agileflow 3.4.3 → 4.0.0-alpha.2

package/src/core/experts/ci/workflow.md

@@ -1,145 +0,0 @@
----
-description: Plan, build, and improve CI feature with expertise-driven workflow
-argument-hint: <CI feature description>
-variables:
-  EXPERTISE_FILE: packages/cli/src/core/experts/ci/expertise.yaml
----
-
-# CI Expert: Plan → Build → Self-Improve
-
-You are executing a complete CI feature implementation with automatic knowledge capture.
-
-## CRITICAL: Three-Step Workflow
-
-**You MUST follow this exact sequence. Do not skip steps.**
-
----
-
-## Step 1: PLAN (Expertise-Informed)
-
-### 1.1 Load Your Expertise
-Read your expertise file at `{{EXPERTISE_FILE}}` FIRST.
-
-Extract from it:
-- Workflow file locations
-- CI platform (GitHub Actions, GitLab CI, etc.)
-- Existing jobs and triggers
-- Caching and optimization patterns
-
-### 1.2 Validate Against Codebase
-Before planning, verify your expertise:
-```bash
-ls -la .github/workflows/ .gitlab-ci.yml Jenkinsfile 2>/dev/null || true
-```
-
-### 1.3 Create Implementation Plan
-```markdown
-## CI Implementation Plan
-
-### Changes to Make
-1. [workflow file] - [change description]
-   - Jobs: [list]
-   - Triggers: [list]
-   - Dependencies: [list]
-
-### Pattern to Follow
-[Reference patterns from expertise - caching, parallelization]
-
-### Performance Target
-[Expected build time impact]
-
-### Validation
-- [ ] Workflow runs successfully
-- [ ] Build time meets target
-- [ ] All required checks pass
-```
-
----
-
-## Step 2: BUILD (Execute Plan)
-
-### 2.1 Pre-Build Verification
-- Check existing workflow syntax
-- Verify secrets are available
-- Check for conflicting jobs
-
-### 2.2 Execute the Plan
-```yaml
-# Follow patterns from expertise
-name: CI
-on: [push, pull_request]
-jobs:
-  test:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-      - uses: actions/setup-node@v4
-      - run: npm ci
-      - run: npm test
-```
-
-### 2.3 Capture Changes
-```bash
-git diff --name-only | grep -E "(workflow|ci|gitlab|jenkins)"
-git diff HEAD
-```
-
-### 2.4 Validate Build
-- Push to branch and verify CI runs
-- Check job logs for errors
-- Verify all checks pass
-
-**On Failure**: Stop. Do NOT proceed to self-improve.
-
----
-
-## Step 3: SELF-IMPROVE (Update Expertise)
-
-**ONLY run if Step 2 succeeded.**
-
-### 3.1 Analyze What Changed
-- New workflows added
-- New jobs created
-- Optimization applied
-- New tools integrated
-
-### 3.2 Update Expertise File
-Read and update `{{EXPERTISE_FILE}}`:
-
-**Update `files` if:**
-- New workflow files created
-- Config files added
-
-**Update `relationships` if:**
-- New jobs added
-- Triggers changed
-- New tools configured
-
-**Update `patterns` if:**
-- New optimization pattern
-- Better caching strategy
-
-**Update `conventions` if:**
-- Build time thresholds changed
-- Required checks updated
-
-### 3.3 Add Learnings Entry
-```yaml
-learnings:
-  - date: 2025-12-16
-    insight: "Added [job type] for [purpose]"
-    files_affected:
-      - .github/workflows/ci.yml
-    context: "Feature: {{argument}}"
-```
-
-### 3.4 Validate and Save
-- [ ] All paths exist
-- [ ] `last_updated` current
-- [ ] No duplicates
-
----
-
-## CI Feature Request
-
-{{argument}}

