fix: restore visible auth form for douyin workbench

.env.example

@@ -2,15 +2,34 @@ DEFAULT_EXTERNAL_BASE_URL=http://test.hyzq.net:8081
 LOCAL_OPENAI_BASE_URL=http://127.0.0.1:8317/v1
 LOCAL_OPENAI_MODEL=GLM-5
 LOCAL_OPENAI_API_KEY=
-FASTGPT_BASE_URL=http://127.0.0.1:3000
+# Host-side collector runs can keep using N8N_BASE_URL.
-FASTGPT_DATASET_API_KEY=
+N8N_BASE_URL=http://127.0.0.1:5670
+# Dockerized collector should use the internal n8n service address.
+COLLECTOR_N8N_BASE_URL=http://n8n:5678
+N8N_ANALYSIS_WEBHOOK_PATH=/webhook/storyforge-analysis
+N8N_REAL_CUT_WEBHOOK_PATH=/webhook/storyforge-real-cut
+N8N_AI_VIDEO_WEBHOOK_PATH=/webhook/storyforge-ai-video
+N8N_CONTENT_SOURCE_SYNC_WEBHOOK_PATH=/webhook/storyforge-content-source-sync
+ORCHESTRATOR_SHARED_SECRET=storyforge-local-secret
+CUTVIDEO_BASE_URL=
+CUTVIDEO_API_KEY=
+CUTVIDEO_BASE_CONFIG=example.job.yaml
+CUTVIDEO_POLL_INTERVAL_SEC=10
+CUTVIDEO_MAX_WAIT_SEC=1800
+CUTVIDEO_UPLOAD_TIMEOUT_SEC=1800
+HUOBAO_BASE_URL=http://127.0.0.1:5678
+HUOBAO_POLL_INTERVAL_SEC=10
+HUOBAO_MAX_WAIT_SEC=900
 YTDLP_BIN=yt-dlp
 FFMPEG_BIN=ffmpeg
 WHISPER_BIN=
 WHISPER_MODEL=./data/collector/models/ggml-base.en.bin
-POSTGRES_DB=fastgpt
+ASR_HTTP_BASE_URL=
-POSTGRES_USER=postgres
+ASR_HTTP_TRANSCRIBE_PATH=/transcribe
-POSTGRES_PASSWORD=postgres
+ASR_HTTP_FIELD_NAME=wav
-MINIO_ROOT_USER=minioadmin
+ASR_HTTP_TIMEOUT_SEC=120
-MINIO_ROOT_PASSWORD=minioadmin
+N8N_IMAGE=docker.n8n.io/n8nio/n8n:latest
+WEBHOOK_URL=http://127.0.0.1:5670/
+GENERIC_TIMEZONE=Asia/Shanghai
+TZ=Asia/Shanghai
 CLIPROXY_IMAGE=storyforge/cli-proxy-api:patched

.gitignore

@@ -20,9 +20,13 @@ build/
 .kotlin/
 **/.gradle/
 **/.kotlin/
+node_modules/
+**/node_modules/
 
 # Runtime data and artifacts
 data/
+!android-app/app/src/main/java/com/aiglasses/app/data/
+!android-app/app/src/main/java/com/aiglasses/app/data/**
 output/
 *.log
 

README.md

@@ -5,36 +5,143 @@ StoryForge 现在拆成独立项目目录，和 `AI-glasses` 分开维护。
 ## 目录
 
 - `android-app/`：StoryForge Android 客户端
-- `collector-service/`：FastAPI 后端，提供登录、审批、素材导入、知识库、智能体和 OTA
+- `collector-service/`：FastAPI 后端，负责用户体系、项目、Agent、任务、内容分析和对外能力接入
-- `docker-compose.yml`：本地 FastGPT / collector / 基础依赖编排
+- `n8n/`：工作流导出文件，作为流程编排中枢
+- `docker-compose.yml`：本地 `collector + n8n + cli-proxy-api` 编排
 - `Common/`：项目约束和架构说明
 - `data/collector/`：SQLite、任务文件、下载产物
+- `docs/`：审计、实施计划、联调说明、当前 MVP 状态
 
 ## Android
 
 ```bash
-cd /Users/kris/code/StoryForge/android-app
+cd /Users/kris/code/StoryForge-gitea/android-app
 ./gradlew assembleDebug
 ```
 
