Skip to content

feat(evolve): support direct entity auto-tagging - #706

Draft
star-nebula wants to merge 3 commits into
agentscope-ai:mainfrom
star-nebula:feat/auto-tag-direct
Draft

star-nebula wants to merge 3 commits into
agentscope-ai:mainfrom
star-nebula:feat/auto-tag-direct

Conversation

@star-nebula

Copy link
Copy Markdown
Contributor

Summary

  • add a one-call structured LLM path for entity-oriented memory tagging
  • validate returned names against exact document evidence and preserve existing-tag reuse
  • canonicalize Windows separators in file graphs and tag indexes

Validation

  • pytest tests/unit/test_auto_tag.py tests/unit/test_file_graph.py tests/unit/test_tag_index.py: 52 passed
  • git diff --check: passed

Add a single structured model call for entity extraction with evidence validation, avoiding the agent tool loop for predictable bulk tagging. Canonicalize persisted Windows paths in file graphs and tag indexes so tags and wikilinks resolve consistently.
@ployts

ployts commented Nov 4, 2026

Copy link
Copy Markdown
Collaborator

@star-nebula Is this PR ready for review?

star-nebula and others added 2 commits November 7, 2026 08:48
Resolve reme/steps/evolve/auto_tag.py: keep the direct-LLM tag path from
this branch and upstream's single agent_reply_result_text(text) extraction,
so both paths return the same variable.

Co-Authored-By: Claude Code <noreply@anthropic.com>

This branch has not been deployed

No deployments
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.

2 participants