From 534b1dc6d063149297311dcfc45b625638e3dbb1 Mon Sep 17 00:00:00 2001 From: Dudu-0223 Date: Wed, 8 Jul 2026 14:37:42 +0800 Subject: [PATCH] refactor(timeout-policy): read budget from ToolDefinition, drop config The enforcer now reads ctx.tools.get(exec.name).timeoutMs instead of a free-text tool-name config map, so a mistyped name is impossible and the tools/change warn-once apparatus is gone. exec.name always resolves in the registry during dispatch, so there is no unknown-name path to warn about. --- packages/timeout/timeout-policy/README.md | 28 +-- packages/timeout/timeout-policy/src/index.ts | 119 +++------- .../tests/timeout-policy.spec.ts | 212 ++++-------------- 3 files changed, 82 insertions(+), 277 deletions(-) diff --git a/packages/timeout/timeout-policy/README.md b/packages/timeout/timeout-policy/README.md index bdf189ba7f..e637a658bf 100644 --- a/packages/timeout/timeout-policy/README.md +++ b/packages/timeout/timeout-policy/README.md @@ -1,47 +1,33 @@ # dsh-timeout-policy -Tool-call timeout policy: a single `tools/execute` around-dispatch listener that arms a per-call cooperative deadline on `exec.signal` for each configured tool and returns a structured `TOOL_TIMEOUT` result when that deadline wins. It is the reference `tools/execute` wrapper and the deployment-owned home for model-facing tool-call budgets (the timeout-library RFC's foreseen middleware). +Tool-call timeout enforcer: a single `tools/execute` around-dispatch listener that arms a per-call cooperative deadline on `exec.signal` for a tool declaring `timeoutMs` on its `ToolDefinition` and returns a structured `TOOL_TIMEOUT` result when that deadline wins. The budget is read from the tool's own declaration (`ToolDefinition.timeoutMs`, set by the owning tool plugin), so this plugin is **zero-config**. It is the reference `tools/execute` wrapper and the enforcement home for model-facing tool-call budgets (the timeout-library RFC's foreseen middleware). ## Plugin (namespace: `timeout-policy`) -A function/namespace plugin (`name` / `Config` / `apply`), not a service. It registers no tool and injects nothing — it consumes `ctx.tools`'s `tools/execute` waterfall, which the `dsh-tools` registry always provides. - -### Config - -Per-tool policy, keyed by the model-facing tool name. There is deliberately **no global default** (a global budget would silently start failing any tool that runs long once the plugin loads) and **no model-facing override** (timeout is deployment policy, not prompt semantics) in this version. +A function/namespace plugin (`name` / `inject` / `apply`), not a service. It registers no tool and takes no config — it consumes `ctx.tools`'s `tools/execute` waterfall (which the `dsh-tools` registry always provides) and reads each dispatched tool's declared `timeoutMs` from the registry (`ctx.tools.get(exec.name)`). ```yaml - id: timeout-policy name: '@deepseek-ai/dsh-timeout-policy' - config: - tools: - web_fetch: - timeoutMs: 30000 - web_search: - timeoutMs: 30000 ``` -| Key | Type | Meaning | -|---|---|---| -| `tools` | `Record` | Per-tool timeout policy; an unlisted tool gets no deadline. `timeoutMs` is required per configured tool and must be positive finite. | - -A configured tool name that never registers (a typo like `web_fech`, or a stale key) would silently apply the timeout to nothing. Because the tool set is dynamic (plugins register in `cordis.yml` order, HMR re-registers), this is not a load-time error — a real tool may register later. Instead, on every `tools/change` (and once at load) the plugin `logger.warn`s each configured name still absent from `ctx.tools`, warning each name at most once so a late registration silences it. This mirrors `dsh-tool-subagent`'s lifecycle-driven handling of a configured-but-unregistered provider name. +The per-tool budget is declared by the tool plugin (e.g. `dsh-tool-web`'s `fetchTimeoutMs`/`searchTimeoutMs` config, attached as `ToolDefinition.timeoutMs`); this plugin only enforces it, so a mistyped tool name is not possible. ### Behavior -For a **configured** tool the listener: +For a tool that **declares a `timeoutMs`** the listener: -1. Arms `deadline(exec.signal, timeoutMs, 'TOOL_TIMEOUT')` — one signal fusing the caller's abort with this plugin's timer (`@deepseek-ai/dsh-timeout`). +1. Reads the budget from the tool's own declaration in the registry (`ctx.tools.get(exec.name)?.timeoutMs`) and arms `deadline(exec.signal, timeoutMs, 'TOOL_TIMEOUT')` — one signal fusing the caller's abort with this plugin's timer (`@deepseek-ai/dsh-timeout`). 