@slatesvideo/shared 0.6.9 → 0.6.11

package/dist/update-check.d.ts

@@ -0,0 +1,22 @@
+export declare const UPDATE_CACHE_FILE: string;
+/** Numeric semver compare on the release segments; a prerelease suffix is ignored. */
+export declare function compareVersions(a: string, b: string): number;
+/** The newest version the last registry lookup recorded for `pkgName`. Sync, disk only. */
+export declare function cachedLatestVersion(pkgName: string, cacheFile?: string): string | null;
+/**
+ * Refresh the cached latest version from the npm registry when the entry is
+ * older than an hour. Bounded by FETCH_TIMEOUT_MS, never throws. Returns the
+ * latest version known after the call (fresh or cached), or null.
+ */
+export declare function refreshLatestVersion(pkgName: string, options?: {
+    cacheFile?: string;
+    registryUrl?: string;
+    now?: number;
+}): Promise<string | null>;
+/**
+ * One sentence when `current` is behind `latest`, else null. `howToUpdate` is
+ * the surface-specific action: the MCP server's is a client restart, the CLI's
+ * is a reinstall.
+ */
+export declare function updateNotice(pkgName: string, current: string, latest: string | null, howToUpdate: string): string | null;
+//# sourceMappingURL=update-check.d.ts.map

package/dist/update-check.js

@@ -0,0 +1,109 @@
+// Version handshake for the two published entry points (@slatesvideo/mcp-server
+// and @slatesvideo/cli).
+//
+// WHY THIS EXISTS (2026-09-13): a Discord user's agent reported "H3 isn't in
+// the API tool, only Kling, Veo and Seedance are exposed" — a server older
+// than 0.5.10 (2026-08-28). Nothing told him, and nothing told his agent. The
+// install path is `npx -y @slatesvideo/mcp-server` with no version pinned, so
+// a client RESTART is the whole update; the failure is a client that never
+// restarts, a global install nobody re-runs, or skill files copied months ago.
+//
+// HOW IT WORKS. One small registry GET (`/<pkg>/latest`), cached on disk in
+// ~/.slates/update-check.json and refreshed at most once an hour. Readers are
+// SYNCHRONOUS and disk-only so the MCP server can put the notice into its
+// `instructions` at construction time without delaying startup; the refresh
+// runs in the background for the NEXT launch. The CLI awaits the refresh
+// (bounded by FETCH_TIMEOUT_MS) because a CLI turn already pays for a network
+// call. Every path is fail-silent: no network, no home dir, no registry —
+// no notice, never an error.
+import { mkdirSync, readFileSync, writeFileSync } from 'node:fs';
+import { join } from 'node:path';
+import { AGENT_DIR } from './auth.js';
+export const UPDATE_CACHE_FILE = join(AGENT_DIR, 'update-check.json');
+const REFRESH_AFTER_MS = 60 * 60 * 1000;
+const FETCH_TIMEOUT_MS = 2500;
+/** Numeric semver compare on the release segments; a prerelease suffix is ignored. */
+export function compareVersions(a, b) {
+    const parse = (v) => v.replace(/^v/, '').split('-')[0].split('.').map((n) => Number.parseInt(n, 10) || 0);
+    const pa = parse(a);
+    const pb = parse(b);
+    for (let i = 0; i < Math.max(pa.length, pb.length); i++) {
+        const d = (pa[i] ?? 0) - (pb[i] ?? 0);
+        if (d !== 0)
+            return d;
+    }
+    return 0;
+}
+function readCache(file) {
+    try {
+        const parsed = JSON.parse(readFileSync(file, 'utf8'));
+        return parsed && typeof parsed === 'object' ? parsed : {};
+    }
+    catch {
+        return {};
+    }
+}
+function writeCache(file, cache) {
+    try {
+        mkdirSync(join(file, '..'), { recursive: true });
+        writeFileSync(file, JSON.stringify(cache, null, 2) + '\n', 'utf8');
+    }
+    catch {
+        // A read-only home is not a reason to fail a generation.
+    }
+}
+/** The newest version the last registry lookup recorded for `pkgName`. Sync, disk only. */
+export function cachedLatestVersion(pkgName, cacheFile = UPDATE_CACHE_FILE) {
+    const entry = readCache(cacheFile)[pkgName];
+    return entry && typeof entry.latest === 'string' ? entry.latest : null;
+}
+/**
+ * Refresh the cached latest version from the npm registry when the entry is
+ * older than an hour. Bounded by FETCH_TIMEOUT_MS, never throws. Returns the
+ * latest version known after the call (fresh or cached), or null.
+ */
+export async function refreshLatestVersion(pkgName, options = {}) {
+    const cacheFile = options.cacheFile ?? UPDATE_CACHE_FILE;
+    const now = options.now ?? Date.now();
+    const cache = readCache(cacheFile);
+    const entry = cache[pkgName];
+    if (entry && now - entry.checkedAt < REFRESH_AFTER_MS)
+        return entry.latest;
+    const registryUrl = options.registryUrl ?? 'https://registry.npmjs.org';
+    const controller = new AbortController();
+    const timer = setTimeout(() => controller.abort(), FETCH_TIMEOUT_MS);
+    // A stdio server exits when its client closes; a pending timer must not
+    // hold the process open for the rest of the timeout.
+    timer.unref?.();
+    try {
+        const res = await fetch(`${registryUrl}/${pkgName}/latest`, {
+            signal: controller.signal,
+            headers: { accept: 'application/json' },
+        });
+        if (!res.ok)
+            return entry?.latest ?? null;
+        const body = (await res.json());
+        if (typeof body.version !== 'string')
+            return entry?.latest ?? null;
+        cache[pkgName] = { latest: body.version, checkedAt: now };
+        writeCache(cacheFile, cache);
+        return body.version;
+    }
+    catch {
+        return entry?.latest ?? null;
+    }
+    finally {
+        clearTimeout(timer);
+    }
+}
+/**
+ * One sentence when `current` is behind `latest`, else null. `howToUpdate` is
+ * the surface-specific action: the MCP server's is a client restart, the CLI's
+ * is a reinstall.
+ */
+export function updateNotice(pkgName, current, latest, howToUpdate) {
+    if (!latest || compareVersions(current, latest) >= 0)
+        return null;
+    return `UPDATE AVAILABLE: ${pkgName} v${current} is running; v${latest} is published. ${howToUpdate}`;
+}
+//# sourceMappingURL=update-check.js.map

