diff --git a/docs/module-graph.md b/docs/module-graph.md index ed1cc592d4..a4e729484d 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -9,6 +9,7 @@ Inter-package dependencies among the `@deepseek-ai/dsh-*` harness packages, deri flowchart TD subgraph group_util["packages/util"] pkg_brand["brand"] + pkg_timeout["timeout"] end subgraph group_llm["packages/llm"] pkg_llm["llm"] @@ -86,6 +87,7 @@ flowchart TD pkg_session --> pkg_llm pkg_system_prompt --> pkg_llm pkg_bash_local --> pkg_bash + pkg_bash_local --> pkg_timeout pkg_fs --> pkg_brand pkg_fs --> pkg_llm pkg_web --> pkg_llm @@ -97,6 +99,7 @@ flowchart TD pkg_fs_policy --> pkg_fs pkg_compact --> pkg_llm pkg_compact --> pkg_session + pkg_web_fetch_local --> pkg_timeout pkg_web_fetch_local --> pkg_web pkg_web_search_deepseek --> pkg_web pkg_web_search_exa --> pkg_web @@ -205,6 +208,7 @@ flowchart TD | Package | Group | Depends on | | --- | --- | --- | | [`brand`](../packages/util/brand) | `util` | — | +| [`timeout`](../packages/util/timeout) | `util` | — | | [`app-boot`](../packages/ui/app-boot) | `ui` | — | | [`llm`](../packages/llm/llm) | `llm` | [`brand`](../packages/util/brand) | | [`bash`](../packages/bash/bash) | `bash` | [`brand`](../packages/util/brand) | @@ -212,14 +216,14 @@ flowchart TD | [`llm-pi-ai`](../packages/llm/llm-pi-ai) | `llm` | [`llm`](../packages/llm/llm) | | [`session`](../packages/core/session) | `core` | [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm) | | [`system-prompt`](../packages/core/system-prompt) | `core` | [`llm`](../packages/llm/llm) | -| [`bash-local`](../packages/bash/bash-local) | `bash` | [`bash`](../packages/bash/bash) | +| [`bash-local`](../packages/bash/bash-local) | `bash` | [`bash`](../packages/bash/bash), [`timeout`](../packages/util/timeout) | | [`fs`](../packages/fs/fs) | `fs` | [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm) | | [`web`](../packages/web/web) | `web` | [`llm`](../packages/llm/llm) | | [`agent`](../packages/core/agent) | `core` | [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt) | | [`fs-local`](../packages/fs/fs-local) | `fs` | [`fs`](../packages/fs/fs) | | [`fs-policy`](../packages/fs/fs-policy) | `fs` | [`fs`](../packages/fs/fs) | | [`compact`](../packages/compact/compact) | `compact` | [`llm`](../packages/llm/llm), [`session`](../packages/core/session) | -| [`web-fetch-local`](../packages/web/web-fetch-local) | `web` | [`web`](../packages/web/web) | +| [`web-fetch-local`](../packages/web/web-fetch-local) | `web` | [`timeout`](../packages/util/timeout), [`web`](../packages/web/web) | | [`web-search-deepseek`](../packages/web/web-search-deepseek) | `web` | [`web`](../packages/web/web) | | [`web-search-exa`](../packages/web/web-search-exa) | `web` | [`web`](../packages/web/web) | | [`web-search-perplexity`](../packages/web/web-search-perplexity) | `web` | [`web`](../packages/web/web) | diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index 0c5a11a4f9..5307c381c8 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -118,6 +118,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [Add direct directory listing to the filesystem seam](implemented/architecture/2026-07-03-filesystem-directory-listing-seam.md) | 2026-07-03 | | [Prompt variables and tool-guidance ownership](implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md) | 2026-07-05 | | [Subagent provider-lifecycle events — `subagent/provider-added` / `subagent/provider-removed`](implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.md) | 2026-07-05 | +| [A shared timeout/deadline primitive, with hard-kill left to each capability](implemented/architecture/2026-07-06-timeout-deadline-library.md) | 2026-07-06 | ### Process diff --git a/docs/rfc/implemented/architecture/2026-07-06-timeout-deadline-library.md b/docs/rfc/implemented/architecture/2026-07-06-timeout-deadline-library.md new file mode 100644 index 0000000000..84fc5b3ea2 --- /dev/null +++ b/docs/rfc/implemented/architecture/2026-07-06-timeout-deadline-library.md @@ -0,0 +1,98 @@ +# RFC: A shared timeout/deadline primitive, with hard-kill left to each capability + +Status: implemented + +## Problem + +Timeout handling was drifting apart across the tool-bearing capabilities, and the divergence was not superficial — it was the same logic re-implemented three ways, each with its own subtle correctness burden. + +- **bash** ([packages/bash/bash-local/src/run.ts](../../../../packages/bash/bash-local/src/run.ts)) had a full, correct timeout inside the process plumbing: a config-clamped `timeoutMs`, two independent triggers — a `killTimer` for the timeout and an `onAbort` listener for upstream cancellation — each calling one `kill()` closure that escalates SIGTERM→grace→SIGKILL on the process group, and two orthogonal outcome booleans (`timedOut`, `aborted`) latched independently. +- **web_fetch** ([packages/web/web-fetch-local/src/provider.ts](../../../../packages/web/web-fetch-local/src/provider.ts)) had a correct but *hand-rolled* timeout: it constructed an `AbortController`, wired `setTimeout(() => controller.abort(new WebError(…, 'WEB_FETCH_TIMEOUT')))`, manually added and removed the upstream-signal listener, cleared the timer in a `finally`, and recovered the timeout reason from `signal.reason` in a `translateAbortOrNetwork` helper because the reader surfaces a bare `AbortError`. +- **web_search** ([packages/web/tool-web/src/search.ts](../../../../packages/web/tool-web/src/search.ts)) had **no timeout at all**: `WebSearchRequest` ([packages/web/web/src/types.ts](../../../../packages/web/web/src/types.ts)) carries no `timeoutMs` field, and each provider's `search()` only forwards `exec.signal`. (web_search stays untimed here — see Consequences.) + +Each new external-process or network tool re-derived the same four things — clamp the requested value, start a timer, fuse the timeout with upstream cancellation, and distinguish "timed out" from "cancelled" on the way out — and the fusion and reason-recovery are exactly the parts that are easy to get subtly wrong (web_fetch's `signal.reason` dance is evidence). At the same time, the *termination* each performs is irreducibly different: bash kills an OS process group (work runs in a child process, outside this runtime, reachable only by signal), while web aborts an in-process `fetch` (undici tears down the socket). There is no single mechanism that can stop all of them. + +The two reference agents surveyed converged on the same split. Codex models "what will end this exec early" as one value (`ExecExpiration`, an enum fusing timeout and a cancellation token) whose `wait_with_outcome()` returns `TimedOut | Cancelled`, while the actual `kill_process_group` lives outside it — and that abstraction is reused *only* across the exec family, with MCP, model-stream, and guardian each keeping their own bespoke `tokio::time::timeout`. Claude Code shares nothing: bash and ripgrep each own a private SIGTERM→SIGKILL kill and distinguish timeout from cancellation by throwing distinct error types, while file I/O has no timeout. Both confirm the boundary drawn here: the timing-and-classification half is worth sharing within a family of like-terminated operations; the termination half is not shareable and stays in each capability. + +## Decision + +`@deepseek-ai/dsh-timeout` lives under `packages/util/` (peer to `dsh-brand`) and owns the *timing and classification* half of timeout; the *termination* half — the hard kill — stays in each capability's implementation. It is a library of pure functions, **not** a cordis service or plugin: it takes no `ctx`, registers nothing, holds no cross-call state, and emits no events. There is deliberately no central "timeout service" that