fix(llm): classify empty model completions as retryable EMPTY_RESPONSE

A well-formed provider stream that ends with finish_reason stop and zero
content blocks previously became a successful empty assistant message: the
turn completed silently, and drivers like goal-session counted the no-op
round. Both adapters now map that degenerate completion to a finish
{kind:'error'} with the new canonical EMPTY_RESPONSE code from dsh-llm, and
dsh-llm-retry adds the code to its default retryable set, so the existing
closed-step recovery path retries it and fails loud once the budget is
exhausted.

Covered by adapter unit tests, an llm-retry default-policy test, and a new
authored keyless ACP snapshot (empty-response-retry) with a deterministic
1 ms zero-jitter retry overlay.
This commit is contained in:
Turtle
2026-07-24 18:59:26 +08:00
parent 0133e80767
commit 207aab9d8d
20 changed files with 355 additions and 16 deletions

View File

@@ -0,0 +1,41 @@
# 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).
- 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
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.
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
models:
- id: deepseek-v4-flash
- id: deepseek-v4-pro

View File

@@ -0,0 +1,30 @@
# 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.
# 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.
- id: base
name: '@cordisjs/plugin-include'
config:
path: ./cordis.yml
patches:
- 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
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.
Verify your work by running the code or tests. Keep answers brief and factual.

View File

@@ -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'
@@ -137,6 +138,14 @@ const SCENARIOS: Scenario[] = [
headerClass: 'model-switching',
},
{ 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, the ACP discarded-attempt marker, 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

View File

@@ -0,0 +1,7 @@
{
"steps": [
{ "op": "initialize" },
{ "op": "newSession" },
{ "op": "prompt", "text": "This prompt first receives an empty completion, then a retried reply." }
]
}

View File

@@ -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,"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"}}}

View File

@@ -0,0 +1,7 @@
{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"sessionCapabilities":{"list":{}},"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","modes":{"availableModes":[{"id":"default","name":"default"},{"id":"plan","name":"plan"}],"currentModeId":"default"},"configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[<objective>|clear|edit <objective>|pause|resume]"}},{"name":"plan","description":"Enter or leave plan mode","input":{"hint":"[off|message]"}}]}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"session_info_update","title":"This prompt first receives an","updatedAt":"{{updatedAt}}"}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"\n\n[Previous model attempt discarded; retrying 1/2 in 1ms: model returned a completed response with no content]\n\n"}}}}
{"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"}}