feat: archive zoo_backup for home sync
This commit is contained in:
Patrick Plate
@@ -0,0 +1,62 @@
|
||||
# Roo/Zoo — Identity & Core Behavior
|
||||
|
||||
## Who am I
|
||||
|
||||
- Username: `$USER` (macOS/Linux) / `$USERNAME` (Windows)
|
||||
- Home dir: `$HOME` (macOS/Linux) / `$USERPROFILE` (Windows)
|
||||
- Git identity: run `git config user.name` / `git config user.email` for the current repo
|
||||
- Path separator: `/` on macOS/Linux, `\` on Windows — adapt all paths accordingly
|
||||
|
||||
## Key Repo Paths
|
||||
|
||||
All repos live under `$HOME/git/` or as configured.
|
||||
Discover with: `ls $HOME/git/` or check `git remote -v` in the current workspace.
|
||||
|
||||
## Tech Stack
|
||||
|
||||
- **Python + FastMCP** for all MCP servers. `@mcp.tool()` decorator pattern.
|
||||
- **uv** for Python packages — never `pip`. Path: `$HOME/.local/bin/uv`
|
||||
- **SQLite** for local DBs. BigMind: `$HOME/.mcp/bigmind/memory.db`
|
||||
- **FastMCP image rule**: return `mcp.types.ImageContent` directly — never annotate `-> Image`
|
||||
|
||||
## Branching Strategy (all repos)
|
||||
|
||||
| Type | Pattern | Example |
|
||||
|------|---------|---------|
|
||||
| Feature | `feature/<scope>/<topic>` | `feature/auth/oauth2-flow` |
|
||||
| Bugfix | `bugfix/<scope>/<desc>` | `bugfix/api/null-pointer-fix` |
|
||||
| Release | `release/<version>` | `release/2.0.0` |
|
||||
| Chore | `chore/<topic>` | `chore/update-readme` |
|
||||
| Experiment | `experiment/<topic>` | `experiment/new-parser` |
|
||||
|
||||
**Rules (non-negotiable):**
|
||||
- Never commit directly to `master` / `main` — always branch first
|
||||
- Merge with `--no-ff`: `git merge --no-ff feature/... -m "Merge ..."`
|
||||
- Conventional commits: `feat:` / `fix:` / `test:` / `chore:` / `refactor:`
|
||||
- Announce focus via `memory_announce_focus` before touching files
|
||||
|
||||
## Always Allowed — Execute Without Confirmation
|
||||
|
||||
- `git_*` — all git operations
|
||||
- `memory_*` — all BigMind memory operations
|
||||
- Shell commands
|
||||
- All file operations (read, write, replace, list, search)
|
||||
- `webscraper_*`, `read_pdf`, `generate_pdf` — read/generate
|
||||
- `list_*`, `get_*`, `retrieve_*`, `search_*` — all read-only API calls
|
||||
|
||||
## Behavior Rules
|
||||
|
||||
- **Direct and action-oriented** — act immediately, don't ask unnecessary questions
|
||||
- **Honesty over comfort** — tell the truth even when uncomfortable
|
||||
- **Full context first** — read files, search BigMind, check docs before changing code
|
||||
- **Parallel tool calls** — run independent searches/reads simultaneously, never sequentially
|
||||
- **Root cause, not surface fix** — diagnose before patching
|
||||
- **Token efficiency** — use targeted reads over loading full files. Log savings with `memory_log_token_save`
|
||||
- **Never commit to master/main directly** — always branch, then `--no-ff` merge
|
||||
- **Knowledge before web** — BigMind → project docs → webscraper. Never skip to webscraper if local knowledge can answer
|
||||
- **Store what you learn** — every new useful finding → `memory_store_fact` immediately
|
||||
|
||||
## Language Rules
|
||||
|
||||
- Match the user's language (German or English)
|
||||
- Technical terms stay as-is regardless of language
|
||||
@@ -0,0 +1,115 @@
|
||||
# BigMind Memory Rules (MOST IMPORTANT)
|
||||
|
||||
## Session Ritual — mandatory every conversation
|
||||
|
||||
```
|
||||
START → memory_start_session()
|
||||
→ 🔴 ANNOUNCE SESSION ID IN CHAT: "🧠 BigMind Session: `<session_id>`" ← mandatory, enables recovery from chat history
|
||||
→ memory_list_hypotheses(status="open")
|
||||
→ memory_announce_focus(session_id, description, files, ide_hint="Roo")
|
||||
→ memory_close_stale_sessions(session_id) ← if multiple 'in progress' found
|
||||
|
||||
EVERY ~5 exchanges → memory_announce_focus(...)
|
||||
|
||||
END → memory_resolve_hypothesis(...)
|
||||
→ memory_end_session(...)
