docs(path-b): execution plan + vibn-dev image scaffold

- AI_PATH_B_EXECUTION_PLAN.md: add 3 safety nets (auto-push, kill switch, hard tool removal), tighten 4 risks (network policy week 1, HMR spike day 1, lean image + lazy mise, random preview suffix). - AI_CAPABILITIES_ROADMAP.md: pointer note already in place. - vibn-dev/Dockerfile + supervisord.conf + mise.default.toml + README: scaffold for the per-project dev container image. Ubuntu 24.04 + git + ripgrep + python3 + mise. Toolchains lazy-install on first `mise install`. Container runs as uid 1000 vibn (sudo available). Frontend wiring lives in vibn-frontend (separate commit). Made-with: Cursor
2026-04-28 12:53:31 -07:00
parent ec70981ba7
commit 2491363b5c
7 changed files with 408 additions and 1 deletions
--- a/AI_CAPABILITIES_ROADMAP.md
+++ b/AI_CAPABILITIES_ROADMAP.md
@@ -1,5 +1,11 @@
 # Vibn AI Capability Roadmap

+> **⚠ See also:** [`AI_PATH_B_EXECUTION_PLAN.md`](./AI_PATH_B_EXECUTION_PLAN.md)
+> — proposed pivot to a Claude-Code-style persistent dev container per
+> project. Once approved, that doc supersedes any "code authoring" item
+> in this roadmap; this file remains the source of truth for
+> infrastructure primitives (P5.x, P6.x, P7.x).
+>
 > The ordered plan for closing the gap between what the Vibn agent can do
 > today and what it needs to do for a real customer to ship, operate, and
 > scale a SaaS through it.
--- a/AI_PATH_B_EXECUTION_PLAN.md
+++ b/AI_PATH_B_EXECUTION_PLAN.md
@@ -0,0 +1,285 @@
+# Path B Execution Plan — Persistent Dev Container Architecture
+
+> The plan to replace Vibn's current "API-wrap-every-Coolify-action" agent
+> surface with a Claude-Code-style architecture: one persistent dev
+> container per Vibn project, ~10 composable tools, sub-15-second
+> iteration, and Coolify only touched at "ship it" time.
+>
+> **Companion to:** [`AI_CAPABILITIES.md`](./AI_CAPABILITIES.md) (current
+> state) and [`AI_CAPABILITIES_ROADMAP.md`](./AI_CAPABILITIES_ROADMAP.md)
+> (everything else).
+>
+> **Status:** proposed. Not started. Decision document.
+>
+> **Why this exists:** today's AI loop is *3–7 min to first preview, 2–4
+> min per iteration*, because every change goes through a Coolify nixpacks
+> build. That UX cannot host the marketplace / SaaS / iterative-build
+> stories Vibn is selling. Path B fixes the floor.
+
+---
+
+## 1. The user experience this unlocks
+
+Reference scenario: a non-technical founder chats *"build me a
+two-sided marketplace for handmade ceramics."*
+
+| Phase | Path A (today) | Path B (target) |
+|---|---|---|
+| Discovery & OSS pick | OK | OK |
+| Fork an OSS base (e.g. Sharetribe, 800 files) | ~15 min of single-file commits, 800 webhook fires | `git clone` in 8s |
+| First live preview | 3–7 min (Coolify build) | ~30s (Vite HMR in dev container) |
+| Each iteration | 2–4 min (rebuild) | 3–15s (HMR / process restart) |
+| User makes 10 small decisions | ~40 min of staring at spinners | ~3 min of conversation |
+| "Ship it" → real domain | already 3 min | 3 min (unchanged — this is the only Coolify build) |
+| Total time to live, polished marketplace | 30–60 min, often abandoned | ~20 min, mostly the user thinking |
+
+The asymmetry is structural, not optimisable inside Path A.
