create-op-node 0.6.0 → 0.7.0

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:
@@ -527,6 +541,17 @@ 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

@@ -1690,7 +1690,11 @@ var bootstrapCommand = new Command("bootstrap").description(
   const repoName = `opuspopuli-node-${region}`;
   const composeFileDefault = opts.localOnly ? ["docker-compose-prod.yml"] : ["docker-compose-prod.yml", "docker-compose-backup.yml"];
   const composeFile = opts.composeFile ?? composeFileDefault;
-  const [embeddingModel, llmModel] = resolveModels(opts);
+  const llmModelChoice = opts.llmModel ?? await selectLlmModel(opts);
+  const [embeddingModel, llmModel] = resolveModels({
+    llmModel: llmModelChoice,
+    ...opts.embeddingModel !== void 0 ? { embeddingModel: opts.embeddingModel } : {}
+  });
   const sysSpin = p3.spinner();
   sysSpin.start("Inspecting macOS\u2026");
   const snap = await inspectSystem();
@@ -1751,7 +1755,7 @@ var bootstrapCommand = new Command("bootstrap").description(
       unwrap(await p3.confirm({ message: "Homebrew installed?", initialValue: true }));
     }
     const brewSpin = p3.spinner();
-    brewSpin.start("Installing Studio packages\u2026");
+    brewSpin.start("Installing Studio packages\u2026 (~5\u201315 min first run)");
     const report = await installPackages(STUDIO_PACKAGES, (pkg, status) => {
       brewSpin.message(`${status}: ${pkg.name}`);
     });
@@ -1852,7 +1856,7 @@ var bootstrapCommand = new Command("bootstrap").description(
   ghcrSpin.stop(pc2.green("\u2713 Logged in to ghcr.io."));
   if (!opts.skipOllama) {
     const olSpin = p3.spinner();
-    olSpin.start("Pulling + warming Ollama models\u2026");
+    olSpin.start(`Pulling + warming Ollama models\u2026 (${estimatedPullTime(llmModel)})`);
     let olHealth = await checkOllamaHealth();
     if (!olHealth.reachable) {
       olSpin.message("Ollama not reachable \u2014 running `brew services start ollama`\u2026");
@@ -1917,7 +1921,7 @@ 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 +1939,7 @@ 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 +2005,59 @@ 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__";
+async function selectLlmModel(opts) {
+  if (opts.yes) return DEFAULT_LLM_MODEL;
+  const choice = unwrap(
+    await p3.select({
+      message: "Choose the LLM model to pull + run",
+      initialValue: "qwen2.5:72b",
+      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");
 }
@@ -3843,7 +3900,7 @@ async function looksLikeRegionsRepo(dir) {
 }
 
 // src/cli.ts
-var VERSION = "0.6.0";
+var VERSION = "0.7.0";
 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."