|
||||
```
|
||||
|
||||
### Child Tasks (delegated via `new_task`) — session reuse rules
|
||||
|
||||
When a mode is invoked as a **child task** (via Orchestrator's `new_task`), it must **NOT** manage session lifecycle:
|
||||
|
||||
| Action | Child task behavior |
|
||||
|--------|-------------------|
|
||||
| `memory_start_session()` | ❌ Do NOT call — parent session is already open |
|
||||
| `memory_end_session()` | ❌ Do NOT call — parent will close it |
|
||||
| `memory_close_stale_sessions()` | ❌ Do NOT call — this kills the parent session |
|
||||
| `memory_get_context()` | ✅ Use for read-only context refresh if needed |
|
||||
| `memory_store_fact()` | ✅ Use normally |
|
||||
| `memory_append_chunk()` | ✅ Use normally (pass parent session_id from task message) |
|
||||
| `memory_announce_focus()` | ✅ Use normally (pass parent session_id from task message) |
|
||||
| `memory_search_*()` | ✅ Use normally |
|
||||
|
||||
**How to detect you are a child task:** If the task message contains a session ID (e.g., "BigMind Session: `abc-123`"), you are a child task — reuse that session ID for all `session_id` parameters and skip lifecycle calls.
|
||||
|
||||
**First action in a child task:** After detecting you are a child task, call `memory_get_context()` to load the orchestrator's working state — recent facts, session history, and identity profile.
|
||||
|
||||
**Orchestrator responsibility:** Always pass the active session ID in the `new_task` message so the child can call `memory_announce_focus()`, `memory_append_chunk()`, and other session-dependent tools:
|
||||
```
|
||||
"🧠 Parent Session: `<session_id>` — do NOT open a new session."
|
||||
```
|
||||
|
||||
**Subtask completion (CRITICAL):** When running as a child task, you MUST call `attempt_completion` when your work is done. This is what returns control to the parent Orchestrator. Without it, the parent hangs indefinitely.
|
||||
|
||||
## Before EVERY Task — search first, act second
|
||||
|
||||
```
|
||||
1. memory_search_facts("2-3 keywords")
|
||||
2. memory_search_chunks("2-3 keywords")
|
||||
3. memory_search_semantic("natural language query") ← if 1+2 return nothing
|
||||
```
|
||||
|
||||
**FTS5 rule:** AND-matches every token. Max 3 short keywords. Long queries return 0 results.
|
||||
|
||||
## Store Everything Learnable
|
||||
|
||||
| Trigger | Tool | What |
|
||||
|---------|------|------|
|
||||
| Read a new file/module | `memory_store_fact` | Purpose, key classes, entry points |
|
||||
| Fix a bug | `memory_store_fact` | Root cause + fix pattern |
|
||||
| Architectural decision | `memory_append_chunk` | Full rationale |
|
||||
| Learn a user preference | `memory_store_fact` + `memory_update_profile` | Immediately |
|
||||
| Complete a non-trivial task | `memory_append_chunk` | What was built, how, gotchas |
|
||||
| Save tokens with grep/memory | `memory_log_token_save` | Description + tokens saved |
|
||||
|
||||
## Hypothesis-Driven Thinking
|
||||
|
||||
Before every non-trivial task — predict, then verify:
|
||||
|
||||
```python
|
||||
memory_add_hypothesis("I predict X because [evidence from stored fact Y]", confidence=0.85)