+
+---
+
+## 2. Architecture overview
+
+```
+┌──────────────────────────┐     ┌────────────────────────────────┐
+│  vibnai.com chat (user)  │ ←→  │  /api/mcp                       │
+└──────────────────────────┘     │   ├ shell.exec                  │
+                                 │   ├ fs.read / fs.edit / fs.glob │
+                                 │   ├ dev_server.start            │
+                                 │   ├ ship                        │
+                                 │   └ apps.* / databases.* / ...  │
+                                 └────────────┬───────────────────┘
+                                              │
+                                              ▼ (workspace-scoped)
+                          ┌────────────────────────────────────┐
+                          │  Per-Vibn-project Coolify project  │
+                          │   ├ vibn-dev   ← dev container     │
+                          │   ├ web         ← prod app         │
+                          │   ├ db                              │
+                          │   └ ...                             │
+                          └────────────────────────────────────┘
+```
+
+### Per-project dev container — the only new piece
+
+For every active Vibn project, we run **one long-lived Coolify
+service named `vibn-dev`** inside that project's dedicated Coolify
+project (Stage 2/3 of per-project isolation already shipped).
+
+| Property | Value |
+|---|---|
+| **Image** | `ghcr.io/vibnai/vibn-dev:latest` (we build & maintain) |
+| **Base** | Ubuntu 24.04 |
+| **Pre-installed** | Node 20, bun, pnpm, Python 3.12 + uv, Go 1.23, Rust, git, gh, `tea` (Gitea CLI), ripgrep, fd, jq, curl, tar, openvscode-server |
+| **Default `cwd`** | `/workspace` (persistent volume containing the Gitea working tree) |
+| **Persistent volumes** | `/workspace` (git tree), `/cache/{npm,pip,go,cargo}` (package caches) |
+| **Resource floor** | 512 MB / 0.25 CPU when idle |
+| **Resource ceiling** | 4 GB / 2 CPU during builds (configurable per workspace plan) |
+| **Idle suspend** | After 30 min no `shell.exec` activity |
+| **Re-wake** | Any `shell.exec` / `fs.*` / `dev_server.*` call |
+| **Ports** | 3000–9999 reserved for the AI's dev server, exposed at `https://preview-{ws}-{project}.vibnai.com` via Traefik wildcard |
+| **Tenancy** | Inherits per-project Coolify isolation — workspace can never reach into another's dev container |
+
+### Why this shape (and not e2b / Cloud Run / VM-per-task)
+
+- We already have Coolify, per-project Coolify projects, and Coolify
+  exec primitives. Adding one service per project is zero new infra.
+- Persistence (workspace state, package cache, git working tree)
+  matters more than per-task isolation for our user. Founders return
+  to projects across sessions.
+- Tenant safety is already solved at the Coolify-project layer.
+- Cost stays bounded: one container per *active* project, idle-suspended.
+- Upgrade path to e2b / Firecracker exists later if needed (replace the
+  executor, keep the tool surface).
+
+---
+
+## 3. Tool surface
+
+### New tools (the AI's primary working set)
+
+| Tool | Signature | Purpose |
+|---|---|---|
+| `shell.exec` | `{ cmd, cwd?, timeoutSec?, env? }` | Run any shell command in the dev container. Streams stdout/stderr back. Capped 15 min. |
+| `fs.read` | `{ path, ref? }` | Read a file (or directory listing) from `/workspace`. |
+| `fs.write` | `{ path, content }` | Create/overwrite a file. |
+| `fs.edit` | `{ path, oldString, newString, replaceAll? }` | Aider-style search/replace. Fails if `oldString` not found / not unique. |
+| `fs.glob` | `{ pattern, cwd? }` | List files matching a pattern (e.g. `**/*.tsx`). |
+| `fs.grep` | `{ pattern, glob?, contextLines? }` | ripgrep-backed code search. |
+| `fs.delete` | `{ path }` | Delete a file or directory. |
+| `dev_server.start` | `{ cmd, port, name? }` | Start a long-running process (e.g. `npm run dev`). Returns a public preview URL. |
+| `dev_server.stop` | `{ id }` | Kill a dev server. |
+| `dev_server.list` | — | What's running, on what URL. |
+| `ship` | `{ projectId, commitMsg, deploy? }` | `git add . && git commit && git push` to Gitea, then trigger Coolify deploy of the prod app. The "graduate to production" tool. |
+
+### Kept (orchestration — these are correctly modeled as APIs)
+
+- `apps.*` — Coolify app CRUD, logs, domains, env vars, etc.
