Merge remote-tracking branch 'origin/master' into feat/todo-multi-in-progress

examples/acp-agent/retry.cordis.snapshot.yml

@@ -1,8 +1,7 @@
 # Keyless replay for the retry overlay: disable the key-requiring DeepSeek
-# adapter, insert `llm-replay`, and restate the app config with the same
-# deterministic 1 ms zero-jitter retry policy as the live sibling. A config
-# patch replaces the whole app config, so the base fields are restated
-# verbatim (raw JSONL persistence so the harness can harvest the log).
+# adapter, insert `llm-replay`, and give its provider the same deterministic
+# 1 ms zero-jitter retry policy as the live sibling. The app patch still
+# restates its whole config for raw JSONL persistence and the recorded model.
 - id: base
   name: '@cordisjs/plugin-include'
   config:
@@ -20,11 +19,6 @@
           persistenceCompression: none
           workspaceContext:
             maxBytes: 65536
-          llmRetry:
-            maxTransientRetries: 2
-            initialDelayMs: 1
-            maxDelayMs: 1
-            jitterRatio: 0
           persona: |
             You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}. Your bash tool runs under a file sandbox — a `[sandbox: file access denied …]` result is policy, not a command bug.
 
@@ -36,6 +30,13 @@
               providers:
                 - id: deepseek
                   name: DeepSeek
+                  retryPolicy:
+                    mode: normal
+                    maxRetries: 2
+                    backoff:
+                      initialDelayMs: 1
+                      maxDelayMs: 1
+                      jitterRatio: 0
                   models:
                     - id: deepseek-v4-flash
                     - id: deepseek-v4-pro

examples/acp-agent/retry.cordis.yml

@@ -2,14 +2,32 @@
 # deterministic 1 ms zero-jitter delay so the durable `llm/retry` event
 # (`delayMs`) and replay wall time stay reproducible. The overlay changes no
 # tool or prompt composition, so its scenarios share the default header class.
-# A config patch replaces the whole app config, so the base fields are restated
-# verbatim; the model is re-pinned to `deepseek-v4-flash` like the other
-# snapshot overlays because the recorded corpus was captured on flash.
+# Config patches replace whole plugin configs: the provider patch restates its
+# adapter fields around `retryPolicy`, while the app patch re-pins the recorded
+# flash model and restates its base fields.
 - id: base
   name: '@cordisjs/plugin-include'
   config:
     path: ./cordis.yml
     patches:
+      - id: llm-deepseek
+        name: '@deepseek-ai/dsh-llm-deepseek'
+        config:
+          apiKey: !!js process.env.DEEPSEEK_API_KEY
+          baseURL: !!js process.env.DEEPSEEK_BASE_URL
+          thinking: enabled
+          reasoningEffort: max
+          defaultContextWindow: 256000
+          retryPolicy:
+            mode: normal
+            maxRetries: 2
+            backoff:
+              initialDelayMs: 1
+              maxDelayMs: 1
+              jitterRatio: 0
+          models:
+            - id: deepseek-v4-flash
+            - id: deepseek-v4-pro
       - id: acp-agent
         name: '@deepseek-ai/dsh-acp-demo'
         config:
@@ -19,11 +37,6 @@
           persistenceCompression: !!js "process.env.DSH_SNAPSHOT === undefined ? 'zstd' : 'none'"
           workspaceContext:
             maxBytes: 65536
-          llmRetry:
-            maxTransientRetries: 2
-            initialDelayMs: 1
-            maxDelayMs: 1
-            jitterRatio: 0
           persona: |
             You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}. Your bash tool runs under a file sandbox — a `[sandbox: file access denied …]` result is policy, not a command bug.
 

examples/acp-agent/tests/acp.snapshot.ts

@@ -131,10 +131,10 @@ const SCENARIOS: Scenario[] = [
   { name: 'error-finish', hasModelTurn: true, recorded: false, overridden: true },
   // Keyless, authored (like error-finish): a live provider cannot be coaxed
   // into a degenerate empty completion, so the fixture scripts the adapters'
-  // EMPTY_RESPONSE error finish (step 1) followed by the recovered reply
-  // (step 2), proving the default retry policy end to end: the durable
+  // EMPTY_RESPONSE error finish in turn 1 followed by the recovered reply
+  // in retry turn 2, proving the default retry policy end to end: the durable
   // llm/retry event, no ACP output for the discarded attempt, the recovered
-  // reply, and a clean completed turn. Its overlay only pins a deterministic
+  // reply, and a clean completed retry turn. Its overlay only pins a deterministic
   // 1 ms zero-jitter delay, so it shares the default header class.
   { name: 'empty-response-retry', hasModelTurn: true, recorded: false, configPath: RETRY_CONFIG },
   // Keyless, authored (like error-finish/cancel): deterministically forcing a