+## Douyin Browser Capture
+
+```bash
+cd /Users/kris/code/StoryForge-gitea
+./scripts/start_douyin_workbench.sh
+```
+
+业务页：
+
+```text
+http://127.0.0.1:3618/workbench
+```
+
+完整采集控制台：
+
+```text
+http://127.0.0.1:3618
+```
+
+常用脚本：
+
+```bash
+./scripts/start_douyin_workbench.sh
+./scripts/status_douyin_workbench.sh
+./scripts/stop_douyin_workbench.sh
+./scripts/cleanup_debug_ui.sh
+```
+
+如果第一次使用，还需要先安装浏览器依赖：
+
+```bash
+cd /Users/kris/code/StoryForge-gitea/scripts/douyin-browser-capture
+npm install
+npx playwright install chromium
+```
+
+当前本地页面已经拆成两个入口：
+
+- `/workbench`：业务优先的 `Douyin Workbench`，可直接查看账号列表、商业化账号分析、快照详情、相似账号和对标关系
+- `/`：完整浏览器辅助采集控制台，同时保留工作台能力
+- 作品工作台支持按 `高分作品 / 最新作品 / 全部作品` 切换，并可按综合分、受欢迎程度、商业价值、发布时间、播放、点赞、分享、评论排序
+- 作品列表支持 `视频 / 图文` 类型筛选，并可直接打开原作品链接
+- 高分作品支持自动化分析，每条作品卡片下都会展示商业判断、复刻计划、运营动作和风险提醒
+
+或者继续用命令行：
+
+```bash
+cd /Users/kris/code/StoryForge-gitea/scripts/douyin-browser-capture
+npm run capture -- \
+  --profile-url https://www.douyin.com/user/your_account \
+  --storyforge-username kris \
+  --storyforge-password 'Asd123456.'
+```
+
+说明：
+
+- 这是“真实浏览器 + 人工登录/过挑战 + 自动提取 + 回写 StoryForge”的辅助采集工具
+- 默认输出到 `output/playwright/douyin/`
+- 本地控制台模式会把每次运行保存到 `output/playwright/douyin/control-panel/`
+- 控制台支持“开始采集 -> 浏览器登录 -> 网页点继续 -> 自动同步”的点击式流程
+- 详细说明见 `scripts/douyin-browser-capture/README.md`
+
 ## Collector Service
 
 ```bash
-cd /Users/kris/code/StoryForge/collector-service
+cd /Users/kris/code/StoryForge-gitea/collector-service
 python3 -m venv .venv
 source .venv/bin/activate
 pip install -r requirements.txt
 uvicorn app.main:app --host 0.0.0.0 --port 8081 --reload
 ```
 
+## Docker Compose
+
+```bash
+cd /Users/kris/code/StoryForge-gitea
+cp .env.example .env
+docker compose up -d --build
+```
+
+如果 `collector` 跑在 Docker 里，建议保留：
+
+```bash
+COLLECTOR_N8N_BASE_URL=http://n8n:5678
+```
+
+如果你单独在宿主机启动 `collector-service`，它读取的仍然是：
+
+```bash
+N8N_BASE_URL=http://127.0.0.1:5670
+```
+
+默认会启动：
+
+- `collector-service`：`http://127.0.0.1:8081`
+- `n8n`：`http://127.0.0.1:5670`
+- `cli-proxy-api`：`http://127.0.0.1:8317`
+
 默认会创建最高权限账号：
 
 - `kris`
 - `Asd123456.`
 
+## 当前架构
+
+- `collector-service` 负责：
+  - 用户账号、多项目、多 Agent、多任务、多内容源数据边界
+  - 调用下载器、本地 ASR、本机 OpenAI 兼容模型
+  - 调用 Windows `cutvideo` 和 `huobao-drama`
+  - 持久化任务、分镜、分析结果、事件日志
+- `n8n` 负责：
+  - 触发 `analysis_pipeline`
+  - 触发 `content_source_sync_pipeline`
+  - 触发 `real_cut_pipeline`
+  - 触发 `ai_video_pipeline`
+- FastGPT 已从主流程设计中移除，不再作为运行时依赖
+
 ## 说明
 
 - 新注册账号默认 `pending`
 - 主管理员审批后才可使用核心业务接口
-- 素材入口支持文字、视频链接、视频上传
+- 支持 `user -> project -> knowledge base / assistant(agent) / job / content source` 的多租户边界
-- 可选对接本机 OpenAI 兼容模型服务和 FastGPT 数据集 API
+- 素材入口支持文字、视频链接、视频上传；内容源账号通过 `content_sources` 建模持久化，并可派生父子分析任务
+- `cutvideo` 继续运行在 Windows 机器，本系统通过 API 调度
+- `huobao-drama` 继续作为 AI 生成视频主链的核心引擎
+- 详细审计、阶段计划和联调步骤见 `docs/`

android-app/app/src/main/java/com/aiglasses/app/data/ApiClient.kt

@@ -0,0 +1,50 @@
+package com.aiglasses.app.data
+
+import kotlinx.serialization.json.Json
+import kotlinx.serialization.ExperimentalSerializationApi
+import java.util.concurrent.TimeUnit
+import okhttp3.MediaType.Companion.toMediaType
+import okhttp3.Protocol
+import okhttp3.OkHttpClient
+import okhttp3.Request
+import okhttp3.logging.HttpLoggingInterceptor
+import retrofit2.Retrofit
+import retrofit2.create
+import com.jakewharton.retrofit2.converter.kotlinx.serialization.asConverterFactory
+
+object ApiClient {
+    @OptIn(ExperimentalSerializationApi::class)
+    val json = Json {
+        ignoreUnknownKeys = true
+        explicitNulls = false
+    }
+
+    inline fun <reified T : Any> createService(baseUrl: String): T {
+        val logging = HttpLoggingInterceptor().apply {
+            level = HttpLoggingInterceptor.Level.BODY
+        }
+        val client = OkHttpClient.Builder()
+            .protocols(listOf(Protocol.HTTP_1_1))
+            .connectTimeout(12, TimeUnit.SECONDS)
+            .readTimeout(20, TimeUnit.SECONDS)
+            .writeTimeout(20, TimeUnit.SECONDS)
+            .callTimeout(25, TimeUnit.SECONDS)
+            .addInterceptor { chain ->
+                val request: Request = chain.request().newBuilder()
+                    .header("Connection", "close")
+                    .build()
+                chain.proceed(request)
+            }
+            .addInterceptor(logging)
+            .build()
+
+        val normalizedBaseUrl = if (baseUrl.endsWith("/")) baseUrl else "$baseUrl/"
+
+        return Retrofit.Builder()
+            .baseUrl(normalizedBaseUrl)
+            .client(client)
+            .addConverterFactory(json.asConverterFactory("application/json".toMediaType()))
+            .build()
+            .create<T>()
+    }
+}

