mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-13 14:02:16 +00:00
The image-generate tool showed a placeholder, then the model echoed a (often different) image inline in its prose — a second, jarring copy in the wrong place, dimmed as tool scaffolding, with a misplaced download button. Now the generated image lives only in the tool slot: - Strip every embedded image/media link from the assistant prose of a message that produced an image (the model frequently restates the remote URL while the result holds the local path), preserving the agent's words. Applied on hydration, live deltas, and completion. - One stable frame sized from the aspect_ratio arg up front, so the diffusion placeholder and the decoded image share the same box and crossfade with no layout shift; the box derives its height from the true ratio on load (no letterboxing). - Exempt generated images from the tool-block dim-until-hover rule. - Extract a shared useImageDownload hook + ImageLightbox so the tool image and markdown images share one implementation. |
||
|---|---|---|
| .. | ||
| activity-timer-text.tsx | ||
| activity-timer.test.tsx | ||
| activity-timer.ts | ||
| code-card.tsx | ||
| compact-markdown.tsx | ||
| composer-dock.ts | ||
| diff-lines.tsx | ||
| disclosure-row.tsx | ||
| generated-image-result.tsx | ||
| image-generation-placeholder.tsx | ||
| intro-copy.jsonl | ||
| intro.tsx | ||
| preview-attachment.tsx | ||
| shiki-highlighter.tsx | ||
| status-row.tsx | ||
| status-section.tsx | ||
| terminal-output.tsx | ||
| zoomable-image.tsx | ||