Files
hermes-agent/tools
teknium1 503d818ddf fix: vision_analyze does not re-embed an image already attached natively to the current turn
When a surface (Telegram gateway, CLI, TUI, delegated child) attaches an
image natively to the user turn and the model then calls vision_analyze on
the same path, the native fast path embedded the identical pixels a second
time as a multimodal tool result in the same request (#76411).

conversation_loop.run_conversation now scopes the turn's native image
handles (the [Image attached at: ...] hints build_native_content_parts
writes) in a ContextVar for the duration of the turn; the tool answers with
a short text result instead. Region crops and other images still embed;
the scope ends with the turn so later turns can re-load after compression.
2026-09-19 09:52:18 -07:00
..