would have to know how to stop every capability's work — that knowledge is exactly what a microkernel keeps out of shared layers, and what Codex's exec-only `ExecExpiration` scope demonstrates. + +### The library surface + +Three functions plus one reason type: + +```ts ignore-check +/** The internal reason attached to a timeout abort, so consumers can classify it after the fact. */ +export class TimeoutReason extends Error { + override name = 'TimeoutReason' + + constructor(readonly code: string, readonly timeoutMs: number) { + super(`${code} after ${timeoutMs}ms`) + } +} + +/** Validate/fill a caller's optional positive hint from the backend's default, then cap at its max. */ +export function clampTimeout( + requested: number | undefined, + def: number, + max: number, + name = 'timeoutMs', +): number + +/** + * Build a deadline signal that aborts on upstream cancellation OR on timeout, + * with the timeout carrying a `TimeoutReason`. `timeoutMs <= 0` means "no + * timeout" (background tasks): forward only the upstream signal, arm no timer. + * The returned object's `[Symbol.dispose]` clears the timer — `using` for a + * scope-lifetime consumer, a manual call for an event-lifetime one. + */ +export function deadline( + upstream: AbortSignal | undefined, + timeoutMs: number, + code: string, +): { signal: AbortSignal; [Symbol.dispose](): void } + +/** Recover the TimeoutReason from an aborted signal (or error), else undefined. */ +export function timeoutOf(x: AbortSignal | { reason?: unknown }): TimeoutReason | undefined +``` + +`deadline` is `AbortSignal.any([upstream, ])` with three things the standard library does not give: a typed, identifiable `TimeoutReason` on the timeout abort (native `AbortSignal.timeout()` yields a fixed `TimeoutError`, indistinguishable across timeout kinds), an internal `timeoutMs <= 0` "no timeout" sentinel for backend-owned background work, and a `Symbol.dispose` cleanup that works with both `using` and manual disposal. `AbortSignal.any` is a Node ≥ 20 primitive; it is the single mechanism that fuses two abort sources into one, adopting the reason of whichever fires first. External request hints validate as positive finite numbers via `clampTimeout` before they reach `deadline`; `0` is not a model-/plugin-facing "disable timeout" value. When `timeoutMs <= 0` and no upstream signal is present, `deadline()` returns a never-aborting signal plus a no-op disposer so callers keep one call shape. `TimeoutReason` is an internal classification reason: providers translate it into seam-specific public errors or result fields before returning to callers. + +### The division of labor + +| Concern | Owner | +|---|---| +| Validate request hint and clamp default/max | `dsh-timeout` (`clampTimeout`) — pure arithmetic plus the shared positive-finite request contract | +| Arm timer, abort on deadline, carry reason, fuse with upstream cancel | `dsh-timeout` (`deadline`) | +| Clear the timer | `dsh-timeout` (`[Symbol.dispose]`) | +| Classify the first abort reason after abort | `dsh-timeout` (`timeoutOf`) | +| **Actually terminate the work** | the capability's implementation | +| The default/max *values* | the capability's config | +| The timeout `code` string | the capability (`WEB_FETCH_TIMEOUT` ≠ `BASH_TIMEOUT`) | + +The signal only *notifies*; termination is always the listener's job, and the listener differs by capability. bash writes its own `addEventListener('abort', kill)` because the OS process lives outside this runtime and nothing else will kill it; web hands `d.signal` to `fetch` and undici tears down the socket. This is why file read/write/edit take **no** `timeoutMs`: a local syscall is best-effort-abortable at most, a timeout could not force `fsync`/`rename` to stop, and adding one would be an implicit default that violates explicit-over-implicit. Both reference agents leave file I/O untimed for the same reason. + +### How each capability consumes it + +- **web_fetch** — the tool stays validate-and-forward; the provider's hand-rolled controller + `setTimeout` + manual listener + `finally` + `signal.reason` recovery is replaced by provider-owned `deadline`/`timeoutOf`. A pre-aborted upstream signal still throws `WEB_ABORTED` up front; otherwise `fetch` runs against the fused `d.signal`, and `translateAbortOrNetwork` classifies a thrown error by the signal (`timeoutOf` → `WEB_FETCH_TIMEOUT`, else aborted → `WEB_ABORTED`, else network → `WEB_PROVIDER_ERROR`). The public error-code contract is unchanged, and `TimeoutReason` never crosses the web seam as the public error. +- **bash** — `resolve()` stays a pure request-to-spec step: it clamps with `clampTimeout(request.timeoutMs, config.timeoutMs, config.maxTimeoutMs, 'bash-local: request.timeoutMs')` and carries `request.signal` through unchanged. Foreground `run()` owns the timeout: `using d = deadline(spec.signal, spec.timeoutMs, 'BASH_TIMEOUT')`, then `runBash` receives only `d.signal`. `runBash` no longer owns any timer — it listens for abort and runs its existing SIGTERM→grace→SIGKILL process-group kill, and its `SpawnSpec`/`SpawnOutcome` no longer carry `timeoutMs`/`timedOut`/`aborted` (the executor classifies from the deadline signal instead). `run()` computes `timedOut = timeoutOf(d.signal) !== undefined` and `aborted = d.signal.aborted && !timedOut`, so the public seam booleans (`BashRunResult.timedOut`/`aborted`) are mutually exclusive — the shared deadline reports the cause that first cut the command short. Background `start()` creates no deadline and forwards only the upstream signal, so background tasks stay timeout-free; a task's killed-vs-completed status reads its own `spec.signal.aborted`. + +## Consequences + +- `runBash`'s outcome no longer independently latches `timedOut` and `aborted`; a timeout and a user abort racing before process close now report a single first-abort cause instead of both being true. The uniform SIGTERM→grace→SIGKILL kill is unchanged, and the seam type `BashRunResult` keeps both booleans (now mutually exclusive), so `dsh-tool-bash`'s result rendering is untouched. +- `SpawnSpec.timeoutMs` and `SpawnOutcome.timedOut`/`aborted` were removed rather than kept as always-zero/always-false vestiges: with `runBash` owning no timer and the executor owning classification, they were read nowhere. This is the one deviation from the literal proposal shape (which passed `timeoutMs: 0` into `runBash`); an always-0 field read by nothing is dead weight under the per-file coverage gate. +- web_fetch shed its bespoke controller/timer/listener/reason-recovery; the classifier now keys off the deadline signal (`timeoutOf` + `aborted`) rather than the thrown error's shape, which is robust across both the request-phase reject-with-reason and the read-phase bare-`AbortError`. +- `AbortSignal.any` and `using`/`Symbol.dispose` enter the repo for the first time here (Node ≥ 24 baseline, already met). + +Out of scope, named to mark the boundary: `web_search` can gain an optional model-facing `timeout_ms` once its tool-schema/snapshot coverage is planned; future ripgrep-backed fs discovery tools can consume the same provider-owned deadline shape once they exist; a `tools/execute` waterfall middleware could arm a default deadline for every tool call by driving `exec.signal` — that would be a plugin that *consumes* this library and still only notifies, the hard kill remaining each capability's job. + +## Alternatives considered + +**A unified timeout *plugin* / `ctx.timeout` service.