@rizom/ops 0.2.0-alpha.2 → 0.2.0-alpha.200

package/templates/rover-pilot/deploy/scripts/resolve-deploy-handles.ts

@@ -9,14 +9,23 @@ if (eventName === "workflow_dispatch") {
   process.exit(0);
 }
 
-if (eventName !== "push") {
+if (eventName !== "push" && eventName !== "workflow_run") {
   throw new Error(`Unsupported GITHUB_EVENT_NAME: ${eventName}`);
 }
 
 const beforeSha = requireEnv("BEFORE_SHA");
-const currentSha = requireEnv("GITHUB_SHA");
+const currentSha =
+  eventName === "workflow_run"
+    ? execFileSync("git", ["rev-parse", "HEAD"], {
+        encoding: "utf8",
+      }).trim()
+    : requireEnv("GITHUB_SHA");
 
-if (!isUsableGitRevision(beforeSha) || !isUsableGitRevision(currentSha)) {
+if (
+  !isUsableGitRevision(beforeSha) ||
+  !isUsableGitRevision(currentSha) ||
+  beforeSha === currentSha
+) {
   writeGitHubOutput("handles_json", JSON.stringify([]));
   process.exit(0);
 }
@@ -32,7 +41,9 @@ const handles = [
     diffOutput
       .split(/\r?\n/)
       .map((path) => {
-        const match = path.match(/^users\/([^/]+)\/(?:\.env|brain\.yaml)$/);
+        const match =
+          path.match(/^users\/([^/]+)\/(?:\.env|brain\.yaml|content\/.*)$/) ??
+          path.match(/^users\/([^/]+)\.secrets\.yaml\.age$/);
         return match?.[1] ?? null;
       })
       .filter((handle): handle is string => handle !== null)

package/templates/rover-pilot/deploy/scripts/resolve-missing-images.ts

@@ -0,0 +1,13 @@
+import {
+  requireEnv,
+  runResolveMissingImages,
+  writeGitHubOutput,
+} from "./helpers";
+
+// The Build workflow's resolve step — the logic lives in @rizom/ops; this
+// pilot repo only supplies its own paths and repository.
+await runResolveMissingImages({
+  rootDir: process.cwd(),
+  imageRepository: `ghcr.io/${requireEnv("GITHUB_REPOSITORY")}`,
+  writeOutput: writeGitHubOutput,
+});

package/templates/rover-pilot/deploy/scripts/resolve-user-config.ts

@@ -1,5 +1,14 @@
 import { readFileSync } from "node:fs";
-import { parseEnvFile, requireEnv, writeGitHubOutput } from "./helpers";
+
+import { loadPilotRegistry } from "@rizom/ops";
+
+import {
+  parseEnvFile,
+  requireEnv,
+  sitePackagesFor,
+  siteImageTag,
+  writeGitHubOutput,
+} from "./helpers";
 
 const handle = requireEnv("HANDLE");
 const envPath = `users/${handle}/.env`;
@@ -12,32 +21,52 @@ const repositoryOwner = repository.split("/")[0] ?? "";
 const brainYaml = readFileSync(brainYamlPath, "utf8");
 const domainMatch = brainYaml.match(/^domain:\s*(.+)$/m);
 const brainDomain = domainMatch?.[1]?.trim().replace(/^['"]|['"]$/g, "") ?? "";
-
 if (!brainDomain) {
   throw new Error(`Missing domain in ${brainYamlPath}`);
 }
 
