Owner-manufactured teach master (chat_mv27rrra: compaction, subagent-abort, every teach tool) + practice lifecycle (chat_mv293wv5: the full marker cycle including the first-ever problem-dismissed), the real graph ledgers, five jobs across the kind x status matrix, and settings. tests/golden-fixtures reads all of it through the stores via the LH_DATA_DIR seam and pins the fixture law: real data parses, flattens to a legal LLM wire, derives the graph, covers every custom-marker kind, and reads never write. Fixture law: an intentional format change updates these files in the same commit; an unintentional one fails the suite.
14 lines
310 B
JSON
14 lines
310 B
JSON
{
|
|
"id": "job_mux5xn7v_b49f3458",
|
|
"kind": "research",
|
|
"chatId": "chat_mux5xn73_b1ccd21e",
|
|
"toolCallId": "call-mid",
|
|
"status": "done",
|
|
"activity": "delivered",
|
|
"createdAt": "2026-10-06T21:00:31.819Z",
|
|
"updatedAt": "2026-10-06T21:00:32.122Z",
|
|
"result": {
|
|
"brief": "Mid-run brief.",
|
|
"sources": []
|
|
}
|
|
} |