package/exports/slates-prompt-builder/generated/SKILL.md

@@ -16,8 +16,8 @@ This portable skill is deliberately thin. Its reference files are generated dire
 <!-- @generated:model-routing -->
 | Model | Canonical route | Guide |
 |---|---|---|
-| **Kling 3.0** | DEFAULT general-purpose video model — cost-effective, strong start-frame adherence (identity, layout, text), acting, dialogue, lip-sync, and the widest aspect-ratio set. Escalate to Seedance for physics. Kling is also the ONLY engine behind the Motion Transfer and Lip Sync tools. | `reference-kling.md` |
-| **Seedance 2.0** | PREMIUM video tier and the DEFAULT video model — route here the moment physics, effects, destruction or scale matter, and for hero shots. VIDEO-ONLY. Strong image-to-video and own-footage restyle. 4K is Pro-gated (base accounts get PRO_REQUIRED). Stays the default over 2.5: it is the only Seedance with native 4K and it is cheaper at every tier the two share. | `reference-seedance.md` |
+| **Kling 3.0** | THE COST-EFFECTIVE SEAT — strong start-frame adherence (identity, layout, text), acting, dialogue, lip-sync and the widest aspect-ratio set; pick it when the budget matters and the shot is a performance or a start-frame animation. Kling is also the ONLY engine behind the Motion Transfer and Lip Sync tools. | `reference-kling.md` |
+| **Seedance 2.0** | THE 4K AND VALUE SEAT beside the 2.5 default — the only Seedance with native 4K (Pro-gated; base accounts get PRO_REQUIRED) and cheaper than 2.5 at every resolution they share, with the same physics, effects and scale strengths; shorter takes, fewer references, no timestamps. VIDEO-ONLY. A bare "seedance" still resolves here for older CLIs that expect 4K. | `reference-seedance.md` |
 | **Nano Banana 2 (Gemini 3.1 Flash Image)** | DEFAULT image model and the all-rounder — route here unless another seat's speciality is the point. Best start-frame for legible in-scene text. Knowledge cutoff Jan 2025: anything later needs reference images. | `reference-nano-banana.md` |
 <!-- @end:model-routing -->
 

package/exports/slates-prompt-builder/generated/slates-prompt-builder-manifest.json

