Merge origin/master into codex/skill-system

packages/ui/README.md

@@ -10,4 +10,4 @@ Integrations that expose the agent to an external editor or client. These are **
 
 A UI integration is a client-driver plugin, not a loop change and not a capability seam: it consumes the existing `agent/*` event taxonomy and the `dsh-agent` factory. The readline `ui-stdio` plugin is the unstructured analogue but lives in `support/` because it exists chiefly for the examples and the coverage gate — `ui/` is reserved for surfaces shipped as product.
 
-`stdio-agent` and `acp-agent` are the two **app packages**: each composes the [`core/agent-core`](../core/agent-core/README.md) spine with its coupled front-door cluster (and owns the boot `bin`), so a leaf `cordis.yml` is just the swappable backends plus one app entry. They live in `ui/` because each IS a user-facing front door; the stdout-purity coupling (logger vs. no logger) becomes a property of the artifact rather than a leaf convention.
+`stdio-agent` and `acp-agent` are the two **app packages**: each composes the [`core/agent-core`](../core/agent-core/README.md) spine with its coupled front-door cluster (and owns the boot `bin`), so a leaf `cordis.yml` is the swappable backends plus one app entry plus any optional product tools. They live in `ui/` because each IS a user-facing front door; the stdout-purity coupling (logger vs. no logger) becomes a property of the artifact rather than a leaf convention.

packages/ui/acp-agent/src/index.ts

@@ -14,11 +14,12 @@
  * which this app does not prevent — so the rule "never add a stdout logger to an
  * ACP leaf" still stands; the app just gives the leaf nothing to misconfigure.)
  *
- * The leaf supplies only the swappable backends: the LLM adapter (`llm-deepseek`
- * for the real model, `llm-replay` for keyless snapshot replay) and the bash
- * executor (`bash-local`). This app's {@link Config} (model, system prompt,
- * persistence root) routes each value to where it is wired — model/prompt onto
- * the bridge's per-session agent template, the root onto the JSONL backend.
+ * The leaf supplies the swappable backends: the LLM adapter (`llm-deepseek` for
+ * the real model, `llm-replay` for keyless snapshot replay), the bash executor
+ * (`bash-local`), and any optional product tools it wants to expose. This app's
+ * {@link Config} (model, system prompt, persistence root) routes each value to
+ * where it is wired — model/prompt onto the bridge's per-session agent
+ * template, the root onto the JSONL backend.
  *
  * Plugin export shape: named `name`/`Config`/`apply`, NO default export — the
  * cordis Loader's `unwrapExports` does `exports.default ?? exports`, so a stray

packages/ui/acp/package.json

@@ -44,6 +44,7 @@
     "@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^",
     "@deepseek-ai/dsh-system-prompt": "workspace:^",
     "@deepseek-ai/dsh-tool-bash": "workspace:^",
+    "@deepseek-ai/dsh-tool-todo": "workspace:^",
     "@deepseek-ai/dsh-tools": "workspace:^",
     "cordis": "^4.0.0-rc.6"
   }

packages/ui/acp/src/index.ts

@@ -53,6 +53,8 @@ import {
   type LoadSessionResponse,
   type NewSessionRequest,
   type NewSessionResponse,
+  type Plan,
+  type PlanEntry,
   type PromptRequest,
   type PromptResponse,
   type SessionNotification,
@@ -64,7 +66,7 @@ import { CallId } from '@deepseek-ai/dsh-llm'
 import type { Agent, AgentStatus } from '@deepseek-ai/dsh-agent'
 import { AgentId } from '@deepseek-ai/dsh-agent'
 import { SessionId } from '@deepseek-ai/dsh-session'
-import type { SessionEvent, TurnEndReason } from '@deepseek-ai/dsh-session'
+import type { SessionEvent, TodoItem, TurnEndReason } from '@deepseek-ai/dsh-session'
 import type { ToolCallKind, ToolCallPresentation, ToolRegistry, ToolResultPresentation, ToolTerminal } from '@deepseek-ai/dsh-tools'
 // Side-effect type import: declaration-merges `ctx.sessionPersistence` onto
 // Context (the bridge injects it and reads `list()` for load cwd validation).
@@ -873,6 +875,10 @@ export function streamSessionEventUpdate(
       })
       return
     }
+    case 'todo/write': {
+      notify({ sessionId, update: { sessionUpdate: 'plan', ...todosToPlan(event.data.todos) } })
+      return
+    }
     // turn/step boundaries, context/message, steering,
     // assistant/message — no direct ACP client update.
     default:
@@ -880,6 +886,18 @@ export function streamSessionEventUpdate(
   }
 }
 
