deer-flow/backend/tests/fixtures/replay/write_read_file.ultra.json
一片一片 ea1833bd7a
fix(runtime): publish a failed artifact delivery on the run stream (#8252)
* fix(runtime): publish the delivery failure on the run stream

* docs(api): note the delivery-failure stream event

* test(runtime): cover the deferred delivery-failure frame

* docs(runtime): log the delivery fix and explain the fallback exemption

* test(e2e): present the recorded output in the replay scenario

The write/read-file fixture predates the delivery check, so the replayed
run has been ending as an error without presenting note.txt. This PR makes
that failure visible on the stream, which broke the replay golden and the
render e2e. Add the present_files step the current scenario produces and
regenerate the golden.

* docs: drop the CHANGELOG entry

CONTRIBUTING.md asks contributors to leave CHANGELOG.md and CHANGELOG_zh.md
to the maintainers at merge time, so the Unreleased ordering and the
English/Chinese pair stay in sync.
2026-11-16 18:39:06 +08:00

290 lines
9.2 KiB
JSON

{
"scenario": "write_read_file",
"mode": "ultra",
"model": "sre/gpt-5",
"prompt": "Using your own file tools directly, create the file /mnt/user-data/outputs/note.txt with exactly this content: hi from replay. Then read that same file back and reply with its exact contents. Do NOT delegate to a subagent and do NOT use the task tool — do it yourself. Do not ask any clarifying questions.",
"context": {
"is_bootstrap": false,
"mode": "ultra",
"thinking_enabled": true,
"is_plan_mode": true,
"subagent_enabled": true
},
"turns": [
{
"caller": "lead_agent",
"conversation_hash": "9c50eda6ab7e8593dabccbdeadc70a4a7bf778b2c0c3f275f1f96cf2c8ab58db",
"input_hash": "27aeb4c11bff2c3ebc182fe52a06556823c21928620a400c7f26be9733c31f3f",
"output": {
"type": "ai",
"data": {
"content": "",
"additional_kwargs": {},
"response_metadata": {
"finish_reason": "tool_calls",
"model_name": "sre/gpt-5",
"model_provider": "openai"
},
"type": "ai",
"name": null,
"id": "lc_run--019ea641-acda-7423-9a9f-79725057bc20",
"tool_calls": [
{
"name": "write_file",
"args": {
"description": "Create the requested output file with exact content",
"path": "/mnt/user-data/outputs/note.txt",
"content": "hi from replay."
},
"id": "call_FV7zhKonjx5CAa1RwIcKihpi",
"type": "tool_call"
}
],
"invalid_tool_calls": [],
"usage_metadata": {
"input_tokens": 3664,
"output_tokens": 434,
"total_tokens": 4098,
"input_token_details": {
"audio": 0,
"cache_read": 3584
},
"output_token_details": {
"audio": 0,
"reasoning": 384
}
}
}
}
},
{
"caller": "middleware:title",
"conversation_hash": "958df7bac4e74830d46d29bc19cdea85cae2fc3ebc65ca00a9a5d308bba8ad30",
"input_hash": "f1d96cb1f7cfbe6baf6b2c7b82d32f5561656b1c1492e2714c51631808b50b79",
"output": {
"type": "ai",
"data": {
"content": "Direct File Creation and Readback",
"additional_kwargs": {},
"response_metadata": {
"finish_reason": "stop",
"model_name": "sre/gpt-5",
"model_provider": "openai"
},
"type": "ai",
"name": null,
"id": "lc_run--019ea641-cf52-7793-900e-15ad4f032c0e",
"tool_calls": [],
"invalid_tool_calls": [],
"usage_metadata": {
"input_tokens": 104,
"output_tokens": 656,
"total_tokens": 760,
"input_token_details": {
"audio": 0,
"cache_read": 0
},
"output_token_details": {
"audio": 0,
"reasoning": 640
}
}
}
}
},
{
"caller": "lead_agent",
"conversation_hash": "0833d20c981009d1c2f45d1414f8c9b05b4ab16fdf56c56b942035ca085b526a",
"input_hash": "74d9087ad9421881afc9dd000218f5fb85614e80fba2c2b0861ab5fcd81c2b67",
"output": {
"type": "ai",
"data": {
"content": "",
"additional_kwargs": {},
"response_metadata": {
"finish_reason": "tool_calls",
"model_name": "sre/gpt-5",
"model_provider": "openai"
},
"type": "ai",
"name": null,