** Rejected on microkernel grounds. A service that could stop any tool's work would have to understand every capability's termination mechanism (process-group SIGKILL, socket teardown, syscall-boundary checks) — the "kernel knows too much" the architecture forbids. Codex's `ExecExpiration` is scoped to the exec family precisely because the kill it drives (`killpg`) is process-family-specific; MCP and model-stream keep their own. There is no coherent middle layer that owns termination for everything, so the shared piece can only be the pure timing/classification half — a library, not a service. + +**Per-tool ad-hoc timeout, no shared code (the prior status quo, and Claude Code's choice).** Rejected because it was already producing divergence and duplicated correctness burden: web_fetch hand-rolled the exact controller/reason logic that future network/process-backed tools would each have to re-derive, and the fusion + `signal.reason` recovery are the error-prone parts. Claude Code tolerates full duplication; this repo has a single shared abort channel (`exec.signal` on every `execute`) that makes a small shared primitive strictly cleaner, so the cost/benefit differs. + +**A `withTimeout(promise, ms)` wrapper instead of a signal factory.** Rejected because racing a promise against a timer resolves the *tool-call* promise on deadline without stopping the underlying work — the child process or fetch socket leaks on. Handing out a signal and requiring the capability to listen is what forces a real termination path to exist. This mirrors the "dispose must reach quiescence, not just request it" defensive rule. + +**Keep bash's two independent triggers (`killTimer` + `onAbort`) rather than fusing.** Rejected for the convergence goal: fusing into one `deadline` signal removes bash's bespoke timer and gives every capability one shape. The trade-off is that bash's `timedOut`/`aborted` booleans become first-abort classifications rather than independent facts that can both be true when timeout and user abort race before process close. That is acceptable because the result reports the cause that first cut the command short; the termination action stays the same uniform SIGTERM→grace→SIGKILL kill. Note the deliberate non-alignment with Codex: Codex forks its kill by outcome (timeout → immediate SIGKILL; cancel → SIGTERM + 50 ms grace → SIGKILL), whereas the fused signal drives one uniform `kill()` for both, matching Claude Code's unified bash kill. Splitting the kill by `timeoutOf` is possible later if a need appears; there is none now. diff --git a/knip.json b/knip.json index 5e61645458..2e3e101ae1 100644 --- a/knip.json +++ b/knip.json @@ -21,6 +21,11 @@ "project": ["src/**/*.ts"], "ignoreDependencies": ["cordis"] }, + "packages/util/timeout": { + "entry": ["tests/**/*.spec.ts"], + "project": ["src/**/*.ts", "tests/**/*.ts"], + "ignoreDependencies": ["cordis"] + }, "packages/llm/llm-deepseek": { "entry": ["tests/**/*.spec.ts", "tests/**/*.e2e.ts"], "project": ["src/**/*.ts", "tests/**/*.ts"] diff --git a/packages/bash/bash-local/package.json b/packages/bash/bash-local/package.json index bc1dc7eb40..e3c7ffe33b 100644 --- a/packages/bash/bash-local/package.json +++ b/packages/bash/bash-local/package.json @@ -23,6 +23,7 @@ "license": "BSD-3-Clause", "peerDependencies": { "@deepseek-ai/dsh-bash": "^0.0.1", + "@deepseek-ai/dsh-timeout": "^0.0.1", "cordis": "^4.0.0-rc.6" }, "dependencies": { @@ -30,6 +31,7 @@ }, "devDependencies": { "@deepseek-ai/dsh-bash": "workspace:^", + "@deepseek-ai/dsh-timeout": "workspace:^", "cordis": "^4.0.0-rc.6" } } diff --git a/packages/bash/bash-local/src/index.ts b/packages/bash/bash-local/src/index.ts index cdac3985b8..674f410b50 100644 --- a/packages/bash/bash-local/src/index.ts +++ b/packages/bash/bash-local/src/index.ts @@ -18,6 +18,7 @@ import { Context } from 'cordis' import z from 'schemastery' import { BashExecutor, BashTaskId } from '@deepseek-ai/dsh-bash' import type { BashExecRequest, BashExecSpec, BashRunResult, BashTask, BashTaskRead, OwnerToken } from '@deepseek-ai/dsh-bash' +import { clampTimeout, deadline, timeoutOf } from '@deepseek-ai/dsh-timeout' import { DEFAULT_GRACE_MS, runBash } from './run.ts' import type { RunInternals, RunningBash } from './run.ts' @@ -114,8 +115,12 @@ export class LocalBashExecutor extends BashExecutor { * values and never re-default. */ resolve(request: BashExecRequest): BashExecSpec { - if (request.timeoutMs !== undefined) assertPositiveFinite('request.timeoutMs', request.timeoutMs) - const timeoutMs = Math.min(request.timeoutMs ?? this.config.timeoutMs, this.config.maxTimeoutMs) + const timeoutMs = clampTimeout( + request.timeoutMs, + this.config.timeoutMs, + this.config.maxTimeoutMs, + 'bash-local: request.timeoutMs', + ) return { command: request.command, workdir: request.workdir ?? this.config.cwd ?? process.cwd(), @@ -132,29 +137,38 @@ export class LocalBashExecutor extends BashExecutor { } async run(spec: BashExecSpec): Promise { + // One fused deadline drives both the timeout and upstream cancellation; + // runBash listens on d.signal and runs the SIGTERM→grace→SIGKILL kill. + // `using` clears the timer across the awaited process lifetime. + using d = deadline(spec.signal, spec.timeoutMs, 'BASH_TIMEOUT') const outcome = await runBash({ command: spec.command, cwd: spec.workdir, - timeoutMs: spec.timeoutMs, maxOutputBytes: this.config.maxOutputBytes, graceMs: this.config.graceMs, - signal: spec.signal, + signal: d.signal, stdin: spec.stdin, env: spec.env, }, this.internals).done - return { ...outcome, timeoutMs: spec.timeoutMs } + // Classify the FIRST abort reason: a TimeoutReason means the timeout cut the + // command short; any other abort is upstream cancellation. Mutually + // exclusive by construction — the fused signal reports one cause, not two + // independently-latched facts. + const timedOut = timeoutOf(d.signal) !== undefined + const aborted = d.signal.aborted && !timedOut + return { ...outcome, timedOut, aborted, timeoutMs: spec.timeoutMs } } start(spec: BashExecSpec): BashTask { // No timeout for background tasks (matches Claude Code, which detaches // the timeout when backgrounding); callers stop tasks via kill() — or // via spec.signal, which the seam contract honors for background runs - // too (runBash wires it to the group kill). spec.timeoutMs is ignored - // here by design. + // too (runBash wires it to the group kill). No deadline is created here, + // so spec.timeoutMs is ignored by design — background tasks stay + // timeout-free (see the timeout-library RFC). const running = runBash({ command: spec.command, cwd: spec.workdir, - timeoutMs: 0, maxOutputBytes: this.config.maxOutputBytes, graceMs: this.config.graceMs, signal: spec.signal, @@ -174,8 +188,10 @@ export class LocalBashExecutor extends BashExecutor { stdoutOffset: 0, stderrOffset: 0, done: running.done.then((outcome) => { - // Abort-killed tasks report as killed, not completed. - if (task.status === 'running') task.status = outcome.aborted ? 'killed' : 'completed' + // Abort-killed tasks report as killed, not completed. Background runs + // forward only the upstream signal (no timeout), so its aborted state + // is the authoritative "was this cancelled" signal. + if (task.status === 'running') task.status = spec.signal?.aborted === true ? 