GitNexus/.github
Gergo Magyar bb09ce28e0 fix(eval): stop discarding completed benchmark sessions as unverifiable
The evolution loop has not been able to promote anything since it went
online. Run 29907431284 (the last green run) reached the gate and threw
away 5 of its 18 runs, and the gate requires zero excluded runs in both
paired arms — so the generation could never produce a verdict on merit.

Two causes, both in the session layer:

1. Claude Code drains background-task bookkeeping after the final result
   event (`background_tasks_changed`, `task_updated`, `task_notification`,
   all `type: "system"`). The parent-stream check required the result to
   be the literal last event, so three sessions that had exited 0 with a
   complete result and usage payload were recorded as session errors.
   Trailing `system` events carry no tool_use/tool_result/usage payload
   and cannot forge skill or cost evidence; anything else after the
   result still fails closed.

2. The 3600s per-session ceiling killed two `workflow` incumbent runs on
   inv-bug-pdg-note mid-verification. Successful `workflow` rows in the
   same run finished in ~1600-2600s across both sessions, so the ceiling
   moves to 5400s and now lives in one shared constant instead of two
   argparse defaults that could drift apart.

Also marks the activation checklist against reality: the secrets, the
Environment, the runner, and the validation dispatch are all in place;
the repository variable GITNEXUS_EVOLUTION_ENABLED is the one remaining
gap, and until it is set the Saturday cron skips the job in seconds while
the EventBridge schedule still starts the runner for the day.
2026-08-01 16:45:48 +00:00
..
actions ci: update setup composites to setup-node v6 (#2451) 2026-07-14 17:11:26 +01:00
claude-canary-runtime ci: move Node pins to the 22.18 floor 2026-07-21 10:09:34 +00:00
gitnexus-review-runtime ci: move Node pins to the 22.18 floor 2026-07-21 10:09:34 +00:00
ISSUE_TEMPLATE docs: agent development framework, GitHub templates, eval refactor (#479) 2026-03-25 06:48:41 +00:00
prompts feat(review): add PR reviewer swarm agents (#1851) 2026-05-29 18:24:16 +01:00
scripts fix(ci): stop the placeholder review, verify citations, repair once (#2733) 2026-07-28 18:51:01 +01:00
workflows fix(eval): stop discarding completed benchmark sessions as unverifiable 2026-08-01 16:45:48 +00:00
actionlint.yaml fix(eval): self-hosted skill-evolution runner + sandbox Python 3 trust fix (#2600) 2026-07-21 14:40:20 +01:00
CODEOWNERS Update code owners in CODEOWNERS file 2026-07-02 08:05:15 +01:00
dependabot.yml chore(deps): bump github/codeql-action/analyze from 4.36.2 to 4.37.0 (#2506) 2026-07-17 11:40:51 +01:00
FUNDING.yml Fix duplicate GitHub funding entries 2026-07-02 08:03:31 +01:00
PULL_REQUEST_TEMPLATE.md docs: agent development framework, GitHub templates, eval refactor (#479) 2026-03-25 06:48:41 +00:00
release-drafter.yml ci: standardize workflow concurrency and automate release-note labeling (#837) 2026-04-15 13:24:53 +01:00
release.yml feat: configure prettier with pre-commit hook (#563) 2026-03-28 14:58:04 +00:00
vendored-grammars.json fix(lang-kotlin): support fun interface extraction via tree-sitter-kotlin re-vendor (#2271) 2026-06-23 10:01:28 +01:00
zizmor.yml fix(lang-kotlin): support fun interface extraction via tree-sitter-kotlin re-vendor (#2271) 2026-06-23 10:01:28 +01:00