Merge remote-tracking branch 'origin/master' into cross-family-fs-sandbox

# Conflicts:
#	docs/config-catalog.md
#	docs/cordis-catalog/events.md
#	docs/cordis-catalog/services.md
#	docs/event-producer-consumer.md
#	docs/persistence-catalog.md
#	examples/acp-agent/cordis.yml
#	examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl
#	examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl
#	examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl
#	examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl
#	examples/acp-agent/tests/snapshots/permission-switching/session.jsonl
#	examples/acp-agent/tests/snapshots/skill-load/session.jsonl
#	examples/acp-agent/tests/snapshots/text-turn/session.jsonl
#	packages/bash/bash-sandbox/src/index.ts
#	packages/bash/bash/src/types.ts
#	packages/bash/tool-bash/src/index.ts
#	packages/fs/fs/src/index.ts
#	packages/sandbox/sandbox-policy/src/session-mode.ts
#	packages/ui/permission/src/index.ts
#	packages/ui/permission/tests/permission.spec.ts
#	scripts/doc-budgets.manifest.json
This commit is contained in:
kingwl
2026-07-14 21:25:36 +08:00
608 files changed
+7195 -12508

No files matched your search

+17 -56
View File
@@ -1,16 +1,6 @@
/**
* 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 bash executor seam (`ctx.bash`): an abstract service defining what a bash backend does —
* run commands, manage background tasks — without saying how.
* @module @deepseek-ai/dsh-bash
*/
@@ -38,25 +28,11 @@ declare module 'cordis' {
}
/**
* Abstract bash execution service. Subclass, implement the abstract methods,
* and load the subclass as a plugin — it registers as `ctx.bash` (one
* 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.
* - {@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()`).
* Registers one `ctx.bash` implementation. Runtime command failures resolve as
* {@link BashRunResult}; only infrastructure failures reject. Background starts
* return immediately without a timeout, report completion exactly once while
* live, and remain cancellable by signal or {@link kill}. Output reads are
* incremental and flag lost buffered data; disposal kills and awaits all tasks.
*/
export abstract class BashExecutor extends Service {
private listeners = new Set<BashTaskListener>()
@@ -73,14 +49,11 @@ export abstract class BashExecutor extends Service {
}
/**
* 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.
* 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.
* A session or call may override this default, so widening is evaluated per
* execution rather than encoded in this getter.
* @returns the configured default mode of a sandboxing executor;
* `undefined` for an executor that never confines.
*/
@@ -89,12 +62,7 @@ export abstract class BashExecutor extends Service {
}
/**
* 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}.
@@ -124,17 +92,10 @@ export abstract class BashExecutor extends Service {
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.
* 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 the token without interpreting policy; keeping it here
* lets ownership survive a consumer-plugin 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.
+5 -19
View File
@@ -71,14 +71,8 @@ export interface BashSandboxInfo {
*/
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).
* The sandbox runner failed before executing the command. Set only on settled
* background tasks; foreground runs throw `SANDBOX_UNAVAILABLE` instead.
*/
runnerFailed?: boolean
}
@@ -125,17 +119,9 @@ export interface BashExecRequest {
*/
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 `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 policy. The tool stamps a session override or a
* one-shot approved escalation, with the grant taking precedence. Sandboxing
* executors honor it for this call; non-sandboxing executors do not confine.
*/
sandboxMode?: SandboxMode | undefined
}