+const registry = await loadPilotRegistry(process.cwd());
+const user = registry.users.find((entry) => entry.handle === handle);
+if (!user) {
+  throw new Error(`Unknown user handle: ${handle}`);
+}
+const previewDomain = resolvePreviewDomain(
+  handle,
+  brainDomain,
+  registry.pilot.domainSuffix,
+);
+const wwwDomain = isFleetDomain(
+  handle,
+  brainDomain,
+  registry.pilot.domainSuffix,
+)
+  ? ""
+  : `www.${brainDomain}`;
+
+const brainVersion = envEntries["BRAIN_VERSION"] ?? "";
+
+// The image tag is a pure function of this instance's own config: plain
+// `brain-{version}` for a default instance, or its own `brain-{version}-sites-
+// {hash}` when it declares a siteOverride. Resolved through the same helper the
+// build uses so the tag we wait for and run matches exactly what was pushed.
+const sitePackages = sitePackagesFor(user.siteOverride);
+const imageTag = siteImageTag(brainVersion, sitePackages);
+
 const outputs: Record<string, string> = {
-  brain_version: envEntries["BRAIN_VERSION"] ?? "",
-  ai_api_key_secret_name: envEntries["AI_API_KEY_SECRET"] ?? "",
-  git_sync_token_secret_name: envEntries["GIT_SYNC_TOKEN_SECRET"] ?? "",
-  mcp_auth_token_secret_name: envEntries["MCP_AUTH_TOKEN_SECRET"] ?? "",
-  discord_bot_token_secret_name: envEntries["DISCORD_BOT_TOKEN_SECRET"] ?? "",
+  brain_version: brainVersion,
   content_repo: envEntries["CONTENT_REPO"] ?? "",
   brain_domain: brainDomain,
+  preview_domain: previewDomain,
+  www_domain: wwwDomain,
+  cloudflare_zone_id: user.cloudflareZoneId ?? process.env["CF_ZONE_ID"] ?? "",
   brain_yaml_path: brainYamlPath,
   instance_name: `rover-${handle}`,
   image_repository: `ghcr.io/${repository}`,
+  image_tag: imageTag,
   registry_username: repositoryOwner,
 };
 
-const required = [
-  "brain_version",
-  "ai_api_key_secret_name",
-  "git_sync_token_secret_name",
-  "mcp_auth_token_secret_name",
-  "registry_username",
-];
+const required = ["brain_version", "registry_username"];
 for (const key of required) {
   if (!outputs[key]) {
     throw new Error(`Missing ${key} (derived from ${envPath})`);
@@ -47,3 +76,28 @@ for (const key of required) {
 for (const [key, value] of Object.entries(outputs)) {
   writeGitHubOutput(key, value);
 }
+
+function resolvePreviewDomain(
+  userHandle: string,
+  domain: string,
+  pilotDomainSuffix: string,
+): string {
+  if (!isFleetDomain(userHandle, domain, pilotDomainSuffix)) {
+    return `preview.${domain}`;
+  }
+
+  const fleetZone = pilotDomainSuffix.replace(/^\./, "");
+  if (!fleetZone) {
+    throw new Error(`Could not derive preview domain from ${domain}`);
+  }
+
+  return `${userHandle}-preview.${fleetZone}`;
+}
+
+function isFleetDomain(
+  userHandle: string,
+  domain: string,
+  pilotDomainSuffix: string,
+): boolean {
+  return domain === `${userHandle}${pilotDomainSuffix}`;
+}

