Plan: tag properties (LLM-filled structured data) - #229
Open
kenforthewin wants to merge 2 commits into
Open
Conversation
Design settled after analyzing Logseq 2.0's DB release: tags carry lightweight property declarations, the existing tagging pipeline fills them via structured extraction, manual values always win, and the user's text is never edited. Three phases — extraction+display, query surface (search filters + agent tool), then tag-bound templates. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
…mantics From the design talk-through: the reader panel is the primary manual path with declared-but-empty slots as typed affordances; editing an extracted value converts it to manual; ad-hoc keys keep the panel as expressive as frontmatter; extracted values are a projection that untagging and declaration edits re-derive while manual values survive unconditionally; and extraction is honest or silent — nullable fields, high-confidence-only prompting, and a per-field auto_extract opt-out (the auto-tag-targets philosophy, one level down) that keeps judgment fields out of the generated schema entirely. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds `docs/plans/tag-properties.md` — the design for structured data in Atomic, settled after analyzing Logseq 2.0's database release.
Core inversion: Logseq makes the human fill the schema; Atomic's tags declare properties and the existing tagging pipeline extracts them. Manual values (frontmatter, panel edits) always beat extracted ones; the pipeline never edits user text; export materializes everything so the markdown ZIP stays complete. Small type system, no validation apparatus, zero cost until a tag opts in.
Doc only — no code changes.
🤖 Generated with Claude Code