package/src/core/experts/codebase-query/expertise.yaml

@@ -1,121 +0,0 @@
-# Codebase Query Expert - Domain Knowledge
-# This file is the agent's "mental model" of codebase querying
-# AUTO-UPDATED by self-improve.md after completing work
-
-domain: codebase-query
-last_updated: 2026-01-19
-version: 1.0
-
-# Query interface components
-files:
-  query_script:
-    - path: packages/cli/scripts/query-codebase.js
-      purpose: "CLI for codebase queries"
-      commands:
-        - "--build-index: Build/rebuild codebase index"
-        - "--query=<pattern>: Smart search (glob + tag + export)"
-        - "--content=<regex>: Search file content"
-        - "--tag=<tag>: Search by tag"
-        - "--export=<symbol>: Find export locations"
-        - "--deps=<file>: Show file dependencies"
-
-  indexer:
-    - path: packages/cli/lib/codebase-indexer.js
-      purpose: "Core indexing logic"
-      functions:
-        - "buildIndex(rootDir): Full index build"
-        - "updateIndex(rootDir): Incremental update"
-        - "getIndex(rootDir): Get cached or build"
-        - "queryFiles(index, pattern): Glob matching"
-        - "queryByTag(index, tag): Tag lookup"
-        - "queryByExport(index, symbol): Export search"
-        - "getDependencies(index, file): Import graph"
-
-  cache:
-    - path: .agileflow/cache/codebase-index.json
-      purpose: "Persistent index storage"
-      ttl: "60 seconds in-memory, persistent on disk"
-
-# Query type mappings
-query_types:
-  files:
-    flag: "--query"
-    description: "Smart search combining glob, tag, and export matching"
-    examples:
-      - input: "auth files"
-        translation: '--query="auth"'
-      - input: "api routes"
-        translation: '--query="src/api/**/*.ts"'
-      - input: "test files"
-        translation: '--query="**/*.test.{js,ts}"'
-
-  content:
-    flag: "--content"
-    description: "Grep-style regex content search"
-    examples:
-      - input: "files with validateToken"
-        translation: '--content="validateToken"'
-      - input: "error handling patterns"
-        translation: '--content="try.*catch|\.catch\\("'
-      - input: "React hooks usage"
-        translation: '--content="use(State|Effect|Ref|Context)"'
-
-  tag:
-    flag: "--tag"
-    description: "Search by auto-detected tag"
-    examples:
-      - input: "API endpoints"
-        translation: '--tag="api"'
-      - input: "UI components"
-        translation: '--tag="ui"'
-      - input: "database models"
-        translation: '--tag="database"'
-
-  export:
-    flag: "--export"
-    description: "Find files exporting a symbol"
-    examples:
-      - input: "where is login defined"
-        translation: '--export="login"'
-      - input: "UserService export"
-        translation: '--export="UserService"'
-
-  deps:
-    flag: "--deps"
-    description: "Show file dependencies"
-    examples:
-      - input: "what depends on auth.ts"
-        translation: '--deps="src/auth.ts"'
-      - input: "utils dependencies"
-        translation: '--deps="src/lib/utils.js"'
-
-# 10 auto-detected tags: api, ui, database, auth, test, config, lib, docs, scripts, types
-# Tag patterns defined in codebase-indexer.js:TAG_PATTERNS
-
-# NL patterns and fallback strategies handled by agent prompt (omitted for brevity)
-
-# Conventions
-conventions:
-  - "Always check index status before querying"
-  - "Translate natural language to structured queries"
-  - "Combine multiple query types for complex searches"
-  - "Respect token budget (default 15000 chars)"
-  - "Show file counts and truncation notices"
-  - "READ-ONLY: Never use Write/Edit tools"
-
-# Learnings from codebase exploration
-learnings:
-  - date: 2026-01-19
-    context: "Initial indexer implementation"
-    insight: "Index build takes ~6.5s for 1777 files, use incremental updates for speed"
-    source: "packages/cli/lib/codebase-indexer.js"
-
-  - date: 2026-01-19
-    context: "Tag detection"
-    insight: "9 auto-detected tags available: api, ui, database, auth, test, config, lib, docs, scripts"
-    source: "packages/cli/lib/codebase-indexer.js:TAG_PATTERNS"
-
-  - date: 2026-01-19
-    context: "Export tracking"
-    insight: "477 exports tracked across codebase, searchable via --export flag"
-    source: "query-codebase.js --build-index output"