@@ -28,14 +28,14 @@
     },
     {
       "path": "src/prompts/model-facts.ts",
-      "sha256": "63d6709c85d2f11d4244e46bd1a595094f1cf7066e2ac69c8a2b46783e4dc4b6"
+      "sha256": "4df3ac4b003ed29c2e1992a34519e01957e5292211a294bb2af0045daf9d4194"
     }
   ],
   "outputs": [
     {
       "path": "SKILL.md",
-      "bytes": 4598,
-      "sha256": "47cd166742efe1b15fb25603922695c5397ab9d24a839fb524d69cde426a6f89"
+      "bytes": 4622,
+      "sha256": "0c3f1982796fe668824067b06e8d76070aaae2d00d47a978ef5bd8b489b2a3da"
     },
     {
       "path": "reference-character.md",
@@ -65,8 +65,8 @@
   ],
   "archive": {
     "path": "slates-prompt-builder.skill",
-    "bytes": 40497,
-    "sha256": "6289a7827816f38fa6cf6c9afe8c6a0d9efa865861a4e732170a40b584edc8a7",
+    "bytes": 40546,
+    "sha256": "0760799f957aac866590768dd00bc74cd4c32525364455c0eab96dba334c4de4",
     "entries": [
       "SKILL.md",
       "reference-character.md",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@slatesvideo/shared",
-  "version": "0.6.9",
+  "version": "0.6.11",
   "description": "Shared operations layer for the Slates MCP server and CLI: auth, cloud/desktop clients, and the single tool surface both consume. Most users want @slatesvideo/mcp-server or @slatesvideo/cli instead.",
   "license": "MIT",
   "type": "module",
@@ -43,7 +43,7 @@
     "sync-partials": "node scripts/sync-partials.mjs",
     "build-prompt-builder": "node scripts/build-prompt-builder.mjs",
     "check-prompt-builder": "node scripts/build-prompt-builder.mjs --check",
-    "build": "node scripts/sync-partials.mjs --check && node scripts/build-prompt-builder.mjs --check && node scripts/embed-skills.mjs && tsc && node scripts/render-capability-partials.mjs --check",
+    "build": "node scripts/sync-partials.mjs --check && node scripts/build-prompt-builder.mjs --check && node scripts/embed-skills.mjs && tsc && node scripts/render-capability-partials.mjs --check && node scripts/update-check-check.mjs",
     "typecheck": "node scripts/sync-partials.mjs --check && node scripts/build-prompt-builder.mjs --check && node scripts/embed-skills.mjs && tsc --noEmit",
     "prepublishOnly": "npm run build",
     "render-partials": "node scripts/render-capability-partials.mjs"

package/skills/slates-model-selection.md

@@ -1,6 +1,6 @@
 ---
 name: slates-model-selection
-description: Which model to pick for a given job — the routing doctrine. Read BEFORE choosing any video or image model, before quoting a plan, and before defaulting anywhere. Kling 3.0 is the general-purpose video default; Seedance 2.0 is the premium tier for anything where physics, effects, or scale remotely matter; Seedance 2.5 is a SECOND SEAT beside 2.0 (30s takes, 30 references and timestamp control, but no 4K and dearer at every shared resolution — never an upgrade); MiniMax H3 is the AUTHORED-AUDIO seat (three directable sound layers in one pass, declared reference relationships, 480p-4K) with MiniMax H3 Max beside it as a faster 768p-capped, reference-free premium; Veo 3.1 is a narrow niche (native synced audio in one gen, 16:9 or 9:16, 4/6/8s) and never the default.
+description: Which model to pick for a given job — the routing doctrine. Read BEFORE choosing any video or image model, before quoting a plan, and before defaulting anywhere. Seedance 2.5 is the DEFAULT video model (Eric, 2026-09-13: the best in the world — physics, effects, scale, 30s takes, 30 references, timestamps); Seedance 2.0 is the 4K seat and the cheaper one at every shared resolution; Kling 3.0 is the cost-effective seat for performances, start-frame animation and lip-sync; MiniMax H3 is the AUTHORED-AUDIO seat (three directable sound layers in one pass, declared reference relationships, 480p-4K) with MiniMax H3 Max beside it as a faster 768p-capped premium with omni-references; Veo 3.1 is a narrow niche (native synced audio in one gen, 16:9 or 9:16, 4/6/8s) and never the default.
 ---
 
