Merge branch 'codex/goal-session' into codex/commands

# Conflicts:
#	docs/config-catalog.md
#	docs/module-graph.md
#	examples/acp-agent/tests/snapshots/error-finish/stdout.expected.jsonl
#	packages/ui/acp/README.md
#	packages/ui/tui/README.md

packages/ui/acp/README.md

@@ -28,9 +28,9 @@ The `initialize` handshake reports a fixed server identity (`agentInfo: { name:
 | `initialize` | static | negotiate `protocolVersion`; advertise baseline prompt capabilities (`text`, plus `resource_link` rendered as text) and `loadSession: true` |
 | `session/new` | `ctx.agents.create({ sessionId, meta:{cwd} })` | creates a new session/agent; N concurrent sessions are allowed, keyed by id; advertises the effective command snapshot; `cwd` must be absolute (it becomes the session's workspace — see Per-session cwd); non-empty `additionalDirectories` and `mcpServers` rejected |
 | `session/load` | `ctx.agents.resume(...)` | reserves the id, verifies the persisted cwd, resumes, replays user, assistant, and tool events, and re-advertises commands |
-| `session/prompt` | `ctx.commands.execute()` or `agent.send()` | a flattened prompt beginning with `/` stays in the direct command plane; ordinary prompts support ACP `text` and `resource_link`; unsupported content and empty prompts are rejected; one request is in flight per session |
+| `session/prompt` | `ctx.commands.execute()` or `agent.send()` | a flattened prompt beginning with `/` stays in the direct command plane; ordinary prompts support ACP `text` and `resource_link`; unsupported content and empty prompts are rejected; one request is in flight per session and settles on the owning turn's end, with an error turn rejecting the RPC |
 | `session/cancel` | command `AbortSignal` or `agent.cancel()` | aborts the exact direct command, or applies the queue-aware agent cancel and settles its prompt `cancelled`; one session never cancels another |
-| `session/update` | `session/event` | streams user replay, assistant text/reasoning, and tool render intents |
+| `session/update` | `session/event` | streams user replay, assistant text/reasoning, retry/failure attempt markers, and tool render intents |
 | `elicitation/create` | `ctx.userInteraction.ask()` | maps `ask_user_question` questions to ACP form elicitations; option descriptions are shown in enum titles, `multi_select` uses ACP array enums, optionless requests use a required `custom` field, and a non-empty custom answer overrides any selected choice |
 | `session/request_permission` | `approval/request` listener | answers one-shot allow/reject requests for bridge-owned calls; foreign or call-less requests delegate and fail closed if unanswered — see "Permission prompts" |
 | `session/set_config_option` | agent-scoped request target / `ctx.permission.set()` | per-session provider+model and permission-preset switching over [session config options](https://agentclientprotocol.com/protocol/session-config-options) — see "Session config options" |
@@ -53,6 +53,8 @@ When `ctx.permission` is composed, the bridge also advertises a `permission` sel
 
 The shared [`ctx.tasks` runtime](../../tasks/tasks/) fences access to predictable task ids by the owning session; ACP sessions therefore cannot read or stop one another's background work.
 
+ACP updates are append-only, so `llm/retry` emits a visible separator that marks preceding partial model output discarded before the next attempt streams. A terminal model-request failure emits the same discarded-output warning; replay derives both markers from the durable events.
+
 ## Per-session cwd
 
 `session/new` records the request's absolute cwd in the session header. Before constructing an agent, `session/load` uses persisted metadata to require an absolute request cwd that matches the stored one. Bash defaults to that workspace; an explicit relative workdir resolves against it, and multiple sessions may use different workspaces. `additionalDirectories` remains unsupported.

packages/ui/acp/package.json

@@ -31,6 +31,7 @@
     "@deepseek-ai/dsh-bash": "^0.0.1",
     "@deepseek-ai/dsh-commands": "^0.0.1",
     "@deepseek-ai/dsh-llm": "^0.0.1",
+    "@deepseek-ai/dsh-llm-retry": "^0.0.1",
     "@deepseek-ai/dsh-permission": "^0.0.1",
     "@deepseek-ai/dsh-sandbox": "^0.0.1",
     "@deepseek-ai/dsh-session": "^0.0.1",
@@ -52,6 +53,7 @@
     "@deepseek-ai/dsh-fs-policy": "workspace:^",
     "@deepseek-ai/dsh-invariants": "workspace:^",
     "@deepseek-ai/dsh-llm": "workspace:^",
+    "@deepseek-ai/dsh-llm-retry": "workspace:^",
     "@deepseek-ai/dsh-permission": "workspace:^",
     "@deepseek-ai/dsh-sandbox": "workspace:^",
     "@deepseek-ai/dsh-session": "workspace:^",