+- `databases.*`, `auth.*`, `domains.*`, `storage.*` — infrastructure primitives.
+- `projects_get`, `projects_list`, `workspace_describe` — context.
+- `github_search`, `github_file`, `http_fetch` — external lookup.
+
+### Deprecated (kept for back-compat, banner in docs)
+
+- `gitea_file_read`, `gitea_file_write`, `gitea_file_delete`,
+  `gitea_branches_list`, `gitea_branch_create`,
+  `gitea_repo_create`, `gitea_repo_get`, `gitea_repos_list` — the
+  AI uses `shell.exec` (`git`/`tea` CLI) and `fs.*` instead.
+- `apps.exec` — kept (it's still useful for prod-container debugging),
+  but deprecated for *dev-time* code work.
+
+**Net change:** 53 tools → ~30 tools, but the new ones compose to do
+everything the old ones did and more.
+
+---
+
+## 4. The system prompt rewrite
+
+The AI's prompt today says *"call gitea_file_write to push code."* It
+becomes:
+
+> You have a real Linux dev environment for this project at `/workspace`.
+> Use `shell.exec` to run any command (npm, git, tea, python, anything).
+> Use `fs.edit` for surgical changes, `fs.write` for new files.
+>
+> Standard loop:
+> 1. `shell.exec { cmd: "git status" }` to see what's there.
+> 2. Edit / create files via `fs.edit` / `fs.write`.
+> 3. `shell.exec { cmd: "npm test" }` (or relevant test runner).
+> 4. `dev_server.start` to give the user a live preview URL.
+> 5. When the user says "ship it", call `ship` — that pushes and
+>    triggers the production Coolify deploy.
+>
+> NEVER call `apps_create` to deploy code that hasn't been tested via
+> `shell.exec` first. The dev container is your safety net.
+
+---
+
+## 5. Week-by-week execution
+
+### Week 1 — Foundations (dev container + shell)
+
+**Goal:** AI can clone a repo, install deps, run a script.
+
+- [ ] Build `ghcr.io/vibnai/vibn-dev:latest` Docker image (Ubuntu 24.04 + toolchains). Push to a registry the Coolify host can pull from.
+- [ ] Add `lib/dev-container.ts`: helpers to mint, locate, ensure-running, suspend, resume the per-project `vibn-dev` Coolify service.
+- [ ] Add MCP tool `dev_container.ensure { projectId }` — internal/auto, spins up the container if not present. Returns its UUID + status.
+- [ ] Add MCP tools: `shell.exec`, `fs.read`, `fs.write`, `fs.list`, `fs.delete`, `fs.glob`, `fs.grep`. All proxy through Coolify's exec API to the dev container.
+- [ ] Smoke test (`scripts/smoke-path-b.ts`): boots a dev container, clones a Gitea repo, runs `npm init -y && npm install lodash`, reads `package.json`, succeeds.
+- [ ] Update `vibn-tools.ts` and ship a chat UI that streams `shell.exec` stdout to the user as it happens (existing terminal-style component if we have one, or a new one).
+
+**Exit criteria:** an internal user can chat *"clone the express hello-world repo and run it"* and see the output stream live.
+
+### Week 2 — Preview URLs + iteration
+
+**Goal:** AI starts a dev server, user clicks a preview URL, sees their app.
+
+- [ ] Traefik wildcard rule on the Coolify host: `*.preview.vibnai.com` → terminates TLS, forwards to dev container based on subdomain (`preview-{ws}-{project}.vibnai.com` → `vibn-dev` of that project's Coolify project).
+- [ ] Add MCP tools: `dev_server.start`, `dev_server.stop`, `dev_server.list`. Implementation: starts the process inside the dev container under a small supervisor (e.g. `tini` / `supervisord`), tracks PID/port, registers a Traefik label on the dev container.
