OmniRoute

mirror of https://github.com/diegosouzapw/OmniRoute.git synced 2026-09-18 21:02:50 +03:00

Files

Vadim Zhyvylo 50a6f7e325 fix(translator): keep system content parts as Responses instructions (#12207 )

The leading system message was read as `typeof content === "string" ?
content : ""`, so a Chat-Completions content-part array — valid for
`system`, and what every prompt-caching client sends — collapsed the
whole system prompt into an empty `instructions`. Upstream accepted the
request and reported a normal prompt_tokens count, so the model answered
with no instructions at all and nothing in the response said so.

Mid-conversation system turns already handled the array shape (#7056);
only the first one did not. Reuses buildResponsesTextParts() and joins
the text parts, since `instructions` is a string rather than a part array.

Co-authored-by: Vadim Zhyvylo <zhyvylo@involve.software>

2026-09-01 00:46:46 -03:00

helpers

fix(sse): preserve coherent markdown token boundaries across stream translation chunks (#11606 ) (#11851 )

2026-08-28 12:22:09 -03:00

image

fix(types): cast extracted usage to Record<string,number> in stream.ts to resolve TS property errors

2026-03-23 09:21:03 -03:00

request

fix(translator): keep system content parts as Responses instructions (#12207 )

2026-09-01 00:46:46 -03:00

response

fix(sse): defer OpenAI-to-Claude finish emission until real usage arrives (#11915 follow-up on #11883 ) (#11933 )