9router

mirror of https://github.com/decolua/9router.git synced 2026-05-08 12:01:28 +00:00

Files

Manuel B. 58a821d687 fix: granular reasoning_effort handling for Claude models (#791 )

- github.js: split thinking vs reasoning_effort stripping
  - thinking (Claude-native format) still stripped for all Claude on Copilot
  - reasoning_effort now passed through for Opus 4.6 and Sonnet 4.6
  - still stripped for Haiku 4.5 and Opus 4.7 (rejected upstream)
  - reasoning_effort "none" stripped for all models (not all support it)
- openai-to-claude.js: map reasoning_effort → thinking.budget_tokens
  for direct Anthropic backend (none→skip, low→4096, medium→8192,
  high→16384, xhigh→32768)

Previously reasoning_effort was stripped for ALL Claude models,
meaning Opus 4.6 via Copilot never received thinking configuration.

AI-generated commit by Claude Opus 4.6 (Anthropic)

2026-04-28 09:49:27 +07:00

config

Add codex to image providers

2026-04-25 17:01:40 +07:00

executors

fix: granular reasoning_effort handling for Claude models (#791 )

2026-04-28 09:49:27 +07:00

handlers

Add codex to image providers

2026-04-25 17:01:40 +07:00

rtk

- Cap maximum cooldown for rate limit handling in account unavailability and single-model chat flows