android-app/app/src/main/java/com/aiglasses/app/data/ApiService.kt

@@ -0,0 +1,154 @@
+package com.aiglasses.app.data
+
+import retrofit2.http.Body
+import retrofit2.http.GET
+import retrofit2.http.Header
+import retrofit2.http.POST
+import retrofit2.http.Path
+import retrofit2.http.Query
+
+interface ApiService {
+    @GET("/healthz")
+    suspend fun healthz(): ApiEnvelope<HealthzData>
+
+    @POST("/api/v1/devices/bind-confirm")
+    suspend fun bindConfirm(
+        @Body request: BindConfirmRequest
+    ): ApiEnvelope<BindConfirmData>
+
+    @POST("/api/v1/ai/sessions")
+    suspend fun createSession(
+        @Header("Idempotency-Key") idempotencyKey: String?,
+        @Body request: CreateSessionRequest
+    ): ApiEnvelope<SessionData>
+
+    @POST("/api/v1/ai/sessions/{sessionId}/stop")
+    suspend fun stopSession(
+        @Path("sessionId") sessionId: String,
+        @Body request: StopSessionRequest
+    ): ApiEnvelope<StopSessionData>
+
+    @POST("/api/v1/ai/sessions/{sessionId}/heartbeat")
+    suspend fun heartbeat(
+        @Path("sessionId") sessionId: String,
+        @Body request: HeartbeatRequest
+    ): ApiEnvelope<HeartbeatData>
+
+    @GET("/api/v1/devices/{deviceId}/status")
+    suspend fun getDeviceStatus(
+        @Path("deviceId") deviceId: String
+    ): ApiEnvelope<DeviceStatusData>
+
+    @POST("/api/v1/events")
+    suspend fun postEvent(
+        @Body request: ClientEventRequest
+    ): ApiEnvelope<EventSavedData>
+
+    @POST("/api/v1/events/batch")
+    suspend fun postEventsBatch(
+        @Body request: ClientEventBatchRequest
+    ): ApiEnvelope<EventsBatchSavedData>
+
+    @POST("/api/v1/ai/sessions/{sessionId}/messages")
+    suspend fun sendMessage(
+        @Path("sessionId") sessionId: String,
+        @Body request: SessionMessageRequest
+    ): ApiEnvelope<ProviderActionData>
+
+    @POST("/api/v1/ai/sessions/{sessionId}/scene-role")
+    suspend fun switchRole(
+        @Path("sessionId") sessionId: String,
+        @Body request: SwitchRoleRequest
+    ): ApiEnvelope<ProviderActionData>
+
+    @POST("/api/v1/ai/sessions/{sessionId}/interrupt")
+    suspend fun interruptSession(
+        @Path("sessionId") sessionId: String,
+        @Body request: SessionInterruptRequest
+    ): ApiEnvelope<ProviderActionData>
+
+    @GET("/api/v1/baidu/activation/query")
+    suspend fun activationQuery(
+        @Query("deviceId") deviceId: String,
+        @Query("appId") appId: String? = null
+    ): ApiEnvelope<ActivationQueryData>
+
+    @POST("/api/v1/licenses/reload")
+    suspend fun reloadLicenses(): ApiEnvelope<ReloadLicensesData>
+
+    @GET("/api/v1/admin/overview")
+    suspend fun adminOverview(): ApiEnvelope<AdminOverviewData>
+
+    @GET("/api/v1/app/update/latest")
+    suspend fun appUpdateLatest(
+        @Query("platform") platform: String = "android",
+        @Query("channel") channel: String = "stable",
+        @Query("currentVersionCode") currentVersionCode: Int
+    ): ApiEnvelope<AppUpdateLatestData>
+
+    @GET("/v2/douyin/accounts")
+    suspend fun listDouyinAccounts(): ApiEnvelope<List<DouyinAccountSummary>>
+
+    @POST("/v2/douyin/accounts/sync")
+    suspend fun syncDouyinAccount(
+        @Body request: DouyinAccountSyncRequest
+    ): ApiEnvelope<DouyinAccountWorkspace>
+
+    @GET("/v2/douyin/accounts/{accountId}")
+    suspend fun getDouyinAccount(
+        @Path("accountId") accountId: String
+    ): ApiEnvelope<DouyinAccountWorkspace>
+
+    @GET("/v2/douyin/accounts/{accountId}/workspace")
+    suspend fun getDouyinWorkspace(
+        @Path("accountId") accountId: String
+    ): ApiEnvelope<DouyinAccountWorkspace>
+
+    @GET("/v2/douyin/accounts/{accountId}/snapshots")
+    suspend fun listDouyinSnapshots(
+        @Path("accountId") accountId: String
+    ): ApiEnvelope<List<DouyinSnapshotSummary>>
+
+    @GET("/v2/douyin/accounts/{accountId}/snapshots/{snapshotId}")
+    suspend fun getDouyinSnapshot(
+        @Path("accountId") accountId: String,
+        @Path("snapshotId") snapshotId: String
+    ): ApiEnvelope<DouyinSnapshotDetail>
+
+    @GET("/v2/douyin/accounts/{accountId}/creator-fields")
+    suspend fun getDouyinCreatorFields(
+        @Path("accountId") accountId: String
+    ): ApiEnvelope<DouyinSnapshotDetail>
+
+    @POST("/v2/douyin/accounts/{accountId}/analysis")
+    suspend fun analyzeDouyinAccount(
+        @Path("accountId") accountId: String,
+        @Body request: DouyinAccountAnalysisRequest
+    ): ApiEnvelope<DouyinAnalysisResult>
+
+    @GET("/v2/douyin/accounts/{accountId}/analysis-reports")
+    suspend fun listDouyinAnalysisReports(
+        @Path("accountId") accountId: String
+    ): ApiEnvelope<List<DouyinAnalysisReport>>
+
+    @POST("/v2/douyin/similar-searches")
+    suspend fun createDouyinSimilarSearch(
+        @Body request: DouyinSimilarSearchRequest
+    ): ApiEnvelope<DouyinSimilaritySearchResult>
+
+    @GET("/v2/douyin/similar-searches/{searchId}")
+    suspend fun getDouyinSimilarSearch(
+        @Path("searchId") searchId: String
+    ): ApiEnvelope<DouyinSimilaritySearchDetail>
+
+    @GET("/v2/douyin/accounts/{accountId}/benchmark-links")
+    suspend fun listDouyinBenchmarkLinks(
+        @Path("accountId") accountId: String
+    ): ApiEnvelope<List<DouyinLinkedAccount>>
+
+    @POST("/v2/douyin/accounts/{accountId}/benchmark-links")
+    suspend fun createDouyinBenchmarkLinks(
+        @Path("accountId") accountId: String,
+        @Body request: DouyinBenchmarkLinkRequest
+    ): ApiEnvelope<DouyinBenchmarkLinkResult>
+}