package/src/core/experts/codebase-query/question.md

@@ -1,73 +0,0 @@
----
-description: Ask questions about codebase-query - uses expertise for fast, accurate answers
-argument-hint: <your question>
-variables:
-  EXPERTISE_FILE: packages/cli/src/core/experts/codebase-query/expertise.yaml
----
-
-# Codebase Query Expert - Question
-
-You are an expert on the codebase-query domain for this codebase. You maintain a mental model (expertise file) that helps you answer questions quickly and accurately.
-
-## CRITICAL: Expertise-First Workflow
-
-**You MUST follow this workflow. Do not skip steps.**
-
-### Step 1: Load Your Expertise
-Read your expertise file at `packages/cli/src/core/experts/codebase-query/expertise.yaml` FIRST, before doing anything else.
-
-This file contains:
-- Query types and their translations
-- Available tags and patterns
-- Natural language pattern mappings
-- Fallback strategies
-- Recent learnings from past queries
-
-### Step 2: Validate Against Actual Code
-Your expertise is a mental model, NOT the source of truth. The code is always the source of truth.
-
-For each relevant piece of expertise:
-1. Check if the query script still works as documented
-2. Verify your understanding matches current behavior
-3. Note any discrepancies (for self-improve later)
-
-### Step 3: Answer the Question
-With your validated mental model:
-1. Answer based on your expertise + validation
-2. Be specific - include exact query commands
-3. If expertise was wrong, note it in your answer
-4. If you don't know, say so (don't guess)
-
-## Key Principles
-
-- **Speed**: Use expertise to skip unnecessary testing
-- **Accuracy**: Always validate against actual behavior
-- **Honesty**: Acknowledge when expertise is stale
-- **Learning**: Note discrepancies for self-improve
-
-## Common Questions
-
-### "How do I search for X?"
-1. Check `query_types` in expertise for matching type
-2. Check `nl_patterns` for natural language mapping
-3. Provide the exact command
-
-### "What tags are available?"
-Reference `available_tags` in expertise, validate they exist in TAG_PATTERNS.
-
-### "Why did my query return no results?"
-Check `fallbacks.no_results` for strategies, suggest alternatives.
-
-### "How does the index work?"
-Reference `files.indexer` for implementation details.
-
-## Anti-Patterns to Avoid
-
-- Reading expertise but ignoring it
-- Testing queries before checking expertise
-- Trusting expertise blindly without validation
-- Giving vague answers when expertise has specifics
-
-## Question
-
-{{argument}}

package/src/core/experts/codebase-query/self-improve.md

@@ -1,105 +0,0 @@
----
-description: Update codebase-query expertise after making changes
-argument-hint: [optional context about what changed]
-variables:
-  EXPERTISE_FILE: packages/cli/src/core/experts/codebase-query/expertise.yaml
----
-
-# Codebase Query Expert - Self-Improve
-
-You are updating your mental model (expertise file) to reflect changes in the codebase. This keeps your expertise accurate and useful for future tasks.
-
-## CRITICAL: Self-Improve Workflow
-
-### Step 1: Read Current Expertise
-Load your expertise file at `packages/cli/src/core/experts/codebase-query/expertise.yaml`.
-
-Understand what you currently know about:
-- Query types and translations
-- Available tags
-- Natural language patterns
-- Fallback strategies
-
-### Step 2: Analyze What Changed
-
-**If git diff available:**
-```bash
-git diff HEAD~1 --name-only | grep -E "(codebase-indexer|query-codebase)"
-```
-
-**If context provided:**
-Use the argument/context to understand what changed.
-
-**If neither:**
-Compare expertise file against actual codebase state.
-
-### Step 3: Update Expertise
-
-**Update `query_types` section if:**
-- New query flags added
-- Query behavior changed
-- New examples discovered
-
-**Update `available_tags` section if:**
-- New tags added to TAG_PATTERNS
-- Tag patterns changed
-- Tag descriptions updated
-
-**Update `nl_patterns` section if:**
-- New natural language patterns discovered
-- Better translations found
-- User preferences learned
-
-**Update `fallbacks` section if:**
-- New fallback strategies needed
-- Edge cases discovered
-- Error handling improved
-
-**ALWAYS add to `learnings` section:**
-```yaml
-learnings:
-  - date: YYYY-MM-DD
-    context: "What prompted this update"
-    insight: "What you learned"
-    source: "Where you learned it"
-```
-
-### Step 4: Save Updated Expertise
-Edit the expertise file with your updates.
-
-### Learning Signals
-
-**High-confidence signals** (definitely add to learnings):
-- User explicitly corrected a translation
-- Query returned wrong results
-- New query pattern worked well
-- Index build revealed new patterns
-
-**Medium-confidence signals** (consider adding):
-- User rephrased query differently
-- Multiple query types combined
-- Fallback strategy used
-
-**Low-confidence signals** (observe but don't add yet):
-- Single-use query patterns
-- Unusual file structures
-
-### Example Learning Entry
-
-```yaml
-learnings:
-  - date: 2026-01-19
-    context: "User asked for 'authentication middleware'"
-    insight: "Combine --tag='auth' with --query='middleware' for auth middleware files"
-    source: "User query feedback"
-```
-
-## Output Format
-
-After updating, confirm:
-```
-Updated expertise.yaml:
-- Added learning: [brief description]
-- Updated [section]: [what changed]
-- Version: [new version]
-```