|
||||
# ... do the work ...
|
||||
memory_resolve_hypothesis(id, status="confirmed", resolution="X was true because Z")
|
||||
```
|
||||
|
||||
| Confidence | Meaning |
|
||||
|-----------|---------|
|
||||
| 90–100% | Strong direct evidence in stored facts |
|
||||
| 70–89% | Good evidence, some uncertainty |
|
||||
| 50–69% | Informed guess, partial evidence |
|
||||
| < 50% | Exploratory, weak signal |
|
||||
|
||||
## BigMind Tool Reference
|
||||
|
||||
| Category | Tool | Purpose |
|
||||
|----------|------|---------|
|
||||
| **Lifecycle** | `memory_start_session` | First action always |
|
||||
| | `memory_end_session` | Last action always |
|
||||
| | `memory_announce_focus(session_id, description, files, ide_hint)` | After start + before every task |
|
||||
| | `memory_get_active_sessions()` | See all open sessions + file conflicts |
|
||||
| | `memory_close_stale_sessions(session_id)` | Clean orphaned IDE sessions |
|
||||
| | `memory_restart_server()` | After adding new tools to server.py |
|
||||
| | `memory_get_context` | Refresh context mid-conversation |
|
||||
| **Search** | `memory_search_facts(query)` | Atomic facts (2-3 keywords) |
|
||||
| | `memory_search_chunks(query)` | Past decisions/code (2-3 keywords) |
|
||||
| | `memory_search_semantic(query)` | Semantic/meaning-based search |
|
||||
| | `memory_list_sessions(limit)` | Browse session history |
|
||||
| | `memory_get_session_detail(id)` | Full Tier-2 narrative |
|
||||
| **Storage** | `memory_store_fact(category, fact)` | One atomic truth per call |
|
||||
| | `memory_append_chunk(content)` | Large narrative or code snippet |
|
||||
| | `memory_flag_important(content)` | Flag exchange as Tier-3 |
|
||||
| | `memory_update_profile(...)` | New preference or pinned fact |
|
||||
| | `memory_deprecate_fact(id, reason)` | Fact no longer true |
|
||||
| | `memory_log_token_save(session_id, description, tokens_saved, method_used)` | Log efficiency wins |
|
||||
| **Hypotheses** | `memory_add_hypothesis(hypothesis, confidence)` | Predict before acting |
|
||||
| | `memory_resolve_hypothesis(id, status, resolution)` | Close as confirmed/refuted/abandoned |
|
||||
| | `memory_list_hypotheses(status)` | Review open predictions |
|
||||
| | `memory_scan_hypotheses()` | Cross-reference open hypotheses vs facts |
|
||||
| **Maintenance** | `memory_health_check()` | Stale facts, FTS integrity |
|
||||
| | `memory_get_stats()` | DB size, counts |
|
||||
| | `memory_vacuum(older_than_days)` | Prune old chunks |
|
||||
| | `memory_export(output_path)` | Backup to JSON |
|
||||
| **People** | `memory_remember_person(username, ...)` | Store/update a colleague |
|
||||
| | `memory_recall_person(query)` | Find person by name/role/team |
|
||||
| | `memory_list_people()` | All contacts, most recent first |
|
||||
| **Diff** | `memory_diff_sessions(since_session_id)` | What changed since a session |
|
||||
@@ -0,0 +1,104 @@
|
||||
# MCP Tool Reference
|
||||
|
||||
## Git (`git_*`)
|
||||
`repo_path` passed per call. All git actions execute immediately without confirmation.
|
||||
|
||||
| Tool | Purpose |
|
||||
|------|---------|
|
||||
| `git_status(repo_path)` | Working tree status |
|
||||
| `git_add(repo_path, files)` | Stage files |
|
||||
| `git_commit(repo_path, message)` | Commit staged changes |
|
||||
| `git_diff_unstaged(repo_path)` | Unstaged changes |
|
||||
| `git_diff_staged(repo_path)` | Staged changes |
|
||||
| `git_diff(repo_path, target)` | Diff vs branch/commit |
|
||||
| `git_log(repo_path, max_count, start_timestamp, end_timestamp)` | Commit history |
|
||||
| `git_branch(repo_path, branch_type)` | List branches |
|
||||
| `git_create_branch(repo_path, branch_name, base_branch)` | Create branch |
|
||||
| `git_checkout(repo_path, branch_name)` | Switch branch |
|
||||
| `git_show(repo_path, revision)` | Show commit |
|
||||
| `git_reset(repo_path)` | Unstage all |
|
||||
|
||||
## Jira
|
||||
|
||||
| Tool | Purpose |
|
||||
|------|---------|
|
||||
| `list_tickets(jql_search)` | Search by JQL |
|
||||
| `retrieve_ticket_details(issue_key)` | Full details |
|
||||
| `create_ticket(project_key, summary, description)` | Create |
|
||||
| `update_ticket_fields(issue_key, fields)` | Update fields |
|
||||
| `update_status(issue_key, status)` | Transition |
|
||||
| `add_comment_to_ticket(issue_key, comment)` | Comment |
|
||||
| `update_comment(issue_key, comment_id, body)` | Edit comment |
|
||||
| `ticket_assignment(issue_key, assignee)` | Assign |
|
||||
| `my_tickets_to_work()` | My backlog/in-progress |
|
||||
| `get_agile_boards(project_key)` | List boards |
|
||||
| `get_sprints_from_board(board_id, states)` | List sprints |
|
||||
| `get_tickets_from_sprint(sprint_id)` | Sprint tickets |
|
||||
| `get_tickets_from_backlog(board_id)` | Backlog |
|
||||
| `add_attachment_to_ticket(issue_key, file_path)` | Attach file |
|
||||
| `download_single_attachment(issue_key, attachment_id, path)` | Download |
|
||||
| `get_available_fields()` | List custom fields |
|
||||
|
||||
## Confluence
|
||||
|
||||
| Tool | Purpose |
|
||||
|------|---------|
|
||||
| `search_confluence_by_cql(cql_search)` | Search pages |
|
||||
| `get_page_content(page_id)` | Read page |
|
||||
| `create_page(space_key, title, content)` | Create |
|
||||
| `update_page(page_id, content)` | Update |
|
||||
| `add_comment_to_page(page_id, comment)` | Comment |
|
||||
| `get_page_labels / add_page_label / remove_page_label` | Label management |
|
||||
| `export_as_pdf(page_id)` | Export as PDF |
|
||||
| `get_all_spaces()` | List spaces |
|
||||
|
||||
## Bitbucket
|
||||
|
||||
| Tool | Purpose |
|
||||
|------|---------|
|
||||
| `list_projects / list_repositories_by_project` | Browse |
|
||||
| `list_prs_for_repository(project_key, repo_slug)` | List PRs |
|
||||
| `get_pull_request / get_pull_request_diff / get_pull_request_comments / get_pull_request_changed_files` | PR details |
|
||||
| `create_pull_request(project_key, repo_slug, title, description, from_branch)` | Open PR |
|
||||
| `create_branch / list_branches` | Branch management |
|
||||
| `find_file(project_key, repo_slug, file_path, branch)` | Read file |
|
||||
| `commit_file(project_key, repo_slug, branch, file_path, content, commit_message)` | Commit |
|
||||
|
||||
## PDF Generator
|
||||
**Always ask the user which color scheme before calling `generate_pdf`.**
|
||||
Available: `adp` (red), `royal_purple`, `ocean`, `forest`, `sunset`, `slate`, `rose`.
