@stage5/lumine 0.3.20 → 0.3.22

package/README.md

@@ -64,11 +64,17 @@ Approvals are capped at 2 GB and never lower a creator below the default.
 Bridge Builder meetup quest crews (the website's /achievements/bridge-builder
 page) are reviewed with `lumine admin meetup list [--status review|active|completed|all]`,
 `show <crewId>` (includes a one-hour link to the proof video),
+`approve-crew <crewId>`, `approve-grownup <crewId>`,
+`request-changes <crewId> --note <text>`,
 `approve-plan <crewId> [--note <text>]`, `send-back <crewId> --note <text>`
 (sends back whatever is waiting: the video, else the plan) and
 `approve <crewId> --attended <userId,userId,...>`, which unlocks the
-achievement for every member ticked. At least 3 attendees from 3 different
-branches are required.
+achievement for every member ticked once the server confirms the requirements.
+`request-changes` holds the current crew or grown-up approval step, shows the
+staff note to every member on the crew page and chat tracker, and announces it
+in the crew chat. Members can request review again after making the changes;
+staff still need to approve the step. Use `info` only for private questions to
+one member about their identity.
 
 For team projects, Lumine mirrors the website workspace flow: choosing or
 pulling the owner's main project creates or reuses your contribution branch and
@@ -231,10 +237,17 @@ audio, and MIDI data (`.mid`/`.midi`; playback still needs an app-side parser
 or synth); `lumine assets list` prints your uploads and refreshes
 `.twinkle/assets.json`.
 
-`lumine assets generate "<prompt>" --model <gpt-image-2.5-flare|gpt-image-2.5-sunburst|gpt-image-2|nano-banana>` creates
+**Nano Banana migration (0.3.21):** `--model nano-banana` now selects
+Nano Banana 2.1, the fast tier. In CLI 0.3.20 and earlier it selected Pro.
+To preserve Pro output in an existing script, change the option to
+`--model nano-banana-pro` before upgrading. Existing installed CLIs keep
+using Pro through the server's legacy model alias. This CLI release must be
+published after the API update that accepts the new model IDs.
+
+`lumine assets generate "<prompt>" --model <gpt-image-2.5-flare|gpt-image-2.5-sunburst|gpt-image-2|nano-banana|nano-banana-pro>` creates
 an AI-generated image asset instead of uploading one. `--model` is required
 (Flare = fast generation; Sunburst = precise editing; gpt-image-2 = original
-model; nano-banana = Gemini). Generation spends your Twinkle AI Battery, so the
+model; nano-banana = Gemini Nano Banana 2.1, nano-banana-pro = Gemini Nano Banana Pro). Generation spends your Twinkle AI Battery, so the
 CLI shows the estimated cost and asks for confirmation first — non-interactive
 runs must pass
 `--yes` to consent. `--quality low|medium|high|xhigh|max` applies to GPT Image
@@ -246,7 +259,7 @@ actual battery usage also includes prompt and reference input.
 `lumine thumbnail set <file>` uploads a jpg/png/webp (max 8MB) as the build's
 thumbnail. `lumine thumbnail capture` screenshots the running app server-side
 and sets the result (add `--out <file>` to keep a local copy).
-`lumine thumbnail generate ["<prompt>"] --model <gpt-image-2.5-flare|gpt-image-2.5-sunburst|gpt-image-2|nano-banana>`
+`lumine thumbnail generate ["<prompt>"] --model <gpt-image-2.5-flare|gpt-image-2.5-sunburst|gpt-image-2|nano-banana|nano-banana-pro>`
 generates an AI image and sets it as the thumbnail (the image is also kept as a
 normal reusable asset); without a prompt the server composes one from the build
 title and description. Replacing an existing thumbnail asks for confirmation;