 # Model selection — the routing doctrine
@@ -23,12 +23,12 @@ The tables below are a snapshot. This roster churns constantly (NB2 Lite, Omni F
 
 | Job | Model | Why |
 |---|---|---|
-| **General-purpose — the default for most shots** | **Kling 3.0 std** | Cost-effective workhorse. Strong image-to-video: preserves identity, layout, and text from the start frame. 16:9 / 9:16 / 1:1, 3–15s. |
+| **General-purpose — the default for most shots** | **Seedance 2.5** | The strongest seat in the catalogue: physics, effects, scale and hero shots, 4–30s in one take, 30 image + 10 video + 10 audio references, audio-only refs, and the only Seedance seat that acts on timestamps. 480p / 720p / 1080p, no 4K. LENGTH is the price dial — quote any take over ~10s. |
+| **Cost matters and the shot is a performance or a start-frame animation** | **Kling 3.0 std** | Cost-effective workhorse. Strong image-to-video: preserves identity, layout, and text from the start frame. 16:9 / 9:16 / 1:1, 3–15s. |
 | Higher visual polish, no physics demands | Kling 3.0 pro | Mid-price fidelity bump on the same strengths. |
 | Multi-character dialogue / audio co-generation | Kling 3.0 omni | Dialogue syntax, voice direction, language codes, `@element` refs. |
-| **Anything with remotely important physics** — effects, destruction, water/fire/smoke/cloth, creature motion, scale, complex simultaneous action | **Seedance 2.0** | The premium tier. Physics and effects are its whole edge; up to 9 ingredient refs, first+last frame, native 4K (4K video is Pro-only). |
-| The premium hero shot a piece hangs on | Seedance 2.0 | Spend where it shows. |
-| **One take longer than 15 seconds**, or a shot needing more than 9 image references, or an AUDIO-ONLY reference, or **beats that have to land at a named second** | **Seedance 2.5** | A SECOND SEAT beside 2.0, never an upgrade: 4–30s in one take, 30 image + 10 video + 10 audio references, audio-only refs, and the only Seedance seat that **acts on timestamps** (rules in `slates-prompting-seedance-2-5` § Timestamps) — 480p / 720p / 1080p, **no 4K**, and **dearer than 2.0 at every shared resolution** (720p $0.231/s vs $0.15/s, +54%). If you want 4K, or the same resolution cheaper, stay on 2.0. 🚨 Two live hazards: (a) with references attached, the words *add / remove / replace / change / extend / continue* make it reclassify the request as a video EDIT and fail AFTER the job queues — describe the finished frame, or use `seedance-2.5-edit`; (b) LENGTH is the price dial, not resolution — a 30s 720p face gen is 489 credits and a 30s 1080p faceless gen is 614, against a 1,000-credit welcome grant. Quote before any take over ~10s. |
+| **4K delivery**, or the same resolution cheaper than 2.5 | **Seedance 2.0** | The only Seedance with native 4K (4K video is Pro-only) and cheaper than 2.5 at every shared resolution (720p $0.15/s vs $0.231/s). Same physics and effects strengths; 15s takes, 15 references, no timestamps. |
+| **One take longer than 15 seconds**, more than 15 references, an AUDIO-ONLY reference, or **beats that have to land at a named second** | **Seedance 2.5** | Only 2.5 does these (rules in `slates-prompting-seedance-2-5` § Timestamps); it is the default anyway. 🚨 Two live hazards: (a) with references attached, the words *add / remove / replace / change / extend / continue* make it reclassify the request as a video EDIT and fail AFTER the job queues — describe the finished frame, or use `seedance-2.5-edit`; (b) LENGTH is the price dial, not resolution — a 30s 720p face gen is 489 credits and a 30s 1080p faceless gen is 614, against a 1,000-credit welcome grant. Quote before any take over ~10s. |
 | **The SOUND has to be directed, not just present** — a specific line delivered a specific way, scene sound that has to sit under it, and score that must stay out of the characters' world | **MiniMax H3** | The only seat where audio is authored in three separate layers in ONE pass (synchronised events in the body, ambience in a soundscape section, audience-only score in its own) rather than toggled on. 5–15s, 480p / 768p / 2K / 4K, 24fps, 32kHz stereo, 11 languages. Rules in `slates-prompting-minimax-h3`. |
 | **A reference has to keep a DECLARED amount of itself** — especially moving one subject's characteristic onto a *different* subject | **MiniMax H3** | The only seat that understands a stated retention relationship (kept whole / kept in part / transferred onto another subject / loose echo). 9 images + 3 video + 3 audio, 12 files total. 🚨 The first 5 reference images are free and every one after that costs 4 credits — pass `referenceImages` to `slates_estimate_generation_cost` before a reference-heavy job. |
 | **Turnaround is the requirement** on a text-to-video or start-frame shot at 480p/768p | **MiniMax H3 Max** | fal's self-hosted post-train of H3. **Measured 2026-08-27: a 5s 768p clip finished in 4.8s against 57s on base H3 — about 12x faster**, same prompt, queue to file. When turnaround is the requirement this is not a marginal win. 🚨 It is the PREMIUM seat, not a cheap H3 — $0.080/s at 768p against base H3's $0.060/s, 33% more, and it tops out at 768p. It still animates a start frame and an end frame — image-to-video is one of the two things it is for — and since 2026-09-09 it takes the full omni-reference set too (9 images + 3 video + 3 audio), so the seats now differ on ladder and price rather than on what they accept. Never the default; never reach for it to save money. |
@@ -77,11 +77,11 @@ Both tools are **Kling-only**. Every entry in them is a real Kling endpoint that
 
