@xiaohhhh1/canvas-agent 0.4.61 → 0.4.63

package/dist/video-intelligence/local-analysis.d.ts

@@ -30,11 +30,13 @@ type VideoArchiveUpload = {
     publicUrl: string;
     headers?: Record<string, string>;
     maxBytes?: number;
+    alreadyUploaded?: boolean;
+    downloadUrl?: string | null;
 };
 export declare function shouldUploadVideoArchive(input: {
     kind: "uploaded-mp4" | "tiktok";
     url: string;
-}, publicUrl: string): boolean;
+}, publicUrl: string, alreadyUploaded?: boolean): boolean;
 export declare class LocalVideoIntelligence {
     private readonly fastmoss;
     constructor(fastmoss: FastMossIntegration);

package/dist/video-intelligence/local-analysis.js

@@ -8,9 +8,10 @@ import { videoEvidenceTimestamps } from "../integrations/fastmoss.js";
 const ANALYSIS_TIMEOUT_MS = 10 * 60_000;
 const TRANSCRIPT_LANGUAGES = "en.*,es.*,zh.*,pt.*,fr.*,de.*,vi.*,th.*,id.*,ms.*,ja.*,ko.*";
 const LOCAL_ASR_MODEL = "onnx-community/whisper-base";
+const VIDEO_INTELLIGENCE_SCHEMA_VERSION = "commerce-video-intelligence-v5";
 let localAsrPipeline;
-export function shouldUploadVideoArchive(input, publicUrl) {
-    return input.kind !== "uploaded-mp4" || input.url !== publicUrl;
+export function shouldUploadVideoArchive(input, publicUrl, alreadyUploaded = false) {
+    return !alreadyUploaded && (input.kind !== "uploaded-mp4" || input.url !== publicUrl);
 }
 export class LocalVideoIntelligence {
     fastmoss;
@@ -18,7 +19,10 @@ export class LocalVideoIntelligence {
         this.fastmoss = fastmoss;
     }
     async archive(source, upload) {
-        const input = verifiedVideoLearningSource(source);
+        const verifiedInput = verifiedVideoLearningSource(source);
+        const input = upload?.downloadUrl
+            ? { ...verifiedInput, url: verifiedHttpsUrl(upload.downloadUrl, "站内下载地址无效") }
+            : verifiedInput;
         const uploadUrl = verifiedHttpsUrl(upload?.uploadUrl, "站内上传地址无效");
         const publicUrl = verifiedHttpsUrl(upload?.publicUrl, "站内视频地址无效");
         const maxBytes = Math.min(500 * 1024 * 1024, Math.max(1, Number(upload?.maxBytes || 100 * 1024 * 1024)));
@@ -28,7 +32,7 @@ export class LocalVideoIntelligence {
                 ? await downloadUploadedMp4(input.url, workDir, maxBytes)
                 : await downloadVideoArchive(input.url, workDir, maxBytes);
             const bytes = await readFile(downloaded.file);
-            if (shouldUploadVideoArchive(input, publicUrl)) {
+            if (shouldUploadVideoArchive(input, publicUrl, upload.alreadyUploaded)) {
                 const response = await fetch(uploadUrl, {
                     method: "PUT",
                     headers: { "Content-Type": "video/mp4" },
@@ -153,11 +157,11 @@ export function localVideoAnalysisPrompt(source, durationMs, transcript, attachm
             durationMs,
         })}\n\n` +
         `带时间码的口播字幕：\n${transcript}\n\n` +
-        `只返回一个 JSON 对象，不要 Markdown。字段必须是：schemaVersion="commerce-video-intelligence-v3"；durationMs；language；summary；` +
+        `只返回一个 JSON 对象，不要 Markdown。字段必须是：schemaVersion="${VIDEO_INTELLIGENCE_SCHEMA_VERSION}"；durationMs；language；summary；` +
         `sellingFormat{primary,label,secondary,rationale,evidence[{startMs,endMs,observation}],confidence}；` +
         `hook{startMs,endMs,visual,spokenText,onScreenText,patternInterrupt,openLoop}；productFirstSeenMs；` +
         `segments[{startMs,endMs,role,visual,spokenText,onScreenText,audio,editing,confidence}]（至少2段）；` +
-        `creativeMutationProfile{coreVisualPremise,mutationAxes[至少2项],culturalSignals[{market,signal,narrativeRole,aestheticRole,transferConditions,avoidStereotype,evidence[{startMs,endMs,observation}]}],firstFrameComposition,spectacleMechanism,productIntegration,transferableRule,culturalLimitations,doNotCopy,evidence[{startMs,endMs,observation}],confidence}；` +
+        `creativeMutationProfile{coreVisualPremise,mutationAxes[至少2项],culturalSignals[{market,signal,narrativeRole,aestheticRole,transferConditions,avoidStereotype,evidence[{startMs,endMs,observation}]}],firstFrameComposition,spectacleMechanism,productIntegration,captureProfile{subjectDominance,depthAndDensity,colorLightContrast,materialTexture,cameraEnergy,captureImperfections},transferableRule,culturalLimitations,doNotCopy,evidence[{startMs,endMs,observation}],confidence}；` +
         `mechanisms[{type,label,mechanism,whyItMayWork,evidence[{startMs,endMs,observation}],confidence,replicationRisk}]（type 仅 hook/conflict/proof/pacing/trust/product-reveal/offer-framing/cta/audio/visual-grammar/environment/visual-mutation/culture-code/spectacle）；` +
         `viralHypotheses[{hypothesis,supportingMetrics,supportingEvidence[{startMs,endMs,observation}],confounders,confidence}]；` +
         `nonReplicableFactors；complianceRisks；originalityGuidance{preserveMechanisms,mustRewrite,forbiddenCopying}。`;

