Coder/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

test(snapshots): refresh code/both-mode fixtures against the replay model pins

Browse Source 
The re-records for the SDK-prompt change had harvested live v4-pro
headers while every replay overlay pins v4-flash, so keyless replay
diverged on provenance; keyless refresh reconciles the affected
scenarios (dispatch-start pairs preserved).
This commit is contained in:
Tianyi Cui
2026-07-26 11:51:32 +08:00
parent 5bf4d573f7
commit fc2d65fa20
9 changed files with 143 additions and 141 deletions
Download Patch File Download Diff File Expand all files Collapse all files

85
examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl
View File

@@ -21,45 +21,46 @@
{"type":"assistant/chunk","seq":19,"time":1783950000019,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":20,"time":1783957884490,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\": \"return await tools.cordis_inspect({ what: 'dynamic' })\", \"description\": \"Run the scripted inspection program\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[15,16,17,18,19],"surfaceOp":"append"}
{"type":"tool/call","seq":21,"time":1783957884490,"data":{"turn":1,"step":2,"callId":"advanced-code","name":"run_code","arguments":"{\"code\": \"return await tools.cordis_inspect({ what: 'dynamic' })\", \"description\": \"Run the scripted inspection program\"}"}}
{"type":"tool/code-dispatch","seq":22,"time":1783957884560,"data":{"parentCallId":"advanced-code","subCallId":"advanced-code:code:1","name":"cordis_inspect","arguments":{"what":"dynamic"},"isError":false,"content":[{"type":"text","text":"## dynamic\n- dyn-1: snapshot-marker [active]"}]}}
{"type":"tool/result","seq":23,"time":1783957884561,"data":{"turn":1,"step":2,"callId":"advanced-code","content":[{"type":"text","text":"## dynamic\n- dyn-1: snapshot-marker [active]"}],"isError":false},"sourceEventSeqs":[21],"surfaceOp":"append"}
{"type":"step/end","seq":24,"time":1783957884561,"data":{"turn":1,"step":2}}
{"type":"step/start","seq":25,"time":1783957884562,"data":{"turn":1,"step":3}}
{"type":"assistant/chunk","seq":26,"time":1783950000026,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":27,"time":1783950000027,"data":{"turn":1,"step":3,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-direct-child","name":"subagent","argumentsDelta":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}}}
{"type":"assistant/chunk","seq":28,"time":1783950000028,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}}}}
{"type":"assistant/chunk","seq":29,"time":1783950000029,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}
{"type":"assistant/chunk","seq":30,"time":1783950000030,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":31,"time":1783957884562,"data":{"turn":1,"step":3,"content":[{"type":"tool-call","id":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[26,27,28,29,30],"surfaceOp":"append"}
{"type":"tool/call","seq":32,"time":1783957884562,"data":{"turn":1,"step":3,"callId":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}}
{"type":"tool/result","seq":33,"time":1783957884593,"data":{"turn":1,"step":3,"callId":"advanced-direct-child","content":[{"type":"text","text":"DIRECT_CHILD_OK"}],"isError":false},"sourceEventSeqs":[32],"surfaceOp":"append"}
{"type":"step/end","seq":34,"time":1783957884593,"data":{"turn":1,"step":3}}
{"type":"step/start","seq":35,"time":1783957884594,"data":{"turn":1,"step":4}}
{"type":"assistant/chunk","seq":36,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":37,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-workflow","name":"workflow","argumentsDelta":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}}}
{"type":"assistant/chunk","seq":38,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}}}}
{"type":"assistant/chunk","seq":39,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}
{"type":"assistant/chunk","seq":40,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":41,"time":1783957884594,"data":{"turn":1,"step":4,"content":[{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[36,37,38,39,40],"surfaceOp":"append"}
{"type":"tool/call","seq":42,"time":1783957884594,"data":{"turn":1,"step":4,"callId":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}}
{"type":"tool/result","seq":43,"time":1783957884717,"data":{"turn":1,"step":4,"callId":"advanced-workflow","content":[{"type":"text","text":"workflow \"advanced-acp-snapshot\" completed (1 agent).\nReturn value:\n{\n \"reply\": \"WORKFLOW_CHILD_OK\"\n}"}],"isError":false},"sourceEventSeqs":[42],"surfaceOp":"append"}
