@tiens.nguyen/gu-cli 1.0.882 → 1.0.884

package/README.md

@@ -1,8 +1,9 @@
-<h1 align="center">gu — the coding agent in your terminal</h1>
+<h1 align="center">gu — the coding agent for your own models</h1>
 
 <p align="center">
-  <strong>It reads your repo, makes the change, and proves it works.</strong><br>
-  Your models — Ollama, MLX or any OpenAI-compatible provider. Your files stay in your folder.
+  <strong>A coding agent in your terminal that runs on Ollama, MLX or any OpenAI-compatible API.</strong><br>
+  It reads your repo, makes the change, runs the tests and shows you what it did. Your code stays in your folder.<br>
+  <strong>Free for 30 days. No account, no sign-in, no card.</strong>
 </p>
 
 <p align="center">
@@ -15,7 +16,7 @@
 
 <p align="center">
   <a href="https://gucli.com">Website</a> ·
-  <a href="https://gucli.com/docs">Docs</a> ·
+  <a href="https://gucli.com/start">Docs</a> ·
   <a href="https://gucli.com/pricing">Pricing</a> ·
   <a href="https://gucli.com/support">Support</a>
 </p>
@@ -35,33 +36,47 @@ cd your-project
 gu
 ```
 
-The first run asks a few questions: how this machine runs, which model provider to use, and your
-gu token (a free trial is offered). After that, type what you want done.
+**Free to start, no account needed.** The first run creates a free 30-day token for this
+computer automatically. Press Enter to use it. It also asks how this machine runs and which model
+provider to use. Then type what you want done.
 
 > **`gu: command not found`?** Run `npx @tiens.nguyen/gu-cli fix-path`. See [Troubleshooting](#troubleshooting).
 
-## What it does
-
-- **Writes the code, in your terminal.** Ask in plain words; gu reads the repo, edits the files,
-  runs the build and the tests, and tells you what it changed.
-- **Your models.** Run [Ollama](https://ollama.com) or MLX on your own machine, or bring any
-  OpenAI-compatible provider. Switch at any time with `/model`.
-- **It stays in the repo.** Every edit is a file you can read, diff and revert, and `/undo` puts
-  back what a stopped turn changed. No hidden workspace.
-- **Knows your codebase.** Local RAG indexes the folder so the model finds the right files.
-- **Extensible.** [MCP](https://modelcontextprotocol.io) servers, skills (`SKILL.md`), and hooks.
-  Already set up for Claude Code? `/switch-skill claude` reuses its `.claude` folder.
-- **Tests in a real browser.** The `browser` tool drives Chrome to check the web pages it builds.
-- **Private by default.** Logs hold no prompts, code or keys unless you run `gu --log`.
+## Why gu
+
+- **Your models, your choice.** Run [Ollama](https://ollama.com) or MLX on your own machine or a GPU
+  box on your network, or bring any OpenAI-compatible provider (OpenAI, DeepSeek, OpenRouter…). Use
+  one model to plan and another to code; switch any time with `/model`.
+- **Private by default.** Logs hold no prompts, code or keys unless you run `gu --log`. Need
+  everything in-house? Private mode runs the API and database on your own servers.
+- **It proves it works.** gu runs the build and the tests and fixes what fails. For web pages, the
+  `browser` tool drives a real Chrome and checks the result before gu says it is done.
+- **It stays in the repo.** Every edit is a file you can read, diff and revert; `/undo` puts back
+  what a stopped turn changed. No hidden workspace.
+- **Made for servers and SSH.** macOS, Linux and Windows, and it works over SSH in an 80-column
+  terminal, so you can run it where the code actually lives.
+- **Fits the setup you have.** [MCP](https://modelcontextprotocol.io) servers, skills (`SKILL.md`)
+  and hooks. Already use Claude Code? `/switch-skill claude` reuses its `.claude` folder. Local RAG
+  indexes the folder so the model finds the right files.
+
+## Is gu for you?
+
+**A good fit if** you run (or want to run) your own models, can't send code to someone else's
+cloud, work on remote Linux boxes over SSH, or want a coding agent that costs $4 a month instead
+of a model subscription.
+
+**Probably not if** you want the strongest frontier model with zero setup and don't mind where your
+code goes: the model vendors' own agents are simpler for that. gu can still use those models
+through an OpenAI-compatible API, but its strength is everything else.
 
 ## Quick start
 
-1. **Sign in.** `gu login` opens the browser. On a private machine, paste a token from your
-   [account page](https://gucli.com/account) with `gu-cli token <token>` instead.
+1. **Start gu.** Run `gu` in a project folder. Your free 30-day token is created on the spot:
+   no sign-up, no browser, no card.
 2. **Check your models.** `gu doctor` sets up and tests the models on this machine.
    (`gu doctor --client` installs only the agent's dependencies, when the models run elsewhere.)
