Commit Graph

2 Commits

Author SHA1 Message Date
Dev Agent
61e26a8930 fix(observability): merge-gate on deploy, full token input, Plane Done, artifact links
1. BUG 8 (second door): merge webhook no longer fake-completes a task at the
   deploy stage; done is gated by the deployer verdict (check_deploy_status).
   Other stages keep merge->done.
2. Token accounting: parse+persist cache_creation_input_tokens (new
   idempotent agent_runs column). usage_comment / task_summary now show the
   FULL input (input + cache_read + cache_creation) with a cached breakdown.
   cost_usd untouched.
3. deploy->done success now forces the Plane issue to terminal Done state.
4. All agents (architect/developer/reviewer/tester/deployer) attach artifact
   links to their finish comment via gitea_public_url.

Tests added for each fix; pytest 244 passed / 9 failed (off-limits HMAC group).
2026-06-04 11:17:58 +03:00
Dev Agent
9a702a0216 feat(metrics): per-agent token/cost accounting
Feature 4. claude is now launched with --output-format json; the run-log trailing
result JSON is parsed (defensively, never fatal) for usage + total_cost_usd. New
idempotent ALTERs add input_tokens/output_tokens/cache_read_tokens/cost_usd to
agent_runs; the launcher monitor records usage per run, posts a per-agent finish
comment under that agent bot (e.g. Developer gotov · 45.2k in / 12.1k out · $0.21),
and the deployer posts an end-of-task summary (SUM over agent_runs GROUP BY agent)
on done. New src/usage.py holds parse/format/record/summary helpers; test_usage.py
covers parsing a real CLI JSON blob, NULL-on-garbage, recording, formatting, and the
per-task aggregate.
2026-06-03 18:18:46 +03:00