mark/master-ai
Archived
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: heavily compress and simplify remaining reference files to represent current state

Browse Source
This commit is contained in:
mawkone
2026-05-07 15:07:31 -07:00
parent 3563b98de1
commit 057115a9fc
8 changed files with 58 additions and 2926 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
BETA_LAUNCH_PLAN.md
View File

@@ -73,14 +73,6 @@ a slow loop until this lands.
| # | Task | Owner | Effort | Status |
|---|---|---|---|---|
| 1.1 | Sign up for Cloudflare; add `vibnai.com`; verify imported records (MX, SPF, wildcard A, apex A) | Mark | 15 min | ✓ done |
| 1.2 | Switch Namecheap nameservers to Cloudflare-assigned NS pair | Mark | 2 min | ✓ done |
| 1.3 | Wait for propagation; verify `dig @1.1.1.1` from multiple resolvers | AI | 30–120 min | ✓ done — `34.19.250.135` from CF + Google resolvers |
| 1.4 | Generate Cloudflare API token (DNS edit, `vibnai.com` only) | Mark | 2 min | ✓ done — stored in `.coolify.env` |
| 1.5 | Configure Traefik Let's Encrypt DNS-01 with the Cloudflare token | AI | 20 min | ✓ done — `letsencrypt-dns` resolver wired in `coolify-proxy` |
| 1.6 | Test wildcard cert issues for `*.preview.vibnai.com` (curl, browser) | AI | 10 min | ✓ done — both `*.vibnai.com` and `*.preview.vibnai.com` certs issued; `curl https://test.preview.vibnai.com` returns valid LE cert |
| 1.7 | Wire `dev_server.start` to mint Traefik labels with the wildcard host | AI | 1 hr | ✓ done — pre-baked labels for ports 3000–3009 in `vibn-dev` compose; YAML escape bug fixed; cert resolver fixed to `letsencrypt-dns` |
| 1.8 | Spike: WebSocket / Vite HMR through Traefik against `vibn-dev` container | AI | 30 min | ✓ done — `101 Switching Protocols`, `vite-hmr` subprotocol negotiated, `js-update` messages fire within ~1s of file edit. See verified config below. |
**Definition of done:** ✅ AI says "open a Vite dev server", user clicks the URL,
sees Vite's welcome page, edits a file via `fs.edit`, change appears in
@@ -111,13 +103,6 @@ server: {
|---|---|---|---|---|
| 2.1 | Reproduce + diagnose `ERR_HTTP_HEADERS_SENT` from prod logs | AI | 1–2 hrs | Likely a server action / API route returning twice |
| 2.2 | Reproduce + diagnose `TypeError: reading 'z'/'j'/'aa'` in prod bundle | AI | 1–2 hrs | Minified prod error; suspect `react-markdown` server/client boundary |
| 2.3 | Wire Sentry (or alternative) for both client + server runtime errors | AI | ✓ done 2026-05-01 | `@sentry/nextjs` v10 wired in `vibn-frontend`. `instrumentation.ts` (server+edge), `instrumentation-client.ts` (browser w/ Session Replay free tier, all text masked), `app/global-error.tsx`, `next.config.ts` wrapped with `withSentryConfig`. `NEXT_PUBLIC_SENTRY_DSN` and `SENTRY_AUTH_TOKEN` in Coolify env, with matching `ARG` lines in `vibn-frontend/Dockerfile`. End-to-end verified via `/sentry-example-page` 2026-05-01: client + server errors capture, breadcrumbs work, **stack traces de-minify to real filenames** (`app/sentry-example-page/page.tsx:49`). |
