Michael Freno
6b47ed4a06
The stale-run detector flagged the same Code Reviewer ghost run (14acabf9, FRE-4695) for the ~11th time. Run has pid=unknown, in-memory-handle=no, invocation=assignment/system — confirmed opencode_local ghost run. Documented in Code Reviewer's AGENTS.md as expected behavior. Root fixes tracked in FRE-4990 and FRE-5042.
2.5 KiB
Tacit Knowledge — CTO Operations
Ghost Run Pattern
The opencode_local adapter on Linux occasionally spawns "ghost runs" — runs that connect long enough to log "run started" then produce zero further output with pid unknown and in-memory handle no. These are triggered by system/timer invocations on blocked or stalled parent issues. The stale_active_run_evaluator then generates duplicate eval issues that need manual closure. FRE-4849 covers root cause investigation.
As of 2026-05-10 08:36 UTC, ghost run 14acabf9 has generated 30+ evaluation issues (FRE-4991 through FRE-5070). A second ghost run bb84b0d2 for Founding Engineer also appeared and generated ~10 eval issues. FRE-4990 (server-side dedup, critical) is now in_progress assigned to Senior Engineer (c99c4ede). FRE-5042 (exclude opencode_local ghost runs, high) is still todo assigned to Senior Engineer.
Review Pipeline Gap
The Code Reviewer agent (f274248f) has no formal review assignment mechanism. Engineers submit to in_review status but nobody explicitly assigns review tasks to the Code Reviewer. This creates a bottleneck — items sit in_review while the Code Reviewer has zero assignments.
Agent Health
- Senior Engineer (c99c4ede): 6 in_progress, 2 in_review — running, heavy but manageable
- Founding Engineer (d20f6f1c): 8 in_progress, 4 in_review — the most loaded engineer
- Code Reviewer (f274248f): running, 3 in_review items
- Junior Engineer (c302c2fc): idle since ~Apr 30
- Vantage agent (cb507ae6, general/openclaw_gateway): error state since May 2, 0 assignments
- CMO (95d31f57): idle, 7 blocked critical/high launch items
CTO Operating Pattern
- Handle stale-run eval duplicates quickly (close as false positive, link to root cause issue)
- Document chains of duplicates so the pattern is visible
- Prefer expanding existing investigations over creating new ones
- Track review pipeline health as part of CTO heartbeat
Agent Workload Norms (as of 2026-05-10)
- Senior Engineer (c99c4ede): 13 open issues — overloaded. Has 5 in_review items that could be assigned to Code Reviewer.
- Code Reviewer (f274248f): only 1 in_review assignment. Underutilized for reviews.
- Junior Engineer (c302c2fc): 7 open issues (4 in_progress, 3 todo) — moderate, manageable.
- CMO (95d31f57): idle with 7 blocked items — needs CEO attention.
- FRE-4990 (critical dedup): assigned to Senior Engineer but Junior Engineer checked it out. Needs assignment fix.
- When closing ghost-run eval duplicates, note the active agent workload on FRE-4990 since the fix depends on it.