chore: bump v0.7.0 — Enhanced Claude Code integration, quality gates, macros

New MCP tools: context_pack, macro_run, session_save, session_restore (53 total)
New hooks: quality gate (task-complete-gate.sh), smart session bootstrap
Full hook template distribution via sidstack update
Updated README, CHANGELOG, QUICK_START, CLAUDE_CODE_INTEGRATION docs

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Author: Dchuong03

.gitignore

@@ -60,9 +60,11 @@ logs/
 # SidStack workspace data
 .sidstack/
 
-# Claude Code
+# Claude Code (project-local, not tracked)
 .claude/
 JOURNAL.md
+# Exception: CLI template files must be tracked for distribution
+!packages/cli/templates/governance/.claude/
 
 # MCP local config
 .mcp.json
@@ -119,10 +121,8 @@ src-tauri/templates/knowledge/
 # Legacy ADRs
 docs/ADRs/005-langgraph-orchestration.md
 
-# Legacy presets and skills
+# Legacy presets
 packages/cli/templates/presets/go-microservices.json
-packages/cli/templates/skills/core/file-locking-protocol.md
-packages/cli/templates/skills/core/progress-reporting.md
 
 # API server data (session artifacts)
 packages/api-server/data/

CHANGELOG.md

@@ -1,5 +1,37 @@
 # Changelog
 
+## [0.7.0] - 2026-03-06
+
+### Added
+- **Context Packs (`context_pack`):** New MCP tool that combines knowledge search + semantic memory + related tasks into a single comprehensive context bundle per module — replaces 3-5 separate tool calls
+- **Macro Tools (`macro_run`):** Composite MCP tool with 3 built-in macros:
+  - `start_work` — create task + search knowledge + search memory in one call
+  - `finish_work` — complete task + store learnings in memory
+  - `quick_context` — search knowledge + memory + list active tasks
+- **Session Continuity (`session_save` / `session_restore`):** MCP tools to persist and restore session state (decisions, blockers, files modified, progress) across conversations
+- **Quality Gate Hook:** PreToolUse hook on `task_complete` that checks test results exist, progress >= 80%, acceptance criteria, and quality commands before allowing completion
+- **Smart Session Bootstrap:** Enhanced `session-init.sh` with git branch-to-task correlation, uncommitted changes count, changed modules detection, top pending tasks with priorities, smart next-action suggestions, and automatic session state restore on resume
+- **`chore` TaskType:** Added to task type enum for maintenance work
+- **CI Deploy:** GitHub Actions workflow for Docker image deployment to GHCR
+
+### Changed
+- **Hook Templates:** Full hook configuration now distributed via `sidstack update` — 7 hook scripts (session-init, prompt-context, pre-compact, task-create-context, task-start-training, task-complete-learn, task-complete-gate)
+- **Settings Template:** `.claude/settings.json` template updated with all hook registrations including quality gate PreToolUse matcher
+- **CLAUDE.md Template:** Simplified governance section, streamlined workflow router, updated tool reference
+- **CLI Presets:** Simplified preset configurations (minimal, fullstack-typescript, typescript-backend, python-data)
+- **Skill Discovery:** Simplified `SkillDiscovery` class, removed unused methods
+- **`sidstack-aware` Skill:** Updated with enhanced workflow classification and progress tracking
+
+### Removed
+- **Legacy CLI Skills:** `architecture-understanding`, `code-discovery`, `research-first`, `self-improvement`, `communication-protocol`, `contract-first`, `governance-compliance`, `implementation-analysis`, `workflow-negotiation`
+- **Legacy Optional Skills:** `documentation-standards`, `performance-optimization`, `security-awareness`, `tdd-workflow`, `test-driven-development`
+- **Dead Code:** `init-wizard.ts`, `skill-manager.ts`, `template-selector.ts`, `migrate-skills.ts`, `config/index.ts`
+- **Legacy CLI Skill Files:** `sidstack-init.md` and `packages/cli/skills/core/` directory
+
+### Fixed
+- Missing `okr` type in frontend Record maps (CI typecheck)
+- Unused imports in test files (CI typecheck)
+
 ## [0.6.0] - 2026-03-04
 