package/lib/admin.js

@@ -2595,7 +2595,7 @@ export function parseAdminOperation(options) {
     // reviews as the admin controls on the website quest page. Mikey's own
     // decision, any time, never in a daily run.
     const usage =
-      "Usage: lumine admin meetup list [--status review|active|completed|all] | approve-crew <crewId> | approve-grownup <crewId> | emails [list|send <id>|discard <id>|review on|off] | friends [status|on|off] | parent-reply <crewId> <memberUserId> --note <text> | funnel [--days <1-90>] | branches [list|show|approve|reject|merge] | show <crewId> | approve-plan <crewId> [--note <text>] | send-back <crewId> --note <text> | approve <crewId> --attended <userId,userId,...> [--note <text>] | info <crewId> <userId> --decision ask|accept|ask-again|withdraw [--note <text>] | slot <crewId> --confirm <slotIndex> | resend-email <crewId>.";
+      "Usage: lumine admin meetup list [--status review|active|completed|all] | approve-crew <crewId> | approve-grownup <crewId> | request-changes <crewId> --note <text> | emails [list|send <id>|discard <id>|review on|off] | friends [status|on|off] | parent-reply <crewId> <memberUserId> --note <text> | funnel [--days <1-90>] | branches [list|show|approve|reject|merge] | show <crewId> | approve-plan <crewId> [--note <text>] | send-back <crewId> --note <text> | approve <crewId> --attended <userId,userId,...> [--note <text>] | info <crewId> <userId> --decision ask|accept|ask-again|withdraw [--note <text>] | slot <crewId> --confirm <slotIndex> | resend-email <crewId>.";
     const note = String(options.note || "").trim();
     if (note.length > 1000) {
       throw cliValidationError("--note must be at most 1000 characters.");
@@ -2783,6 +2783,17 @@ export function parseAdminOperation(options) {
         { requiresRun: false },
       );
     }
+    if (action === "request-changes") {
+      const crewId = parseRequiredInteger(target, "Crew ID", 1);
+      if (!note) throw cliValidationError("request-changes needs --note <what the whole crew must change>.");
+      return writeOperation(
+        "meetup.request-changes",
+        "POST",
+        `/cli/admin/meetup-quest/crews/${crewId}/request-changes`,
+        { note },
+        { requiresRun: false },
+      );
+    }
     if (action === "approve-crew" || action === "approve-grownup") {
       // Every step passes through the owner: the crew (members + branches) and
       // the grown-up step (parents' yes + the named adult).
@@ -5806,6 +5817,10 @@ function printMeetupCrew(crew) {
     console.log(`  ${step.number}. ${step.label} [${step.state}] ${step.detail}`);
   }
   console.log(`  Members: ${formatMeetupMembers(crew.members)}`);
+  for (const [step, review] of Object.entries(crew.reviews || {})) {
+    console.log(`  ${step === "crew" ? "Crew" : "Parents and adult"} approval: ${review.status}${review.requestedAt ? ` (review requested ${shortDate(review.requestedAt)})` : ""}`);
+    if (review.note) console.log(`    Shared staff note (every crew member sees this): ${review.note}`);
+  }
   // staff's "who are you" checks on these members (any crew), newest first
   for (const check of crew.memberChecks || []) {
     const answer = check.teacherName

package/lib/assets.js

@@ -66,7 +66,7 @@ export async function assetsCommand(options) {
     return;
   }
   throw new Error(
-    'Usage: lumine assets [list] | lumine assets upload <file...> | lumine assets generate "<prompt>" --model <gpt-image-2.5-flare|gpt-image-2.5-sunburst|gpt-image-2|nano-banana> | lumine assets delete <assetId> | lumine assets prune [--yes] | lumine assets storage | lumine assets request-storage [--size 500MB|1GB|2GB] [--reason "<what it is for>"]',
+    'Usage: lumine assets [list] | lumine assets upload <file...> | lumine assets generate "<prompt>" --model <gpt-image-2.5-flare|gpt-image-2.5-sunburst|gpt-image-2|nano-banana|nano-banana-pro> | lumine assets delete <assetId> | lumine assets prune [--yes] | lumine assets storage | lumine assets request-storage [--size 500MB|1GB|2GB] [--reason "<what it is for>"]',
   );
 }
 