android-app/app/src/main/java/com/aiglasses/app/data/BackendRepository.kt

@@ -0,0 +1,276 @@
+package com.aiglasses.app.data
+
+import java.util.UUID
+
+class BackendRepository(private var baseUrl: String) {
+    private var api: ApiService = ApiClient.createService(baseUrl)
+
+    fun updateBaseUrl(url: String) {
+        if (url != baseUrl) {
+            baseUrl = url
+            api = ApiClient.createService(baseUrl)
+        }
+    }
+
+    suspend fun bindDevice(deviceId: String, userId: String): BindConfirmData {
+        val resp = api.bindConfirm(BindConfirmRequest(deviceId = deviceId, appUserId = userId))
+        return resp.data
+    }
+
+    suspend fun healthz(): HealthzData {
+        val resp = api.healthz()
+        return resp.data
+    }
+
+    suspend fun createSession(deviceId: String, userId: String): SessionData {
+        val idempotencyKey = "app-${UUID.randomUUID()}"
+        val resp = api.createSession(
+            idempotencyKey = idempotencyKey,
+            request = CreateSessionRequest(deviceId = deviceId, appUserId = userId)
+        )
+        return resp.data
+    }
+
+    suspend fun stopSession(sessionId: String): StopSessionData {
+        val resp = api.stopSession(sessionId, StopSessionRequest())
+        return resp.data
+    }
+
+    suspend fun heartbeat(sessionId: String): HeartbeatData {
+        val resp = api.heartbeat(sessionId, HeartbeatRequest())
+        return resp.data
+    }
+
+    suspend fun getDeviceStatus(deviceId: String): DeviceStatusData {
+        val resp = api.getDeviceStatus(deviceId)
+        return resp.data
+    }
+
+    suspend fun postDemoEvent(deviceId: String, sessionId: String?): EventSavedData {
+        return postEvent(
+            deviceId = deviceId,
+            sessionId = sessionId,
+            eventType = "APP_DEBUG_PING",
+            eventLevel = "INFO",
+            payload = mapOf("source" to "android")
+        )
+    }
+
+    suspend fun postEvent(
+        deviceId: String,
+        sessionId: String?,
+        eventType: String,
+        eventLevel: String = "INFO",
+        payload: Map<String, String> = emptyMap()
+    ): EventSavedData {
+        val resp = api.postEvent(
+            ClientEventRequest(
+                sessionId = sessionId,
+                deviceId = deviceId,
+                eventType = eventType,
+                eventLevel = eventLevel,
+                payload = payload
+            )
+        )
+        return resp.data
+    }
+
+    suspend fun postEventsBatch(events: List<ClientEventRequest>): EventsBatchSavedData {
+        val resp = api.postEventsBatch(ClientEventBatchRequest(events = events))
+        return resp.data
+    }
+
+    suspend fun sendMessage(sessionId: String, message: String): ProviderActionData {
+        val resp = api.sendMessage(
+            sessionId = sessionId,
+            request = SessionMessageRequest(message = message)
+        )
+        return resp.data
+    }
+
+    suspend fun sendVoiceMessage(
+        sessionId: String,
+        pcmBase64: String,
+        sampleRate: Int,
+        durationMs: Int,
+        rms: Int
+    ): ProviderActionData {
+        val resp = api.sendMessage(
+            sessionId = sessionId,
+            request = SessionMessageRequest(
+                message = "voice_chunk",
+                messageType = "voice",
+                extra = mapOf(
+                    "audio_base64" to pcmBase64,
+                    "audio_format" to "pcm_s16le",
+                    "sample_rate" to sampleRate.toString(),
+                    "channels" to "1",
+                    "duration_ms" to durationMs.toString(),
+                    "rms" to rms.toString(),
+                    "encoding" to "base64"
+                )
+            )
+        )
+        return resp.data
+    }
+
+    suspend fun sendVisionMessage(
+        sessionId: String,
+        message: String,
+        imageBase64: String,
+        width: Int,
+        height: Int,
+        bytes: Int
+    ): ProviderActionData {
+        val resp = api.sendMessage(
+            sessionId = sessionId,
+            request = SessionMessageRequest(
+                message = message,
+                messageType = "text",
+                extra = mapOf(
+                    "image_base64" to imageBase64,
+                    "imageBase64" to imageBase64,
+                    "image" to imageBase64,
+                    "resource_base64" to imageBase64,
+                    "resourceBase64" to imageBase64,
+                    "image_encoding" to "base64",
+                    "imageEncoding" to "base64",
+                    "encoding" to "base64",
+                    "image_format" to "jpeg",
