fix(pty): close final review gaps

packages/tasks/tool-tasks/README.md

@@ -10,7 +10,7 @@ The model-facing control surface for `ctx.tasks`: three kind-independent tools,
 
 All three use generic ACP cards: `read` for output and list, `execute` for kill.
 
-When a producer supplies `outputLimitBytes`, `task_output`, terminal `task_kill`, and completion notices cap the complete UTF-8 result after adding status or notice text. Reads retain the output tail and control suffix when they fit; a bounded completion notice instead reserves `background task <id>` and the `task_output` collection instruction before spending remaining bytes on its variable kind, label, status, and detail. An outer pre/post-execute pair captures the caller-visible task before policy and applies its producer cap to single-text denials, around-dispatch short-circuits, normalized task-control failures, replacements, and blocks; structured multi-block policy results retain their shape. An existing producer truncation marker is reused rather than duplicated. Producers that omit the field retain the existing unbounded control-surface behavior.
+When a producer supplies `outputLimitBytes`, `task_output`, terminal `task_kill`, and completion notices cap the complete UTF-8 result after adding status or notice text. Reads retain the output tail and control suffix when they fit; a bounded completion notice instead reserves `background task <id>` and the `task_output` collection instruction before spending remaining bytes on its variable kind, label, status, and detail. A prepended pre-execute listener captures the caller-visible task before policy, and each task-control definition's final-content callback applies its producer cap to single-text denials, short-circuits, normalized tool or pipeline failures, replacements, and blocks; structured multi-block policy results retain their shape. An existing producer truncation marker is reused rather than duplicated. Producers that omit the field retain the existing unbounded control-surface behavior.
 
 ## Completion notices
 

packages/tasks/tool-tasks/src/index.ts

@@ -11,7 +11,7 @@ import z from 'schemastery'
 import type { ContentBlock } from '@deepseek-ai/dsh-llm'
 import { TextRetainer } from '@deepseek-ai/dsh-retention'
 import { defineTool } from '@deepseek-ai/dsh-tools'
-import type { GenericCallView, PostToolDecision, ToolExecution } from '@deepseek-ai/dsh-tools'
+import type { GenericCallView, ToolDefinition, ToolExecution } from '@deepseek-ai/dsh-tools'
 import { TaskId } from '@deepseek-ai/dsh-tasks'
 import type { TaskSnapshot } from '@deepseek-ai/dsh-tasks'
 import type {} from '@deepseek-ai/dsh-system-prompt'
@@ -128,18 +128,11 @@ export function apply(ctx: Context, config: Config): void {
     if (maxBytes !== undefined) outputLimits.set(exec, maxBytes)
     return next()
   }, { prepend: true })
-  ctx.on('tools/post-execute', async (exec, result, next): Promise<PostToolDecision> => {
-    const decision = await next()
-    const maxBytes = outputLimits.get(exec)
+  const finalizeTaskContent: NonNullable<ToolDefinition['finalizeContent']> = (exec, result) => {
+    const maxBytes = outputLimits.get(exec) ?? visibleOutputLimit(ctx, exec)
     outputLimits.delete(exec)
-    if (maxBytes === undefined) return decision
-    const content = decision.kind === 'block' ? decision.feedback : decision.content ?? result.content
-    const bounded = boundSingleText(content, maxBytes)
-    if (bounded === undefined) return decision
-    return decision.kind === 'block'
-      ? { ...decision, feedback: bounded }
-      : { ...decision, content: bounded }
-  }, { prepend: true })
+    return maxBytes === undefined ? undefined : boundSingleText(result.content, maxBytes)
+  }
 
   // Producers may start work only while a control surface is attached.
   ctx.tasks.attachSurface('tool-tasks')
@@ -181,6 +174,7 @@ export function apply(ctx: Context, config: Config): void {
       wait: { type: 'boolean', description: 'Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive.' },
       timeout_ms: { type: 'number', description: 'Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum.' },
     },
+    finalizeContent: finalizeTaskContent,
     async execute(args, exec) {
       const id = validateTaskId(args.task_id)
       if (args.wait === true) {
@@ -224,6 +218,7 @@ export function apply(ctx: Context, config: Config): void {
       task_id: { type: 'string', required: true, description: 'Task id returned by the tool that started the background work.' },
       reason: { type: 'string', description: 'Optional short reason, recorded in the log and forwarded to the task.' },
     },
+    finalizeContent: finalizeTaskContent,
     execute(args, exec) {
       const id = validateTaskId(args.task_id)
       const snapshot = ctx.tasks.get(id, exec.agent)

packages/tasks/tool-tasks/tests/tool-tasks.spec.ts

@@ -162,19 +162,27 @@ describe('task_output', () => {
     expect(text(result)).toContain('[result truncated]')
   })
 
-  it('captures producer limits before pre- and around-execute policy', async () => {
+  it('bounds pre-, around-, and post-execute policy outcomes and failures', async () => {
     const { ctx } = await setup()
-    ctx.tasks.start(producer({ outputLimitBytes: 64 }).spec)
-    ctx.tasks.start(producer({ outputLimitBytes: 64 }).spec)
+    for (let index = 0; index < 5; index += 1) {
+      ctx.tasks.start(producer({ outputLimitBytes: 64 }).spec)
+    }
     ctx.on('tools/pre-execute', async (exec, next) => {
       const taskId = (exec.arguments as { task_id?: unknown }).task_id
-      return taskId === 'bash-1' ? { kind: 'deny', reason: 'd'.repeat(1_000) } : next()
+      if (taskId === 'bash-1') return { kind: 'deny', reason: 'd'.repeat(1_000) }
+      if (taskId === 'bash-3') throw new Error(`pre failed: ${'p'.repeat(1_000)}`)
+      return next()
     })
     ctx.on('tools/execute', async (exec, next) => {
       const taskId = (exec.arguments as { task_id?: unknown }).task_id
-      return taskId === 'bash-2'
-        ? { content: [{ type: 'text', text: 'a'.repeat(1_000) }], isError: false }
-        : next()
+      if (taskId === 'bash-2') return { content: [{ type: 'text', text: 'a'.repeat(1_000) }], isError: false }
+      if (taskId === 'bash-4') throw new Error(`around failed: ${'e'.repeat(1_000)}`)
+      return next()
+    })
+    ctx.on('tools/post-execute', async (exec, _result, next) => {
+      const taskId = (exec.arguments as { task_id?: unknown }).task_id
+      if (taskId === 'bash-5') throw new Error(`post failed: ${'o'.repeat(1_000)}`)
+      return next()
     })
 
     const denied = await call(ctx, 'task_output', { task_id: 'bash-1' })
@@ -186,6 +194,17 @@ describe('task_output', () => {
     expect(shortCircuited.isError).toBe(false)
     expect(Buffer.byteLength(text(shortCircuited))).toBeLessThanOrEqual(64)
     expect(text(shortCircuited)).toContain('[result truncated]')
+
+    const failures = [
+      await call(ctx, 'task_output', { task_id: 'bash-3' }),
+      await call(ctx, 'task_output', { task_id: 'bash-4' }),
+      await call(ctx, 'task_output', { task_id: 'bash-5' }),
+    ]
+    for (const failure of failures) {
+      expect(failure.isError).toBe(true)
+      expect(Buffer.byteLength(text(failure))).toBeLessThanOrEqual(64)
+      expect(text(failure)).toContain('[result truncated]')
+    }
   })
 
   it('wait: true blocks until settlement and reports the terminal state', async () => {