Teknium 80a899a8e2 fix: enable fine-grained tool streaming for Claude/OpenRouter + retry SSE errors (#3497) ...

Root cause: Anthropic buffers entire tool call arguments and goes silent
for minutes while thinking (verified: 167s gap with zero SSE events on
direct API).  OpenRouter's upstream proxy times out after ~125s of
inactivity and drops the connection with 'Network connection lost'.

Fix: Send the x-anthropic-beta: fine-grained-tool-streaming-2025-05-14
header for Claude models on OpenRouter.  This makes Anthropic stream
tool call arguments token-by-token instead of buffering them, keeping
the connection alive through OpenRouter's proxy.

Live-tested: the exact prompt that consistently failed at ~128s now
completes successfully — 2,972 lines written, 49K tokens, 8 minutes.

Additional improvements:

1. Send explicit max_tokens for Claude through OpenRouter.  Without it,
   OpenRouter defaults to 65,536 (confirmed via echo_upstream_body) —
   only half of Opus 4.6's 128K limit.

2. Classify SSE 'Network connection lost' as retryable in the streaming
   inner retry loop.  The OpenAI SDK raises APIError from SSE error
   events, which was bypassing our transient error retry logic.

3. Actionable diagnostic guidance when stream-drop retries exhaust.

2026-03-28 08:01:37 -07:00

28 KiB

Raw Blame History

View Raw