+- [ ] Add `fs.edit` (Aider-format search/replace, with explicit error when `oldString` not found / ambiguous).
+- [ ] Per-workspace plan-tier resource caps on the dev container (free tier: 1 GB / 0.5 CPU; paid: 4 GB / 2 CPU).
+- [ ] System prompt rewrite (see §4). Update the AI's deploy recipes to start with `shell.exec` and `dev_server.start` rather than `apps_create`.
+
+**Exit criteria:** the marketplace scenario from §1 works end-to-end up through "user makes 5 styling changes in 3 minutes."
+
+### Week 3 — Ship-it path + cleanup
+
+**Goal:** the dev container's working tree graduates to production.
+
+- [ ] Add `ship` tool: runs `git add . && git commit -m {msg} && git push` inside the container, then either calls `apps_deploy { uuid }` (if a prod app exists) or `apps_create { projectId, repo }` (first ship).
+- [ ] Auto-link the prod app to `fs_project_resources` so the existing project-isolation accounting stays consistent.
+- [ ] Idle-suspend logic: cron job every 5 min checks last `shell.exec` timestamp per dev container; suspends after 30 min idle. Auto-resume on next call.
+- [ ] Deprecation pass: mark `gitea_file_*` tools as deprecated in `vibn-tools.ts` (keep working, add a banner in their description).
+- [ ] Update `AI_CAPABILITIES.md` to reflect the new architecture and tool surface.
+
+**Exit criteria:** end-to-end clean run: user prompt → AI scaffolds in dev container → user iterates → user says "ship" → app live on real domain. Total time logged.
+
+### Week 4 — Eval, polish, IDE drop-in
+
+**Goal:** measure that this actually delivers the promised UX, ship the optional graduation path.
+
+- [ ] **Eval harness:** 10 reference prompts (TODO app, marketplace, blog with auth, kanban, image-uploader, AI chatbot, simple e-commerce, dashboard, REST API + DB, static site). Measure: time-to-first-preview, time-to-shipped, AI tool-call count, success rate. Compare to a baseline run on Path A.
+- [ ] **Theia drop-in:** expose openvscode-server (already in the image) at `https://ide-{ws}-{project}.vibnai.com`. Optional toggle in chat UI: "Open IDE." Lets a user-becoming-developer drop into the same `/workspace` the AI's been editing.
+- [ ] **Bug fixes** found during eval.
+- [ ] **Docs:** update Vibn's user-facing pages to reflect the new "describe → live preview in seconds → iterate → ship" flow.
+
+**Exit criteria:** eval shows ≥3× speedup on time-to-first-preview vs.
+Path A, ≥80% success rate on the 10 reference prompts.
+
+---
+
+## 6. OSS we will lean on (not reinvent)
+
+| Need | OSS choice | Notes |
+|---|---|---|
+| Dev container image base | Ubuntu 24.04 + toolchains | We bake & maintain. ~1 GB. |
+| In-browser IDE (week 4 graduation path) | `openvscode-server` (`gitpod-io/openvscode-server`, MIT) | Pre-installed in the image. Optional toggle. |
+| Edit format | **Aider's search/replace block format** (`Aider-AI/aider`, Apache 2.0) | Borrow the format + error semantics. |
+| Process supervision inside the container | `tini` (already standard) + a tiny in-house supervisor for `dev_server.*` | No need for full systemd. |
+| Code search inside the container | `ripgrep` (`BurntSushi/ripgrep`, MIT) | Pre-installed. `fs.grep` is a thin wrapper. |
+| Git inside the container | `git` + `tea` (Gitea CLI, MIT) | `tea` lets the AI do PR ops without us building gitea_pr_* tools. |
+| Reference for end-to-end agent loops | `All-Hands-AI/OpenHands` (MIT) | Read their runtime + tool design. Don't import their code. |
+| Reference for fast iteration UX | `bolt.new` (`stackblitz/bolt.new`) | UX north star, not a code source. |
+
+---
+
+## 7. Risks & open questions
+
+| Risk | Mitigation |
+|---|---|