@@ -156,7 +156,7 @@ export function resolveGenerateModel(options) {
   const model = GENERATE_MODEL_ALIASES[rawModel];
   if (!model) {
     throw new Error(
-      "--model is required: gpt-image-2.5-flare (fast generation), gpt-image-2.5-sunburst (precise editing), gpt-image-2, or nano-banana. No default model is applied.",
+      "--model is required: gpt-image-2.5-flare (fast generation), gpt-image-2.5-sunburst (precise editing), gpt-image-2, nano-banana (Nano Banana 2.1) or nano-banana-pro. No default model is applied.",
     );
   }
   const rawQuality = String(options.quality || "").trim();
@@ -165,7 +165,7 @@ export function resolveGenerateModel(options) {
   }
   if (rawQuality && !model.startsWith("gpt-image-")) {
     throw new Error(
-      "--quality only applies to GPT Image models; nano-banana has a single quality tier.",
+      "--quality only applies to GPT Image models; nano-banana and nano-banana-pro have a single quality tier.",
     );
   }
   if (model === "gpt-image-2" && ["xhigh", "max"].includes(rawQuality)) {
@@ -212,7 +212,7 @@ export async function assetsGenerate(options) {
   const prompt = String(options.positional[1] || "").trim();
   if (!prompt) {
     throw new Error(
-      'Usage: lumine assets generate "<prompt>" --model <gpt-image-2.5-flare|gpt-image-2.5-sunburst|gpt-image-2|nano-banana> [--quality low|medium|high|xhigh|max] [--name <fileName>] [--yes]',
+      'Usage: lumine assets generate "<prompt>" --model <gpt-image-2.5-flare|gpt-image-2.5-sunburst|gpt-image-2|nano-banana|nano-banana-pro> [--quality low|medium|high|xhigh|max] [--name <fileName>] [--yes]',
     );
   }
   const { model, quality } = resolveGenerateModel(options);