2. Swaps that derived signal onto `exec` for the downstream dispatch, then restores the caller's own signal afterward (cordis `next()` ignores passed arguments, so the wrapper mutates the shared `exec` in place; restoring keeps `tools/post-execute` seeing the caller's signal). 3. After dispatch, if `timeoutOf(d.signal, 'TOOL_TIMEOUT')` matches — this plugin's own timer fired — replaces the result with a structured `TOOL_TIMEOUT` tool result: `{ isError: true, error: { name: 'ToolTimeoutError', code: 'TOOL_TIMEOUT' }, content: 'Error: tool call timed out after ms' }`. -An **unconfigured** tool delegates untouched (no deadline). +A tool that **declares no budget** delegates untouched (no deadline). The base `next()` of `tools/execute` is the registry's dispatch-with-normalization thunk, so when the timeout signal reaches a provider that throws its own upstream-abort error, dispatch first turns it into a normal error result, and this wrapper then replaces that with `TOOL_TIMEOUT`. That ordering is why the replacement is keyed off the signal (`timeoutOf`), not off the dispatched result's shape. ### Cooperative, not a hard kill -The derived signal only **notifies**; termination stays with the tool and the capability it forwards `exec.signal` to (the `dsh-timeout` library owns no kill). **"Configured" therefore means "cooperative with `exec.signal`"**: a tool that ignores the signal will not stop on timeout. A deployment must only configure tools that forward the signal to their implementation — the shipped `web_fetch`/`web_search` (which forward through `ctx.web` to providers) are the reference. `TOOL_TIMEOUT` needs no session event for reconstructability: it is the final model-facing `tool/result`, already logged by the loop. +The derived signal only **notifies**; termination stays with the tool and the capability it forwards `exec.signal` to (the `dsh-timeout` library owns no kill). **Declaring `timeoutMs` therefore means "cooperative with `exec.signal`"**: a tool that ignores the signal will not stop on timeout. Only signal-forwarding tools should declare it — the shipped `web_fetch`/`web_search` (which forward through `ctx.web` to providers) are the reference. `TOOL_TIMEOUT` needs no session event for reconstructability: it is the final model-facing `tool/result`, already logged by the loop. ### Composing with other `tools/execute` wrappers diff --git a/packages/timeout/timeout-policy/src/index.ts b/packages/timeout/timeout-policy/src/index.ts index b57091fe91..319de676a9 100644 --- a/packages/timeout/timeout-policy/src/index.ts +++ b/packages/timeout/timeout-policy/src/index.ts @@ -1,16 +1,20 @@ /** - * `@deepseek-ai/dsh-timeout-policy`: the tool-call timeout policy plugin. It - * registers ONE `tools/execute` around-dispatch listener that, for each - * configured tool, arms a per-call deadline on `exec.signal` and returns a - * structured `TOOL_TIMEOUT` result when that deadline wins. + * `@deepseek-ai/dsh-timeout-policy`: the tool-call timeout ENFORCER. It registers + * ONE `tools/execute` around-dispatch listener that, for a tool declaring a + * `timeoutMs` on its {@link ToolDefinition}, arms a per-call deadline on + * `exec.signal` and returns a structured `TOOL_TIMEOUT` result when that deadline + * wins. The budget is DECLARED by the tool (see `ToolDefinition.timeoutMs`, set + * by the owning tool plugin from its own config); this