Files
vibn-frontend/ai-new-thread.md

205 lines
12 KiB
Markdown

# VibnCode / Master-AI Context Injector
This file serves as a high-density, comprehensive bootstrap guide for any AI Coding Agent starting a new thread in this workspace.
---
## 1. System Architecture at a Glance
`VibnCode` (formerly TalkCody) is a **Cloud-Powered Agent Desktop IDE**. It functions as a high-fidelity window into cloud-hosted project workspaces, routing file modifications, terminal tasks, and AI session runs to a sandboxed Docker/Coolify VM backend.
```mermaid
graph TD
subgraph Client [Desktop client - vibn-code]
UI[React 19 / Monaco Editor UI]
State[Zustand Stores / SQLite Cache]
Tauri[Tauri v2 App Wrapper]
end
subgraph CloudRunner [Cloud Workspace - vibn-agent-runner]
Runner[Agent Session Runner Engine]
Workspace[Sandboxed Project Dir: /workspaces]
end
subgraph Infrastructure [Vibnai Platform]
DB[(PostgreSQL Database)]
WebAPI[Next.js API Server: vibn-frontend]
Gitea[(Gitea Git Server)]
Coolify[Coolify Server Hosting]
end
UI <-->|Event Streams & Cloud FS| WebAPI
WebAPI -->|Route Exec Request| Runner
Runner <-->|Code Edits & Shell Runs| Workspace
Runner <-->|Push/Pull/Clone Code| Gitea
Runner -->|Manage & Deploy Apps| Coolify
```
---
## 2. Directory Structure & Individual Git Repositories
> **`master-ai` is a LOCAL development workspace on Mark's Mac. It does not exist in production and is never accessed by any running cloud service.** Production runs entirely from the individual Gitea repositories → Coolify builds → running containers on `34.19.250.135`. Once a change is pushed to the matching Gitea remote, `master-ai` is completely out of the picture.
The local `master-ai` directory houses folders that each map to an **independent Gitea repository**. The `master-ai` git repo itself is just a convenience — a single place to commit and track changes across all sub-projects before pushing each one to its own Gitea remote.
DO NOT treat `master-ai` as a single monorepo on Gitea — it is not deployed as one. You must push changes inside specific directories to their matching Gitea remote targets.
```
/Users/markhenderson/master-ai/ <-- Local Parent Directory
├── vibn-code/ <-- Nested Git Repository (Submodule)
│ Remote 'origin' -> https://git.vibnai.com/mark/vibn-code.git (main)
├── vibn-agent-runner/ <-- Subfolder of master-ai. Pushes via:
│ Remote 'coolify_agent_gitea' -> https://git.vibnai.com/mark/vibn-agent-runner.git
├── vibn-frontend/ <-- Subfolder of master-ai. Pushes via:
│ Remote 'coolify_gitea' -> https://git.vibnai.com/mark/vibn-frontend.git
├── vibn-api/ <-- Subfolder of master-ai. Pushes via:
│ Remote 'coolify_api_gitea' -> https://git.vibnai.com/mark/vibn-api.git
└── vibn-telemetry-service/ <-- Subfolder of master-ai (Training Data Microservice). Pushes via:
Remote 'coolify_telemetry_gitea' -> https://git.vibnai.com/mark/vibn-telemetry-service.git
```
### Git Remotes Reference (local Mac remotes — these exist only on Mark's machine):
These are git remotes configured in the local `master-ai` repo. They are the **one-way bridge** between local development and production. Production Coolify services pull directly from the Gitea URLs; they have no knowledge of `master-ai`.
| Remote | Gitea URL | What it deploys |
|---|---|---|
| `coolify_gitea` | `https://git.vibnai.com/mark/vibn-frontend.git` | vibn-frontend (Next.js platform) |
| `coolify_agent_gitea` | `https://git.vibnai.com/mark/vibn-agent-runner.git` | vibn-agent-runner |
| `coolify_api_gitea` | `https://git.vibnai.com/mark/vibn-api.git` | vibn-api |
| `coolify_telemetry_gitea` | `https://git.vibnai.com/mark/vibn-telemetry-service.git` | vibn-telemetry-service |
| `gitea` | `https://git.vibnai.com/mark/master-ai.git` | *(share-only — coworker local setup; **builds do NOT use this**)* |
| `origin` | `https://github.com/MawkOne/master-ai.git` | *(GitHub mirror only — not used by Coolify)* |
**The full deploy lifecycle:**
```
Local Mac (master-ai) → git push <remote> HEAD:main → Gitea repo → Coolify build → Production
↑ ↑
master-ai ends here Production begins here
```
1. Make changes in `master-ai/vibn-frontend/` (or whichever subfolder).
2. `git commit` in `master-ai`.
