Callers that need ready work across several statuses (e.g. Gas City's
native store Ready(), which spans open/blocked/deferred/pinned/hooked/
review/testing) currently issue one GetReadyWork per status. Each call
re-pays the deferred-parents pre-query, the wisps arm, and the
per-transaction round trips — measured at 30-70ms per call on a live
server-mode store, ~7x per Ready().
WorkFilter.Statuses (OR semantics) renders a single status IN (...)
clause through BuildReadyWorkWhere and propagates to the wisp-side
IssueFilter.Statuses, so multi-status callers pay the fixed per-call
work once. Singular Status keeps precedence; both empty keeps the
legacy ('open', 'in_progress') default.
Review round 2: a conformance audit case (ReadyMultiStatusFilter) pins
the contract at the result level against both backends — real issues
and wisps across several statuses, OR semantics in one call, singular-
Status precedence, the empty default, a custom status through the same
IN clause, and the ephemeral exclusion of wisps without
IncludeEphemeral. The library guide documents Statuses, and
BuildReadyWorkWhere computes the status clause and args in one pass.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
||
|---|---|---|
| .. | ||
| bash-agent | ||
| bd-example-extension-go | ||
| claude-desktop-mcp | ||
| compaction | ||
| contributor-workflow | ||
| formulas | ||
| library-usage | ||
| linear-workflow | ||
| multi-phase-development | ||
| multiple-personas | ||
| protected-branch | ||
| python-agent | ||
| startup-hooks | ||
| team-workflow | ||
| README.md | ||
Beads Examples
This directory contains examples of how to integrate bd with AI agents and workflows.
Examples
Agent Integration
- python-agent/ - Simple Python agent that discovers ready work and completes tasks
- bash-agent/ - Bash script showing the full agent workflow
- startup-hooks/ - Session startup scripts for automatic bd upgrade detection
- claude-desktop-mcp/ - MCP server for Claude Desktop integration
Tools & Utilities
- monitor-webui/ - Standalone web interface for real-time issue monitoring and visualization
- git-hooks/ - Pre-configured git hooks for automatic Dolt sync
Workflow Patterns
- contributor-workflow/ - OSS contributor setup with separate planning repo
- team-workflow/ - Team collaboration with shared repositories
- multi-phase-development/ - Organize large projects by phases (planning, MVP, iteration, polish)
- multiple-personas/ - Architect/implementer/reviewer role separation
- protected-branch/ - Protected branch workflow for team collaboration
Quick Start
# Try the Python agent example
cd python-agent
python agent.py
# Try the bash agent example
cd bash-agent
./agent.sh
# Install git hooks
cd git-hooks
./install.sh
# REMOVED (bd-4c74): branch-merge demo - hash IDs eliminate collision resolution
Creating Your Own Agent
The basic agent workflow:
- Find ready work:
bd ready --json --limit 1 - Claim the task:
bd update <id> --claim --json - Do the work: Execute the task
- Discover new issues:
bd create "Found bug" --json - Link discoveries:
bd dep add <new-id> <parent-id> --type discovered-from - Complete the task:
bd close <id> --reason "Done" --json
All commands support --json for easy parsing.