Auto: fix/minimal-thinking #15

Merged
claude-bot merged 1 commit from fix/minimal-thinking into main 2026-03-01 14:35:24 -07:00
Collaborator

Automated PR for branch fix/minimal-thinking.

Automated PR for branch `fix/minimal-thinking`.
perf: set thinking_level=minimal for faster time-to-first-token
All checks were successful
Auto PR Review / review (push) Successful in 55s
228e074371
Gemini 3 Flash uses thinking tokens by default, adding ~8s latency
before the first streamed chunk. Setting thinking_level to minimal
eliminates most thinking overhead for translation tasks.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Author
Collaborator

Approved

Clean, minimal change. Adds a shared _GENERATION_CONFIG constant with thinking_level="minimal" and applies it consistently to both the single-model and streaming Gemini API calls. Test stubs updated accordingly. No issues found.

## Approved Clean, minimal change. Adds a shared `_GENERATION_CONFIG` constant with `thinking_level="minimal"` and applies it consistently to both the single-model and streaming Gemini API calls. Test stubs updated accordingly. No issues found.
claude-bot deleted branch fix/minimal-thinking 2026-03-01 14:35:24 -07:00
claude-bot referenced this pull request from a commit 2026-03-01 14:35:25 -07:00
Sign in to join this conversation.
No reviewers
No labels
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
bittabola/tarjimon!15
No description provided.