Merge pull request #289 from deepseek-harness/codex/simp-prune-tools-prompt-surface

refactor: prune core tool and prompt surface

docs/config-catalog.md

@@ -983,7 +983,7 @@ export interface Config {
 export type ToolPresentationMode = 'native' | 'code' | 'both'
 ```
 
-Source: [`packages/core/tools/src/index.ts:308`](../packages/core/tools/src/index.ts)
+Source: [`packages/core/tools/src/index.ts:307`](../packages/core/tools/src/index.ts)
 
 ## `@deepseek-ai/dsh-user-approval`
 

docs/cordis-catalog/services.md

@@ -256,7 +256,7 @@ async execute(exec: ToolExecutionInput): Promise<ToolExecutionResult>
 
 Types: [ToolDefinition](../core-data-structures/tools.md) · [ToolExecutionInput](../core-data-structures/tools.md) · [ToolExecutionResult](../core-data-structures/tools.md)
 
-Source: [`packages/core/tools/src/index.ts:364`](../../packages/core/tools/src/index.ts)
+Source: [`packages/core/tools/src/index.ts:363`](../../packages/core/tools/src/index.ts)
 
 ## `ctx.userInteraction` — `UserInteractionService`
 

docs/core-data-structures/tools.md

@@ -137,7 +137,6 @@ type ToolGuard = (execution: Readonly<ToolExecution>) => string | undefined
 
 ```ts type-equiv
 interface ToolExecutionResult {
-  callId: CallId
   content: ContentBlock[]
   isError: boolean
   /**
@@ -167,6 +166,8 @@ interface ToolExecutionResult {
 }
 ```
 
+The result carries only the outcome. Call identity remains on the immutable `ToolExecution` that accompanies it through every hook and on the durable `tool/call` / `tool/result` session events, so wrappers cannot create a second, disagreeing identity.
+
 The registry materializes and freezes the final accepted result immediately before `tools/result`. Its content, structured error, additional context, and presentation metadata must round-trip losslessly through JSON; an invalid outcome becomes a JSON-safe `isError` result, so the observed live outcome is safe for the later durable `tool/result` append.
 
 Each interception waterfall returns a typed **Decision** (the idiom shared with the `agent/*` seams). `tools/pre-execute` listeners receive `(exec, next)` and return a `PreToolDecision`; `tools/execute` wrappers return a `ToolExecutionResult`; `tools/post-execute` listeners receive `(exec, result, next)` and return a `PostToolDecision`:

docs/rfc/implemented/architecture/2026-07-07-tool-call-timeout-policy.md

@@ -57,9 +57,8 @@ Signal replacement is by **in-place mutation of `exec.signal`**, not by passing
 `timeout-policy` owns both uses of the `TOOL_TIMEOUT` code: the internal deadline code passed to `deadline()`/`timeoutOf()` (scoped so a nested outer deadline reads as an ordinary cancel) and the structured tool-result error code. Its replacement result is:
 
 ```ts ignore-check
-function toolTimeoutResult(callId: CallId, timeoutMs: number): ToolExecutionResult {
+function toolTimeoutResult(timeoutMs: number): ToolExecutionResult {
   return {
-    callId,
     content: [{ type: 'text', text: `Error: tool call timed out after ${timeoutMs}ms` }],
     isError: true,
     error: { name: 'ToolTimeoutError', code: 'TOOL_TIMEOUT' },

docs/rfc/proposed/simplification/2026-07-12-simplify-session-log-representation.md

@@ -26,7 +26,7 @@ Amend the session-surface and reconstructable-request RFCs where they describe t
 
 ## Acceptance criteria
 
-- `SurfaceManager.nodes` is one ordered seq array with no `SurfaceNode`, link fields, or seq-to-node map; incremental append processing and the internal replace-generation signal remain, while the separate public `invalidate()` deletion stays owned by the dead-surface RFC.
+- `SurfaceManager.nodes` is one ordered seq array with no `SurfaceNode`, link fields, or seq-to-node map; incremental append processing and the internal replace-generation signal remain.
 - Replaying full changed-header snapshots reconstructs exactly the same requests; no header-delta event/type/codec remains.
 - A v0 seed or persisted log containing legacy `request/header-delta` is rejected before replay, with coverage for JSONL and SQLite load paths.
 - New-shape v0 JSONL/SQLite replay, provenance, crash repair, compaction, snapshots, invariants, typecheck, coverage, doc-sync, build, and hygiene pass.

