Spaces:
Running
Running
Commit History
-
Make agent turns outcome-driven: soft-fail after signal, auto-cycle, resume-first.
Stop hard-failing the turn when discovery already produced results, humanize batch/infra errors correctly, auto-broaden on discovered>0/scored=0, and route colloquial continue to the active SearchRun. Co-authored-by: Cursor <cursoragent@cursor.com>de1f194 -
Add lab observability for Hirebase search failures.
Surface upstream HTTP detail in agent run logs and debug traces, add a lab Hirebase probe endpoint, and emit structured hirebase.search logs on failed API calls. Co-authored-by: Cursor <cursoragent@cursor.com>308afe2
-
Enforce 24h Hirebase recency, relax over-filtered queries, surface raw errors.
Co-authored-by: Cursor <cursoragent@cursor.com>c06d3db
-
Add agent observability (Redis run logs, lab debugger) and copy session export
Persist agent runs to Redis with optional verbose LLM traces when LAB_LOG_INFERENCE is enabled. Instrument runAgentConversation with completion steps and tool timeline; expose X-Agent-Run-Id on chat responses. Add lab GET /api/lab/agent-runs and AgentRunsDebugger UI. Lab admins get Copy debug trace in AgentChat; all users keep markdown Copy session export. Co-authored-by: Cursor <cursoragent@cursor.com>888d34f