 **Rules:**
 
-- **Default video = Kling 3.0 std.** Escalate to Seedance the moment the shot has physics/effects weight or is the hero moment — and say why in the plan ("physics-heavy, routing to Seedance").
+- **Default video = Seedance 2.5.** Route to Seedance 2.0 for 4K or when the same resolution must be cheaper, and to Kling 3.0 std when the budget matters and the shot is a performance or a start-frame animation — and say why in the plan ("4K delivery, routing to 2.0"; "budget dialogue shot, routing to Kling").
 - **Veo is never the default.** 16:9 or 9:16 only, 4/6/8s only (and 8s only at 1080p/4K, or with reference images), and it is not the quality pick — treat it as a single-purpose tool for native-synced-audio shots. If audio can be added after (Kling lip-sync, edit stage), prefer Kling or Seedance + audio in post.
 - **9:16 vertical → Kling or Seedance by preference**, not by necessity: Veo does take 9:16 on the route Slates uses. Route away from it because it is the niche seat, not because it can't.
 - **Ratios and durations are enforced before submit.** `slates_generate_video` validates the aspect ratio, resolution and duration against the model you picked and refuses out-of-set values with the legal list — it will not silently ignore or downgrade them. The authoritative per-model sets are in the op's own param descriptions, which are generated from the capability SSOT; prefer those over any list written in prose here.
-- **Image-to-video from an NB2 start frame** (the standard pipeline) → Kling by default, Seedance when the motion is physics-heavy. Not Veo.
+- **Image-to-video from an NB2 start frame** (the standard pipeline) → Seedance 2.5 by default, Kling when the budget matters and the motion is a performance. Not Veo.
 - **User names a model explicitly → use it.** But if it's a mismatch for the job (crazy physics on Kling std, a 30s take on anything but Seedance 2.5, 4K on Seedance 2.5 which has none), say so in one line and offer the right route before generating.
 
 ## Image routing

package/skills/slates-one-prompt-film.md

@@ -64,9 +64,10 @@ Fork each bound frame's image Shot with `slates_duplicate_shot` (`model:` the vi
 ⚠️ **It runs SEQUENTIALLY and blocks until the last clip lands** — a 6-shot film is one long wait, and it will usually outlast the HTTP timeout while the run keeps going. When that happens, poll `slates_get_shot` for each Shot's `generationIds` and then `slates_get_generation_status`; **never re-fire, that double-spends.** (Concurrent batch firing needs a real queue — concurrency limiting, per-item failure isolation, partial-billing semantics — and is deliberately not built yet.)
 
