xpltdco/chrysopedia
2
0
Fork 0
Code Issues 2 Pull requests Projects Releases Packages Wiki Activity Actions

feat: Log LLM response token usage (prompt/completion/total, content_len, finish_reason)

Browse source
This commit is contained in:
jlightner 2026-03-30 06:15:24 +00:00
parent 17347da87e
commit 0b0ca598b4
1 changed files with 14 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
backend/pipeline/llm_client.py
View file

@ -140,6 +140,13 @@ class LLMClient:
**kwargs,
)
raw = response.choices[0].message.content or ""
usage = getattr(response, "usage", None)
if usage:
logger.info(
"LLM response: prompt_tokens=%s, completion_tokens=%s, total=%s, content_len=%d, finish=%s",
usage.prompt_tokens, usage.completion_tokens, usage.total_tokens,
len(raw), response.choices[0].finish_reason,
)
if modality == "thinking":
raw = strip_think_tags(raw)
return raw
@ -161,6 +168,13 @@ class LLMClient:
**kwargs,
)
raw = response.choices[0].message.content or ""
usage = getattr(response, "usage", None)
if usage:
logger.info(
"LLM response (fallback): prompt_tokens=%s, completion_tokens=%s, total=%s, content_len=%d, finish=%s",
usage.prompt_tokens, usage.completion_tokens, usage.total_tokens,
len(raw), response.choices[0].finish_reason,
)
if modality == "thinking":
raw = strip_think_tags(raw)
return raw