+/**
+ * Map a harness todo list to an ACP `plan` body. ACP's `PlanEntry` requires
+ * `content` + `priority` + `status`, but a {@link TodoItem} carries no priority,
+ * so synthesize a constant `'medium'` on every entry; `status` maps 1:1 (the
+ * harness status triple IS `PlanEntryStatus`). The ACP client REPLACES its whole
+ * plan on each `plan` update, matching the harness's whole-list-replace
+ * semantics, so no per-entry diffing is needed.
+ */
+export function todosToPlan(todos: TodoItem[]): Plan {
+  return { entries: todos.map((todo): PlanEntry => ({ content: todo.content, priority: 'medium', status: todo.status })) }
+}
+
 /**
  * Per-connection terminal-rendering context threaded into
  * {@link streamSessionEventUpdate}: whether the client advertised the

packages/ui/acp/tests/harness.ts

@@ -20,6 +20,7 @@ import AgentLoop from '@deepseek-ai/dsh-agent-loop'
 import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
 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 {
   ClientSideConnection,
   ndJsonStream,
@@ -158,6 +159,12 @@ export async function makeBridgeHarness(options: {
    * implementation over a mock in tests").
    */
   withBash?: boolean
+  /**
+   * Plug the REAL `dsh-tool-todo` tool so a test can drive `todo_write` through
+   * the bridge and assert the resulting `plan` sessionUpdate — the shipping
+   * tool + the bridge's own todo/write→plan mapping, not a stand-in.
+   */
+  withTodo?: boolean
 } = { storageDir: '' }): Promise<BridgeHarness> {
   const adapter = new MockAdapter(options.script ?? [])
 
@@ -173,6 +180,9 @@ export async function makeBridgeHarness(options: {
     await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 })
     await ctx.plugin(ToolBash)
   }
+  if (options.withTodo) {
+    await ctx.plugin(ToolTodo)
+  }
   ctx.llm.registerAdapter(['mock'], adapter)
 
   // Two identity byte pipes cross-wired into the two ndJsonStreams: bytes the

packages/ui/acp/tests/load.spec.ts

@@ -94,6 +94,44 @@ describe('acp bridge — session/load replay', () => {
     expect(content[0]?.content.text).toBe('```console\nhello\n```')
   })
 
+  it('replays a persisted todo/write as a plan sessionUpdate on load', async () => {
+    // A turn whose model called todo_write persists a todo/write event. A fresh
+    // bridge loading the session must re-emit the ACP `plan` update from the log
+    // (the load replay runs every event through streamSessionEventUpdate), so an
+    // editor reopening the session sees the current plan.
+    live = await makeBridgeHarness({
+      storageDir,
+      withTodo: true,
+      script: [
+        toolCallResponse('c1', 'todo_write', {
+          todos: [
+            { content: 'first step', status: 'in_progress' },
+            { content: 'second step', status: 'pending' },
+          ],
+        }),
+        textResponse('planned'),
+      ],
+    })
+    await live.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
+    const { sessionId } = await live.client.newSession({ cwd: process.cwd(), mcpServers: [] })
+    await live.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'plan it' }] })
+    await live.dispose()
+    live = undefined
+
+    loader = await makeBridgeHarness({ storageDir, withTodo: true, script: [] })
+    await loader.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
+    await loader.client.loadSession({ sessionId, cwd: process.cwd(), mcpServers: [] })
+
+    const plan = loader.updates.find(u => u.sessionUpdate === 'plan')
+    expect(plan).toEqual({
+      sessionUpdate: 'plan',
+      entries: [
+        { content: 'first step', priority: 'medium', status: 'in_progress' },
+        { content: 'second step', priority: 'medium', status: 'pending' },
+      ],
+    })
+  })
+
   it('replays a persisted bash call as a TERMINAL card when the loader advertises the capability', async () => {
     // The presentation is resolved at replay time, so a loader that advertised
     // _meta.terminal_output must reconstruct the terminal card (content + _meta)

