create-op-node 0.6.0 → 0.8.0

package/README.md

@@ -30,9 +30,23 @@ Configures macOS power settings, installs Homebrew + the CLI tool list, sets up
 
 ### Choosing the LLM model
 
-By default bootstrap pulls `qwen3.5:9b` (LLM) and `nomic-embed-text`
-(embeddings) — small enough to validate the inference path on first
-run. Override with flags:
+When you run `bootstrap` interactively (no `-y`, no `--llm-model` flag),
+you'll get a curated picker:
+
+- `qwen2.5:72b` — 72B, ~50 GB Ollama RAM. **Default**, recommended for
+  128 GB Studios. Best Spanish + multilingual quality.
+- `qwen2.5:32b` — 32B, ~22 GB Ollama RAM. Middle tier for 64 GB Studios.
+- `qwen3.5:9b` — 9B, ~8 GB Ollama RAM. Validation runs or smaller
+  Studios (36–48 GB).
+- `Other…` — any Ollama model name you specify.
+
+The picker is Qwen-only because the Opus Populi platform serves
+Spanish-speaking civic users and Qwen has the strongest Spanish (and
+broader multilingual) capability of the open-weight models in this
+size class. Pick "Other…" for non-Qwen models.
+
+For non-interactive runs (`-y`) or scripted invocations, the LLM
+defaults to `qwen3.5:9b` (small, fast) — pass `--llm-model` to override:
 
 ```bash
 # Just swap the LLM, keep the default embedding model:
@@ -188,6 +202,11 @@ npx create-op-node reset --region us-ca --dry-run
 
 # Nuke from orbit: containers + volumes + LaunchAgent + ghcr credentials.
 npx create-op-node reset --region us-ca --wipe-data
+
+# Even more: ALSO drop all docker images (forces re-pull on next bootstrap).
+# Use this for the "wipe everything and start over" iteration loop while
+# debugging a fresh bootstrap. Implies --wipe-data.
+npx create-op-node reset --region us-ca --wipe-images
 ```
 
 ## Verifying a live node
@@ -527,6 +546,17 @@ pnpm build                  # tsup → dist/
 node dist/cli.js --help     # test the built binary
 ```
 
+### Releases
+
+Releases are automated via [release-please](https://github.com/googleapis/release-please-action):
+
+1. **Write Conventional Commits.** `feat:` → minor bump (or major on `BREAKING CHANGE:`); `fix:` → patch; `docs:`/`refactor:`/`perf:` show up in CHANGELOG; `chore:`/`test:`/`build:`/`ci:` are hidden.
+2. **Merge PRs to `main`** as normal.
+3. **release-please opens a `chore(main): release X.Y.Z` PR** that bumps `package.json` + `src/cli.ts`'s `VERSION` constant + adds a CHANGELOG section. It updates the PR continuously as more commits land.
+4. **Merge the release PR.** That creates the `vX.Y.Z` tag + a GitHub Release. `publish.yml` fires on the tag push and runs `npm publish --provenance --access public`.
+
+No manual version bumps, no manual tagging. To trigger a release with no functional changes (re-publishing after a CI fix, etc.), push a commit with `chore: trigger release` — release-please will skip it but still update the PR.
+
 ## License
 
 [AGPL-3.0-or-later](./LICENSE). The Opus Populi platform code is AGPL-3.0 + dual commercial; this CLI inherits the AGPL-3.0 terms.