examples/acp-agent/tests/snapshots/empty-response-retry/session.jsonl

@@ -7,7 +7,7 @@
 {"type":"assistant/chunk","seq":5,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":0,"outputTokens":0}}}}
 {"type":"assistant/chunk","seq":6,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"error","failure":{"message":"model returned a completed response with no content","code":"EMPTY_RESPONSE"}}}}}
 {"type":"step/end","seq":7,"time":0,"data":{"turn":1,"step":1}}
-{"type":"llm/retry","seq":8,"time":0,"data":{"turn":1,"step":1,"retry":1,"maxRetries":2,"delayMs":1,"failure":{"message":"model returned a completed response with no content","code":"EMPTY_RESPONSE"}}}
+{"type":"llm/retry","seq":8,"time":0,"data":{"turn":1,"step":1,"provider":"deepseek","mode":"normal","policyKey":"[\"normal\",2,[\"EMPTY_RESPONSE\",\"RATE_LIMIT\",\"SERVER\",\"TIMEOUT\",\"TRANSPORT\"],1,1,0]","retry":1,"maxRetries":2,"delayMs":1,"failure":{"message":"model returned a completed response with no content","code":"EMPTY_RESPONSE"}}}
 {"type":"turn/end","seq":9,"time":1785047244285,"data":{"turn":1,"reason":{"kind":"error","step":1,"failure":{"message":"model returned a completed response with no content","code":"EMPTY_RESPONSE"}}}}
 {"type":"turn/start","seq":10,"time":1785047244285,"data":{"turn":2,"trigger":{"kind":"retry"}}}
 {"type":"step/start","seq":11,"time":1785047244289,"data":{"turn":2,"step":1}}

examples/headless-agent/retry.cordis.snapshot.yml

@@ -0,0 +1,12 @@
+# Keyless provider-retry composition for the headless stream-json snapshot.
+- id: base
+  name: '@cordisjs/plugin-include'
+  config:
+    path: ./cordis.yml
+    patches:
+      - id: llm-deepseek
+        name: '@deepseek-ai/dsh-llm-deepseek'
+        disabled: true
+      - insert:
+          - id: retry-snapshot-backend
+            name: './tests/fixtures/retry-snapshot-backend.mjs'

examples/headless-agent/tests/fixtures/retry-snapshot-backend.mjs

@@ -0,0 +1,53 @@
+/** Deterministic provider adapter for the headless retry-policy snapshot. */
+
+import {
+  LlmAdapter,
+  LlmError,
+  resolveRetryPolicy,
+} from '@deepseek-ai/dsh-llm'
+
+class RetrySnapshotAdapter extends LlmAdapter {
+  requests = 0
+  firstMessages
+  policy = resolveRetryPolicy({
+    mode: 'normal',
+    maxRetries: 1,
+    retryableCodes: ['RATE_LIMIT'],
+    backoff: { initialDelayMs: 1, maxDelayMs: 1, jitterRatio: 0 },
+  }, 'retry-snapshot-backend.retryPolicy')
+
+  providerRetryPolicy() {
+    return this.policy
+  }
+
+  async * stream(options) {
+    const messages = JSON.stringify(options.messages)
+    this.requests++
+    if (this.requests === 1) {
+      this.firstMessages = messages
+      throw new LlmError('snapshot transient failure', 'RATE_LIMIT', { status: 429 })
+    }
+    if (this.requests === 2 && messages !== this.firstMessages) {
+      throw new Error('retry snapshot changed the model-visible messages')
+    }
+    const text = 'RETRY_OK'
+    yield { type: 'block-start', index: 0, blockType: 'text' }
+    yield { type: 'text-delta', index: 0, text }
+    yield { type: 'block-end', index: 0, block: { type: 'text', text } }
+    yield { type: 'usage', usage: { inputTokens: 4, outputTokens: 2 } }
+    yield { type: 'finish', reason: { kind: 'stop' } }
+  }
+}
+
+/** Cordis plugin name. */
+export const name = 'retry-snapshot-backend'
+/** Required LLM registry service. */
+export const inject = ['llm']
+
+/**
+ * Register the deterministic provider adapter.
+ * @param {import('cordis').Context} ctx - plugin context carrying the LLM service.
+ */
+export function apply(ctx) {
+  ctx.llm.registerAdapter(['deepseek'], new RetrySnapshotAdapter())
+}

examples/headless-agent/tests/headless.snapshot.ts

@@ -24,6 +24,8 @@ const ptyStreamExpected = join(ptyScenarioDir, 'stream-json.expected.jsonl')
 const ptyConfigPath = fileURLToPath(new URL('../pty.cordis.snapshot.yml', import.meta.url))
 const goalScenarioDir = join(snapshotsDir, 'goal-tools')
 const goalConfigPath = fileURLToPath(new URL('../goal.cordis.snapshot.yml', import.meta.url))
+const retryScenarioDir = join(snapshotsDir, 'provider-retry')
+const retryConfigPath = fileURLToPath(new URL('../retry.cordis.snapshot.yml', import.meta.url))
 const ralphScenarioDir = join(snapshotsDir, 'ralph-loop')
 const ralphConfigPath = fileURLToPath(new URL('../ralph.cordis.snapshot.yml', import.meta.url))
 const binScript = fileURLToPath(new URL('../../../packages/examples/cli-demo/src/bin.ts', import.meta.url))
@@ -125,6 +127,46 @@ async function persistedLogs(cwd: string): Promise<PersistedLog[]> {
 }
 
