Tag-eval review actions: bigger clickable thumbnails + inline confirm/reject #137

Merged

bvandeusen merged 2 commits from dev into main 2026-06-27 23:49:12 -04:00

Conversation 0 Commits 2 Files Changed 2

+104 -20

bvandeusen commented 2026-06-27 23:49:08 -04:00

Owner

Copy Link

Copy Source

Makes the eval card's example galleries an actionable label-review surface.

• 4974b7c — thumbnails 56→120px, each links to /explore/<id> (new tab).
• 13d297b — green ✓ / red ✗ on every example thumbnail, writing the same tables the head trains on: ✓ applies a tag (positive), ✗ records a rejection (negative via suggestions/dismiss), and on a doubted positive ✗ removes the tag + records the rejection. Acted thumbs grey out; re-run to watch the head sharpen. No backend change — reuses existing endpoints.

Closes the learn-from-tags loop on the eval surface (operator-flagged: no way to confirm/refine the head's suggestions). Inline is the starting point; the modal Suggestions rail gets the native red-✗ negative next (#1134).

🤖 Generated with Claude Code

Makes the eval card's example galleries an actionable label-review surface. - **`4974b7c`** — thumbnails 56→120px, each links to `/explore/<id>` (new tab). - **`13d297b`** — green ✓ / red ✗ on every example thumbnail, writing the same tables the head trains on: ✓ applies a tag (positive), ✗ records a rejection (negative via `suggestions/dismiss`), and on a doubted positive ✗ removes the tag + records the rejection. Acted thumbs grey out; re-run to watch the head sharpen. No backend change — reuses existing endpoints. Closes the learn-from-tags loop on the eval surface (operator-flagged: no way to confirm/refine the head's suggestions). Inline is the starting point; the modal Suggestions rail gets the native red-✗ negative next (#1134). 🤖 Generated with [Claude Code](https://claude.com/claude-code)

bvandeusen added 2 commits 2026-06-27 23:49:08 -04:00

feat(tag-eval): bigger, clickable example thumbnails (label-review queue) ... 4974b7cf77

The 56px example thumbs were too small to judge a label (operator-flagged).
Bump to 120px and wrap each in a link to /explore/<id> (new tab) so the
"head doubts / would suggest" galleries double as a review-and-fix queue —
click a doubted positive, land on it in Explore, correct the tag, re-run.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

feat(tag-eval): inline confirm/reject actions on example thumbnails ... 13d297b881

Closes the learn-from-tags loop directly on the eval lists (operator-flagged:
no surface to confirm/refine the head's suggestions). Each thumbnail gets a
green ✓ / red ✗ that writes the SAME tables the head trains on:
- suggest + ✓  → apply tag (new positive, POST /images/<id>/tags)
- suggest + ✗  → record rejection (hard negative, suggestions/dismiss)
- doubt   + ✗  → remove tag + record rejection (kill bad positive, add negative)
- doubt   + ✓  → keep (stays a positive, no write)
Acted thumbs grey out with a badge; re-run to see the head sharpen. Thumb still
links to /explore/<id>. All endpoints already existed — no backend change.

Inline is the starting point; longer-term the modal Suggestions rail gets the
red "No" (negative) so per-image rejection is native there too (next slice).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

bvandeusen merged commit 55e8632dab into main 2026-06-27 23:49:12 -04:00

Sign in to join this conversation.

Reviewers

No Reviewers

Labels

No items

No Label

Milestone

No items

No Milestone

Projects

Clear projects

No project

Assignees

Clear assignees

bvandeusen

No Assignees

1 Participants

Notifications

Subscribe

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: bvandeusen/FabledCurator#137