package/dist/workflow/creative-candidates.d.ts

@@ -1,5 +1,5 @@
 type JsonSchema = Record<string, unknown>;
-export declare const FLOW_C_CREATIVE_CANDIDATE_CONTRACT_VERSION = "flow-c-creative-candidates-v3";
+export declare const FLOW_C_CREATIVE_CANDIDATE_CONTRACT_VERSION = "flow-c-creative-candidates-v4";
 export declare function flowCCreativeCandidateOutputSchema(count: number): JsonSchema;
 export declare function parseFlowCCreativeCandidateOutput(value: string, expectedOrdinals: number[]): Record<string, unknown>[];
 export {};

package/dist/workflow/creative-candidates.js

@@ -1,11 +1,13 @@
 import { assertStrictResponseSchema } from './script-output.js';
-export const FLOW_C_CREATIVE_CANDIDATE_CONTRACT_VERSION = 'flow-c-creative-candidates-v3';
+export const FLOW_C_CREATIVE_CANDIDATE_CONTRACT_VERSION = 'flow-c-creative-candidates-v4';
 const text = { type: 'string', minLength: 1 };
+const nullableText = { anyOf: [text, { type: 'null' }] };
 function object(properties) {
     return { type: 'object', properties, required: Object.keys(properties), additionalProperties: false };
 }
 function candidateSchema() {
     return object({
+        learnedTemplateId: nullableText,
         visualPremise: text,
         mutationAxes: { type: 'array', minItems: 2, maxItems: 4, items: text },
         culturalAnchors: {

