mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-05-06 02:41:48 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 7

fix(gemini): extract usageMetadata from streaming chunks for token tracking

Browse source
This commit is contained in:
flobo3 2026-04-24 20:18:06 +03:00 • committed by Teknium
parent f6aa1965d7
commit ba8337464d
1 changed files with 15 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

16
agent/gemini_native_adapter.py
View file

@ -679,7 +679,21 @@ def translate_stream_event(event: Dict[str, Any], model: str, tool_call_indices:
finish_reason_raw = str(cand.get("finishReason") or "")
if finish_reason_raw:
mapped = "tool_calls" if tool_call_indices else _map_gemini_finish_reason(finish_reason_raw)
chunks.append(_make_stream_chunk(model=model, finish_reason=mapped))
finish_chunk = _make_stream_chunk(model=model, finish_reason=mapped)
# Attach usage from this event's usageMetadata so the streaming
# loop in run_agent.py can record token counts (mirrors the
# non-streaming path in translate_gemini_response).
usage_meta = event.get("usageMetadata") or {}
if usage_meta:
finish_chunk.usage = SimpleNamespace(
prompt_tokens=int(usage_meta.get("promptTokenCount") or 0),
completion_tokens=int(usage_meta.get("candidatesTokenCount") or 0),
total_tokens=int(usage_meta.get("totalTokenCount") or 0),
prompt_tokens_details=SimpleNamespace(
cached_tokens=int(usage_meta.get("cachedContentTokenCount") or 0),
),
)
chunks.append(finish_chunk)
return chunks