packages/ui/acp/tests/stream-update.spec.ts

@@ -3,7 +3,7 @@ import { CallId } from '@deepseek-ai/dsh-llm'
 import { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session'
 import type { SessionNotification } from '@agentclientprotocol/sdk'
 import type { ToolDefinition, ToolRegistry } from '@deepseek-ai/dsh-tools'
-import { streamSessionEventUpdate, agentOptions, ToolPresenter } from '../src/index.ts'
+import { streamSessionEventUpdate, agentOptions, todosToPlan, ToolPresenter } from '../src/index.ts'
 
 /** Collect the updates a single event produces (no presenter → generic fallback). */
 function updatesFor(event: SessionEvent): SessionNotification['update'][] {
@@ -118,6 +118,43 @@ describe('streamSessionEventUpdate', () => {
     expect(updatesFor(evt('turn/end', { turn: 1, reason: { kind: 'completed' } }))).toEqual([])
     expect(updatesFor(evt('step/start', { turn: 1, step: 1 }))).toEqual([])
   })
+
+  it('maps todo/write to a plan sessionUpdate with priority synthesized as medium', () => {
+    expect(updatesFor(evt('todo/write', {
+      todos: [
+        { content: 'plan the work', status: 'in_progress' },
+        { content: 'write the code', status: 'pending' },
+        { content: 'run the tests', status: 'completed' },
+      ],
+    }))).toEqual([{
+      sessionUpdate: 'plan',
+      entries: [
+        { content: 'plan the work', priority: 'medium', status: 'in_progress' },
+        { content: 'write the code', priority: 'medium', status: 'pending' },
+        { content: 'run the tests', priority: 'medium', status: 'completed' },
+      ],
+    }])
+  })
+
+  it('maps an empty todo list to a plan with no entries', () => {
+    expect(updatesFor(evt('todo/write', { todos: [] }))).toEqual([{ sessionUpdate: 'plan', entries: [] }])
+  })
+})
+
+describe('todosToPlan', () => {
+  it('maps status 1:1 and stamps every entry priority medium', () => {
+    expect(todosToPlan([
+      { content: 'a', status: 'pending' },
+      { content: 'b', status: 'in_progress' },
+      { content: 'c', status: 'completed' },
+    ])).toEqual({
+      entries: [
+        { content: 'a', priority: 'medium', status: 'pending' },
+        { content: 'b', priority: 'medium', status: 'in_progress' },
+        { content: 'c', priority: 'medium', status: 'completed' },
+      ],
+    })
+  })
 })
 
 describe('ToolPresenter (tool-owned presentation via the tool registry)', () => {

packages/ui/stdio-agent/src/index.ts

@@ -6,9 +6,10 @@
  *
  * The cluster is BAKED IN, not left to the leaf: a stdio app always logs to the
  * console (stdout is just the terminal) and always pre-creates the `main` agent
- * `ui-stdio` sends to. The leaf supplies only the swappable backends (the LLM
- * adapter, the bash executor), the optional `hmr` dev-reload plugin, and this
- * app's {@link Config} (model, prompt, persistence root, welcome banner).
+ * `ui-stdio` sends to. The leaf supplies the swappable backends (the LLM
+ * adapter, the bash executor), optional product tools, the optional `hmr`
+ * dev-reload plugin, and this app's {@link Config} (model, prompt, persistence
+ * root, welcome banner).
  *
  * `hmr` is deliberately a LEAF entry, not baked in here: it is a Loader-only,
  * subprocess-only dev plugin (its constructor throws without `--expose-internals`