'killed' : 'completed' task.exitCode = outcome.exitCode task.signal = outcome.signal this.notifyTaskDone(task) diff --git a/packages/bash/bash-local/src/run.ts b/packages/bash/bash-local/src/run.ts index 489d380787..98ccca19e7 100644 --- a/packages/bash/bash-local/src/run.ts +++ b/packages/bash/bash-local/src/run.ts @@ -6,6 +6,12 @@ * Everything here is deliberately free of Cordis concepts so it can be unit * tested in isolation; `LocalBashExecutor` owns lifecycle and configuration. * + * runBash owns NO timing: it kills the process group when its `spec.signal` + * fires and does not distinguish a timeout from a cancel. The executor fuses + * timeout + upstream cancellation into that one signal via + * `@deepseek-ai/dsh-timeout`'s `deadline`, and classifies the outcome from the + * signal afterward — the timing/classification half is shared, the kill is not. + * * Design notes (surveyed against Claude Code, OpenCode, Codex, and pi — see * the package README): spawn-per-call with `detached: true` so the child * leads its own process group; kills target the group (`kill(-pid)`) so @@ -69,13 +75,17 @@ export function childEnv(extra?: Record): NodeJS.ProcessEnv { export interface SpawnSpec { command: string cwd: string - /** Kill the process group after this many milliseconds. 0 = no timeout. */ - timeoutMs: number /** Per-stream in-memory cap; overflow spills to disk (tail kept in memory). */ maxOutputBytes: number /** Grace period between the SIGTERM and the SIGKILL escalation on a kill. */ graceMs: number - /** Abort signal — kills the process group when fired. */ + /** + * Abort signal — kills the process group when it fires. The executor owns + * timing: `run()` passes a fused timeout/cancel deadline signal (see + * `@deepseek-ai/dsh-timeout`), `start()` passes the bare upstream signal. + * runBash only listens and kills; it does NOT classify why (the executor + * reads the signal's reason afterward). + */ signal?: AbortSignal | undefined /** * Bytes to write to the child's stdin, then close it. Absent (or empty) @@ -92,12 +102,15 @@ export interface SpawnSpec { env?: Record | undefined } -/** Raw outcome of one closed process (before result shaping). */ +/** + * Raw outcome of one closed process (before result shaping). Deliberately + * carries NO timeout/cancel classification: runBash kills on abort but does not + * decide why — the executor's `run()`/`start()` reads the deadline signal it + * owns to classify `timedOut`/`aborted` (see the package README). + */ export interface SpawnOutcome { exitCode: number | null signal: NodeJS.Signals | null - timedOut: boolean - aborted: boolean stdout: CollectedOutput stderr: CollectedOutput } @@ -318,9 +331,6 @@ export function runBash(spec: SpawnSpec, internals: RunInternals = {}): RunningB child.stdout.on('data', (chunk: Buffer) => { stdout.push(chunk) }) child.stderr.on('data', (chunk: Buffer) => { stderr.push(chunk) }) - let timedOut = false - let aborted = false - let killTimer: NodeJS.Timeout | undefined let graceTimer: NodeJS.Timeout | undefined // pid is undefined when the spawn itself fails (bad cwd, missing binary); @@ -333,17 +343,12 @@ export function runBash(spec: SpawnSpec, internals: RunInternals = {}): RunningB graceTimer = setTimeout(() => { killGroup(pid, 'SIGKILL') }, spec.graceMs) } - if (spec.timeoutMs > 0) { - killTimer = setTimeout(() => { - timedOut = true - kill() - }, spec.timeoutMs) - } - - const onAbort = (): void => { - aborted = true - kill() - } + // runBash owns no timer: the executor's `run()` fuses timeout+cancel into one + // deadline signal (`@deepseek-ai/dsh-timeout`) and passes it here; we only + // listen and run the SIGTERM→grace→SIGKILL kill. Whether the abort was a + // timeout or an upstream cancel is classified by the executor from that + // signal, not tracked here. + const onAbort = (): void => { kill() } spec.signal?.addEventListener('abort', onAbort, { once: true }) // Write stdin and close it, but ONLY when the caller supplied bytes — with no @@ -376,14 +381,11 @@ export function runBash(spec: SpawnSpec, internals: RunInternals = {}): RunningB resolve({ exitCode, signal, - timedOut, - aborted, stdout: stdout.finalize(), stderr: stderr.finalize(), }) }) function cleanup(): void { - if (killTimer !== undefined) clearTimeout(killTimer) if (graceTimer !== undefined) clearTimeout(graceTimer) spec.signal?.removeEventListener('abort', onAbort) } diff --git a/packages/bash/bash-local/tests/executor.spec.ts b/packages/bash/bash-local/tests/executor.spec.ts index ce89b2a0ae..fcd06b8bb3 100644 --- a/packages/bash/bash-local/tests/executor.spec.ts +++ b/packages/bash/bash-local/tests/executor.spec.ts @@ -101,6 +101,8 @@ describe('LocalBashExecutor.run', () => { const { bash } = await setup({ timeoutMs: 60_000 }) const result = await bash.run(bash.resolve({ command: 'sleep 60', timeoutMs: 100 })) expect(result.timedOut).toBe(true) + // Mutually exclusive: a timeout classifies as timedOut, never also aborted. + expect(result.aborted).toBe(false) expect(result.timeoutMs).toBe(100) }) @@ -111,6 +113,20 @@ describe('LocalBashExecutor.run', () => { setTimeout(() => { controller.abort() }, 50) const result = await pending expect(result.aborted).toBe(true) + // Mutually exclusive: an upstream cancel classifies as aborted, never also timedOut. + expect(result.timedOut).toBe(false) + }) + + it('classifies a self-killed command as neither timed out nor aborted', async () => { + // The command kills itself (SIGTERM) with no timeout and no upstream abort: + // the deadline signal never fires, so both classifications are false — the + // fused-signal classification reports the cause that cut the command short, + // and here nothing the executor owns did. + const { bash } = await setup({ timeoutMs: 60_000 }) + const result = await bash.run(bash.resolve({ command: 'kill -TERM $$' })) + expect(result.signal).toBe('SIGTERM') + expect(result.timedOut).toBe(false) + expect(result.aborted).toBe(false) }) it('rejects on spawn failure (bad workdir)', async () => { diff --git a/packages/bash/bash-local/tests/run.spec.ts b/packages/bash/bash-local/tests/run.spec.ts index d2888e2fee..1103637b92 100644 --- a/packages/bash/bash-local/tests/run.spec.ts +++ b/packages/bash/bash-local/tests/run.spec.ts @@ -26,7 +26,6 @@ function spec(command: string, overrides: Partial[0]> return { command, cwd: process.cwd(), - timeoutMs: 0, maxOutputBytes: 64_000, graceMs: 3_000, ...overrides, @@ -61,8 +60,6 @@ describe('runBash', () => { const result = await runBash(spec('echo hello')).done expect(result.exitCode).toBe(0) expect(result.signal).toBeNull() - expect(result.timedOut).toBe(false) - expect(result.aborted).toBe(false) expect(result.stdout.text).toBe('hello\n') expect(result.stdout.truncated).toBe(false) expect(result.stderr.text).toBe('') @@ -97,11 +94,16 @@ describe('runBash', () => { expect(result.stdout.text.trim()).toMatch(/\/tmp$/) }) - it('kills with SIGTERM on timeout', async () => { + it('kills the process group with SIGTERM when the signal fires', async () => { + // runBash owns no timer: it kills on abort. The executor drives the timeout + // by firing this signal via a deadline (see executor.spec.ts); here we + // assert the kill itself lands as SIGTERM. + const controller = new AbortController() const start = Date.now() - const result = await runBash(spec('sleep 60', { timeoutMs: 100 })).done + const running = runBash(spec('sleep 60', { signal: controller.signal })) + setTimeout(() => { controller.abort('deadline') }, 100) + const result = await running.done expect(Date.now() - start).toBeLessThan(5_000) - expect(result.timedOut).toBe(true) expect(result.signal).toBe('SIGTERM') expect(result.exitCode).toBeNull() }) @@ -134,7 +136,6 @@ describe('runBash', () => { const running = runBash(spec('sleep 60', { signal: controller.signal })) setTimeout(() => { controller.abort('user cancelled') }, 50) const result = await running.done - expect(result.aborted).toBe(true) expect(result.signal).toBe('SIGTERM') }) @@ -211,7 +212,6 @@ describe('stdin and extra env (set by in-process plugins)', () => { const big = 'x'.repeat(1024 * 1024) const result = await runBash(spec('exit 7', { stdin: big })).done expect(result.exitCode).toBe(7) - expect(result.aborted).toBe(false) }) }) @@ -339,11 +339,11 @@ describe('abort edge cases', () => { .toThrow(/aborted before spawn: aborted/) }) - it('reports an externally self-killed command without the timeout marker', async () => { + it('reports the terminating signal of an externally self-killed command', async () => { + // runBash reports the raw signal; whether it counts as timeout/cancel is the + // executor's classification (a self-kill is neither) — see executor.spec.ts. const result = await runBash(spec('kill -TERM $$')).done expect(result.signal).toBe('SIGTERM') - expect(result.timedOut).toBe(false) - expect(result.aborted).toBe(false) }) }) @@ -396,10 +396,9 @@ describe('review fixes: env scrubbing and spill hardening', () => { it('honors AbortSignal on background-style runs (no timeout)', async () => { const controller = new AbortController() - const running = runBash(spec('sleep 60', { timeoutMs: 0, signal: controller.signal })) + const running = runBash(spec('sleep 60', { signal: controller.signal })) setTimeout(() => { controller.abort() }, 50) const result = await running.done - expect(result.aborted).toBe(true) expect(result.signal).toBe('SIGTERM') }) }) diff --git a/packages/bash/bash-local/tsconfig.json b/packages/bash/bash-local/tsconfig.json index ae31546543..02448770f4 100644 --- a/packages/bash/bash-local/tsconfig.json +++ b/packages/bash/bash-local/tsconfig.json @@ -20,6 +20,9 @@ { "path": "../../util/brand" }, + { + "path": "../../util/timeout" + }, { "path": "../../bash/bash" } diff --git a/packages/fs/README.md b/packages/fs/README.md index 985a9f3ad6..04f979b59f 100644 --- a/packages/fs/README.md +++ b/packages/fs/README.md @@ -10,3 +10,8 @@ The filesystem stack: a provider seam (text IO + atomic mutation with an optiona | `tool-fs/` | Model-facing `read`/`write`/`edit` tools AND the executor (reads via `ctx.fs`, owns read windowing, dispatches `fs/*`) | (registers on `ctx.tools`) | The interface lives at `fs/fs/`. A sandboxed, remote, or project-scoped filesystem backend can replace `fs-local` without touching the seam, the policy gate, or the model-facing tool schemas. The policy (`fs-policy/`) is a plugin that participates only through the `fs/*` event gate, not a service the tool injects — so dropping it gracefully loses the policy and leaves the unconstrained bare provider rather than breaking the tool. A deployment that loads `tool-fs/` is expected to also load it. + +## No timeouts on file IO + +`read`/`write`/`edit` take **no** `timeoutMs`, and the provider seam arms no deadline — unlike bash and web, which consume [`@deepseek-ai/dsh-timeout`](../util/timeout/README.md). A local syscall is best-effort-abortable at most: a timeout could not force an in-progress `fsync`/`rename` to stop, so a deadline here would be a knob that cannot deliver on its promise. Adding one would also be an implicit default in the exact place explicit-over-implicit forbids. Both reference agents (Claude Code, Codex) leave file IO untimed for the same reason; cancellation still propagates through the tool-execution signal for best-effort abort at syscall boundaries. + diff --git a/packages/util/README.md b/packages/util/README.md index ae73c8125f..45afe7b0a9 100644 --- a/packages/util/README.md +++ b/packages/util/README.md @@ -5,5 +5,8 @@ Zero-dependency primitives shared across the other groups. A package lands here | Package | Role | |---|---| | `brand/` | The type-only `Branded` nominal-typing primitive (no runtime code, no harness deps) | +| `timeout/` | The timing/classification half of a timeout — `clampTimeout`/`deadline`/`timeoutOf`/`TimeoutReason` (pure functions, no harness deps); termination stays in each capability | `dsh-brand` is the canonical case: it owns ONLY the `Branded` helper, so a capability package can brand the ids it owns (`dsh-bash`'s `BashTaskId`/`OwnerToken`, `dsh-session`'s `SessionId`, …) by depending on `dsh-brand` alone, without pulling in an unrelated package just to reach `Branded`. + +`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)). diff --git a/packages/util/timeout/README.md b/packages/util/timeout/README.md new file mode 100644 index 0000000000..4aa4485108 --- /dev/null +++ b/packages/util/timeout/README.md @@ -0,0 +1,40 @@ +# dsh-timeout + +The **timing-and-classification** half of a timeout — a zero-dependency library of pure functions (no runtime harness deps) shared by every capability that clamps a caller's timeout hint, arms a deadline, and later has to tell "timed out" apart from "cancelled". + +It owns **no termination**. The signal it hands out only *notifies*; actually stopping the work stays in each capability, because that mechanism differs — bash SIGKILLs an OS process group, web tears down a `fetch` socket — and no shared layer can own all of them. This is the boundary the [RFC](../../../docs/rfc/implemented/architecture/2026-07-06-timeout-deadline-library.md) draws: share the timing/classification, keep the hard kill local. + +It is a **library, not a service or plugin**: no `ctx`, registers nothing, holds no state, emits no events. A "timeout service" would have to understand how to stop every capability's work — exactly the knowledge a microkernel keeps out of shared layers. + +## Surface + +```ts +import { clampTimeout, deadline, timeoutOf, TimeoutReason } from '@deepseek-ai/dsh-timeout' +``` + +| Export | Role | +|---|---| +| `clampTimeout(requested, def, max, name?)` | Validate the caller's optional positive-finite hint, fill from `def`, cap at `max`. Throws (with `name`) on a non-positive/non-finite hint. | +| `deadline(upstream, timeoutMs, code)` | Fuse `upstream` cancellation with a timeout into one `AbortSignal` (`AbortSignal.any`); the timeout carries a `TimeoutReason`. `[Symbol.dispose]` clears the timer. | +| `timeoutOf(signal \| { reason })` | Recover the `TimeoutReason` from an aborted signal/error, else `undefined` — the timeout-vs-cancel classifier. | +| `TimeoutReason` | The internal reason (`code` + `timeoutMs`) stamped on a timeout abort. Not a public error — providers translate it into their own error/field. | + +## The `timeoutMs <= 0` sentinel + +`0` is the **internal** "no timeout" value for backend-owned background work (bash `start()`): `deadline()` arms no timer and forwards only `upstream`; with no upstream either, it returns a never-aborting signal plus a no-op disposer, so every caller keeps one call shape. External request hints validate as **positive finite** via `clampTimeout` before they reach `deadline`, so `0` is never a model-/plugin-facing "disable timeout" value. + +## Usage shape + +```ts ignore-check +// Scope-lifetime consumer (foreground bash, one fetch): `using` disposes the timer. +using d = deadline(upstream, timeoutMs, 'BASH_TIMEOUT') +const outcome = await runWork({ signal: d.signal }) // work listens on d.signal and terminates itself +const timedOut = timeoutOf(d.signal) !