Merge branch 'master' into worktree/charming-swartz-83bf33

examples/headless-agent/tests/harness.ts

@@ -30,8 +30,9 @@ export const SYSTEM_PROMPT = 'You are a coding agent. Use bash for file operatio
 /** System prompt for the todo_write e2e: nudges the model to plan with the tool. */
 export const TODO_SYSTEM_PROMPT = 'You are a coding agent. For multi-step work, '
   + 'use the todo_write tool to track a task list: send the WHOLE list each call, '
-  + 'keep at most one task in_progress (exactly one while work remains), and mark '
-  + 'a task completed as soon as it is done.'
+  + 'mark every task being actively worked on in_progress (several at once when '
+  + 'work runs in parallel, at least one while work remains), and mark a task '
+  + 'completed as soon as it is done.'
 
 /** Options for {@link codingHarness}. */
 export interface CodingHarnessOptions {
@@ -65,7 +66,7 @@ export async function codingHarness(workdir: string, options: CodingHarnessOptio
   await ctx.plugin(BashEnvPlugin)
   await ctx.plugin(LocalBashExecutor, { cwd: workdir, timeoutMs: 30_000 })
   await ctx.plugin(ToolBash)
-  await ctx.plugin(ToolTodo)
+  await ctx.plugin(ToolTodo, { allowParallelInProgress: true })
   // Compaction is opt-in: only the compaction e2e loads the reusable meter and backend.
   if (options.compact !== undefined) {
     await ctx.plugin(TokenMeterService)

examples/headless-agent/tests/todo-write.e2e.ts

@@ -31,9 +31,10 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('todo_write: real model records a
 
     agent.followup(createUserMessage({
       content: [{ type: 'text', text:
-      'Use the todo_write tool to record a plan of exactly two steps: first '
-      + '"inspect the failing test" (in_progress), then "apply the fix" (pending). '
-      + 'Send both in one todo_write call, then reply with the single word DONE.' }], source: { kind: 'user' } }))
+      'Use the todo_write tool to record a plan of exactly three steps for work '
+      + 'running in parallel: "inspect the failing test" (in_progress), '
+      + '"watch the background build" (in_progress), then "apply the fix" (pending). '
+      + 'Send all three in one todo_write call, then reply with the single word DONE.' }], source: { kind: 'user' } }))
     await waitForIdle(ctx, agent)
 
     const events = [...agent.session.events]
@@ -42,13 +43,15 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('todo_write: real model records a
     const calls = events.filter(event => event.type === 'tool/call')
     expect(calls.some(event => event.data.name === 'todo_write')).toBe(true)
 
-    // And the tool wrote a todo/write event to the log — verify the WORLD.
+    // And the tool wrote a todo/write event to the log — verify the WORLD,
+    // including two simultaneously in_progress tasks (the parallel contract).
     const todoEvents = events.filter(event => event.type === 'todo/write')
     expect(todoEvents.length).toBeGreaterThan(0)
 
     const todos = (todoEvents.at(-1)!).data.todos
     expect(todos).toEqual([
       { content: 'inspect the failing test', status: 'in_progress' },
+      { content: 'watch the background build', status: 'in_progress' },
       { content: 'apply the fix', status: 'pending' },
     ])
   }, 120_000)