@genex-ai/cli-demo 1.35.0-dev.741 → 1.35.0-dev.742

package/dist/index.js

@@ -23304,7 +23304,9 @@ async function readRuntimeLane(apiUrl, token) {
     state,
     models: null,
     recommendedDeclaredHeadroomBps: null,
-    externalProviders: null
+    externalProviders: null,
+    total: null,
+    featuredCount: null
   });
   try {
     const res = await apiFetch(`${apiUrl}/api/runtime/models`, {
@@ -23320,7 +23322,9 @@ async function readRuntimeLane(apiUrl, token) {
       state: "live",
       models: body.models,
       recommendedDeclaredHeadroomBps: typeof body.recommendedDeclaredHeadroomBps === "number" && Number.isFinite(body.recommendedDeclaredHeadroomBps) ? body.recommendedDeclaredHeadroomBps : null,
-      externalProviders: Array.isArray(body.externalProviders) ? body.externalProviders : null
+      externalProviders: Array.isArray(body.externalProviders) ? body.externalProviders : null,
+      total: typeof body.total === "number" && Number.isFinite(body.total) ? body.total : null,
+      featuredCount: typeof body.featuredCount === "number" && Number.isFinite(body.featuredCount) ? body.featuredCount : null
     };
   } catch {
     return empty("unknown");
@@ -23457,6 +23461,8 @@ async function reportModels(apiUrl, token, opts, log, toolsOnly = false) {
         models: null,
         externalProviders: null,
         recommendedDeclaredHeadroomBps: null,
+        total: null,
+        featuredCount: null,
         convertHint: toolsOnly ? LLM_TOOLS_CONVERT_HINT.join(" ") : null
       });
     }
@@ -23470,9 +23476,14 @@ async function reportModels(apiUrl, token, opts, log, toolsOnly = false) {
       status: lane.state,
       error: null,
       enabled: lane.state === "live",
+      // --json ALWAYS carries every row with its `featured` flag. The short
+      // list is a rendering decision for a person reading a terminal; a program
+      // reading this object gets the whole catalog and decides for itself.
       models: lane.models,
       externalProviders: lane.externalProviders,
       recommendedDeclaredHeadroomBps: lane.recommendedDeclaredHeadroomBps,
+      total: lane.total ?? lane.models?.length ?? null,
+      featuredCount: lane.featuredCount ?? (lane.models ? lane.models.filter((m) => m.featured).length : null),
       // Always present, `null` off a tools workspace — the same
       // every-key-always-present rule the other keys follow, so a reader can
       // tell "no hint" from "a CLI that predates the hint".
@@ -23507,12 +23518,21 @@ async function reportModels(apiUrl, token, opts, log, toolsOnly = false) {
     process.exitCode = 1;
     return;
   }
-  log.plain(`  ${lane.models.length} model${lane.models.length === 1 ? "" : "s"} live:`);
-  for (const m of lane.models) {
+  const featured = lane.models.filter((m) => m.featured);
+  const shown = opts.all || featured.length === 0 ? lane.models : featured;
+  const hiddenCount = lane.models.length - shown.length;
+  log.plain(
+    shown === lane.models ? `  ${lane.models.length} model${lane.models.length === 1 ? "" : "s"} live:` : `  ${shown.length} featured model${shown.length === 1 ? "" : "s"} of ${lane.models.length} live:`
+  );
+  for (const m of shown) {
+    const plan = m.personalPlan ? `  \xB7  personal plan: ${m.personalPlan}` : "";
     log.plain(
-      `    ${c.cyan(m.id)}  ${m.label} \u2014 ${usdPerMillion(m.inputUsdPerMillion)} in / ${usdPerMillion(m.outputUsdPerMillion)} out per million tokens`
+      `    ${c.cyan(m.id)}  ${m.label} \u2014 ${usdPerMillion(m.inputUsdPerMillion)} in / ${usdPerMillion(m.outputUsdPerMillion)} out per million tokens${plan}`
     );
   }
+  if (hiddenCount > 0) {
+    log.dim(`  ${hiddenCount} more available \u2014 ${c.cyan("genex llm models --all")} to list them.`);
+  }
   if (lane.externalProviders && lane.externalProviders.length > 0) {
     log.plain("");
     log.plain(`  Personal plans offered here: ${lane.externalProviders.map((p) => p.label).join(", ")}`);
@@ -26520,6 +26540,7 @@ ${c.bold("Examples")}
   genex shop test sku_123
   genex shop remove sku_123
   genex llm models
+  genex llm models --all
   genex llm bench "Reply with one short taunt." --samples 5 --max-coins 20 --user-approved
   genex llm price
   genex player install
@@ -26758,11 +26779,13 @@ ${c.bold("How the allowance works")}
   llm: `${c.bold("genex llm")} \u2014 in-game model calls: is the lane live, what does one call cost, what should the game declare?
 
