fix(#2180 P0): VLM/LLM timeout 调大,适配方舟视觉API 24-38s响应 #2180

Merged
xiaoxia merged 2 commits from fix/vlm-timeout-tune into develop 2026-10-04 18:36:02 +08:00

2 Commits

Author SHA1 Message Date
xiaoxia 42dd5fabc6 fix(#2180): 全局 max_retries 2→1,避免重试叠加到351s
CI/CD Pipeline / Check push changed paths (pull_request) Has been skipped
CI/CD Pipeline / Dedup Check - skip PR tests when covered by push pipeline (pull_request) Successful in 1s
CI/CD Pipeline / Check if frontend-only change (pull_request) Successful in 2s
CI/CD Pipeline / Build Staging API Image (pull_request) Has been skipped
CI/CD Pipeline / Build Staging Web Image (pull_request) Has been skipped
CI/CD Pipeline / Build Staging Worker Image (pull_request) Has been skipped
CI/CD Pipeline / Frontend Lint (pull_request) Has been skipped
CI/CD Pipeline / Frontend Unit Tests (pull_request) Has been skipped
CI/CD Pipeline / PR Build Web Image (pull_request) Has been skipped
CI/CD Pipeline / Retag skipped Staging API Image (pull_request) Has been skipped
CI/CD Pipeline / Retag skipped Staging Web Image (pull_request) Has been skipped
CI/CD Pipeline / Retag skipped Staging Worker Image (pull_request) Has been skipped
CI/CD Pipeline / Deploy Staging (Watchtower auto-deploy) (pull_request) Has been skipped
CI/CD Pipeline / Staging E2E Tests (pull_request) Has been skipped
CI/CD Pipeline / Staging API Integration Tests (pull_request) Has been skipped
CI/CD Pipeline / ACR Image Cleanup (pull_request) Has been skipped
Preview Deploy / Deploy Preview Environment (pull_request) Successful in 2m2s
Preview Cleanup / Cleanup Preview Environment (pull_request) Successful in 54s
ACR Cleanup / ACR Image Cleanup (pull_request_target) Successful in 1m6s
CI/CD Pipeline / PR Build API Image (pull_request) Successful in 4m14s
CI/CD Pipeline / PR Build Worker Image (pull_request) Successful in 4m19s
CI/CD Pipeline / Unit Tests (pull_request) Failing after 4m43s
AI Code Review / AI Code Review (pull_request) Successful in 5m5s
CI/CD Pipeline / Integration Tests (pull_request) Successful in 5m10s
CI/CD Pipeline / Validate - Style (pull_request) Successful in 5m48s
PR Automation / Auto Approve on CI Green (pull_request) Successful in 8m22s
CI/CD Pipeline / Validate - Python (mypy + alembic) (pull_request) Successful in 8m23s
PR Automation / Auto Merge on CI Green + Approved (pull_request) Successful in 1m48s
CI/CD Pipeline / Validate - Security (pull_request) Successful in 11m52s
CI/CD Pipeline / Build Production API Image (pull_request) Has been skipped
CI/CD Pipeline / Build Production Web Image (pull_request) Has been skipped
CI/CD Pipeline / Build Production Worker Image (pull_request) Has been skipped
CI/CD Pipeline / Deploy Production (pull_request) Has been skipped
CI/CD Pipeline / Canary Release to Production (pull_request) Has been skipped
CI/CD Pipeline / CI Gate (pull_request) Failing after 2s
CI/CD Pipeline / Production Browser E2E (pull_request) Has been skipped
原配置max_retries=2(即3次尝试),lite失败→3次超时→pro降级→3次超时,
VLM最坏46.6+76.7=123s,文案三级重试最坏351s。
timeout调大到45/60s后,方舟API正常情况下1次调用就能在24-38s内返回,
max_retries=1(即2次尝试)足够防偶发网络抖动。
最坏情况VLM总耗时:45+45+60+60=210s,比351s改善40%。