3. `git push coolify_gitea HEAD:main` (or relevant remote) — **this is the complete hand-off**.
4. Coolify detects the push, builds a Docker image from the Gitea repo, and deploys it.
5. `master-ai` is no longer involved. Production runs entirely from the Gitea repo + Coolify.
`vibn-code` is a nested submodule with its own `.git` — commit & push it via its own `origin`.
Secret `.env*` files at the repo root are gitignored — never commit them.
**⚠️ NEVER use `git subtree push` for these remotes.** Coolify is configured with `vibn-frontend` as its **base directory**, so it expects the full `master-ai` repo structure at the Gitea root and resolves the Dockerfile at `vibn-frontend/Dockerfile`. A subtree push flattens the repo to just the subfolder contents, making `vibn-frontend/` disappear and breaking the build with `open Dockerfile: no such file or directory`. Always use:
```bash
git push <remote> HEAD:main # normal
git push <remote> HEAD:main --force # if remote has diverged
```
### Deploying the Telemetry Service manually via Coolify UI:
Because Coolify's API strictly blocks the programmatic creation of GitHub/Gitea Apps, the Telemetry service must be linked manually once:
1. Open [Coolify Dashboard -> vibn-infrastructure -> production](https://coolify.vibnai.com/project/f4owwggokksgw0ogo0844os0/environment/foskksoccksk0kc4g8sk88ok)
2. Click **+ Add -> Application -> Private Repository (with Gitea)**.
3. Select `vibn-telemetry-service` and branch `main`.
4. Set Build Pack to `Dockerfile` and Ports Exposes to `4000`.
5. Under Environment Variables, add `DATABASE_URL=postgresql://<user>:<password>@<host>/<database>`
6. Deploy it, then add `TELEMETRY_SERVICE_URL=http://<the-new-coolify-url>:4000` to the `vibn-frontend` environments.
---
## 3. Key Tech Stacks & Development Tools
### Runtimes & Package Managers (Local Mac)
* **Bun**: **NOT installed** on this local Mac's CLI path. Use **`pnpm`** (v10.33.2) or **`node`** (v24.1.0) instead.
* **Rust**: Fully configured. Built/managed via cargo.
### Sub-Project Configurations
#### A. `vibn-code` (The Desktop App)
* **Frontend**: React 19 + TypeScript + Zustand + Tailwind CSS v4 + Shadcn UI + Monaco Editor.
* **Backend**: Tauri v2 + Rust (split into `core` and `desktop` workspace members).
* **Startup Command**:
```bash
cd /Users/markhenderson/master-ai/vibn-code
pnpm dev:tauri # Compiles Rust backend, launches desktop shell, and starts Vite
```
*(To start React web preview only, run `pnpm dev`)*
#### B. `vibn-frontend` (The Next.js Web Dashboard & API Bridge)
* **Frontend/Backend**: Next.js + PostgreSQL + NextAuth.js.
* **Startup Command**:
```bash
cd /Users/markhenderson/master-ai/vibn-frontend
docker compose -f docker-compose.local-db.yml up -d # Start local Postgres
pnpm dev # Start Next.js
```
#### C. `vibn-api`
* **Stack**: Bun/TypeScript + Drizzle ORM + sqlite/libsql + Wrangler/Cloudflare.
---
## 4. The Cloud-Powered Bridge Architecture
VibnCode overrides local OS actions to communicate with your cloud containers (on GCP VM `34.19.250.135` via Coolify/Traefik):
1. **Virtual Filesystem (`src/services/cloud-fs-service.ts` & `repository-service.ts`)**:
Monaco & File Tree operations POST to Next.js `/api/mcp` with actions `"fs_tree"`, `"fs_read"`, and `"fs_write"`.
* `fs_tree` returns an ASCII tree parsed by `parseAsciiTreeToNodes` on the client into UI `FileNode` trees.
