ReWiG 2aaad43fd7 fix(proxy): forward stream_options.include_usage to OpenAI-compatible upstreams ...

Claude Code's status line and the session log showed 0 tokens for every
streaming response routed through the OpenAI-compatible proxy. The root
cause was that the upstream request did not include
`stream_options: { include_usage: true }`, so the provider (LiteLLM and
other OpenAI-compatible endpoints) never emitted the final SSE chunk
that carries `usage`. The proxy's stream parser was already wired to
forward that chunk into an Anthropic-shaped `message_delta` event but
had nothing to forward.

Set `stream_options.include_usage` whenever the incoming Anthropic
request is streamed. Non-streamed requests are unaffected.

Ref: https://platform.openai.com/docs/api-reference/chat-streaming
     (search 'include_usage')

2026-06-19 21:45:47 +03:00

..

request-transformer-regressions.test.ts

test(proxy): assert tool_result image URLs stay redacted

2026-04-30 02:22:49 +09:00

request-transformer.test.ts

fix(proxy): forward stream_options.include_usage to OpenAI-compatible upstreams

2026-06-19 21:45:47 +03:00

sse-stream-transformer.test.ts

refactor(proxy): internalize sse translation and cleanup handlers

2026-04-15 01:44:01 -04:00