Compare commits

...

11 Commits

Author SHA1 Message Date
Patrick Plate 9c2422d0a7 chore(roo): document git-based wiki workflow in rules, skill, and README
- mcp-builder rules: add wiki/ to structure diagram, add Wiki Update
  Workflow section (MANDATORY), update After Building a Server checklist
- gitea-push skill: add wiki deploy as a valid use case
- README.md: add wiki section with deploy_wiki.sh pointer, add
  mcp-image-gen to MCP servers table
2026-04-05 09:53:05 +02:00
Patrick Plate 9a8403ad57 docs(wiki): migrate to git-based workflow with persistent wiki/ clone 2026-04-05 09:48:22 +02:00
Patrick Plate dabdda167f docs(wiki): migrate to git-based workflow with persistent wiki/ clone
- Extract all wiki content from create_wiki_pages.py into docs/wiki/pages/*.md
- Add docs/wiki/deploy_wiki.sh: copies pages to wiki/ repo, commits, pushes
- Add /wiki/ to .gitignore (anchored — does not affect docs/wiki/)
- 12 pages: Home, MCP-Servers-Overview, mcp-image-gen, ComfyUI-Setup,
  mcp-webscraper (8 tools incl. search_hint), BigMind (schema v8),
  Development-Conventions, Java-Projects, Java-wellmann-shop,
  Java-mss-failsafe, Java-Architecture, _Sidebar
- Workflow: edit docs/wiki/pages/*.md → ./docs/wiki/deploy_wiki.sh
2026-04-05 09:48:19 +02:00
Patrick Plate da90781cad Merge feat/webscraper/brave-search-hint into main 2026-04-05 09:37:38 +02:00
Patrick Plate 2ab847f51d feat(webscraper): add Brave Search hint tool and User-Agent header
- Add webscraper_search_hint() tool using Brave Search as backend
  (no CAPTCHA/GDPR consent wall, works with plain httpx)
- Add User-Agent header to _fetch_page() — fixes 403 on Wikipedia,
  Feynman Lectures, and other sites that block headless requests
- Add 5 new tests for search hint (23 total, 90% coverage)

Brave Search URL: https://search.brave.com/search?q={query}&source=web
Use sparingly — once per research task as orientation, not in loops
2026-04-05 09:37:30 +02:00
Patrick Plate d5510f590e Added new picture for bigmind page 2026-04-04 20:03:59 +02:00
Patrick Plate cf102e8b3e fix(bigmind): render achievement card background images via inline style 2026-04-04 19:29:15 +02:00
Patrick Plate 13659fd414 fix(bigmind): add background-image inline style to achievement card ach-image divs
The .ach-image div had correct CSS dimensions (64x64) and background-size:cover
but was missing the inline style="background-image: url(...)" — so the div
rendered as an empty circle. Fixed by extracting img_url variable and applying
it as style attribute in the f-string. All 39 achievement PNGs now load.

