Bertho Joris 345cdcf6a5 fix(combo): detect images from Hermes and attachment payloads for Vision Adapter ... Inspect images[], experimental_attachments/attachments, message-level image/image_url/audio_url, and inline data:image|audio|pdf URIs on trailing user turns so Vision Adapter auto-switch fires for Hermes/Ollama/Vercel AI SDK shapes. stripOpenAI now also drops msg.images and image attachments when the active model lacks vision support.		2026-08-13 18:30:44 +07:00
..
concerns	fix(combo): detect images from Hermes and attachment payloads for Vision Adapter	2026-08-13 18:30:44 +07:00
formats	fix(translator): don't drop image-only user messages in prepareClaudeRequest	2026-08-05 13:20:27 +07:00
request	fix(translator): preserve prompt_cache_key when converting chat to responses	2026-08-13 11:46:49 +07:00
response	fix(responses): don't close message on empty tool_calls array	2026-08-13 11:40:45 +07:00
schema	fix(translator): preserve Responses Lite tools across Chat providers	2026-08-05 13:27:25 +07:00
formats.js	feat: add CommandCode provider support	2026-05-07 23:01:33 +07:00
index.js	fix(translator): preserve Responses Lite tools across Chat providers	2026-08-05 13:27:25 +07:00