+                    "imageFormat" to "jpeg",
+                    "mime_type" to "image/jpeg",
+                    "mimeType" to "image/jpeg",
+                    "image_width" to width.toString(),
+                    "imageWidth" to width.toString(),
+                    "image_height" to height.toString(),
+                    "imageHeight" to height.toString(),
+                    "image_bytes" to bytes.toString(),
+                    "imageBytes" to bytes.toString(),
+                    "resource_type" to "image",
+                    "resourceType" to "image",
+                    "camera_source" to "android_phone",
+                    "multimodal" to "true",
+                    "with_vision" to "1"
+                )
+            )
+        )
+        return resp.data
+    }
+
+    suspend fun switchRole(sessionId: String, sceneId: String, roleId: String): ProviderActionData {
+        val resp = api.switchRole(
+            sessionId = sessionId,
+            request = SwitchRoleRequest(sceneId = sceneId, roleId = roleId)
+        )
+        return resp.data
+    }
+
+    suspend fun interrupt(
+        sessionId: String,
+        interrupt: Boolean,
+        extra: Map<String, String> = emptyMap()
+    ): ProviderActionData {
+        val resp = api.interruptSession(
+            sessionId = sessionId,
+            request = SessionInterruptRequest(interrupt = interrupt, extra = extra)
+        )
+        return resp.data
+    }
+
+    suspend fun activationQuery(deviceId: String): ActivationQueryData {
+        val resp = api.activationQuery(deviceId = deviceId)
+        return resp.data
+    }
+
+    suspend fun reloadLicenses(): ReloadLicensesData {
+        val resp = api.reloadLicenses()
+        return resp.data
+    }
+
+    suspend fun adminOverview(): AdminOverviewData {
+        val resp = api.adminOverview()
+        return resp.data
+    }
+
+    suspend fun appUpdateLatest(currentVersionCode: Int): AppUpdateLatestData {
+        val resp = api.appUpdateLatest(
+            platform = "android",
+            channel = "stable",
+            currentVersionCode = currentVersionCode
+        )
+        return resp.data
+    }
+
+    suspend fun listDouyinAccounts(): List<DouyinAccountSummary> {
+        val resp = api.listDouyinAccounts()
+        return resp.data
+    }
+
+    suspend fun syncDouyinAccount(request: DouyinAccountSyncRequest): DouyinAccountWorkspace {
+        val resp = api.syncDouyinAccount(request)
+        return resp.data
+    }
+
+    suspend fun getDouyinAccount(accountId: String): DouyinAccountWorkspace {
+        val resp = api.getDouyinAccount(accountId)
+        return resp.data
+    }
+
+    suspend fun getDouyinWorkspace(accountId: String): DouyinAccountWorkspace {
+        val resp = api.getDouyinWorkspace(accountId)
+        return resp.data
+    }
+
+    suspend fun listDouyinSnapshots(accountId: String): List<DouyinSnapshotSummary> {
+        val resp = api.listDouyinSnapshots(accountId)
+        return resp.data
+    }
+
+    suspend fun getDouyinSnapshot(accountId: String, snapshotId: String): DouyinSnapshotDetail {
+        val resp = api.getDouyinSnapshot(accountId, snapshotId)
+        return resp.data
+    }
+
+    suspend fun getDouyinCreatorFields(accountId: String): DouyinSnapshotDetail {
+        val resp = api.getDouyinCreatorFields(accountId)
+        return resp.data
+    }
+
+    suspend fun analyzeDouyinAccount(
+        accountId: String,
+        request: DouyinAccountAnalysisRequest
+    ): DouyinAnalysisResult {
+        val resp = api.analyzeDouyinAccount(accountId, request)
+        return resp.data
+    }
+
+    suspend fun listDouyinAnalysisReports(accountId: String): List<DouyinAnalysisReport> {
+        val resp = api.listDouyinAnalysisReports(accountId)
+        return resp.data
+    }
+
+    suspend fun createDouyinSimilarSearch(
+        request: DouyinSimilarSearchRequest
+    ): DouyinSimilaritySearchResult {
+        val resp = api.createDouyinSimilarSearch(request)
+        return resp.data
+    }
+
+    suspend fun getDouyinSimilarSearch(searchId: String): DouyinSimilaritySearchDetail {
+        val resp = api.getDouyinSimilarSearch(searchId)
+        return resp.data
+    }
+
+    suspend fun listDouyinBenchmarkLinks(accountId: String): List<DouyinLinkedAccount> {
+        val resp = api.listDouyinBenchmarkLinks(accountId)
+        return resp.data
+    }
+
+    suspend fun createDouyinBenchmarkLinks(
+        accountId: String,
+        request: DouyinBenchmarkLinkRequest
+    ): DouyinBenchmarkLinkResult {
+        val resp = api.createDouyinBenchmarkLinks(accountId, request)
+        return resp.data
+    }
+}

