Skip to content

fix(compression): remove hardcoded gemini-3-flash-preview as default summary model#2464

Merged
teknium1 merged 1 commit intomainfrom
hermes/hermes-40b195db
Mar 22, 2026
Merged

fix(compression): remove hardcoded gemini-3-flash-preview as default summary model#2464
teknium1 merged 1 commit intomainfrom
hermes/hermes-40b195db

Conversation

@teknium1
Copy link
Copy Markdown
Contributor

Salvage of PR #2457 by @Mibayy. Fixes #2453.

The default config hardcoded google/gemini-3-flash-preview as the compression summary model, causing unexpected OpenRouter charges for users on other providers. Now defaults to empty string, which falls through to the user's configured main model.

Users who want a dedicated cheap model can still set it explicitly in config.yaml.

…summary model

Closes #2453

The DEFAULT_CONFIG was hardcoding google/gemini-3-flash-preview as the
summary_model for context compression. This caused unexpected OpenRouter
charges for users who configured a different provider/model, because the
compression task would silently fall back to gemini via OpenRouter even
when the user's main model was on a different provider.

Fix: change summary_model default to empty string. When empty,
call_llm() resolves the model through the standard auto-detection chain
(auxiliary.compression config -> env vars -> main provider), which
correctly uses the user's configured provider and model.

Users who want a dedicated cheap model for compression can still
explicitly set compression.summary_model in their config.yaml.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

1 participant