fix(gateway): read context_length from custom_providers in session info header#19708
Merged
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Salvage of #16579 by @JanCong onto current main.
Summary
_format_session_info()ingateway/run.pyonly readcontext_lengthfrom top-levelmodel.context_lengthin config.yaml. When users setcontext_lengthunder acustom_providersentry (the place the provider actually lives), the session-info header reported no context length and downstream bookkeeping fell back to defaults. Match the current model againstcustom_providersentries and use theircontext_lengthas a secondary source.Conflict resolution during salvage
Main has since added a
custom_provs = get_compatible_custom_providers(data)hoist for related callsites. Preserved that alongside the PR'sdatainitialization so both the session-info header (this PR) and the related custom-provider usage lines continue to work.Changes
_format_session_inforeads context_length from custom_providers when model.context_length is unset (+36/-0)Validation
Manual review; diff is surgical and scoped to the single function.
Original PR: #16579