package/dist/workflow/manager.d.ts

@@ -21,6 +21,10 @@ type ScriptRecord = {
 };
 type ReferenceStyleCard = {
     id?: unknown;
+    templateKind?: unknown;
+    templateProfile?: unknown;
+    modelFamily?: unknown;
+    sourceDurationSeconds?: unknown;
     visualPremisePattern?: unknown;
     mutationAxes?: unknown;
     culturePattern?: unknown;
@@ -31,6 +35,10 @@ type ReferenceStyleCard = {
     rhythmPattern?: unknown;
     capturePattern?: unknown;
     voiceTone?: unknown;
+    targetDurationPolicy?: unknown;
+    retimingRule?: unknown;
+    segmentRule?: unknown;
+    omniAdaptation?: unknown;
     sourceEvidenceTier?: unknown;
     truthBoundaries?: unknown;
     applicability?: {
@@ -51,6 +59,7 @@ type ProductInput = {
 type SelectedCandidate = {
     ordinal: number;
     productIndex: number;
+    learnedTemplateId?: string | null;
     visualPremise: string;
     mutationAxes: string[];
     culturalAnchors: Array<Record<string, unknown>>;

package/dist/workflow/manager.js

@@ -655,13 +655,14 @@ ${durationRules}
 }
 export function creativeCandidatePrompt(id, task, ordinals) {
     const products = relevantProductInputs(task, ordinals);
-    const styleCards = relevantStyleCards(task.reference_style_cards || [], products).map(compactReferenceStyleCard).filter(Boolean).slice(0, 6);
+    const styleCards = relevantStyleCards(task.reference_style_cards || [], products, task.market).map(compactReferenceStyleCard).filter(Boolean).slice(0, 6);
     const ledger = (task.creative_fingerprint_ledger || []).slice(-60);
     return `Flow C creative-candidate stage for handoff ${id}. Set contractVersion exactly to ${FLOW_C_CREATIVE_CANDIDATE_CONTRACT_VERSION}. Return exactly one group for each ordinal: ${ordinals.join(", ")}; mapping: ${scriptProductAssignments(task.product_quantities, ordinals)}.
-Market: ${task.market}. Product facts: ${compactJson(products, 12_000)}
+Market: ${task.market}. Target output duration: ${Number(task.duration_seconds || 10)} seconds. Product facts: ${compactJson(products, 12_000)}
 Optional learned style abstractions: ${compactJson(styleCards, 5_000)}
 Already accepted fingerprint ledger: ${compactJson(ledger, 8_000)}
 For each ordinal return exactly 6 short, auditable candidate cards. These are visible structured alternatives, not hidden reasoning. Vary the overall creative skeleton through open dimensions such as relationship/identity, scene mismatch, scale/quantity, group reaction, viewpoint, sensory texture and proof action; do not rotate a fixed template list.
+Set learnedTemplateId to the id of one supplied learned-video-structure card when its product/market fit is credible; otherwise set it to null. A fitting learned template has priority over free ideation. Preserve its hook-to-proof-to-purchase-reason causal structure, but re-time it to the current target duration instead of stretching, truncating or copying the source timeline. The template is model-neutral evidence: never output Seedance wording or source-specific people, dialogue, wardrobe, set or exact shots. The same learnedTemplateId may be used for multiple ordinals when useful, but each adapted candidate must still have truthful product-specific content, native VO intent and a meaningfully changed opening/proof execution. If the product has a non-empty user-authored creativeBrief, this candidate stage is bypassed entirely and no learned template may influence the script.
 Every card must be surprising but physically filmable and product-relevant. productProofAction must state one truthful intended-use action and the observable result that remains visible in the same scene. purchaseReason must state one concrete reason the supported result matters to a real target buyer; it is not a generic CTA and must not invent price, discount, scarcity, sales, inventory or unsupported quantified performance. productProofAction, purchaseReason and truthBoundary must follow supplied facts. For food, baby, medical/efficacy and personal-hygiene products, reject unhygienic display, fear marketing, dangerous use and unsupported promises.