{"type":"step/end","seq":44,"time":1783957884718,"data":{"turn":1,"step":4}}
{"type":"step/start","seq":45,"time":1783957884718,"data":{"turn":1,"step":5}}
{"type":"assistant/chunk","seq":46,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":47,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-unmount","name":"cordis_unmount","argumentsDelta":"{\"id\":\"dyn-1\"}"}}}
{"type":"assistant/chunk","seq":48,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}}}}
{"type":"assistant/chunk","seq":49,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}
{"type":"assistant/chunk","seq":50,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":51,"time":1783957884719,"data":{"turn":1,"step":5,"content":[{"type":"tool-call","id":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[46,47,48,49,50],"surfaceOp":"append"}
{"type":"tool/call","seq":52,"time":1783957884719,"data":{"turn":1,"step":5,"callId":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}}
{"type":"tool/result","seq":53,"time":1783957884719,"data":{"turn":1,"step":5,"callId":"advanced-unmount","content":[{"type":"text","text":"unmounted dyn-1 (plugin \"snapshot-marker\")"}],"isError":false},"sourceEventSeqs":[52],"surfaceOp":"append"}
{"type":"step/end","seq":54,"time":1783957884719,"data":{"turn":1,"step":5}}
{"type":"step/start","seq":55,"time":1783957884720,"data":{"turn":1,"step":6}}
{"type":"assistant/chunk","seq":56,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
{"type":"assistant/chunk","seq":57,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"text-delta","index":0,"text":"ADVANCED_ACP_OK"}}}
{"type":"assistant/chunk","seq":58,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"ADVANCED_ACP_OK"}}}}
{"type":"assistant/chunk","seq":59,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}
{"type":"assistant/chunk","seq":60,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":61,"time":1783957884720,"data":{"turn":1,"step":6,"content":[{"type":"text","text":"ADVANCED_ACP_OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[56,57,58,59,60],"surfaceOp":"append"}
{"type":"step/end","seq":62,"time":1783957884721,"data":{"turn":1,"step":6}}
{"type":"turn/end","seq":63,"time":1783957884721,"data":{"turn":1,"reason":{"kind":"completed"}}}
{"type":"tool/code-dispatch-start","seq":22,"time":1785036891166,"data":{"parentCallId":"advanced-code","subCallId":"advanced-code:code:1","name":"cordis_inspect","arguments":{"what":"dynamic"}}}
{"type":"tool/code-dispatch","seq":23,"time":1785036891167,"data":{"parentCallId":"advanced-code","subCallId":"advanced-code:code:1","name":"cordis_inspect","arguments":{"what":"dynamic"},"isError":false,"content":[{"type":"text","text":"## dynamic\n- dyn-1: snapshot-marker [active]"}]}}
{"type":"tool/result","seq":24,"time":1785036891170,"data":{"turn":1,"step":2,"callId":"advanced-code","content":[{"type":"text","text":"## dynamic\n- dyn-1: snapshot-marker [active]"}],"isError":false},"sourceEventSeqs":[21],"surfaceOp":"append"}
{"type":"step/end","seq":25,"time":1785036891171,"data":{"turn":1,"step":2}}
{"type":"step/start","seq":26,"time":1785036891175,"data":{"turn":1,"step":3}}
{"type":"assistant/chunk","seq":27,"time":1783950000027,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":28,"time":1783950000028,"data":{"turn":1,"step":3,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-direct-child","name":"subagent","argumentsDelta":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}}}
{"type":"assistant/chunk","seq":29,"time":1783950000029,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}}}}
{"type":"assistant/chunk","seq":30,"time":1783950000030,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}
{"type":"assistant/chunk","seq":31,"time":1785036891179,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":32,"time":1785036891179,"data":{"turn":1,"step":3,"content":[{"type":"tool-call","id":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[27,28,29,30,31],"surfaceOp":"append"}
{"type":"tool/call","seq":33,"time":1785036891180,"data":{"turn":1,"step":3,"callId":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}}
{"type":"tool/result","seq":34,"time":1785036891203,"data":{"turn":1,"step":3,"callId":"advanced-direct-child","content":[{"type":"text","text":"DIRECT_CHILD_OK"}],"isError":false},"sourceEventSeqs":[33],"surfaceOp":"append"}
{"type":"step/end","seq":35,"time":1785036891204,"data":{"turn":1,"step":3}}
