ci(pr-review): increase LLM timeout to 600s, retry-max-time to 1200s
Some checks failed
PR Review Automation / review (pull_request) Has been cancelled
Test / rust-fmt-check (pull_request) Has been cancelled
Test / rust-clippy (pull_request) Has been cancelled
Test / frontend-typecheck (pull_request) Has been cancelled
Test / frontend-tests (pull_request) Has been cancelled
Test / rust-tests (pull_request) Has been cancelled

qwen3.5-122b-think on a 253KB prompt was consistently hitting the 300s
--max-time wall. --retry-max-time also equalled --max-time, so retries
never fired. Now: 10 min per attempt, 2 retries, 20 min total budget.
This commit is contained in:
Shaun Arman 2026-06-20 19:49:42 -05:00
parent 4d066e47fd
commit 9b94e99e4d

View File

@ -290,8 +290,8 @@ jobs:
'{model: $model, messages: [{role: "user", content: $content}], stream: false}' \ '{model: $model, messages: [{role: "user", content: $content}], stream: false}' \
> /tmp/body.json > /tmp/body.json
echo "[$(date -u +%Y-%m-%dT%H:%M:%SZ)] PR #${PR_NUMBER} - Calling liteLLM API ($(wc -c < /tmp/body.json) bytes)..." echo "[$(date -u +%Y-%m-%dT%H:%M:%SZ)] PR #${PR_NUMBER} - Calling liteLLM API ($(wc -c < /tmp/body.json) bytes)..."
HTTP_CODE=$(curl -s --max-time 300 --connect-timeout 30 \ HTTP_CODE=$(curl -s --max-time 600 --connect-timeout 30 \
--retry 3 --retry-delay 10 --retry-connrefused --retry-max-time 300 \ --retry 2 --retry-delay 15 --retry-connrefused --retry-max-time 1200 \
-o /tmp/llm_response.json -w "%{http_code}" \ -o /tmp/llm_response.json -w "%{http_code}" \
-X POST "$LITELLM_URL/chat/completions" \ -X POST "$LITELLM_URL/chat/completions" \
-H "Authorization: Bearer $LITELLM_API_KEY" \ -H "Authorization: Bearer $LITELLM_API_KEY" \