Hannes Rudolph 84f58cd518 feat(models): add per-model timeout disable to avoid global override for long-running models (e.g., gpt-5-pro) ... - Introduce ModelInfo.disableTimeout to opt out of request timeouts on a per-model basis - Apply in OpenAI-compatible, Ollama, and LM Studio providers (timeout=0 when flag is true) - Preserve global “API Request Timeout” behavior (0 still disables globally); per-model flag takes precedence for that model - Motivation: gpt-5-pro often requires longer runtimes; per-model override avoids forcing a global setting that impacts all models - Add/extend unit tests to validate provider behavior		2025-12-09 18:29:12 -07:00
..
npm	chore: bump version to v1.89.0 (#9718)	2025-12-01 14:25:48 -08:00
scripts	Fix publish-npm script (#7093)	2025-08-14 03:17:56 -07:00
src	feat(models): add per-model timeout disable to avoid global override for long-running models (e.g., gpt-5-pro)	2025-12-09 18:29:12 -07:00
.gitignore	Task metadata (#7092)	2025-08-14 03:14:17 -07:00
eslint.config.mjs	Task metadata (#7092)	2025-08-14 03:14:17 -07:00
package.json	Task metadata (#7092)	2025-08-14 03:14:17 -07:00
tsconfig.json	Task metadata (#7092)	2025-08-14 03:14:17 -07:00
tsup.config.ts	Bump @roo-code/types to v1.42.0 (#6610)	2025-08-02 13:27:59 -07:00
vitest.config.ts	Convert jest tests to vitest and disable default watch mode for vitest (#4568)	2025-06-11 14:48:01 -07:00