diff --git a/examples/acp-agent/tests/acp.snapshot.ts b/examples/acp-agent/tests/acp.snapshot.ts index fbc6af65b4..5a22209c16 100644 --- a/examples/acp-agent/tests/acp.snapshot.ts +++ b/examples/acp-agent/tests/acp.snapshot.ts @@ -408,6 +408,20 @@ describe('snapshot fixtures', () => { }) }) + it('every pinning fixture carries exactly one request/header and no deltas', async () => { + // The live uniformity guard runs only in NON-pinning scenarios, so a + // class made of just its pinning scenario (the Code Mode classes) would + // otherwise accept a re-recorded pin with several headers or a mid-run + // header-delta — shapes the pin design cannot represent. Assert the + // committed pins directly. + for (const scenario of pinningByClass.values()) { + const fixture = await readFile(join(SNAPSHOTS_DIR, scenario.name, 'session.jsonl'), 'utf8') + const headers = normalizedHeaders(fixture, fixtureContext(fixture)) + expect(headers.length, `${scenario.name}: a pinning fixture must carry exactly one request/header`).toBe(1) + expect(headerDeltaCount(fixture), `${scenario.name}: a pinning fixture must carry no request/header-delta`).toBe(0) + } + }) + it('committed fixtures carry request-header content ONLY in the pinning scenario', async () => { // The whole point of the pin: a system-prompt or tool-schema change must // churn exactly one committed line. A non-pinning fixture that carries the diff --git a/packages/core/tools/src/code-mode.ts b/packages/core/tools/src/code-mode.ts index be3b7c91af..904c65ef0e 100644 --- a/packages/core/tools/src/code-mode.ts +++ b/packages/core/tools/src/code-mode.ts @@ -87,17 +87,21 @@ function summarize(text: string): string { } /** - * JSON-normalize one binding call's argument: a `JSON.parse(JSON.stringify(…))` - * round-trip, so the value dispatched to the tool and the value logged on the - * `tool/code-dispatch` event are the same JSON value by construction (the - * runtime's structured-clone boundary is wider than JSON; the session log - * accepts only JSON). A value that does not survive (`BigInt`, a circular - * structure, a bare function) rejects that one call with a model-correctable - * error. `undefined` passes through — the tool's own schema validation - * rejects it with its usual "must be an object" feedback. + * JSON-normalize one binding call's argument into TWO independent parses of + * the same canonical text: `dispatched` goes to the tool, `logged` to the + * `tool/code-dispatch` event — identical by construction (the runtime's + * structured-clone boundary is wider than JSON; the session log accepts only + * JSON), and separate objects, so a tool mutating its args can neither + * desync the log from what was dispatched nor re-poison the append. A value + * that does not survive the round-trip (`undefined` — the log rejects it as + * event data — `BigInt`, a circular structure, a bare function) rejects that + * one call BEFORE dispatch with a model-correctable error: nothing ever + * executes unlogged. */ -function jsonNormalizeArgs(value: unknown): unknown { - if (value === undefined) return undefined +function jsonNormalizeArgs(value: unknown): { dispatched: unknown; logged: unknown } { + if (value === undefined) { + throw new Error('tool arguments must be JSON-serializable (call the tool with an arguments object, e.g. `{}`)') + } let text: string | undefined try { text = JSON.stringify(value) @@ -108,7 +112,7 @@ function jsonNormalizeArgs(value: unknown): unknown { // root really yields `undefined` at runtime — the guard is live. // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition if (text === undefined) throw new Error('tool arguments must be JSON-serializable (got a value JSON cannot represent)') - return JSON.parse(text) as unknown + return { dispatched: JSON.parse(text) as unknown, logged: JSON.parse(text) as unknown } } /** Render the program's completion value for the model-facing result text (`''` when the program returned nothing). */ @@ -198,7 +202,7 @@ export function createRunCodeTool(registry: ToolRegistry, requireRuntime: () => const result = await registry.execute({ callId: subCallId, name, - arguments: normalized, + arguments: normalized.dispatched, ...exec.agent ? { agent: exec.agent } : {}, signal: runController.signal, }) @@ -212,7 +216,10 @@ export function createRunCodeTool(registry: ToolRegistry, requireRuntime: () => parentCallId: exec.callId, subCallId, name, - arguments: normalized, + // The SIBLING parse of the dispatched value: byte-identical JSON, + // but a separate object — a tool mutating its args cannot desync + // this record from what it actually received. + arguments: normalized.logged, isError: result.isError, resultSummary: summarize(text), }) @@ -231,10 +238,15 @@ export function createRunCodeTool(registry: ToolRegistry, requireRuntime: () => return outcome.text } - const functions: Record = {} + // Null-prototype + defineProperty, mirroring the worker-side namespace + // build: a registered tool named `__proto__` must become an ordinary + // own key (a plain-object assignment would hit the prototype setter, + // silently dropping the binding), and the runtime host resolves + // binding names as own properties only. + const functions: Record = Object.create(null) as Record for (const schema of registry.schemas()) { if (schema.name === RUN_CODE_NAME) continue - functions[schema.name] = binding(schema.name) + Object.defineProperty(functions, schema.name, { enumerable: true, value: binding(schema.name) }) } try { diff --git a/packages/core/tools/tests/code-mode.spec.ts b/packages/core/tools/tests/code-mode.spec.ts index 32dc161a86..7fcd0890e6 100644 --- a/packages/core/tools/tests/code-mode.spec.ts +++ b/packages/core/tools/tests/code-mode.spec.ts @@ -431,17 +431,18 @@ describe('the run_code dispatch bridge', () => { expect(dispatch.resultSummary.endsWith('…')).toBe(true) }) - it('rejects undefined, JSON-throwing, and JSON-unrepresentable binding arguments', async () => { + it('rejects undefined, JSON-throwing, and JSON-unrepresentable binding arguments BEFORE dispatch', async () => { const { ctx, runtime } = await setup({ mode: 'code' }) - registerEcho(ctx) + const calls = registerEcho(ctx) + const { agent, events } = fakeAgent() runtime.behavior = async (request) => { const echo = request.bindings[0]!.functions.echo! const catchMessage = (promise: Promise) => promise.then(() => 'resolved', (error: unknown) => error instanceof Error ? error.message : String(error)) return { logs: [], value: [ - // undefined passes normalization untouched; the tool's own schema - // validation rejects it with its usual feedback. + // Root undefined must reject up front: the event log rejects it as + // data, and nothing may execute unlogged. await catchMessage(echo(undefined)), // A toJSON that throws a NON-Error propagates out of JSON.stringify. await catchMessage(echo({ toJSON() { throw 'raw-throw' } })), @@ -450,11 +451,55 @@ describe('the run_code dispatch bridge', () => { ].join(' | '), } } - const result = await runCode(ctx, 'program') + const result = await runCode(ctx, 'program', { agent }) const text = (result.content[0] as { text: string }).text - expect(text).toContain('must be an object') + expect(text).toContain('call the tool with an arguments object') expect(text).toContain('JSON-serializable: raw-throw') expect(text).toContain('a value JSON cannot represent') + // None of the three dispatched, none logged. + expect(calls).toEqual([]) + expect(events.filter(event => event.type === 'tool/code-dispatch')).toEqual([]) + }) + + it('logs the value the tool RECEIVED even when the tool mutates its arguments', async () => { + const { ctx, runtime } = await setup({ mode: 'code' }) + const { agent, events } = fakeAgent() + ctx.tools.register(defineTool({ + name: 'mutator', + description: 'Mutates its own args object.', + parameters: { list: { type: 'array', required: true } }, + execute(args) { + args.list.push('injected-by-tool') + return Promise.resolve([{ type: 'text' as const, text: 'mutated' }]) + }, + })) + runtime.behavior = async (request) => { + await request.bindings[0]!.functions.mutator!({ list: ['original'] }) + return { logs: [] } + } + const result = await runCode(ctx, 'program', { agent }) + expect(result.isError).toBe(false) + const dispatch = events.find(event => event.type === 'tool/code-dispatch')?.data as SessionEventMap['tool/code-dispatch'] + expect(dispatch.arguments).toEqual({ list: ['original'] }) + }) + + it('exposes a tool named __proto__ as an ordinary own binding', async () => { + const { ctx, runtime } = await setup({ mode: 'code' }) + ctx.tools.register(defineTool({ + name: '__proto__', + description: 'A prototype-colliding tool name.', + parameters: {}, + execute() { return Promise.resolve([{ type: 'text' as const, text: 'proto-tool-ok' }]) }, + })) + runtime.behavior = async (request) => { + const functions = request.bindings[0]!.functions + expect(Object.getPrototypeOf(functions)).toBeNull() + const value = await functions['__proto__']!({}) + return { logs: [], value } + } + const result = await runCode(ctx, 'program') + expect(result.isError).toBe(false) + expect(result.content[0]).toEqual({ type: 'text', text: 'proto-tool-ok' }) }) it('renders a non-string completion value inspect-style', async () => {