== undefined // classify the first abort +const aborted = d.signal.aborted && !timedOut // mutually exclusive: timeout won, or cancel did +``` + +The signal only *notifies* — the caller MUST attach its own termination (`d.signal.addEventListener('abort', kill)`, or hand `d.signal` to `fetch`). Racing a promise against a timer would resolve the tool-call while the child process or socket leaks on; handing out a signal forces a real termination path to exist. + +## What does NOT get a timeout + +Local file `read`/`write`/`edit` take no `timeoutMs`: a syscall is best-effort-abortable at most, a timeout could not force `fsync`/`rename` to stop, and adding one would be an implicit default that violates explicit-over-implicit. See [`fs/`](../../fs/README.md). diff --git a/packages/util/timeout/package.json b/packages/util/timeout/package.json new file mode 100644 index 0000000000..150a155324 --- /dev/null +++ b/packages/util/timeout/package.json @@ -0,0 +1,30 @@ +{ + "name": "@deepseek-ai/dsh-timeout", + "description": "Zero-dependency timeout/deadline primitive: clampTimeout, deadline, timeoutOf, TimeoutReason (timing + classification only, no termination)", + "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" + } +} diff --git a/packages/util/timeout/src/index.ts b/packages/util/timeout/src/index.ts new file mode 100644 index 0000000000..dbfc76adb4 --- /dev/null +++ b/packages/util/timeout/src/index.ts @@ -0,0 +1,149 @@ +/** + * The timing-and-classification half of a timeout — a zero-dependency library + * of pure functions shared by every capability that clamps a caller's timeout + * hint, arms a deadline, and later has to tell "timed out" apart from + * "cancelled". It owns NO termination: the returned {@link deadline} signal only + * NOTIFIES; actually stopping the work (SIGKILL a process group, tear down a + * fetch socket, …) stays in each capability's implementation, because that + * mechanism differs per capability and no shared layer can own all of them. + * + * This is deliberately a library, not a cordis service or plugin: it takes no + * `ctx`, registers nothing, holds no cross-call state, and emits no events. A + * "timeout service" would have to understand how to stop every capability's + * work — exactly the knowledge a microkernel keeps out of shared layers. + * + * The four exports and their division of labor: + * - {@link clampTimeout} — validate a caller's optional positive hint, fill the + * backend default, cap at the backend max (pure arithmetic + the shared + * positive-finite request contract). + * - {@link deadline} — fuse upstream cancellation with a timeout into one + * `AbortSignal`, the timeout carrying an identifiable {@link TimeoutReason}; + * `[Symbol.dispose]` clears the timer. + * - {@link timeoutOf} — classify an aborted signal (or error): a + * {@link TimeoutReason} means the timeout fired, anything else (or nothing) + * means it did not. + * - {@link TimeoutReason} — the internal classification reason; providers + * translate it into their own public error/result shape before returning. + * + * @module @deepseek-ai/dsh-timeout + */ + +/** + * The internal reason attached to a timeout abort so consumers can classify it + * after the fact. It carries the failing `code` (each capability's own string — + * `BASH_TIMEOUT`, `WEB_FETCH_TIMEOUT`, …) and the `timeoutMs` that elapsed. + * + * It is an INTERNAL classification reason, not a public error: providers + * translate it into their seam-specific error code or result field (via + * {@link timeoutOf}) before returning to callers. Native `AbortSignal.timeout()` + * yields a fixed `TimeoutError` indistinguishable across timeout kinds; this + * type is identifiable and carries the code/duration. + */ +export class TimeoutReason extends Error { + override name = 'TimeoutReason' + + /** + * @param code Capability-owned timeout code (e.g. `BASH_TIMEOUT`). + * @param timeoutMs The deadline that elapsed, in milliseconds. + */ + constructor(readonly code: string, readonly timeoutMs: number) { + super(`${code} after ${timeoutMs}ms`) + } +} + +/** + * Validate a caller's optional timeout hint, fill it from the backend default, + * then cap at the backend max. The shared positive-finite request contract: + * a supplied `requested` must be a positive finite number or this throws — + * `0` is NOT a caller-facing "disable timeout" value (that sentinel is internal + * to {@link deadline}). A missing `requested` falls back to `def`. + * + * @param requested The caller's optional hint; validated when present. + * @param def The backend default applied when `requested` is absent. + * @param max The backend upper bound the result is capped to. + * @param name Field name used in the thrown message (so the caller sees which input was bad). + * @returns The effective timeout in milliseconds: `min(requested ?? def, max)`. + */ +export function clampTimeout( + requested: number | undefined, + def: number, + max: number, + name = 'timeoutMs', +): number { + if (requested !== undefined && (!Number.isFinite(requested) || requested <= 0)) { + throw new Error(`${name} must be a positive finite number`) + } + return Math.min(requested ?? def, max) +} + +/** A deadline signal plus the cleanup that clears its timer (dispose-once). */ +export interface Deadline { + /** Aborts on upstream cancellation OR on timeout (the timeout carries a {@link TimeoutReason}). */ + readonly signal: AbortSignal + /** Clear the timer. Safe to call once; `using` calls it at scope exit. */ + [Symbol.dispose](): void +} + +/** + * Build a deadline signal that aborts on upstream cancellation OR on timeout, + * with the timeout carrying an identifiable {@link TimeoutReason} (unlike + * native `AbortSignal.timeout()`, whose fixed `TimeoutError` is opaque). It is + * `AbortSignal.any([upstream, ])` — the single primitive that fuses + * two abort sources — with the reason and a disposable timer added on top. + * + * `timeoutMs <= 0` is the INTERNAL "no timeout" sentinel for backend-owned + * background work: arm no timer and forward only the upstream signal; with no + * upstream either, return a never-aborting signal so callers keep one call + * shape. External request hints validate as positive finite via + * {@link clampTimeout} before reaching here, so `0` never arrives from a model + * or plugin. + * + * The returned object's `[Symbol.dispose]` clears the timer — use `using` for a + * scope-lifetime consumer, or call it manually for an event-lifetime one. The + * signal only NOTIFIES; the caller must attach its own termination (kill the + * process group, abort the fetch, …). + * + * @param upstream The caller's cancellation signal, if any, fused into the result. + * @param timeoutMs Deadline in milliseconds; `<= 0` means "no timeout" (arm no timer). + * @param code Capability-owned code stamped onto the timeout's {@link TimeoutReason}. + * @returns The fused {@link Deadline} (signal + timer cleanup). + */ +export function deadline( + upstream: AbortSignal | undefined, + timeoutMs: number, + code: string, +): Deadline { + if (timeoutMs <= 0) { + // No timeout (background work): forward only the upstream signal, or a + // never-aborting one when there is no upstream. No timer, so dispose is a + // no-op — the empty method keeps the one call shape for every caller. + return { signal: upstream ?? new AbortController().signal, [Symbol.dispose]() {} } + } + + const timer = new AbortController() + const id = setTimeout(() => { timer.abort(new TimeoutReason(code, timeoutMs)) }, timeoutMs) + return { + // AbortSignal.any adopts the reason of whichever source aborts FIRST, so a + // race resolves to a single cause: timeoutOf() reads TimeoutReason only + // when the timeout won, and upstream-wins leaves an ordinary abort reason. + signal: upstream !