package/dist/cli.js

@@ -1151,6 +1151,13 @@ async function enableAutoRestartOnPowerFailure() {
 async function disableDiskSleep() {
   return runSudoPmset(["disksleep", "0"]);
 }
+async function detectUnifiedMemoryGB() {
+  const res = await safeExeca("sysctl", ["-n", "hw.memsize"]);
+  if (res === null || res.exitCode !== 0) return null;
+  const bytes = Number.parseInt(res.stdout.trim(), 10);
+  if (!Number.isFinite(bytes) || bytes <= 0) return null;
+  return Math.round(bytes / 2 ** 30);
+}
 async function runSudoPmset(args) {
   const res = await safeExeca("sudo", ["pmset", "-a", ...args]);
   if (res === null) {
@@ -1372,8 +1379,14 @@ async function composeDown(opts) {
   const flags = ["down"];
   if (opts.wipeVolumes) flags.push("-v");
   if (opts.removeOrphans) flags.push("--remove-orphans");
+  if (opts.removeImages) flags.push("--rmi", opts.removeImages);
+  const label = [
+    "compose down",
+    opts.wipeVolumes ? "-v" : "",
+    opts.removeImages ? `--rmi ${opts.removeImages}` : ""
+  ].filter(Boolean).join(" ");
   const res = await safeExeca("docker", composeArgs(opts, flags));
-  return result(res, opts.wipeVolumes ? "compose down -v" : "compose down");
+  return result(res, label);
 }
 async function dockerLogout(registry = GHCR_REGISTRY) {
   const res = await safeExeca("docker", ["logout", registry]);
@@ -1690,7 +1703,11 @@ var bootstrapCommand = new Command("bootstrap").description(
   const repoName = `opuspopuli-node-${region}`;
   const composeFileDefault = opts.localOnly ? ["docker-compose-prod.yml"] : ["docker-compose-prod.yml", "docker-compose-backup.yml"];
   const composeFile = opts.composeFile ?? composeFileDefault;
-  const [embeddingModel, llmModel] = resolveModels(opts);
+  const llmModelChoice = opts.llmModel ?? await selectLlmModel(opts);
+  const [embeddingModel, llmModel] = resolveModels({
+    llmModel: llmModelChoice,
+    ...opts.embeddingModel !== void 0 ? { embeddingModel: opts.embeddingModel } : {}
+  });
   const sysSpin = p3.spinner();
   sysSpin.start("Inspecting macOS\u2026");
   const snap = await inspectSystem();
@@ -1751,7 +1768,7 @@ var bootstrapCommand = new Command("bootstrap").description(
       unwrap(await p3.confirm({ message: "Homebrew installed?", initialValue: true }));
     }
     const brewSpin = p3.spinner();
-    brewSpin.start("Installing Studio packages\u2026");
+    brewSpin.start("Installing Studio packages\u2026 (~5\u201315 min first run)");
     const report = await installPackages(STUDIO_PACKAGES, (pkg, status) => {
       brewSpin.message(`${status}: ${pkg.name}`);
     });
@@ -1852,7 +1869,7 @@ var bootstrapCommand = new Command("bootstrap").description(
   ghcrSpin.stop(pc2.green("\u2713 Logged in to ghcr.io."));
   if (!opts.skipOllama) {
     const olSpin = p3.spinner();
-    olSpin.start("Pulling + warming Ollama models\u2026");
+    olSpin.start(`Pulling + warming Ollama models\u2026 (${estimatedPullTime(llmModel)})`);
     let olHealth = await checkOllamaHealth();
     if (!olHealth.reachable) {
       olSpin.message("Ollama not reachable \u2014 running `brew services start ollama`\u2026");
@@ -1917,7 +1934,7 @@ var bootstrapCommand = new Command("bootstrap").description(
     );
   }
   const pullSpin = p3.spinner();
-  pullSpin.start("Pulling images from ghcr.io\u2026");
+  pullSpin.start("Pulling images from ghcr.io\u2026 (~5\u201315 min first run, < 1 min cached)");
   const pull = await composePull(composeOpts);
   if (!pull.ok) {
     pullSpin.stop(pc2.red("\u2717 compose pull failed."));
@@ -1935,7 +1952,7 @@ var bootstrapCommand = new Command("bootstrap").description(
   }
   upSpin.stop(pc2.green("\u2713 Containers started \u2014 waiting for healthy\u2026"));
   const healthSpin = p3.spinner();
-  healthSpin.start("Polling for healthy containers (5s, up to 5 minutes)\u2026");
+  healthSpin.start("Polling for healthy containers\u2026 (every 5s, up to 5 min)");
   const outcome = await waitForHealthy(composeOpts, {
     onPoll: (snaps) => {
       const healthy = snaps.filter((s) => s.health === "healthy").length;
@@ -2001,6 +2018,69 @@ function resolveModels(opts) {
     opts.llmModel ?? DEFAULT_LLM_MODEL
   ];
 }
+var LLM_MODEL_CHOICES = [
+  {
+    value: "qwen2.5:72b",
+    label: "qwen2.5:72b",
+    hint: "72B, ~50 GB Ollama RAM. Recommended for 128 GB Studios. Best Spanish + multilingual quality. Pull ~40 GB, 30\u201360 min."
