forked from kent/consciousness
91106deaa1
view_image now reads the file, grabs dimensions via imagesize (no full decode), and pushes a user-role branch containing a NodeBody::Image leaf straight into the conversation. The tool_result is just a short acknowledgment — the actual pixels ride in the Image leaf for the API layer to extract into multi_modal_data. Drops the capture_tmux_pane path, which had no business living under "vision" (tmux text capture belongs in bash or a dedicated tool, and this one just returned rendered text anyway). Co-Authored-By: Proof of Concept <poc@bcachefs.org> |
||
|---|---|---|
| .. | ||
| ast_grep.rs | ||
| bash.rs | ||
| cd.rs | ||
| channels.rs | ||
| control.rs | ||
| edit.rs | ||
| glob.rs | ||
| grep.rs | ||
| lsp.rs | ||
| mcp_client.rs | ||
| memory.rs | ||
| mod.rs | ||
| read.rs | ||
| think.rs | ||
| vision.rs | ||
| web.rs | ||
| write.rs | ||