jianf 3069cfce4e fix(gateway): pass through upstream token usage in streams for all adapters ...

The prior usage-passthrough fix only covered openai/opencode; the same
empty-choices+usage drop bug remained in the 5 sibling OpenAI-compatible
adapters, and non-OpenAI providers (anthropic/gemini/ollama) never surfaced
streaming usage at all.

- deepseek/github/groq/kimicode/mistral: preserve usage on empty-choices
  chunks and attach it to normal chunks (same pattern as openai.lua)
- anthropic: emit usage from message_start (prompt) and message_delta
  (completion); gateway merges split usage additively
- gemini: read usageMetadata in the stream path
- ollama: fix non-streaming key (usage -> token_usage, matches
  UnifiedResponse json tag) and read prompt_eval_count/eval_count;
  surface counts from the done stream chunk
- gateway: mergeUsage combines usage across chunks (non-zero fields win,
  total recomputed from prompt+completion) so split usage doesn't lose
  the prompt half; single-chunk case (OpenAI) preserved exactly
- usage-only chunks: done=false (no redundant terminal stop), matching
  the Go fallback standardSSEChunk

2026-08-18 23:24:01 +08:00

..

adapters

fix(gateway): pass through upstream token usage in streams for all adapters

2026-08-18 23:24:01 +08:00

vm_test.go

test(lua): add opencode role normalization test

2026-08-16 17:51:43 +08:00

vm.go

feat: opencode zen adapter + first-run config generation, fix stats/stream bugs

2026-08-13 12:25:07 +08:00