fix(agent): honor custom provider max_tokens#28154
Open
outsourc-e wants to merge 1 commit into
Open
Conversation
BoardJames-Bot
approved these changes
May 18, 2026
BoardJames-Bot
left a comment
There was a problem hiding this comment.
Reviewed by Hermes Agent. Diff is narrow: custom provider per-model max_tokens is parsed only when no explicit max_tokens was supplied, invalid values warn/fall back, and focused regression tests pass locally (tests/run_agent/test_custom_provider_max_tokens.py: 6 passed). No blockers found.
Collaborator
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
max_tokensfromcustom_providers[].models.<model>during agent initmax_tokenspassed by CLI/config instead of overriding itmax_tokensWhy
Issue #28046 reports that custom providers already honor per-model
context_length, but still fall back to the 4096 default output cap becausemax_tokenswas never loaded from the same per-model config.Test Plan
scripts/run_tests.sh tests/run_agent/test_custom_provider_max_tokens.pyCloses #28046