package/templates/rover-pilot/deploy/scripts/sync-content-repo.ts

@@ -0,0 +1,183 @@
+import { cp, mkdtemp, mkdir, readFile, readdir } from "node:fs/promises";
+import { existsSync } from "node:fs";
+import { tmpdir } from "node:os";
+import { dirname, join } from "node:path";
+import { execFileSync } from "node:child_process";
+import { readJsonResponse, requireEnv } from "./helpers";
+
+const STALE_ANCHOR_PROFILE_MARKERS = [
+  "name: Your Name Here",
+  "Delete this and write your own",
+];
+
+interface EnsureGitHubRepoOptions {
+  owner: string;
+  repo: string;
+  token: string;
+}
+
+interface GitHubRepoResponse {
+  clone_url?: string;
+  private?: boolean;
+}
+
+async function main(): Promise<void> {
+  const handle = requireEnv("HANDLE");
+  const contentRepo = requireEnv("CONTENT_REPO");
+  const token = requireEnv("GIT_SYNC_TOKEN");
+  const sourceDir = join("users", handle, "content");
+
+  if (!existsSync(sourceDir)) {
+    return;
+  }
+
+  const { owner, repo } = parseRepoSlug(contentRepo);
+  await ensureGitHubRepo({ owner, repo, token });
+
+  const tempRoot = await mkdtemp(join(tmpdir(), "brains-ops-content-"));
+  const checkoutDir = join(tempRoot, "repo");
+  const remoteUrl = buildAuthenticatedRemoteUrl(owner, repo, token);
+
+  runGit(["clone", remoteUrl, checkoutDir]);
+  runGit(["-C", checkoutDir, "checkout", "-B", "main"]);
+
+  const copiedFiles = await copyMissingFiles(sourceDir, checkoutDir);
+  if (copiedFiles === 0) {
+    return;
+  }
+
+  runGit(["-C", checkoutDir, "config", "user.name", "brains-ops[bot]"]);
+  runGit([
+    "-C",
+    checkoutDir,
+    "config",
+    "user.email",
+    "41898282+github-actions[bot]@users.noreply.github.com",
+  ]);
+  runGit(["-C", checkoutDir, "add", "."]);
+
+  if (hasNoStagedChanges(checkoutDir)) {
+    return;
+  }
+
+  runGit([
+    "-C",
+    checkoutDir,
+    "commit",
+    "-m",
+    `chore(content): seed ${handle} anchor profile`,
+  ]);
+  runGit(["-C", checkoutDir, "push", "origin", "HEAD:main"]);
+}
+
+async function ensureGitHubRepo(
+  options: EnsureGitHubRepoOptions,
+): Promise<void> {
+  const headers = {
+    Authorization: `Bearer ${options.token}`,
+    Accept: "application/vnd.github+json",
+    "Content-Type": "application/json",
+  };
+  const repoUrl = `https://api.github.com/repos/${options.owner}/${options.repo}`;
+  const repoResponse = await fetch(repoUrl, { headers });
+
+  if (repoResponse.ok) {
+    await readJsonResponse(repoResponse, "GitHub repo lookup");
+    return;
+  }
+
+  if (repoResponse.status !== 404) {
+    const payload = await readJsonResponse(repoResponse, "GitHub repo lookup");
+    throw new Error(`GitHub repo lookup failed: ${JSON.stringify(payload)}`);
+  }
+
+  const createResponse = await fetch(
+    `https://api.github.com/orgs/${options.owner}/repos`,
+    {
+      method: "POST",
+      headers,
+      body: JSON.stringify({
+        name: options.repo,
+        private: true,
+        auto_init: false,
+      }),
+    },
+  );
+  const payload = (await readJsonResponse(
+    createResponse,
+    "GitHub repo create",
+  )) as GitHubRepoResponse;
+
+  if (!createResponse.ok) {
+    throw new Error(`GitHub repo create failed: ${JSON.stringify(payload)}`);
+  }
+}
+
+function parseRepoSlug(contentRepo: string): { owner: string; repo: string } {
+  const [owner, repo] = contentRepo.split("/");
+  if (!owner || !repo) {
+    throw new Error(`Invalid CONTENT_REPO: ${contentRepo}`);
+  }
+  return { owner, repo };
+}
+
+function buildAuthenticatedRemoteUrl(
+  owner: string,
+  repo: string,
+  token: string,
+): string {
+  return `https://x-access-token:${encodeURIComponent(token)}@github.com/${owner}/${repo}.git`;
+}
+
+function runGit(args: string[]): void {
+  execFileSync("git", args, { stdio: "inherit" });
+}
+
+function hasNoStagedChanges(checkoutDir: string): boolean {
+  try {
+    execFileSync("git", ["-C", checkoutDir, "diff", "--cached", "--quiet"], {
+      stdio: "ignore",
+    });
+    return true;
+  } catch {
+    return false;
+  }
+}
+
+async function copyMissingFiles(
+  sourceDir: string,
+  targetDir: string,
+): Promise<number> {
+  const entries = await readdir(sourceDir, { withFileTypes: true });
+  let copiedFiles = 0;
+
+  for (const entry of entries) {
+    const sourcePath = join(sourceDir, entry.name);
+    const targetPath = join(targetDir, entry.name);
+
+    if (entry.isDirectory()) {
+      await mkdir(targetPath, { recursive: true });
+      copiedFiles += await copyMissingFiles(sourcePath, targetPath);
+      continue;
+    }
+
+    const existing = await readFile(targetPath, "utf8").catch(() => undefined);
+    if (existing !== undefined && !isStaleAnchorProfile(existing)) {
+      continue;
+    }
+
+    await mkdir(dirname(targetPath), { recursive: true });
+    await cp(sourcePath, targetPath, { force: true });
+    copiedFiles += existing === (await readFile(sourcePath, "utf8")) ? 0 : 1;
+  }
+
+  return copiedFiles;
+}
+
+function isStaleAnchorProfile(content: string): boolean {
+  return STALE_ANCHOR_PROFILE_MARKERS.some((marker) =>
+    content.includes(marker),
+  );
+}
+
+await main();