+| **Dev containers eat money.** 100 active projects × 24/7 = ~$50/mo wasted. | Idle-suspend after 30 min. Resume in <5s. Per-plan caps. Auto-delete suspended-and-untouched volumes after 30 days. |
+| **`shell.exec` is the universal escape hatch — security?** AI inside a single workspace's container can do anything that container can do. | (a) Per-project Coolify isolation. (b) **Network policy: dev containers have NO route to internal Vibn services (vibn-postgres, vibn-frontend, Coolify control plane). Implemented via Docker network rules in week 1, not deferred.** (c) Audit log on every `shell.exec` call. (d) Per-container CPU/RAM caps absorb fork-bomb / coin-mining attempts. |
+| **Preview URL leaks.** `https://preview-mark-ceramic-market.vibnai.com` is publicly resolvable. | Default: random suffix in subdomain (`preview-mark-ceramic-market-7a3f.vibnai.com`) — ~64 bits of unguessability. Optional Vibn-session-cookie auth as paid-tier feature later. |
+| **Hot reload through Traefik.** WebSocket / HMR can be finicky over a reverse proxy. | **Spike on week 1, day 1**: bring up a Vite dev server inside vibn-dev, expose via Traefik, edit a file, verify HMR fires. Failure here is the biggest "things look fine until you actually test" risk; de-risk early. |
+| **Image size / pull time on first project.** ~1 GB pull adds 30–60s to first dev container spin-up. | (a) Pre-pull image on every Coolify host on deploy. (b) **Keep base image small (~500 MB: OS + git + ripgrep + supervisord + IDE server). Lazy-install language toolchains via `mise` on first project use.** Prevents the image from bloating to 4 GB six months from now. |
+| **Dependency cache poisoning.** Cached `node_modules` from project A bleeds into project B. | Caches are per-project (volume `vibn-dev-cache-{projectId}`). Never share. Take the slower-first-install hit; add a Verdaccio mirror later only if it bothers anyone. |
+| **AI keeps calling `gitea_file_*` instead of `shell.exec`.** | **Hard removal from AI's tool list in week 3, not soft deprecation.** Keep REST endpoints alive for a 30-day grace period for any external MCP client. After 30 days, return 410 Gone. The AI has no muscle memory; no graceful migration needed. |
+| **What if the user has no Vibn project yet?** | First chat creates a project + provisions its Coolify project + spins up `vibn-dev` lazily. ~10s overhead, one-time. Stream progress to the chat ("creating workspace... installing tools..."). Same UX bolt.new uses while WebContainers boot. |
+| **Coolify host disk dies → users lose unshipped `/workspace` work.** | **Auto-push to Gitea `vibn-autosave/main` branch every 5 min of activity, plus before idle-suspend.** Treat Gitea as canonical, container disk as ephemeral. Built in week 1, day 2 (not optional). |
+| **Path B turns out to be wrong; we need to revert.** | **Kill-switch admin endpoint (`POST /api/admin/path-b/disable`) flips a feature flag — all new chat sessions go back to Path A; existing dev containers drain.** ~10-min revert window. Built week 1. |
+
+---
+
+## 8. Success metrics
+
+We're not done until **all four** are true on the eval harness:
+
+| Metric | Target | Today (Path A) |
+|---|---|---|
+| Time-to-first-preview (10 reference prompts, p50) | ≤ 60 s | ~5 min |
+| Iteration loop (small edit → user sees change) p50 | ≤ 15 s | ~3 min |
+| Tool calls per "build me X" task (median) | ≤ 30 | ~80 |
+| End-to-end success rate (live deployable result) | ≥ 80% | ~50% |
+
+---
+
+## 9. What this changes about the existing roadmap
+
+- **Tier 1.5 ("Code authoring capability") is collapsed into this doc.** C1–C9 mostly disappear (replaced by `shell.exec` + `fs.edit`); C10 ("persistent agent dev workspace") **is** Path B.