packages/cordis/tool-cordis/src/api-catalog.ts

@@ -979,7 +979,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [
   },
   {
     name: 'ToolExecutionResult',
-    declaration: 'export interface ToolExecutionResult {\n    callId: CallId;\n    content: ContentBlock[];\n    isError: boolean;\n    error?: ToolErrorInfo;\n    additionalContext?: HookContext;\n    meta?: unknown;\n}',
+    declaration: 'export interface ToolExecutionResult {\n    content: ContentBlock[];\n    isError: boolean;\n    error?: ToolErrorInfo;\n    additionalContext?: HookContext;\n    meta?: unknown;\n}',
   },
   {
     name: 'ToolExecutionToken',

packages/core/agent-loop/src/loop.ts

@@ -578,7 +578,8 @@ async function runStep(
     })
     session.append('tool/result', {
       turn, step,
-      // Preserve transcript pairing even if a post-execute listener returns another id.
+      // Correlation comes from the immutable execution input; the result does
+      // not duplicate this authoritative transcript identity.
       callId: call.id,
       content: result.content,
       isError: result.isError,

packages/core/agent-loop/tests/contract-regressions.spec.ts

@@ -1043,8 +1043,7 @@ describe('tool result call identity', () => {
 
     // A post-execute listener transforms the result (accept-with-replacement).
     // The loop must still record the tool/result under the model's authoritative
-    // call.id (the loop ignores result.callId — which the registry always sets to
-    // exec.callId anyway — and uses call.id, the model-transcript id).
+    // call.id, which is the immutable identity carried by the execution input.
     ctx.on('tools/post-execute', (exec, _result) => {
       expect(exec.callId).toBe(CallId('c1')) // the loop passed the real id in
       return Promise.resolve({ kind: 'accept', content: [{ type: 'text', text: 'ok' }] })
@@ -1054,8 +1053,7 @@ describe('tool result call identity', () => {
     send(agent, 'use tool')
     await waitForIdle(ctx, agent)
 
-    // The logged tool/result.callId is the originating call.id, NOT the
-    // listener's wrong id.
+    // The logged tool/result.callId is the originating call.id.
     const resultEvent = [...agent.session.events].find(e => e.type === 'tool/result')
     expect(resultEvent?.type).toBe('tool/result')
     if (resultEvent?.type === 'tool/result') {

packages/core/system-prompt/src/index.ts

@@ -226,7 +226,7 @@ export class SystemPrompt extends Service {
   private scopedVariableProviders = new Map<ScopeKey, Map<string, (context: AssembleContext) => string | undefined>>()
   private readonly toolOrder: string[] | undefined
 
-  constructor(ctx: Context, public config: Config) {
+  constructor(ctx: Context, config: Config) {
     super(ctx, 'systemPrompt')
     this.toolOrder = validateToolOrder(config.toolOrder)
     // Keep harness-owned openers independent of the selected loop plugin.

packages/core/tools/README.md

@@ -36,7 +36,7 @@ The live registry pipeline has three transformable waterfalls followed by the ob
 - `ToolExecutionInput` — the caller-supplied call description: `{ callId, name, arguments, agent?, parent?, signal? }`; callers may pass an enclosing execution's opaque token as `parent` but never choose the new execution's own token.
 - `ToolExecutionToken` — a fresh branded `Symbol` assigned by the registry. It supports equality correlation only and never crosses a model, log, or worker boundary.
 - `ToolExecution` — the pipeline-owned call: immutable `{ token, callId, name, arguments, agent?, parent? }` identity plus optional operational `signal`, which an around wrapper may add, replace, remove, and restore. A nested call's `parent` is a `ToolExecutionToken`, not an execution object.
-- `ToolExecutionResult` — losslessly JSON-serializable outcome: `{ callId, content, isError, error?, additionalContext?, meta? }`. The registry materializes and freezes the complete post-policy value before final observation. On failure with a `HarnessError`, `error: { name, code }` carries the structured failure class alongside the model-facing text.
+- `ToolExecutionResult` — losslessly JSON-serializable outcome: `{ content, isError, error?, additionalContext?, meta? }`. Call identity stays on the immutable `ToolExecution` supplied alongside the result instead of being duplicated on the outcome. The registry materializes and freezes the complete post-policy value before final observation. On failure with a `HarnessError`, `error: { name, code }` carries the structured failure class alongside the model-facing text.
 - `PreToolDecision` — `{kind:'allow'}` | `{kind:'deny', reason}` | `{kind:'ask', reason?}`. Input rewrite is deliberately not offered; `ask` is serviced by [`ctx.approval`](../../ui/user-approval/README.md) when mounted and otherwise degrades to deny.
 - `PostToolDecision` — `{kind:'accept', content?, additionalContext?}` (keep the call successful, optionally replacing the model-facing content) | `{kind:'block', feedback, additionalContext?}` (turn it into an `isError` whose content is the corrective feedback). Output replacement is clean because `tool/result` is logged AFTER `execute()` returns.
 - `ToolGuard` — `(execution) => string | undefined`; the returned string is a final monotonic denial reason evaluated after the reorderable pre-execute waterfall and before dispatch.

