ModelRouter

mirror of https://gitcode.com/JianFeeeee/ModelRouter.git synced 2026-09-20 00:48:00 +00:00

Files

JianFeeeee 0528941e24 fix(opencode): only send stream_options with stream:true

OpenCode Go (and other strict OpenAI-compatible upstreams) reject a
non-streaming request that carries stream_options with
"stream_options should be set along with stream". The adapter attached it
unconditionally, so every non-stream call through the opencode adapter
failed on those upstreams.

Verified against OpenCode Go: 25/25 configured models now pass a real
completion through the gateway (they previously 400'd).

Test: TestOpenCodeStreamOptionsOnlyWhenStreaming (absent when
non-streaming, include_usage present when streaming).

2026-09-11 13:13:05 +08:00

agentrouter.lua

fix(gateway): AUTO scope grants all models — restrict to routing mode only

2026-09-10 12:51:40 +08:00

anthropic.lua

fix(anthropic): count cached input in prompt_tokens instead of dropping it

2026-09-06 09:55:22 +08:00

deepseek.lua

feat: surface zero cache hits — distinguish 'missed' from 'not reported'

2026-08-25 10:04:44 +08:00

gemini.lua

fix: empty-array content becomes invalid {} on every pass-through adapter; gemini/ollama drop tool calls