open-swe/docs/upstream-sync
amoussa1229 3a92a42f57 feat: port model-fallback resilience from upstream (#1694, #1695)
- Add httpx.TransportError to the transient-exception set so
  incomplete chunked reads on streamed responses trigger a
  fallback instead of cancelling the run (#1694 / c9f6dd86).
- Rewrite fallback to alternate primary/fallback with exponential
  backoff instead of a single failover, so the agent survives
  multi-minute gateway outages spanning both providers (#1695 /
  c9a9a7cd).
- Default backoff schedule (0, 5, 15, 30, 45) reaches past the
  gateway's ~30s recovery window; jittered ±25%.
- On exhaustion, surface a terminal AIMessage explaining the
  outage instead of crashing — progress is checkpointed so the
  user can retrigger to continue.
- Preserve fork conventions: Bedrock ClientError retryability
  check, sync wrap_model_call (using time.sleep instead of
  asyncio.sleep), and existing access-error surfacing for
  Anthropic, OpenAI, and Bedrock (botocore) provider errors.
- Update triage ledger (c9f6dd86, c9a9a7cd → landed) and
  re-render triage.md.

Refs: #139
2026-07-09 19:03:25 +00:00
..
cherry-pick-hook-plan.md feat(infra): upstream-sync triage ledger, cherry-pick hooks, and git cp (#118) 2026-07-03 11:46:00 -04:00
cherry-pick-runbook.md chore: cherry-pick clean upstream fixes + cherry-pick runbook (#117) 2026-07-03 11:48:40 -04:00
triage.jsonl feat: port model-fallback resilience from upstream (#1694, #1695) 2026-07-09 19:03:25 +00:00
triage.md feat: port model-fallback resilience from upstream (#1694, #1695) 2026-07-09 19:03:25 +00:00