packages/core/tools/src/index.ts

@@ -220,7 +220,7 @@ export interface ToolErrorInfo {
  * distinguish it from a tool body's own error.
  */
 export class ToolNotFoundError extends HarnessError {
-  constructor(public readonly toolName: string) {
+  constructor(toolName: string) {
     super(`unknown tool "${toolName}"`, 'UNKNOWN_TOOL')
     this.name = 'ToolNotFoundError'
   }
@@ -228,7 +228,6 @@ export class ToolNotFoundError extends HarnessError {
 
 /** The outcome of one tool call. */
 export interface ToolExecutionResult {
-  callId: CallId
   content: ContentBlock[]
   isError: boolean
   /**
@@ -704,7 +703,7 @@ export class ToolRegistry extends Service {
       }
     } catch (error: unknown) {
       execution = { ...base, arguments: undefined }
-      const result = this.materializeFinalResult(toolErrorResult(callId, error))
+      const result = this.materializeFinalResult(toolErrorResult(error))
       this.notifyResult(execution, result)
       return result
     }
@@ -714,7 +713,7 @@ export class ToolRegistry extends Service {
     } catch (error: unknown) {
       // Outer backstop: a throwing pre/post-execute listener, guard, or the
       // waterfall machinery becomes an isError result, never a turn failure.
-      result = this.materializeFinalResult(toolErrorResult(execution.callId, error))
+      result = this.materializeFinalResult(toolErrorResult(error))
     }
     this.notifyResult(execution, result)
     return result
@@ -739,7 +738,6 @@ export class ToolRegistry extends Service {
       // Every non-grant, including a failed/unavailable approval request, takes
       // the same deny path and still reaches post-policy plus result observers.
       const denied: ToolExecutionResult = {
-        callId: exec.callId,
         content: [{ type: 'text', text: `Error: ${denialReason}` }],
         isError: true,
       }
@@ -770,16 +768,12 @@ export class ToolRegistry extends Service {
           const returned = await tool.execute(exec.arguments, exec)
           const content = Array.isArray(returned) ? returned : returned.content
           const meta = Array.isArray(returned) ? undefined : returned.meta
-          return { callId: exec.callId, content, isError: false, ...meta !== undefined ? { meta } : {} }
+          return { content, isError: false, ...meta !== undefined ? { meta } : {} }
         } catch (error: unknown) {
-          return toolErrorResult(exec.callId, error)
+          return toolErrorResult(error)
         }
       },
     )
-    if (result.callId !== exec.callId) {
-      throw new TypeError(`tools/execute returned callId "${String(result.callId)}" for authoritative call "${exec.callId}"`)
-    }
-
     return await this.postExecute(exec, result)
   }
 
@@ -854,7 +848,6 @@ export class ToolRegistry extends Service {
     const additionalContext = decision.additionalContext
     if (decision.kind === 'block') {
       return {
-        callId: result.callId,
         content: decision.feedback,
         isError: true,
         ...additionalContext ? { additionalContext } : {},
@@ -883,10 +876,9 @@ function createExecutionToken(): ToolExecutionToken {
   return Symbol('dsh.tool.execution') as ToolExecutionToken
 }
 