 **Model mixing — route per `slates-model-selection`** (details in the per-model guides):
-- **Kling V3** (`slates-prompting-kling-v3`): the DEFAULT for most shots — 16:9 / 9:16 / 1:1, 3-15s, strong start-frame adherence; std is the workhorse, Omni for multi-character dialogue.
-- **Seedance 2** (`slates-prompting-seedance`): the PREMIUM tier — any shot where physics/effects/scale remotely matter, plus the hero shot; audio included, first+last frame guidance, native 4K (4K video is Pro-only).
-- **MiniMax H3** (`slates-prompting-minimax-h3`): route here when a shot's SOUND is part of the writing — a line delivered a particular way, scene sound under it, score that must stay outside the characters' world. It authors all three in one pass, which **collapses a shot's audio pass into its video pass** and removes the separate `slates_generate_audio` step for that shot. 5-15s, 480p/768p/2K/4K. Its sibling `minimax-h3-max` is faster, tops out at 1080p, takes the same references, and costs MORE at 768p — a deliberate speed pick, never a saving.
+- **Seedance 2.5** (`slates-prompting-seedance-2-5`): the DEFAULT for most shots — physics, effects, scale and the hero shot; 4-30s takes, 30 image references, timestamps; 480p/720p/1080p, no 4K. LENGTH is the price dial.
+- **Seedance 2** (`slates-prompting-seedance`): the 4K seat, cheaper than 2.5 at every shared resolution; audio included, first+last frame guidance, native 4K (4K video is Pro-only).
+- **Kling V3** (`slates-prompting-kling-v3`): the cost-effective seat — 16:9 / 9:16 / 1:1, 3-15s, strong start-frame adherence; std is the workhorse, Omni for multi-character dialogue.
+- **MiniMax H3** (`slates-prompting-minimax-h3`): route here when a shot's SOUND is part of the writing — a line delivered a particular way, scene sound under it, score that must stay outside the characters' world. It authors all three in one pass, which **collapses a shot's audio pass into its video pass** and removes the separate `slates_generate_audio` step for that shot. 5-15s, 480p/768p/2K/4K. Its sibling `minimax-h3-max` is faster, tops out at 768p, takes the same references, and costs MORE at 768p — a deliberate speed pick, never a saving.
 - **Veo 3.1** (`slates-prompting-veo-3`): niche, never the default — only when native synced audio must generate WITH the video in one gen; 16:9 or 9:16, 4/6/8s (8s only at 1080p/4K or with reference images).
 
 Failed gen? The run continues past it and **nothing is retried automatically**. Read the per-Shot error in the result, fix that Shot with `slates_update_shot`, and re-fire only it (a retry beyond the plan = announce the delta cost).

package/skills/slates-prompting-minimax-h3.md

@@ -1,6 +1,6 @@
 ---
 name: slates-prompting-minimax-h3
-description: How to prompt MiniMax H3 and MiniMax H3 Max. Read before calling slates_generate_video with model minimax-h3 or minimax-h3-max. H3 is the only Slates video seat where AUDIO IS AUTHORED rather than toggled — synchronised dialogue, scene sound and an audience-only score are three separate sections of the prompt, generated in one pass — and the only one where a reference carries a DECLARED RELATIONSHIP (kept whole, partly kept, transferred onto a different subject, or a loose echo). Base minimax-h3 runs 480p/768p/2K/4K and reads 9 images + 3 video + 3 audio references; minimax-h3-max is fal's faster post-train, capped at 768p, and costs MORE than base H3 at 768p — a deliberate speed pick, never the default and never the cheap one; it animates start and end frames AND takes the same 9+3+3 omni-reference set (corrected 2026-09-09), so the seats differ on ladder and price, not on what they accept. Two hazards live here: reference images past the free allowance are billed (5 free then +4 credits on base H3; 4 free then +1 on Max), and audio written into the wrong section is dropped or duplicated.
+description: How to prompt MiniMax H3 and MiniMax H3 Max. Read before calling slates_generate_video with model minimax-h3 or minimax-h3-max. H3 is the only Slates video seat where AUDIO IS AUTHORED rather than toggled — synchronised dialogue, scene sound and an audience-only score are three separate sections of the prompt, generated in one pass — and the only one where a reference carries a DECLARED RELATIONSHIP (kept whole, partly kept, transferred onto a different subject, or a loose echo). Base minimax-h3 runs 480p/768p/2K/4K and reads 9 images + 3 video + 3 audio references; minimax-h3-max is fal's faster post-train, capped at 768p, and costs MORE than base H3 at 768p — a deliberate speed pick, never the default and never the cheap one; it animates start and end frames AND takes the same 9+3+3 omni-reference set (corrected 2026-09-09), so the seats differ on ladder and price, not on what they accept. Two hazards live here: reference images past the free allowance are billed (5 free then +4 credits on base H3; pooled media tokens on Max), and audio written into the wrong section is dropped or duplicated.
 ---
 
