Repository navigation
fix: use a conservative output-token fallback for unknown models (WI-1796) - #426
Merged
Merged
Conversation
… (WI-1796) The unknown-model output fallback was raised from 4096 to 65536 in WI-1795 to avoid truncating reasoning models, but a model that supports fewer output tokens rejects the request outright — worse than truncating an unusually long answer. Clamping the fallback to the context window did not establish a valid limit either. Restore a conservative fallback so an unknown model is never sent a cap larger than any catalogued model advertises. An operator who knows the model supports more raises it per connection via provider_config.max_output_tokens.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The unknown-model output fallback was raised from 4096 to 65536 in WI-1795 to avoid truncating reasoning models. But a model that supports fewer output tokens rejects the request outright — worse than truncating an unusually long answer — and clamping the fallback to the context window did not establish a valid limit.
Change
Restore a conservative fallback so an unknown model is never sent a cap larger than any catalogued model advertises. An operator who knows the model supports more raises it per connection via
provider_config.max_output_tokens.Tests
Windshiftapp/core-tests-internal#27 — the fallback must not exceed the smallest catalog limit, and a context larger than the fallback keeps the fallback.