specweave 1.0.593 → 2.0.3

package/plugins/specweave/commands/lsp.md

@@ -1,205 +0,0 @@
----
-description: >
-  Code navigation with LSP. When user says "find references", "go to definition",
-  "where defined", "show type", "list symbols", "what uses", or "who calls" -
-  use native LSP tools if available, otherwise fall back to specweave lsp commands.
-user-invocable: false
----
-
-# LSP Code Intelligence
-
-## Project Overrides
-
-**Skill Memories**: If `.specweave/skill-memories/lsp.md` exists, read and apply its learnings.
-
-Semantic code navigation and analysis.
-
-## Current Status (v2.1.0+)
-
-**⚠️ Native LSP is BROKEN** in Claude Code v2.1.0+ ([Issue #17468](https://github.com/anthropics/claude-code/issues/17468))
-
-| Version | Native LSP | SpecWeave CLI |
-|---------|------------|---------------|
-| ≤2.0.76 | ✅ Works | ✅ Works |
-| ≥2.1.0 | ❌ Broken | ✅ Works |
-
-**Always use SpecWeave CLI** until native LSP is fixed.
-
-## SpecWeave LSP CLI (Always Works)
-
-```bash
-# Find all references to a symbol (SEMANTIC, not grep!)
-specweave lsp refs <file> <symbol>
-
-# Go to definition
-specweave lsp def <file> <symbol>
-
-# Get type information (hover)
-specweave lsp hover <file> <symbol>
-
-# List all symbols in a file
-specweave lsp symbols <file>
-
-# Search workspace for symbols
-specweave lsp search <query>
-```
-
-## File Path Required
-
-If user doesn't specify a file path, find it first:
-
-```bash
-# Step 1: Find which file(s) contain the symbol
-grep -rn --include="*.ts" "function symbolName\|class symbolName" .
-
-# Step 2: Then use LSP on the found file
-specweave lsp refs <found-file> <symbol>
-```
-
-## Why Use SpecWeave CLI over Grep
-
-| Aspect | Grep | SpecWeave LSP |
-|--------|------|---------------|
-| Type | Text matching | Semantic analysis |
-| Results | Includes comments, strings, docs | Actual code usages only |
-| Speed | Fast | 52x faster than grep |
-| Accuracy | Many false positives | Zero false positives |
-
-**⚠️ Never use Grep for "find references"** - Grep finds TEXT matches (including comments, strings, docs). LSP finds SEMANTIC references (actual code usages only).
-
-## Workarounds for Native LSP
-
-If you need native LSP tools:
-
-```bash
-# Option 1: Use older Claude Code version
-ENABLE_LSP_TOOL=1 npx @anthropic-ai/claude-code@2.0.76
-
-# Option 2: Use tweakcc patch
-npx tweakcc --apply
-```
-
-## Multi-Repo LSP Setup (v1.0.203+)
-
-For umbrella projects with multiple repositories, use the interactive setup:
-
-```bash
-# Scan project and install LSP plugins interactively
-specweave lsp setup
-
-# Options:
-specweave lsp setup --max 5       # Limit to top 5 languages
-specweave lsp setup --min-files 10  # Min files to consider a language
-specweave lsp setup --scope project # Install to .claude/settings.json
-specweave lsp setup --dry-run       # Show what would be installed
-```
-
-### What Setup Does
-
-1. **Scans all repos** - Finds languages in `repositories/`, `packages/`, `services/`, etc.
-2. **Ranks by file count** - Shows top languages with file counts
-3. **Shows implications** - Restart required, startup time impact
-4. **Prompts for approval** - User selects which plugins to install
-5. **Installs plugins** - Uses `claude plugin install` with specified scope
-
-### Scan Coverage
-
-Scans these directories for nested repositories:
-- `repositories/` - Multi-repo umbrella pattern
-- `packages/` - Monorepo (Lerna, Nx, etc.)