plugin only enforces it, + * so it is zero-config and there is no tool-name map to mistype. * * This is a COOPERATIVE deadline, not a hard kill: the derived signal only - * NOTIFIES. A configured tool (and the capability it forwards `exec.signal` to) - * must honor that signal and reach quiescence — the plugin never races the tool - * promise or terminates work itself (see the timeout-library RFC's rejection of - * `Promise.race`). "Configured" therefore MEANS "cooperative with `exec.signal`": - * a tool that ignores the signal will not stop on timeout, so a deployment must - * only list tools that forward it (the shipped web tools are the reference). + * NOTIFIES. A tool that declares `timeoutMs` (and the capability it forwards + * `exec.signal` to) must honor that signal and reach quiescence — the plugin + * never races the tool promise or terminates work itself (see the timeout-library + * RFC's rejection of `Promise.race`). Declaring `timeoutMs` therefore MEANS "this + * tool is cooperative with `exec.signal`": a tool that ignores the signal will + * not stop on timeout, so only signal-forwarding tools should declare it (the + * shipped web tools are the reference). * * Ownership of the `TOOL_TIMEOUT` code is entirely here: it is both the internal * {@link deadline} code (so {@link timeoutOf} scopes the classification to THIS @@ -29,7 +33,6 @@ */ import type { Context } from 'cordis' -import z from 'schemastery' import type { CallId } from '@deepseek-ai/dsh-llm' import { deadline, timeoutOf } from '@deepseek-ai/dsh-timeout' import type { ToolExecutionResult } from '@deepseek-ai/dsh-tools' @@ -46,40 +49,9 @@ export const TOOL_TIMEOUT = 'TOOL_TIMEOUT' /** Cordis plugin name used by loader diagnostics. */ export const name = 'timeout-policy' -/** The tool registry seam this plugin wraps (`tools/execute`) and reads (`tools/change`, `get`). */ +/** The tool registry seam this plugin wraps (`tools/execute`) and reads (`get`). */ export const inject = ['tools'] -/** Per-tool timeout policy. `timeoutMs` is required and must be positive finite. */ -export interface ToolTimeoutPolicy { - /** The per-call cooperative deadline for this tool, in milliseconds. */ - timeoutMs: number -} - -/** - * Plugin config: per-tool timeout policy, keyed by the model-facing tool name. - * There is deliberately NO global default (a global budget would silently start - * failing any tool that happens to run long once the plugin loads) and NO model - * override (timeout is deployment policy, not prompt semantics) in this version. - */ -export interface Config { - /** Timeout policy per tool name; an unlisted tool gets no deadline from this plugin. */ - tools?: Record -} - -export const Config: z = z.object({ - tools: z.dict(z.object({ timeoutMs: z.number() })).default({}), -}) - -/** The shape after schemastery fills `tools` with its `{}` default. */ -type ResolvedConfig = Required - -/** A per-tool timeout must be a positive finite number (0 is not a "disable" value). */ -function assertPositiveFinite(toolName: string, value: number): void { - if (!Number.isFinite(value) || value <= 0) { - throw new Error(`timeout-policy: tools.${toolName}.timeoutMs must be a positive finite number`) - } -} - /** * The structured result substituted when this plugin's deadline wins. `content` * is the model-facing message; `error.code` is the same {@link TOOL_TIMEOUT} @@ -99,56 +71,23 @@ export function toolTimeoutResult(callId: CallId, timeoutMs: number): ToolExecut } /** - * Register the tool-call timeout policy. For a configured tool the listener arms - * a {@link deadline} on the caller's `exec.signal`, swaps it onto `exec` for the - * downstream dispatch (cordis `next()` ignores passed arguments, so a wrapper - * mutates the shared `exec` in place), restores the original signal afterward so - * `tools/post-execute` sees the caller's own signal, and replaces the result - * with {@link toolTimeoutResult} when its own timer fired. An unconfigured