decolua ced51ed62f feat(nvidia): add new models and capabilities for NVIDIA provider ...

- Updated capabilities for NVIDIA models to enforce OpenAI-compatible reasoning formats.
- Added new models: MiniMax M3, GLM 5.2, DeepSeek V4 Pro, DeepSeek V4 Flash, Kimi K2.6, and Nemotron 3 Ultra to the NVIDIA registry.

This enhances the provider's functionality and aligns with OpenAI standards.

2026-07-03 12:15:58 +07:00

..

all-formats.real.test.js

fix(translator): ESM-safe registry + tool-id pairing + responses max_tokens; add real-creds tests

2026-06-15 11:38:43 +07:00

antigravity-models.real.test.js

Fix AG, Kiro, Xiaomi Provider

2026-06-18 14:58:00 +07:00

file-base64-survey.real.test.js

Refactor

2026-06-15 18:18:04 +07:00

nvidia-thinking.e2e.test.js

feat(nvidia): add new models and capabilities for NVIDIA provider

2026-07-03 12:15:58 +07:00

provider-cases.real.test.js

fix(translator): ESM-safe registry + tool-id pairing + responses max_tokens; add real-creds tests

2026-06-15 11:38:43 +07:00

smoke-providers.real.test.js

test(translator): add data-driven coverage, bug-exposing cases, and real provider smoke

2026-06-06 12:19:59 +07:00

thinking.real.test.js

Refactor

2026-06-15 18:18:04 +07:00

vision-capability-survey.real.test.js

Refactor

2026-06-15 18:18:04 +07:00