-3. **Ask.** Run `gu` in a project folder. Conversations are saved per folder and resumed next
-   time; `/new` starts a fresh one.
+3. **Ask.** Type what you want done. Conversations are saved per folder and resumed next time;
+   `/new` starts a fresh one.
 
 ## Models
 
@@ -119,6 +134,7 @@ Ctrl-C stops the running turn. Type `/` at the prompt to see every command; Tab
 | `/save-settings`, `/load-settings` | move providers, models and key *names* (no secrets) to another machine |
 | `/save-preset`, `/open-presets`, `/use-presets` | your whole setup, keys included, to copy, edit and apply (backs up first) |
 | `/clear-logs` | show what logs, RAG indexes and old API versions take on disk, then ask what to clear |
+| `/voucher CODE` | use a voucher code: adds free days to this computer's trial or your free account |
 | `/support` | send the support team a request with gu's logs attached (secrets masked; shows what goes first) |
 | `/help`, `/exit` | list commands / quit |
 
@@ -161,8 +177,17 @@ gu fix-path | fix-powershell   repair PATH / remove PowerShell's `gu` alias
 
 ## Plans
 
-Every new computer gets a **free trial**. After it, the **Free** plan covers 1 device and **Pro**
-covers more, plus provider budgets. Current prices: [gucli.com/pricing](https://gucli.com/pricing).
+| | How long | What you need |
+| --- | --- | --- |
+| **Free trial** | 30 days, starts on the first run | nothing: the token is created for you |
+| **Free plan** | 3 more months on that computer | a free account at [gucli.com](https://gucli.com) |
+| **Pro** | while subscribed: **$4 a month** (110.000 ₫) + VAT, or $40 a year | the hosted agent and coder (no model server to run), up to 5 computers, provider budgets |
+
+Got a **voucher code**? Type `/voucher CODE` in gu (or enter it on your
+[account page](https://gucli.com/account)) for extra free days on top.
+
+Free time belongs to the computer: reinstalling doesn't restart it. Already have a token? Paste
+it at the first-run question instead, or later with `gu-cli token <token>`. Current prices: [gucli.com/pricing](https://gucli.com/pricing).
 
 ## Troubleshooting
 

package/cli-token.mjs

@@ -533,6 +533,35 @@ export async function renewToken({ mode, apiBase, hostedBase, token, workerKey,
   }
 }
 
+/**
+ * /voucher CODE (#425): redeem a marketing code with this computer's token as the credential — a
+ * trial (no account) or an account. Returns { ok: true, days, token } — the token already carries the
+ * extra days — or { ok: false, why, error } where error is the service's own sentence. Never throws.
+ */
+export async function redeemVoucher({ mode, apiBase, hostedBase, token, device, code, fetchImpl = fetch, timeoutMs = 8000 }) {
+  const base = String(mode === "expert" ? hostedBase : apiBase || hostedBase).replace(/\/+$/, "");
+  if (!token) return { ok: false, why: "no-token", error: "This computer has no gu token yet — restart gu to get the free trial, then try again." };
+  if (!base) return { ok: false, why: "no-api", error: "No gu service address is set on this computer." };
+  try {
+    const res = await fetchImpl(`${base}/api/billing/cli-token/voucher`, {
+      method: "POST",
+      headers: { "content-type": "application/json", authorization: `Bearer ${token}` },
+      body: JSON.stringify({ code: String(code ?? ""), ...(device ? { device } : {}) }),
+      signal: AbortSignal.timeout(timeoutMs),
+    });
+    const data = await res.json().catch(() => null);
+    if (!res.ok) {
+      const error = typeof data?.error === "string" && data.error
+        ? data.error
+        : res.status === 404 ? "This gu service does not take vouchers yet." : `The gu service answered HTTP ${res.status}.`;
+      return { ok: false, why: typeof data?.why === "string" ? data.why : `http-${res.status}`, error };
+    }
+    return { ok: true, days: Number(data?.days ?? 0), token: typeof data?.token === "string" ? data.token : "" };
+  } catch (e) {
+    return { ok: false, why: "network", error: e?.name === "TimeoutError" ? "The gu service did not answer in time. Try again." : "Can't reach the gu service right now." };
+  }
+}
+
 // ---------------------------------------------------------------------------
 // WHAT THE BAR SAYS
 // ---------------------------------------------------------------------------

package/gu-repl.mjs

@@ -1041,6 +1041,7 @@ const COMMANDS = [
   { name: "/shells", desc: "long commands the agent left running in the background — status, runtime, command, output; stop one" },
   { name: "/budget", desc: "short view of your API provider budgets and balances (Pro) — the same items as the web /providers page" },
   { name: "/tokens", desc: "break down the last prompt sent to the coding model — how much of it was RAG" },