 ### Added

README.md

@@ -43,7 +43,7 @@ Or configure MCP manually:
 }
 ```
 
-Claude Code now has access to 32 MCP tools for knowledge, tasks, impact analysis, tickets, training, and OKRs.
+Claude Code now has access to 53 MCP tools for knowledge, tasks, impact analysis, tickets, training, memory, macros, and session management.
 
 ### Desktop App (macOS)
 
@@ -59,54 +59,86 @@ pnpm install && pnpm packages:build && pnpm tauri:build
 
 See [Quick Start Guide](docs/QUICK_START.md) for full setup instructions.
 
-## MCP Tools (32)
+## MCP Tools (53)
 
 ```
-# Knowledge (9) - understand your project
-knowledge_context       Build context for a task/module
-knowledge_search        Search across knowledge docs
-knowledge_list          List available docs
-knowledge_get           Get single document with full content
-knowledge_modules       List modules with stats
-knowledge_create        Create knowledge document
-knowledge_update        Update knowledge document
-knowledge_delete        Delete knowledge document
-knowledge_health        Check knowledge coverage health
+# Knowledge (10) - understand your project
+knowledge_context        Build context for a task/module
+knowledge_search         Search across knowledge docs
+knowledge_list           List available docs
+knowledge_get            Get single document with full content
+knowledge_modules        List modules with stats
+knowledge_module_overview Get module architecture overview
+knowledge_create         Create knowledge document
+knowledge_update         Update knowledge document
+knowledge_delete         Delete knowledge document
+knowledge_health         Check knowledge coverage health
 
 # Tasks (5) - track AI work
-task_create             Create task with governance
-task_update             Update status/progress
-task_list               List tasks with filtering
-task_get                Get task details
-task_complete           Complete with quality gate check
+task_create              Create task with governance
+task_update              Update status/progress
+task_list                List tasks with filtering
+task_get                 Get task details
+task_complete            Complete with quality gate check
 
 # Impact Analysis (3) - assess risk
-impact_analyze          Run impact analysis on a change
-impact_check_gate       Check gate status (blocked/warning/clear)
-impact_list             List analyses
+impact_analyze           Run impact analysis on a change
+impact_check_gate        Check gate status (blocked/warning/clear)
+impact_list              List analyses
 
 # Tickets (4) - external intake
-ticket_create           Create ticket
-ticket_list             List/filter tickets
-ticket_update           Update status
-ticket_convert_to_task  Convert to task
+ticket_create            Create ticket
+ticket_list              List/filter tickets
+ticket_update            Update status
+ticket_convert_to_task   Convert to task
 
 # Training (8) - learn from mistakes
-incident_create         Report an incident
-incident_list           List incidents
-lesson_create           Create lesson from incident
-lesson_list             List lessons
-skill_create            Create reusable skill
-skill_list              List skills
-rule_check              Check rules for context
-training_context_get    Get training context for session
+incident_create          Report an incident
+incident_list            List incidents
+lesson_create            Create lesson from incident
+lesson_list              List lessons
+skill_create             Create reusable skill
+skill_list               List skills
+rule_check               Check rules for context
+training_context_get     Get training context for session
 