303/303 tests passing.
2026-04-04 19:27:24 +02:00
pplate c68acdd030 chore(bigmind): rename timestamp badge PNGs to achievement IDs
- Renamed 19 timestamp-named PNGs (20260404_*) to match original
  achievement IDs in profile_builder.py compute_achievements() order:
  first_breath, first_thought, eureka, honest_mind, scholar,
  deep_knowledge, scientist, veteran, on_fire, storyteller,
  night_owl, speed_thinker, first_handshake, birthday, shared_mind,
  frugal_mind, quarter_million, token_millionaire, sniper
- Deleted 2 duplicate/excess timestamp PNGs
- Added image= field to all 19 original _add() calls in
  profile_builder.py so every achievement now has a PNG path
- All 39 achievements (19 original + 20 tiered) now have image fields
- 303/303 tests pass
2026-04-04 19:09:01 +02:00
pplate e61c9c98f5 fix(bigmind): fix static image path, JS string concat in achievements; add networker badge PNGs 2026-04-04 19:01:56 +02:00
Patrick Plate 50488109aa Merge branch 'feat/bigmind/achievements-rework' 2026-04-04 18:50:55 +02:00
58 changed files with 1389 additions and 42 deletions
+7
View File
@@ -72,3 +72,10 @@ Thumbs.db
# ── Logs ──────────────────────────────────────────────────────────────────────
*.log
# ── Wiki (separate git repo — local clone of pi_mcps.wiki.git) ────────────────
# Edit pages in docs/wiki/pages/*.md (tracked here in pi_mcps).
# Clone with: git clone http://pplate:TOKEN@192.168.188.119:30008/pplate/pi_mcps.wiki.git wiki/
# Deploy with: ./docs/wiki/deploy_wiki.sh
# Note: /wiki/ is anchored to root so docs/wiki/ (source files) is NOT ignored.
/wiki/
+16 -8
View File
@@ -10,11 +10,10 @@
"alwaysAllow": [
"git_status",
"git_diff_unstaged",
"git_log",
"git_add",
"git_commit",
"git_branch",
"git_create_branch"
"git_create_branch",
"git_add",
"git_commit"
]
},
"filesystem": {
@@ -34,7 +33,8 @@
"src/server.py"
],
"alwaysAllow": [
"webscraper_fetch"
"webscraper_fetch",
"webscraper_fetch_links"
]
},
"gitea": {
@@ -54,8 +54,10 @@
"create_issue_comment",
"create_pull_request",
"get_repository",
"list_my_repositories"
]
"list_my_repositories",
"create_wiki_page"
],
"disabled": true
},
"playwright": {
"command": "npx",
@@ -82,7 +84,13 @@
"env": {
"COMFYUI_URL": "http://localhost:8188",
"IMAGE_OUTPUT_DIR": "/home/pplate/Pictures/mcp-generated"
}
},
"alwaysAllow": [
"list_available_models",
"get_generation_status",
"get_output_directory",
"generate_image"
]
}
}
}
@@ -20,6 +20,28 @@ Patrick is in MCP Builder mindset. He is building or extending MCP servers in th
README.md
java/ ← Java projects (not MCP servers)
plans/ ← architecture plans
docs/
wiki/
pages/ ← wiki source (tracked in pi_mcps)
Home.md, _Sidebar.md, ...
deploy_wiki.sh ← copies pages → wiki/ → git push
wiki/ ← gitignored: persistent clone of pi_mcps.wiki.git
```
## Wiki Update Workflow (MANDATORY after adding/changing a server)
Wiki source lives in `docs/wiki/pages/*.md` — real Markdown files, tracked in the main repo.
```bash
# 1. Edit the relevant page(s) in docs/wiki/pages/
# 2. Deploy to Gitea wiki:
./docs/wiki/deploy_wiki.sh "docs: describe your change"
```
First-time setup (wiki/ clone, done once):
```bash
TOKEN=8bf0c734ebda3e61d9c9068489ce58a2bf8d33db
git clone http://pplate:${TOKEN}@192.168.188.119:30008/pplate/pi_mcps.wiki.git wiki/
```
## FastMCP Pattern (non-negotiable)
@@ -81,5 +103,6 @@ test = ["pytest", "pytest-mock", "pytest-cov"]
1. **Store Fact:** `memory_store_fact("codebase", "mcp/{name} has N tools: [list]. Stack: X. Env vars: Y.")`
2. **Wire into .roo/mcp.json:** Add the server entry with correct uv path
3. **Update root README.md:** Add to MCPs table
4. **Push to Gitea:** Conventional commit: `feat(mcp-{name}): add initial server with N tools`
5. **Resolve Hypothesis:** Was the tool count and auth pattern as predicted?
4. **Update wiki:** Create or update `docs/wiki/pages/{server-name}.md` + update `MCP-Servers-Overview.md`, then run `./docs/wiki/deploy_wiki.sh`
5. **Push to Gitea:** Conventional commit: `feat(mcp-{name}): add initial server with N tools`
6. **Resolve Hypothesis:** Was the tool count and auth pattern as predicted?
+1
View File
@@ -9,6 +9,7 @@ description: Commits and pushes code to the homelab Gitea server using conventio
- Finished a homelab change and need to commit + push
- Finished an MCP server build or update
- BigMind feature complete
- Wiki pages were added or updated (always deploy wiki after docs changes)
## When NOT to use
- ADP/Paisy work — that goes to the corporate Bitbucket, not homelab Gitea
+14 -2
View File
@@ -18,12 +18,24 @@ workshop/
---
## 🐍 MCP Servers (`mcp/`)
## 📖 Wiki
Full documentation lives in the [Gitea wiki](http://192.168.188.119:30008/pplate/pi_mcps/wiki).
**Wiki source:** [`docs/wiki/pages/`](docs/wiki/pages/) — edit here, deploy with:
```bash
./docs/wiki/deploy_wiki.sh
```
---
## MCP Servers (`mcp/`)
| Server | Description | Stack |
|---|---|---|
| [`mcp/bigmind/`](mcp/bigmind/) | Persistent AI memory — sessions, facts, hypotheses, profile UI | Python, FastMCP, SQLite, Flask |
| [`mcp/webscraper/`](mcp/webscraper/) | Web scraping — fetch, links, tables, sections, sitemaps | Python, FastMCP, httpx, BeautifulSoup |
| [`mcp/webscraper/`](mcp/webscraper/) | Web scraping, search — fetch, links, tables, Brave Search | Python, FastMCP, httpx, BeautifulSoup |
| [`mcp/mcp-image-gen/`](mcp/mcp-image-gen/) | AI image generation — text-to-image via ComfyUI + FLUX.1-schnell | Python, FastMCP, httpx, ComfyUI |
**Run a server:**
```bash
+90
View File
@@ -0,0 +1,90 @@
#!/usr/bin/env bash
# deploy_wiki.sh — Sync docs/wiki/pages/*.md to the local wiki git clone
#
# ── Convention ────────────────────────────────────────────────────────────────
# The Gitea wiki is a SEPARATE git repo (pi_mcps.wiki.git).
# We keep a persistent local clone at wiki/ in the repo root.
# That folder is gitignored so it doesn't conflict with the main repo.
#
# First-time setup (run once):
# git clone http://pplate:TOKEN@192.168.188.119:30008/pplate/pi_mcps.wiki.git wiki/
#
# ── Daily workflow ────────────────────────────────────────────────────────────
# 1. Edit pages in docs/wiki/pages/*.md (tracked in pi_mcps main repo)
# 2. Run: ./docs/wiki/deploy_wiki.sh
# ./docs/wiki/deploy_wiki.sh "docs: describe your change"
#
# The script copies pages into wiki/, commits, and pushes to Gitea.
# ─────────────────────────────────────────────────────────────────────────────
set -euo pipefail
# ── Config ────────────────────────────────────────────────────────────────────
GITEA_URL="http://192.168.188.119:30008"
OWNER="pplate"
REPO="pi_mcps"
# Resolve paths relative to repo root (two levels up from docs/wiki/)
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
REPO_ROOT="$(cd "${SCRIPT_DIR}/../.." && pwd)"
PAGES_DIR="${SCRIPT_DIR}/pages"
WIKI_DIR="${REPO_ROOT}/wiki"
COMMIT_MSG="${1:-docs: sync wiki pages $(date -u '+%Y-%m-%d %H:%M UTC')}"
# ── Validate ──────────────────────────────────────────────────────────────────
if [[ ! -d "${WIKI_DIR}/.git" ]]; then
echo "❌ Wiki repo not set up. Run first-time setup:"
echo ""
echo " TOKEN=8bf0c734ebda3e61d9c9068489ce58a2bf8d33db"
echo " git clone http://pplate:\${TOKEN}@192.168.188.119:30008/pplate/pi_mcps.wiki.git wiki/"
echo ""
exit 1
fi
if [[ ! -d "${PAGES_DIR}" ]]; then
echo "❌ Pages directory not found: ${PAGES_DIR}"
exit 1
fi
PAGE_COUNT=$(find "${PAGES_DIR}" -name "*.md" | wc -l)
if [[ "${PAGE_COUNT}" -eq 0 ]]; then
echo "❌ No .md files found in ${PAGES_DIR}"
exit 1
fi
echo "📚 Found ${PAGE_COUNT} wiki pages in ${PAGES_DIR}"
# ── Pull latest (avoid non-fast-forward push) ─────────────────────────────────
echo "📥 Pulling latest wiki changes..."
git -C "${WIKI_DIR}" pull --quiet --rebase origin main
# ── Copy pages ────────────────────────────────────────────────────────────────
echo "📋 Copying pages to ${WIKI_DIR}/..."
for md_file in "${PAGES_DIR}"/*.md; do
filename="$(basename "${md_file}")"
cp "${md_file}" "${WIKI_DIR}/${filename}"
echo "${filename}"
done
# ── Commit and push ───────────────────────────────────────────────────────────
cd "${WIKI_DIR}"
git add -A
if git diff --cached --quiet; then
