dda7a73909
Align the Anthropic endpoint's sampling surface with /v1/chat/completions. Adds the three fields as x-unsloth extensions on AnthropicMessagesRequest and threads them through all three code paths: server-side tool loop, no-tool plain, and client-side passthrough. The passthrough builder emits "repeat_penalty" (not "repetition_penalty") because that is llama-server's field name; the backend methods already apply the same rename internally. |
||
|---|---|---|
| .. | ||
| data_recipe | ||
| .gitkeep | ||
| __init__.py | ||
| auth.py | ||
| datasets.py | ||
| export.py | ||
| inference.py | ||
| models.py | ||
| training.py | ||
| training_history.py | ||