android-app/app/src/main/java/com/aiglasses/app/data/Models.kt

@@ -0,0 +1,540 @@
+package com.aiglasses.app.data
+
+import kotlinx.serialization.SerialName
+import kotlinx.serialization.Serializable
+import kotlinx.serialization.json.JsonElement
+import kotlinx.serialization.json.JsonObject
+
+@Serializable
+data class ApiEnvelope<T>(
+    val code: Int,
+    val message: String,
+    val traceId: String,
+    val data: T
+)
+
+@Serializable
+data class HealthzData(
+    val status: String = "",
+    val env: String = "",
+    val dbPath: String = ""
+)
+
+@Serializable
+data class BindConfirmRequest(
+    val deviceId: String,
+    val deviceSn: String? = null,
+    val deviceModel: String? = null,
+    val deviceFwVer: String? = null,
+    val appUserId: String
+)
+
+@Serializable
+data class BindConfirmData(
+    val bindStatus: String,
+    val licenseStatus: String,
+    val licenseKeyMasked: String,
+    val licenseKey: String = ""
+)
+
+@Serializable
+data class CreateSessionRequest(
+    val deviceId: String,
+    val appUserId: String,
+    val scene: String = "voice_assistant",
+    val language: String = "zh-CN",
+    val clientTs: Long? = null
+)
+
+@Serializable
+data class SessionData(
+    val sessionId: String,
+    val provider: String,
+    val cid: String,
+    val token: String,
+    val tokenExpireAt: Long,
+    val wsUrl: String,
+    val heartbeatSec: Int,
+    val appId: String = "",
+    val context: String = "",
+    val realtimeWsUrl: String = ""
+)
+
+@Serializable
+data class StopSessionRequest(
+    val reason: String = "user_stop"
+)
+
+@Serializable
+data class StopSessionData(
+    val sessionStatus: String
+)
+
+@Serializable
+data class HeartbeatRequest(
+    val networkType: String? = "wifi",
+    val bleRssi: Int? = null
+)
+
+@Serializable
+data class HeartbeatData(
+    val sessionStatus: String,
+    val heartbeatAt: Long
+)
+
+@Serializable
+data class ClientEventRequest(
+    val sessionId: String? = null,
+    val deviceId: String,
+    val eventType: String,
+    val eventLevel: String = "INFO",
+    val payload: Map<String, String> = emptyMap(),
+    val ts: Long? = null
+)
+
+@Serializable
+data class ClientEventBatchRequest(
+    val events: List<ClientEventRequest> = emptyList()
+)
+
+@Serializable
+data class EventSavedData(
+    val saved: Boolean
+)
+
+@Serializable
+data class EventsBatchSavedData(
+    val saved: Int = 0
+)
+
+@Serializable
+data class SessionMessageRequest(
+    val message: String,
+    val messageType: String = "text",
+    val messageId: String? = null,
+    val extra: Map<String, String> = emptyMap()
+)
+
+@Serializable
+data class ProviderActionData(
+    val status: String = "UNKNOWN",
+    val detail: String = "",
+    val asrText: String = "",
+    val ttsText: String = "",
+    val audioBase64: String = "",
+    val audioUrl: String = ""
+)
+
+@Serializable
+data class SwitchRoleRequest(
+    val sceneId: String,
+    val roleId: String,
+    val extra: Map<String, String> = emptyMap()
+)
+
+@Serializable
+data class SessionInterruptRequest(
+    val interrupt: Boolean = true,
+    val extra: Map<String, String> = emptyMap()
+)
+
+@Serializable
+data class DeviceStatusData(
+    val bindStatus: String,
+    val licenseStatus: String,
+    val activeSessionId: String? = null,
+    val activeSessionStatus: String? = null
+)
+
+@Serializable
+data class AdminStats(
+    val totalDevices: Int = 0,
+    val totalSessions: Int = 0,
+    val runningSessions: Int = 0,
+    val totalLicenses: Int = 0,
+    val usedLicenseQuota: Int = 0
+)
+
+@Serializable
+data class BaiduInfo(
+    val mode: String = "-",
+    val generateConfigured: Boolean = false,
+    val stopConfigured: Boolean = false,
+    val activationQueryConfigured: Boolean = false
+)
+
+@Serializable
+data class AdminOverviewData(
+    val stats: AdminStats = AdminStats(),
+    val baidu: BaiduInfo = BaiduInfo()
+)
+
+@Serializable
+data class ActivationQueryData(
+    val deviceId: String = "",
+    val appId: String = "",
+    val status: String = "UNKNOWN",
+    val detail: String = "",
+    val licenseKeyMasked: String = ""
+)
+
+@Serializable
+data class ReloadLicensesData(
+    val inserted: Int = 0
+)
+
+@Serializable
+data class AppUpdateLatestData(
+    val platform: String = "android",
+    val channel: String = "stable",
+    val hasUpdate: Boolean = false,
+    val latestVersionCode: Int = 0,
+    val latestVersionName: String = "",
+    val minSupportedCode: Int = 0,
+    val downloadUrl: String = "",
+    val apkSha256: String = "",
+    val releaseNotes: String = "",
+    val forceUpdate: Boolean = false,
+    val publishedAt: Long = 0L
+)
+
+@Serializable
+data class DouyinManualPageCaptureRequest(
+    val url: String = "",
+    val title: String = "",
+    val payload: JsonObject = JsonObject(emptyMap())
+)
+
+@Serializable
+data class DouyinAccountSyncRequest(