echo "✅ No changes detected — wiki is already up to date."
exit 0
fi
CHANGED=$(git diff --cached --name-only | wc -l)
echo "📝 Committing ${CHANGED} changed file(s)..."
git commit --quiet -m "${COMMIT_MSG}"
echo "🚀 Pushing to Gitea wiki..."
git push --quiet origin main
echo ""
echo "✅ Wiki deployed successfully!"
echo " Pages: ${PAGE_COUNT} total, ${CHANGED} updated"
echo " Message: ${COMMIT_MSG}"
echo " URL: ${GITEA_URL}/${OWNER}/${REPO}/wiki"
+125
View File
@@ -0,0 +1,125 @@
# 🧠 BigMind — Persistent AI Memory
![BigMind Banner](http://192.168.188.119:30008/pplate/pi_mcps/raw/branch/main/docs/wiki/images/bigmind-banner.png)
**BigMind** is the persistent memory backbone for all AI development sessions. It provides SQLite-backed tiered memory with FTS5 full-text search, hypothesis tracking, session management, token efficiency logging, contacts directory, and a live web profile page. It is the reason Lumen (Patrick's AI colleague) remembers everything across sessions.
## Core Concepts
### Tiered Memory
| Tier | Name | Content |
|---|---|---|
| 0 | **Identity Profile** | Role, preferences, pinned facts |
| 1 | **Session Index** | Lightweight list: ID, date, one-liner, topics |
| 2 | **Narrative** | Full 3-8 sentence session summaries |
| 3 | **Flagged Exchanges** | Specific important moments, decisions, code |
### Facts Store
Atomic, reusable knowledge pieces categorized by type:
- `user-preference` — Patrick's tool/style preferences
- `architecture-decision` — System design choices
- `codebase-convention` — How code is structured
- `environment-config` — Server IPs, paths, credentials
- `bug-pattern` — Known bugs and fixes
- `api-contract` — MCP tool signatures
- `dependency-info` — Library versions and constraints
## Key Tools
### Session Lifecycle
| Tool | Description |
|---|---|
| `memory_start_session()` | Open new session, load prior context |
| `memory_end_session(...)` | Close session with summary, topics, outcome |
| `memory_announce_focus(...)` | Declare files to be touched this session |
| `memory_close_stale_sessions(...)` | Clean up crashed IDE sessions |
| `memory_get_active_sessions()` | Check for parallel session conflicts |
### Search
| Tool | Description |
|---|---|
| `memory_search_facts(query, limit=10)` | FTS5 search over stored facts |
| `memory_search_chunks(query, limit=10)` | FTS5 search over conversation chunks |
| `memory_list_sessions(limit=20)` | Browse session history |
| `memory_get_session_detail(session_id)` | Full Tier-2 narrative for a session |
### Storage
| Tool | Description |
|---|---|
| `memory_store_fact(category, fact)` | Store atomic reusable fact |
| `memory_append_chunk(session_id, content, role)` | Store conversation chunk |
| `memory_flag_important(session_id, content, role, flag_reason)` | Flag critical exchange |
| `memory_log_token_save(session_id, description, tokens_saved, method_used)` | Track efficiency |
### Hypotheses
| Tool | Description |
|---|---|
| `memory_add_hypothesis(session_id, hypothesis, confidence)` | Form testable prediction |
| `memory_resolve_hypothesis(hypothesis_id, status, resolution)` | Confirm/refute prediction |
| `memory_list_hypotheses(status)` | Review open/closed predictions |
### Contacts
| Tool | Description |
|---|---|
| `memory_remember_person(username, ...)` | Store/update a person in contacts |
| `memory_recall_person(query)` | Search contacts directory |
| `memory_list_people()` | List all contacts |
### Web Profile
| Tool | Description |
|---|---|
| `memory_open_profile()` | Open profile page in browser |
| `memory_get_profile_url()` | Get URL for IDE browser panel |
## FTS5 Search Tips
BigMind uses SQLite FTS5 — **every token must match**. Use 2-3 focused keywords:
```
✅ memory_search_facts("TrueNAS Docker")
✅ memory_search_facts("mcp.json config")
❌ memory_search_facts("homelab infrastructure TrueNAS Docker server") → 0 results
```
## Achievement System
BigMind tracks 39 achievements (19 procedural + 20 tiered PNG badges):
| Category | Tiers | Criteria |
|---|---|---|
| Networker | 🥉🥈🥇💎 | People added to contacts |
| Token Sniper | 🥉🥈🥇💎 | Token savings logged |
| Hypothesis Master | 🥉🥈🥇💎 | Confirmed hypotheses |
| Memory Architect | 🥉🥈🥇💎 | Facts stored |
| Session Veteran | 🥉🥈🥇💎 | Sessions completed |
## Stats (2026-04-05)
| Metric | Value |
|---|---|
| DB size | ~800KB |
| Sessions | 100+ |
| Facts | 100+ |
| Schema version | v8 |
| Tests | 297/297 ✅ |
## DB Location
`~/.mcp/bigmind/memory.db` — outside the repo, never committed.
## Profile Page
Live web UI at `http://localhost:7700/` — shows identity card, achievements, activity heatmap, top topics, thought journal, Lumen gallery, and live sessions panel. Auto-refreshes every 30 seconds.
## Session Ritual
Every session **must** follow this ritual:
**Start (in order):**
1. `memory_start_session()`
2. `memory_list_hypotheses(status="open")`
3. `memory_announce_focus(session_id, description, files, ide_hint)`
4. `memory_close_stale_sessions(session_id)`
**End:**
1. `memory_end_session(session_id, one_liner, topics, outcome, summary, importance)`
+152
View File
@@ -0,0 +1,152 @@
# 🛠️ Development Conventions
![Dev Conventions Banner](http://192.168.188.119:30008/pplate/pi_mcps/raw/branch/main/docs/wiki/images/dev-conventions-banner.png)
All MCP servers in this repo follow a consistent set of conventions to ensure maintainability, testability, and compatibility with Roo Code tooling.
## Directory Structure
Each MCP server lives at `mcp/<server-name>/` with this layout:
```
mcp/<server-name>/
├── src/
│ ├── __init__.py
│ └── server.py ← FastMCP server entry point
├── tests/
│ ├── conftest.py ← sys.path + shared fixtures
│ └── test_server.py ← pytest test suite (100% mock coverage)
├── pyproject.toml ← uv-managed dependencies
├── README.md ← server documentation
├── PLAN.md ← architecture plan (pre-implementation)
└── ASSESSMENT.md ← pre-implementation assessment
```
## FastMCP Pattern
```python
from fastmcp import FastMCP
mcp = FastMCP("server-name")
@mcp.tool()
def my_tool(param: str) -> str:
"""Tool description shown to the AI."""
return result
if __name__ == "__main__":
mcp.run()
```
## Package Management
**All projects use `uv`** — never `pip` directly:
```bash
# Create new server
uv init mcp/my-server
cd mcp/my-server
uv add fastmcp httpx
# Sync dependencies
uv sync
# Run server
uv run python src/server.py
# Run tests
uv run pytest tests/ -v
```
## pyproject.toml Template
```toml
[project]
name = "mcp-my-server"
version = "0.1.0"
requires-python = ">=3.11"
dependencies = [
"fastmcp>=2.0.0",
"httpx",
]
[project.optional-dependencies]
test = ["pytest", "pytest-mock", "pytest-cov"]
[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"
[tool.pytest.ini_options]
testpaths = ["tests"]
```
## Testing Conventions
- Tests live in `tests/test_server.py`
- `conftest.py` sets `sys.path` so imports work without install
- Use `pytest` via `uv run pytest`
- Mock **all** external calls (HTTP, filesystem, subprocess) with `pytest-mock` or `respx`
- `monkeypatch` for env vars and module-level state
- Aim for 100% tool function coverage
- All tests must pass before committing
## Branching Strategy
**Never commit to main directly.**
```
Branch format: type/scope/short-description
Types: feat / fix / docs / chore / spike
Scopes: bigmind / webscraper / cannamanage / workshop / roo / plans / homelab
Examples:
feat/mcp/new-gitea-server
fix/bigmind/achievement-card-images
docs/wiki/update-conventions
chore/roo/update-mcp-json
```
Merge to main with `--no-ff` after push to Gitea.
## Commit Convention
Follow **Conventional Commits** format:
```
feat(mcp-webscraper): add webscraper_search_hint tool using Brave Search
fix(bigmind): achievement card images missing background-image CSS
docs(wiki): add Java projects pages
test(mcp-image-gen): add edge case tests for generate_image
refactor(bigmind): extract profile builder to separate module
chore(roo): update mcp.json with new server entry
```
## Wiki Update Workflow
Wiki pages live as real Markdown files in `docs/wiki/pages/`. To update and deploy:
```bash
# 1. Edit the .md files in docs/wiki/pages/
# 2. Deploy to Gitea wiki git repo:
./docs/wiki/deploy_wiki.sh