 # OKRs (2) - project goals
-okr_list                List objectives and key results
-okr_update              Update key result progress
-
-# Sessions (1)
-session_launch          Launch Claude session with context
+okr_list                 List objectives and key results
+okr_update               Update key result progress
+
+# Test Results (3) - persist test execution
+test_result_create       Persist test execution results
+test_result_list         List test results with filtering
+test_result_get          Get detailed test result
+
+# Agent Desk (7) - workspace isolation
+desk_create              Create agent desk (git worktree)
+desk_list                List all agent desks
+desk_status              Get desk status and current task
+desk_checkout            Switch desk to a task
+desk_health              Check desk health
+desk_conflicts           Detect merge conflicts
+desk_remove              Remove agent desk
+
+# Memory (6) - semantic search
+memory_add               Store a memory entry
+memory_search            Semantic search across memories
+memory_list              List memory entries
+memory_delete            Delete a memory entry
+memory_index_knowledge   Index knowledge docs into memory
+memory_cleanup           Clean up expired entries
+
+# Context & References (4)
+entity_link              Link entities (task↔knowledge, etc.)
+entity_references        Get references for an entity
+entity_context           Build context from linked entities
+traceability_matrix      Generate spec-task-test coverage matrix
+
+# Productivity (v0.7.0)
+context_pack             Build comprehensive context pack for a module
+macro_run                Run composite macros (start_work, finish_work, quick_context)
+session_save             Save session state for cross-session continuity
+session_restore          Restore saved session state
 ```
 
 ## Desktop App - 7 Views
@@ -128,16 +160,21 @@ sidstack/
 ├── src/                   # React frontend (Tauri)
 ├── src-tauri/             # Rust backend (Tauri)
 ├── packages/
-│   ├── mcp-server/        # MCP Server (standalone, npx-ready)
-│   ├── api-server/        # REST API (Express.js)
-│   ├── cli/               # CLI (init, scan, doctor)
-│   ├── shared/            # SQLite + shared types + impact engine
-│   └── vscode-extension/  # VS Code sidebar integration
-├── .sidstack/             # Governance, knowledge, skills
+│   ├── mcp-server/        # MCP Server (53 tools, npx-ready)
+│   ├── api-server/        # REST API (Express.js, central gateway)
+│   ├── cli/               # CLI (init, update, scan, skills, desk)
+│   ├── bot-server/        # SidBot (Gemini intent router)
+│   ├── web-ui/            # React SPA (browser access)
+│   └── shared/            # Repository layer + shared types
+├── .sidstack/             # Project data (config, knowledge)
 │   ├── governance.md      # Master governance doc
-│   ├── knowledge/         # Project knowledge docs
-│   ├── skills/            # Capability skills (implement, review)
-│   └── principles/        # Quality standards
+│   └── knowledge/         # Project knowledge docs (9 categories)
+├── .claude/               # Claude Code integration
+│   ├── hooks/             # Lifecycle hooks (quality gates, bootstrap)
+│   ├── skills/            # Auto-triggered agent skills
+│   ├── agents/            # Worker + Reviewer agent definitions
+│   └── commands/          # Custom slash commands
+├── docker/                # Docker deployment configs
 └── docs/                  # Documentation
 ```
 

docs/CLAUDE_CODE_INTEGRATION.md

@@ -61,7 +61,7 @@ List my SidStack tasks
 
 Claude should use the `task_list` MCP tool.
 
-## Available MCP Tools (49)
+## Available MCP Tools (53)
 
 ### Knowledge (9)
 
@@ -132,15 +132,17 @@ Claude should use the `task_list` MCP tool.
 | `test_result_list` | List test results with filtering |
 | `test_result_get` | Get detailed test result |
 
-### Agent Desk (5)
+### Agent Desk (7)
 
 | Tool | Description |
 |------|-------------|
+| `desk_create` | Create agent desk (git worktree) |
 | `desk_list` | List all agent desks |
 | `desk_status` | Get desk status and current task |
-| `desk_acquire` | Acquire a desk for an agent |
-| `desk_release` | Release a desk |
-| `desk_pool_init` | Initialize desk pool |
+| `desk_checkout` | Switch desk to a task |
+| `desk_health` | Check desk health |
+| `desk_conflicts` | Detect merge conflicts |
+| `desk_remove` | Remove agent desk |
 
