xinyin025/LangBot
1
0
Fork 0
mirror of https://github.com/langbot-app/LangBot.git synced 2026-06-12 08:46:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

refactor(provider): simplify LiteLLM requester usage handling

Browse Source 
- Remove unused Anthropic-specific tool schema generation
  - Share completion argument construction between normal and streaming calls
  - Use LiteLLM/OpenAI native usage fields for monitoring
  - Collect stream token usage from LiteLLM stream_options
  - Update LiteLLM requester tests for unified usage fields
This commit is contained in:
huanghuoguoguo
2026-04-25 09:22:37 +08:00
parent 31ad85517b
commit 7ea1ce2fd3
5 changed files with 59 additions and 102 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
src/langbot/pkg/provider/modelmgr/requester.py
View File

@@ -67,8 +67,8 @@ class RuntimeProvider:
if isinstance(result, tuple):
msg, usage_info = result
if usage_info:
input_tokens = usage_info.get('input_tokens', 0)
output_tokens = usage_info.get('output_tokens', 0)
input_tokens = usage_info.get('prompt_tokens', 0)
output_tokens = usage_info.get('completion_tokens', 0)
return msg
else:
return result
@@ -128,7 +128,6 @@ class RuntimeProvider:
start_time = time.time()
status = 'success'
error_message = None
# Note: Stream doesn't easily provide token counts, set to 0
input_tokens = 0
output_tokens = 0
@@ -143,6 +142,15 @@ class RuntimeProvider:
remove_think=remove_think,
):
yield chunk
# Extract usage from stream if available (stored by LiteLLM requester)
if query:
if query.variables is None:
query.variables = {}
if '_stream_usage' in query.variables:
usage_info = query.variables['_stream_usage']
input_tokens = usage_info.get('prompt_tokens', 0)
output_tokens = usage_info.get('completion_tokens', 0)
del query.variables['_stream_usage']
except Exception as e:
status = 'error'
error_message = str(e)