package/templates/rover-pilot/deploy/scripts/update-dns.ts

@@ -16,8 +16,11 @@ interface CloudflareResult {
   result?: Array<{ id: string }>;
 }
 
-async function upsertRecord(name: string): Promise<void> {
-  const lookupUrl = `${baseUrl}/zones/${zoneId}/dns_records?type=A&name=${encodeURIComponent(name)}`;
+async function findRecordId(
+  name: string,
+  type: "A" | "CNAME",
+): Promise<string | undefined> {
+  const lookupUrl = `${baseUrl}/zones/${zoneId}/dns_records?type=${type}&name=${encodeURIComponent(name)}`;
   const lookup = await fetch(lookupUrl, { headers });
   const payload = (await readJsonResponse(
     lookup,
@@ -27,9 +30,16 @@ async function upsertRecord(name: string): Promise<void> {
     throw new Error(`Cloudflare DNS lookup failed: ${JSON.stringify(payload)}`);
   }
 
-  const existing = payload.result?.[0];
+  return payload.result?.[0]?.id;
+}
+
+async function upsertRecord(name: string): Promise<void> {
+  // Prefer an existing A record. If the hostname currently has a CNAME,
+  // replace that CNAME in-place so deploys can claim legacy www aliases.
+  const existing =
+    (await findRecordId(name, "A")) ?? (await findRecordId(name, "CNAME"));
   const url = existing
-    ? `${baseUrl}/zones/${zoneId}/dns_records/${existing.id}`
+    ? `${baseUrl}/zones/${zoneId}/dns_records/${existing}`
     : `${baseUrl}/zones/${zoneId}/dns_records`;
 
   const response = await fetch(url, {

package/templates/rover-pilot/deploy/scripts/validate-secrets.ts

@@ -4,7 +4,7 @@ import { parseEnvSchema } from "./helpers";
 const envSchemaPath = ".env.schema";
 const schema = parseEnvSchema(readFileSync(envSchemaPath, "utf8"));
 const requiredKeys = schema
-  .filter((entry) => entry.required)
+  .filter((entry) => entry.required && entry.key !== "BWS_ACCESS_TOKEN")
   .map((entry) => entry.key);
 
 const missing: string[] = [];

