[Fix] Ollama tasks condense before their configured context limit - #1174
Open
zoomote[bot] wants to merge 1 commit into
Open
[Fix] Ollama tasks condense before their configured context limit#1174zoomote[bot] wants to merge 1 commit into
zoomote[bot] wants to merge 1 commit into
Conversation
Codecov Report✅ All modified and coverable lines are covered by tests. 📢 Thoughts on this report? Let us know! |
navedmerchant
marked this pull request as ready for review
August 6, 2026 06:07
navedmerchant
requested review from
JamesRobert20,
edelauna,
hannesrudolph,
navedmerchant and
taltas
as code owners
August 6, 2026 06:07
github-actions
Bot
added
the
awaiting-review
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What changed
Native Ollama now fetches model metadata before task context management reads the model limits. The fetch is single-flight, avoids repeat requests once metadata is populated, and can recover after a failed request.
Focused regression coverage verifies that a detected 1M context window replaces the 128k fallback before a model request, while preserving duplicate suppression and retry behavior.
Why this change was made
After VS Code restarted or rebuilt the API handler, existing Ollama tasks could condense around 125k because context management ran before native Ollama fetched
/api/showmetadata.Closes #1151.
Impact
Ollama tasks now use the model's detected context window for condensing decisions from the start of a resumed task, avoiding premature context loss for large-context models.
Related PRs