package/lib/commands.js

@@ -2713,6 +2713,7 @@ export function parseArgs(args) {
     repeat: Math.min(Math.max(Math.floor(Number(raw.repeat) || 1), 1), 20),
     allowWrite: parseBoolean(raw.allowWrite, false),
     assumeYes: parseBoolean(raw.yes, false),
+    show: parseBoolean(raw.show, false),
     sdkPath: raw.path ? String(raw.path) : "",
     sdkScopes: String(raw.scopes || "")
       .split(",")
@@ -3050,7 +3051,7 @@ export function printHelp() {
   lumine sdk call <namespace.method> [jsonArgs]
   lumine assets [list]
   lumine assets upload <file...>
-  lumine assets generate "<prompt>" --model <gpt-image-2.5-flare|gpt-image-2.5-sunburst|gpt-image-2|nano-banana>
+  lumine assets generate "<prompt>" --model <gpt-image-2.5-flare|gpt-image-2.5-sunburst|gpt-image-2|nano-banana|nano-banana-pro>
   lumine assets delete <assetId>
   lumine assets prune [--yes]
   lumine assets storage [--json]
@@ -3064,7 +3065,7 @@ export function printHelp() {
   lumine cardcraft check|status|review
   lumine thumbnail set <file>
   lumine thumbnail capture [--out <file>]
-  lumine thumbnail generate ["<prompt>"] --model <gpt-image-2.5-flare|gpt-image-2.5-sunburst|gpt-image-2|nano-banana>
+  lumine thumbnail generate ["<prompt>"] --model <gpt-image-2.5-flare|gpt-image-2.5-sunburst|gpt-image-2|nano-banana|nano-banana-pro>
   lumine doctor runtime-assets
   lumine admin identity list|status|use <zero|ciel|auto> [--json]
   lumine admin identity inspect <user-id|username> --reason <management-reason> [--include-private-evidence] [--output <file>] [--json]   (nothing kept on disk unless --output; that copy is 0600)
@@ -3101,7 +3102,7 @@ export function printHelp() {
   lumine admin reward-review list [--status pending|approved|all] [--cursor <id>] [--json]
   lumine admin cardcraft-review list [--status pending|approved|all] [--cursor <id>] | show <id> | approve|reject|revoke <id> [--reason <text>]
   lumine admin storage list [--status pending|approved|rejected|all] [--cursor <id>] | show <user-id-or-username> | approve <request-id> [--size <500MB|1GB|2GB|n MB>] [--reason <text>] | reject <request-id> [--reason <text>] | grant <user-id-or-username> --size <500MB|1GB|2GB|n MB> [--reason <text>]
-  lumine admin meetup list [--status review|active|completed|all] | approve-crew <crewId> | approve-grownup <crewId> | emails [list|send <id>|discard <id>|review on|off] | friends [status|on|off] | parent-reply <crewId> <memberUserId> --note <text> | funnel [--days <1-90>] | branches [list [--status pending|official|rejected|all] | show <id> | approve <id> | reject <id> [--note <text>] | merge <id> --into <officialId>] | show <crewId> | approve-plan <crewId> [--note <text>] | send-back <crewId> --note <text> | approve <crewId> --attended <userId,userId,...> [--note <text>] | info <crewId> <userId> --decision ask|accept|ask-again|withdraw [--note <text>] | slot <crewId> --confirm <slotIndex> | resend-email <crewId>   (Bridge Builder meetup quest)
+  lumine admin meetup list [--status review|active|completed|all] | approve-crew <crewId> | approve-grownup <crewId> | request-changes <crewId> --note <text> | emails [list|send <id>|discard <id>|review on|off] | friends [status|on|off] | parent-reply <crewId> <memberUserId> --note <text> | funnel [--days <1-90>] | branches [list [--status pending|official|rejected|all] | show <id> | approve <id> | reject <id> [--note <text>] | merge <id> --into <officialId>] | show <crewId> | approve-plan <crewId> [--note <text>] | send-back <crewId> --note <text> | approve <crewId> --attended <userId,userId,...> [--note <text>] | info <crewId> <userId> --decision ask|accept|ask-again|withdraw [--note <text>] | slot <crewId> --confirm <slotIndex> | resend-email <crewId>   (Bridge Builder meetup quest)
   lumine admin meetup story list | show <crewId> | approve <crewId> [--note <text>] [--no-announce] | send-back <crewId> --note <text> | unpublish <crewId> --note <text>   (Bridge Builder story pages: publishes only what every tagged member's parent allowed)
   lumine admin reward-activity [--date YYYY-MM-DD] [--days <1..31>] [--build <id>] [--json]
   lumine admin chat-reports list [--status pending|open|reviewing|resolved|dismissed|all] [--cursor <id>] [--json]
@@ -3317,7 +3318,7 @@ Options:
   --json                Print machine-readable output where supported
   --keep-assets         Keep doctor probe assets instead of deleting them
   --no-browser          Skip doctor browser probes
-  --model <model>       Image model for generate: gpt-image-2.5-flare, gpt-image-2.5-sunburst, gpt-image-2, or nano-banana (required)
+  --model <model>       Image model for generate: gpt-image-2.5-flare, gpt-image-2.5-sunburst, gpt-image-2, nano-banana (Nano Banana 2.1) or nano-banana-pro (required)
   --quality <q>         GPT Image quality: low, medium, high, xhigh, max (default high; xhigh/max require 2.5)
   --name <fileName>     File name hint for a generated asset
   --out <path>          With thumbnail capture: also save the capture locally

