Updates the `lore robot-docs` manifest with comprehensive documentation
for the new since-last-check inbox feature, enabling AI agents to
discover and use the functionality programmatically.
robot-docs manifest additions:
- since_last_check response schema with cursor_iso, groups, events
- --reset-cursor flag documentation
- Design notes: cursor persistence location, --project filter behavior
- Example commands in personal_dashboard section
Agent instruction updates (AGENTS.md, CLAUDE.md):
- Added --mrs, --project, --user flags to command examples
- Added --reset-cursor example
- Aligned both files for consistency
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Replace all MCP Agent Mail references with Liquid Mail in AGENTS.md and
CLAUDE.md. The old system used file reservations and MCP-based messaging
with inbox/outbox/thread semantics. Liquid Mail provides a simpler
post-based shared log with topic-scoped messages, decision conflict
detection, and polling via the liquid-mail CLI.
Key changes:
- Remove entire MCP Agent Mail section (identity registration, file
reservations, macros vs granular tools, common pitfalls)
- Update Beads integration workflow to reference Liquid Mail: replace
reservation + announce patterns with post-based progress logging and
decision-first workflows
- Update bv scope boundary note to reference Liquid Mail
- Append full Liquid Mail integration block to CLAUDE.md: conventions,
typical flow, decision conflicts, posting format, topic rules, context
refresh, live updates, mapping cheat-sheet, quick reference
- Add .liquid-mail.toml project configuration (Honcho backend)
Enriched all per-note search beads (NOTE-0A through NOTE-2I) with:
- Corrected migration numbers (022, 024, 025)
- Verified file paths and line numbers from codebase
- Complete function signatures for referenced code
- Detailed approach sections with SQL and Rust patterns
- DocumentData struct field mappings
- TDD anchors with specific test names
- Edge cases from codebase analysis
- Dependency context explaining what each blocker provides
Establishes Jujutsu (jj) as the preferred VCS tool for this colocated
repo, matching the global Claude Code rules. Agents should use jj
equivalents for all git operations and only fall back to raw git for
hooks, LFS, submodules, or gh CLI interop.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
README.md:
- Feature summary updated to mention work item status sync and GraphQL
- New config reference entry for sync.fetchWorkItemStatus (default true)
- Issue listing/show examples include --status flag usage
- Valid fields list expanded with status_name, status_category,
status_color, status_icon_name, status_synced_at_iso
- Database schema table updated for issues table
- Ingest/sync command descriptions mention status enrichment phase
- Adaptive page sizing and graceful degradation documented
AGENTS.md:
- Robot mode example shows --status flag usage
docs/robot-mode-design.md:
- Issue available fields list expanded with status fields
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Expert mode now surfaces the specific MR references (project/path!iid) that
contributed to each expert's score, capped at 50 per user. A new --detail flag
adds per-MR breakdowns showing role (Author/Reviewer/both), note count, and
last activity timestamp.
Scoring weights (author_weight, reviewer_weight, note_bonus) are now
configurable via the config file's `scoring` section with validation that
rejects negative values. Defaults shift to author_weight=25, reviewer_weight=10,
note_bonus=1 — better reflecting that code authorship is a stronger expertise
signal than review assignment alone.
Path resolution gains suffix matching: typing "login.rs" auto-resolves to
"src/auth/login.rs" when unambiguous, with clear disambiguation errors when
multiple paths match. Project-scoping (-p) narrows the candidate set.
The MAX_MR_REFS_PER_USER constant is promoted to module scope for reuse
across expert and overlap modes. Human output shows MR refs inline and detail
sub-rows when requested. Robot JSON includes mr_refs, mr_refs_total,
mr_refs_truncated, and optional details array.
