Alex 9eb7878ad3 feat(v1): support multimodal content arrays (text + image_url) ...

OpenAI-compatible clients send multimodal user turns as a `content` array of
typed parts. translate_request previously assigned the array straight to the
question, breaking the string-only retrieval / token-budgeting / history paths
(HTTP 500). Now:

- content_to_text() extracts text from content arrays for the question,
  history and system prompt, so the string paths work unchanged.
- The full content array (text + image_url parts) is preserved as
  `multimodal_content`, threaded to the agent and emitted as the final user
  message so images reach the model. Token budgeting uses the text only.

The content array (incl. image_url) now reaches the LLM call intact; images
render for vision-capable models. A text-only upstream model will reject the
image_url variant, as expected.

2026-06-04 12:23:08 +01:00

..

routes

fix: issues with local tool calling on non openai endpoint

2026-06-03 22:50:03 +01:00

services

feat(v1): support multimodal content arrays (text + image_url)

2026-06-04 12:23:08 +01:00

__init__.py

fix search (#2210)

2025-12-22 00:51:06 +02:00