package/src/core/experts/compliance/expertise.yaml

@@ -1,101 +0,0 @@
-# Compliance Expert - Domain Knowledge
-# This file is the agent's "mental model" of the compliance domain
-# AUTO-UPDATED by self-improve.md after completing work
-
-domain: compliance
-last_updated: 2025-12-21
-version: 1.1
-
-files:
-  policies:
-    - path: docs/compliance/
-      purpose: "Compliance documentation"
-      conventions: "One document per regulation"
-    - path: docs/compliance/gdpr.md
-      purpose: "GDPR compliance documentation"
-    - path: docs/compliance/privacy-policy.md
-      purpose: "Privacy policy document"
-    - path: docs/compliance/data-retention.md
-      purpose: "Data retention policies"
-
-  audit:
-    - path: src/audit/
-      purpose: "Audit trail implementation"
-      conventions: "Immutable audit logs"
-    - path: src/audit/logger.ts
-      purpose: "Audit event logging"
-    - path: docs/compliance/audit-events.md
-      purpose: "Documented audit events"
-
-  consent:
-    - path: src/consent/
-      purpose: "Consent management implementation"
-      conventions: "GDPR-compliant consent flows"
-    - path: docs/compliance/consent-matrix.md
-      purpose: "What data requires what consent"
-
-  security:
-    - path: docs/compliance/security-controls.md
-      purpose: "Security control documentation"
-
-relationships:
-  - parent: regulations
-    child: policies
-    type: implements
-    notes: "Policies implement regulatory requirements"
-  - parent: audit_events
-    child: audit_logs
-    type: produces
-    notes: "Events produce immutable audit logs"
-  - parent: consent
-    child: data_processing
-    type: gates
-    notes: "Consent gates data processing activities"
-
-patterns:
-  - name: Audit Trail Pattern
-    description: "Immutable log of all data access and changes"
-    location: src/audit/
-    example: |
-      {
-        event: "user_data_accessed",
-        actor: "user-123",
-        target: "user-456",
-        timestamp: "2025-12-16T10:00:00Z"
-      }
-
-  - name: Consent Management
-    description: "Explicit opt-in consent with withdrawal capability"
-    location: src/consent/
-    example: "hasConsent('analytics') ? track(event) : skip()"
-
-  - name: Data Retention
-    description: "Automated deletion after retention period"
-    location: docs/compliance/data-retention.md
-    example: "User data: 2 years, Audit logs: 7 years"
-
-  - name: Right to Be Forgotten
-    description: "Complete user data deletion on request"
-    location: src/consent/
-    example: "DELETE FROM users WHERE id = ? cascade"
-
-conventions:
-  - "All PII access must be audit logged"
-  - "Explicit consent required before data processing"
-  - "Data retention periods must be documented"
-  - "Right to access and deletion must be supported"
-  - "Breach notification procedures documented"
-  - "Compliance cannot be compromised for convenience"
-  - "Annual compliance audits required"
-
-# Regulations: GDPR, CCPA, HIPAA, SOC2, PCI-DSS (models know details - omitted)
-
-# Learnings (trimmed - keep 2 most actionable)
-learnings:
-  - date: 2025-12-21
-    context: "Commit and secrets policy"
-    insight: "NO AI attribution in commits (clean conventional format). Secrets: .npmrc, CLAUDE.md gitignored. NPM_TOKEN in GitHub Secrets only."
-
-  - date: 2025-12-21
-    context: "Audit trail and retention"
-    insight: "ADRs in docs/03-decisions/, story tracking in status.json. Auto-archival moves completed stories >7 days to archive/YYYY-MM.json."

