coldxiangyu de0b5b3d91 fix: filter image_url for non-vision models at provider layer ...

- 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)

2026-03-15 22:32:34 +08:00

..

__init__.py

Support Azure OpenAI

2026-03-06 08:43:58 +00:00

azure_openai_provider.py

fix: raise tool result history limit to 16k and force save_memory in consolidation

2026-03-12 03:08:53 +00:00

base.py

fix: raise tool result history limit to 16k and force save_memory in consolidation

2026-03-12 03:08:53 +00:00

custom_provider.py

fix: raise tool result history limit to 16k and force save_memory in consolidation

2026-03-12 03:08:53 +00:00

litellm_provider.py

fix: filter image_url for non-vision models at provider layer

2026-03-15 22:32:34 +08:00

openai_codex_provider.py

fix: raise tool result history limit to 16k and force save_memory in consolidation

2026-03-12 03:08:53 +00:00

registry.py

fix: filter image_url for non-vision models at provider layer

2026-03-15 22:32:34 +08:00

transcription.py

style: unify code formatting and import order

2026-02-28 20:55:43 +08:00