tool - * delegates untouched. + * Register the tool-call timeout enforcer. For a tool whose {@link ToolDefinition} + * declares `timeoutMs`, the listener arms a {@link deadline} on the caller's + * `exec.signal`, swaps it onto `exec` for the downstream dispatch (cordis + * `next()` ignores passed arguments, so a wrapper mutates the shared `exec` in + * place), restores the original signal afterward so `tools/post-execute` sees the + * caller's own signal, and replaces the result with {@link toolTimeoutResult} + * when its own timer fired. A tool that declares no budget delegates untouched. * - * A configured tool name that is never registered is almost always a typo or a - * stale config key (e.g. `web_fech` for `web_fetch`): the wrapper would then - * silently never fire for the intended tool. Since the tool set is dynamic - * (plugins register in `cordis.yml` order, and HMR re-registers), this cannot - * be a load-time hard error — a real tool may register later. Instead, mirror - * `dsh-tool-subagent`'s lifecycle-driven approach: on every `tools/change` (and - * once at apply), `logger.warn` each configured name still absent from the - * registry, warning each name at most once so a late registration silences it. + * The budget source is the tool's own declaration read from the registry + * (`ctx.tools.get(exec.name)?.timeoutMs`), NOT a plugin config map — `exec.name` + * is the tool being dispatched, so the lookup always resolves and there is no + * mistypable tool name and no unknown-name path to warn or throw about. */ -export function apply(ctx: Context, config: Config): void { - // schemastery (Config) has already filled `tools` with its {} default. - const resolved = config as ResolvedConfig - for (const [toolName, policy] of Object.entries(resolved.tools)) { - assertPositiveFinite(toolName, policy.timeoutMs) - } - - // Warn once per configured name that no registered tool matches, so a typo'd - // or stale config key is visible instead of silently applying to nothing. A - // name that later registers is dropped from `pending` before it is warned; a - // name that never registers is warned at most once (moved to `warned`), so a - // busy `tools/change` stream cannot spam the same key. - const pending = new Set(Object.keys(resolved.tools)) - const warned = new Set() - const warnUnknownToolNames = (): void => { - const nowUnknown: string[] = [] - for (const name of pending) { - if (ctx.tools.get(name) !== undefined) { pending.delete(name); continue } - if (!warned.has(name)) { warned.add(name); nowUnknown.push(name) } - } - if (nowUnknown.length > 0) { - ctx.logger.warn( - `timeout-policy: configured timeout for unregistered tool(s) ${nowUnknown.map(n => `"${n}"`).join(', ')} ` - + '— check for a typo or stale config key; the timeout applies to nothing until the tool registers.', - ) - } - } - ctx.on('tools/change', warnUnknownToolNames) - warnUnknownToolNames() - +export function apply(ctx: Context): void { ctx.on('tools/execute', async (exec, next): Promise => { - const timeoutMs = resolved.tools[exec.name]?.timeoutMs - // Unconfigured tool: no deadline, delegate unchanged. + const timeoutMs = ctx.tools.get(exec.name)?.timeoutMs + // A tool that declares no budget: no deadline, delegate unchanged. if (timeoutMs === undefined) return next() using d = deadline(exec.signal, timeoutMs, TOOL_TIMEOUT) diff --git a/packages/timeout/timeout-policy/tests/timeout-policy.spec.ts b/packages/timeout/timeout-policy/tests/timeout-policy.spec.ts index 967e5659ed..ef5c52030f 100644 --- a/packages/timeout/timeout-policy/tests/timeout-policy.spec.ts +++ b/packages/timeout/timeout-policy/tests/timeout-policy.spec.ts @@ -15,188 +15,86 @@ import ToolRegistry, { defineTool, type ToolExecution, type ToolExecutionResult, import * as timeoutPolicy from '@deepseek-ai/dsh-timeout-policy' import { TOOL_TIMEOUT, toolTimeoutResult } from '@deepseek-ai/dsh-timeout-policy' -/** Mount the registry + the timeout-policy plugin