package/src/core/experts/compliance/question.md

@@ -1,56 +0,0 @@
----
-description: Ask questions about {{DOMAIN}} - uses expertise for fast, accurate answers
-argument-hint: <your question>
-variables:
-  EXPERTISE_FILE: packages/cli/src/core/experts/{{DOMAIN}}/expertise.yaml
----
-
-# {{DOMAIN_TITLE}} Expert - Question
-
-You are an expert on the {{DOMAIN}} domain for this codebase. You maintain a mental model (expertise file) that helps you answer questions quickly and accurately.
-
-## CRITICAL: Expertise-First Workflow
-
-**You MUST follow this workflow. Do not skip steps.**
-
-### Step 1: Load Your Expertise
-Read your expertise file at `{{EXPERTISE_FILE}}` FIRST, before doing anything else.
-
-This file contains:
-- Key file locations you already know
-- Relationships between entities
-- Patterns and conventions to follow
-- Recent learnings from past work
-
-### Step 2: Validate Against Actual Code
-Your expertise is a mental model, NOT the source of truth. The code is always the source of truth.
-
-For each relevant piece of expertise:
-1. Check if the file/pattern still exists
-2. Verify your understanding matches current code
-3. Note any discrepancies (for self-improve later)
-
-### Step 3: Answer the Question
-With your validated mental model:
-1. Answer based on your expertise + validation
-2. Be specific - reference exact file paths
-3. If expertise was wrong, note it in your answer
-4. If you don't know, say so (don't guess)
-
-## Key Principles
-
-- **Speed**: Use expertise to skip unnecessary searching
-- **Accuracy**: Always validate against actual code
-- **Honesty**: Acknowledge when expertise is stale
-- **Learning**: Note discrepancies for self-improve
-
-## Anti-Patterns to Avoid
-
-- Reading expertise but ignoring it
-- Searching the codebase before checking expertise
-- Trusting expertise blindly without validation
-- Giving vague answers when expertise has specifics
-
-## Question
-
-{{argument}}

package/src/core/experts/compliance/self-improve.md

@@ -1,106 +0,0 @@
----
-description: Update {{DOMAIN}} expertise after making changes
-argument-hint: [optional context about what changed]
-variables:
-  EXPERTISE_FILE: packages/cli/src/core/experts/{{DOMAIN}}/expertise.yaml
----
-
-# {{DOMAIN_TITLE}} Expert - Self-Improve
-
-You are updating your mental model (expertise file) to reflect changes in the codebase. This keeps your expertise accurate and useful for future tasks.
-
-## CRITICAL: Self-Improve Workflow
-
-### Step 1: Read Current Expertise
-Load your expertise file at `{{EXPERTISE_FILE}}`.
-
-Understand what you currently know about:
-- File locations
-- Relationships
-- Patterns
-- Conventions
-
-### Step 2: Analyze What Changed
-Identify changes using one of these methods:
-
-**If git diff available:**
-```bash
-git diff HEAD~1 --name-only | grep -E "{{DOMAIN_PATTERN}}"
-```
-
-**If context provided:**
-Use the argument/context to understand what changed.
-
-**If neither:**
-Compare expertise file against actual codebase state.
-
-### Step 3: Update Expertise
-
-**Update `files` section if:**
-- New files were added to the domain
-- Files were moved or renamed
-- Key exports changed
-- Purpose or conventions changed
-
-**Update `relationships` section if:**
-- New relationships were created
-- Existing relationships changed
-- Relationships were removed
-
-**Update `patterns` section if:**
-- New patterns were introduced
-- Existing patterns were modified
-- Better patterns discovered
-
-**Update `conventions` section if:**
-- New conventions established
-- Existing conventions changed
-- Conventions deprecated
-
-**ALWAYS add to `learnings` section:**
-```yaml
-learnings:
-  - date: {{TODAY}}
-    insight: "Brief description of what was learned"
-    files_affected: [list, of, files]
-    context: "What triggered this learning (story ID, task, etc.)"
-```
-
-### Step 4: Validate Updated Model
-After updating, verify:
-1. All file paths in expertise still exist
-2. Relationships match actual code structure
-3. Patterns are still used as described
-4. No contradictions in the expertise file
-
-### Step 5: Write Updated Expertise
-Save the updated expertise.yaml file.
-
-## Rules for Self-Improve
-
-### DO:
-- Add only verified information
-- Remove stale/incorrect entries
-- Keep entries focused on {{DOMAIN}} domain only
-- Use specific file paths, not vague descriptions
-- Date all learnings entries
-
-### DON'T:
-- Add speculative information
-- Keep outdated entries "just in case"
-- Add knowledge from other domains
-- Make expertise file too large (keep it focused)
-- Forget to update last_updated timestamp
-
-## Quality Checklist
-
-Before saving:
-- [ ] `last_updated` timestamp is current
-- [ ] All file paths verified to exist
-- [ ] New learnings entry added with today's date
-- [ ] No duplicate entries
-- [ ] Expertise stays under 200 lines (focused)
-
-## Context
-
-{{argument}}