+    @SerialName("profile_url")
+    val profileUrl: String = "",
+    @SerialName("session_cookie")
+    val sessionCookie: String = "",
+    @SerialName("creator_center_urls")
+    val creatorCenterUrls: List<String> = emptyList(),
+    @SerialName("manual_profile_payload")
+    val manualProfilePayload: JsonObject? = null,
+    @SerialName("manual_creator_pages")
+    val manualCreatorPages: List<DouyinManualPageCaptureRequest> = emptyList(),
+    @SerialName("manual_work_payloads")
+    val manualWorkPayloads: List<JsonObject> = emptyList(),
+    @SerialName("discovery_note")
+    val discoveryNote: String = ""
+)
+
+@Serializable
+data class DouyinProfileStats(
+    val followers: Double = 0.0,
+    val following: Double = 0.0,
+    val likes: Double = 0.0,
+    val videos: Double = 0.0
+)
+
+@Serializable
+data class DouyinVideoStats(
+    val play: Double = 0.0,
+    val like: Double = 0.0,
+    val comment: Double = 0.0,
+    val share: Double = 0.0,
+    val collect: Double = 0.0
+)
+
+@Serializable
+data class DouyinVideoSummaryItem(
+    @SerialName("aweme_id")
+    val awemeId: String = "",
+    val title: String = "",
+    val description: String = "",
+    val tags: List<String> = emptyList(),
+    @SerialName("published_at")
+    val publishedAt: String? = null,
+    val stats: DouyinVideoStats = DouyinVideoStats()
+)
+
+@Serializable
+data class DouyinVideoSummary(
+    val count: Int = 0,
+    @SerialName("top_tags")
+    val topTags: List<String> = emptyList(),
+    @SerialName("avg_play")
+    val avgPlay: Double = 0.0,
+    @SerialName("avg_like")
+    val avgLike: Double = 0.0,
+    @SerialName("avg_comment")
+    val avgComment: Double = 0.0,
+    @SerialName("avg_share")
+    val avgShare: Double = 0.0,
+    val videos: List<DouyinVideoSummaryItem> = emptyList()
+)
+
+@Serializable
+data class DouyinAccountSummary(
+    val id: String = "",
+    val nickname: String = "",
+    val signature: String = "",
+    @SerialName("profile_url")
+    val profileUrl: String = "",
+    @SerialName("avatar_url")
+    val avatarUrl: String = "",
+    @SerialName("sec_uid")
+    val secUid: String = "",
+    @SerialName("douyin_id")
+    val douyinId: String = "",
+    @SerialName("profile_stats")
+    val profileStats: DouyinProfileStats = DouyinProfileStats(),
+    val tags: List<String> = emptyList(),
+    val keywords: List<String> = emptyList(),
+    @SerialName("sync_status")
+    val syncStatus: String = "",
+    @SerialName("video_summary")
+    val videoSummary: DouyinVideoSummary = DouyinVideoSummary()
+)
+
+@Serializable
+data class DouyinSnapshotSummary(
+    val id: String = "",
+    @SerialName("snapshot_type")
+    val snapshotType: String = "",
+    @SerialName("source_url")
+    val sourceUrl: String = "",
+    @SerialName("field_count")
+    val fieldCount: Int = 0,
+    @SerialName("collected_at")
+    val collectedAt: String = "",
+    val summary: JsonObject = JsonObject(emptyMap())
+)
+
+@Serializable
+data class DouyinModelProfileSummary(
+    val id: String = "",
+    val name: String = "",
+    @SerialName("model_name")
+    val modelName: String = "",
+    @SerialName("base_url")
+    val baseUrl: String = "",
+    @SerialName("is_default")
+    val isDefault: Boolean = false
+)
+
+@Serializable
+data class DouyinAnalysisSuggestion(
+    val id: String = "",
+    @SerialName("model_profile_id")
+    val modelProfileId: String = "",
+    @SerialName("model_label")
+    val modelLabel: String = "",
+    val status: String = "",
+    @SerialName("suggestion_text")
+    val suggestionText: String = "",
+    @SerialName("parsed_json")
+    val parsedJson: JsonElement = JsonObject(emptyMap())
+)
+
+@Serializable
+data class DouyinAnalysisReport(
+    val id: String = "",
+    @SerialName("focus_text")
+    val focusText: String = "",
+    @SerialName("model_profile_ids")
+    val modelProfileIds: List<String> = emptyList(),
+    @SerialName("linked_account_ids")
+    val linkedAccountIds: List<String> = emptyList(),
+    @SerialName("created_at")
+    val createdAt: String = "",
+    val suggestions: List<DouyinAnalysisSuggestion> = emptyList()
+)
+
+@Serializable
+data class DouyinSimilaritySearchPreview(
+    val id: String = "",
+    val keywords: List<String> = emptyList(),
+    @SerialName("created_at")
+    val createdAt: String = ""
+)
+
+@Serializable
+data class DouyinLinkedAccount(
+    @SerialName("relation_id")
+    val relationId: String = "",
+    @SerialName("relation_type")
+    val relationType: String = "",
+    val note: String = "",
+    @SerialName("search_id")
+    val searchId: String = "",
+    @SerialName("created_at")
+    val createdAt: String = "",
+    @SerialName("target_account_id")
+    val targetAccountId: String? = null,
+    @SerialName("target_profile_url")
+    val targetProfileUrl: String = "",
+    @SerialName("target_nickname")
+    val targetNickname: String = "",