-function toolErrorResult(callId: ToolExecution['callId'], error: unknown): ToolExecutionResult {
+function toolErrorResult(error: unknown): ToolExecutionResult {
   const info = errorInfo(error)
   return {
-    callId,
     content: [{ type: 'text', text: `Error: ${errorMessage(error)}` }],
     isError: true,
     ...info ? { error: info } : {},

packages/core/tools/tests/scoped.spec.ts

@@ -548,7 +548,6 @@ describe('scoped execution dispatch', () => {
 
     expect(reads).toBe(1)
     expect(result).toEqual({
-      callId: CallId('unstable-arguments'),
       content: [{ type: 'text', text: 'ran:t' }],
       isError: false,
     })
@@ -564,10 +563,9 @@ describe('scoped execution dispatch', () => {
     ctx.on('internal/dispatch', (mode, name) => {
       if (name === 'tools/result') dispatchModes.push(mode)
     })
-    ctx.on('tools/execute', async (exec, next) => {
+    ctx.on('tools/execute', async (_exec, next) => {
       await next()
       return {
-        callId: exec.callId,
         content: [{ type: 'text', text: 'outer failure' }],
         isError: true,
       }

packages/core/tools/tests/tools.spec.ts

@@ -80,7 +80,7 @@ describe('ToolRegistry', () => {
     const ctx = await setup()
     ctx.tools.register(echoTool)
     const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'echo', arguments: { text: 'hi' } })
-    expect(result).toEqual({ callId: CallId('c1'), content: [{ type: 'text', text: 'hi' }], isError: false })
+    expect(result).toEqual({ content: [{ type: 'text', text: 'hi' }], isError: false })
   })
 
   it('threads a tool-attached meta (object return form) onto the result', async () => {
@@ -94,7 +94,6 @@ describe('ToolRegistry', () => {
     })
     const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'meta-tool', arguments: {} })
     expect(result).toEqual({
-      callId: CallId('c1'),
       content: [{ type: 'text', text: 'ok' }],
       isError: false,
       meta: { diffs: [{ path: 'a', oldText: null, newText: 'x' }] },
@@ -111,7 +110,7 @@ describe('ToolRegistry', () => {
       },
     })
     const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'no-meta-tool', arguments: {} })
-    expect(result).toEqual({ callId: CallId('c1'), content: [{ type: 'text', text: 'ok' }], isError: false })
+    expect(result).toEqual({ content: [{ type: 'text', text: 'ok' }], isError: false })
     expect('meta' in result).toBe(false)
   })
 
@@ -178,13 +177,12 @@ describe('ToolRegistry', () => {
     })
   })
 
-  it('ToolNotFoundError carries the tool name and a stable code', async () => {
+  it('ToolNotFoundError carries a stable message and code', async () => {
     const { HarnessError } = await import('@deepseek-ai/dsh-llm')
     const err = new ToolNotFoundError('ghost')
     expect(err).toBeInstanceOf(HarnessError)
     expect(err.name).toBe('ToolNotFoundError')
     expect(err.code).toBe('UNKNOWN_TOOL')
-    expect(err.toolName).toBe('ghost')
     expect(err.message).toBe('unknown tool "ghost"')
   })
 
@@ -425,7 +423,7 @@ describe('ToolRegistry', () => {
     ctx.on('tools/post-execute', async (_exec, _result, next) => { order.push('post'); return next() })
 
     const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'traced', arguments: { text: 'hi' } })
-    expect(result).toEqual({ callId: CallId('c1'), content: [{ type: 'text', text: 'hi' }], isError: false })
+    expect(result).toEqual({ content: [{ type: 'text', text: 'hi' }], isError: false })
     // The around seam wraps dispatch; pre gates before it, post runs over its result.
     expect(order).toEqual(['pre', 'execute:before', 'dispatch', 'execute:after', 'post'])
   })
@@ -526,8 +524,8 @@ describe('ToolRegistry', () => {
       async execute() { dispatched = true; return [] },
     })
 
-    ctx.on('tools/execute', async (exec: ToolExecution, _next: () => Promise<ToolExecutionResult>): Promise<ToolExecutionResult> =>
-      ({ callId: exec.callId, content: [{ type: 'text', text: 'short-circuited' }], isError: false }))
+    ctx.on('tools/execute', async (_exec: ToolExecution, _next: () => Promise<ToolExecutionResult>): Promise<ToolExecutionResult> =>
+      ({ content: [{ type: 'text', text: 'short-circuited' }], isError: false }))
 
     const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'never-runs', arguments: {} })
     expect(dispatched).toBe(false) // returning without next() skips core dispatch
@@ -537,8 +535,7 @@ describe('ToolRegistry', () => {
   it('preserves additionalContext supplied by an around-dispatch result', async () => {
     const ctx = await setup()
     ctx.tools.register(echoTool)
-    ctx.on('tools/execute', async exec => ({
-      callId: exec.callId,
+    ctx.on('tools/execute', async () => ({
       content: [{ type: 'text', text: 'short-circuited with context' }],
       isError: false,
       additionalContext: {
@@ -556,20 +553,6 @@ describe('ToolRegistry', () => {
     })
   })
 