-- `services/` - Microservices
-- `apps/`, `libs/`, `modules/` - Nx/Turborepo patterns
-
-### Status and Diagnostics
-
-```bash
-# Check current LSP status
-specweave lsp status
-
-# Shows:
-#   - LSP env ready (ENABLE_LSP_TOOL)
-#   - Detected languages
-#   - Missing servers/plugins
-#   - Warm-up state
-```
-
-## Supported Languages (10 LSPs)
-
-SpecWeave LSP supports 10 major languages via their respective language servers:
-
-| Language | Server | Install Command |
-|----------|--------|-----------------|
-| **TypeScript/JavaScript** | tsserver (built-in) | `npm i -g typescript` |
-| **Python** | pyright | `npm i -g pyright` or `pip install pyright` |
-| **Go** | gopls | `go install golang.org/x/tools/gopls@latest` |
-| **Rust** | rust-analyzer | `rustup component add rust-analyzer` |
-| **Java** | jdtls | Via VS Code or manual install |
-| **C#** | csharp-ls | `dotnet tool install -g csharp-ls` |
-| **Kotlin** | kotlin-language-server | Via IntelliJ or manual install |
-| **Swift** | sourcekit-lsp | Comes with Xcode/Swift toolchain |
-| **PHP** | intelephense | `npm i -g intelephense` |
-| **Ruby** | solargraph | `gem install solargraph` |
-
-### Auto-Detection
-
-SpecWeave automatically detects which language servers to use based on project files:
-
-| Language | Detection Files |
-|----------|----------------|
-| TypeScript | `tsconfig.json`, `package.json` |
-| Python | `pyproject.toml`, `requirements.txt`, `setup.py` |
-| Go | `go.mod`, `go.sum` |
-| Rust | `Cargo.toml` |
-| Java | `pom.xml`, `build.gradle` |
-| C# | `*.csproj`, `*.sln` |
-| Kotlin | `build.gradle.kts`, `*.kt` |
-| Swift | `Package.swift`, `*.xcodeproj` |
-| PHP | `composer.json` |
-| Ruby | `Gemfile`, `*.gemspec` |
-
-## How to Enable LSP in Your Project
-
-### 1. Install the Language Server
-
-```bash
-# For Python projects
-pip install pyright
-# OR
-npm install -g pyright
-
-# For Go projects
-go install golang.org/x/tools/gopls@latest
-
-# For Rust projects
-rustup component add rust-analyzer
-
-# For C# projects
-dotnet tool install -g csharp-ls
-```
-
-### 2. Run SpecWeave LSP
-
-```bash
-# It auto-detects languages!
-specweave lsp refs src/file.py MyClass
-specweave lsp def src/main.go HandleRequest
-specweave lsp hover src/lib.rs calculate
-```
-
-### 3. Verify Setup
-
-```bash
-specweave lsp status
-```
-
-## How SpecWeave CLI Works
-
-Uses language-specific clients:
-- **TypeScript**: `TsServerClient` (direct tsserver protocol, fastest)
-- **Other languages**: Generic `LSPClient` (JSON-RPC over stdio)
-
-Features:
-1. Spawns language server directly
-2. Uses native LSP protocol
-3. Provides real semantic analysis
-4. Works in any environment (CI/CD, Claude Code, scripts)

package/plugins/specweave/commands/next.md

@@ -1,81 +0,0 @@
----
-description: Close current increment if ready and suggest next work. Use when saying "what's next", "next increment", or "move on".
----
-
-# Next Increment (Smart Workflow Transition)
-
-**CRITICAL**: This command requires **EXPLICIT USER CONFIRMATION** before closing any increment!
-
-## Workflow
-
-### Step 1: Find Active Increment
-
-```bash
-find .specweave/increments -type f -name "spec.md" -exec grep -l "status: in-progress" {} \;
-```
-
-- One in-progress → Validate for closure
-- Multiple in-progress → Warn about WIP limit, ask which to close
-- None in-progress → Skip to Step 4 (suggest next work)
-
-### Step 2: PM Validation (3 Gates)
-
-#### Gate 1: Tasks Completed
-- All P1 (critical) tasks completed
-- All P2 (important) tasks completed OR deferred with reason
-- P3 tasks completed, deferred, or moved to backlog
-- No tasks in "blocked" state
-
-#### Gate 2: Tests Passing
-- All test suites passing (no failures)
-- Coverage meets target (default 80%+ critical paths)
-- No skipped tests without documentation
-
-#### Gate 3: Documentation Updated
-- CLAUDE.md updated with new features
-- README.md updated with usage examples
-- CHANGELOG.md updated (if public API changed)
-
-### Step 3: Closure Decision
-
-**If ALL gates pass** — use AskUserQuestion for explicit confirmation:
-```
-AskUserQuestion({
-  questions: [{
-    header: "Close increment?",
-    question: "All PM gates passed. Ready to permanently close this increment?",
-    options: [
-      { label: "Yes, close it", description: "Mark as completed (irreversible)" },
-      { label: "No, keep open", description: "Stay at ready_for_review status" }
-    ],
-    multiSelect: false
-  }]
-})
-```
-
-Only on user confirmation: update status → completed, set completion date, generate report, free WIP slot.
