Skip to content

feat(vision): tag command — AI-generated tags appended to caption#80

Merged
gfargo merged 1 commit into
mainfrom
feat/vision-tag
May 11, 2026
Merged

feat(vision): tag command — AI-generated tags appended to caption#80
gfargo merged 1 commit into
mainfrom
feat/vision-tag

Conversation

@gfargo
Copy link
Copy Markdown
Owner

@gfargo gfargo commented May 11, 2026

Closes #79. See issue for design notes.

`localpress tag [ids...]` generates 3-6 short tags via the Ollama
vision model and appends them to the attachment's caption as a
`[tags: tag1, tag2, …]` block.

Caption-block approach over WP taxonomies because WP attachment
taxonomies aren't registered by default — caption is universal via
REST and survives gallery markup. Future iteration can write to actual
taxonomies when doctor detects support.

- Uses the kind: 'tags' vision call (introduced in #73) + cleanTagsArray
- Idempotent: existing [tags: …] block respected unless --overwrite
- Preserves existing caption text — block is appended, not replaced
- Bulk via --missing-tags (caption lacks the block) or --all
- Time-machine snapshot before each update
- MCP tool `tag` registered

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
@gfargo gfargo merged commit f574ba8 into main May 11, 2026
4 checks passed
@gfargo gfargo deleted the feat/vision-tag branch May 11, 2026 20:49
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

feat(vision): tag command — AI-generated tags appended to caption

1 participant