package/lib/constants.js

@@ -21,8 +21,14 @@ export const GENERATE_MODEL_ALIASES = {
   flare: "gpt-image-2.5-flare",
   sunburst: "gpt-image-2.5-sunburst",
   "gpt-image-2": "gpt-image-2",
-  "nano-banana": "gemini-3-pro-image-preview",
-  "gemini-3-pro-image-preview": "gemini-3-pro-image-preview",
+  // Gemini by tier (the API's NANO_BANANA_MODEL / NANO_BANANA_PRO_MODEL):
+  // nano-banana = the fast tier (Nano Banana 2.1 since 2026-10-08), pro = Pro
+  "nano-banana": "gemini-nano-banana-2.1",
+  "nano-banana-2.1": "gemini-nano-banana-2.1",
+  "gemini-nano-banana-2.1": "gemini-nano-banana-2.1",
+  "nano-banana-pro": "gemini-3-pro-image",
+  "gemini-3-pro-image": "gemini-3-pro-image",
+  "gemini-3-pro-image-preview": "gemini-3-pro-image",
 };
 export const GENERATE_QUALITIES = new Set([
   "low",
@@ -278,10 +284,10 @@ lumine save --summary "Describe the change"
   replaces. Update code references, then delete or prune the old asset.
 - Prefer one small assets module (e.g. src/assets.js) mapping names to asset
   URLs over scattering URLs through the code.
-- \`lumine assets generate "<prompt>" --model <gpt-image-2|nano-banana>\` creates
+- \`lumine assets generate "<prompt>" --model <gpt-image-2|nano-banana|nano-banana-pro>\` creates
   an AI-generated image asset. --model is REQUIRED (no default): gpt-image-2 is
-  best quality but slower and pricier; nano-banana (Gemini) is faster and
-  cheaper. It spends the logged-in user's AI Battery, so it asks y/N with the
+  best quality but slower and pricier; nano-banana (Gemini Nano Banana 2.1) is
+  the fastest and cheapest; nano-banana-pro (Gemini Nano Banana Pro) sits between. It spends the logged-in user's AI Battery, so it asks y/N with the
   estimated cost first; non-interactive runs must pass --yes to consent.
   Optional: --quality low|medium|high (gpt-image-2 only, default high),
   --name <fileName>. The asset lands in .twinkle/${ASSETS_METADATA_FILE} like an upload.
@@ -313,7 +319,7 @@ lumine save --summary "Describe the change"
   build's thumbnail. Thumbnails display ~16:9; the image is uploaded uncropped.
 - \`lumine thumbnail capture\` screenshots the running app server-side and sets
   the result as the thumbnail (add --out <file> to also save it locally).
-- \`lumine thumbnail generate "<prompt>" --model <gpt-image-2|nano-banana>\`
+- \`lumine thumbnail generate "<prompt>" --model <gpt-image-2|nano-banana|nano-banana-pro>\`
   generates an AI image and sets it as the thumbnail (also stored as a normal
   reusable asset). Same battery-cost consent rules as \`assets generate\`.
 - Replacing an existing thumbnail asks y/N; pass --yes for non-interactive runs.

package/lib/thumbnail.js

@@ -42,7 +42,7 @@ export async function thumbnailCommand(options) {
     return;
   }
   throw new Error(
-    'Usage: lumine thumbnail set <file> | lumine thumbnail capture [--out <file>] | lumine thumbnail generate "<prompt>" --model <gpt-image-2.5-flare|gpt-image-2.5-sunburst|gpt-image-2|nano-banana>',
+    'Usage: lumine thumbnail set <file> | lumine thumbnail capture [--out <file>] | lumine thumbnail generate "<prompt>" --model <gpt-image-2.5-flare|gpt-image-2.5-sunburst|gpt-image-2|nano-banana|nano-banana-pro>',
   );
 }
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@stage5/lumine",
-  "version": "0.3.20",
+  "version": "0.3.22",
   "description": "Command line tools for launching Lumine builds on Twinkle.",
   "type": "module",
   "bin": {

package/sdk/BUILD_SDK_INDEX.md

@@ -2,7 +2,7 @@
 
 Version: 1.63.0
 Updated: 2026-09-28
-Generated: 2026-10-07T07:52:06.040Z
+Generated: 2026-10-08T04:59:03.150Z
 