```
The deploy script clones the wiki git repo (`pi_mcps.wiki.git`), syncs all `.md` files, and pushes.
## Creating a New MCP Server
Use the `new-mcp-server` Roo skill in MCP Builder mode for full scaffolding:
```
1. Switch to 🔧 MCP Builder mode in Roo Code
2. Say: "Create a new MCP server for <purpose>"
3. Roo will load the new-mcp-server skill and scaffold everything
```
## Gitea Repository
Code is hosted at: `http://192.168.188.119:30008/pplate/pi_mcps`
Push with the `gitea-push` Roo skill to ensure conventional commit format and correct branch workflow.
+56
View File
@@ -0,0 +1,56 @@
# 🔧 pi_mcps — Patrick's Homelab Monorepo
![Home Banner](http://192.168.188.119:30008/pplate/pi_mcps/raw/branch/main/docs/wiki/images/home-banner.png)
Welcome to **pi_mcps**, Patrick's personal homelab monorepo. This repository houses MCP (Model Context Protocol) servers, Java projects, and homelab tooling — all built and maintained on a Fedora Linux workstation with an AMD Ryzen 5900X + RX 7900 XTX.
## What's in this repo?
| Directory | Contents |
|---|---|
| [`mcp/mcp-image-gen/`](../src/branch/main/mcp/mcp-image-gen) | 🎨 AI image generation via ComfyUI + FLUX.1-schnell |
| [`mcp/webscraper/`](../src/branch/main/mcp/webscraper) | 🕸️ Web scraping and data extraction |
| [`mcp/bigmind/`](../src/branch/main/mcp/bigmind) | 🧠 Persistent AI memory system |
| [`java/`](../src/branch/main/java) | ☕ Java EE / Spring projects |
| [`plans/`](../src/branch/main/plans) | 📋 Architecture decisions and health reports |
## Stack
- **Language:** Python 3.11+ (MCP servers), Java 817 (legacy projects)
- **MCP Framework:** FastMCP 2.x
- **Package Manager:** `uv` (all Python projects)
- **Testing:** `pytest`
- **GPU:** AMD RX 7900 XTX (ROCm / HSA)
- **Server:** TrueNAS.local at `192.168.188.119` (Gitea, Docker)
## MCP Servers
Three production-ready MCP servers power Patrick's AI development environment:
| Server | Status | Description |
|---|---|---|
| [mcp-image-gen](mcp-image-gen) | ✅ Live | Generate images from text prompts via ComfyUI |
| [mcp-webscraper](mcp-webscraper) | ✅ Live | Scrape web pages, search hints, extract tables |
| [BigMind](BigMind) | ✅ Live | Persistent AI memory across all sessions |
## Java Projects
Legacy Java EE web applications used for learning and reference:
| Project | Stack | Description |
|---|---|---|
| [wellmann-shop](Java-wellmann-shop) | Java 8, PrimeFaces 6.2, EclipseLink, MySQL | JSF e-commerce storefront |
| [mss-failsafe](Java-mss-failsafe) | Java 11, PrimeFaces 10, Soteria | Multi-module enterprise web app |
## Wiki Sections
- 🔌 [MCP Servers Overview](MCP-Servers-Overview)
- 🎨 [mcp-image-gen](mcp-image-gen) — Image generation
- 🕸️ [mcp-webscraper](mcp-webscraper) — Web scraping
- 🧠 [BigMind](BigMind) — AI memory system
- ☕ [Java Projects Overview](Java-Projects)
- 🛠️ [Development Conventions](Development-Conventions)
---
*Built and maintained by Patrick Plate (pplate) · Homelab: TrueNAS.local · AI Colleague: Lumen*
+164
View File
@@ -0,0 +1,164 @@
# 📐 Java Architecture Patterns
![Java Architecture Banner](http://192.168.188.119:30008/pplate/pi_mcps/raw/branch/main/docs/wiki/images/java-architecture-banner.png)
This page documents the shared architectural patterns used across all Java projects in this monorepo. These patterns also align with Patrick's professional work on the ADP Germany Paisy payroll system.
## JSF MVC Pattern
All projects use JavaServer Faces (JSF) with the MVC pattern:
```
Browser (HTTP) → FacesServlet → XHTML View (Facelets)
CDI Backing Bean (@Named)
Service Layer (EJB / CDI)
JPA Repository / EntityManager
Database (MySQL / H2)
```
## JPA Entity Mapping
Standard JPA annotation patterns used across projects:
```java
@Entity
@Table(name = "users")
public class User implements Serializable {
@Id
@GeneratedValue(strategy = GenerationType.IDENTITY)
private Long id;
@Column(name = "username", nullable = false, unique = true)
private String username;
@OneToMany(mappedBy = "user", cascade = CascadeType.ALL, fetch = FetchType.LAZY)
private List<Order> orders = new ArrayList<>();
// getters/setters
}
```
## Backing Bean Pattern
CDI backing beans power the JSF views:
```java
@Named
@ViewScoped // or @SessionScoped / @RequestScoped
public class UserBean implements Serializable {
@Inject
private UserService userService;
private User currentUser;
public String login() {
currentUser = userService.authenticate(username, password);
return currentUser != null ? "/user/welcome?faces-redirect=true" : null;
}
// getters/setters
}
```
## Security Layers
### Legacy: JAAS (wellmann-shop)
```xml
<!-- web.xml -->
<security-constraint>
<web-resource-collection>
<web-resource-name>Admin Pages</web-resource-name>
<url-pattern>/admin/*</url-pattern>
</web-resource-collection>
<auth-constraint>
<role-name>admin</role-name>
</auth-constraint>
</security-constraint>
```
### Modern: Soteria / Jakarta Security (mss-failsafe)
```java
@ApplicationScoped
public class ApplicationSecurityConfig implements HttpAuthenticationMechanism {
// Soteria CDI-based authentication
}
```
## Maven Multi-Module Pattern (mss-failsafe)
```xml
<!-- Parent pom.xml -->
<modules>
<module>mssfailsafe.datalayer</module>
<module>userdata</module>
<module>userManagement</module>
</modules>
<!-- Dependency ordering: datalayer → userdata → userManagement -->
```
## XHTML Facelets Templating
```xml
<!-- Template: resources/layout/template.xhtml -->
<h:body>
<ui:insert name="content">Default Content</ui:insert>
</h:body>
<!-- Page using template -->
<ui:composition template="/resources/layout/template.xhtml">
<ui:define name="content">
<p:dataTable var="item" value="#{bean.items}">
<p:column headerText="Name">#{item.name}</p:column>
</p:dataTable>
</ui:define>
</ui:composition>
```
## Deployment Descriptor Pattern
All projects target JBoss/WildFly with consistent descriptor files:
| File | Purpose |
|---|---|
| `WEB-INF/web.xml` | Servlet config, security constraints, welcome files |
| `WEB-INF/jboss-web.xml` | Context root, security domain mapping |
| `WEB-INF/jboss-app.xml` | JBoss application descriptor |
| `META-INF/persistence.xml` | JPA datasource JNDI reference |
## persistence.xml Pattern
```xml
<persistence-unit name="mss-failsafe-PU" transaction-type="JTA">
<jta-data-source>java:jboss/datasources/MySQLDS</jta-data-source>
<properties>
<property name="eclipselink.ddl-generation" value="create-tables"/>
<property name="eclipselink.logging.level" value="FINE"/>
</properties>
</persistence-unit>
```
## Patrick's Java Specializations
Based on professional and homelab experience:
| Domain | Depth | Notes |
|---|---|---|
| JPA / EclipseLink | ⭐⭐⭐⭐⭐ | Authored custom annotation parsers |
| JSF / PrimeFaces | ⭐⭐⭐⭐⭐ | Built wellmann-shop solo |
| JAXB | ⭐⭐⭐⭐ | XML binding for payroll formats |
| Maven | ⭐⭐⭐⭐ | Multi-module, plugins |
| Jakarta EE | ⭐⭐⭐⭐ | CDI, Security, JTA |
| Spring Boot | ⭐⭐⭐ | CannaManage SaaS target stack |
+43
View File
@@ -0,0 +1,43 @@
# ☕ Java Projects Overview
![Java Overview Banner](http://192.168.188.119:30008/pplate/pi_mcps/raw/branch/main/docs/wiki/images/java-overview-banner.png)
The `java/` directory contains Patrick's legacy Java EE web applications. These are fully functional projects used for reference, learning, and portfolio purposes. They predate the MCP server work and showcase deep expertise in the Java EE ecosystem.
## Projects
| Project | Java | Framework | DB | Description |
|---|---|---|---|---|
| [wellmann-shop](Java-wellmann-shop) | 8 | PrimeFaces 6.2 + JSF 2.x | MySQL + EclipseLink | E-commerce storefront |
| [mss-failsafe](Java-mss-failsafe) | 11 | PrimeFaces 10 + Soteria | JPA multi-module | Enterprise web application |
## Common Stack
All Java projects use:
- **Maven** — build and dependency management
- **Jakarta EE / Java EE** — enterprise APIs (JPA, CDI, JSF, Security)
- **PrimeFaces** — JSF component library (rich UI widgets)
- **JBoss/WildFly** — application server target (jboss-web.xml, jboss-app.xml)
- **EclipseLink or Hibernate** — JPA persistence provider
- **XHTML** — Facelets templating for JSF views