== undefined ? AbortSignal.any([upstream, timer.signal]) : timer.signal, + [Symbol.dispose]() { clearTimeout(id) }, + } +} + +/** + * Recover the {@link TimeoutReason} from an aborted signal (or any object with a + * `reason`), else `undefined`. This is the classification half: a provider + * calls it on the deadline signal after an abort to decide whether the cause + * was its timeout (translate to the capability's timeout error/field) or an + * ordinary upstream cancellation (`undefined` → the cancel path). + * + * @param x An {@link AbortSignal} or any `{ reason }` carrier (e.g. a caught abort error). + * @returns The {@link TimeoutReason} when the abort was a timeout, else `undefined`. + */ +export function timeoutOf(x: AbortSignal | { reason?: unknown }): TimeoutReason | undefined { + // AbortSignal.reason is typed `any`; pin it to `unknown` so no `any` leaks and + // the instanceof narrows cleanly for both a signal and a bare reason carrier. + const reason: unknown = x.reason + return reason instanceof TimeoutReason ? reason : undefined +} diff --git a/packages/util/timeout/tests/timeout.spec.ts b/packages/util/timeout/tests/timeout.spec.ts new file mode 100644 index 0000000000..4e60cf35b7 --- /dev/null +++ b/packages/util/timeout/tests/timeout.spec.ts @@ -0,0 +1,160 @@ +import { afterEach, describe, expect, it, vi } from 'vitest' +import { clampTimeout, deadline, timeoutOf, TimeoutReason } from '@deepseek-ai/dsh-timeout' + +describe('TimeoutReason', () => { + it('is an Error carrying the code and elapsed ms', () => { + const reason = new TimeoutReason('BASH_TIMEOUT', 100) + expect(reason).toBeInstanceOf(Error) + expect(reason.name).toBe('TimeoutReason') + expect(reason.code).toBe('BASH_TIMEOUT') + expect(reason.timeoutMs).toBe(100) + expect(reason.message).toBe('BASH_TIMEOUT after 100ms') + }) +}) + +describe('clampTimeout', () => { + it('fills the default when the hint is absent', () => { + expect(clampTimeout(undefined, 120_000, 600_000)).toBe(120_000) + }) + + it('caps the hint at max', () => { + expect(clampTimeout(999_999, 120_000, 600_000)).toBe(600_000) + }) + + it('keeps a valid hint under the cap', () => { + expect(clampTimeout(5_000, 120_000, 600_000)).toBe(5_000) + }) + + it('caps the default itself when the default exceeds max', () => { + // min(def, max) applies even with no hint — a misconfigured backend never + // exceeds its own cap. + expect(clampTimeout(undefined, 900_000, 600_000)).toBe(600_000) + }) + + it('rejects a non-finite hint with the caller-provided name', () => { + expect(() => clampTimeout(Number.NaN, 100, 200, 'bash-local: request.timeoutMs')) + .toThrow(/bash-local: request\.timeoutMs must be a positive finite number/) + expect(() => clampTimeout(Number.POSITIVE_INFINITY, 100, 200)) + .toThrow(/timeoutMs must be a positive finite number/) + }) + + it('rejects a non-positive hint', () => { + expect(() => clampTimeout(0, 100, 200)).toThrow(/must be a positive finite number/) + expect(() => clampTimeout(-1, 100, 200)).toThrow(/must be a positive finite number/) + }) +}) + +describe('deadline — timeout arm', () => { + afterEach(() => { vi.useRealTimers() }) + + it('aborts on timeout with a TimeoutReason after the elapsed ms', () => { + vi.useFakeTimers() + using d = deadline(undefined, 100, 'BASH_TIMEOUT') + expect(d.signal.aborted).toBe(false) + vi.advanceTimersByTime(100) + expect(d.signal.aborted).toBe(true) + const reason = timeoutOf(d.signal) + expect(reason).toBeInstanceOf(TimeoutReason) + expect(reason?.code).toBe('BASH_TIMEOUT') + expect(reason?.timeoutMs).toBe(100) + }) + + it('[Symbol.dispose] clears the timer so no abort fires afterward', () => { + vi.useFakeTimers() + const d = deadline(undefined, 100, 'BASH_TIMEOUT') + d[Symbol.dispose]() + vi.advanceTimersByTime(1_000) + expect(d.signal.aborted).toBe(false) + expect(timeoutOf(d.signal)).toBeUndefined() + }) +}) + +describe('deadline — fuse with upstream', () => { + it('aborts on upstream cancellation, classified as NOT a timeout', () => { + const upstream = new AbortController() + using d = deadline(upstream.signal, 60_000, 'BASH_TIMEOUT') + upstream.abort('user cancelled') + expect(d.signal.aborted).toBe(true) + expect(timeoutOf(d.signal)).toBeUndefined() + }) + + it('cancel wins when it fires before the timeout', () => { + vi.useFakeTimers() + try { + const upstream = new AbortController() + using d = deadline(upstream.signal, 100, 'BASH_TIMEOUT') + upstream.abort('user cancelled') // fires first, before the 100ms timer + vi.advanceTimersByTime(200) + expect(d.signal.aborted).toBe(true) + // AbortSignal.any adopts the FIRST source's reason: cancel won, so no + // TimeoutReason even though the timer later elapsed. + expect(timeoutOf(d.signal)).toBeUndefined() + } finally { + vi.useRealTimers() + } + }) + + it('timeout wins when it fires before upstream cancellation', () => { + vi.useFakeTimers() + try { + const upstream = new AbortController() + using d = deadline(upstream.signal, 100, 'WEB_FETCH_TIMEOUT') + vi.advanceTimersByTime(100) // timer fires first + upstream.abort('too late') + expect(timeoutOf(d.signal)?.code).toBe('WEB_FETCH_TIMEOUT') + } finally { + vi.useRealTimers() + } + }) + + it('forwards a pre-aborted upstream signal immediately', () => { + const upstream = new AbortController() + upstream.abort('already gone') + using d = deadline(upstream.signal, 60_000, 'BASH_TIMEOUT') + expect(d.signal.aborted).toBe(true) + expect(timeoutOf(d.signal)).toBeUndefined() + }) +}) + +describe('deadline — timeoutMs <= 0 (no-timeout sentinel)', () => { + afterEach(() => { vi.useRealTimers() }) + + it('arms no timer and forwards only the upstream signal', () => { + vi.useFakeTimers() + const upstream = new AbortController() + using d = deadline(upstream.signal, 0, 'BASH_TIMEOUT') + vi.advanceTimersByTime(1_000_000) + expect(d.signal.aborted).toBe(false) // no timer ever armed + upstream.abort('kill') + expect(d.signal.aborted).toBe(true) + expect(timeoutOf(d.signal)).toBeUndefined() // never a timeout + }) + + it('returns a never-aborting signal with a no-op disposer when there is no upstream', () => { + vi.useFakeTimers() + const d = deadline(undefined, 0, 'BASH_TIMEOUT') + expect(() => { d[Symbol.dispose]() }).not.toThrow() + vi.advanceTimersByTime(1_000_000) + expect(d.signal.aborted).toBe(false) + expect(timeoutOf(d.signal)).toBeUndefined() + }) + + it('treats a negative timeout the same as zero', () => { + const d = deadline(undefined, -5, 'BASH_TIMEOUT') + expect(d.signal.aborted).toBe(false) + d[Symbol.dispose]() + }) +}) + +describe('timeoutOf', () => { + it('classifies a bare reason carrier that holds a TimeoutReason', () => { + const reason = new TimeoutReason('WEB_FETCH_TIMEOUT', 50) + expect(timeoutOf({ reason })).toBe(reason) + }) + + it('returns undefined for a non-timeout reason', () => { + expect(timeoutOf({ reason: new Error('other') })).toBeUndefined() + expect(timeoutOf({ reason: 'user cancelled' })).toBeUndefined() + expect(timeoutOf({})).toBeUndefined() + }) +}) diff --git a/packages/util/timeout/tsconfig.json b/packages/util/timeout/tsconfig.json new file mode 100644 index 0000000000..749cb0208e --- /dev/null +++ b/packages/util/timeout/tsconfig.json @@ -0,0 +1,11 @@ +{ + "extends": "../../../tsconfig.base.json", + "compilerOptions": { + "rootDir": "src", + "outDir": "lib/types" + }, + "include": [ + "src" + ], + "references": [] +} diff --git a/packages/web/web-fetch-local/package.json b/packages/web/web-fetch-local/package.json index 8d9a599a52..9b847db6f3 100644 --- a/packages/web/web-fetch-local/package.json +++ b/packages/web/web-fetch-local/package.json @@ -22,6 +22,7 @@ ], "license": "BSD-3-Clause", "peerDependencies": { + "@deepseek-ai/dsh-timeout": "^0.0.1", "@deepseek-ai/dsh-web": "^0.0.1", "cordis": "^4.0.0-rc.6" }, @@ -29,6 +30,7 @@ "schemastery": "^3.18.0" }, "devDependencies": { + "@deepseek-ai/dsh-timeout": "workspace:^", "@deepseek-ai/dsh-web": "workspace:^", "cordis": "^4.0.0-rc.6" } diff --git a/packages/web/web-fetch-local/src/provider.ts b/packages/web/web-fetch-local/src/provider.ts index 29b183b710..53fc57f621 100644 --- a/packages/web/web-fetch-local/src/provider.ts +++ b/packages/web/web-fetch-local/src/provider.ts @@ -21,6 +21,7 @@ import { WebError } from '@deepseek-ai/dsh-web' import type { WebFetchBody, WebFetchProvider, WebFetchRequest, WebFetchResult, WebProviderStatus } from '@deepseek-ai/dsh-web' +import { clampTimeout, deadline, timeoutOf } from '@deepseek-ai/dsh-timeout' import { classifyContentType, decoderForCharset, isSameOrigin, parseCharset, validateFetchUrl } from './policy.ts' /** Resolved provider limits (the plugin's schemastery Config supplies defaults). */ @@ -56,35 +57,25 @@ export class LocalFetchProvider implements WebFetchProvider { } async fetch(request: WebFetchRequest, exec?: { readonly signal?: AbortSignal }): Promise { - const timeoutMs = request.timeoutMs !