 ${c.bold("Usage")}
-  genex llm models [--json]          Which models this stand serves, their provider rates per
+  genex llm models [--all] [--json]  Which models this stand serves, their provider rates per
                                      million tokens, and the headroom it recommends over a
-                                     benchmark. Off on this stand: it says so and exits 0 \u2014
-                                     build the feature without a model rather than promising
-                                     a 404.
+                                     benchmark. The catalog is synced from OpenRouter, so the
+                                     FEATURED short list is printed by default and --all
+                                     prints every row (--json always carries every row). Off
+                                     on this stand: it says so and exits 0 \u2014 build the feature
+                                     without a model rather than promising a 404.
   genex llm bench "<prompt>" --max-coins <n> --user-approved [options]
                                      Run the real model <n> times through the development
                                      lane and report what each attempt was CHARGED. Refused

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@genex-ai/cli-demo",
-  "version": "1.35.0-dev.741",
+  "version": "1.35.0-dev.742",
   "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-llm-in-games/SKILL.md

@@ -31,24 +31,36 @@ or two per session means a grant.
 npx genex llm models
 ```
 
-- **live** — it prints the models this stand serves. Build the feature.
+- **live** — it prints the FEATURED models this stand serves, and how many more
+  there are. Build the feature.
 - **off on this stand** — the routes answer 404. Build the feature behind a
   graceful `unavailable` state (the NPC uses its authored lines, the quest falls
   back to the written one) and **say so plainly in the handoff**. Never promise
   the player something that 404s.
 - **misconfigured** — say that too; it is an operator fix, not a game bug.
 
+The stand's catalog is synced and filtered, so it can hold far more rows than
+anyone wants to read. **Offer the featured set. Run `npx genex llm models --all`
+only when the user asks for more**, and put the full list in front of them
+rather than picking an obscure row for them.
+
 Model ids come from that command and from `getGenerationModels()` at runtime.
 Never write one into the game's source: they differ per stand, and a hardcoded
-id is a feature that dies on somebody else's environment.
+id is a feature that dies on somebody else's environment. **A picker's label
+must be the model's own `label`** — a name you invent for a row ("Fast", "Smart")
+is a label that differs from the model the player is billed for.
 
 ## The SDK surface (exact — do not invent methods)
 
 From `@genex-ai/embed-sdk`, already installed. `initEmbed()` must have run and
 identity must be resolved first — `$genex-threejs-embed-auth`.
 
-- `getGenerationModels()` — the models this stand serves. Any picker renders
-  from this, never from a list you wrote.
+- `getGenerationModels()` — `{ models, featuredCount, … }`, featured first. Any
+  picker renders from this, never from a list you wrote: show the rows where
+  `featured` is true (or all of them when `featuredCount` is 0) and offer the
+  rest only if the player asks. Each row carries `label`, `vendor`,
+  `contextLength`, `personalPlan` and `structuredOutputs`; render `label`
+  verbatim, so the name on screen is the model that gets billed.
 - `generate({ modelId, prompt, outputFormat, schema?, estimateCoins,
   allowExternal?, idempotencyKey?, grantId?, timeoutMs? })` →
   `{ status, generationId, output, source, error }` plus billing fields
@@ -222,6 +234,7 @@ These are source contracts, not a claim that every stand runs this lane —
 
 - [ ] `npx genex llm models` was run and its verdict is in the handoff
 - [ ] Model ids come from `getGenerationModels()`, never from source
+- [ ] The picker offers the featured set, labelled with the server's own `label`
 - [ ] `estimateCoins` came from `npx genex llm bench`, not from judgement
 - [ ] `generate()` / `requestSpendGrant()` is the first statement of a click handler
 - [ ] A repeated-call feature uses a grant; a one-off uses `generate()`

package/templates/skills/genex-tool-llm/SKILL.md

@@ -53,7 +53,11 @@ expand the offer into a pitch — one line, one question.
    which models. It answers in this folder as it is, before anything is
    converted, so it comes first: if it says the lane is off, in-game calls
    answer 404 here — tell the user so plainly, build the graceful fallback, and
-   do not convert a folder for a feature the stand does not serve.
+   do not convert a folder for a feature the stand does not serve. It prints
+   the FEATURED models; `--all` lists the whole catalog, and you run that only
+   when the user asks for more. Whatever they pick, the picker in the game
+   shows the server's own label for it — a name you invent is a name that
+   differs from the model they are billed for.
 2. `npx genex init --convert` — it connects this folder to a hosted Genex game
    in place. The code, the files and this toolkit stay exactly as they are, and
    generations still land in `./assets`. It is the user's yes that runs it, so