fix(agent): task completion safety net — stop tasks sticking at Running

Implements fixes 1-3 of plans/2026-07-11-task-completion-safety-net.md.
Confirmed live that 50/50 production sessions never reached a terminal
status because the model almost never calls complete_task, even for
trivial single-tool Q&A turns SOUL.md explicitly calls out as needing it.

- Inline safety net (agent.go): a session that never called set_goal never
  framed itself as a structured task, so its first plain-text turn-end IS
  the task ending — auto-complete it there instead of leaving status stuck
  at its creation default forever.
- Idle sweep (continue.go, new completion_nudges column): goal-bearing
  sessions that stall get one nudge, then auto-close with outcome=partial
  if the nudge goes unanswered, mirroring the pattern resumeSession already
  uses for a different stuck-session failure mode.

Fix 4 (backfill of the 50 already-stuck live sessions) is deliberately
separate — deferred until this is deployed and verified live, per the
plan's implementation order.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
2026-07-11 22:11:24 +02:00
parent e3850f6820
commit 3b9c75fa3f
6 changed files with 185 additions and 0 deletions

View File

@@ -0,0 +1,10 @@
-- 019_task_completion_nudges.up.sql
-- See plans/2026-07-11-task-completion-safety-net.md (fix 2+3): a
-- goal-bearing session (set_goal was called, so it's a real structured
-- task, not the trivial-Q&A case handled by the inline safety net) can
-- still stall without ever calling complete_task. completion_nudges tracks
-- how many times the idle sweep has already nudged a stalled session, so it
-- can tell "never nudged" (nudge it) from "nudged once already, still
-- stuck" (auto-close it) rather than nudging forever.
ALTER TABLE agent_sessions ADD COLUMN IF NOT EXISTS completion_nudges INT NOT NULL DEFAULT 0;