Sandbox facts, present iff a sandboxing executor ran the command — an
* unsandboxed executor (e.g. `dsh-bash-local`) never sets it. See
* {@link BashSandboxInfo} for the `denied` classification semantics.
*/
/** Sandbox execution facts, absent for an unsandboxed executor. */
sandbox?: BashSandboxInfo
}
/** Lifecycle of a background task. */
export type BashTaskStatus = 'running' | 'completed' | 'killed'
/** Lifecycle of a background process. */
export type BashProcessStatus = 'running' | 'completed' | 'killed'
/** A tracked background task handle. */
export interface BashTask {
readonly id: BashTaskId
readonly command: string
status: BashTaskStatus
/** Exit code once finished (null = killed by signal / still running). */
exitCode: number | null
/** Terminating signal name, when signal-killed. */
signal: NodeJS.Signals | null
/** Resolves when the underlying process closes (never rejects). */
readonly done: Promise<void>
/**
* Sandbox facts for this task's execution, stamped by a sandboxing executor
* once the task settles and BEFORE completion listeners are notified — an
* `onTaskDone` consumer and a `done` awaiter both see it. Denial
* classification runs against the settled task's collected stderr, so the
* field cannot exist earlier: absent while the task is running and under an
* executor that does not sandbox. See {@link BashSandboxInfo} for the
* `denied` semantics.
*/
sandbox?: BashSandboxInfo
}
/** One incremental {@link BashExecutor.readOutput} read. */
export interface BashTaskRead {
task: BashTask
/** One incremental {@link BashProcess.readOutput} read. */
export interface BashProcessRead {
/** Output produced since the previous read (stderr in a marked section). */
delta: string
/** True when truncation dropped unread bytes the delta cannot include. */
@@ -284,5 +145,31 @@ export interface BashTaskRead {
stderrSpillPath?: string
}
/** Completion callback for background tasks. */
export type BashTaskListener = (task: BashTask) => void
/**
* A background process handle returned by {@link BashExecutor.start}. It is the
* only access path; buffered output remains readable after exit. Executor
* disposal kills running processes and awaits {@link done}.
*/
export interface BashProcess {
/** Process lifecycle state (settled exactly once). */
status: BashProcessStatus
/** Exit code once finished (null = killed by signal / still running). */
exitCode: number | null
/** Terminating signal name, when signal-killed. */
signal: NodeJS.Signals | null
/** Resolves when the underlying process closes (never rejects — a spawn failure settles as `killed` with the error on stderr). */
readonly done: Promise<void>
/** Sandbox facts, stamped once a confined process settles. */
sandbox?: BashSandboxInfo
/**
* Read output produced since the previous read (consuming — consecutive
* reads never re-deliver). Reads that lost data flag `lossy` and point at
* full-stream spill files when available.
*/
readOutput(): BashProcessRead
/**
* Kill the process group. Returns false when it had already finished
* (no-op); idempotent.
*/
kill(): boolean
}