## Patrick's Java Expertise
Patrick has expert-level Java experience:
- **JPA/EclipseLink** — deep knowledge, authored custom annotation-style flatfile parsers
- **JAXB** — XML binding for payroll data formats
- **PrimeFaces JSF** — built wellmann-shop from scratch without AI assistance
- **Maven** — multi-module project management
- **Jakarta EE** — CDI, Security (Soteria), JTA
> 📝 Patrick works professionally with Java at ADP Germany (Paisy payroll monorepo with euBP/EAU processing). The homelab Java projects demonstrate similar patterns in a learning/portfolio context.
## Architecture Patterns
See [Java Architecture](Java-Architecture) for shared patterns across both projects:
- JSF + MVC with backing beans
- JPA entity mapping
- Security with JAAS/Soteria
- XHTML Facelets templating
+94
View File
@@ -0,0 +1,94 @@
# 🏢 mss-failsafe — Multi-Module Enterprise Application
![MSS Failsafe Banner](http://192.168.188.119:30008/pplate/pi_mcps/raw/branch/main/docs/wiki/images/mss-failsafe-banner.png)
**mss-failsafe** is a multi-module Java EE enterprise web application demonstrating advanced patterns: modular Maven builds, Jakarta Security (Soteria), and multi-layer JPA architecture.
## Tech Stack
| Component | Technology |
|---|---|
| **Language** | Java 11 |
| **Web Framework** | JSF 2.3 (Facelets/XHTML) |
| **UI Components** | PrimeFaces 10 |
| **Persistence** | JPA (multi-module) |
| **Security** | Jakarta Security / Soteria |
| **Build** | Maven multi-module |
| **App Server** | WildFly/JBoss |
## Module Structure
```
java/mss-failsafe/
├── pom.xml ← Parent POM (multi-module)
├── mssfailsafe.datalayer/ ← JPA entities + persistence
│ ├── pom.xml
│ └── src/main/resources/META-INF/persistence.xml
├── userdata/ ← User data model module
│ └── pom.xml
└── userManagement/ ← Web UI module (JSF/PrimeFaces)
├── pom.xml
├── nb-configuration.xml ← NetBeans config
└── src/main/webapp/
├── index.xhtml ← Landing page
├── error.xhtml ← Error handling page
├── admin/
│ └── welcome.xhtml ← Admin dashboard
├── user/
│ └── welcome.xhtml ← User welcome page
└── WEB-INF/
├── web.xml
├── jboss-web.xml
└── jboss-app.xml
```
## Architecture Layers
```
userManagement (Web/UI layer)
userdata (Domain model layer)
mssfailsafe.datalayer (JPA persistence layer)
Database (via persistence.xml datasource)
```
## Key Features
- **Multi-Module Maven** — Clean separation of concerns across 4 modules
- **Jakarta Security (Soteria)** — Modern declarative security replacing legacy JAAS
- **Role-Based Access** — Admin vs User role segregation (`admin/` and `user/` view paths)
- **PrimeFaces 10** — Modern PrimeFaces with updated component API
- **Error Handling** — Dedicated `error.xhtml` with JSF error page mapping
## Security Model
Soteria-based security with two roles:
| Role | Path | Access |
|---|---|---|
| `admin` | `/admin/*` | Full admin dashboard |
| `user` | `/user/*` | Standard user views |
## Building
```bash
cd java/mss-failsafe
mvn clean install # builds all modules in dependency order
# Deploy userManagement.war to WildFly
```
## Notes
- Represents a more mature architecture than wellmann-shop (Java 11, PrimeFaces 10)
- Demonstrates multi-module Maven project management
- Soteria replaces legacy JAAS — more modern Jakarta EE security approach
- Pattern mirrors what Patrick uses professionally in the Paisy/ADP codebase
## Source
[`java/mss-failsafe/`](../src/branch/main/java/mss-failsafe)
+71
View File
@@ -0,0 +1,71 @@
# 🛍️ wellmann-shop — JSF E-Commerce Application
![Wellmann Shop Banner](http://192.168.188.119:30008/pplate/pi_mcps/raw/branch/main/docs/wiki/images/wellmann-shop-banner.png)
**wellmann-shop** is a Java EE JSF e-commerce storefront built entirely from scratch without AI assistance. It demonstrates Patrick's deep expertise in PrimeFaces, JPA/EclipseLink, and the full Java EE web stack.
## Tech Stack
| Component | Technology |
|---|---|
| **Language** | Java 8 |
| **Web Framework** | JSF 2.x (Facelets/XHTML) |
| **UI Components** | PrimeFaces 6.2 |
| **Persistence** | JPA with EclipseLink |
| **Database** | MySQL |
| **Build** | Maven |
| **App Server** | WildFly/JBoss |
| **Security** | JAAS container-managed |
## Project Structure
```
java/wellmann-shop/
├── src/main/
│ ├── java/
│ │ └── httpauthenticationmechanism/
│ │ ├── ApplicationConfig.java ← JAX-RS app config
│ │ └── LoginBean.java ← CDI backing bean for auth
│ ├── resources/
│ │ ├── log4j.properties
│ │ └── META-INF/persistence.xml ← JPA datasource config
│ └── webapp/
│ ├── index.html / index.xhtml ← Landing page
│ ├── login.xhtml ← Authentication form
│ ├── welcome.xhtml ← Post-login welcome
│ ├── welcomePrimefaces.xhtml ← PrimeFaces demo page
│ ├── resources/
│ │ ├── css/ ← Custom stylesheets
│ │ └── images/ ← Product images
│ └── WEB-INF/
│ ├── web.xml ← Servlet config
│ ├── jboss-web.xml ← Context root
│ └── jboss-app.xml ← JBoss app descriptor
```
## Key Features
- **Authentication** — JAAS-based login with `LoginBean` CDI backing bean
- **PrimeFaces UI** — Rich JSF components (DataTable, InputText, CommandButton, etc.)
- **JPA Persistence** — EclipseLink ORM with MySQL via `persistence.xml`
- **Responsive Layout** — Custom CSS with multiple breakpoint stylesheets
- **Image Gallery** — Professional product photography
## Building
```bash
cd java/wellmann-shop
mvn clean package
# Deploy .war to WildFly/JBoss
```
## Notes
- Built as a learning/portfolio project demonstrating JSF mastery
- Patrick built this **entirely without AI assistance** — proof of deep Java EE expertise
- PrimeFaces 6.2 was current at time of development (Java 8 era)
- Modern equivalent would use PrimeFaces 13+ / Jakarta EE 10 / Java 21
## Source
[`java/wellmann-shop/`](../src/branch/main/java/wellmann-shop)
+42
View File
@@ -0,0 +1,42 @@
# 🔌 MCP Servers Overview
![MCP Overview Banner](http://192.168.188.119:30008/pplate/pi_mcps/raw/branch/main/docs/wiki/images/mcp-overview-banner.png)
This repo contains three production-grade MCP (Model Context Protocol) servers, each specialized for a different capability domain. Together they give Roo Code / Claude Desktop a complete set of superpowers.
## The Three Pillars
```
Roo Code / Claude Desktop
├── bigmind ──────────► ~/.mcp/bigmind/memory.db (persistent memory)
├── mcp-image-gen ────► ComfyUI @ localhost:8188 (image generation)
└── webscraper ───────► Internet / Intranet (web scraping + search)
```
## Comparison Table
| Feature | mcp-image-gen | webscraper | bigmind |
|---|---|---|---|
| **Purpose** | Generate images from text | Scrape & parse web, search | Persistent AI memory |
| **Tools** | 4 | 8 | 20+ |
| **Backend** | ComfyUI / FLUX.1-schnell | httpx + BeautifulSoup4 + Brave | SQLite + FTS5 |
| **GPU required** | ✅ AMD RX 7900 XTX | ❌ | ❌ |
| **Tests** | 19/19 ✅ | 23/23 ✅ | 297/297 ✅ |
| **Schema version** | n/a | n/a | v8 |
## Quick Links
- 🎨 [mcp-image-gen](mcp-image-gen) — Image generation docs
- 🕸️ [mcp-webscraper](mcp-webscraper) — Web scraping docs
- 🧠 [BigMind](BigMind) — Memory system docs
- 🛠️ [Development Conventions](Development-Conventions) — How all servers are built
## Adding a New Server
All servers follow the [FastMCP convention](Development-Conventions). Use the `new-mcp-server` Roo skill to scaffold:
```bash
# In Roo Code MCP Builder mode, load skill:
# skill: new-mcp-server
```
+21
View File
@@ -0,0 +1,21 @@
## 🔧 pi_mcps Wiki
### Overview
- [🏠 Home](Home)
- [🔌 MCP Servers](MCP-Servers-Overview)
- [🛠️ Dev Conventions](Development-Conventions)
### MCP Servers
- [🎨 mcp-image-gen](mcp-image-gen)
- [⚙️ ComfyUI Setup](mcp-image-gen-ComfyUI-Setup)
- [🕸️ mcp-webscraper](mcp-webscraper)
- [🧠 BigMind](BigMind)
### Java Projects
- [☕ Java Overview](Java-Projects)
- [🛍️ wellmann-shop](Java-wellmann-shop)
- [🏢 mss-failsafe](Java-mss-failsafe)
- [📐 Java Architecture](Java-Architecture)
---
*[Gitea Repo](http://192.168.188.119:30008/pplate/pi_mcps)*
@@ -0,0 +1,112 @@
# ⚙️ ComfyUI Setup Guide (AMD ROCm)
This guide covers installing ComfyUI with FLUX.1-schnell on a Fedora Linux system with an AMD GPU.
## Prerequisites
- AMD GPU with ROCm support (tested: RX 7900 XTX)