 # MiniMax H3 — prompting
@@ -28,7 +28,7 @@ description: How to prompt MiniMax H3 and MiniMax H3 Max. Read before calling sl
 - `A woman sits still at a kitchen table for a beat, then looks up. She says in English, "You said Tuesday." Scene sound: a fridge hum, a spoon set down on formica. Score: none.`
 - `Two mechanics either side of an open bonnet. The younger one wipes his hands, waits, then speaks in Spanish, "No es el alternador." Scene sound: a socket wrench, a radio two bays over. Score: a low sustained cello under the last three seconds, audience only.`
 
-**Hard constraint:** the two seats differ in what the ENDPOINT accepts, not in grammar. Base H3 reaches 2K/4K and takes references; `minimax-h3-max` tops out at 1080p rather than 4K, takes the same 9+3+3 references, and costs MORE at the tier they share — it is a speed pick, never the cheap one. H3's top two resolution tiers are UPSCALES of the native render: judge at native. Reference images past the free allowance are a paid dimension of the cost key (5 free on base, 4 on Max) — declare the count when quoting.
+**Hard constraint:** the two seats differ in what the ENDPOINT accepts, not in grammar. Base H3 reaches 2K/4K and takes references; `minimax-h3-max` tops out at 768p rather than 4K, takes the same 9+3+3 references, and costs MORE at the tier they share — it is a speed pick, never the cheap one. H3's top two resolution tiers are UPSCALES of the native render: judge at native. Reference inputs affect the quote; include every attached modality when estimating.
 <!-- @card:end -->
 
 <!-- @banned:start -->
@@ -55,7 +55,7 @@ endpoint accepts:
 
 | | `minimax-h3` | `minimax-h3-max` |
 |---|---|---|
-| Resolution | 480p / 768p / **2K / 4K** | 480p / 768p / **1080p** |
+| Resolution | 480p / 768p / **2K / 4K** | 480p / 768p |
 | References | 9 images + 3 video + 3 audio (12 files) | 9 images + 3 video + 3 audio (12 files) |
 | Frames | start and/or end | start and/or end |
 | Price at 768p | **$0.060/s** | $0.080/s |
@@ -262,11 +262,12 @@ with at least one image or video reference.
 
 ### 💸 Reference images past the free allowance are billed — and the two rows differ
 
-On `minimax-h3` the first **5** are free and each additional image adds **4 credits**. On
-`minimax-h3-max` the first **4** are free and each additional image adds **1 credit** — fal prices
-Max's references by token rather than per image, and Slates normalises every Max reference to
-1024x1024 so that per-image number is exact. Both rows take **9** images, at every resolution and
-every length. Four extra images on a 10s
+On `minimax-h3` the first **5** are free and each additional image adds **4 credits**.
+Max pools image pixels, reference-video seconds and reference-audio seconds into one token
+allowance. Include `referenceImages`, `videoRefSeconds` and `audioRefSeconds` when estimating;
+character voices count as audio. The generation preflight resolves the actual attached media.
+
+Four extra images on a 10s
 768p clip add 16 credits to a 30-credit generation: **more than half again**, for references that
 often make the output worse rather than better (see the 2–4 rule above).
 