== undefined - ? Math.min(request.timeoutMs, this.limits.maxTimeoutMs) - : this.limits.timeoutMs + if (exec?.signal?.aborted) throw new WebError('web fetch aborted', 'WEB_ABORTED') + const timeoutMs = clampTimeout(request.timeoutMs, this.limits.timeoutMs, this.limits.maxTimeoutMs) - // One controller drives both the caller's abort and our own timeout, so the - // network request and the streaming read both stop on either. - const controller = new AbortController() - const onAbort = (): void => { controller.abort() } - if (exec?.signal !== undefined) { - if (exec.signal.aborted) throw new WebError('web fetch aborted', 'WEB_ABORTED') - exec.signal.addEventListener('abort', onAbort, { once: true }) - } - const timer = setTimeout(() => { controller.abort(new WebError('web fetch timed out', 'WEB_FETCH_TIMEOUT')) }, timeoutMs) - - try { - return await this.followAndRead(request.url, controller) - } finally { - clearTimeout(timer) - if (exec?.signal !== undefined) exec.signal.removeEventListener('abort', onAbort) - } + // One deadline signal fuses the caller's abort with our own timeout, so the + // network request and the streaming read both stop on either. The timeout + // abort carries a TimeoutReason we recover afterward to classify the cause + // (translateAbortOrNetwork), instead of hand-rolling a controller + timer + + // reason-recovery dance. + using d = deadline(exec?.signal, timeoutMs, 'WEB_FETCH_TIMEOUT') + return await this.followAndRead(request.url, d.signal) } /** Follow same-origin redirects up to the hop cap, then read the final response. */ - private async followAndRead(initialUrl: string, controller: AbortController): Promise { + private async followAndRead(initialUrl: string, signal: AbortSignal): Promise { let currentUrl = validateFetchUrl(initialUrl, this.limits.maxUrlLength) let redirectsFollowed = 0 for (;;) { - const response = await this.requestOnce(currentUrl, controller) + const response = await this.requestOnce(currentUrl, signal) if (isRedirectStatus(response.status)) { // The redirect budget is enforced BEFORE this hop's target is resolved @@ -127,20 +118,20 @@ export class LocalFetchProvider implements WebFetchProvider { continue } - return await this.readBody(response, currentUrl, controller.signal) + return await this.readBody(response, currentUrl, signal) } } - private async requestOnce(url: URL, controller: AbortController): Promise { + private async requestOnce(url: URL, signal: AbortSignal): Promise { try { return await fetch(url, { method: 'GET', redirect: 'manual', headers: { 'user-agent': this.limits.userAgent, 'accept': 'text/html,application/xhtml+xml,text/*;q=0.9,application/json;q=0.8' }, - signal: controller.signal, + signal, }) } catch (error: unknown) { - throw translateAbortOrNetwork(error, controller.signal) + throw translateAbortOrNetwork(error, signal) } } @@ -255,24 +246,17 @@ function resolveRedirect(location: string, base: URL): URL { } /** - * Translate a thrown fetch/stream error into a `WebError`. Our own - * `WEB_FETCH_TIMEOUT` (passed to `controller.abort(reason)`) and any other - * already-typed `WebError` pass through; an `AbortError` becomes `WEB_ABORTED`, - * UNLESS the abort was our timeout — the body-read reader surfaces a generic - * `AbortError` rather than the abort reason, so we recover the timeout's - * `WebError` from `signal.reason`; anything else is a transport/network failure - * (`WEB_PROVIDER_ERROR`). + * Translate a thrown fetch/stream error into a `WebError`, classified by the + * deadline signal rather than the error's shape (which differs by phase: the + * request-phase `fetch` rejects with the abort reason, while the read-phase + * reader surfaces a bare `AbortError`). `timeoutOf(signal)` recovering a + * `TimeoutReason` means our timeout fired (`WEB_FETCH_TIMEOUT`); any other abort + * is upstream cancellation (`WEB_ABORTED`); a throw with the signal NOT aborted + * is a transport/network failure (`WEB_PROVIDER_ERROR`). */ -function translateAbortOrNetwork(error: unknown, signal?: AbortSignal): WebError { - if (error instanceof WebError) return error - if (error instanceof DOMException && error.name === 'AbortError') { - // A timeout abort carries its WebError as the signal reason; honor the - // WEB_FETCH_TIMEOUT contract instead of reporting a generic cancellation. - // (Node rejects WITH the reason — the WebError branch above — so this only - // fires on a runtime that surfaces a bare AbortError while reason is set.) - /* v8 ignore next */ - if (signal?.reason instanceof WebError) return signal.reason - return new WebError('web fetch aborted', 'WEB_ABORTED', { cause: error }) - } +function translateAbortOrNetwork(error: unknown, signal: AbortSignal): WebError { + const timeout = timeoutOf(signal) + if (timeout !== undefined) return new WebError('web fetch timed out', 'WEB_FETCH_TIMEOUT', { cause: timeout }) + if (signal.aborted) return new WebError('web fetch aborted', 'WEB_ABORTED', { cause: error }) return new WebError(`web fetch failed: ${String(error)}`, 'WEB_PROVIDER_ERROR', { cause: error }) } diff --git a/packages/web/web-fetch-local/tsconfig.json b/packages/web/web-fetch-local/tsconfig.json index aa7c949fec..c6fb75a5c1 100644 --- a/packages/web/web-fetch-local/tsconfig.json +++ b/packages/web/web-fetch-local/tsconfig.json @@ -17,6 +17,9 @@ { "path": "../../../vendor/schemastery" }, + { + "path": "../../util/timeout" + }, { "path": "../web" } diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index d5fb68c746..54050bd0f4 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -93,6 +93,9 @@ importers: '@deepseek-ai/dsh-bash': specifier: workspace:^ version: link:../bash + '@deepseek-ai/dsh-timeout': + specifier: workspace:^ + version: link:../../util/timeout cordis: specifier: ^4.0.0-rc.6 version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4) @@ -960,6 +963,12 @@ importers: specifier: ^4.0.0-rc.6 version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4) + packages/util/timeout: + devDependencies: + cordis: + specifier: ^4.0.0-rc.6 + version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4) + packages/web/tool-web: dependencies: schemastery: @@ -1013,6 +1022,9 @@ importers: specifier: ^3.18.0 version: 3.18.0 devDependencies: + '@deepseek-ai/dsh-timeout': + specifier: workspace:^ + version: link:../../util/timeout '@deepseek-ai/dsh-web': specifier: workspace:^ version: link:../web diff --git a/tsconfig.build.json b/tsconfig.build.json index b6ba7901f2..ebf8ffef14 100644 --- a/tsconfig.build.json +++ b/tsconfig.build.json @@ -11,6 +11,7 @@ { "path": "./vendor/hmr" }, { "path": "./vendor/logger-console" }, { "path": "./packages/util/brand" }, + { "path": "./packages/util/timeout" }, { "path": "./packages/llm/llm" }, { "path": "./packages/core/session" }, { "path": "./packages/session-persistence/session-persistence" }, diff --git a/tsconfig.json b/tsconfig.json index 9cd7aa8a6d..49cce594dd 100644 --- a/tsconfig.json +++ b/tsconfig.json @@ -22,6 +22,7 @@ { "path": "./vendor/hmr" }, { "path": "./vendor/logger-console" }, { "path": "./packages/util/brand" }, + { "path": "./packages/util/timeout" }, { "path": "./packages/llm/llm" }, { "path": "./packages/core/session" }, { "path": "./packages/session-persistence/session-persistence" },