Merge remote-tracking branch 'origin/master' into codex/provider-retry-policy

# Conflicts: # .agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md # docs/core-data-structures/llm-streaming.i18n.yaml # packages/llm/llm-retry/README.md # packages/llm/llm-retry/src/index.ts # packages/llm/llm-retry/tests/retry.spec.ts
2026-07-25 16:05:05 +08:00
parent efc725b7e4 f51f1d6f9e
commit 5345e93ceb
156 changed files with 1412 additions and 1079 deletions
--- a/examples/acp-agent/retry.cordis.snapshot.yml
+++ b/examples/acp-agent/retry.cordis.snapshot.yml
@@ -0,0 +1,42 @@
+# Keyless replay for the retry overlay: disable the key-requiring DeepSeek
+# 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:
+    path: ./cordis.yml
+    patches:
+      - id: llm-deepseek
+        name: '@deepseek-ai/dsh-llm-deepseek'
+        disabled: true
+      - id: acp-agent
+        name: '@deepseek-ai/dsh-acp-demo'
+        config:
+          provider: deepseek
+          model: deepseek-v4-flash
+          persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
+          persistenceCompression: none
+          workspaceContext:
+            maxBytes: 65536
+          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.
+
+            Verify your work by running the code or tests. Keep answers brief and factual.
+      - insert:
+          - id: llm-replay
+            name: '@deepseek-ai/dsh-llm-replay'
+            config:
+              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
--- a/examples/acp-agent/retry.cordis.yml
+++ b/examples/acp-agent/retry.cordis.yml
@@ -0,0 +1,43 @@
+# Retry-scenario overlay: pin the bounded transient retry policy to a
+# 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.
+# 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:
+          provider: deepseek
+          model: deepseek-v4-flash
+          persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
+          persistenceCompression: !!js "process.env.DSH_SNAPSHOT === undefined ? 'zstd' : 'none'"
+          workspaceContext:
+            maxBytes: 65536
+          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.
+
+            Verify your work by running the code or tests. Keep answers brief and factual.
--- a/examples/acp-agent/tests/acp.e2e.ts
+++ b/examples/acp-agent/tests/acp.e2e.ts
@@ -114,7 +114,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('acp-agent e2e: real prompt over
    })
    expect(['end_turn', 'max_tokens']).toContain(res.stopReason)

-    // Verify the WORLD, not the agent's self-report: read the file from disk.
+    // Assert the filesystem effect independently of the model response.
    const proof = await readFile(join(workdir, 'proof.txt'), 'utf8')
    expect(proof).toContain('ACP_OK')

--- a/examples/acp-agent/tests/acp.snapshot.ts
+++ b/examples/acp-agent/tests/acp.snapshot.ts
@@ -38,6 +38,7 @@ const PTY_CONFIG = fileURLToPath(new URL('../pty.cordis.yml', import.meta.url))
 const DEPTH_TWO_CONFIG = fileURLToPath(new URL('../depth-two.cordis.yml', import.meta.url))
 const PACKED_CHUNKS_CONFIG = fileURLToPath(new URL('../packed-chunks.cordis.yml', import.meta.url))
 const SESSION_SANDBOX_ROOT_CONFIG = fileURLToPath(new URL('../session-sandbox-root.cordis.yml', import.meta.url))
+const RETRY_CONFIG = fileURLToPath(new URL('../retry.cordis.yml', import.meta.url))
 const LSP_CONFIG = fileURLToPath(new URL('./lsp.cordis.yml', import.meta.url))
 const SNAPSHOTS_DIR = join(dirname(fileURLToPath(import.meta.url)), 'snapshots')
 const PACKED_CHUNKS_SOURCE = 'hook-cc-pretool-deny'
@@ -112,6 +113,14 @@ const SCENARIOS: Scenario[] = [
  { name: 'fs-policy-reject', hasModelTurn: true, recorded: true },
  { name: 'multi-turn', hasModelTurn: true, recorded: true },
  { 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
+  // llm/retry event, no ACP output for the discarded attempt, the recovered
+  // reply, and a clean completed 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
  // LIVE model to repeat one call three times is not a stable recording, so
  // the fixture scripts five identical todo_write calls and pins BOTH reminder
--- a/examples/acp-agent/tests/hooks.e2e.ts
+++ b/examples/acp-agent/tests/hooks.e2e.ts
@@ -62,7 +62,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('acp-agent e2e: a PreToolUse hook
    // the model, not a turn failure).
    expect(['end_turn', 'max_tokens']).toContain(res.stopReason)

-    // Verify that the denied hook left no filesystem effect.
+    // Assert the denied operation independently of the model response.
    await expect(access(join(workdir, 'proof.txt'))).rejects.toThrow()

    // ACP publishes only the committed answer; hook/tool trace stays in the session log.
--- a/examples/acp-agent/tests/snapshots/empty-response-retry/input.json
+++ b/examples/acp-agent/tests/snapshots/empty-response-retry/input.json
@@ -0,0 +1,7 @@
+{
+  "steps": [
+    { "op": "initialize" },
+    { "op": "newSession" },
+    { "op": "prompt", "text": "This prompt first receives an empty completion, then a retried reply." }
+  ]
+}
--- a/examples/acp-agent/tests/snapshots/empty-response-retry/session.jsonl
+++ b/examples/acp-agent/tests/snapshots/empty-response-retry/session.jsonl
@@ -0,0 +1,19 @@
+{"type":"session","version":0,"id":"{{sessionId}}","createdAt":0,"cwd":"{{cwd}}","delegationDepth":0}
+{"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
+{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"This prompt first receives an empty completion, then a retried reply."}],"source":{"kind":"user"}},"surfaceOp":"append"}
+{"type":"session/title","seq":2,"time":0,"data":{"title":"This prompt first receives an","messageSeqs":[1],"source":{"kind":"fallback"}}}
+{"type":"step/start","seq":3,"time":0,"data":{"turn":1,"step":1}}
+{"type":"request/header","seq":4,"time":0,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
+{"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,"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":"step/start","seq":9,"time":0,"data":{"turn":1,"step":2}}
+{"type":"assistant/chunk","seq":10,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
+{"type":"assistant/chunk","seq":11,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":0,"text":"Recovered."}}}
+{"type":"assistant/chunk","seq":12,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"Recovered."}}}}
+{"type":"assistant/chunk","seq":13,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":12,"outputTokens":3}}}}
+{"type":"assistant/chunk","seq":14,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
+{"type":"assistant/message","seq":15,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"text","text":"Recovered."}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":12,"outputTokens":3}},"sourceEventSeqs":[10,11,12,13,14],"surfaceOp":"append"}
+{"type":"step/end","seq":16,"time":0,"data":{"turn":1,"step":2}}
+{"type":"turn/end","seq":17,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}
--- a/examples/acp-agent/tests/snapshots/empty-response-retry/stdout.expected.jsonl
+++ b/examples/acp-agent/tests/snapshots/empty-response-retry/stdout.expected.jsonl
@@ -0,0 +1,4 @@
+{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
+{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"Recovered."}}}}
+{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}}