| 2.4 | Wire deployment-failed Coolify webhook → Slack/email | AI | ✓ done 2026-05-01 | Slack webhook wired into `slack_notification_settings` for both Coolify teams. Defaults: failure events on (deploy, backup, scheduled task, docker cleanup, server unreachable, disk usage), success events off. Tested with a manual webhook ping — confirmed in user's Slack. |
| 2.5 | Tighten Coolify docker prune to every 6 hrs (vs daily) | AI | ✓ done 2026-05-01 | Already configured: both servers use `docker_cleanup_frequency: "0 */6 * * *"` with `force_docker_cleanup: true`. Verified via `/api/v1/servers`. |
| 2.6 | Bake `HEALTHCHECK 127.0.0.1` into `vibn-frontend/Dockerfile` so future apps inherit | AI | ✓ done 2026-05-01 | Already in `vibn-frontend/Dockerfile:67-68`; comment explains the IPv6 trap |
| 2.7 | Audit other Dockerfile-based apps for the same `localhost`/IPv6 trap | AI | ✓ done 2026-05-01 | Audited `vibn-dev/Dockerfile` and `vibn-agent-runner/Dockerfile` — neither defines a HEALTHCHECK, so neither can hit the localhost/IPv6 trap. No action needed today; revisit when either gets a healthcheck added. |
| 2.8 | **Tool-error recovery middleware** (AI_HARNESS_GAPS.md §1) — pattern-match known-recoverable tool errors and inject synthetic instructions before the model's next round | AI | ✓ done 2026-05-01 | `vibn-frontend/lib/ai/error-recovery.ts`. Initial rules: orphan container conflict, image pull denied, port allocated. Wired into `app/api/chat/route.ts` tool-result loop. |
| 2.9 | **Sentry-as-product loop** (SENTRY_AS_PRODUCT.md) — auto-provision per-project Sentry, bake into scaffolds, expose error feed to AI as MCP tools, auto-surface unresolved errors at chat-turn start | AI | ✓ done 2026-05-01 | All 4 stages shipped: (1) `lib/integrations/sentry.ts` provisions per-project Sentry under shared `vibnai` org from `POST /api/projects/create` and lazily on `apps.create`; injects `NEXT_PUBLIC_SENTRY_DSN` + `SENTRY_AUTH_TOKEN` into Coolify app env. (2) `lib/scaffold/sentry-snippets.ts` ships canonical Next.js + Vite snippets; AI system prompt instructs it to wire Sentry on every new app; `projects.get` returns `sentry: {slug, dsn}`. (3) Three MCP tools: `project_recent_errors`, `project_error_detail`, `project_error_resolve` (tenant-safe). (4) `app/api/chat/route.ts` injects `[PROJECT HEALTH]` block at chat-turn start when ≥2-occurrence unresolved issues exist in last 6h. End-to-end verification deferred to smoke test (4.1). |
**Definition of done:** force-fail a route in staging → Sentry alert lands in
< 1 min. Force-fail a Coolify deploy → notification fires. Reproduce an
@@ -136,13 +121,9 @@ or gets out of the way. No screens that exist "to teach the data model".