package/templates/rover-pilot/docs/onboarding-checklist.md

@@ -1,11 +1,46 @@
 # Onboarding Checklist
 
 1. Run `bun install` so the repo uses its pinned `@rizom/ops` version.
-2. Fill in `pilot.yaml`.
-3. Add or edit `users/<handle>.yaml`.
-4. Add the user to a cohort in `cohorts/*.yaml`.
-5. Run `bunx brains-ops render <repo>`.
-6. Run `bunx brains-ops secrets:push <repo> <handle>`.
-7. Run `bunx brains-ops onboard <repo> <handle>`.
-8. For fleet upgrades, edit `pilot.yaml.brainVersion` and push once; CI rebuilds the shared image tag, refreshes generated user env files, and redeploys affected users.
-9. Hand the MCP connection details to the user.
+2. Run `bunx brains-ops age-key:bootstrap <repo> --push-to gh`.
+3. Fill in `pilot.yaml`.
+   - keep your pinned `brainVersion`
+   - confirm shared selectors for `aiApiKey`, `gitSyncToken`, and `contentRepoAdminToken`
+   - use different tokens for `contentRepoAdminToken` and `gitSyncToken`: admin creates/checks content repos; sync is used by runtime directory-sync
+   - confirm `agePublicKey`
+4. Run `bunx brains-ops user:add <repo> <handle> --cohort <cohort>`.
+   - Web chat is the primary interface; it needs no per-user setup beyond the passkey.
+   - `user:add` currently writes `discord: enabled: true`; set it to `false` unless the user's cohort actually uses Discord.
+   - if the user should be an anchor on Discord, add `--anchor-id <discord-user-id>`.
+   - the command creates `users/<handle>.yaml`, `users/<handle>.secrets.yaml`, and the cohort membership without duplicating existing entries.
+5. Edit the generated user file if the anchor profile needs richer metadata.
+   - Set `setup.delivery: email` and `setup.email` so the user gets the passkey setup email — this is the default onboarding path.
+   - For ATProto publishing, add `atproto.identifier` to the user file; put only `atprotoAppPassword` in the per-user secrets file.
+   - Ensure `SETUP_EMAIL_API_KEY` and `SETUP_EMAIL_FROM` exist as GitHub Secrets before deploying any email-setup user.
+6. Run `bunx brains-ops render <repo>`.
+7. Run `bunx brains-ops ssh-key:bootstrap <repo> --push-to gh`.
+8. Run `bunx brains-ops cert:bootstrap <repo> --push-to gh`.
+9. Keep raw user secret material locally for now (`.env.local`, file-backed env vars, or equivalent local inputs), including `CONTENT_REPO_ADMIN_TOKEN` for operator onboarding.
+10. Run `bunx brains-ops secrets:encrypt <repo> <handle>`.
+11. Commit and push `users/<handle>.secrets.yaml.age`.
+12. Run `bunx brains-ops onboard <repo> <handle>`.
+13. Verify the deployed Rover contract:
+    - all presets:
+      - `https://<handle>.rizom.ai/health` returns `200`
+      - `https://<handle>.rizom.ai/chat` loads the web chat and accepts passkey sign-in
+      - `https://<handle>.rizom.ai/` loads the dashboard (or site surface on `default` preset)
+      - `https://<handle>.rizom.ai/cms` loads the CMS/login surface
+      - unauthenticated `POST https://<handle>.rizom.ai/mcp` returns the expected auth failure
+      - content repo exists and runtime sync is healthy
+      - background jobs are not repeatedly failing, except for expected missing optional integrations
+    - for `presetOverride: default` users:
+      - initial site build completes
+14. For fleet upgrades, edit `pilot.yaml.brainVersion` and push once; CI rebuilds the shared image tag, refreshes generated user env files, and redeploys affected users.
+15. Confirm the user received the setup email, registered their passkey, and can sign in to web chat at `https://<handle>.rizom.ai/chat`. That completes the default onboarding; everything below is per-cohort extras.
+16. Hand over the browser surfaces:
+    - Chat (primary): `https://<handle>.rizom.ai/chat`
+    - Dashboard: `https://<handle>.rizom.ai/`
+    - CMS: `https://<handle>.rizom.ai/cms`, plus GitHub token guidance if CMS editing is part of their cohort
+17. For Discord-enabled cohorts, hand the Discord setup details to the user as a secondary chat surface.
+18. If they need direct client access (MCP), use OAuth/passkey-capable clients where possible.
+19. If you are also giving them a content repo workflow, describe it as optional and frame git/Obsidian as an advanced file-based path, not the default.
+20. Send `docs/user-onboarding.md` to the user as the pilot handoff guide.

package/templates/rover-pilot/docs/operator-playbook.md

@@ -33,6 +33,36 @@ When a push changes only deploy contract files and no generated `users/<handle>/
 
 They are scaffolded from `@rizom/ops`, then versioned in this repo like any other deploy contract.
 
