feat(local): configurable request timeout (default 180s)#303
Open
julio4 wants to merge 1 commit into
Open
Conversation
Local calls used a fixed 60s URLSession timeout. Because requests are non-streaming, that timer is effectively an idle timeout that must cover the whole generation, which is too tight on cold load / long prompts and causes spurious "The request timed out." failures. Make it configurable via a new llmLocalRequestTimeout setting, defaulting to 180s.
julio4
changed the title
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Local calls use hardcoded 60s
URLRequest.timeoutInterval. Because requests are non-streaming, that timer behaves as an idle timeout that must cover the model's entire generation with no keep-alive bytes to reset it.60s can easily be reached on slower hardware especially on cold load of model, causing failures that become "Processing failed" cards.
Changes
Makes the timeout configurable via a new
llmLocalRequestTimeoutsetting with a more generous default of 180s.OllamaProvider.requestTimeout, readsllmLocalRequestTimeout, default180.OllamaProvider+Networking.callChatAPIuses it instead of the hardcoded60.0.Risk / scope