steve 67c3ebe067 feat(ollama): add automatic retry with exponential backoff for transient HTTP errors ...

Ollama Cloud returns HTTP 503 when the model is temporarily overloaded,
429 on rate limit, and 502 on upstream failures. These are transient
conditions that resolve on retry. Previously they bubbled up as hard
errors, forcing callers to implement their own retry logic.

The retry is implemented at the HTTP transport level in doChatRequest,
so both Complete and Stream benefit transparently. Strategy: up to 3
retries with exponential backoff (1s, 2s, 4s), Retry-After header
respected for 429, context cancellation checked between retries.
Non-transient errors (400, 401, 403, 404, 500) are never retried.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

2026-05-25 11:58:25 -04:00

..

native_test.go

feat(ollama): add automatic retry with exponential backoff for transient HTTP errors

2026-05-25 11:58:25 -04:00

native.go

feat(ollama): add automatic retry with exponential backoff for transient HTTP errors

2026-05-25 11:58:25 -04:00

ollama_test.go

refactor(v2/ollama): drop openaicompat shim, use native provider

2026-05-01 18:29:59 +00:00

ollama.go

refactor(v2/ollama): drop openaicompat shim, use native provider

2026-05-01 18:29:59 +00:00