mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-20 06:02:14 +03:00
83f7be8227
The native Moonshot `kimi` provider (executor "default") is a thinking-mode upstream that returns 400 "reasoning_content must be passed back" when a prior assistant turn lacks it. OpencodeExecutor already injects a placeholder for OpenCode-routed thinking models, but the direct kimi connection went through DefaultExecutor, which did not — so multi-turn kimi conversations 400'd. Wire the same injection into DefaultExecutor, scoped to `kimi` so gateway-served models that merely match the thinking-model name pattern (and may reject an extra field) are unaffected. Regression guard: tests/unit/kimi-native-reasoning-injected-1480.test.ts. Reported-by: 2220258345 (https://github.com/decolua/9router/issues/1480)