Mario Zechner c5543f7586 GitHub Copilot: auto-enable models, fix gpt-5 API, normalize tool call IDs ... - Auto-enable all models after /login via POST /models/{model}/policy - Use openai-responses API for gpt-5/o3/o4 models (not accessible via completions) - Normalize tool call IDs when switching between github-copilot models with different APIs (fixes #198: openai-responses generates 450+ char IDs with special chars that break other models) - Update README with streamlined GitHub Copilot docs		2025-12-15 20:06:11 +01:00
..
anthropic.ts	Auto-retry on transient provider errors (overloaded, rate limit, 5xx)	2025-12-10 23:36:46 +01:00
google.ts	Support thinking level configuration for Gemini 3 Pro models (#176)	2025-12-13 02:09:54 +01:00
openai-completions.ts	Restore assistant bridge message insertion for compat flag	2025-12-11 00:36:35 +01:00
openai-responses.ts	Add xhigh thinking level for OpenAI codex-max models	2025-12-08 21:12:54 +01:00
transorm-messages.ts	GitHub Copilot: auto-enable models, fix gpt-5 API, normalize tool call IDs	2025-12-15 20:06:11 +01:00