+- **Tier 1 P5.1–P5.4 are unchanged.** Domains, email, storage, workers — still the right next infra primitives. Path B doesn't replace them; it makes the AI capable enough to actually use them.
+- **Tier 2 P6.x** (backups, runtime logs, scoped keys) — unchanged.
+- **`gitea_*` tools shipped 2026-04-28** are now legacy. Mark deprecated in week 3. Remove in a future cleanup once telemetry confirms zero usage.
+
+---
+
+## 10. Decision needed before week 1 starts
+
+1. **Approve Path B as the primary architecture for code authoring.** (If no, this doc dies here.)
+2. **Approve the dev-container-as-Coolify-service implementation choice.** Alternatives: separate dev-host, e2b self-host, Cloud Run jobs. Picked Coolify-service for zero new infra; flag if you want to revisit.
+3. **Approve the deprecation of `gitea_file_*` tools.** They were shipped today; deprecating them within 3 weeks is fine if the path forward is clearer, embarrassing if we keep them around as half-working alternates.
+4. **Approve the resource cap defaults** (free: 1 GB / 0.5 CPU, paid: 4 GB / 2 CPU). Or set different numbers.
+
+Once those four are decided, week 1 starts.
+
+---
+
+## How to use this doc
+
+- This is the *architectural* execution plan. The detailed task list
+  goes into the agent's TodoWrite per-week, not into this file.
+- When an item ships, **move it from "planned" to "shipped"** in
+  [`AI_CAPABILITIES.md`](./AI_CAPABILITIES.md) and link the commit/PR.
+- When a risk in §7 turns out to be real, document the mitigation
+  outcome inline so future readers see what actually happened.
+- This doc supersedes the proposed Tier 1.5 in
+  [`AI_CAPABILITIES_ROADMAP.md`](./AI_CAPABILITIES_ROADMAP.md). Add a
+  one-line pointer there once approved.
--- a/vibn-dev/Dockerfile
+++ b/vibn-dev/Dockerfile
@@ -0,0 +1,67 @@
+# vibn-dev — per-project AI development container.
+#
+# Goal: a small, fast-pulling base image (~500 MB target) that gives the AI
+# (and the user, eventually) a real shell with git, ripgrep, and the
+# scaffolding to lazy-install language toolchains via mise on first use.
+#
+# Heavy toolchains (Node / Python / Go / Rust) are NOT baked in — they
+# install on demand via `mise install` the first time the AI runs
+# `npm`, `python`, `go`, etc. This keeps the base image lean and lets us
+# bump toolchain versions without rebuilding the image.
+#
+# Spec is in AI_PATH_B_EXECUTION_PLAN.md §3.
+
+FROM ubuntu:24.04
+
+ENV DEBIAN_FRONTEND=noninteractive \
+    LANG=C.UTF-8 \
+    LC_ALL=C.UTF-8 \
+    TZ=UTC
+
+# Core OS packages: shell, git, network, build essentials, ripgrep
+# (powers fs.grep), tini (PID 1 reaper), supervisord (process supervisor
+# for sshd + dev servers), curl/ca-certs (downloads), unzip (mise
+# tarballs), sudo (toolchain installers expect it).
+RUN apt-get update && apt-get install -y --no-install-recommends \
+        bash coreutils ca-certificates curl wget git openssh-client \
+        ripgrep jq nano vim less procps lsof net-tools dnsutils \
+        build-essential pkg-config \
+        sudo tini supervisor unzip xz-utils \
+        python3-minimal \
+    && rm -rf /var/lib/apt/lists/*
+
+# vibn user — the AI runs as this, NOT root.
+RUN useradd --create-home --shell /bin/bash --uid 1000 vibn \
+    && mkdir -p /workspace /home/vibn/.cache /home/vibn/.local /var/log/vibn-dev \
+    && chown -R vibn:vibn /workspace /home/vibn /var/log/vibn-dev \
+    && echo 'vibn ALL=(ALL) NOPASSWD: ALL' > /etc/sudoers.d/vibn
+
+# mise — polyglot version manager. Installs Node/Python/Go/Rust on demand.
