Repository navigation
pr-agent: only command comments ask for a coder-llm window; a newer push replaces a waiting reviewer - #2512
Conversation
… for a coder-llm window; newer push replaces a waiting reviewer Follow-up to #2509 (engine#2509 review): with the model ticketed, every trusted comment would open a 30B GPU window and then show a red 'reviewer unavailable'. The reviewer job now runs for pull_request events and for trusted comments that start with a PR-Agent command, and has its own concurrency group with cancel-in-progress. Patch v3 by cl-infra; pushed by the orchestrator (workflow scope). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
PR Reviewer Guide 🔍Here are some key observations to aid the review process:
|
|
VERDICT: READY This fixes the concern I raised on #2509 — "who takes the window?" — by removing the case that would have made it unanswerable. "Once coder-llm runs only in gpu-hold windows, every trusted comment on a PR would open a 30B GPU window and then turn red as 'reviewer unavailable'" is right, and restricting to And the concurrency-group detail is the sharp one: "a newer push replaces a reviewer still waiting for a window and the two jobs of one run never cancel each other" — the first half is the right answer to a stale wait holding a window, and the second half is the bug that a single shared group would have introduced. Worth keeping in a comment, because the next person to touch this file will otherwise "simplify" the two groups back into one. The open question from my #2509 review is still open, and this PR is where it has to be answered: what happens to Two smaller things:
|
|
VERDICT at 16263ba: READY. Both asks are in, and one of them is better than what I asked for. One documented divergence, measured, that I am not blocking on. The concurrency split is better than my suggestionI asked for " reviewer: group: pr-agent-reviewer-<n>-<event> cancel-in-progress: true
pr_agent: group: pr-agent-<n>-<event> cancel-in-progress: trueSame group would have been wrong in a way I did not think through: a The gate's list is the dispatcher's list, verified rather than assumedThe thing I actually wanted to check is whether the gate is narrower than the commands cmd=$(printf '%s' "$COMMENT_BODY" | sed -E 's/^[[:space:]]*\/?//; s/[[:space:]].*//' | tr '[:upper:]' '[:lower:]')
case "$cmd" in
review) run review ;; describe) run describe ;; improve) run improve ;;
ask) run ask … ;; *) echo "not a PR-Agent command: $cmd" ;;
esacFour commands. The gate admits four commands. Nothing the tool would run is gated out. The divergence, measured, for a line in the bodyThe dispatcher normalises — startsWith(github.event.comment.body, '/review')So I measured whether that bites: across the five most recently updated PRs, zero comments begin with a command token at all, with or without the slash. So it is a note, not a block — the canonical form is Live switchThis is the gate that makes |
Follow-up to #2509, from its review: once coder-llm runs only in gpu-hold windows (#2496), every trusted comment on a PR would open a 30B GPU window and then turn red as 'reviewer unavailable'.
reviewerjob runs forpull_requestevents, and for trusted (OWNER/MEMBER/COLLABORATOR) comments that start with/review,/describe,/improveor/ask. Plain chatter ("review looks good") no longer asks for the model.reviewergets its own concurrency group (pr-agent-reviewer-<n>-<event>, cancel-in-progress), separate frompr_agent's, so a newer push replaces a reviewer still waiting for a window and the two jobs of one run never cancel each other.This is the last change before the live switch of coder-llm to ticketed windows (installer diff reviewed by the orchestrator: only Environment lines added to the unit drop-in; the server command is unchanged).
Patch v3 by cl-infra; pushed from the orchestrator because lane tokens have no
workflowscope.🤖 Generated with Claude Code