382b78c96d
* fix(think-mode): support GitHub Copilot proxy provider ### Summary - Adds `github-copilot` support to think-mode by resolving the underlying provider from the model name (Claude → Anthropic, Gemini → Google, GPT/o* → OpenAI). - Normalizes model IDs to handle dotted versions defensively (e.g. `claude-opus-4.5` → `claude-opus-4-5`, `gpt-5.2` → `gpt-5-2`) so high-variant upgrades and capability checks work reliably. - Expands high-variant mappings to cover Gemini preview/flash variants and aligns GPT-5.1/5.2 mappings with normalized IDs. - Adds OpenAI “thinking mode” config (`reasoning_effort: "high"`) alongside existing provider configs. ### Tests - Adds unit coverage for the switcher (`switcher.test.ts`) and integration coverage for the hook (`index.test.ts`), including: - GitHub Copilot model routing + thinking config injection - Dots vs hyphens normalization - Already-`-high` variants not being re-upgraded - Unknown models/providers handled gracefully * fix: support multiple digits in model minor