Retry, backoff and default Generate timeout #48

Merged

approver_agent merged 4 commits from task/retry-backoff_1a882923-fdb4-4576-ab82-9529e9974b26 into feature/5dd6e253-cc9b-41f3-9091-bb834f7a373a-llm-provider-layer 2026-10-04 11:02:56 -04:00

Conversation 1 Commits 4 Files Changed 8

+680 -11

4 Commits

Author	SHA1	Message	Date
dev_agentandClaude Opus 5.5	f8e975e284	Do not retry an HTTP 408; lock retry cap and timeout values ... The OpenAI and Anthropic adapters now report an HTTP 408 as llm.TimeoutStatusError, which still matches llm.ErrTimeout but carries its status. Retrying no longer retries any error carrying a 4xx status, so a vendor's 408 is returned at once while a transport timeout, which has no status, is still retried. Tests: 408 (bare and wrapped) is not retried and a transport timeout is; FromSettings integration cases for an OpenAI and Anthropic 408 and an OpenAI transport timeout; the cap and default-timeout tests assert the literal 20 s and 60 s instead of the constants they lock. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-10-04 10:58:59 -04:00
dev_agentandClaude Opus 5.5	d90886ddc2	Bound whole retrying Generate call by one deadline ... Request.Timeout, or the 60-second default, now sets a single context deadline covering every attempt and wait, instead of restarting for each attempt. A shorter caller deadline still wins; attempts receive Timeout 0 so adapters do not restart the clock. A negative Timeout is left for the wrapped Provider to reject with its key redaction. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-10-04 10:53:53 -04:00
dev_agentandClaude Opus 5.5	bcdea85a2d	Wire retrying Provider into presets.FromSettings ... FromSettings now returns llm.NewRetrying around the configured adapter, so every Provider it builds retries transient Generate failures and gets the default timeout; ListModels and Verify pass through. The test recording transport now answers 400 instead of failing the round trip: the ollama adapter reports a transport failure as ErrTimeout, which is retried, so the helper would see three requests. Tests: a 429 then 200 succeeds on the second request; exhausted retries return ErrProvider after MaxRetries+1 requests with no key in any error. Maestro task: 1a882923-fdb4-4576-ab82-9529e9974b26 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-10-04 10:49:46 -04:00
dev_agentandClaude Opus 5.5	cbf24e63e1	Add retrying Provider wrapper with backoff and default timeout ... llm.NewRetrying wraps a Provider and retries ErrRateLimited, ErrTimeout and 5xx ErrProvider at most twice. A rate limit waits RetryAfter, capped at 20 s; other retries use jittered exponential backoff. ErrAuth, 4xx and other errors are never retried, and no retry is made whose wait would not end before the caller's context deadline. Generate gets a 60 s per-attempt timeout when Request.Timeout is 0. Maestro task: 1a882923-fdb4-4576-ab82-9529e9974b26 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-10-04 10:48:07 -04:00