Ollama - Fix inline output parsing and adapter caching #942
Conversation
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
olimorris
changed the title
on_exit is called when request is cancelled and ollama models are cached
cleong14
pushed a commit
to cleong14/codecompanion.nvim
that referenced
this pull request
May 21, 2025
…is#942) Co-authored-by: Oli Morris <[email protected]>
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Outdated suggestions cannot be applied.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.
Description
The Ollama model allows
schema.models.defaultandschema.models.choicesto be functions. Without caching, during the same request, this is potentially "expensive" as the adapter class has to resolve them.The
handlers.on_exitfunction is the ideal place to reset the cache however it's only called when the request ends completely. If the user cancels the request then previously it was not called.This PR fixes the above and also streamlines Ollama's
inline_outputmethod.