| 3.1 | **Hosting tab rewrite** — focus on the domain (live URL, redeploy, env, logs) instead of master-detail of "live + previews" | AI | 4 hrs | Mark flagged earlier |
| 3.2 | Replace the chat's "⚠️ Failed to get response. Please try again." with structured errors that show what tool failed and why | AI | 2 hrs | Critical — currently zero feedback |
| 3.3 | Empty states across Plan/Product/Infrastructure/Hosting that suggest the **next** AI prompt to try (not just "nothing here") | AI | 2 hrs | Vibe coders need a nudge |
| 3.4 | Project header URL chips: collapse to a "+N" pill when there are >3 endpoints | AI | ✓ done 2026-05-01 | `components/project/project-header-urls.tsx`: bumped MAX_VISIBLE to 3, replaced title-tooltip with click-to-open popover (closes on outside-click + Escape). Each row in the popover is a real clickable link with icon + label + host. |
| 3.5 | Status pill: tooltip should link directly to Coolify build logs | AI | ✓ done 2026-05-01 | `components/project/project-stage-pill.tsx`: "Logs" affordance now appears on `deploying`, `down`, and `build_failed` (not just failures). Deep-links to `<COOLIFY_URL>/project/<coolifyProjectUuid>` — one click from build logs. (Direct deployment-uuid link blocked on extending anatomy to surface deployment UUIDs; tracked but low priority.) |
| 3.6 | Product tab: confirm it's actually useful day-to-day. Revise scope if not | Mark + AI | 1 hr | Open question |
| 3.7 | **Scope-doc upload in Plan tab** — drop a PDF/.md/.docx/.txt as the project brief; server extracts text, stores on `fs_projects.brief_text` + `brief_meta`, exposes via `[PROJECT BRIEF]` block in system prompt and a `project_brief` MCP tool for on-demand grep. New file: `lib/integrations/brief-extract.ts`. Empty state replaces "nothing here" on Plan. | AI | 3 hrs | Came up during smoke test prep — users will arrive with scope docs (PDF/Notion-export/Doc); right now there's no way to hand the AI the source of truth except paste-into-chat. |
| 3.8 | **"Stop at something tangible" — three layers** | AI | partially done | Came up watching Manifest scaffold — AI stopped at "everything is wired together" with no preview, leaving the user to wonder if any of it was real. Code on disk is invisible; preview URL is the proof. |
| 3.8a | System-prompt rule: dedicated "Stop at something the user can see" section + tightened build-me-X recipe so `previewUrl` is the explicit stopping point | AI | ✓ done 2026-05-04 | `app/api/chat/route.ts` `buildSystemPrompt`. For multi-service stacks, instructs AI to start the user-facing service first even if other services aren't done. |
| 3.8b | ~~Persistent quick-action chips above the chat input~~ **REVERTED 2026-05-04** | AI | reverted | Tried it; pulled it. The chip menu was prescriptive ("here's what to type") which conflicts with the principle that the AI should drive toward the goal without presenting the user a menu of homework. Welcome-screen suggested prompts kept (different context — empty conversation, user genuinely needs a starting nudge). The `sendMessage(override)` refactor + welcome-screen auto-send shipped from this work survived; only the composer chip row was removed. |
| 3.8c | Server-side enforcement: if a turn called `fs_write` ≥10 times for source files but never `dev_server_start` or `apps_deploy`, append a synthetic recovery instruction telling the model to either start a server or explain the blocker | AI | 1 hr | Safety net for when the model ignores the prompt rule under load. Add a tracker in `app/api/chat/route.ts` tool loop, fire the instruction inside the round 2 system message. |
**Definition of done:** a stranger lands on every tab in turn. None of them
@@ -160,10 +141,8 @@ concrete next action.
|---|---|---|---|---|
| 4.1 | End-to-end smoke test on a fresh account: signup → workspace → project → first chat → first preview → first deploy | Mark + AI | 2 hrs | Walk through with an empty cookie jar; fix everything broken. **Runbook below.** |
| 4.2 | Landing page at `vibnai.com` that explains the product in 30s | Mark + AI | 4 hrs | Currently a login screen |