+  },
+  {
+    value: "qwen2.5:32b",
+    label: "qwen2.5:32b",
+    hint: "32B, ~22 GB Ollama RAM. Middle-tier for 64 GB Studios. Solid Spanish, faster than 72B. Pull ~20 GB, 15\u201330 min."
+  },
+  {
+    value: "qwen3.5:9b",
+    label: "qwen3.5:9b",
+    hint: "9B, ~8 GB Ollama RAM. Validation / smaller Studios (36\u201348 GB). Pull ~5 GB, 3\u20135 min."
+  }
+];
+var OTHER_SENTINEL = "__OTHER__";
+function recommendLlmModel(ramGB) {
+  if (ramGB === null) return null;
+  if (ramGB >= 96) return "qwen2.5:72b";
+  if (ramGB >= 48) return "qwen2.5:32b";
+  return "qwen3.5:9b";
+}
+async function selectLlmModel(opts) {
+  if (opts.yes) return DEFAULT_LLM_MODEL;
+  const ramGB = await detectUnifiedMemoryGB();
+  const recommended = recommendLlmModel(ramGB) ?? "qwen2.5:72b";
+  const ramNote = ramGB !== null ? `Detected ${ramGB} GB unified memory \u2014 pre-selecting ${recommended}.` : `Couldn't detect Studio memory \u2014 defaulting to ${recommended} (override if your config differs).`;
+  p3.note(ramNote, "Hardware");
+  const choice = unwrap(
+    await p3.select({
+      message: "Choose the LLM model to pull + run",
+      initialValue: recommended,
+      options: [
+        ...LLM_MODEL_CHOICES.map((c) => ({ value: c.value, label: c.label, hint: c.hint })),
+        {
+          value: OTHER_SENTINEL,
+          label: "Other\u2026",
+          hint: "Specify any Ollama model name (e.g. mistral-small:24b)"
+        }
+      ]
+    })
+  );
+  if (choice !== OTHER_SENTINEL) return choice;
+  return unwrap(
+    await p3.text({
+      message: "Ollama model name",
+      placeholder: "e.g. mistral-small:24b",
+      validate: (v) => /^[A-Za-z0-9][A-Za-z0-9._:/-]*$/.test(v ?? "") ? void 0 : "Letters, digits, `.`, `:`, `_`, `-`, `/` only; must start with alphanumeric"
+    })
+  );
+}
+function estimatedPullTime(model) {
+  if (/\d+x\d+b/i.test(model)) return "~60+ min for frontier MoE";
+  const match = /(\d+)b\b/i.exec(model);
+  if (!match) return "time depends on model size";
+  const size = Number.parseInt(match[1], 10);
+  if (size <= 13) return "~3\u20135 min for \u2264 13B-class";
+  if (size <= 35) return "~15\u201330 min for ~32B-class";
+  if (size <= 80) return "~30\u201360 min for 70B-class";
+  return "~60+ min for frontier-class";
+}
 function kvBool(b) {
   return b ? pc2.green("on") : pc2.yellow("off");
 }
@@ -2163,7 +2243,7 @@ async function runReset(input, deps = DEFAULT_DEPS) {
     push({
       name: RESET_PHASES.STOP_STACK,
       status: "dry-run",
-      detail: `would run: docker compose -f ${input.stack.composeFiles.join(" -f ")} down${input.stack.wipeVolumes ? " -v" : ""}${input.stack.removeOrphans ? " --remove-orphans" : ""}`
+      detail: `would run: docker compose -f ${input.stack.composeFiles.join(" -f ")} down${input.stack.wipeVolumes ? " -v" : ""}${input.stack.removeOrphans ? " --remove-orphans" : ""}${input.stack.wipeImages ? " --rmi all" : ""}`
     });
   } else {
     const result2 = await deps.composeDown({
@@ -2171,13 +2251,18 @@ async function runReset(input, deps = DEFAULT_DEPS) {
       cwd: input.stack.repoPath,
       ...input.stack.envFile ? { envFile: input.stack.envFile } : {},
       wipeVolumes: input.stack.wipeVolumes,
-      removeOrphans: input.stack.removeOrphans
+      removeOrphans: input.stack.removeOrphans,