with the given per-tool config. */ -async function setup(tools: Record = {}) { +/** Mount the registry + the zero-config timeout-policy enforcer. */ +async function setup() { const ctx = new Context() await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) - await ctx.plugin(timeoutPolicy, { tools }) + await ctx.plugin(timeoutPolicy) return ctx } -/** A fast tool: returns immediately, ignoring the signal. */ -const fastTool = defineTool({ - name: 'fast', - description: 'returns at once', - parameters: {}, - async execute() { return [{ type: 'text' as const, text: 'ok' }] }, -}) - /** A cooperative tool that settles ONLY when its exec.signal aborts (returns text). */ const cooperativeTool = defineTool({ - name: 'slow', - description: 'stops when aborted', - parameters: {}, + name: 'slow', description: 'stops when aborted', parameters: {}, timeoutMs: 100, execute(_args, exec): Promise<{ type: 'text'; text: string }[]> { const done = [{ type: 'text' as const, text: 'stopped cooperatively' }] if (exec.signal?.aborted) return Promise.resolve(done) - return new Promise((resolve) => { - exec.signal?.addEventListener('abort', () => { resolve(done) }) - }) + return new Promise((resolve) => { exec.signal?.addEventListener('abort', () => { resolve(done) }) }) }, }) /** A cooperative tool that THROWS its own upstream-abort error when aborted (web-provider shape). */ const abortThrowingTool = defineTool({ - name: 'aborter', - description: 'throws WEB_ABORTED when aborted', - parameters: {}, + name: 'aborter', description: 'throws WEB_ABORTED when aborted', parameters: {}, timeoutMs: 100, execute(_args, exec): Promise { if (exec.signal?.aborted) return Promise.reject(new HarnessError('web fetch aborted', 'WEB_ABORTED')) - return new Promise((_resolve, reject) => { - exec.signal?.addEventListener('abort', () => { reject(new HarnessError('web fetch aborted', 'WEB_ABORTED')) }) - }) + return new Promise((_resolve, reject) => { exec.signal?.addEventListener('abort', () => { reject(new HarnessError('web fetch aborted', 'WEB_ABORTED')) }) }) }, }) -describe('timeout-policy config validation', () => { - it('rejects a non-positive timeout at apply', async () => { - const ctx = new Context() - await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry) - await expect(ctx.plugin(timeoutPolicy, { tools: { web_fetch: { timeoutMs: 0 } } })) - .rejects.toThrow('tools.web_fetch.timeoutMs must be a positive finite number') - }) - - it('rejects a non-finite timeout at apply', async () => { - const ctx = new Context() - await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry) - await expect(ctx.plugin(timeoutPolicy, { tools: { web_fetch: { timeoutMs: Infinity } } })) - .rejects.toThrow('must be a positive finite number') - }) - - it('mounts with no config (empty tools default) and delegates every call', async () => { - const ctx = await setup() - ctx.tools.register(fastTool) - const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'fast', arguments: {} }) - expect(result).toEqual({ callId: CallId('c1'), content: [{ type: 'text', text: 'ok' }], isError: false }) - }) -}) - -describe('timeout-policy unknown-tool-name diagnostics', () => { - it('warns for a configured tool name that is never registered (typo/stale key)', async () => { - const ctx = new Context() - await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry) - const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) - // web_fech is a typo for web_fetch, and no tool by that name is registered. - await ctx.plugin(timeoutPolicy, { tools: { web_fech: { timeoutMs: 30_000 } } }) - expect(warn).toHaveBeenCalledTimes(1) - expect(warn.mock.calls[0]?.[0]).toContain('"web_fech"') - expect(warn.mock.calls[0]?.