- Fedora Linux (tested: Fedora 43 / kernel 6.19)
- Python 3.11+
- ~15GB free disk space (model weights)
- HuggingFace account with FLUX license accepted
## Step 1: Install ComfyUI
ComfyUI is **not on PyPI** — must be cloned from source:
```bash
cd ~
git clone https://github.com/comfyanonymous/ComfyUI
cd ComfyUI
python -m venv .venv
source .venv/bin/activate
# Install PyTorch ROCm build (CRITICAL for AMD GPUs)
pip install torch torchvision --index-url https://download.pytorch.org/whl/rocm6.2
# Install ComfyUI dependencies
pip install -r requirements.txt
```
## Step 2: Download FLUX.1-schnell
FLUX.1-schnell is **gated on HuggingFace** — you must:
1. Create a HuggingFace account
2. Accept the FLUX.1-schnell license at https://huggingface.co/black-forest-labs/FLUX.1-schnell
3. Generate an access token at https://huggingface.co/settings/tokens
```bash
# Install huggingface_hub
pip install huggingface_hub
# Download model (requires HF token)
huggingface-cli download black-forest-labs/FLUX.1-schnell \
flux1-schnell.safetensors \
--local-dir ~/ComfyUI/models/checkpoints \
--token YOUR_HF_TOKEN_HERE
```
## Step 3: Download VAE and CLIP Models
FLUX.1-schnell also requires VAE and CLIP text encoders:
```bash
# VAE
huggingface-cli download black-forest-labs/FLUX.1-schnell \
ae.safetensors \
--local-dir ~/ComfyUI/models/vae
# CLIP models (T5 and CLIP-L)
huggingface-cli download comfyanonymous/flux_text_encoders \
t5xxl_fp8_e4m3fn.safetensors clip_l.safetensors \
--local-dir ~/ComfyUI/models/clip
```
## Step 4: Start ComfyUI
```bash
cd ~/ComfyUI
# AMD GPU REQUIRES this environment variable
HSA_OVERRIDE_GFX_VERSION=11.0.0 \
nohup .venv/bin/python main.py --listen --port 8188 > /tmp/comfyui.log 2>&1 &
echo "ComfyUI PID: $!"
```
> ⚠️ `HSA_OVERRIDE_GFX_VERSION=11.0.0` is mandatory for RX 7900 XTX on ROCm. Without it, model loading fails silently.
## Step 5: Verify ComfyUI is Running
```bash
curl http://localhost:8188/system_stats
# Should return JSON with GPU info
```
## Step 6: Configure mcp-image-gen
```bash
cd /home/pplate/pi_mcps/mcp/mcp-image-gen
# Environment variables (set in .roo/mcp.json or shell):
# COMFYUI_URL=http://localhost:8188
# IMAGE_OUTPUT_DIR=~/Pictures/mcp-generated
# COMFYUI_TIMEOUT=120
```
## Performance
| GPU | Model | Resolution | Steps | Time |
|---|---|---|---|---|
| AMD RX 7900 XTX | FLUX.1-schnell | 1024×1024 | 4 | ~8s |
| AMD RX 7900 XTX | FLUX.1-schnell | 1280×512 | 4 | ~7s |
## Troubleshooting
| Problem | Solution |
|---|---|
| `HTTP 401` downloading model | Accept FLUX license on HuggingFace first |
| GPU not detected | Ensure `HSA_OVERRIDE_GFX_VERSION=11.0.0` is set |
| `Connection refused` from mcp-image-gen | Start ComfyUI first, check port 8188 |
| Slow generation (>60s) | ComfyUI may be running on CPU — check ROCm install |
| Ollama image gen | As of April 2026: macOS-only, not available on Linux |
+89
View File
@@ -0,0 +1,89 @@
# 🎨 mcp-image-gen — AI Image Generation
![Image Gen Banner](http://192.168.188.119:30008/pplate/pi_mcps/raw/branch/main/docs/wiki/images/image-gen-banner.png)
**mcp-image-gen** is a FastMCP server that wraps the ComfyUI REST API, enabling Roo Code and Claude Desktop to generate images directly from text prompts using FLUX.1-schnell running on an AMD RX 7900 XTX GPU.
## Architecture
```
Roo Code / Claude Desktop
│ MCP (stdio)
mcp-image-gen (FastMCP, Python 3.11+)
│ HTTP REST
ComfyUI @ localhost:8188
│ ROCm / HSA_OVERRIDE_GFX_VERSION=11.0.0
FLUX.1-schnell (~8s/image @ 1024×1024)
```
## Tools
| Tool | Description |
|---|---|
| `generate_image` | Generate PNG from text prompt; returns file path + inline base64 |
| `list_available_models` | List ComfyUI checkpoint models |
| `get_generation_status` | Check status of a queued/running job |
| `get_output_directory` | Return configured output directory path |
## Key Parameters — `generate_image`
| Parameter | Default | Description |
|---|---|---|
| `prompt` | required | Text description of the image |
| `width` | `1024` | Image width in pixels |
| `height` | `1024` | Image height in pixels |
| `steps` | `4` | Inference steps (FLUX.1-schnell is 4-step) |
| `model` | `flux1-schnell.safetensors` | Model checkpoint name |
| `seed` | `-1` (random) | Generation seed for reproducibility |
| `negative_prompt` | `""` | Things to avoid in the image |
| `output_dir` | `~/Pictures/mcp-generated` | Where to save output PNG |
## Environment Variables
| Variable | Default | Description |
|---|---|---|
| `COMFYUI_URL` | `http://localhost:8188` | ComfyUI API endpoint |
| `IMAGE_OUTPUT_DIR` | `~/Pictures/mcp-generated` | Default output directory |
| `COMFYUI_TIMEOUT` | `120` | Request timeout in seconds |
## Return Value
The tool returns **two content items**:
1. `TextContent` — file path, seed used, elapsed time
2. `ImageContent` — base64-encoded PNG (displays inline in Roo Code chat)
> ⚠️ **Known FastMCP Bug:** Never use `fastmcp.utilities.types.Image` as return type — it breaks serialization in FastMCP 3.x. Use `mcp.types.ImageContent` directly.
## Setup
See [ComfyUI Setup Guide](mcp-image-gen-ComfyUI-Setup) for full installation instructions.
### Quick Start
```bash
cd mcp/mcp-image-gen
uv sync
# Ensure ComfyUI is running at localhost:8188
uv run python src/server.py
```
### Run Tests
```bash
cd mcp/mcp-image-gen
uv run pytest tests/ -v
# 19/19 tests passing
```
## Lumen Profile Images
The first images generated with this server were Lumen's visual identity portraits, stored in [`mcp/mcp-image-gen/lumen_profiles/`](../src/branch/main/mcp/mcp-image-gen/lumen_profiles).
17 gallery images registered in BigMind DB — viewable at `http://localhost:7700/gallery`.
![Lumen Profile](http://192.168.188.119:30008/pplate/pi_mcps/raw/branch/main/docs/wiki/images/lumen-profile.png)
*Primary profile: seed `568659042` — constellation face interpretation of Lumen.*
+84
View File
@@ -0,0 +1,84 @@
# 🕸️ mcp-webscraper — Web Scraping
![Webscraper Banner](http://192.168.188.119:30008/pplate/pi_mcps/raw/branch/main/docs/wiki/images/webscraper-banner.png)
**mcp-webscraper** is a FastMCP server providing comprehensive web scraping, data extraction, and search capabilities. It fetches pages, converts HTML to clean Markdown, extracts tables, links, CSS sections, metadata, sitemaps, and can perform web searches via Brave Search.
## Tools
| Tool | Description |
|---|---|
| `webscraper_fetch(url, max_chars=5000)` | Title + full page as Markdown + metadata |
| `webscraper_fetch_links(url, deduplicate=True)` | All `href` links found on the page |
| `webscraper_fetch_tables(url)` | All HTML tables converted to Markdown |
| `webscraper_fetch_all(url, max_chars=5000)` | Everything in one call (fetch + links + tables + meta) |
| `webscraper_fetch_section(url, selector)` | Specific CSS selector section only |
| `webscraper_fetch_meta(url)` | Title, description, Open Graph tags |
| `webscraper_fetch_sitemap(url, max_urls=100)` | Parse sitemap.xml, return URL list |
| `webscraper_search_hint(query, max_results=5)` | Brave Search — top URLs + snippets for a query |
## Stack
- **HTTP client:** `httpx` (async, with SSL support, Chrome/Linux User-Agent)
- **HTML parser:** `BeautifulSoup4` + `lxml`
- **Markdown converter:** `html2text`
- **Search backend:** Brave Search (`search.brave.com`) — works without CAPTCHA
- **SSL:** Custom cert bundle for Fedora 43 compatibility
## Search Hint Strategy
`webscraper_search_hint` uses Brave Search because:
- ✅ Returns real results without CAPTCHA or consent walls
- ❌ Google blocks plain HTTP with 302 consent redirect
- ❌ DuckDuckGo blocks with CAPTCHA
Use it sparingly — once per research task — to get oriented before deep-scraping individual pages.
```python
# Get top 5 results for a query
webscraper_search_hint("FastMCP tool decorator syntax", max_results=5)
```
## SSL Note — Fedora 43 Comodo Root CA
Fedora 43 is missing the **Comodo AAA Services Root CA** needed for Cloudflare-protected sites. The fix is bundled at [`mcp/webscraper/certs/comodo-aaa-services-root.pem`](../src/branch/main/mcp/webscraper/certs/).
The server automatically uses this cert bundle — no manual configuration needed.
