Propagate upstream token usage across Gemini usage metadata

This commit is contained in:
CJACK.
2026-04-07 10:16:00 +08:00
parent 96b8587c5b
commit 5bcea3d727
5 changed files with 42 additions and 5 deletions

View File

@@ -267,6 +267,7 @@ data: [DONE]
- `deepseek-reasoner` / `deepseek-reasoner-search` models emit `delta.reasoning_content`
- Text emits `delta.content`
- Last chunk includes `finish_reason` and `usage`
- Token counting prefers pass-through from upstream DeepSeek SSE (`accumulated_token_usage` / `token_usage`), and only falls back to local estimation when upstream usage is absent
#### Tool Calls
@@ -535,6 +536,7 @@ Returns SSE (`text/event-stream`), each chunk as `data: <json>`:
- regular text: incremental text chunks
- `tools` mode: buffered and emitted as `functionCall` at finalize phase
- final chunk: includes `finishReason: "STOP"` and `usageMetadata`
- Token counting prefers pass-through from upstream DeepSeek SSE (`accumulated_token_usage` / `token_usage`), and only falls back to local estimation when upstream usage is absent
---