[0]).toContain('unregistered tool') - }) - - it('does NOT warn when the configured tool is already registered at load', async () => { - const ctx = new Context() - await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry) - ctx.tools.register(fastTool) - const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) - await ctx.plugin(timeoutPolicy, { tools: { fast: { timeoutMs: 30_000 } } }) - expect(warn).not.toHaveBeenCalled() - }) - - it('does NOT warn once a configured tool registers LATER (load-order safe)', async () => { - const ctx = new Context() - await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry) - const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) - // Plugin loads before the tool it configures — the initial check would warn, - // so register first is the interesting case: mount with a not-yet-present - // name, then register it; the tools/change listener must clear it. - await ctx.plugin(timeoutPolicy, { tools: { late: { timeoutMs: 30_000 } } }) - expect(warn).toHaveBeenCalledTimes(1) // absent at load → warned once - warn.mockClear() - ctx.tools.register({ ...fastTool, name: 'late' }) // now it registers - // A subsequent tools/change must NOT re-warn the now-registered name. - ctx.tools.register({ ...fastTool, name: 'other' }) - expect(warn).not.toHaveBeenCalled() - }) - - it('warns at most once per unknown name across repeated tools/change', async () => { - const ctx = new Context() - await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry) - const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) - await ctx.plugin(timeoutPolicy, { tools: { ghost: { timeoutMs: 30_000 } } }) - expect(warn).toHaveBeenCalledTimes(1) // apply-time check - // Each register/unregister emits tools/change; the ghost stays unknown but - // must not be warned again. - const dispose = ctx.tools.register(fastTool) - dispose() - ctx.tools.register({ ...fastTool, name: 'another' }) - expect(warn).toHaveBeenCalledTimes(1) - }) -}) - describe('timeout-policy delegation (unconfigured / fast)', () => { - it('delegates an UNCONFIGURED tool unchanged and does not touch exec.signal', async () => { - const ctx = await setup({ other: { timeoutMs: 50 } }) + it('delegates a tool with NO declared budget unchanged and does not touch exec.signal', async () => { + const ctx = await setup() let seenSignal: AbortSignal | undefined - ctx.tools.register({ ...fastTool, name: 'probe', async execute(_a, exec) { seenSignal = exec.signal; return [{ type: 'text' as const, text: 'ok' }] } }) - + ctx.tools.register(defineTool({ name: 'probe', description: 'd', parameters: {}, + async execute(_a, exec) { seenSignal = exec.signal; return [{ type: 'text' as const, text: 'ok' }] } })) const upstream = new AbortController().signal const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'probe', arguments: {}, signal: upstream }) expect(result.isError).toBe(false) - expect(seenSignal).toBe(upstream) // no deadline derived for an unconfigured tool + expect(seenSignal).toBe(upstream) }) - it('a configured tool that returns fast keeps its own result (no timeout)', async () => { - const ctx = await setup({ fast: { timeoutMs: 10_000 } }) - ctx.tools.register(fastTool) + it('a tool with a budget that returns fast keeps its own result (no timeout)', async () => { + const ctx = await setup() + ctx.tools.register(defineTool({ name: 'fast', description: 'd', parameters: {}, timeoutMs: 10_000, + async execute() { return [{ type: 'text' as const, text: 'ok' }] } })) const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'fast', arguments: {} }) expect(result).toEqual({ callId: CallId('c1'), content: [{ type: 'text', text: 'ok' }], isError: false }) }) - it('a configured tool receives the DERIVED deadline signal (not the caller signal) during dispatch', async () => { - const ctx = await setup({ probe: { timeoutMs: 10_000 } }) + it('a budgeted tool receives the DERIVED deadline signal (not the caller signal) during dispatch', async () => { + const ctx = await setup() let seenSignal: AbortSignal | undefined - ctx.tools.register({ ...fastTool, name: 'probe', async execute(_a, exec) { seenSignal = exec.signal; return [{ type: 'text' as const, text: 'ok' }] } }) - + ctx.tools.register(defineTool({ name: 'probe', description: 'd', parameters: {}, timeoutMs: 10_000, + async execute(_a, exec) { seenSignal = exec.signal; return [{ type: 'text' as const, text: 'ok' }] } })) const upstream = new AbortController().signal await ctx.tools.execute({ callId: CallId('c1'), name: 'probe', arguments: {}, signal: upstream }) expect(seenSignal).toBeDefined() - expect(seenSignal).not.toBe(upstream) // the plugin swapped in its fused deadline signal + expect(seenSignal).not.toBe(upstream) }) }) describe('timeout-policy signal restoration', () => { it('restores the caller signal for post-execute after wrapping', async () => { - const ctx = await setup({ fast: { timeoutMs: 10_000 } }) - ctx.tools.register(fastTool) + const ctx = await setup() + ctx.tools.register(defineTool({ name: 'fast', description: 'd', parameters: {}, timeoutMs: 10_000, + async execute() { return [{ type: 'text' as const, text: 'ok' }] } })) let postSignal: AbortSignal | undefined | 'unset' = 'unset' - ctx.on('tools/post-execute', async (exec, _result, next): Promise => { - postSignal = exec.signal - return next() - }) - + ctx.on('tools/post-execute', async (exec, _result, next): Promise => { postSignal = exec.signal; return next() }) const upstream = new AbortController().signal await ctx.tools.execute({ callId: CallId('c1'), name: 'fast', arguments: {}, signal: upstream }) - expect(postSignal).toBe(upstream) // restored to the caller's own signal, not the deadline + expect(postSignal).toBe(upstream) }) it('deletes exec.signal again when the caller passed none', async () => { - const ctx = await setup({ fast: { timeoutMs: 10_000 } }) - ctx.tools.register(fastTool) + const ctx = await setup() + ctx.tools.register(defineTool({ name: 'fast', description: 'd', parameters: {}, timeoutMs: 10_000, + async execute() { return [{ type: 'text' as const, text: 'ok' }] } })) let hadSignal: boolean | undefined - ctx.on('tools/post-execute', async (exec, _result, next): Promise => { - hadSignal = 'signal' in exec && exec.signal !== undefined - return next() - }) - + ctx.on('tools/post-execute', async (exec, _result, next): Promise => { hadSignal = 'signal' in exec && exec.signal !== undefined; return next() }) await ctx.tools.execute({ callId: CallId('c1'), name: 'fast', arguments: {} }) - expect(hadSignal).toBe(false) // no caller signal → exec.signal absent again after wrapping + expect(hadSignal).toBe(false) }) }) @@ -205,13 +103,11 @@ describe('timeout-policy TOOL_TIMEOUT replacement (deadline wins)', () => { afterEach(() => { vi.useRealTimers() }) it('replaces a cooperative tool result with TOOL_TIMEOUT when its own deadline fires', async () => { - const ctx = await setup({ slow: { timeoutMs: 100 } }) + const ctx = await setup() ctx.tools.register(cooperativeTool) - const pending = ctx.tools.execute({ callId: CallId('c1'), name: 'slow', arguments: {} }) - await vi.advanceTimersByTimeAsync(150) // past the 100ms deadline: the timer fires, the tool settles + await vi.advanceTimersByTimeAsync(150) const result = await pending - expect(result).toEqual({ callId: CallId('c1'), content: [{ type: 'text', text: 'Error: tool call timed out after 100ms' }], @@ -220,33 +116,25 @@ describe('timeout-policy TOOL_TIMEOUT replacement (deadline wins)', () => { }) }) - it('replaces a provider-owned abort ERROR result with TOOL_TIMEOUT (not WEB_ABORTED) when the signal was ours', async () => { - const ctx = await setup({ aborter: { timeoutMs: 100 } }) + it('replaces a provider-owned abort ERROR result with TOOL_TIMEOUT when the signal was ours', async () => { + const ctx = await setup() ctx.tools.register(abortThrowingTool) - const pending = ctx.tools.execute({ callId: CallId('c1'), name: 'aborter', arguments: {} }) await vi.advanceTimersByTimeAsync(150) const result = await pending - - // Dispatch first normalized the thrown WEB_ABORTED into an isError result; - // the plugin then replaced THAT with TOOL_TIMEOUT because its own timer won. expect(result.isError).toBe(true) expect(result.error).toEqual({ name: 'ToolTimeoutError', code: 'TOOL_TIMEOUT' }) expect(result.content[0]).toMatchObject({ text: 'Error: tool call timed out after 100ms' }) }) it('does NOT replace when the caller aborts first (upstream cancel, not our timeout)', async () => { - const ctx = await setup({ slow: { timeoutMs: 100 } }) + const ctx = await setup() ctx.tools.register(cooperativeTool) - const upstream = new AbortController() const pending = ctx.tools.execute({ callId: CallId('c1'), name: 'slow', arguments: {}, signal: upstream.signal }) - upstream.abort('user cancelled') // fires before the 100ms timer + upstream.abort('user cancelled') await vi.advanceTimersByTimeAsync(0) const result = await pending - - // Our timer never fired, so timeoutOf(code) is undefined: the tool's own - // cooperative result stands, not a TOOL_TIMEOUT. expect(result.isError).toBe(false) expect(result.content[0]).toMatchObject({ text: 'stopped cooperatively' }) }) @@ -273,46 +161,38 @@ describe('timeout-policy disposal (HMR safety)', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) let seenSignal: AbortSignal | undefined - ctx.tools.register({ ...fastTool, name: 'probe', async execute(_a, exec) { seenSignal = exec.signal; return [{ type: 'text' as const, text: 'ok' }] } }) - - // Mount the policy on its OWN fiber so disposing it removes only the wrapper. - const fiber = await ctx.plugin(timeoutPolicy, { tools: { probe: { timeoutMs: 10_000 } } }) + ctx.tools.register(defineTool({ name: 'probe', description: 'd', parameters: {}, timeoutMs: 10_000, + async execute(_a, exec) { seenSignal = exec.signal; return [{ type: 'text' as const, text: 'ok' }] } })) + const fiber = await ctx.plugin(timeoutPolicy) const upstream = new AbortController().signal await ctx.tools.execute({ callId: CallId('c1'), name: 'probe', arguments: {}, signal: upstream }) - expect(seenSignal).not.toBe(upstream) // wrapper live: dispatch saw the derived deadline signal - + expect(seenSignal).not.toBe(upstream) await fiber.dispose() - // Listener gone: the tool now receives the caller's own signal unwrapped. A - // leaked stale wrapper would still derive a deadline and fail this. await ctx.tools.execute({ callId: CallId('c2'), name: 'probe', arguments: {}, signal: upstream }) expect(seenSignal).toBe(upstream) }) }) describe('dsh-timeout-policy real-load-path guard', () => { - it('has no default export and keeps name/inject/Config through unwrapExports', () => { + it('has no default export and keeps name/inject through unwrapExports', () => { expect('default' in timeoutPolicy).toBe(false) - const loader = Object.create(Loader.prototype) as Loader const unwrapped = loader.unwrapExports(timeoutPolicy) as Record expect(unwrapped).toBe(timeoutPolicy) expect(unwrapped.name).toBe('timeout-policy') expect(unwrapped.inject).toEqual(['tools']) expect(typeof unwrapped.apply).toBe('function') - expect(unwrapped.Config).toBeDefined() }) - it('boots over ctx.tools through the unwrapped module and wraps a configured tool', async () => { + it('boots over ctx.tools through the unwrapped module and wraps a budgeted tool', async () => { const ctx = new Context() await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) - ctx.tools.register(fastTool) - + ctx.tools.register(defineTool({ name: 'fast', description: 'd', parameters: {}, timeoutMs: 5_000, + async execute() { return [{ type: 'text' as const, text: 'ok' }] } })) const loader = Object.create(Loader.prototype) as Loader const unwrapped = loader.unwrapExports(timeoutPolicy) as Parameters[0] - const fiber = await ctx.plugin(unwrapped, { tools: { fast: { timeoutMs: 5_000 } } }) - // A configured fast tool still succeeds (deadline never fires); this proves - // the wrapper is live through the real Loader path. + const fiber = await ctx.plugin(unwrapped) const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'fast', arguments: {} } satisfies ToolExecution) expect(result.isError).toBe(false) await fiber.dispose()