-
-**If ANY gate fails** — present options:
-- A. Complete remaining work (recommended)
-- B. Force close and defer incomplete tasks
-- C. Stay on current increment
-
-**NEVER auto-close!** Always give user control.
-
-### Step 3.5: Post-Closure Quality Assessment
-
-After successful closure, automatically run `sw:qa ${incrementId}`. Quality gate: PASS (≥80), CONCERNS (60-79), FAIL (<60). If FAIL, suggest creating follow-up increment.
-
-### Step 4: Suggest Next Work
-
-1. Check for planned increments in backlog
-2. Present options: start backlog item, continue in-progress work, or create new increment
-
-## Key Differences
-
-| Command | Purpose |
-|---------|---------|
-| `sw:do` | Execute tasks in increment |
-| `sw:progress` | Check status (no action) |
-| `sw:done` | Explicit close with validation |
-| `sw:next` | **Smart transition** (close + QA + suggest next) |

package/plugins/specweave/commands/progress.md

@@ -1,39 +0,0 @@
----
-description: Show progress for active increments with task/AC completion. Use when saying "show progress", "status", or "how far along".
-argument-hint: "[incrementId]"
----
-
-# Increment Progress
-
-## Project Overrides
-
-**Skill Memories**: If `.specweave/skill-memories/progress.md` exists, read and apply its learnings.
-
-## Hook Execution (Default)
-
-This command is intercepted by the **UserPromptSubmit hook** for instant execution (<10ms). The hook reads from `.specweave/state/dashboard.json` cache.
-
-**CRITICAL**: The hook output in `<system-reminder>` is ALREADY FORMATTED for the user. You MUST:
-1. Present the hook output VERBATIM — copy it exactly as-is
-2. Do NOT reformat into a markdown table
-3. Do NOT re-summarize or paraphrase the data
-4. Do NOT add interpretation unless the user asks a follow-up question
-5. If the user asks "what should I work on next?" THEN add recommendations
-
-## CLI Fallback
-
-If hook output isn't displayed (rare), execute:
-
-```bash
-specweave status --verbose
-```
-
-## Arguments
-
-- `sw:progress` - Show all active increments
-- `sw:progress 0042` - Show specific increment details (partial ID match supported)
-
-## Related Commands
-
-- `sw:done <id>` - Close increment after review
-- `sw:increment` - Start new work

package/plugins/specweave/commands/qa.md

@@ -1,295 +0,0 @@
----
-description: Run quality assessment on a SpecWeave increment with risk scoring and quality gate decisions
----
-
-# sw:qa - Quality Assessment Command
-
-**IMPORTANT**: You MUST invoke the CLI `specweave qa` command using the Bash tool. The slash command provides guidance and orchestration only.
-
-## Purpose
-
-Run comprehensive quality assessment on an increment using:
-- ✅ **Gate 1: Rule-based validation** (130+ automated checks)
-- ✅ **Gate 2: LLM-as-Judge** (AI quality assessment with chain-of-thought reasoning)
-- ✅ **Gate 3: Risk scoring** (BMAD Probability × Impact quantitative assessment)
-- ✅ **Quality gate decisions** (PASS/CONCERNS/FAIL)
-
-## LLM-as-Judge Pattern
-
-This command implements the **LLM-as-Judge** pattern - an established AI/ML evaluation technique where an LLM evaluates outputs using structured reasoning.
