@genex-ai/cli-demo 1.35.0 → 1.35.2-dev.749

package/dist/{blender-mcp-6TEAE65U.js → blender-mcp-HKT7N5BQ.js}

@@ -7,10 +7,10 @@ import {
   isRenderMode,
   sceneSummary,
   sheetOf
-} from "./chunk-5WBSWMH5.js";
+} from "./chunk-FYHYZYBC.js";
 import {
   getCliVersion
-} from "./chunk-QI7FIYBY.js";
+} from "./chunk-K4EHXOZK.js";
 
 // src/commands/blender-mcp.ts
 import fs from "fs/promises";

package/dist/{blender-serve-66OHC4ML.js → blender-serve-EH2MOW3U.js}

@@ -1,7 +1,7 @@
 import {
   c,
   getTemplatesDir
-} from "./chunk-QI7FIYBY.js";
+} from "./chunk-K4EHXOZK.js";
 
 // src/lib/blender-serve.ts
 import { spawn } from "child_process";

package/dist/{chunk-5WBSWMH5.js → chunk-FYHYZYBC.js}

@@ -10,7 +10,7 @@ import {
   getGenexEnvPath,
   normalizeApiOrigin,
   originKey
-} from "./chunk-QI7FIYBY.js";
+} from "./chunk-K4EHXOZK.js";
 
 // src/lib/terms.ts
 import readline from "readline";

package/dist/{chunk-QI7FIYBY.js → chunk-K4EHXOZK.js}

@@ -38,7 +38,7 @@ import fs from "fs";
 import os from "os";
 import path from "path";
 import { fileURLToPath } from "url";
-var RAW_CHANNEL = "latest";
+var RAW_CHANNEL = "dev";
 var CLI_CHANNEL = RAW_CHANNEL === "dev" ? "dev" : "latest";
 var STANDS = {
   prod: { api: "https://api.genex.games", dashboard: "https://genex.games" },

package/dist/index.js

@@ -42,7 +42,7 @@ import {
   writeSecretFile,
   writeUserToken,
   writeWorkspace
-} from "./chunk-5WBSWMH5.js";
+} from "./chunk-FYHYZYBC.js";
 import {
   CLI_CHANNEL,
   DEFAULT_API_URL,
@@ -63,7 +63,7 @@ import {
   normalizeApiOrigin,
   originKey,
   resolveAgentTargets
-} from "./chunk-QI7FIYBY.js";
+} from "./chunk-K4EHXOZK.js";
 
 // src/instrument.ts
 import * as Sentry from "@sentry/node";
@@ -22772,7 +22772,7 @@ async function runBlender(opts) {
     return 1;
   }
   if (sub === "serve") {
-    const { serveLocalBlender } = await import("./blender-serve-66OHC4ML.js");
+    const { serveLocalBlender } = await import("./blender-serve-EH2MOW3U.js");
     const port = Number(process.env.GENEX_BLENDER_PORT ?? 8088);
     log.step(`Starting a local Blender service on port ${port}`);
     log.plain(
@@ -22781,7 +22781,7 @@ async function runBlender(opts) {
     return serveLocalBlender({ port, log });
   }
   if (sub === "mcp") {
-    const { runBlenderMcp } = await import("./blender-mcp-6TEAE65U.js");
+    const { runBlenderMcp } = await import("./blender-mcp-HKT7N5BQ.js");
     return runBlenderMcp();
   }
   if (sub === "seat") {
@@ -23564,8 +23564,9 @@ async function reportModels(apiUrl, token, opts, log, toolsOnly = false) {
   );
   for (const m of shown) {
     const plan = m.personalPlan ? `  \xB7  personal plan: ${m.personalPlan}` : "";
+    const kind = m.kind === "typesafe" ? "  \xB7  judge (classifier): judge() under a budget, not generate() or bench" : "";
     log.plain(
-      `    ${c.cyan(m.id)}  ${m.label} \u2014 ${usdPerMillion(m.inputUsdPerMillion)} in / ${usdPerMillion(m.outputUsdPerMillion)} out per million tokens${plan}`
+      `    ${c.cyan(m.id)}  ${m.label} \u2014 ${usdPerMillion(m.inputUsdPerMillion)} in / ${usdPerMillion(m.outputUsdPerMillion)} out per million tokens${plan}${kind}`
     );
   }
   if (hiddenCount > 0) {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@genex-ai/cli-demo",
-  "version": "1.35.0",
+  "version": "1.35.2-dev.749",
   "description": "Set up your project's agent workspace (.claude/.codex/.cursor in the game folder), authorize, create a game project, generate AI assets, and publish (genex CLI).",
   "type": "module",
   "bin": {

package/templates/skills/genex-getting-started/SKILL.md

@@ -161,7 +161,7 @@ downloads the game too, binary assets and all:
 
 ```bash
 mkdir my-game && cd my-game
-npx @genex-ai/cli-demo@latest link <slug>   # slug = the name in the play URL
+npx @genex-ai/cli-demo@dev link <slug>   # slug = the name in the play URL
 npm install
 ```
 
