Redeliver an interrupted review comment, and close the issue on completion
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 1m16s
Adopt an already-published PR instead of publishing again
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 1m12s
Bind approvals and feedback to the revision they were about
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 1m16s
Model the orchestrator in Quint, and reproduce its counterexamples
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 1m18s
Match approvals and commands regardless of case and trailing punctuation
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 1m15s
Add the abandon command
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 1m18s
Keep Gitea threads watched across restarts and interruptions
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 1m20s
Don't assert the exact word in the LiteLLM smoke test
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 1m24s
Never leave the agent stranded in a working state
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 1m19s
Publish work the executor committed itself, and gate when there is none
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 1m15s
Handle leading mentions in Matrix messages
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 1m24s
Keep a pending question across restarts, and make the restart question answerable
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 1m18s
Use qwen3.8-27b as the example executor
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 1m22s
Benchmark the finalists on all eight tasks, and archive older results
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 1m12s
Spec: prefer one local model for all roles; record host sharing, park vision
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 1m18s
Add four harder benchmark tasks
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 1m14s
Keep runs with different tuning apart in the report, and raise max_turns to 40
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 1m11s
Render one assistant message per turn, and make the request timeout a setting
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 1m16s
Record rate-limit waits in benchmark runs, and leave them out of time
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 1m17s
Benchmark seven new RTX 4090 models, and local-fast on the 4090
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 1m16s