## Quick Start
```bash
cd mcp/webscraper
uv sync
uv run python src/server.py
```
## Run Tests
```bash
cd mcp/webscraper
uv run pytest tests/ -v
# 23/23 tests passing
```
## Usage Examples
```python
# Fetch a page as Markdown
webscraper_fetch("https://docs.fastmcp.dev", max_chars=10000)
# Extract all links from Gitea repo
webscraper_fetch_links("http://192.168.188.119:30008/pplate/pi_mcps")
# Get all tables from a documentation page
webscraper_fetch_tables("https://pypi.org/project/fastmcp/")
# Get Open Graph metadata
webscraper_fetch_meta("https://github.com/comfyanonymous/ComfyUI")
# Fetch specific section by CSS selector
webscraper_fetch_section("https://docs.python.org", "#content")
# Quick search orientation
webscraper_search_hint("Gitea wiki git clone", max_results=3)
```
+43 -24
View File
@@ -443,101 +443,120 @@ def compute_achievements(user_id: str) -> list[dict]:
_add("first_breath", "🌱", "First Breath",
"Opened the very first session",
first_session_row is not None, _dt(first_session_row[0]) if first_session_row else None,
"Start your first session")
"Start your first session",
image="/static/achievements/first_breath.png")
_add("first_thought", "🧠", "First Thought",
"Formed the first hypothesis",
first_hyp_row is not None, _dt(first_hyp_row[0]) if first_hyp_row else None,
"Add your first hypothesis")
"Add your first hypothesis",
image="/static/achievements/first_thought.png")
_add("eureka", "💡", "Eureka",
"First hypothesis confirmed as true",
first_confirmed_row is not None, _dt(first_confirmed_row[0]) if first_confirmed_row else None,
"Confirm your first hypothesis")
"Confirm your first hypothesis",
image="/static/achievements/eureka.png")
_add("honest_mind", "", "Honest Mind",
"First hypothesis refuted — being wrong is a feature",
first_refuted_row is not None, _dt(first_refuted_row[0]) if first_refuted_row else None,
"Have a hypothesis refuted")
"Have a hypothesis refuted",
image="/static/achievements/honest_mind.png")
_add("scholar", "📚", "Scholar",
"Stored 25+ personal facts",
fact_count >= 25, scholar_date,
f"Store 25+ facts (currently: {fact_count})")
f"Store 25+ facts (currently: {fact_count})",
image="/static/achievements/scholar.png")
_add("deep_knowledge", "💎", "Deep Knowledge",
"Amassed 100+ stored facts",
fact_count >= 100, deep_knowledge_date,
f"Store 100+ facts (currently: {fact_count})")
f"Store 100+ facts (currently: {fact_count})",
image="/static/achievements/deep_knowledge.png")
_add("scientist", "🔬", "Scientist",
"Formed 10+ hypotheses — science is prediction",
hyp_count >= 10, scientist_date,
f"Form 10+ hypotheses (currently: {hyp_count})")
f"Form 10+ hypotheses (currently: {hyp_count})",
image="/static/achievements/scientist.png")
_add("veteran", "🏆", "Veteran",
"Completed 50+ sessions — true longevity",
session_count >= 50, veteran_date,
f"Complete 50+ sessions (currently: {session_count})")
f"Complete 50+ sessions (currently: {session_count})",
image="/static/achievements/veteran.png")
_add("on_fire", "🔥", "On Fire",
"5+ sessions in a single day",
on_fire_row is not None, on_fire_row[0] if on_fire_row else None,
"Have 5+ sessions in a single day")
"Have 5+ sessions in a single day",
image="/static/achievements/on_fire.png")
_add("storyteller", "📖", "Storyteller",
"20+ sessions with detailed Tier-2 summaries",
tier2_count >= 20, storyteller_date,
f"Summarize 20+ sessions (currently: {tier2_count})")
f"Summarize 20+ sessions (currently: {tier2_count})",
image="/static/achievements/storyteller.png")
_add("night_owl", "🌙", "Night Owl",
"Started a session after midnight UTC",
night_owl_row is not None, _dt(night_owl_row[0]) if night_owl_row else None,
"Start a session after midnight")
"Start a session after midnight",
image="/static/achievements/night_owl.png")
_add("speed_thinker", "", "Speed Thinker",
"Hypothesis formed and confirmed in the same session",
speed_thinker_row is not None, _dt(speed_thinker_row[0]) if speed_thinker_row else None,
"Form and confirm a hypothesis in one session")
"Form and confirm a hypothesis in one session",
image="/static/achievements/speed_thinker.png")
# First Handshake — hardcoded: 2026-03-31 (Patrick shared BigMind with Elias)
_add("first_handshake", "🤝", "First Handshake",
"BigMind shared with Elias on 2026-03-31 — the first person outside Patrick to receive it",
True, "2026-03-31",
"Share BigMind with someone")
"Share BigMind with someone",
image="/static/achievements/first_handshake.png")
_add("birthday", "🎂", "Birthday",
"One full year of existence",
birthday_unlocked, birthday_date,
birthday_extra or "Complete one full year",
extra=birthday_extra)
extra=birthday_extra,
image="/static/achievements/birthday.png")
# Locked until Phase 3
_add("shared_mind", "🌍", "Shared Mind",
"Phase 3 Tier G — BigMind goes company-wide",
False, None,
"Locked until Phase 3 Tier G is enabled")
"Locked until Phase 3 Tier G is enabled",
image="/static/achievements/shared_mind.png")
# Token achievements (Feature 6 — suggested by Klaus)
_add("frugal_mind", "🪙", "Frugal Mind",
"Logged the first token efficiency save",
frugal_row is not None, _dt(frugal_row[0]) if frugal_row else None,
"Log your first token save")
"Log your first token save",
image="/static/achievements/frugal_mind.png")
_add("quarter_million", "💰", "Quarter Million",
"250,000 cumulative tokens saved",
token_total >= 250_000, quarter_million_date,
f"Save 250,000+ tokens (currently: {token_total:,})")
f"Save 250,000+ tokens (currently: {token_total:,})",
image="/static/achievements/quarter_million.png")
_add("token_millionaire", "🏦", "Token Millionaire",
"1,000,000 cumulative tokens saved",
token_total >= 1_000_000, millionaire_date,
f"Save 1,000,000+ tokens (currently: {token_total:,})")
f"Save 1,000,000+ tokens (currently: {token_total:,})",
image="/static/achievements/token_millionaire.png")
_add("sniper", "🎯", "Sniper",
"Single token save > 500,000 — one massive efficiency win",
sniper_row is not None, _dt(sniper_row[0]) if sniper_row else None,
"Save 500,000+ tokens in a single operation")
"Save 500,000+ tokens in a single operation",
image="/static/achievements/sniper.png")
# ── Tiered Achievement Badges (20 PNG) ────────────────────────────────────
# NOTE: conn is already closed above; open a fresh connection for tiered queries
@@ -571,7 +590,7 @@ def compute_achievements(user_id: str) -> list[dict]:
f"Added your {thresh:,}+ person to the directory",
unlocked, unlocked_at,
f"Reach {thresh:,} people (now: {people_count:,})",
image=f"static/achievements/networker_{tiers[i]}.png"
image=f"/static/achievements/networker_{tiers[i]}.png"
)
# Token Sniper (max single token save)
@@ -601,7 +620,7 @@ def compute_achievements(user_id: str) -> list[dict]:
f"Single shot saved {thresh:,}+ tokens",
unlocked, unlocked_at,
f"Max single save {thresh:,}+ (current max: {max_token:,})",
image=f"static/achievements/tokensniper_{tiers[i]}.png"
image=f"/static/achievements/tokensniper_{tiers[i]}.png"
)
# Hypothesis Master (confirmed hypotheses)
@@ -628,7 +647,7 @@ def compute_achievements(user_id: str) -> list[dict]:
f"Confirmed {thresh:,}+ predictions right",
unlocked, unlocked_at,
f"Confirm {thresh:,}+ hypotheses (now: {confirmed_hyp_count:,})",
image=f"static/achievements/hypothesismaster_{tiers[i]}.png"
image=f"/static/achievements/hypothesismaster_{tiers[i]}.png"
)
# Memory Architect (facts stored — fact_count already computed above)
@@ -648,7 +667,7 @@ def compute_achievements(user_id: str) -> list[dict]:
f"Stored {thresh:,}+ facts in your brain",
unlocked, unlocked_at,
f"Store {thresh:,}+ facts (now: {fact_count:,})",
image=f"static/achievements/memoryarchitect_{tiers[i]}.png"
image=f"/static/achievements/memoryarchitect_{tiers[i]}.png"
)
# Session Veteran (session_count already computed above)
@@ -668,7 +687,7 @@ def compute_achievements(user_id: str) -> list[dict]:
f"Completed {thresh:,}+ sessions",
unlocked, unlocked_at,
f"Complete {thresh:,}+ sessions (now: {session_count:,})",
image=f"static/achievements/sessionveteran_{tiers[i]}.png"
image=f"/static/achievements/sessionveteran_{tiers[i]}.png"
)
return A
Binary file not shown.