packages/ui/acp/src/index.ts

@@ -46,6 +46,7 @@ import {
 } from '@agentclientprotocol/sdk'
 import type { ContentBlock, LlmCallConfig, LlmModelInfo, LlmProviderInfo } from '@deepseek-ai/dsh-llm'
 import { assertNever, CallId } from '@deepseek-ai/dsh-llm'
+import type {} from '@deepseek-ai/dsh-llm-retry'
 import type { Agent } from '@deepseek-ai/dsh-agent'
 import type {} from '@deepseek-ai/dsh-commands'
 import { SessionId } from '@deepseek-ai/dsh-session'
@@ -564,7 +565,7 @@ export function apply(ctx: Context, config: AcpConfig): void {
     reason: TurnEndReason,
   ): void => {
     if (reason.kind === 'error') {
-      inflight.reject(internalError(`turn failed: ${reason.message}`))
+      inflight.reject(internalError(`turn failed: ${'failure' in reason ? reason.failure.message : reason.message}`))
     } else {
       inflight.resolve(turnEndToStopReason(reason))
     }
@@ -1176,6 +1177,7 @@ function validateMcpServers(params: { mcpServers?: unknown[] }): void {
  * identical update stream from the same event log.
  *
  * - `assistant/chunk` text-delta/reasoning-delta → message/thought chunks
+ * - `llm/retry` and terminal model failure → visible discarded-attempt markers
  * - `user/message` → `user_message_chunk` during load replay only — so a
  *   loaded transcript reconstructs the USER side of each turn without echoing
  *   a live `session/prompt` back to the client
@@ -1223,6 +1225,13 @@ export function streamSessionEventUpdate(
       }
       return
     }
+    case 'llm/retry': {
+      const text = '\n\n[Previous model attempt discarded; retrying '
+        + `${event.data.retry}/${event.data.maxRetries} in ${event.data.delayMs}ms: `
+        + `${event.data.failure.message}]\n\n`
+      notify({ sessionId, update: { sessionUpdate: 'agent_message_chunk', content: { type: 'text', text } } })
+      return
+    }
     case 'user/message': {
       if (!includeUserMessages) return
       // Replay the user's prompt so a loaded session shows both sides of each
@@ -1254,7 +1263,13 @@ export function streamSessionEventUpdate(
       notify({ sessionId, update: { sessionUpdate: 'plan', ...todosToPlan(event.data.todos) } })
       return
     }
-    // turn/step boundaries, context/message, steering,
+    case 'turn/end': {
+      if (event.data.reason.kind !== 'error' || !('failure' in event.data.reason)) return
+      const text = `\n\n[Model attempt failed; any partial output above is discarded: ${event.data.reason.failure.message}]\n\n`
+      notify({ sessionId, update: { sessionUpdate: 'agent_message_chunk', content: { type: 'text', text } } })
+      return
+    }
+    // non-error turn/step boundaries, context/message, steering,
     // assistant/message — no direct ACP client update.
     default:
       return

packages/ui/acp/tests/harness.ts

@@ -101,7 +101,7 @@ export function errorResponse(message: string): StreamChunk[] {
   return [
     { type: 'block-start', index: 0, blockType: 'text' },
     { type: 'text-delta', index: 0, text: 'partial' },
-    { type: 'finish', reason: { kind: 'error', message, code: 'PROVIDER_ERROR' } },
+    { type: 'finish', reason: { kind: 'error', failure: { message, code: 'PROVIDER_ERROR' } } },
   ]
 }
 

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

@@ -65,6 +65,37 @@ describe('streamSessionEventUpdate', () => {
       .toEqual([])
   })
 
+  it('marks retry and terminal model failure boundaries but not ordinary turn errors', () => {
+    expect(updatesFor(evt('llm/retry', {
+      turn: 1,
+      step: 1,
+      retry: 1,
+      maxRetries: 2,
+      delayMs: 500,
+      failure: { message: 'backend busy', code: 'SERVER' },
+    }))).toEqual([{
+      sessionUpdate: 'agent_message_chunk',
+      content: {
+        type: 'text',
+        text: '\n\n[Previous model attempt discarded; retrying 1/2 in 500ms: backend busy]\n\n',
+      },
+    }])
+    expect(updatesFor(evt('turn/end', {
+      turn: 1,
+      reason: { kind: 'error', step: 2, failure: { message: 'still busy', code: 'SERVER' } },
+    }))).toEqual([{
+      sessionUpdate: 'agent_message_chunk',
+      content: {
+        type: 'text',
+        text: '\n\n[Model attempt failed; any partial output above is discarded: still busy]\n\n',
+      },
+    }])
+    expect(updatesFor(evt('turn/end', {
+      turn: 1,
+      reason: { kind: 'error', step: 2, message: 'post-step failed' },
+    }))).toEqual([])
+  })
+
   it('maps tool/call to an in_progress tool_call with kind other and parsed rawInput (generic fallback, no presenter)', () => {
     const updates = updatesFor(evt('tool/call', { turn: 1, step: 1, callId: CallId('c1'), name: 'bash', arguments: '{"command":"ls"}' }))
     expect(updates).toEqual([{

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

@@ -49,6 +49,15 @@ describe('acp bridge — turn outcomes', () => {
       .rejects.toThrow(/turn failed: provider boom/)
   })
 
+  it('rejects an ordinary plugin turn failure through the same ACP boundary', async () => {
+    harness = await makeBridgeHarness({ storageDir, script: [textResponse('must not run')] })
+    harness.ctx.on('agent/pre-step', () => { throw new Error('plugin pre-step failed') })
+    const sessionId = await newSession(harness)
+
+    await expect(harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }))
+      .rejects.toThrow(/turn failed: plugin pre-step failed/)
+  })
+
   it('streams a tool call as tool_call then tool_call_update', async () => {
     harness = await makeBridgeHarness({
       storageDir,

packages/ui/acp/tsconfig.json

@@ -20,6 +20,9 @@
     {
       "path": "../../llm/llm"
     },
+    {
+      "path": "../../llm/llm-retry"
+    },
     {
       "path": "../../core/session"
     },