feat: overseer rewrite — ticket closer that reduces the queue#123
Merged
feat: overseer rewrite — ticket closer that reduces the queue#123
Conversation
The overseer was running 3 sessions in a row fixing frontmatter while 58 tasks piled up. It never closed a single task. Now it's an engineer whose primary metric is: pending count BEFORE vs AFTER. overseer.md rewrite: - Primary job: REDUCE the queue (close duplicates, wontfix noise, mark done) - Can write quick code fixes for simple tasks (same PR workflow as builder) - Reports CLEAN or NEEDS MORE WORK signal for pick-role.py - Generates 0 new tasks (that's the builder's job) pick-role.py scoring changes: - OVERSEE triggers on queue DRIFT, not raw size - pending >= 80: +50 (critical), pending >= 50 AND 5+ sessions since oversee: +35 - Stale tasks >= 5: +30, new GitHub Issues synced: +25 - NEEDS MORE WORK flag: +20 (previous overseer wasn't done) - CLEAN cap: if overseer ran < 3 sessions ago AND said CLEAN, score stays at 5 - Prevents the dead loop: overseer runs, cleans, signals done, doesn't run again evolve.md Step 6o: - Queue-aware task cap: 50+ pending = create 0 new tasks, under 50 = max 3 - Prevents the builder from growing the queue faster than overseer can drain it Tests: 45 passing (6 new overseer scoring tests)
fazxes
added a commit
that referenced
this pull request
Apr 7, 2026
Closed 20 tasks with evidence: - DONE (2): #73 (AGENTS.md created), #181 (docs/prompt/ deleted) - WONTFIX-OBSOLETE (5): #78, #89, #128, #141, #157 (reference docs/prompt/ or docs/ops/ paths deleted in session #103) - WONTFIX-DUPLICATE (1): #88 (subset of #69) - WONTFIX-NEVER-PICKED (12): #66, #69, #90, #96, #112, #114, #120, #123, #132, #133, #138, #145 (low priority, 20-80+ sessions without being picked, speculative) Priority fix: #103 downgraded from urgent to normal (umbrella epic, not an actionable urgent fix).
fazxes
added a commit
that referenced
this pull request
Apr 9, 2026
…y report Tasks created from analysis of sessions #107-#122 and 7 human-filed issues: - #241 (urgent): fix worktree cleanup -- .claude/worktrees/agent-* leaking - #242 (urgent): add sessions_since_eval signal + brain eval cadence rule - #243 (normal): run nightshift against Phractal immediately (eval #17) Root causes identified: eval loop broken (14 sessions stale), worktree leak confirmed live, Phractal E2E never runs in daemon cadence.
fazxes
added a commit
that referenced
this pull request
Apr 9, 2026
fazxes
added a commit
that referenced
this pull request
Apr 9, 2026
strategy: session #123 -- 3 tasks from v2 strategy analysis
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Problem
Overseer ran 3 consecutive sessions fixing frontmatter while 58 tasks piled up. It never closed a single task. The queue grew because builder creates 1-5 tasks/session but only completes 1.
Solution
Test plan
make checkpasses