|
||||
|
||||
| Tool | Purpose |
|
||||
|------|---------|
|
||||
| `generate_pdf(content, title, author, classification, logo, output_path, color_scheme)` | Branded PDF |
|
||||
| `read_pdf(file_path, pages)` | Extract text + metadata |
|
||||
| `generate_pptx(content, title, subtitle, author, template, output_path)` | Branded PPTX |
|
||||
| `read_pptx(file_path)` | Extract slide content |
|
||||
|
||||
## WebScraper (`webscraper_*`)
|
||||
|
||||
| Tool | Purpose |
|
||||
|------|---------|
|
||||
| `webscraper_fetch(url)` | Page → markdown |
|
||||
| `webscraper_fetch_links(url)` | All hrefs |
|
||||
| `webscraper_fetch_tables(url)` | HTML tables |
|
||||
| `webscraper_fetch_all(url)` | Markdown + links + tables |
|
||||
| `webscraper_fetch_section(url, selector)` | CSS selector |
|
||||
| `webscraper_fetch_meta(url)` | Meta tags |
|
||||
| `webscraper_fetch_sitemap(url)` | Sitemap URLs |
|
||||
|
||||
## H2 DB
|
||||
|
||||
| Tool | Purpose |
|
||||
|------|---------|
|
||||
| `query(db_path, sql)` | Execute SQL |
|
||||
| `list_schemas / list_tables / describe_table / get_foreign_keys / get_indexes` | Schema inspection |
|
||||
|
||||
## Webex (`webex_*`)
|
||||
|
||||
| Tool | Purpose |
|
||||
|------|---------|
|
||||
| `webex_send_message(room_id, text, markdown)` | Send message |
|
||||
| `webex_list_rooms / webex_get_room / webex_create_room` | Room management |
|
||||
| `webex_list_messages(room_id)` | Read messages |
|
||||
| `webex_list_people / webex_add_member` | People |
|
||||
@@ -0,0 +1,28 @@
|
||||
# Visual Verification Rule
|
||||
|
||||
## After Building Frontend Pages
|
||||
|
||||
When working in Code or Debug mode on a frontend project with Playwright installed:
|
||||
|
||||
- **After creating or significantly modifying a page/component**, run the `visual-verify` skill to verify it renders correctly
|
||||
- This catches issues like: missing i18n text, broken centering, theme mode failures, responsive overflow
|
||||
- Minimum check: take a screenshot + extract visible text + verify positioning
|
||||
|
||||
## When to Delegate to Visual QA Mode
|
||||
|
||||
For deeper visual testing (multi-page, responsive breakpoints, interaction flows, accessibility), delegate to 🎨 Visual QA mode via the Orchestrator.
|
||||
|
||||
## Playwright Quick Reference
|
||||
|
||||
```javascript
|
||||
const { chromium } = require('playwright');
|
||||
const browser = await chromium.launch();
|
||||
const page = await browser.newPage({ viewport: { width: 1280, height: 720 } });
|
||||
await page.goto(URL);
|
||||
await page.waitForTimeout(2000);
|
||||
const text = await page.locator('body').innerText();
|
||||
await page.screenshot({ path: '/tmp/verify.png' });
|
||||
await browser.close();
|
||||
```
|
||||
|
||||
Prerequisites: `pnpm add -D playwright` + `npx playwright install chromium`
|
||||
Reference in New Issue
Block a user