Repository navigation
fix(llm): pass the configured max tokens to Ollama models as num_predict - #711
Open
pcbeingused333 wants to merge 1 commit into
Open
pcbeingused333 wants to merge 1 commit into
pcbeingused333 wants to merge 1 commit into
Conversation
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
get_ollama_responsecopiesmax_tokensandmax_completion_tokensinto the Ollamaoptionsdict under those names. Ollama only readsnum_predictfor the output limit, so the limit a caller passes is ignored and the model generates until it stops by itself, with the matching cost and latency.Both keys are now sent as
options["num_predict"]instead (max_completion_tokenswins if both are given, and aNonevalue is skipped). The other pass-through options (temperature,top_p,top_k, …) are unchanged.tests/test_ollama_num_predict.pyreplacesollama.Clientwith a fake that records theoptionsof thechatcall: each key arrives asnum_predictand is not forwarded under its own name, other options are untouched, andNoneadds nothing. The two translation cases fail onmain(nonum_predict) and pass with this change. It was not run against a live Ollama server, and the existing live tests intests/test_response.pywere not run.This change was made with Claude Code.
🤖 Generated with Claude Code