Merge remote-tracking branch 'origin/master' into compact-basic-refactor

# Conflicts:
#	docs/cordis-catalog/events-and-services.md
#	examples/AGENTS.md
#	examples/coding-agent/cordis.yml
#	examples/coding-agent/tests/harness.ts
#	scripts/gen-cordis-catalog.ts

examples/coding-agent/tests/harness.ts

@@ -8,6 +8,7 @@ import AgentRegistry from '@deepseek-ai/dsh-agent'
 import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
 import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
 import * as ToolBash from '@deepseek-ai/dsh-tool-bash'
+import * as ToolTodo from '@deepseek-ai/dsh-tool-todo'
 import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
 import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
 import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic'
@@ -15,14 +16,21 @@ import type { BasicCompactConfig } from '@deepseek-ai/dsh-compact-basic'
 
 /**
  * Shared harness for the coding-agent e2e suites: the full plugin stack
- * with the real DeepSeek adapter and the real bash tool. Lives outside the
- * *.e2e.ts pattern so importing it never re-registers another file's tests.
+ * with the real DeepSeek adapter and the real bash + todo_write tools. Lives
+ * outside the *.e2e.ts pattern so importing it never re-registers another
+ * file's tests.
  */
 
-export const SYSTEM_PROMPT = 'You are a coding agent. Your only tool is bash; '
-  + 'do file operations with cat/grep/heredocs, check [exit code: N] markers, '
+export const SYSTEM_PROMPT = 'You are a coding agent. Use bash for file operations '
+  + 'with cat/grep/heredocs; check [exit code: N] markers, '
   + 'and report results briefly.'
 
+/** 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.'
+
 /** Options for {@link codingHarness}. */
 export interface CodingHarnessOptions {
   /** Durable JSONL persistence root (the resume suite needs it; others stay file-free). */
@@ -46,6 +54,7 @@ export async function codingHarness(workdir: string, options: CodingHarnessOptio
   await ctx.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] })
   await ctx.plugin(LocalBashExecutor, { cwd: workdir, timeoutMs: 30_000 })
   await ctx.plugin(ToolBash)
+  await ctx.plugin(ToolTodo)
   // Compaction is opt-in: only the compaction e2e loads it, with a lowered
   // contextWindow/retainTokens so a short real session crosses the threshold.
   if (options.compact !== undefined) await ctx.plugin(BasicCompactService, options.compact)

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

@@ -0,0 +1,49 @@
+import { afterEach, describe, expect, it } from 'vitest'
+import type { Context } from 'cordis'
+import { AgentId } from '@deepseek-ai/dsh-agent'
+import { codingHarness, TODO_SYSTEM_PROMPT, waitForIdle } from './harness.ts'
+
+/**
+ * A REAL model drives the REAL todo_write tool: verify the WORLD (the session
+ * log gains a todo/write event whose snapshot the model actually produced), not
+ * the agent's self-report. Key-gated (see vitest.e2e.config.ts).
+ */
+
+let ctx: Context | undefined
+
+afterEach(async () => {
+  await ctx?.fiber.dispose()
+  ctx = undefined
+})
+
+describe.skipIf(!process.env.DEEPSEEK_API_KEY)('todo_write: real model records a plan', () => {
+  it('appends a todo/write event with the model-produced task list', async () => {
+    ctx = await codingHarness(process.cwd())
+    const agent = ctx.agentLoop.create(AgentId('e2e-todo'), {
+      model: 'deepseek-v4-flash',
+      systemPrompt: TODO_SYSTEM_PROMPT,
+    })
+
+    agent.send([{ 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.' }])
+    await waitForIdle(ctx, agent)
+
+    const events = [...agent.session.events]
+
+    // The model actually called the tool.
+    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.
+    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: 'apply the fix', status: 'pending' },
+    ])
+  }, 120_000)
+})