+## Stale deploy lock recovery
+
+Kamal intentionally leaves its remote deploy lock in place when a deployment is cancelled or interrupted. Confirm that no deployment for the user is still active before releasing the lock, then use the deploy workflow's explicit recovery input:
+
+```sh
+gh workflow run Deploy --ref main \
+  -f handle=<handle> \
+  -f release_stale_lock=true
+```
+
+Recovery is opt-in and scoped to one handle. Normal push, reconcile, and manual deploy runs never remove a lock automatically.
+
+## Bootstrap flow
+
+For this fleet, operator-local secret material remains the source of truth during onboarding and rotation. The repo stores encrypted per-user secrets, not raw values.
+
+For a new pilot user, the operator bootstrap order is:
+
+1. `bunx brains-ops age-key:bootstrap <repo> --push-to gh`
+2. `bunx brains-ops ssh-key:bootstrap <repo> --push-to gh`
+3. `bunx brains-ops cert:bootstrap <repo> --push-to gh`
+4. `bunx brains-ops secrets:encrypt <repo> <handle>`
+5. `bunx brains-ops onboard <repo> <handle>`
+
+`age-key:bootstrap` keeps a repo-local canonical age identity under `.brains-ops/age/identity.txt`, writes the matching public recipient to `pilot.yaml.agePublicKey`, and can push the private key to GitHub as `AGE_SECRET_KEY`.
+
+The shared cert bootstrap writes local cert artifacts under `.brains-ops/certs/shared/`, which stays repo-local and ignored by git.
+
+Preview hosts use the shape `<handle>-preview.rizom.ai`, so one wildcard origin cert for `*.rizom.ai` covers both the primary and preview hosts for every pilot user.
+
 ## Upgrading operator behavior
 
 When `@rizom/ops` changes the scaffolded deploy contract:
@@ -42,6 +72,158 @@ When `@rizom/ops` changes the scaffolded deploy contract:
 3. review the resulting changes to `.env.schema`, `deploy/scripts/`, and workflows in git
 4. commit the updated deploy artifacts together
 