@@ -225,7 +225,7 @@ Safe to run any time — genex-owned skills are refreshed to the latest version,
 and your own files are never touched:
 
 ```bash
-npx @genex-ai/cli-demo@latest init
+npx @genex-ai/cli-demo@dev init
 ```
 
 Use `--force` only if you intentionally want your own existing files overwritten

package/templates/skills/genex-llm-in-games/SKILL.md

@@ -25,6 +25,23 @@ Two modes. Picking the wrong one is the most expensive mistake on this lane:
 A popup per NPC turn is not a feature, it is an interruption. More than a call
 or two per session means a grant.
 
+**Deciding, not writing? Use the judge.** When the game needs to KNOW something
+— is this NPC lying, which of five moods is the player in, how threatening is
+the scene on a scale — and not to produce words, ask the grant's classifier with
+`judge()` instead of asking `generate()` for a label. It answers typed questions
+(`choice`, `score`, `noul`) with calibrated probabilities in about a third of a
+second, writes no prose and cannot drift out of your options. It is grant-only
+and billed as used: each call is a small fraction of a coin and accrues on the
+budget, so a check every turn is affordable where a generate every turn is not.
+`generate()` for words, `judge()` for decisions; a feature often wants both —
+the judge picks the branch, generate writes the line.
+
+**Words the player watches appear? Stream them.** Dialogue, narration, an NPC's
+reply in a speech bubble: under a grant, `generateStream()` is the same call as
+`generate({ grantId })`, but the text arrives while the model writes it instead
+of all at once after it. Keep `generate()` for answers the game only uses whole
+(a quest object, a list of decisions) — nobody watches those being written.
+
 ## Step 0 — is the lane live on this stand?
 
 ```bash
@@ -67,9 +84,24 @@ identity must be resolved first — `$genex-threejs-embed-auth`.
   (`billingStatus`, `reservedCoins`, `chargedCoins`, their display-USD twins).
 - `requestSpendGrant({ models, perCallMaxCoins, perCallEstimateCoins,
   disclosure: { periodLabel, estimatedCallsPerPeriod, estimatedCoinsPerPeriod },
-  maxConcurrent?, maxCallsPerMinute?, allowExternal?, idempotencyKey? })` →
+  maxConcurrent?, maxCallsPerMinute?, allowExternal?, judge?: { enabled,
+  estimatedCallsPerPeriod }, idempotencyKey? })` →
   `{ status, grantId, … the limits the player approved }`; status is `active` |
   `canceled` | `expired` | `failed` | `pending`.
+- `judge({ grantId, state, questions, idempotencyKey?, timeoutMs? })` →
+  `{ status, generationId, answers, error, billing }` — the grant's classifier,
+  answered in the same response. `questions` is 1–64 named `choice`
+  (`{ instructions, criteria: { option: description } }`), `score`
+  (`{ instructions, criteria: [levels, lowest first] }`) or `noul`
+  (`{ instructions }`); each answer has its question's type, and `noul` is a
+  probability — pick your own threshold. Needs a budget requested with `judge`.
+- `generateStream({ …the generate() options, grantId, onDelta?(text, soFar),
+  onPartialField?(name, partialText), signal? })` → the same result as
+  `generate()`. Grant-only. `onDelta` hands over each piece and all the text so
+  far; for `outputFormat: 'json'`, `onPartialField` reports the schema's FIRST
+  top-level string property as far as it is written — put the spoken line first
+  in the schema. `signal` stops the reading, never the call (it still finishes
+  and is charged).
 - `getSpendGrant(grantId)` — live state and counters; the ONE source for an
   in-game budget readout.
 - `stopSpendGrant(grantId)` — the game's own stop door. Prospective: no further
@@ -188,6 +220,36 @@ arithmetic into `DESIGN.md` beside the feature. The player sees your estimate
 attributed to the game, beside the platform's own worst case; an estimate that
 is transparently low is a grant that dies mid-session.
 
+**Using the judge too?** Add `judge: { enabled: true, estimatedCallsPerPeriod }`
+to the same request — the checks you really expect per `periodLabel`, from the
+same loop arithmetic. The sheet tells the player the game also uses a fast
+classifier billed as used, with the platform's own worst case beside your count.