@@ -300,9 +301,7 @@ dropping one side.
 | `minimax-h3` · 2K · 10s | 65 |
 | `minimax-h3` · 4K · 10s | 80 |
 | `minimax-h3-max` · 768p · 10s | 40 |
-| `minimax-h3-max` · 1080p · 10s | 80 |
 | `minimax-h3` — every reference image past the **fifth** | **+4** |
-| `minimax-h3-max` — every reference image past the **fourth** | **+1** |
 
 **768p is the default for a reason.** It is the tier the model natively generates.
 

package/skills/slates-prompting-seedance-2-5.md

@@ -1,6 +1,6 @@
 ---
 name: slates-prompting-seedance-2-5
-description: How to prompt Seedance 2.5 and Seedance 2.5 Edit. Read before calling slates_generate_video with model seedance-2.5, or slates_edit_video with model seedance-2.5-edit. 2.5 is a SECOND SEAT next to 2.0, not an upgrade — it buys 30-second takes, 30 image references, audio-only references and INTEGER-SECOND TIMESTAMPS, and it gives up native 4K and costs more than 2.0 at every resolution they share. Timestamps are the one grammar difference that matters: 2.0 ignores them and answers only to shot numbers, 2.5 acts on them. Otherwise it shares 2.0's grammar (read slates-prompting-seedance for subject binding, camera and constraint vocabulary); this file covers what is different, plus the two hazards unique to 2.5 — the prompt-intent task classifier and the cost trap that comes with 30-second takes.
+description: How to prompt Seedance 2.5 and Seedance 2.5 Edit. Read before calling slates_generate_video with model seedance-2.5, or slates_edit_video with model seedance-2.5-edit. 2.5 is the DEFAULT video model (Eric, 2026-09-13) — against 2.0 it buys 30-second takes, 30 image references, audio-only references and INTEGER-SECOND TIMESTAMPS, and it gives up native 4K and costs more than 2.0 at every resolution they share. Timestamps are the one grammar difference that matters: 2.0 ignores them and answers only to shot numbers, 2.5 acts on them. Otherwise it shares 2.0's grammar (read slates-prompting-seedance for subject binding, camera and constraint vocabulary); this file covers what is different, plus the two hazards unique to 2.5 — the prompt-intent task classifier and the cost trap that comes with 30-second takes.
 ---
 
 # Seedance 2.5 — prompting
@@ -28,7 +28,7 @@ description: How to prompt Seedance 2.5 and Seedance 2.5 Edit. Read before calli
 - `[0-6] Wide shot, <Subject_1>@<Image_1> crosses an empty car park toward a idling van, slow track right. [6-12] Medium, she stops as the driver's window comes down. [12-18] Close-up, she looks off past the lens and does not answer. Rich details, natural colors. Keep it subtitle-free.`
 - `[0-10] A single continuous handheld follow behind a courier climbing a fire escape, rain. [10-20] She reaches the landing, turns, and the city opens behind her. Cinematic texture, soft lighting.`
 
-**Hard constraint:** it is the EXPENSIVE seat and it has NO 4K — 480p/720p/1080p only, and dearer than 2.0 at every resolution they share. It is a second seat, never an upgrade. Long takes multiply cost linearly: quote a 30-second take before you fire it.
+**Hard constraint:** it is the default AND the dearer seat, and it has NO 4K — 480p/720p/1080p only, dearer than 2.0 at every resolution they share. Long takes multiply cost linearly: quote a 30-second take before you fire it.
 <!-- @card:end -->
 
 <!-- @banned:start -->
@@ -70,11 +70,10 @@ So 2.5 does not replace 2.0; it sits beside it, and you pay for what it buys:
 | **Timestamps in the prompt** | **✗ — ignored; shot numbers only** | **✓ — integer seconds, acted on** |
 | Multi-view image as ONE subject reference | ✗ (not recommended) | **✓ (up to 5 subjects)** |
 | Video edit as its own task type | ✗ | **✓ (`seedance-2.5-edit`)** |
-| Default video model | **yes** | no |
+| Default video model | no | **yes** (since 2026-09-13) |
 
-**Route to 2.5 when the shot needs LENGTH, MANY REFERENCES, or an audio-only reference.
-Route to 2.0 when resolution matters at all** — which, for anything a client will see full-screen,
-is most of the time.
+**2.5 is the default. Route to 2.0 for 4K delivery, or when the same resolution has to be
+cheaper** — its 720p is $0.15/s against 2.5's $0.231/s.
 
 ---