Jeroen UbbinkandClaude Opus 4.8 ccee76b31e fix(upstream): source litellm context from max_input_tokens only ...

litellm's max_tokens is the completion cap (it equals max_output_tokens for
~94% of models), not the context window, so falling back to it overstated the
context as the output limit. Take context from max_input_tokens alone; a model
that reports none falls through to the id-based estimate downstream, which is
honest about being a guess rather than mislabelling the output cap.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

2026-07-05 15:39:41 +02:00

..

integration

refactor(upstream): resolve a provider's own row by primary key

2026-07-01 12:53:31 +02:00

unit

fix(upstream): source litellm context from max_input_tokens only

2026-07-05 15:39:41 +02:00

run_integration.py

dump wip stash

2025-08-06 20:31:55 -03:00