-  it('normalizes a tools/execute result with the wrong call id', async () => {
-    const ctx = await setup()
-    ctx.tools.register(echoTool)
-    ctx.on('tools/execute', async () => ({ callId: CallId('other'), content: [], isError: false }))
-
-    const result = await ctx.tools.execute({
-      callId: CallId('malformed-shape'), name: 'echo', arguments: {},
-    })
-    expect(result.isError).toBe(true)
-    expect(result.content[0]).toMatchObject({
-      text: 'Error: tools/execute returned callId "other" for authoritative call "malformed-shape"',
-    })
-  })
-
   it('returns an isError result when a tools/execute listener throws', async () => {
     const ctx = await setup()
     ctx.tools.register(echoTool)
@@ -577,7 +560,6 @@ describe('ToolRegistry', () => {
 
     const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'echo', arguments: { text: 'hi' } })
     expect(result).toEqual({
-      callId: CallId('c1'),
       content: [{ type: 'text', text: 'Error: wrapper broke' }],
       isError: true,
     })
@@ -593,7 +575,6 @@ describe('ToolRegistry', () => {
     const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'echo', arguments: { text: 'hi' } })
 
     expect(result).toEqual({
-      callId: CallId('c1'),
       content: [{ type: 'text', text: 'Error: permission hook broke' }],
       isError: true,
     })
@@ -609,7 +590,6 @@ describe('ToolRegistry', () => {
     const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'echo', arguments: { text: 'hi' } })
 
     expect(result).toEqual({
-      callId: CallId('c1'),
       content: [{ type: 'text', text: 'Error: post hook broke' }],
       isError: true,
     })
@@ -625,7 +605,6 @@ describe('ToolRegistry', () => {
     const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'echo', arguments: { text: 'hi' } })
 
     expect(result).toMatchObject({
-      callId: CallId('c1'),
       isError: true,
       error: { name: 'HarnessError', code: 'DENIED' },
     })
@@ -1254,7 +1233,7 @@ describe('defineTool validation (the runtime-validation RFC, part 1)', () => {
       },
     }))
     const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'reader', arguments: { path: '/x' } })
-    expect(result).toEqual({ callId: CallId('c1'), content: [{ type: 'text', text: 'read /x' }], isError: false })
+    expect(result).toEqual({ content: [{ type: 'text', text: 'read /x' }], isError: false })
   })
 
   it('ToolArgsError carries a stable code and the violation list', () => {

packages/support/invariants/tests/invariants.spec.ts

@@ -855,9 +855,9 @@ describe('scoped-dispatch invariants', () => {
       ['agent/error', [agent, 1, 0, new Error('x')]],
       ['approval/request', [{ agent, toolName: 'echo' }, () => Promise.resolve('unavailable')]],
       ['tools/pre-execute', [{ callId: 'c', name: 't', arguments: {}, agent }, () => Promise.resolve({ kind: 'allow' })]],
-      ['tools/execute', [{ callId: 'c', name: 't', arguments: {}, agent }, () => Promise.resolve({ callId: 'c', content: [], isError: false })]],
-      ['tools/post-execute', [{ callId: 'c', name: 't', arguments: {}, agent }, { callId: 'c', content: [], isError: false }, () => Promise.resolve({ kind: 'accept' })]],
-      ['tools/result', [{ callId: 'c', name: 't', arguments: {}, agent }, { callId: 'c', content: [], isError: false }]],
+      ['tools/execute', [{ callId: 'c', name: 't', arguments: {}, agent }, () => Promise.resolve({ content: [], isError: false })]],
+      ['tools/post-execute', [{ callId: 'c', name: 't', arguments: {}, agent }, { content: [], isError: false }, () => Promise.resolve({ kind: 'accept' })]],
+      ['tools/result', [{ callId: 'c', name: 't', arguments: {}, agent }, { content: [], isError: false }]],
     ]
     for (const [event, args] of rows) {
       const subject = agent

packages/timeout/timeout-policy/src/index.ts

@@ -6,7 +6,6 @@
  */
 
 import type { Context } from 'cordis'
-import type { CallId } from '@deepseek-ai/dsh-llm'
 import { deadline, timeoutOf } from '@deepseek-ai/dsh-timeout'
 import type { ToolExecutionResult } from '@deepseek-ai/dsh-tools'
 
