Files
letta-server/letta
Ani Tunturi 93337ce680 fix: pass images from tool returns to vision models
OpenAI Chat Completions requires tool message content to be a string,
so images in tool returns were silently replaced with [Image omitted].

Now: text stays in the tool return, images get injected as a user
message right after. The model actually sees what the tool saw.

to_openai_dict also cleaned up — image handling lives in
to_openai_dicts_from_list where it can inject the extra message.
2026-03-21 12:41:37 -04:00
..
2025-10-07 17:50:45 -07:00
2025-09-17 15:47:40 -07:00
2025-09-17 15:47:40 -07:00
2025-09-17 15:47:40 -07:00
2025-09-17 15:47:40 -07:00
2026-03-03 18:34:51 -08:00
2025-10-07 17:50:45 -07:00
2025-09-17 15:47:40 -07:00
2026-02-24 10:55:08 -08:00
2025-09-17 15:47:40 -07:00
2025-09-17 15:47:40 -07:00