2. **Server-Delegated Run-Loop (`src/services/execution-service.ts`)**:
Instead of launching local task compilers, the client calls `POST /api/projects/:projectId/agent/sessions` and initiates a real-time `while (isRunning)` polling loop against PostgreSQL to pull output lines and stream them to the Monaco chat panel.
3. **SSO Authentication Loop (`vibncode://` Custom Scheme)**:
OAuth logins redirect from Gitea back to `vibncode://auth/callback?token=...`.
* **Important:** This scheme is registered in macOS via `vibn-code/src-tauri/Info.plist` (updated and verified).
* Relaunching/recompiling the app (`pnpm dev:tauri`) registers `vibncode://` with Launch Services, enabling local SSO redirects.
---
## 5. Development Guidelines & Safety Nets
1. **Rust Clippy Warnings are treated as Errors**:
The pre-commit hooks will fail commits if cargo clippy warnings exist.
* *Unused structs*: Annotate with `#[allow(dead_code)]`.
* *Nested matches/ifs*: Collapse nested `if` statements into outer `match` arms using pattern guards (e.g. `ContentPart::Text { text } if !text.trim().is_empty() => { ... }`).
2. **Commit Bypasses**:
If blocking cargo file locks (`Blocking waiting for file lock on build directory`) occur because the app is running, stage your changes and commit using `--no-verify` to bypass pre-commit compilation:
```bash
git commit -m "commit message" --no-verify
```
3. **Push to Individual remotes (the ONLY way changes reach production)**:
Commit in `master-ai`, then push the relevant subfolder's remote. Production never reads from `master-ai` directly — the push to Gitea is the complete hand-off.
```bash
git push coolify_gitea HEAD:main # deploy vibn-frontend
git push coolify_agent_gitea HEAD:main # deploy vibn-agent-runner
git push coolify_api_gitea HEAD:main # deploy vibn-api
git push coolify_telemetry_gitea HEAD:main # deploy vibn-telemetry-service
```
---
## 6. Where We Left Off (As of May 31, 2026)
**Read `VIBNCODE_THIN_CLIENT_CHANGES.md` first** — it is the live, prioritized change list with exact files,
steps, and acceptance criteria for the thin-client conversion, plus a STATUS section of what's done.
**Chat works end-to-end.** A desktop message → `POST /api/projects/:id/agent/sessions` → cloud runner executes
the Coder agent (Gemini) → output polled back into the Monaco chat. Recent fixes that got it there:
* **Local SQLite was wiping chats (fixed):** `database-service.ts` used `INSERT OR REPLACE INTO projects`, which
(via `ON DELETE CASCADE`) deleted the active conversation mid-run. Switched to UPSERT; made `task-service`
persistence non-blocking. The cloud is the source of truth; local SQLite is just a cache.
* **Empty `appPath` broke every run (fixed):** the desktop sent `appPath: ""`; the runner's `/agent/execute`
rejects falsy `appPath` with HTTP 400 and does nothing (no logs). Desktop now sends `appPath: "."`.
* **Agent tools `fetch failed` (fixed, pushed):** the runner's `buildContext()` hardcoded
`vibnApiUrl: 'http://localhost:3000'` and an empty `mcpToken`, so tool calls fetched a dead port. Now
`/agent/execute` reads `mcpToken` from the body and sets `ctx.vibnApiUrl` (from `VIBN_API_URL`) + `mcpToken`.
Pushed to `coolify_agent_gitea/main` — confirm the runner redeploy.
* **Single model:** desktop model picker restricted to the VibnAI model, relabeled "Gemini 3.5 Flash". The
runner's real model is set by `GEMINI_MODEL` env (currently `gemini-3.1-pro-preview`); the desktop label is
cosmetic until model-passthrough is wired (CHANGE 4.1 in the change doc).
**Known open items (in the change doc):** the desktop still has a hardcoded `vibn_sk_` API key to remove;
`/agent/sessions/:id/stop` returns 401 to the desktop (uses browser-session auth, not the workspace key); runner
early-failures are silently swallowed (failure PATCHes omit the `x-agent-runner-secret` header).
**Earlier (still true):** `vibncode://` deep link scheme is registered in `src-tauri/Info.plist`; Rust clippy is
treated as errors on commit.