2026-10-04 18:34:11 +08:00
xiaoxia c7aed2c152 fix(#2180 P0): VLM/LLM timeout 调大,适配方舟视觉API 24-38s 响应
CI/CD Pipeline / Check push changed paths (pull_request) Has been skipped
CI/CD Pipeline / Dedup Check - skip PR tests when covered by push pipeline (pull_request) Successful in 2s
CI/CD Pipeline / Check if frontend-only change (pull_request) Successful in 6s
CI/CD Pipeline / Build Staging API Image (pull_request) Has been skipped
CI/CD Pipeline / Build Staging Web Image (pull_request) Has been skipped
CI/CD Pipeline / Build Staging Worker Image (pull_request) Has been skipped
Preview Deploy / Deploy Preview Environment (pull_request) Successful in 1m39s
PR Automation / Auto Approve on CI Green (pull_request) Successful in 2m52s
CI/CD Pipeline / Frontend Lint (pull_request) Has been skipped
CI/CD Pipeline / Frontend Unit Tests (pull_request) Has been skipped
CI/CD Pipeline / PR Build Web Image (pull_request) Has been skipped
CI/CD Pipeline / PR Build API Image (pull_request) Successful in 25s
CI/CD Pipeline / Retag skipped Staging API Image (pull_request) Has been skipped
CI/CD Pipeline / Retag skipped Staging Web Image (pull_request) Has been skipped
CI/CD Pipeline / Retag skipped Staging Worker Image (pull_request) Has been skipped
CI/CD Pipeline / Deploy Staging (Watchtower auto-deploy) (pull_request) Has been skipped
CI/CD Pipeline / Staging E2E Tests (pull_request) Has been skipped
CI/CD Pipeline / Staging API Integration Tests (pull_request) Has been skipped
CI/CD Pipeline / ACR Image Cleanup (pull_request) Has been skipped
CI/CD Pipeline / Validate - Style (pull_request) Successful in 4m53s
CI/CD Pipeline / Integration Tests (pull_request) Successful in 3m31s
CI/CD Pipeline / Unit Tests (pull_request) Failing after 3m33s
CI/CD Pipeline / Validate - Python (mypy + alembic) (pull_request) Successful in 4m28s
AI Code Review / AI Code Review (pull_request) Successful in 6m33s
CI/CD Pipeline / PR Build Worker Image (pull_request) Successful in 4m12s
CI/CD Pipeline / Build Production API Image (pull_request) Has been cancelled
CI/CD Pipeline / Build Production Web Image (pull_request) Has been cancelled
CI/CD Pipeline / Build Production Worker Image (pull_request) Has been cancelled
CI/CD Pipeline / Deploy Production (pull_request) Has been cancelled
CI/CD Pipeline / Production Browser E2E (pull_request) Has been cancelled
CI/CD Pipeline / Canary Release to Production (pull_request) Has been cancelled
CI/CD Pipeline / CI Gate (pull_request) Has been cancelled
CI/CD Pipeline / Validate - Security (pull_request) Has been cancelled
PR Automation / Auto Merge on CI Green + Approved (pull_request) Has been cancelled
- VLM lite timeout: 15s → 45s(方舟VLM实测服务端处理24-38s,原15s必超时3次重试全挂)
- VLM pro fallback timeout: 25s → 60s
- 意图解析 chat timeout: 25s → 45s
- 文案fast-first/fast-retry timeout: 25s → 45s
- 文案pro-fallback timeout: 40s → 60s
- 文案审核timeout: 20s → 30s
- doubao_timeout默认: 30s → 45s

根因:方舟VLM视觉API从staging服务器实测响应24-38s(x-envoy-upstream-service-time:23357ms),
原timeout=15s每次都被截断,3次重试全超时→lite降级pro又3次超时→总123s。
文案三级重试同理叠加到351s。调大timeout后单次调用应能在45s内返回。
2026-10-04 18:25:49 +08:00