{"type":"step/start","seq":36,"time":1785036891207,"data":{"turn":1,"step":4}}
{"type":"assistant/chunk","seq":37,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":38,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-workflow","name":"workflow","argumentsDelta":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}}}
{"type":"assistant/chunk","seq":39,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}}}}
{"type":"assistant/chunk","seq":40,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}
{"type":"assistant/chunk","seq":41,"time":1785036891211,"data":{"turn":1,"step":4,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":42,"time":1785036891211,"data":{"turn":1,"step":4,"content":[{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[37,38,39,40,41],"surfaceOp":"append"}
{"type":"tool/call","seq":43,"time":1785036891211,"data":{"turn":1,"step":4,"callId":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}}
{"type":"tool/result","seq":44,"time":1785036891785,"data":{"turn":1,"step":4,"callId":"advanced-workflow","content":[{"type":"text","text":"workflow \"advanced-acp-snapshot\" completed (1 agent).\nReturn value:\n{\n \"reply\": \"WORKFLOW_CHILD_OK\"\n}"}],"isError":false},"sourceEventSeqs":[43],"surfaceOp":"append"}
{"type":"step/end","seq":45,"time":1785036891786,"data":{"turn":1,"step":4}}
{"type":"step/start","seq":46,"time":1785036891789,"data":{"turn":1,"step":5}}
{"type":"assistant/chunk","seq":47,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":48,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-unmount","name":"cordis_unmount","argumentsDelta":"{\"id\":\"dyn-1\"}"}}}
{"type":"assistant/chunk","seq":49,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}}}}
{"type":"assistant/chunk","seq":50,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}
{"type":"assistant/chunk","seq":51,"time":1785036891795,"data":{"turn":1,"step":5,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":52,"time":1785036891796,"data":{"turn":1,"step":5,"content":[{"type":"tool-call","id":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[47,48,49,50,51],"surfaceOp":"append"}
{"type":"tool/call","seq":53,"time":1785036891796,"data":{"turn":1,"step":5,"callId":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}}
{"type":"tool/result","seq":54,"time":1785036891798,"data":{"turn":1,"step":5,"callId":"advanced-unmount","content":[{"type":"text","text":"unmounted dyn-1 (plugin \"snapshot-marker\")"}],"isError":false},"sourceEventSeqs":[53],"surfaceOp":"append"}
{"type":"step/end","seq":55,"time":1785036891799,"data":{"turn":1,"step":5}}
{"type":"step/start","seq":56,"time":1785036891801,"data":{"turn":1,"step":6}}
{"type":"assistant/chunk","seq":57,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
{"type":"assistant/chunk","seq":58,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"text-delta","index":0,"text":"ADVANCED_ACP_OK"}}}
{"type":"assistant/chunk","seq":59,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"ADVANCED_ACP_OK"}}}}
{"type":"assistant/chunk","seq":60,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}
{"type":"assistant/chunk","seq":61,"time":1785036891804,"data":{"turn":1,"step":6,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":62,"time":1785036891804,"data":{"turn":1,"step":6,"content":[{"type":"text","text":"ADVANCED_ACP_OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[57,58,59,60,61],"surfaceOp":"append"}
{"type":"step/end","seq":63,"time":1785036891806,"data":{"turn":1,"step":6}}
{"type":"turn/end","seq":64,"time":1785036891806,"data":{"turn":1,"reason":{"kind":"completed"}}}

2
examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md
View File

@@ -30,7 +30,7 @@ Pass `run_code` the body of an async TypeScript function (erasable syntax only
- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools["my-tool"](args)`. Every call resolves to the tool's typed canonical JSON value. Tool arguments must be lossless JSON.
- A FAILED tool call rejects with `ToolCallError`, whose `toolName` identifies the failed tool and whose `message` is human-readable — `try/catch` it to handle and continue.
- Calls execute sequentially, even under `Promise.all`.
- Independent read-only calls MAY overlap under `Promise.all` (safe calls run concurrently; mutating calls run alone, in submission order). Sequence dependent work with `await`.
- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.
The available tools: