@miller-tech/uap 1.0.0

package/templates/CLAUDE_MEMORY.template.md

@@ -0,0 +1,131 @@
+# Memory System Guide Template
+
+**Version**: 1.0.0
+**Last Updated**: {{STRUCTURE_DATE}}
+
+---
+
+## Memory Layers
+
+| Layer        | Storage                   | Capacity                 | Latency |
+| ------------ | ------------------------- | ------------------------ | ------- |
+| L1 Working   | SQLite `memories`         | {{SHORT_TERM_LIMIT}} max | <1ms    |
+| L2 Session   | SQLite `session_memories` | Current session          | <5ms    |
+| L3 Semantic  | {{LONG_TERM_BACKEND}}     | Unlimited                | ~50ms   |
+| L4 Knowledge | SQLite `entities/rels`    | Graph                    | <20ms   |
+
+**Database**: `./{{MEMORY_DB_PATH}}`
+**Vector DB**: {{LONG_TERM_BACKEND}} at `{{LONG_TERM_ENDPOINT}}`
+
+---
+
+## Working Memory (L1)
+
+Quick actions stored directly in SQLite.
+
+```bash
+# Store action
+sqlite3 ./{{MEMORY_DB_PATH}} "INSERT INTO memories (timestamp,type,content) VALUES (datetime('now'),'action','...');"
+
+# Query recent
+sqlite3 ./{{MEMORY_DB_PATH}} "SELECT * FROM memories ORDER BY id DESC LIMIT 10;"
+```
+
+---
+
+## Session Memory (L2)
+
+Session-specific context for current task.
+
+```bash
+# Store decision
+sqlite3 ./{{MEMORY_DB_PATH}} "INSERT INTO session_memories (session_id,timestamp,type,content,importance) VALUES ('current',datetime('now'),'decision','...',7);"
+```
+
+---
+
+## Semantic Memory (L3)
+
+Long-term lessons stored in Qdrant vector database.
+
+```bash
+# Store lesson
+{{MEMORY_STORE_CMD}} lesson "..." --tags t1,t2 --importance 8
+
+# Query relevant lessons
+{{MEMORY_QUERY_CMD}} "security best practices"
+```
+
+---
+
+## Pattern RAG
+
+Patterns are retrieved dynamically from the `{{PATTERN_RAG_COLLECTION}}` collection.
+
+Top-2 relevant patterns are injected per task (score >= {{PATTERN_RAG_THRESHOLD}}).
+
+```bash
+# Query patterns
+{{PATTERN_RAG_QUERY_CMD}} "task description"
+
+# Re-index patterns
+{{PATTERN_RAG_INDEX_CMD}}
+
+# Check status
+uap patterns status
+```
+
+---
+
+## Pattern Files
+
+Patterns are defined in `.factory/patterns/`:
+
+```
+.factory/patterns/
+├── P12_output_existence.md
+├── P13_iterative_refinement.md
+├── ...
+├── IaC-Parity.md
+└── index.json
+```
+
+To add a new pattern:
+
+1. Create `P37_new_pattern.md` in `.factory/patterns/`
+2. Add entry to `index.json`
+3. Run `python agents/scripts/index_patterns.py`
+
+---
+
+## Reinforcement Learning
+
+Pattern effectiveness is tracked for self-improvement.
+
+```bash
+# View pattern effectiveness
+sqlite3 ./agents/data/memory/reinforcement.db "SELECT * FROM v_pattern_effectiveness;"
+
+# View recent outcomes
+sqlite3 ./agents/data/memory/reinforcement.db "SELECT * FROM v_recent_outcomes;"
+```
+
+---
+
+## Qdrant Setup
+
+```bash
+# Start Qdrant
+docker run -p 6333:6333 qdrant/qdrant
+
+# Or with persistence
+docker run -p 6333:6333 -v $(pwd)/qdrant_data:/qdrant/storage qdrant/qdrant
+```
+
+---
+
+## See Also
+
+- `.factory/patterns/` - Pattern definitions
+- `agents/scripts/index_patterns.py` - Pattern indexing
+- `agents/scripts/query_patterns.py` - Pattern query

package/templates/CLAUDE_WORKFLOWS.template.md

@@ -0,0 +1,139 @@
+# Workflows Guide Template
+
+**Version**: 1.0.0
+**Last Updated**: {{STRUCTURE_DATE}}
+
+---
+
+## Session Start
+
+```bash
+uap task ready
+sqlite3 ./{{MEMORY_DB_PATH}} "SELECT * FROM memories ORDER BY id DESC LIMIT 10;"
+uap agent status
+```
+
+---
+
+## Decision Loop
+
+```
+1. CLASSIFY  -> complexity? backup? tools?
+2. PROTECT   -> cp file file.bak (configs, DBs)
+3. MEMORY    -> query context + past failures
+4. PLAN      -> create TODO list of steps
+5. VALIDATE  -> review plan for gaps, security, feasibility
+6. WORK      -> implement (ALWAYS use worktree)
+7. REVIEW    -> self-review diff
+8. TEST      -> completion gates pass
+9. LEARN     -> store outcome
+```
+
+---
+
+## Worktree Workflow (MANDATORY)
+
+**ALL file changes MUST use a worktree.** No exceptions.
+
+```bash
+{{WORKTREE_CREATE_CMD}} <slug>
+cd {{WORKTREE_DIR}}/NNN-<slug>/
+git add -A && git commit -m "type: description"
+{{WORKTREE_PR_CMD}} <id>
+# After merge:
+{{WORKTREE_CLEANUP_CMD}} <id>  # MANDATORY
+```
+
+---
+
+## Testing Requirements
+
+1. Create worktree
+2. Update/create tests
+3. Run `{{TEST_COMMAND}}`
+4. Run linting: `{{LINT_COMMAND}}`
+5. Create PR
+
+---
+
+## Completion Gates
+
+**CANNOT say "done" until ALL gates pass.**
+
+### GATE 1: Output Existence
+
+```bash
+for f in $EXPECTED_OUTPUTS; do
+  [ -f "$f" ] && echo "ok $f" || echo "MISSING: $f"
+done
+```
+
+### GATE 2: Constraint Compliance
+
+Extract ALL constraints from task:
+
+- "exactly", "only", "must be", "no more than"
+- Verify EACH constraint
+
+### GATE 3: Tests Pass
+
+```bash
+{{TEST_COMMAND}}
+```
+
+If < 100%: iterate (fix specific failure, re-run).
+
+---
+
+## Completion Checklist
+
+```
+☐ Tests pass
+☐ Lint pass
+☐ Worktree used (MANDATORY)
+☐ Worktree cleaned up after PR merge (MANDATORY)
+☐ Self-review completed
+☐ Memory updated
+☐ PR created
+☐ Reviews passed
+☐ No secrets in code
+```
+
+---
+
+## Parallel Review Protocol
+
+**Before ANY commit/PR, invoke quality droids in PARALLEL:**
+
+```bash
+Task(subagent_type: "code-quality-reviewer", prompt: "Review: <files>")
+Task(subagent_type: "security-code-reviewer", prompt: "Audit: <files>")
+```
+
+---
+
+## Automatic Triggers
+
+| Pattern         | Action                           |
+| --------------- | -------------------------------- |
+| work request    | `uap task create --type task`    |
+| bug report      | `uap task create --type bug`     |
+| feature request | `uap task create --type feature` |
+| ANY file change | **create worktree (MANDATORY)**  |
+
+---
+
+## Completion Protocol
+
+```
+MERGE -> CLEANUP WORKTREE -> DEPLOY -> MONITOR -> FIX (iterate until 100%)
+```
+
+**Never "done" until:** PR merged + worktree cleaned up + deployed + verified working
+
+---
+
+## See Also
+
+- `CLAUDE_CODING.md` - Coding standards
+- `.factory/droids/worktree-manager.md` - Worktree automation (if applicable)

package/templates/PROJECT.template.md

@@ -0,0 +1,209 @@
+<!--
+  PROJECT.md Template - Project-Specific Configuration
+  
+  This file contains ALL project-specific content that gets merged into CLAUDE.md.
+  By separating project content from the universal template:
+  
+  1. Template upgrades are SEAMLESS - just update CLAUDE.template.md
+  2. No merge conflicts - project content stays in PROJECT.md
+  3. Project knowledge persists across template versions
+  4. Easy to review what's project-specific vs universal
+  
+  Usage:
+  - CLAUDE.md imports this file via {{> PROJECT}}
+  - Generator reads PROJECT.md and injects into template
+  - Only edit this file for project-specific content
+-->
+
+# {{PROJECT_NAME}} - Project Configuration
+
+## Project Overview
+
+{{#if DESCRIPTION}}
+> {{DESCRIPTION}}
+{{/if}}
+
+**Repository**: `{{PROJECT_NAME}}`
+**Default Branch**: `{{DEFAULT_BRANCH}}`
+**Last Updated**: {{STRUCTURE_DATE}}
+
+---
+
+## Repository Structure
+
+```
+{{PROJECT_NAME}}/
+{{{REPOSITORY_STRUCTURE}}}
+```
+
+---
+
+{{#if ARCHITECTURE_OVERVIEW}}
+## Architecture
+
+{{{ARCHITECTURE_OVERVIEW}}}
+
+{{/if}}
+{{#if CORE_COMPONENTS}}
+## Core Components
+
+{{{CORE_COMPONENTS}}}
+
+{{/if}}
+{{#if DATABASE_ARCHITECTURE}}
+## Database Architecture
+
+{{{DATABASE_ARCHITECTURE}}}
+
+{{/if}}
+{{#if AUTH_FLOW}}
+## Authentication Flow
+
+{{{AUTH_FLOW}}}
+
+{{/if}}
+---
+
+## Quick Reference
+
+{{#if CLUSTER_CONTEXTS}}
+### Clusters
+```bash
+{{{CLUSTER_CONTEXTS}}}
+```
+
+{{/if}}
+{{#if PROJECT_URLS}}
+### URLs
+{{{PROJECT_URLS}}}
+
+{{/if}}
+{{#if KEY_WORKFLOWS}}
+### Workflows
+```
+{{{KEY_WORKFLOWS}}}
+```
+
+{{/if}}
+{{#if ESSENTIAL_COMMANDS}}
+### Commands
+```bash
+{{{ESSENTIAL_COMMANDS}}}
+```
+
+{{/if}}
+---
+
+{{#if LANGUAGE_DROIDS}}
+## Language Droids
+| Droid | Purpose |
+|-------|---------|
+{{{LANGUAGE_DROIDS}}}
+
+{{/if}}
+{{#if DISCOVERED_SKILLS}}
+## Available Skills
+| Skill | Purpose |
+|-------|---------|
+{{{DISCOVERED_SKILLS}}}
+
+{{/if}}
+{{#if MCP_PLUGINS}}
+## MCP Plugins
+| Plugin | Purpose |
+|--------|---------|
+{{{MCP_PLUGINS}}}
+
+{{/if}}
+---
+
+{{#if HAS_INFRA}}
+## Infrastructure
+
+{{#if HAS_PIPELINE_POLICY}}
+**ALL infrastructure changes go through CI/CD pipelines. No exceptions.**
+
+### Approved Operations
+```bash
+gh workflow run ops-approved-operations.yml \
+  -f operation=restart \
+  -f target=deployment/my-service \
+  -f namespace=production
+```
+
+### PROHIBITED Commands
+```bash
+# ❌ NEVER run locally
+terraform apply
+terraform destroy
+kubectl apply -f ...
+kubectl delete ...
+```
+{{else}}
+{{{INFRA_WORKFLOW}}}
+{{/if}}
+
+{{/if}}
+---
+
+## Testing
+
+1. Create worktree: `{{WORKTREE_CREATE_CMD}} <slug>`
+2. Update/create tests
+3. Run tests: `{{TEST_COMMAND}}`
+4. Run lint: `{{LINT_COMMAND}}`
+5. Create PR: `{{WORKTREE_PR_CMD}} <id>`
+
+---
+
+## Config Files
+| File | Purpose |
+|------|---------|
+{{#if KEY_CONFIG_FILES}}
+{{{KEY_CONFIG_FILES}}}
+{{else}}
+| `README.md` | Project documentation |
+| `.uap.json` | UAP agent memory configuration |
+| `package.json` | Node.js project configuration |
+{{/if}}
+
+{{#if HAS_PIPELINE_POLICY}}
+### Policy Documents
+| Document | Purpose |
+|----------|---------|
+| `docs/adr/ADR-0006-pipeline-only-infrastructure-changes.md` | Pipeline-only policy |
+
+{{/if}}
+---
+
+{{#if TROUBLESHOOTING}}
+## Troubleshooting
+{{{TROUBLESHOOTING}}}
+
+{{/if}}
+{{#if PREPOPULATED_KNOWLEDGE}}
+## Project Knowledge
+
+{{{PREPOPULATED_KNOWLEDGE}}}
+{{/if}}
+
+---
+
+## Completion Checklist
+
+```
+☐ Tests pass ({{TEST_COMMAND}})
+☐ Lint/typecheck pass ({{LINT_COMMAND}})
+☐ Worktree used (not {{DEFAULT_BRANCH}})
+☐ Memory updated
+☐ PR created
+☐ Parallel reviews passed
+{{#if HAS_INFRA}}
+☐ Terraform plan verified
+{{/if}}
+{{#if HAS_PIPELINE_POLICY}}
+☐ No manual kubectl commands (use pipelines)
+☐ No local terraform apply (use pipelines)
+{{/if}}
+☐ No secrets in code
+```

package/templates/SCHEMA.md

@@ -0,0 +1,57 @@
+# UAP Memory Schema
+
+> Loaded every session alongside working memory. Teaches the agent how the memory system works.
+
+## Memory Tiers
+
+| Tier | Storage | Latency | Loaded |
+|------|---------|---------|--------|
+| L1 Working | SQLite `memories` | <1ms | Always (last 50) |
+| L2 Session | SQLite `session_memories` | <5ms | Current session |
+| L3 Semantic | Qdrant vectors | ~50ms | On-demand search |
+| L4 Graph | SQLite `entities`/`relationships` | <20ms | On-demand |
+| Daily Log | SQLite `daily_log` | <1ms | Today + yesterday |
+
+## Write Rules
+
+**Write Gate**: Before storing anything, it must pass at least one criterion:
+1. Changes future behavior (preference, boundary, recurring pattern)
+2. Commitment with consequences (deadline, deliverable, follow-up)
+3. Decision with rationale (why X over Y)
+4. Stable recurring fact (not transient, will matter again)
+5. Explicit "remember this" request
+
+**Default destination**: Daily log first. Promote to permanent memory later.
+
+**Never**: silently overwrite. Mark old entries `[superseded]` with date and reason.
+
+## Read Rules
+
+- Working memory and this schema are always loaded
+- Daily log checked for today and yesterday
+- Registers/semantic memory searched on demand when topic is relevant
+- Use `uap memory query` for anything older
+
+## When to Write
+
+| Trigger | Destination |
+|---------|-------------|
+| User says "remember" | Daily log + maybe working memory |
+| User corrects you | Supersede old + write corrected across all tiers |
+| Decision with rationale | Daily log, promote if durable |
+| Preference expressed | Daily log, promote to working memory |
+| Commitment/deadline | Daily log + working memory |
+| Debugging details | **DISCARD** |
+| Transient state | **DISCARD** |
+| Acknowledgments | **DISCARD** |
+
+## Correction Protocol
+
+When corrected: (1) find original, (2) mark superseded with reason, (3) write corrected version to daily log + working memory + semantic memory, (4) verify next session.
+
+## Maintenance
+
+- Memories decay: `effective_importance = importance * (0.95 ^ days_since_access)`
+- Consolidation triggers every 10 new entries
+- Stale entries (>14 days unaccessed) auto-demote from hot to warm tier
+- Run `uap memory maintain` periodically for health checks