@@ -30,13 +29,11 @@ export const inject = ['tools']
  * is the model-facing message; `error.code` is the same {@link TOOL_TIMEOUT}
  * this plugin owns, so a retry/sandbox plugin (and replay) can route on it.
  *
- * @param callId - the timed-out call's id, carried onto the replacement result.
  * @param timeoutMs - the elapsed budget, rendered into the model-facing message.
  * @returns the `isError` {@link ToolExecutionResult} with a `TOOL_TIMEOUT` error.
  */
-export function toolTimeoutResult(callId: CallId, timeoutMs: number): ToolExecutionResult {
+function toolTimeoutResult(timeoutMs: number): ToolExecutionResult {
   return {
-    callId,
     content: [{ type: 'text', text: `Error: tool call timed out after ${timeoutMs}ms` }],
     isError: true,
     error: { name: 'ToolTimeoutError', code: TOOL_TIMEOUT },
@@ -68,7 +65,7 @@ export function apply(ctx: Context): void {
       // quiescence; replace whatever it returned (its own abort result) with the
       // structured TOOL_TIMEOUT the model sees.
       if (timeoutOf(d.signal, TOOL_TIMEOUT) !== undefined) {
-        return toolTimeoutResult(exec.callId, timeoutMs)
+        return toolTimeoutResult(timeoutMs)
       }
       return result
     } finally {

packages/timeout/timeout-policy/tests/timeout-policy.spec.ts

@@ -11,9 +11,9 @@ import { Context } from 'cordis'
 import Loader from '@cordisjs/plugin-loader'
 import { CallId, HarnessError } from '@deepseek-ai/dsh-llm'
 import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
-import ToolRegistry, { defineTool, type ToolExecutionInput, type ToolExecutionResult, type PostToolDecision } from '@deepseek-ai/dsh-tools'
+import ToolRegistry, { defineTool, type ToolExecutionInput, type PostToolDecision } from '@deepseek-ai/dsh-tools'
 import * as timeoutPolicy from '@deepseek-ai/dsh-timeout-policy'
-import { TOOL_TIMEOUT, toolTimeoutResult } from '@deepseek-ai/dsh-timeout-policy'
+import { TOOL_TIMEOUT } from '@deepseek-ai/dsh-timeout-policy'
 
 /** Mount the registry + the zero-config timeout-policy enforcer. */
 async function setup() {
@@ -60,7 +60,7 @@ describe('timeout-policy delegation (unconfigured / fast)', () => {
     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 })
+    expect(result).toEqual({ content: [{ type: 'text', text: 'ok' }], isError: false })
   })
 
   it('a budgeted tool receives the DERIVED deadline signal (not the caller signal) during dispatch', async () => {
@@ -109,7 +109,6 @@ describe('timeout-policy TOOL_TIMEOUT replacement (deadline wins)', () => {
     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' }],
       isError: true,
       error: { name: 'ToolTimeoutError', code: 'TOOL_TIMEOUT' },
@@ -140,16 +139,7 @@ describe('timeout-policy TOOL_TIMEOUT replacement (deadline wins)', () => {
   })
 })
 
-describe('toolTimeoutResult', () => {
-  it('builds the structured TOOL_TIMEOUT result', () => {
-    expect(toolTimeoutResult(CallId('c9'), 250)).toEqual({
-      callId: CallId('c9'),
-      content: [{ type: 'text', text: 'Error: tool call timed out after 250ms' }],
-      isError: true,
-      error: { name: 'ToolTimeoutError', code: 'TOOL_TIMEOUT' },
-    } satisfies ToolExecutionResult)
-  })
-
+describe('timeout-policy contract', () => {
   it('exposes the owned code constant', () => {
     expect(TOOL_TIMEOUT).toBe('TOOL_TIMEOUT')
   })