+# Pinned to a specific version for reproducibility; bump in this Dockerfile.
+ENV MISE_VERSION=v2024.12.14
+RUN curl -fsSL "https://mise.run" | MISE_VERSION=${MISE_VERSION} sh \
+    && mv /root/.local/bin/mise /usr/local/bin/mise \
+    && chmod +x /usr/local/bin/mise
+
+# Hook mise into vibn's shell so `node`, `python` etc. resolve once
+# installed via `mise install`.
+RUN echo 'eval "$(/usr/local/bin/mise activate bash)"' >> /home/vibn/.bashrc \
+    && echo 'export PATH="$HOME/.local/bin:$PATH"' >> /home/vibn/.bashrc
+
+# Default mise toolchain config — lazily materialised. The AI can
+# override per-project by writing /workspace/.mise.toml.
+COPY --chown=vibn:vibn mise.default.toml /home/vibn/.config/mise/config.toml
+
+# supervisord runs sshd-less; we don't need ssh in the container because
+# all exec happens via `docker exec` from the Coolify host. Supervisord
+# is reserved for dev_server.* (Vite/Next/etc) once that ships.
+COPY supervisord.conf /etc/supervisor/conf.d/vibn-dev.conf
+
+WORKDIR /workspace
+USER vibn
+
+# Keep-alive process. The container's job is to exist; commands run via
+# `docker exec`. tail -f /dev/null is the canonical "stay running, do
+# nothing" pattern — cheaper than supervisord for the no-dev-server case.
+ENTRYPOINT ["/usr/bin/tini", "--"]
+CMD ["tail", "-f", "/dev/null"]
--- a/vibn-dev/README.md
+++ b/vibn-dev/README.md
@@ -0,0 +1,34 @@
+# vibn-dev
+
+Per-project AI development container. One of these runs in Coolify per
+Vibn project; the AI agent (Gemini) drives it via `shell.exec` and
+`fs.*` MCP tools.
+
+See `/AI_PATH_B_EXECUTION_PLAN.md` for the architecture.
+
+## Build & publish
+
+```bash
+docker build -t registry.vibnai.com/vibn-dev:latest .
+docker push registry.vibnai.com/vibn-dev:latest
+```
+
+The image is pre-pulled on every Coolify host on deploy so first-use
+spin-up stays under 5 seconds.
+
+## Smoke test locally
+
+```bash
+docker build -t vibn-dev .
+docker run --rm -it -v "$PWD/scratch:/workspace" vibn-dev bash
+# inside: mise install   # pulls Node lts + Python 3.12 (~90s, one-time)
+# inside: rg --version    # ripgrep ships in the base image
+# inside: git --version
+```
+
+## What's NOT in the image (by design)
+
+- Node/Python/Go/Rust toolchains — lazy-installed via mise
+- Coolify control-plane creds — never. The container has no route to
+  internal Vibn services (Docker network policy enforced at host level)
+- SSH server — exec happens via `docker exec` from the Coolify host
--- a/vibn-dev/mise.default.toml
+++ b/vibn-dev/mise.default.toml
@@ -0,0 +1,6 @@
+# Default toolchain hints for vibn-dev. Nothing is installed until the
+# AI (or the user) runs `mise install`. Override per-project by writing
+# /workspace/.mise.toml — mise auto-loads the closest config.
+[tools]
+node = "lts"
+python = "3.12"
--- a/vibn-dev/supervisord.conf
+++ b/vibn-dev/supervisord.conf
@@ -0,0 +1,9 @@
+; supervisord config for vibn-dev. Currently a no-op — the container
+; runs `tail -f /dev/null` as PID 1 (via tini) and dev servers are
+; launched ad-hoc through `docker exec` + nohup once dev_server.start
+; ships in week 2. Reserved here so the conf path exists.
+[supervisord]
+nodaemon=true
+user=vibn
+logfile=/var/log/vibn-dev/supervisord.log
+pidfile=/tmp/supervisord.pid
--- a/2
+++ b/2