+## Rover verification notes
+
+Use the verification script after deploy:
+
+```sh
+bunx brains-ops verify-user . <handle>
+```
+
+It checks every Rover preset:
+
+- `https://<handle>.rizom.ai/health` should return `200`
+- unauthenticated `POST https://<handle>.rizom.ai/mcp` should return the expected auth failure
+- background jobs should not be repeatedly failing, except for expected missing optional integrations
+
+Additional `rover:core` note:
+
+- Rover core is MCP-only; a bare `GET /` may return `401`, which does not indicate a bad deploy.
+
+For `preset: default`, the script also checks:
+
+- `https://<handle>.rizom.ai/` loads the browser/site surface
+- `https://<handle>.rizom.ai/cms` loads the CMS/login surface
+
+Manual checks that remain:
+
+- initial site build is correct for the expected content/theme
+- content repo exists and runtime sync is healthy beyond the basic `/health` response
+- passkey setup/handoff is completed from the setup email
+
+## One-user `rover:default` baseline canary
+
+Run this before adding custom site/theme packages or rolling a larger browser/CMS-first cohort.
+
+1. Create or choose a canary cohort with the default preset:
+
+   ```yaml
+   presetOverride: default
+   ```
+
+2. Add exactly one canary user to that cohort.
+3. For browser/CMS-first onboarding, configure setup email in `users/<handle>.yaml`:
+
+   ```yaml
+   setup:
+     delivery: email
+     email: user@example.com
+   ```
+
+4. Encrypt the user's secrets and commit only the `.age` file.
+5. Run `bunx brains-ops onboard . <handle>`.
+6. Run `bunx brains-ops verify-user . <handle>` with no custom site/theme overrides.
+7. Ask the user to complete passkey setup from the setup email.
+8. Continue to visual customization only after the canary is healthy.
+
+Rollback:
+
+- move the canary back to a core cohort, or remove `presetOverride: default` from the cohort
+- reconcile generated outputs
+- rebuild/redeploy the affected user
+
+## Setup email checklist
+
+Use this for browser/CMS-first users who should receive their own first-passkey setup link by email.
+
+1. Add setup delivery to the user file:
+
+   ```yaml
+   setup:
+     delivery: email
+     email: user@example.com
+   ```
+
+2. Configure these GitHub Secrets before deploy:
+   - `SETUP_EMAIL_API_KEY`
+   - `SETUP_EMAIL_FROM`
+
+3. Reconcile/deploy the user or cohort:
+   - `bunx brains-ops onboard . <handle>`
+   - or `bunx brains-ops reconcile-cohort . <cohort>`
+
+4. Verify the generated `users/<handle>/brain.yaml` contains `auth-service.setupEmail` and `email-resend` config.
+5. Ask the user to complete passkey setup from the email link, then use:
+   - Dashboard: `https://<handle>.rizom.ai/`
+   - CMS: `https://<handle>.rizom.ai/cms`
+
+Notes:
+
+- The setup URL is generated and sent by the running brain; operators should not scrape logs or SSH into the instance to retrieve it.
+- The auth service owns setup email dedupe. It should not resend for the same persisted setup token after restart, but should retry failed delivery and resend after token rotation.
+- `SETUP_EMAIL_FROM` is not marked required because fleets without email setup can omit it, but it is required for users with `setup.delivery: email`.
+
+## AT Protocol smoke/config checklist
+
+Use this when enabling AT Protocol publishing for a single pilot user.
+
+1. Add the public PDS identifier to the user file:
+
+   ```yaml
+   atproto:
+     identifier: rizom-test.bsky.social
+   ```
+
+2. Put the app password in `users/<handle>.secrets.yaml`:
+
+   ```yaml
+   atprotoAppPassword: <app-password>
+   ```
+
+3. Encrypt the per-user secret payload:
+   - `bunx brains-ops secrets:encrypt . <handle>`
+4. Reconcile/deploy the user or cohort:
+   - `bunx brains-ops onboard . <handle>`
+   - or `bunx brains-ops reconcile-cohort . <cohort>`
+5. Verify the generated `users/<handle>/brain.yaml` contains `plugins.atproto.identifier` and `appPassword: ${ATPROTO_APP_PASSWORD}`.
+
+Notes:
+
+- The ATProto identifier is public instance config and belongs in `users/<handle>.yaml`.
+- The ATProto app password is secret and belongs only in the encrypted per-user secret payload.
+- For smoke deployments, pin only the smoke cohort/user to the released brain version that contains ATProto support.
+
+## Discord bot token checklist
+
+Use this when enabling Discord for a pilot user.
+
+1. Pick the user handle (for example `smoke`).
+2. Open the Discord Developer Portal.
+3. Create a **new application** for that user's rover.
+4. Add a **Bot** to the application.
+5. Copy the bot token.
+6. Put that value in `.env` or `.env.local` in this repo as `DISCORD_BOT_TOKEN=...` while onboarding that user.
+7. Keep `discord.enabled: true` in `users/<handle>.yaml` unless you explicitly want to disable the primary pilot interface.
+8. Encrypt the current per-user secret payload:
+   - `bunx brains-ops secrets:encrypt . <handle>`
+9. Reconcile/deploy the user or cohort:
+
+- `bunx brains-ops onboard . <handle>`
+- or `bunx brains-ops reconcile-cohort . <cohort>`
+
+11. In the Discord Developer Portal, generate an install URL and invite the bot to the right server.
+12. Send a test message in Discord and confirm the rover responds.
+
+Notes:
+
+- Use **one bot token per user/rover**.
+- Do not reuse the same Discord bot token across multiple pilot users.
+- Discord is the default pilot interface moving forward.
+- The encrypted `users/<handle>.secrets.yaml.age` file is the durable checked-in deploy input; your local env is only the operator staging source.
+- Direct MCP client access should use OAuth/passkey-capable clients where possible.
+- When explaining the content workflow, describe it first as a normal **git repo** of **markdown/text files**.
+- Position **Obsidian** as optional: it is just one possible editor for those same files, not the default requirement.
+
 ## Recovery notes
 
 Document known failure modes, recovery steps, and operator notes here.