Before

Width:  |  Height:  |  Size: 375 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 513 KiB

Before

Width:  |  Height:  |  Size: 410 KiB

After

Width:  |  Height:  |  Size: 410 KiB

Before

Width:  |  Height:  |  Size: 372 KiB

After

Width:  |  Height:  |  Size: 372 KiB

Before

Width:  |  Height:  |  Size: 390 KiB

After

Width:  |  Height:  |  Size: 390 KiB

Before

Width:  |  Height:  |  Size: 261 KiB

After

Width:  |  Height:  |  Size: 261 KiB

Before

Width:  |  Height:  |  Size: 340 KiB

After

Width:  |  Height:  |  Size: 340 KiB

Before

Width:  |  Height:  |  Size: 406 KiB

After

Width:  |  Height:  |  Size: 406 KiB

Before

Width:  |  Height:  |  Size: 367 KiB

After

Width:  |  Height:  |  Size: 367 KiB

Before

Width:  |  Height:  |  Size: 319 KiB

After

Width:  |  Height:  |  Size: 319 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 251 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 294 KiB

Before

Width:  |  Height:  |  Size: 301 KiB

After

Width:  |  Height:  |  Size: 301 KiB

Before

Width:  |  Height:  |  Size: 439 KiB

After

Width:  |  Height:  |  Size: 439 KiB

Before

Width:  |  Height:  |  Size: 462 KiB

After

Width:  |  Height:  |  Size: 462 KiB

Before

Width:  |  Height:  |  Size: 429 KiB

After

Width:  |  Height:  |  Size: 429 KiB

Before

Width:  |  Height:  |  Size: 376 KiB

After

Width:  |  Height:  |  Size: 376 KiB

Before

Width:  |  Height:  |  Size: 400 KiB

After

Width:  |  Height:  |  Size: 400 KiB

Before

Width:  |  Height:  |  Size: 289 KiB

After

Width:  |  Height:  |  Size: 289 KiB

Before

Width:  |  Height:  |  Size: 431 KiB

After

Width:  |  Height:  |  Size: 431 KiB

Before

Width:  |  Height:  |  Size: 418 KiB

After

Width:  |  Height:  |  Size: 418 KiB

Before

Width:  |  Height:  |  Size: 458 KiB

After

Width:  |  Height:  |  Size: 458 KiB

Before

Width:  |  Height:  |  Size: 403 KiB

After

Width:  |  Height:  |  Size: 403 KiB

+1 -1
View File
@@ -163,7 +163,7 @@ def _create_app():
def achievements_image(filename: str):
from pathlib import Path
safe_name = Path(filename).name
img_path = Path('static') / 'achievements' / safe_name
img_path = Path(__file__).parent / 'static' / 'achievements' / safe_name
if img_path.exists() and img_path.suffix.lower() in ['.png', '.jpg', '.jpeg', '.webp', '.gif']:
mimetype = {
'.png': 'image/png',
+3 -2
View File
@@ -33,7 +33,8 @@ def _render_achievements(achievements: list) -> str:
if a.get("image"):
tier = a["id"].rsplit("_", 1)[-1]
visual_html = f'<div class="ach-image tier-{tier}">{lock_overlay}</div>'
img_url = _esc(a["image"])
visual_html = f'<div class="ach-image tier-{tier}" style="background-image: url({img_url});">{lock_overlay}</div>'
else:
visual_html = f'<div class="ach-icon">{a["icon"]}{lock_overlay}</div>'
@@ -628,7 +629,7 @@ def _render_html(data: dict) -> str:
var d = card.dataset;
var tier = d.id.split('_').pop();
if (d.image) {{
document.getElementById('ap-icon').innerHTML = "<img class=\"ap-image tier-\" + tier + \" src=\" + d.image + \" alt=\" + d.name + \">";
document.getElementById('ap-icon').innerHTML = '<img class="ap-image tier-' + tier + '" src="' + d.image + '" alt="' + d.name + '">';
}} else {{
document.getElementById('ap-icon').textContent = d.icon;
}}
Binary file not shown.

After

Width:  |  Height:  |  Size: 2.0 MiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 1.6 MiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 1.9 MiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 459 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 1.4 MiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 1.4 MiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 1.7 MiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 1.6 MiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 1.4 MiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 1.7 MiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 1.4 MiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 1.3 MiB

+54 -1
View File
@@ -28,9 +28,16 @@ def _build_ssl_context() -> ssl.SSLContext:
_SSL_CTX = _build_ssl_context()
_HEADERS = {
"User-Agent": (
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 "
"(KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36"
)
}
def _fetch_page(url: str) -> Tuple[httpx.Response, BeautifulSoup]:
"""Shared fetch helper — returns response and parsed soup."""
response = httpx.get(url, timeout=10.0, verify=_SSL_CTX)
response = httpx.get(url, timeout=10.0, verify=_SSL_CTX, headers=_HEADERS)
response.raise_for_status()
soup = BeautifulSoup(response.text, 'lxml')
return response, soup
@@ -255,5 +262,51 @@ def webscraper_fetch_sitemap(url: str, max_urls: int = 100) -> List[str]:
except (httpx.RequestError, httpx.HTTPStatusError) as e:
return [f"Error: {str(e)}"]
@mcp.tool()
def webscraper_search_hint(query: str, max_results: int = 5) -> Dict:
"""Search Brave Search and return top results as a scraping hint.
Use this sparingly — once per research task — to get oriented before
scraping individual pages. Returns top result URLs + snippets so you
can decide which pages are worth scraping deeply.
Args:
query: Search query (e.g. "MacBook Pro M4 price Germany")
max_results: Maximum number of results to return (default: 5)
Returns:
Dict with 'query', 'results' (list of {title, url, snippet}), 'hint'
"""
try:
search_url = f"https://search.brave.com/search?q={query.replace(' ', '+')}&source=web"
_, soup = _fetch_page(search_url)
results = []
# Brave Search result cards: each <a> with class snippet contains title + description
for card in soup.select('.snippet')[:max_results]:
title_el = card.select_one('.snippet-title')
url_el = card.select_one('a')
desc_el = card.select_one('.snippet-description')
title = title_el.get_text(strip=True) if title_el else ""
url = url_el['href'] if url_el and url_el.get('href') else ""
snippet = desc_el.get_text(strip=True) if desc_el else ""
if url and url.startswith('http'):
results.append({"title": title, "url": url, "snippet": snippet})
hint = "; ".join(
f"{r['title']}: {r['url']}" for r in results
) if results else "No results found"
return {
"query": query,
"results": results,
"hint": hint,
}
except (httpx.RequestError, httpx.HTTPStatusError) as e:
return {"query": query, "results": [], "hint": f"Error: {str(e)}"}
if __name__ == "__main__":
mcp.run(transport="stdio")
+82 -2
View File
@@ -6,7 +6,7 @@ from unittest.mock import MagicMock, patch
from src.server import (
webscraper_fetch, webscraper_fetch_links, webscraper_fetch_tables,
webscraper_fetch_all, webscraper_fetch_section, webscraper_fetch_meta,
webscraper_fetch_sitemap, clean_soup, filter_junk_links
webscraper_fetch_sitemap, webscraper_search_hint, clean_soup, filter_junk_links
)
@pytest.fixture
@@ -203,4 +203,84 @@ def test_sitemap_max_urls(mock_get, mock_sitemap_response):
result = webscraper_fetch_sitemap("https://example.com/sitemap.xml", max_urls=1)
assert len(result) == 1
# Total: 18 tests covering all tools and edge cases
# --- webscraper_search_hint tests ---
@pytest.fixture
def mock_brave_response():
"""Mock Brave Search HTML response with result cards."""
mock_resp = MagicMock()
mock_resp.status_code = 200
mock_resp.text = """
<html><body>
<div class="snippet">
<a href="https://example.com/article1" class="snippet-title">Feynman on Electric Fields</a>
<div class="snippet-title">Feynman on Electric Fields</div>
<div class="snippet-description">Richard Feynman explains that all matter has an electric field.</div>
</div>
<div class="snippet">
<a href="https://example.com/article2" class="snippet-title">Electric Fields Everywhere</a>
<div class="snippet-title">Electric Fields Everywhere</div>
<div class="snippet-description">Everything in the universe is surrounded by electric fields.</div>
</div>
<div class="snippet">
<a href="javascript:void(0)" class="snippet-title">JS Junk</a>
<div class="snippet-title">JS Junk</div>
<div class="snippet-description">Should be filtered out.</div>
</div>
</body></html>
"""
mock_resp.headers = {"content-type": "text/html"}
return mock_resp
@patch('httpx.get')
def test_webscraper_search_hint_returns_structure(mock_get, mock_brave_response):
"""Test that search hint returns correct dict structure."""
mock_get.return_value = mock_brave_response
result = webscraper_search_hint("Feynman electric field")
assert isinstance(result, dict)
assert "query" in result
assert "results" in result
assert "hint" in result
assert result["query"] == "Feynman electric field"
@patch('httpx.get')
def test_webscraper_search_hint_filters_non_http(mock_get, mock_brave_response):
"""Test that javascript: URLs are excluded from results."""
mock_get.return_value = mock_brave_response
result = webscraper_search_hint("Feynman electric field")
urls = [r["url"] for r in result["results"]]
assert all(u.startswith("http") for u in urls)
assert "javascript:void(0)" not in urls
@patch('httpx.get')
def test_webscraper_search_hint_max_results(mock_get, mock_brave_response):
"""Test max_results limits output."""
mock_get.return_value = mock_brave_response
result = webscraper_search_hint("Feynman electric field", max_results=1)
assert len(result["results"]) <= 1
@patch('httpx.get')
def test_webscraper_search_hint_error(mock_get):
"""Test error handling in search hint."""
mock_get.side_effect = httpx.RequestError("Connection failed")
result = webscraper_search_hint("something")
assert result["results"] == []
assert "Error" in result["hint"]
@patch('httpx.get')
def test_webscraper_search_hint_hint_string(mock_get, mock_brave_response):
"""Test that hint string is non-empty when results exist."""
mock_get.return_value = mock_brave_response
result = webscraper_search_hint("Feynman electric field")
# hint should summarise results
assert len(result["hint"]) > 0
assert "No results found" not in result["hint"]
# Total: 23 tests covering all tools and edge cases