+  { name: "/voucher", usage: "/voucher CODE", desc: "use a voucher code — it adds free days to this computer's trial or your free account" },
   { name: "/support", desc: "send the gu support team a request with gu's logs attached (secrets masked) — shows what goes first, then asks" },
   { name: "/clear-logs", desc: "show what gu's logs, RAG indexes and old API versions take on disk, then ask what to clear — the logs first" },
   { name: "/prices", usage: "/prices [update]", desc: "the price table and the cache table, and what the last turn and this session cost — \"update\" applies gu's newest published tables" },
@@ -8397,6 +8398,54 @@ async function noteTurnCost(inputTokens, breakdown, coder = null) {
  * use marked; what the last turn and this session cost; and, when gu has published newer tables,
  * that they are waiting. `/prices update` applies them — the same as clicking the notice.
  */
+/**
+ * /voucher CODE (#425) — a marketing code that adds free days. Works on the free trial (no account)
+ * and on a free account; the service answers with a fresh token that already carries the days, so
+ * the bar and the licence see them at once — no restart.
+ */
+async function runVoucherCommand(line = "/voucher") {
+  const code = line.trim().slice("/voucher".length).trim();
+  console.log("");
+  if (!code) {
+    console.log(GUTTER + "Type the code after the command: " + accent("/voucher CODE") + "\n");
+    return;
+  }
+  const ct = await import("./cli-token.mjs");
+  const pk = ct.publicKey();
+  const dir = join(homedir(), ".gonext");
+  const state = await ct.readState(dir);
+  const { DEFAULT_API_BASE } = await import("./device-login.mjs");
+  const device = await ct.thisDevice({ instanceId: myInstanceId || "" }).catch(() => null);
+  const r = await withPendingStatus("checking the voucher", () =>
+    ct.redeemVoucher({
+      mode: isClientExpert() ? "expert" : "client",
+      apiBase,
+      hostedBase: String(process.env.GU_TOKEN_API_BASE ?? "").trim() || DEFAULT_API_BASE,
+      token: state.token,
+      device,
+      code,
+    })
+  );
+  if (!r.ok) {
+    console.log(GUTTER + yellow(r.error) + "\n");
+    return;
+  }
+  // Kept only if it checks out here, like every renewal.
+  const check = r.token && pk ? ct.verifyCliToken(r.token, pk) : { ok: false };
+  if (check.ok) {
+    await ct.writeState(dir, { token: r.token, lastAttemptAt: new Date().toISOString() }).catch(() => {});
+    const d = ct.enforcementDecision({ token: r.token, publicKeyB64: pk, site: ct.siteUrl(), deviceId: await thisDeviceId(ct) });
+    licenceBlock = d.enforced && !d.allowed ? d.why : null;
+    tokenNotice = ct.barNotice({ token: r.token, publicKeyB64: pk, mode: isClientExpert() ? "expert" : "client", now: new Date(), attempted: true, site: ct.siteUrl() });
+  }
+  const p = check.ok ? check.payload : null;
+  const until = p?.plan === "trial" ? p.paidUntil : p?.plan === "free" && typeof p.freeUntil === "string" ? p.freeUntil : null;
+  console.log(GUTTER + accent(`✓ +${r.days} free days added.`) + (until ? ` Free on this computer until ${ct.shortDate(until)}.` : ""));
+  if (!check.ok) console.log(GUTTER + dim("gu picks the days up at its next token refresh (within the hour)."));
+  console.log("");
+  if (barPinned()) paintBar();
+}
+
 async function runPricesCommand(line = "/prices") {
   const mp = await import("./model-prices.mjs");
   console.log("");
@@ -14061,7 +14110,10 @@ async function main() {
       if (isClientExpert()) {
         try {
           const ceApi = await import("./client-expert-api.mjs");
-          apiBannerVersion = String((await ceApi.probeLocalApi()).body?.version ?? "").trim();
+          // The API this gu is configured for, on ITS port — not the default port, which another
+          // API (or none) may hold (#254: the banner differed between two machines).
+          const port = Number(new URL(apiBase).port) || undefined;
+          apiBannerVersion = String((await ceApi.probeLocalApi(port)).body?.version ?? "").trim();
         } catch { /* absent beats guessed — no suffix */ }
       }
       const statusRows = [
@@ -15080,6 +15132,10 @@ async function main() {
       await runPricesCommand(line);
       continue;
     }
+    if (line === "/voucher" || line.startsWith("/voucher ")) {
+      await runVoucherCommand(line);
+      continue;
+    }
     if (line === "/clear-logs") {
       await runClearLogs();
       continue;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tiens.nguyen/gu-cli",
-  "version": "1.0.882",
+  "version": "1.0.884",
   "description": "gu: the coding agent in your terminal. It reads your repo, makes the change and runs the tests, with your own models (Ollama, MLX or any OpenAI-compatible provider). macOS, Linux and Windows.",
   "keywords": [
     "ai",