beads/website/docs/cli-reference/find-duplicates.md
matt wilkie b2a4d1d04a
docs: generate CLI reference from live help (#3704)
* docs: generate CLI reference from live help

* docs(cli): move bd version stamp from per-command pages to index only

Drops the `(bd version X.Y.Z)` suffix from the auto-generated header on
every per-command CLI reference page (writeSingleCommandDoc) and the
docs/CLI_REFERENCE.md preamble (writeAllHelp). The version label now
lives only on the index page emitted by scripts/generate-cli-docs.sh:

- Dev tree (website/docs/cli-reference/index.md, docs/CLI_REFERENCE.md):
  labelled "Latest"
- Versioned snapshots (website/versioned_docs/version-X.Y.Z/...):
  labelled with the explicit semver tag parsed from the directory name

This eliminates the 100+-file no-signal diff a release version bump
otherwise produces, restoring the "regen as a separate small commit"
workflow PR #3704 enables. After this change a version bump alone
yields zero diff on the dev tree; only the new versioned snapshot
created at release-cut time carries the new tag. No datestamps are
introduced anywhere — scripts/generate-cli-docs.sh --check remains
deterministic across CI runs.

Refs: mybd-afb, PR #3704

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: CI Bot <ci@beads.test>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 19:43:49 -07:00

1.9 KiB

id title slug sidebar_position
find-duplicates bd find-duplicates /cli-reference/find-duplicates 999

Generated from bd help --doc find-duplicates

bd find-duplicates

Find issues that are semantically similar but not exact duplicates.

Unlike 'bd duplicates' which finds exact content matches, find-duplicates uses text similarity or AI to find issues that discuss the same topic with different wording.

Approaches: mechanical Token-based text similarity (default, no API key needed) ai LLM-based semantic comparison (requires ANTHROPIC_API_KEY or ai.api_key)

The mechanical approach tokenizes titles and descriptions, then computes Jaccard similarity between all issue pairs. It's fast and free but may miss semantically similar issues with very different wording.

The AI approach sends candidate pairs to Claude for semantic comparison. It first uses mechanical pre-filtering to reduce the number of API calls, then asks the LLM to judge whether the remaining pairs are true duplicates.

Examples: bd find-duplicates # Mechanical similarity (default) bd find-duplicates --threshold 0.4 # Lower threshold = more results bd find-duplicates --method ai # Use AI for semantic comparison bd find-duplicates --status open # Only check open issues bd find-duplicates --limit 20 # Show top 20 pairs bd find-duplicates --json # JSON output

bd find-duplicates [flags]

Aliases: find-dups

Flags:

  -n, --limit int         Maximum number of pairs to show (default 50)
      --method string     Detection method: mechanical, ai (default "mechanical")
      --model string      AI model to use (only with --method ai; default from config ai.model)
  -s, --status string     Filter by status (default: non-closed)
      --threshold float   Similarity threshold (0.0-1.0, lower = more results) (default 0.5)