Replace the static provider-level supports_vision check with a
reactive fallback: when a model returns an image-unsupported error,
strip image_url blocks from messages and retry once. This avoids
maintaining an inaccurate vision capability table and correctly
handles gateway/unknown model scenarios.
Also extract _safe_chat() to deduplicate try/except boilerplate
in chat_with_retry().
- Add field to ProviderSpec (default True)
- Add and methods in LiteLLMProvider
- Filter image_url content blocks in before sending to non-vision models
- Reverts session-layer filtering from original PR (wrong layer)
This fixes the issue where switching from Claude (vision-capable) to
non-vision models (e.g., Baidu Qianfan) causes API errors due to
unsupported image_url content blocks.
The provider layer is the correct place for this filtering because:
1. It has access to model/provider capabilities
2. It only affects non-vision models
3. It preserves session layer purity (storage should not know about model capabilities)
With custom_llm_provider kwarg handling routing, the openrouter/ prefix
caused model names like anthropic/claude-sonnet-4-6 to become
openrouter/anthropic/claude-sonnet-4-6, which OpenRouter API rejects.
Add native Ollama support so local models (e.g. nemotron-3-nano) can be
used without an API key. Adds ProviderSpec with ollama_chat LiteLLM
prefix, ProvidersConfig field, and skips API key validation for local
providers.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The bare keyword "codex" causes false positive matches when any model
name happens to contain "codex" (e.g. "gpt-5.3-codex" on a custom
provider). This incorrectly routes the request through the OAuth-based
OpenAI Codex provider, producing "OAuth credentials not found" errors
even when a valid custom api_key and api_base are configured.
Keep only the explicit "openai-codex" keyword so that auto-detection
requires the canonical prefix. Users can still set provider: "custom"
to force the custom endpoint, but auto-detection should not collide.
Closes#1311
Inject cache_control: {"type": "ephemeral"} on the system message and
last tool definition for providers that support prompt caching. Adds
supports_prompt_caching flag to ProviderSpec (enabled for Anthropic only)
and skips caching when routing through a gateway.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add VolcEngine ProviderSpec entry in registry.py
- Add volcengine to ProvidersConfig class in schema.py
- Update model providers table in README.md
- Add description about VolcEngine coding plan endpoint
Add SiliconFlow (硅基流动) as an OpenAI-compatible gateway provider.
SiliconFlow hosts multiple models (Qwen, DeepSeek, etc.) via an
OpenAI-compatible API at https://api.siliconflow.cn/v1.
Changes:
- Add ProviderSpec for siliconflow in providers/registry.py
- Add siliconflow field to ProvidersConfig in config/schema.py
Co-authored-by: Cursor <cursoragent@cursor.com>
- Add is_oauth and oauth_provider fields to ProviderSpec
- Update _make_provider() to use registry for OAuth provider detection
- Update get_provider() to support OAuth providers (no API key required)
- Mark OpenAI Codex as OAuth-based provider in registry
This improves the provider registry architecture to support OAuth-based
authentication flows, making it extensible for future OAuth providers.
Benefits:
- OAuth providers are now registry-driven (not hardcoded)
- Extensible design: new OAuth providers only need registry entry
- Backward compatible: existing API key providers unaffected
- Clean separation: OAuth logic centralized in registry
- Add OpenAI Codex ProviderSpec to registry.py
- Add openai_codex config field to ProvidersConfig in schema.py
- Mark Codex as OAuth-based (no API key required)
- Set appropriate default_api_base for Codex API
This integrates the Codex OAuth provider with the refactored
provider registry system introduced in upstream commit 299d8b3.
Xubin RenandXubin Ren
coldxiangyuandXubin Ren
Paresh MathurandXubin Ren
gaoyiman
Jerome Sonnet (letzdoo)andClaude Opus 4.6
Kunal Karmakar
ouyangwulin
gaoyimanandGitHub
Nikolas de Hor
init-new-world
tercerapersonaandGitHub
tercerapersonaandClaude Sonnet 4.6
PiEgg
Your Name
ras_botandCursor
Darye
Zhiwei LiandCursor
pinhua33
pinhua33