-
-**How it works:**
-```
-┌─────────────────────────────────────────────────────────────┐
-│                    LLM-as-Judge Gate                        │
-├─────────────────────────────────────────────────────────────┤
-│  Input: spec.md, plan.md, tasks.md                         │
-│                                                             │
-│  Process:                                                   │
-│  1. Chain-of-thought analysis (7 dimensions)               │
-│  2. Evidence-based scoring (0-100 per dimension)           │
-│  3. Risk identification (BMAD P×I formula)                 │
-│  4. Formal verdict (PASS/CONCERNS/FAIL)                    │
-│                                                             │
-│  Output: Structured quality report with:                   │
-│  - Blockers (MUST fix)                                     │
-│  - Concerns (SHOULD fix)                                   │
-│  - Recommendations (NICE to fix)                           │
-└─────────────────────────────────────────────────────────────┘
-```
-
-**Why LLM-as-Judge?**
-- **Consistency**: Applies uniform evaluation criteria
-- **Depth**: Catches nuanced issues humans might miss
-- **Speed**: ~30 seconds vs hours of manual review
-- **Documented reasoning**: Explains WHY something is an issue
-
-## Usage
-
-```bash
-sw:qa <increment-id> [options]
-```
-
-### Examples
-
-```bash
-# Quick mode (default)
-sw:qa 0008
-
-# Pre-implementation check
-sw:qa 0008 --pre
-
-# Quality gate check (comprehensive)
-sw:qa 0008 --gate
-
-# Export blockers to tasks.md
-sw:qa 0008 --export
-
-# CI mode (exit 1 on FAIL)
-sw:qa 0008 --ci
-
-# Skip AI assessment (rule-based only)
-sw:qa 0008 --no-ai
-
-# Force run even if rule-based fails
-sw:qa 0008 --force
-```
-
-### Options
-
-- `--quick` - Quick mode (default) - Fast assessment with core checks
-- `--pre` - Pre-implementation mode - Check before starting work
-- `--gate` - Quality gate mode - Comprehensive check before closing
-- `--full` - Full multi-agent mode (Phase 3)
-- `--ci` - CI mode - Exit 1 on FAIL (for automation)
-- `--no-ai` - Skip AI assessment - Rule-based validation only (free, fast)
-- `--export` - Export blockers/concerns to tasks.md
-- `--force` - Force run even if rule-based validation fails
-- `-v, --verbose` - Show recommendations in addition to blockers/concerns
-
-## What It Does
-
-### Step 1: Rule-Based Validation (Always First, Always Free)
-
-The command runs 120+ validation checks on increment files:
-- ✅ File existence (spec.md, plan.md, tasks.md)
-- ✅ YAML frontmatter structure
-- ✅ AC-ID traceability (spec.md → tasks.md)
-- ✅ Link integrity
-- ✅ Format consistency
-
-**If rule-based fails** → Stop (don't waste AI tokens) unless `--force` flag used
-
-### Step 2: AI Quality Assessment (Optional, skip with `--no-ai`)
-
-**IMPORTANT**: This step uses the `increment-quality-judge-v2` **skill** (auto-activated).
-
-The skill provides guidance and the CLI handles execution:
-```bash
-# CLI invokes quality assessment directly
-specweave qa 0008 --pre
-```
-
-**DO NOT spawn agents for quality assessment** - use the CLI command which handles everything internally.
-
-The assessment evaluates:
-- **7 Dimensions**:
-  1. Clarity (18% weight)
-  2. Testability (22% weight)
-  3. Completeness (18% weight)
-  4. Feasibility (13% weight)
-  5. Maintainability (9% weight)
-  6. Edge Cases (9% weight)
-  7. **Risk Assessment (11% weight)**
-
-**Risk Assessment** uses quantitative method:
-- Probability (0.0-1.0) × Impact (1-10) = Risk Score (0.0-10.0)
-- 4 categories: Security, Technical, Implementation, Operational
-- Severity: CRITICAL (≥9.0), HIGH (6.0-8.9), MEDIUM (3.0-5.9), LOW (<3.0)
-
-### Step 3: Quality Gate Decision
-
-Based on thresholds:
-
-**FAIL** if any:
-- Risk score ≥ 9.0 (CRITICAL)
-- Test coverage < 60%
-- Spec quality < 50
-- Critical security vulnerabilities ≥ 1
-
-**CONCERNS** if any:
-- Risk score 6.0-8.9 (HIGH)
-- Test coverage < 80%
-- Spec quality < 70
-- High security vulnerabilities ≥ 1
-
-**PASS** otherwise
-
-### Step 4: Display Report
-
-Show results with:
-- 🟢 PASS / 🟡 CONCERNS / 🔴 FAIL decision
-- Blockers (MUST fix)
-- Concerns (SHOULD fix)