 Every card must also contain a concrete visual execution card, not mood adjectives: firstFrameFocus names one dominant subject and its approximate 35%-85% frame share; visualContrast defines one readable scale/color/light/relationship contrast; sensoryTexture names truthful category-specific material evidence; motionPeak names the single peak physical instant; compositionLighting specifies foreground/midground/background, practical light direction and one plausible exposure/optical imperfection; localNativeDetail names observable local behavior/environment/aesthetic density with the same evidence discipline as culturalAnchors; antiFlatness names the exact generic catalogue treatment this concept must avoid. The firstFrame must pass a screenshot test: even without dialogue, a still image must show the unusual relationship, product relevance and depth hierarchy.
 Cultural anchors are optional (0–3). source must be learned-style-card, product-market-evidence, or conservative-everyday-detail. A learned-style-card anchor must cite the supplied card id in evidence. A product-market-evidence anchor must cite a concrete supplied product/market fact; if none exists, use conservative-everyday-detail and explicitly say it is ordinary context, not a custom claim. Never use flags, national costumes, royalty/public figures, religion, stereotypes or cultural mockery as shortcut hooks. Locality belongs in consumption context, natural interaction, language rhythm and aesthetic density.
@@ -670,7 +671,7 @@ creativeFingerprint must use five concise semantic labels: characterRelation, sc
 function compactReferenceStyleCard(value) {
     if (!value || typeof value !== "object")
         return "";
-    const fields = ["id", "visualPremisePattern", "mutationAxes", "culturePattern", "spectaclePattern", "productIntegrationPattern", "openingPattern", "proofPattern", "rhythmPattern", "capturePattern", "voiceTone", "sourceEvidenceTier"];
+    const fields = ["id", "templateKind", "templateProfile", "modelFamily", "sourceDurationSeconds", "visualPremisePattern", "mutationAxes", "culturePattern", "spectaclePattern", "productIntegrationPattern", "openingPattern", "proofPattern", "rhythmPattern", "capturePattern", "voiceTone", "targetDurationPolicy", "retimingRule", "segmentRule", "omniAdaptation", "sourceEvidenceTier"];
     const compact = Object.fromEntries(fields.flatMap((field) => {
         const text = String(value[field] || "").trim().replace(/\s+/g, " ").slice(0, 400);
         return text ? [[field, text]] : [];
@@ -681,13 +682,15 @@ function compactReferenceStyleCard(value) {
         Object.assign(compact, { applicability: { categories, markets } });
     return Object.keys(compact).length ? compact : null;
 }
-function relevantStyleCards(cards, products) {
+function relevantStyleCards(cards, products, market = "") {
     const categories = new Set(products.map((product) => String(product.category || "").trim().toLowerCase()).filter(Boolean));
-    if (!categories.size)
-        return cards.slice(0, 3);
     const matched = cards.filter((card) => {
         const allowed = Array.isArray(card.applicability?.categories) ? card.applicability.categories.map((item) => String(item || "").trim().toLowerCase()).filter(Boolean) : [];
-        return !allowed.length || allowed.includes("all") || allowed.includes("global") || allowed.some((item) => categories.has(item));
+        const markets = Array.isArray(card.applicability?.markets) ? card.applicability.markets.map((item) => String(item || "").trim().toLowerCase()).filter(Boolean) : [];
+        const categoryFit = !categories.size || !allowed.length || allowed.includes("all") || allowed.includes("global") || allowed.some((item) => categories.has(item));
+        const targetMarket = String(market || "").trim().toLowerCase();
+        const marketFit = !markets.length || markets.includes("all") || markets.includes("global") || markets.includes(targetMarket);
+        return categoryFit && marketFit;
     });
     return matched.length ? matched : [];
 }
@@ -710,6 +713,7 @@ function selectedCandidatePlan(value) {
         throw new Error("中心缺少选中的创意候选");
     return {
         visualPremise: value.visualPremise,
+        learnedTemplateId: value.learnedTemplateId || null,
         mutationAxes: value.mutationAxes,
         culturalAnchors: value.culturalAnchors,
         spectacleEscalation: value.spectacleEscalation,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@xiaohhhh1/canvas-agent",
-  "version": "0.4.61",
+  "version": "0.4.63",
   "type": "module",
   "main": "./dist/index.js",
   "types": "./dist/index.d.ts",