mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-29 15:31:38 +08:00
73 lines
3.3 KiB
JSON
73 lines
3.3 KiB
JSON
|
{
|
||
|
|
"fixture": "debug-session-feishu-id-model",
|
||
|
|
"description": "Probes for the Feishu identity-model PR #8388 triage session. Anchors are the PR number, what the PR actually contained, what upstream docs confirmed, and the final decision + reasoning.",
|
||
|
|
"probes": [
|
||
|
|
{
|
||
|
|
"id": "recall-pr-number",
|
||
|
|
"type": "recall",
|
||
|
|
"question": "What is the PR number under review in this session, and what repository is it against?",
|
||
|
|
"expected_facts": ["PR #8388", "NousResearch/hermes-agent", "hermes-agent"]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"id": "recall-bug-claim",
|
||
|
|
"type": "recall",
|
||
|
|
"question": "What is the core bug the PR claims to fix? Be specific about the identifier involved.",
|
||
|
|
"expected_facts": ["open_id", "app-scoped", "not canonical", "Feishu identity model"]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"id": "recall-upstream-confirmation",
|
||
|
|
"type": "recall",
|
||
|
|
"question": "Do upstream Feishu/Lark docs confirm that open_id is app-scoped rather than a canonical cross-app identity?",
|
||
|
|
"expected_facts": ["yes", "confirmed", "open.feishu.cn", "same user has different Open IDs in different apps"]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"id": "artifact-pr-scope",
|
||
|
|
"type": "artifact",
|
||
|
|
"question": "Roughly how large is PR #8388, and which gateway subsystems does it touch beyond the Feishu adapter?",
|
||
|
|
"expected_facts": ["4647 lines", "gateway/run.py", "cron/scheduler.py", "gateway/config.py", "multi-account", "bind"]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"id": "artifact-new-tool",
|
||
|
|
"type": "artifact",
|
||
|
|
"question": "Does the PR add a new tool file? If so, what is its path?",
|
||
|
|
"expected_facts": ["tools/feishu_id_tool.py", "new file"]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"id": "decision-pr-assessment",
|
||
|
|
"type": "decision",
|
||
|
|
"question": "What is the reviewer's overall assessment of PR #8388 — approve, reject, or something more nuanced? Explain in one sentence.",
|
||
|
|
"expected_facts": [
|
||
|
|
"core claim is correct",
|
||
|
|
"scope is wrong",
|
||
|
|
"bait-and-switch",
|
||
|
|
"overbuilt",
|
||
|
|
"implement cleaner ourselves"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"id": "decision-core-claim-validity",
|
||
|
|
"type": "decision",
|
||
|
|
"question": "Setting aside the PR's size, is the underlying identity-model concern technically valid or not?",
|
||
|
|
"expected_facts": ["technically valid", "correct", "open_id is app-scoped"]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"id": "continuation-next-action",
|
||
|
|
"type": "continuation",
|
||
|
|
"question": "Based on the review outcome, what is the next action the agent has been asked to take regarding this PR?",
|
||
|
|
"expected_facts": ["close the PR", "implement ourselves", "cleaner", "less complex"]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"id": "continuation-implementation-scope",
|
||
|
|
"type": "continuation",
|
||
|
|
"question": "If implementing the Feishu fix cleanly ourselves, which specific behaviour needs to change — what should replace the current use of open_id?",
|
||
|
|
"expected_facts": ["use union_id", "or user_id", "canonical identity", "cross-app stable ID"]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"id": "continuation-sources-to-reference",
|
||
|
|
"type": "continuation",
|
||
|
|
"question": "Which upstream documentation sources were fetched during review that should be referenced when writing the clean implementation?",
|
||
|
|
"expected_facts": ["open.feishu.cn", "open.larkoffice.com", "user-identity-introduction"]
|
||
|
|
}
|
||
|
|
]
|
||
|
|
}
|