-- Recommendations (NICE to fix, with `--verbose`)
-- Spec quality scores (7 dimensions)
-- Summary (duration, tokens, cost)
-
-### Step 5: Export (Optional)
-
-If `--export` flag provided:
-- Append blockers/concerns to tasks.md
-- Add priority (P0 for blockers, P1 for concerns)
-- Include mitigation strategies
-
-## Implementation
-
-**When user runs `/qa <increment-id>`**:
-
-1. **Parse and normalize arguments**
-   ```typescript
-   let incrementId = args[0]; // e.g., "0008" or "0008-feature-name"
-
-   // Normalize increment ID
-   if (incrementId.includes('-')) {
-     // Extract numeric portion: "0008-feature-name" → "0008"
-     incrementId = incrementId.split('-')[0];
-   }
-   // Convert to 4-digit format: "8" → "0008"
-   incrementId = incrementId.padStart(4, '0');
-
-   const options = parseOptions(args.slice(1));
-   ```
-   Both formats work: `sw:qa 0153` or `sw:qa 0153-feature-name`
-
-2. **Invoke CLI command via Bash tool**
-   ```bash
-   specweave qa 0008 --pre --export
-   ```
-
-3. **CLI handles everything**:
-   - Rule-based validation
-   - AI assessment invocation
-   - Quality gate decision
-   - Report display
-   - Export to tasks.md
-
-4. **Return result to user**
-   - Show CLI output (already formatted)
-   - Suggest next steps based on decision
-
-## Modes Explained
-
-### Quick Mode (Default)
-
-**Use when**: Quick check during development
-**Checks**: Rule-based + AI spec quality + risk assessment
-**Time**: ~30 seconds
-**Cost**: ~$0.025-$0.050
-
-### Pre-Implementation Mode (`--pre`)
-
-**Use when**: Before starting increment work
-**Checks**: All quick mode checks + architecture review
-**Time**: ~1 minute
-**Cost**: ~$0.05-$0.10
-
-### Quality Gate Mode (`--gate`)
-
-**Use when**: Before closing increment (via `sw:done`)
-**Checks**: All pre-implementation checks + test coverage + security audit
-**Time**: ~2-3 minutes
-**Cost**: ~$0.10-$0.20
-
-### Full Multi-Agent Mode (`--full`, Phase 3)
-
-**Use when**: Comprehensive audit for critical increments
-**Checks**: 6 specialized subagents in parallel
-**Time**: ~5 minutes
-**Cost**: ~$0.50-$1.00
-
-## Cost Breakdown
-
-| Mode | Tokens | Cost (USD) | Time |
-|------|--------|------------|------|
-| Quick | ~2,500 | ~$0.025 | 30s |
-| Pre | ~5,000 | ~$0.050 | 1m |
-| Gate | ~10,000 | ~$0.100 | 2-3m |
-| Full | ~50,000 | ~$0.500 | 5m |
-
-**Optimization**: Use Haiku model by default (cheapest, fastest)
-
-## Exit Codes (for CI)
-
-When `--ci` flag used:
-- **Exit 0**: PASS or CONCERNS (warning, but not blocking)
-- **Exit 1**: FAIL (blocking issues found)
-
-**CI Integration Example**:
-```yaml
-# .github/workflows/qa-check.yml
-- name: Run QA Check
-  run: specweave qa ${{ env.INCREMENT_ID }} --gate --ci
-```
-
-## Error Handling
-
-**Common errors**:
-- ❌ Increment not found → Check ID format (4 digits: 0001, 0008)
-- ❌ Missing files → Run `sw:inc` to create increment first
-- ❌ Rule-based fails → Fix validation errors before AI assessment
-- ❌ AI timeout → Retry with `--quick` mode or `--no-ai`
-
-## Integration Points
-
-**Auto-invoked by**:
-- `sw:done` - Runs `--gate` mode before closing increment
-- Post-task-completion hook (optional) - Runs `--quick` mode after tasks complete
-
-**Manual invocation**:
-- During development - `/qa 0008` for quick checks
-- Before commit - `/qa 0008 --pre` to catch issues early
-- Before PR - `/qa 0008 --gate --export` for comprehensive check
-
-## Best Practices
-
-1. **Run early and often** - Use `--quick` during development
-2. **Fix blockers immediately** - Don't proceed with FAIL decision
-3. **Address concerns before release** - CONCERNS = should fix
-4. **Use risk scores to prioritize** - Fix CRITICAL (≥9.0) risks first
-5. **Export to tasks.md** - Convert blockers/concerns to actionable tasks
-6. **CI integration** - Block PRs with FAIL decision
-
-## Related
-
-- **Skill**: `increment-quality-judge-v2` (7 dimensions with risk assessment)
-- **Command**: `sw:done` (auto-runs QA gate)
-- **CLI**: `specweave qa` (direct invocation)
-- **Types**: `src/core/qa/types.ts` (TypeScript definitions)
-- **Tests**: `tests/unit/qa/` (58 test cases, 100% passing)
-
-## Example Session
-
-```
-User: sw:qa 0008
-```