Cline rules

1# Generated Project Configuration
2 
3> **🔄 Updated by `analyze_project`** (incremental update)
4> **Scanned:** 2026-06-03
5 
6> **Auto-generated by `analyze_project`**
7> **Project:** fluentui-mcp
8> **Type:** library
9 
10Save this content to `.clinerules/project.md` in your project root,
11then review and adjust the values as needed.
12 
13---
14 
15## 🚨 MANDATORY: Load CodeOps Rules Before Any Work
16 
17**Before ANY planning or implementation, the AI agent MUST load these rules
18using the codeops-mcp tools:**
19 
201. `get_rule("agents")` — Load agent behavior rules **(REQUIRED FIRST)**
212. `get_rule("code")` — Load coding standards
223. `get_rule("testing")` — Load testing workflows
234. `get_rule("git-commands")` — Load git commit protocols
24 
25These rules are **mandatory** and must be consulted before every task.
26**Do NOT skip this step. Do NOT proceed without reading these documents.**
27 
28---
29 
30## Project Overview
31 
32- **Name:** fluentui-mcp
33- **Description:** MCP server providing FluentUI v9 documentation, component references, patterns, and implementation guides as tools and resources for AI agents. Backed by a schema-driven pipeline (scraper → LLM enhancer → bundled enhanced JSON schema) served from an in-memory store.
34- **Type:** library
35 
36## Toolchain
37 
38- **Language(s):** TypeScript
39- **Framework(s):** MCP SDK
40- **Package Manager:** yarn
41- **Test Framework:** Vitest
42 
43**Manifest files found:** package.json, tsconfig.json
44 
45## Commands
46 
47All commands assume execution from the project root. Prefix all shell commands with `clear && sleep [delay] &&` (see Terminal Delay below).
48 
49### Terminal Delay
50 
51- **Delay (seconds):** 3
52- The `clear` ensures a clean terminal; the `sleep` gives VS Code time to initialize the terminal before the command runs.
53- Adjust the delay for your environment: `1` for fast machines, `3` (default) for normal, `5` for slower environments.
54- All command examples below use `sleep 3` — replace `3` with your configured delay.
55 
56### Build
57 
58```bash
59clear && sleep 3 && yarn build
60```
61 
62### Test
63 
64```bash
65# Run all tests
66clear && sleep 3 && yarn test
67```
68 
69### Verify (before commit)
70 
71```bash
72# Full verification — run this before any git commit
73clear && sleep 3 && yarn build && yarn test
74```
75 
76### Schema Pipeline (offline, build-time)
77 
78```bash
79# Scrape props/slots/stories from FluentUI source
80clear && sleep 3 && yarn scrape --version v9 --clone --verbose
81 
82# Enhance with AI descriptions, best practices, a11y, guides/patterns
83clear && sleep 3 && yarn enhance --version v9 --full --verbose
84 
85# Whole pipeline (scrape → enhance → build → test)
86clear && sleep 3 && yarn pipeline:full
87```
88 
89## Project Structure
90 
91### Type: Single repository
92 
93### Directory Layout
94 
95```
96LICENSE/
97data/
98docs/
99maintenance/
100node_modules/
101plans/
102scripts/
103src/
104```
105 
106## Coding Conventions
107 
108### Naming
109 
110- **Files:** kebab-case
111- **Components/Classes:** PascalCase
112- **Functions/Methods:** camelCase
113- **Constants:** UPPER_SNAKE_CASE
114 
115## Git & Commit Conventions
116 
117### Commit Scope
118 
119```
120# Use module/feature as scope:
121# feat(module): description
122```
123 
124### Branch Strategy
125 
126- **Main branch:** `main`
127- **Feature branches:** `feature/[name]`
128 
129## Special Rules (Project-Specific)
130 
131```
132- The bundled enhanced schema lives in data/v9/fluentui-schema-enhanced.json and is the
133  single source of truth served at runtime. It is generated offline by the scraper + enhancer.
134- Schema pipeline tooling lives in scripts/: scripts/scraper/ (ts-morph extraction) and
135  scripts/enhancer/ (LLM enrichment + guide/pattern generation). Run via tsx, not built.
136- MCP tools are defined in src/tools/ as individual files per tool (12 tools).
137- Runtime schema subsystem: src/schema/ (loader, store, validator), src/search/ (TF-IDF
138  search engine + index), src/formatters/ (render schema entries → markdown).
139- All enhanced-schema enrichment fields are OPTIONAL/additive — formatters render a section
140  only when its field is present, preserving back-compat with un-enhanced schemas.
141- LLM provider note: newer OpenAI models (gpt-5.x / o-series) require max_completion_tokens
142  and reject custom temperature; the OpenAI provider branches on model family accordingly.
143```
144 
145## Cross-References
146 
147The generic rule files that read this `project.md`:
148 
149- **make_plan.md** — Uses verify command, file paths, commit scope, task file path patterns
150- **code.md** — Uses language conventions, architecture rules
151- **testing.md** — Uses test commands, test locations, test framework
152- **git-commands.md** — Uses commit scope, verify command
153- **agents.md** — Uses shell commands, verify command
154- **requirements.md** — Uses project type, tech stack, and conventions for requirements discovery
155- **retro_requirements.md** — Uses project type, tech stack for codebase analysis adaptation
156- **techdocs.md** — Uses project type, tech stack for documentation generation
157- **upgrade_plan.md** — Uses project context for upgrade compatibility checks
158- **grill_me.md** — Uses project context for deep disambiguation before planning or requirements
159- **preflight.md** — Uses project type, tech stack, and conventions for grounded quality audits
160