Spaces:

elmerzole
/

llm-api-proxy

Paused

App Files Files Community

llm-api-proxy / src /rotator_library /providers

755 kB

11 contributors

History: 175 commits

mirrobot-agent[bot]

fix(antigravity): add propertyNames to incompatible schema keywords (#52)

92db52f unverified about 2 months ago

utilities
fix(antigravity): 🐛 TLDR: Huge ass pass fixing things + Gemini 3 Flash addition 2 months ago
__init__.py
5.11 kB

feat(providers): ✨ add antigravity provider and auth base 3 months ago
antigravity_auth_base.py
28.8 kB

refactor(auth): 🔨 consolidate OAuth credential management into base classes 2 months ago
antigravity_provider.py
208 kB

fix(antigravity): add propertyNames to incompatible schema keywords (#52) about 2 months ago
chutes_provider.py
1.04 kB

feat: Refactor logging to use a dedicated logger across providers and enhance model retrieval with httpx 8 months ago
cohere_provider.py
1.03 kB

feat: Refactor logging to use a dedicated logger across providers and enhance model retrieval with httpx 8 months ago
gemini_auth_base.py
29 kB

refactor(auth): 🔨 consolidate OAuth credential management into base classes 2 months ago
gemini_cli_provider.py
107 kB

fix(antigravity): 🐛 TLDR: Huge ass pass fixing things + Gemini 3 Flash addition 2 months ago
gemini_provider.py
6.49 kB

refactor(gemini): standardize default temperature to 1 3 months ago
google_oauth_base.py
70.1 kB

fix(oauth): 🐛 prevent deadlock and token desync for rotating refresh tokens 2 months ago
groq_provider.py
1.03 kB

feat: Refactor logging to use a dedicated logger across providers and enhance model retrieval with httpx 8 months ago
iflow_auth_base.py
75.1 kB

fix(oauth): 🐛 prevent deadlock and token desync for rotating refresh tokens 2 months ago
iflow_provider.py
27.5 kB

refactor(iflow): 🔨 reorganize model registry and integrate new LLM options 2 months ago
mistral_provider.py
1.04 kB

feat: Refactor logging to use a dedicated logger across providers and enhance model retrieval with httpx 8 months ago
nvidia_provider.py
2.3 kB

feat(providers): ✨ inject NVIDIA 'thinking' flag for DeepSeek v3.1+ models 4 months ago
openai_compatible_provider.py
3.93 kB

feat(core): enable static model configuration and LiteLLM compatibility for custom providers 3 months ago
openai_provider.py
1.03 kB

feat: Refactor logging to use a dedicated logger across providers and enhance model retrieval with httpx 8 months ago
openrouter_provider.py
1.05 kB

feat: Refactor logging to use a dedicated logger across providers and enhance model retrieval with httpx 8 months ago
provider_cache.py
22 kB

refactor(cache): 🔨 decouple memory cleanup from disk persistence lifecycle 2 months ago
provider_interface.py
23.1 kB

docs(background): reduce default background job interval from 15min to 5min 2 months ago
qwen_auth_base.py
65 kB

fix(oauth): 🐛 prevent deadlock and token desync for rotating refresh tokens 2 months ago
qwen_code_provider.py
28.3 kB

refactor(core): 🔨 centralize path management for PyInstaller compatibility 2 months ago