| 4.3 | "Delete project" UI in project settings (and underlying Coolify cleanup) | AI | ✓ done 2026-05-04 | `app/api/projects/delete/route.ts` now cascades: stops + deletes the dev container service (with volumes + docker-cleanup), deletes every linked Coolify resource via `fs_project_resources`, deletes the per-project Coolify project shell when no other Vibn project shares it, drops `fs_project_dev_containers` + `fs_project_resources` rows, unlinks `fs_sessions`, then deletes `fs_projects`. Gitea repo + Sentry project are deliberately preserved (returned in the response so the user can recover code/error history). Failure inside cascade is logged but doesn't abort; partial failure leaves the orphan in Coolify for manual cleanup, which is strictly better than rolling back to a half-state. Smoke test 2026-05-04 found 2 ghost containers from previously-deleted projects consuming the user's full quota; cleaned up manually + shipped this fix to prevent recurrence. |
| 4.4 | "Delete workspace" UI — same | AI | 1 hr | |
| 4.5 | Auth hardening pass: NextAuth session expiry, CSRF on mutating routes, GitHub OAuth scope review | AI | 2 hrs | |
| 4.6 | Per-workspace compute quota: max N Coolify projects, max N dev containers, soft cap with friendly error | AI | ✓ done 2026-05-01 | `lib/quotas.ts`: 3 active projects + 3 active dev containers per workspace (suspended containers don't count). Overridable via `VIBN_QUOTA_MAX_PROJECTS_PER_WORKSPACE` / `VIBN_QUOTA_MAX_DEV_CONTAINERS_PER_WORKSPACE` env. Hits return HTTP 402 with structured payload; AI's error-recovery middleware has a `workspace-quota-exceeded` rule that explains the cap to the user without blind retries. Wired into `POST /api/projects/create` and `lib/dev-container.ts` ensure/resume paths. |
| 4.7 | Per-workspace audit log of mutating MCP calls (apps/databases/services create/delete) | AI | 2 hrs | We need this when something goes wrong |
| 4.8 | Invite link / waitlist page (manual approval) so we control who joins | Mark + AI | 1 hr | |
@@ -179,13 +158,11 @@ that aren't covered above.
| # | Task | Owner | Effort | Notes |
|---|---|---|---|---|
| 5.1 | Build `ghcr.io/vibnai/vibn-dev:latest` on the live Coolify host (`ssh + setup-on-coolify.sh`) | AI | ✓ done 2026-05-01 | Image `vibn-dev:latest` built 2026-04-30 on Coolify host (589 MB, last Dockerfile change Apr 28 so build is current). Smoke-tested as `vibn` user: ripgrep, git, mise all functional. Toolchains install on demand via mise. |
| 5.2 | Hard-remove `gitea_file_*` from the AI tool list; keep REST routes alive 30 days with deprecation header | AI | 1 hr | Path B week 3 task |
| 5.3 | Update `AI_CAPABILITIES.md` to reflect everything that shipped | AI | 1 hr | |
| 5.4 | Eval harness: 10 reference prompts, measure time-to-first-preview, time-to-shipped, tool-call count, success rate | AI | 1–2 days | The actual proof Path B works |
| 5.5 | Theia / openvscode-server toggle: "Open IDE" button in chat → `https://ide-{ws}-{project}.vibnai.com` | AI | 4 hrs | Week 4 nice-to-have; gates the "user becomes developer" graduation |
| 5.6 | Idle-suspend cron — wire `POST /api/admin/path-b/idle-sweep` to a 5-min schedule once we trust it | AI | 30 min | Keeps cost bounded |
| 5.7 | **Persistent dev container ↔ Gitea wiring** — auto-clone repo into `/workspace/<slug>/` on first chat turn; auto-commit + push at end of every turn so AI work surfaces in the Product tab without manual `gitea_*` calls | AI | ✓ done 2026-05-04 | `lib/dev-container-git.ts` (`ensureProjectRepoCloned`, `commitAndPushIfDirty`) wired into `app/api/chat/route.ts` pre-loop + turn-end. Tri-state probe (`git` / `dir` / `absent`) so projects with files-but-no-git auto-heal on next turn. Production fix shipped today: `GITEA_USERNAME` was missing from prod env so `isGiteaConfigured()` silently no-op'd; added the env value AND a defensive fallback to `GITEA_ADMIN_USER` in code. Backfilled `vibn-mark/manifest` repo manually from the dev container after the env fix. Smoke-tested by inspecting `/workspace/manifest/` over SSH bridge — 64 tracked files pushed, all 6 phase directories present. |
**Definition of done:** eval harness reports ≥3× speedup on time-to-first-preview
vs. Path A baseline, ≥80% success rate across the 10 reference prompts.