SSO MCP Server

# Tasks: Process Query Feature **Input**: Design documents from `specs/003-process-query/` **Prerequisites**: design.md (required), spec.md (required for user stories), research.md, data-model.md, contracts/ **Tests**: Unit tests included per ground-rules requirement (Principle II: Test-First Development) **Organization**: Tasks are grouped by user story to enable independent implementation and testing of each story. ## Format: `[ID] [P?] [Story] Description` - **[P]**: Can run in parallel (different files, no dependencies) - **[Story]**: Which user story this task belongs to (e.g., US1, US2, US3) - Include exact file paths in descriptions ## Architecture Alignment - **ADR-006**: Parallel Module Design for Processes - Process module follows checklist module structure - **ADR-007**: In-Memory Search with Relevance Ranking - No external search engine needed --- ## Phase 1: Setup (Shared Infrastructure) **Purpose**: Configuration and directory setup for process module - [ ] T001 Add PROCESS_DIR setting to src/sso_mcp_server/config/settings.py with default ./processes - [ ] T002 [P] Create processes/ directory at repository root for default process files - [ ] T003 [P] Create src/sso_mcp_server/processes/ module directory with __init__.py --- ## Phase 2: Foundational (Blocking Prerequisites) **Purpose**: Core infrastructure that MUST be complete before ANY user story can be implemented **⚠️ CRITICAL**: No user story work can begin until this phase is complete - [ ] T004 Implement discover_processes function in src/sso_mcp_server/processes/discovery.py (glob pattern *.md) - [ ] T005 Implement parse_process_file function in src/sso_mcp_server/processes/parser.py (YAML frontmatter extraction) - [ ] T006 [P] Write unit tests for discovery in tests/unit/processes/test_discovery.py - [ ] T007 [P] Write unit tests for parser in tests/unit/processes/test_parser.py **Checkpoint**: Foundation ready - user story implementation can now begin in parallel --- ## Phase 3: User Story 1 - Query Development Processes (Priority: P1) 🎯 MVP **Goal**: Enable developers to retrieve specific process documentation by name through the MCP server **Independent Test**: Call get_process tool with process name "code-review" → returns complete process content ### Tests for User Story 1 > **NOTE: Write these tests FIRST, ensure they FAIL before implementation** - [ ] T008 [P] [US1] Write unit tests for ProcessService.get_process in tests/unit/processes/test_service.py - [ ] T009 [P] [US1] Write unit tests for get_process_impl in tests/unit/tools/test_get_process.py ### Implementation for User Story 1 - [ ] T010 [US1] Implement ProcessService class with get_process method in src/sso_mcp_server/processes/service.py - [ ] T011 [US1] Implement get_available_names helper method in ProcessService for error messages - [ ] T012 [US1] Implement get_process_impl function in src/sso_mcp_server/tools/get_process.py - [ ] T013 [US1] Register get_process tool in src/sso_mcp_server/server.py with auth middleware - [ ] T014 [US1] Create example process file processes/code-review.md with YAML frontmatter **Checkpoint**: At this point, User Story 1 should be fully functional and testable independently --- ## Phase 4: User Story 2 - List Available Processes (Priority: P2) **Goal**: Enable developers to discover all available processes with names and descriptions **Independent Test**: Call list_processes tool → returns array of all process metadata (name + description) ### Tests for User Story 2 - [ ] T015 [P] [US2] Write unit tests for ProcessService.list_processes in tests/unit/processes/test_service.py (append to existing) - [ ] T016 [P] [US2] Write unit tests for list_processes_impl in tests/unit/tools/test_list_processes.py ### Implementation for User Story 2 - [ ] T017 [US2] Add list_processes method to ProcessService in src/sso_mcp_server/processes/service.py - [ ] T018 [US2] Implement list_processes_impl function in src/sso_mcp_server/tools/list_processes.py - [ ] T019 [US2] Register list_processes tool in src/sso_mcp_server/server.py with auth middleware - [ ] T020 [P] [US2] Create additional example process file processes/deployment.md with YAML frontmatter **Checkpoint**: At this point, User Stories 1 AND 2 should both work independently --- ## Phase 5: User Story 3 - Search Processes by Keyword (Priority: P3) **Goal**: Enable developers to search across all process documents by keyword with relevance ranking **Independent Test**: Call search_processes with query "deploy" → returns matching processes ordered by relevance ### Tests for User Story 3 - [ ] T021 [P] [US3] Write unit tests for SearchEngine in tests/unit/processes/test_search.py - [ ] T022 [P] [US3] Write unit tests for ProcessService.search_processes in tests/unit/processes/test_service.py (append to existing) - [ ] T023 [P] [US3] Write unit tests for search_processes_impl in tests/unit/tools/test_search_processes.py ### Implementation for User Story 3 - [ ] T024 [US3] Implement SearchEngine class with relevance scoring in src/sso_mcp_server/processes/search.py - [ ] T025 [US3] Implement calculate_relevance method (name: 100pts, description: 50pts, content: 10pts/match) - [ ] T026 [US3] Implement extract_snippet method for search result context - [ ] T027 [US3] Add search_processes method to ProcessService in src/sso_mcp_server/processes/service.py - [ ] T028 [US3] Implement search_processes_impl function in src/sso_mcp_server/tools/search_processes.py - [ ] T029 [US3] Register search_processes tool in src/sso_mcp_server/server.py with auth middleware - [ ] T030 [P] [US3] Create additional example process file processes/incident-response.md with YAML frontmatter **Checkpoint**: All user stories should now be independently functional --- ## Phase 6: Polish & Cross-Cutting Concerns **Purpose**: Improvements that affect multiple user stories - [ ] T031 [P] Update module exports in src/sso_mcp_server/processes/__init__.py - [ ] T032 [P] Add integration tests for all process tools in tests/integration/test_process_tools.py - [ ] T033 [P] Update README.md with process tools documentation - [ ] T034 Run ruff check and ruff format on all new files - [ ] T035 Run pytest to verify all tests pass - [ ] T036 Run quickstart.md validation scenarios manually --- ## Dependencies & Execution Order ### Phase Dependencies - **Setup (Phase 1)**: No dependencies - can start immediately - **Foundational (Phase 2)**: Depends on Setup completion - BLOCKS all user stories - **User Stories (Phase 3+)**: All depend on Foundational phase completion - User stories can then proceed in parallel (if staffed) - Or sequentially in priority order (P1 → P2 → P3) - **Polish (Final Phase)**: Depends on all desired user stories being complete ### User Story Dependencies - **User Story 1 (P1)**: Can start after Foundational (Phase 2) - No dependencies on other stories - **User Story 2 (P2)**: Can start after Foundational (Phase 2) - Reuses ProcessService from US1 - **User Story 3 (P3)**: Can start after Foundational (Phase 2) - Reuses ProcessService, adds SearchEngine ### Within Each User Story - Tests MUST be written and FAIL before implementation - ProcessService methods before tool implementations - Tool implementation before server registration - Story complete before moving to next priority ### Parallel Opportunities - T002, T003 can run in parallel (different directories) - T006, T007 can run in parallel (different test files) - T008, T009 can run in parallel (different test files) - T015, T016 can run in parallel (different test files) - T021, T022, T023 can run in parallel (different test files) - T031, T032, T033 can run in parallel (different files) - Once Foundational phase completes, all user stories can start in parallel (if team capacity allows) --- ## Parallel Example: User Story 3 ```bash # Launch all tests for User Story 3 together: Task: "Write unit tests for SearchEngine in tests/unit/processes/test_search.py" Task: "Write unit tests for ProcessService.search_processes in tests/unit/processes/test_service.py" Task: "Write unit tests for search_processes_impl in tests/unit/tools/test_search_processes.py" # After tests written, implement sequentially: Task: "Implement SearchEngine class in src/sso_mcp_server/processes/search.py" Task: "Add search_processes method to ProcessService" Task: "Implement search_processes_impl function" Task: "Register search_processes tool in server.py" ``` --- ## Implementation Strategy ### MVP First (User Story 1 Only) 1. Complete Phase 1: Setup (T001-T003) 2. Complete Phase 2: Foundational (T004-T007) 3. Complete Phase 3: User Story 1 (T008-T014) 4. **STOP and VALIDATE**: Test get_process tool independently 5. Deploy/demo if ready ### Incremental Delivery 1. Complete Setup + Foundational → Foundation ready 2. Add User Story 1 (get_process) → Test independently → Deploy/Demo (MVP!) 3. Add User Story 2 (list_processes) → Test independently → Deploy/Demo 4. Add User Story 3 (search_processes) → Test independently → Deploy/Demo 5. Each story adds value without breaking previous stories ### Parallel Team Strategy With multiple developers: 1. Team completes Setup + Foundational together 2. Once Foundational is done: - Developer A: User Story 1 (get_process) - Developer B: User Story 2 (list_processes) - Developer C: User Story 3 (search_processes) 3. Stories complete and integrate independently --- ## Notes - [P] tasks = different files, no dependencies - [Story] label maps task to specific user story for traceability - Each user story should be independently completable and testable - Verify tests fail before implementing - Commit after each task or logical group - Stop at any checkpoint to validate story independently - Follow existing checklist module patterns (ADR-006) - Use in-memory search with relevance ranking (ADR-007)