feat: implement bounded LLM request recovery

packages/ui/stdio/README.md

@@ -11,7 +11,7 @@ This package owns the terminal channel only. It injects `agents` and `userIntera
 | `welcome` | `ready.` | Banner printed before the first prompt |
 | `sessionId` | `main` | Exact agent/session identity driven by stdin and observed for EOF shutdown |
 
-The plugin seeds display labels from the live agent registry, then tracks `agent/created` and `agent/disposed` so HMR and externally managed agents render consistently. While an initial exact identity is pending, it buffers nonblank input until `agent/session-start` and observes live `agent-loop/config-start-failed`; a matching failure drops queued lines, reports the loss, and lets piped EOF finish instead of hanging. The composing app must mount this front door before its config-created agent. Disposal closes readline and unregisters every listener/provider through Cordis effects.
+The plugin seeds display labels from the live agent registry, then tracks `agent/created` and `agent/disposed` so HMR and externally managed agents render consistently. While an initial exact identity is pending, it buffers nonblank input until `agent/session-start` and observes live `agent-loop/config-start-failed`; a matching failure drops queued lines, reports the loss, and lets piped EOF finish instead of hanging. When a composed retry policy closes a failed step, the append-only transcript inserts an explicit discarded-attempt marker before later chunks; terminal request failure marks any preceding partial output discarded. The composing app must mount this front door before its config-created agent. Disposal closes readline and unregisters every listener/provider through Cordis effects.
 
 ```yaml
 - id: stdio

packages/ui/stdio/package.json

@@ -25,6 +25,7 @@
     "@deepseek-ai/dsh-agent": "^0.0.1",
     "@deepseek-ai/dsh-agent-loop": "^0.0.1",
     "@deepseek-ai/dsh-llm": "^0.0.1",
+    "@deepseek-ai/dsh-llm-retry": "^0.0.1",
     "@deepseek-ai/dsh-session": "^0.0.1",
     "@deepseek-ai/dsh-user-interaction": "^0.0.1",
     "cordis": "^4.0.0-rc.7"
@@ -42,6 +43,7 @@
     "@deepseek-ai/dsh-agent": "workspace:^",
     "@deepseek-ai/dsh-agent-loop": "workspace:^",
     "@deepseek-ai/dsh-llm": "workspace:^",
+    "@deepseek-ai/dsh-llm-retry": "workspace:^",
     "@deepseek-ai/dsh-session": "workspace:^",
     "@deepseek-ai/dsh-user-interaction": "workspace:^",
     "cordis": "^4.0.0-rc.7"

packages/ui/stdio/src/index.ts

@@ -16,6 +16,7 @@ import type { Context } from 'cordis'
 import z from 'schemastery'
 import type { Agent } from '@deepseek-ai/dsh-agent'
 import type {} from '@deepseek-ai/dsh-agent-loop'
+import type {} from '@deepseek-ai/dsh-llm-retry'
 import { SessionId } from '@deepseek-ai/dsh-session'
 import {
   UserInteractionError,
@@ -119,6 +120,10 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt
   // append order keeps `inReasoning` transitions deterministic across chunk and
   // boundary events.
   let inReasoning = false
+  const resetReasoning = (): void => {
+    if (inReasoning) output.write('\x1B[0m')
+    inReasoning = false
+  }
   ctx.on('session/event', (session, event) => {
     if (event.type === 'assistant/chunk') {
       const { chunk } = event.data
@@ -135,22 +140,31 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt
     } else if (event.type === 'turn/start') {
       const label = target?.session === session ? 'main' : session.id
       output.write(`\n[${label} turn ${event.data.turn}] `)
+    } else if (event.type === 'llm/retry') {
+      resetReasoning()
+      output.write(
+        `\n  [previous model attempt discarded; retry ${event.data.retry}/${event.data.maxRetries}`
+        + ` in ${event.data.delayMs}ms: ${event.data.failure.message}]\n  `,
+      )
     } else if (event.type === 'turn/end') {
-      if (inReasoning) output.write('\x1B[0m')
-      inReasoning = false
+      resetReasoning()
+      if (event.data.reason.kind === 'error') {
+        const message = 'failure' in event.data.reason
+          ? event.data.reason.failure.message
+          : event.data.reason.message
+        output.write(`\n  [model attempt failed; any partial output above is discarded: ${message}]`)
+      }
       output.write('\n> ')
     } else if (event.type === 'tool/call') {
       const { name: toolName, arguments: args } = event.data
-      if (inReasoning) output.write('\x1B[0m')
-      inReasoning = false
+      resetReasoning()
       output.write(`\n  [tool call] ${toolName}(${args})`)
     } else if (event.type === 'tool/result') {
       const { content } = event.data
       const text = content.filter(block => block.type === 'text').map(block => block.text).join('')
       output.write(`\n  [tool result] ${text}\n  `)
     } else if (event.type === 'todo/write') {
-      if (inReasoning) output.write('\x1B[0m')
-      inReasoning = false
+      resetReasoning()
       const glyph = (status: string): string =>
         status === 'completed' ? '[x]' : status === 'in_progress' ? '[~]' : '[ ]'
       const lines = event.data.todos.map(todo => `    ${glyph(todo.status)} ${todo.content}`).join('\n')

packages/ui/stdio/tests/stdio.spec.ts

@@ -290,6 +290,51 @@ describe('createStdioChat rendering', () => {
     expect(out.text()).toContain('\x1B[2mmid\x1B[0m')
   })
 
+  it('marks failed partial output at retry and terminal failure boundaries', async () => {
+    const { ctx, out } = await setup()
+    const session = makeSession('main')
+    ctx.emit('session/event', session, chunkEvent({ type: 'reasoning-delta', index: 0, text: 'partial' }))
+    ctx.emit('session/event', session, {
+      type: 'llm/retry',
+      seq: 1,
+      time: 0,
+      data: {
+        turn: 1,
+        step: 1,
+        retry: 1,
+        maxRetries: 2,
+        delayMs: 500,
+        failure: { message: 'backend busy', code: 'SERVER' },
+      },
+    })
+    ctx.emit('session/event', session, {
+      type: 'turn/end',
+      seq: 3,
+      time: 0,
+      data: { turn: 2, reason: { kind: 'error', step: 1, message: 'loop defect' } },
+    })
+    ctx.emit('session/event', session, chunkEvent({ type: 'text-delta', index: 0, text: 'also partial' }))
+    ctx.emit('session/event', session, {
+      type: 'turn/end',
+      seq: 2,
+      time: 0,
+      data: {
+        turn: 1,
+        reason: { kind: 'error', step: 2, failure: { message: 'still busy', code: 'SERVER' } },
+      },
+    })
+
+    expect(out.text()).toContain(
+      '\x1B[2mpartial\x1B[0m\n  [previous model attempt discarded; retry 1/2 in 500ms: backend busy]',
+    )
+    expect(out.text()).toContain(
+      'also partial\n  [model attempt failed; any partial output above is discarded: still busy]\n> ',
+    )
+    expect(out.text()).toContain(
+      '[model attempt failed; any partial output above is discarded: loop defect]\n> ',
+    )
+  })
+
   it('drops the target object on agent/disposed', async () => {
     const { ctx, out } = await setup()
     const agent = makeAgent('main')

packages/ui/stdio/tsconfig.json

@@ -26,6 +26,9 @@
     {
       "path": "../../llm/llm"
     },
+    {
+      "path": "../../llm/llm-retry"
+    },
     {
       "path": "../user-interaction"
     }