"id": "lc_run--019ea641-f523-7d60-a416-b051fba469a2",
"tool_calls": [
{
"name": "read_file",
"args": {
"description": "Verify contents to echo back exactly",
"path": "/mnt/user-data/outputs/note.txt"
},
"id": "call_YevFCnLcjWfWHaZm8wwMpEk8",
"type": "tool_call"
}
],
"invalid_tool_calls": [],
"usage_metadata": {
"input_tokens": 3719,
"output_tokens": 35,
"total_tokens": 3754,
"input_token_details": {
"audio": 0,
"cache_read": 3584
},
"output_token_details": {
"audio": 0,
"reasoning": 0
}
}
}
}
},
{
"caller": "lead_agent",
"conversation_hash": "bf8d15b438660f957ce93aee2145d37d69cceedf5d127c096466addd347f5291",
"input_hash": "3e64bf27addeac7731f5d1acf4f4a9c04b0974a538244f52c6f7cf1d5ee7c019",
"output": {
"type": "ai",
"data": {
"content": "",
"additional_kwargs": {},
"response_metadata": {
"finish_reason": "tool_calls",
"model_name": "sre/gpt-5",
"model_provider": "openai"
},
"type": "ai",
"name": null,
"id": "lc_run--present-note-file",
"tool_calls": [
{
"name": "present_files",
"args": {
"filepaths": [
"/mnt/user-data/outputs/note.txt"
]
},
"id": "call_PresentNoteFile",
"type": "tool_call"
}
],
"invalid_tool_calls": [],
"usage_metadata": {
"input_tokens": 3719,
"output_tokens": 35,
"total_tokens": 3754,
"input_token_details": {
"audio": 0,
"cache_read": 3584
},
"output_token_details": {
"audio": 0,
"reasoning": 0
}
}
}
}
},
{
"caller": "lead_agent",
"conversation_hash": "ee08f3a198eb8a120d07c755ccfa1918bb62d27aa930cd646d40c1389cc0122d",
"input_hash": "7c7e912bd806ef2c2de0217596096523f005a047c0409a5bbae830f4701adae9",
"output": {
"type": "ai",
"data": {
"content": "hi from replay.",
"additional_kwargs": {},
"response_metadata": {
"finish_reason": "stop",
"model_name": "sre/gpt-5",
"model_provider": "openai"
},
"type": "ai",
"name": null,
"id": "lc_run--019ea641-ff38-7751-9c2b-cc648811883b",
"tool_calls": [],
"invalid_tool_calls": [],
"usage_metadata": {
"input_tokens": 3768,
"output_tokens": 8,
"total_tokens": 3776,
"input_token_details": {
"audio": 0,
"cache_read": 3584
},
"output_token_details": {
"audio": 0,
"reasoning": 0
}
}
}
}
},
{
"caller": "suggest_agent",
"conversation_hash": "036fcf61f733a11153586db4fc8c39c412c90ac99d5043c22e812c90572176bf",
"input_hash": "d8b5968661b908283a8c3aadae3f4529ba3a5b0098849b0dde330d5b6ce7941a",
"output": {
"type": "ai",
"data": {
"content": "[\n \"Can you show the file size and last modified time of /mnt/user-data/outputs/note.txt?\",\n \"List the contents of /mnt/user-data/outputs/ to confirm the file exists.\",\n \"Append 'second line' to /mnt/user-data/outputs/note.txt and print its new contents.\"\n]",
"additional_kwargs": {
"refusal": null
},
"response_metadata": {
"token_usage": {
"completion_tokens": 909,
"prompt_tokens": 224,
"total_tokens": 1133,
"completion_tokens_details": {
"accepted_prediction_tokens": 0,
"audio_tokens": 0,
"reasoning_tokens": 832,
"rejected_prediction_tokens": 0
},
"prompt_tokens_details": {
"audio_tokens": 0,
"cached_tokens": 0
},
"latency_checkpoint": {
"engine_tbt_ms": 12,
"engine_ttft_ms": 324,
"engine_ttlt_ms": 10965,
"pre_inference_ms": 153,
"service_tbt_ms": 12,
"service_ttft_ms": 849,
"service_ttlt_ms": 11491,
"total_duration_ms": 11351,
"user_visible_ttft_ms": 696
}
},
"model_provider": "openai",
"model_name": "sre/gpt-5",
"system_fingerprint": null,
"id": "chatcmpl-DoPFALdwiyEDYOIN7wFYhqBrr6eTA",
"service_tier": "default",
"finish_reason": "stop",
"logprobs": null
},
"type": "ai",
"name": null,
"id": "lc_run--019ea642-0eac-78f1-a506-931e343184f1-0",
"tool_calls": [],
"invalid_tool_calls": [],
"usage_metadata": {
"input_tokens": 224,
"output_tokens": 909,
"total_tokens": 1133,
"input_token_details": {
"audio": 0,
"cache_read": 0
},
"output_token_details": {
"audio": 0,
"reasoning": 832
}
}
}
}
}
]
}