Includes comprehensive tests for suffix resolution, scoring weight
configurability, MR ref aggregation across projects, and detail mode.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Sync the agent instructions with the current robot mode implementation:
- Add RUST_CLI_TOOLS_BEST_PRACTICES.md reference for Rust coding guidance
- Expand robot mode description to cover all new capabilities
- Add --fields examples (minimal preset, custom field lists)
- Document error actions array for automated recovery workflows
- Update response format to show elapsed_ms and actions in error envelope
- Add field selection section with usage examples
- Separate health check to exit code 19 (was overloaded on exit code 1)
- Add robot-docs recommendation for response schema discovery
- Update best practices with --fields minimal for token efficiency
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
AGENTS.md: Comprehensive rewrite adding file deletion safeguards,
destructive git command protocol, Rust toolchain conventions, code
editing discipline rules, compiler check requirements, TDD mandate,
MCP Agent Mail coordination protocol, beads/bv/ubs/ast-grep/cass
tool documentation, and session completion workflow.
README.md: Document NO_COLOR/CLICOLOR env vars, --since 1m duration,
project resolution cascading match logic, lore health and robot-docs
commands, exit codes 17 (not found) and 18 (ambiguous match),
--color/--quiet global flags, dirty_sources and
pending_discussion_fetches tables, and version command git hash output.
docs/embedding-pipeline-hardening.md: Detailed spec covering the three
problems from the chunk size reduction (broken --full wiring, mixed
chunk sizes in vector space, static dedup multiplier) with decision
records, implementation plan, and acceptance criteria.
docs/phase-b-temporal-intelligence.md: Draft planning document for
transforming gitlore from a search engine into a temporal code
intelligence system by ingesting structured event data from GitLab.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- README.md: Add hybrid search and robot mode to feature list. Update
quick start to use new noun-first CLI syntax (lore issues, lore mrs,
lore search). Add embedding configuration section. Update command
examples throughout.
- AGENTS.md: Update robot mode examples to new CLI syntax. Add search,
sync, stats, and generate-docs commands to the robot mode reference.
Update flag conventions (-n for limit, -s for state, -J for JSON).
- docs/prd/checkpoint-3.md: Major expansion with gated milestone
structure (Gate A: lexical, Gate B: hybrid, Gate C: sync). Add
prerequisite rename note, code sample conventions, chunking strategy
details, and sqlite-vec rowid encoding scheme. Clarify that Gate A
requires only SQLite + FTS5 with no sqlite-vec dependency.
- docs/phase-a-spec.md: New detailed specification for Gate A (lexical
search MVP) covering document schema, FTS5 configuration, dirty
queue mechanics, CLI interface, and acceptance criteria.
- docs/api-efficiency-findings.md: Analysis of GitLab API pagination
behavior and efficiency observations from production sync runs.
Documents the missing x-next-page header issue and heuristic fix.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Updates project documentation to reflect the complete CP2 feature set
with merge request ingestion and robot mode capabilities.
README.md:
- Add MR-related CLI examples (gi list mrs, gi show mr, gi ingest)
- Document robot mode (--robot flag, GI_ROBOT env, auto-detect)
- Update feature list with MR support and DiffNote positions
- Add configuration section with all config file options
- Expand CLI reference with new commands and flags
AGENTS.md:
- Add MR ingestion patterns for AI agent consumption
- Document robot mode JSON schemas for parsing
- Include error handling patterns with exit codes
- Add discussion/note querying examples for code review context
Cargo.toml:
- Bump version to 0.2.0 reflecting major feature addition
The documentation emphasizes the robot mode design which enables
AI agents like Claude Code to reliably parse gi output for automated
GitLab workflow integration.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Set up the GitLab Inbox (gi) CLI tool as a Rust 2024 edition project.
Dependencies organized by purpose:
- Database: rusqlite (bundled SQLite), sqlite-vec for vector search
- Serialization: serde/serde_json for GitLab API responses
- CLI: clap for argument parsing, dialoguer for interactive prompts,
comfy-table for formatted output, indicatif for progress bars
- HTTP: reqwest with tokio async runtime for GitLab API calls
- Async: async-stream and futures for paginated API iteration
- Utilities: thiserror for error types, chrono for timestamps,
flate2 for payload compression, sha2 for content hashing
- Logging: tracing with env-filter for structured debug output
Release profile optimized for small binary size (LTO, strip symbols).
Project structure follows standard Rust conventions with src/lib.rs
exposing modules and src/main.rs as CLI entry point.
Added .gitignore for Rust/Cargo artifacts and local database files.
Added AGENTS.md with TDD workflow guidance and beads issue tracking
integration instructions for AI-assisted development.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
