omar-nahhas 95841f9a48 fix(github): preserve reasoning_effort for non-Claude models (#713) ...

The previous blanket strip in GithubExecutor.transformRequest removed
`thinking` AND `reasoning_effort` for every GitHub-routed model to avoid
Claude-on-Copilot 400s from OpenClaw. That regressed GPT-5 family support
(gh/gpt-5-mini honors reasoning_effort: low/medium/high).

Make supportsThinking(model) model-aware — return false only for Claude
models, so the strip fires only where the upstream actually rejects these
fields.

Benchmarks on /v1/chat/completions via GitHub Copilot:
  effort=(none) → 64 reasoning_tokens, ~2.0s
  effort=low    → 0  reasoning_tokens, ~1.55s
  effort=medium → 64 reasoning_tokens, ~1.9s
  effort=high   → 128 reasoning_tokens, ~2.2s

Made-with: Cursor

2026-04-22 10:23:31 +07:00

..

config

chore: refresh provider model list (#723)

2026-04-22 09:57:52 +07:00

executors

fix(github): preserve reasoning_effort for non-Claude models (#713)

2026-04-22 10:23:31 +07:00

handlers

Refactor error handling to config-driven approach with centralized error rules

2026-04-15 11:46:47 +07:00

services

fix: update backoff configuration and improve CLI detection messages

2026-04-17 12:54:50 +07:00

transformer

feat: enhance request handling and error management in chatCore and streamToJsonConverter

2026-02-15 12:02:53 +07:00

translator

fix(codex): await image URL fetches before sending to upstream (closes #575)

2026-04-17 12:15:10 +07:00

utils

Enhance error formatting to include low-level cause details, update HeaderMenu to use MenuItem component for better structure, and improve LanguageSwitcher to support controlled open state. Update subproject commit status.

2026-04-17 12:15:10 +07:00

.npmignore

Update jsconfig.json and package.json to correct open-sse path references from relative to local directory.

2026-01-05 10:37:09 +07:00

index.js

Refactor config

2026-03-12 16:20:46 +07:00