 describe('headless stream-json snapshots', () => {
+  it('retries a transient provider failure through the one-shot app', async () => {
+    const prompt = await scenarioPrompt(retryScenarioDir, 'provider-retry')
+    const streamExpected = join(retryScenarioDir, 'stream-json.expected.jsonl')
+    let runCwd = ''
+    const result = await runLoaderSmoke({
+      label: 'provider retry headless stream-json snapshot',
+      tempDirPrefix: 'headless-snapshot-provider-retry-',
+      binScript,
+      configPath: retryConfigPath,
+      binArgs: ['--config', retryConfigPath, '--output-format', 'stream-json', prompt],
+      tsconfigPath,
+      env: {
+        DSH_SNAPSHOT: 'replay',
+        NODE_OPTIONS: [process.env.NODE_OPTIONS, '--disable-warning=ExperimentalWarning'].filter(Boolean).join(' '),
+      },
+      prepare: (cwd) => { runCwd = cwd },
+      inspect: async (cwd) => {
+        const logs = await persistedLogs(cwd)
+        expect(logs).toHaveLength(1)
+        const records = parseJsonl(logs[0]?.content ?? '')
+        const retries = records.filter(record => record.type === 'llm/retry')
+        expect(retries).toHaveLength(1)
+        expect(retries[0]?.data).toMatchObject({
+          provider: 'deepseek',
+          mode: 'normal',
+          policyKey: '["normal",1,["RATE_LIMIT"],1,1,0]',
+          retry: 1,
+          maxRetries: 1,
+          delayMs: 1,
+          failure: { message: 'snapshot transient failure', code: 'RATE_LIMIT', status: 429 },
+        })
+      },
+    })
+
+    expect(result.stderr).toBe('')
+    const normalized = normalizeHeadlessStream(result.stdout, runCwd)
+    if (refreshing) await writeFile(streamExpected, normalized)
+    expect(normalized).toBe(await readFile(streamExpected, 'utf8'))
+  }, LOADER_SMOKE_TEST_TIMEOUT_MS)
+
   it('logs the model default and a dynamic next-step reasoning effort', async () => {
     const result = await runLoaderSmoke({
       label: 'reasoning effort headless stream-json snapshot',

examples/headless-agent/tests/snapshots/provider-retry/input.json

@@ -0,0 +1,8 @@
+{
+  "steps": [
+    {
+      "op": "prompt",
+      "text": "retry the transient provider failure"
+    }
+  ]
+}

examples/headless-agent/tests/snapshots/provider-retry/stream-json.expected.jsonl

@@ -0,0 +1,19 @@
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"retry the transient provider failure"}],"source":{"kind":"user"}},"surfaceOp":"append"}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"session/title","seq":2,"time":0,"data":{"title":"retry the transient provider failure","messageSeqs":[1],"source":{"kind":"fallback"}}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":3,"time":0,"data":{"turn":1,"step":1}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/header","seq":4,"time":0,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":5,"time":0,"data":{"turn":1,"step":1}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"llm/retry","seq":6,"time":0,"data":{"turn":1,"step":1,"provider":"deepseek","mode":"normal","policyKey":"[\"normal\",1,[\"RATE_LIMIT\"],1,1,0]","retry":1,"maxRetries":1,"delayMs":1,"failure":{"message":"snapshot transient failure","code":"RATE_LIMIT","status":429}}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/end","seq":7,"time":0,"data":{"turn":1,"reason":{"kind":"error","step":1,"failure":{"message":"snapshot transient failure","code":"RATE_LIMIT","status":429}}}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/start","seq":8,"time":0,"data":{"turn":2,"trigger":{"kind":"retry"}}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":9,"time":0,"data":{"turn":2,"step":1}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":10,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":11,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"text-delta","index":0,"text":"RETRY_OK"}}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":12,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"RETRY_OK"}}}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":13,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":4,"outputTokens":2}}}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":14,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":15,"time":0,"data":{"turn":2,"step":1,"content":[{"type":"text","text":"RETRY_OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":4,"outputTokens":2}},"sourceEventSeqs":[10,11,12,13,14],"surfaceOp":"append"}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":16,"time":0,"data":{"turn":2,"step":1}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/end","seq":17,"time":0,"data":{"turn":2,"reason":{"kind":"completed"}}}}
+{"type":"result","success":true,"sessionId":"{{sessionId}}","turn":2,"result":"RETRY_OK","reason":{"kind":"completed"},"usage":{"inputTokens":4,"outputTokens":2}}