 ## Notes
 - This SDK is injected into Build iframes via the Build preview/runtime.
@@ -536,6 +536,7 @@ const result = await Twinkle.ai.chat({ message, history: chatHistory, systemProm
   - referenceImageB64 may be a raw base64 string or a data:image/...;base64 URL.
   - Optional model: gpt-image-2.5-flare or gpt-image-2.5-sunburst. Without a model, OpenAI uses Flare for new images and Sunburst when a reference image or continuation is supplied. Explicit gpt-image-2 remains supported.
   - Quality accepts low, medium, high, xhigh, or max. xhigh and max require a GPT Image 2.5 model. Gemini has one quality tier.
+  - engine: 'gemini' uses Google's Nano Banana 2.1 (the fast Gemini image tier; it replaced the retired original Nano Banana on 2026-10-08).
   - GPT Image 2.5 battery spending uses actual image-model input and output token usage. The confirmation shows an image-output estimate; prompts and reference images use additional energy.
   - responseId and imageId are opaque continuation handles. Pass them back unchanged to edit a prior result; do not assume an OpenAI ID format. Existing GPT Image 2 continuations remain usable.
   - Example: const result = await Twinkle.ai.generateImage({ prompt: 'Create a fashion guide portrait for this face with flattering colors and outfit ideas', referenceImageB64, quality: 'high', onStatus: (status) => console.log(status.stage) });

package/sdk/LUMINE_ADMIN.md

@@ -4927,3 +4927,14 @@ After the Study review migration is deployed, the full daily website run also re
 Study's registered `study-record-v1` checks use learner AI Energy for accepted, revise and uncertain results. Preview checks use real AI Energy but cannot award XP/Coins. The agreed proposal pays 2,000 XP + 500 Coins at most once per learner per UTC day. Breadface's `breadface-v1` uses deterministic server physics, not a model. Both creator proposals must be accepted to publish; inspect the canonical review state and acceptance/rejection events during follow-up.
 
 For total JEV cost, include `dailyAiCosts.byProviderModel` for TypeSafe/JEV across both AI Energy and system-covered ledgers. Report serving/shadow/audit operations separately as above; the Build SDK's system-covered/failed calls use `jev_decision`, while ordinary viewer SDK checks are already counted by the AI Energy ledger. Do not add the Study report's known-cost sum on top of the canonical overall AI-cost total: it is a diagnostic breakdown of those same calls.
+
+## Bridge Builder crew reviews (no daily run required)
+
+- `lumine admin meetup list` shows steps waiting for staff. Use `list --status active` to include crews making requested changes.
+- `lumine admin meetup show <crewId>` shows canonical progress, approval status, shared feedback, and private staff evidence.
+- `lumine admin meetup approve-crew <crewId>` and `approve-grownup <crewId>` approve the corresponding ready step.
+- `lumine admin meetup request-changes <crewId> --note <text>` holds the current crew or grown-up step, displays the note to **every crew member**, and announces it in the crew chat. The note is required (maximum 1,000 characters). Members use **Request review again** after making changes; this alerts staff and returns the step to the queue without approving it.
+- `lumine admin meetup send-back <crewId> --note <text>` is for a pending plan or video. Those steps keep their existing revise-and-submit flow.
+- `lumine admin meetup info <crewId> <userId> --decision ask|accept|ask-again|withdraw` is a **private identity check**. Its question and answer are visible only to the named member and staff. Use `request-changes`, not `info`, for instructions the whole crew needs to see.
+
+Every decision requires Mikey's authorization for that crew and action. Mutations are audited and idempotent; `--output <path>` is an explicit request to retain the canonical JSON. General write receipts omit private crew details.