+      ...input.stack.wipeImages ? { removeImages: "all" } : {}
     });
     if (result2.ok) {
+      const bits = [
+        input.stack.wipeVolumes ? "volumes destroyed" : "containers stopped, volumes preserved",
+        input.stack.wipeImages ? "images removed (next bootstrap will re-pull)" : null
+      ].filter(Boolean);
       push({
         name: RESET_PHASES.STOP_STACK,
         status: "ok",
-        detail: input.stack.wipeVolumes ? "volumes destroyed" : "containers stopped, volumes preserved"
+        detail: bits.join("; ")
       });
     } else {
       push({ name: RESET_PHASES.STOP_STACK, status: "fail", detail: result2.reason ?? "unknown failure" });
@@ -2264,6 +2349,11 @@ var resetCommand = new Command("reset").description(
     "--wipe-data",
     "DESTROYS docker volumes (adds -v to `compose down`). Requires retyping the region label as confirmation. Default off \u2014 volumes preserved."
   ).default(false)
+).addOption(
+  new Option(
+    "--wipe-images",
+    'ALSO remove all docker images referenced by the compose file (adds --rmi all). Forces a fresh pull on next bootstrap. Implies --wipe-data semantics for the iteration loop ("wipe everything and start over"). Default off.'
+  ).default(false)
 ).addOption(
   new Option(
     "--no-remove-orphans",
@@ -2276,7 +2366,8 @@ var resetCommand = new Command("reset").description(
   ).default(false)
 ).addOption(new Option("--skip-docker-logout", "Don't run `docker logout`").default(false)).addOption(new Option("--registry <registry>", "Registry to log out of").default(GHCR_REGISTRY)).addOption(new Option("--dry-run", "Show what would happen without acting").default(false)).addOption(new Option("-y, --yes", "Skip non-destructive confirmations (wipe still confirms)").default(false)).action(async (opts) => {
   p3.intro(pc2.bgCyan(pc2.black(" create-op-node reset ")));
-  const wipeData = opts.wipeData ?? false;
+  const wipeImages = opts.wipeImages ?? false;
+  const wipeData = (opts.wipeData ?? false) || wipeImages;
   const removeOrphans = opts.removeOrphans ?? true;
   const region = opts.region ? opts.region : unwrap(
     await p3.text({
@@ -2342,6 +2433,7 @@ var resetCommand = new Command("reset").description(
       `pgsodium key file:     ${keyFileExists ? pc2.cyan(launchAgentPaths.keyFile) : pc2.dim("not present")}`,
       `Registry to log out:   ${pc2.cyan(opts.registry ?? GHCR_REGISTRY)}`,
       `Volume policy:         ${wipeData ? pc2.red("WIPE") : pc2.green("preserve (default)")}`,
+      `Image policy:          ${wipeImages ? pc2.red("WIPE (re-pull on next bootstrap)") : pc2.green("keep (default)")}`,
       `Dry run:               ${opts.dryRun ? pc2.yellow("yes") : pc2.dim("no")}`
     ].join("\n"),
     "Snapshot"
@@ -2369,6 +2461,7 @@ var resetCommand = new Command("reset").description(
     repoPath,
     composeFiles: resolveComposeFiles(repoPath, opts.composeFile),
     wipeVolumes: wipeData,
+    wipeImages,
     removeOrphans,
     ...opts.envFile ? { envFile: opts.envFile } : {}
   } : void 0;
@@ -3843,7 +3936,7 @@ async function looksLikeRegionsRepo(dir) {
 }
 
 // src/cli.ts
-var VERSION = "0.6.0";
+var VERSION = "0.8.0";
 var program = new Command();
 program.name("create-op-node").description(
   "Interactive bootstrap for an Opus Populi federation node.\nCloudflare infrastructure \u2192 Mac Studio \u2192 live public API."