fix: increase agent evaluation and apply timeouts for slow models - #165
Open
cwbcheng wants to merge 1 commit into
Open
fix: increase agent evaluation and apply timeouts for slow models#165cwbcheng wants to merge 1 commit into
cwbcheng wants to merge 1 commit into
Conversation
The DeepSeek-backed codex agent frequently times out on long review comments: evaluation had a 3-minute cap and apply had a 15-minute cap, which was not enough for multi-file fixes (e.g. 21 generated fixtures). When apply timed out mid-run, the uncommitted worktree edits were discarded. Raise evaluation to 7 minutes and the default apply timeout to 30 minutes (matching the code-owner fallback timeout) so complex review threads can be evaluated and fixed to completion.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Fixed timeouts in
server/agentRunner.tsare too tight for slower model providers (e.g. DeepSeek via a LiteLLM bridge), which causes two failure modes:Evaluation timeout (3 min,
180000). Evaluating whether a long review comment needs a fix routinely exceeds 3 minutes for models with slower first-token/long-context latency. An evaluation timeout fails the whole run and pushes the PR into recovery mode; recovery runs never trigger the code-owner fallback, so the run just fails.Apply timeout (15 min,
900000). Multi-file fixes (e.g. editing contract shapes plus regenerating ~20 fixtures) exceed 15 minutes. When apply is killed mid-run, the uncommitted worktree edits are discarded.Changes
server/agentRunner.ts:180000→420000(7 min) for both codex and claude evaluation.900000→1800000(30 min), matching the code-owner fallback timeout (CODE_OWNER_FALLBACK_TIMEOUT_MS).Tests
Existing timeout tests still pass (they assert the formatted timeout string from stderr, not the default).
Environment