+A judge-only feature passes `models: []`. A budget with the judge is coin-funded
+only, and judge calls share the budget's `maxConcurrent` and
+`maxCallsPerMinute`: batch questions into one call (up to 64) rather than one
+call per question.
+
+**Streaming a reply under the budget:**
+
+```ts
+const res = await generateStream({
+  grantId, modelId, outputFormat: 'json', schema: LINE_SCHEMA,   // `line` is its first property
+  prompt: npcPrompt(npc, playerLine), estimateCoins: NPC_CALL_PRICE,
+  idempotencyKey: `npc:${npc.id}:${turnId}`,
+  onPartialField: (_name, soFar) => npc.bubble.show(soFar),     // provisional
+});
+applyGeneration(res);                                            // the answer is THIS
+```
+
+The pieces are provisional: a call can still fail after text has shown (the
+model broke off, the JSON missed the schema), so the bubble shows them and
+`applyGeneration` decides what the game keeps — the same one writer as always.
+Price, benchmark and receipt are `generate()`'s: a started stream is charged its
+declared price even when the player walks away mid-sentence. A stream holds one
+of the budget's `maxConcurrent` slots until it has settled. Sometimes the reply
+arrives whole — a busy stand, a retried call, a budget on the player's own plan —
+and `onDelta` then gets the whole text once; the game needs no second path.
+
 **Then keep the burn low, because you wrote the loop:** batch those five NPCs
 into ONE call returning five decisions, cache a decision until the situation
 that caused it changes, pick the cheapest model that passes your own check, and
@@ -285,6 +347,8 @@ These are source contracts, not a claim that every stand runs this lane —
 - [ ] A bench refused as `generation_limit` was answered with `npx genex llm status`, never a retry
 - [ ] `generate()` / `requestSpendGrant()` is the first statement of a click handler
 - [ ] A repeated-call feature uses a grant; a one-off uses `generate()`
+- [ ] A decision (a label, a yes/no, a level) is a `judge()` question under the grant, not a `generate()` asked for a word
+- [ ] Dialogue the player watches appear uses `generateStream()` under the grant; the resolved result, not the pieces, goes to `applyGeneration()`
 - [ ] Disclosure numbers derive from the real loop and are written in `DESIGN.md`
 - [ ] Calls are batched and cached; nothing fires on an invisible timer
 - [ ] Every grant-ending code has in-fiction copy and a playable fallback
@@ -316,6 +380,19 @@ cause rather than showing it for both.
 **`grant_price_unreasonable`** — the declared per-call price is far above what
 that prompt can cost on that model. Re-benchmark and declare what it prints.
 
+**`judge_not_enabled`** — the budget was approved without the judge. Request a
+new one with `judge` from the next deliberate click; never auto-renew.
+**`judge_requires_grant`** — the judge's model was sent to `generate()` with no
+budget; the judge is grant-only and is called with `judge()`.
+**`judge_period_limit`** — the checks reached the ceiling the player approved for
+the period (your own `estimatedCallsPerPeriod` at the largest size): wait, and
+if it keeps happening your declared rate is too low — fix the loop or the
+estimate, never retry in a tight loop.
+
+**`stream_requires_grant`** — `generateStream()` was called without a
+`grantId`. Streaming is grant-only: a one-time call waits on the player's
+approval popup, so use `generate()` for it.
+
 **`generation_limit`** — three ad-hoc calls are already in flight for this
 account, or recently stopped with their bill still pending; a pending call
 stops counting ten minutes after it was dispatched. From the bench: run

package/templates/skills/genex-updates/SKILL.md

@@ -38,7 +38,7 @@ update, so update immediately.)
 Run exactly the command the nudge printed, from the game project root:
 
 ```bash
-npm i -D @genex-ai/cli-demo@latest   # the genex CLI (a dev dependency)
+npm i -D @genex-ai/cli-demo@dev   # the genex CLI (a dev dependency)
 npm i @genex-ai/embed-sdk@latest     # identity/saves SDK (ships inside the game)
 npm i @genex-ai/multiplayer@latest   # multiplayer SDK (only if the game uses it)
 ```