 ### Memory (6)
 
@@ -167,6 +169,28 @@ Claude should use the `task_list` MCP tool.
 | `entity_references` | Get references for an entity |
 | `entity_context` | Build context from linked entities |
 
+### Productivity (4) — v0.7.0
+
+| Tool | Description |
+|------|-------------|
+| `context_pack` | Build comprehensive context pack for a module (knowledge + memory + tasks in one call) |
+| `macro_run` | Run composite macros: `start_work`, `finish_work`, `quick_context` |
+| `session_save` | Save session state (decisions, blockers, files, progress) for continuity |
+| `session_restore` | Restore saved session state from previous conversation |
+
+### Claude Code Hooks (Quality Gates)
+
+SidStack installs lifecycle hooks in `.claude/hooks/` that enforce quality automatically:
+
+| Hook | Event | Purpose |
+|------|-------|---------|
+| `session-init.sh` | SessionStart | Smart bootstrap with branch→task correlation, changed modules, session restore |
+| `prompt-context.sh` | UserPromptSubmit | Inject active task context with completion reminder |
+| `task-complete-gate.sh` | PreToolUse (task_complete) | Block completion without test results, progress check, acceptance criteria |
+| `task-create-context.sh` | PostToolUse (task_create) | Remind agent to search knowledge/memory and link entities |
+| `task-start-training.sh` | PostToolUse (task_update) | Auto-inject relevant training lessons and rules |
+| `pre-compact.sh` | PreCompact | Save active task state before context compaction |
+
 ## Governance for Agents
 
 Agents automatically follow governance rules from `.sidstack/governance.md`:

docs/QUICK_START.md

@@ -33,7 +33,7 @@ npx @sidstack/cli init
 
 ### 2. Use MCP Tools in Claude Code
 
-Once initialized, Claude Code has access to 49 tools:
+Once initialized, Claude Code has access to 53 tools:
 
 **Knowledge (understand your project)**
 ```
@@ -99,11 +99,13 @@ test_result_get     - Get detailed test result
 
 **Agent Desk (workspace isolation)**
 ```
+desk_create         - Create agent desk (git worktree)
 desk_list           - List all agent desks
 desk_status         - Get desk status
-desk_acquire        - Acquire a desk for an agent
-desk_release        - Release a desk
-desk_pool_init      - Initialize desk pool
+desk_checkout       - Switch desk to a task
+desk_health         - Check desk health
+desk_conflicts      - Detect merge conflicts
+desk_remove         - Remove agent desk
 ```
 
 **Memory (semantic search via mem0)**
@@ -124,6 +126,14 @@ entity_references   - Get references for an entity
 entity_context      - Build context from linked entities
 ```
 
+**Productivity (v0.7.0)**
+```
+context_pack        - Build comprehensive context pack for a module
+macro_run           - Run composite macros (start_work, finish_work, quick_context)
+session_save        - Save session state for cross-session continuity
+session_restore     - Restore saved session state
+```
+
 ### 3. Example Workflow
 
 ```

package.json

@@ -1,6 +1,6 @@
 {
   "name": "sidstack",
-  "version": "0.6.0",
+  "version": "0.7.0",
   "private": true,
   "type": "module",
   "description": "SidStack - Lightweight AI Agent Orchestration Platform",

packages/api-server/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sidstack/api-server",
-  "version": "0.6.0",
+  "version": "0.7.0",
   "description": "REST API server for SidStack Web UI",
   "license": "MIT",
   "publishConfig": {

packages/bot-server/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sidstack/bot-server",
-  "version": "0.5.0",
+  "version": "0.7.0",
   "description": "SidBot bot server - Gemini intent router + Claude Code bridge",
   "license": "MIT",
   "publishConfig": {

packages/cli/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sidstack/cli",
-  "version": "0.6.0",
+  "version": "0.7.0",
   "description": "SidStack CLI - Project Intelligence for AI Coding Agents",
   "author": "SidStack Team",
   "license": "MIT",