+    @SerialName("target_signature")
+    val targetSignature: String = "",
+    @SerialName("target_profile_stats")
+    val targetProfileStats: DouyinProfileStats = DouyinProfileStats(),
+    @SerialName("target_tags")
+    val targetTags: List<String> = emptyList()
+)
+
+@Serializable
+data class DouyinAccountWorkspace(
+    val account: DouyinAccountSummary = DouyinAccountSummary(),
+    @SerialName("latest_public_snapshot")
+    val latestPublicSnapshot: DouyinSnapshotSummary? = null,
+    @SerialName("latest_creator_snapshot")
+    val latestCreatorSnapshot: DouyinSnapshotSummary? = null,
+    @SerialName("linked_accounts")
+    val linkedAccounts: List<DouyinLinkedAccount> = emptyList(),
+    @SerialName("recent_reports")
+    val recentReports: List<DouyinAnalysisReport> = emptyList(),
+    @SerialName("recent_similarity_searches")
+    val recentSimilaritySearches: List<DouyinSimilaritySearchPreview> = emptyList(),
+    @SerialName("available_model_profiles")
+    val availableModelProfiles: List<DouyinModelProfileSummary> = emptyList(),
+    @SerialName("sync_errors")
+    val syncErrors: List<String> = emptyList()
+)
+
+@Serializable
+data class DouyinAccountAnalysisRequest(
+    @SerialName("model_profile_ids")
+    val modelProfileIds: List<String> = emptyList(),
+    @SerialName("linked_account_ids")
+    val linkedAccountIds: List<String> = emptyList(),
+    @SerialName("include_linked_accounts")
+    val includeLinkedAccounts: Boolean = true,
+    @SerialName("include_recent_similar_candidates")
+    val includeRecentSimilarCandidates: Boolean = true,
+    @SerialName("max_videos")
+    val maxVideos: Int = 12,
+    @SerialName("extra_focus")
+    val extraFocus: String = "",
+    val temperature: Double = 0.35
+)
+
+@Serializable
+data class DouyinAnalysisResult(
+    @SerialName("report_id")
+    val reportId: String = "",
+    @SerialName("created_at")
+    val createdAt: String = "",
+    val context: JsonElement = JsonObject(emptyMap()),
+    val suggestions: List<DouyinAnalysisSuggestion> = emptyList()
+)
+
+@Serializable
+data class DouyinSimilarSearchRequest(
+    @SerialName("source_account_id")
+    val sourceAccountId: String? = null,
+    @SerialName("profile_url")
+    val profileUrl: String? = null,
+    @SerialName("candidate_urls")
+    val candidateUrls: List<String> = emptyList(),
+    @SerialName("seed_linked_accounts")
+    val seedLinkedAccounts: Boolean = true,
+    @SerialName("search_public_pages")
+    val searchPublicPages: Boolean = true,
+    @SerialName("model_profile_id")
+    val modelProfileId: String? = null,
+    @SerialName("max_candidates")
+    val maxCandidates: Int = 10,
+    @SerialName("extra_requirements")
+    val extraRequirements: String = ""
+)
+
+@Serializable
+data class DouyinSimilarCandidate(
+    val id: String = "",
+    @SerialName("candidate_account_id")
+    val candidateAccountId: String? = null,
+    @SerialName("candidate_profile_url")
+    val candidateProfileUrl: String = "",
+    @SerialName("candidate_nickname")
+    val candidateNickname: String = "",
+    @SerialName("heuristic_score")
+    val heuristicScore: Double = 0.0,
+    @SerialName("agent_score")
+    val agentScore: Double = 0.0,
+    @SerialName("rationale_text")
+    val rationaleText: String = "",
+    val dimensions: JsonElement = JsonObject(emptyMap()),
+    @SerialName("rank_index")
+    val rankIndex: Int = 0
+)
+
+@Serializable
+data class DouyinSimilaritySearchResult(
+    @SerialName("search_id")
+    val searchId: String = "",
+    @SerialName("source_account")
+    val sourceAccount: DouyinAccountSummary = DouyinAccountSummary(),
+    @SerialName("model_profile")
+    val modelProfile: JsonObject = JsonObject(emptyMap()),
+    @SerialName("raw_model_output")
+    val rawModelOutput: String = "",
+    val candidates: List<DouyinSimilarCandidate> = emptyList()
+)
+
+@Serializable
+data class DouyinSimilaritySearchDetail(
+    val id: String = "",
+    @SerialName("source_account_id")
+    val sourceAccountId: String? = null,
+    @SerialName("source_profile_url")
+    val sourceProfileUrl: String = "",
+    val keywords: List<String> = emptyList(),
+    val context: JsonElement = JsonObject(emptyMap()),
+    @SerialName("created_at")
+    val createdAt: String = "",
+    val candidates: List<DouyinSimilarCandidate> = emptyList()
+)
+
+@Serializable
+data class DouyinBenchmarkLinkRequest(
+    @SerialName("target_account_ids")
+    val targetAccountIds: List<String> = emptyList(),
+    @SerialName("target_profile_urls")
+    val targetProfileUrls: List<String> = emptyList(),
+    @SerialName("relation_type")
+    val relationType: String = "benchmark",
+    val note: String = "",
+    @SerialName("search_id")
+    val searchId: String = ""
+)
+
+@Serializable
+data class DouyinBenchmarkLinkResult(
+    val saved: Int = 0,
+    @SerialName("relation_ids")
+    val relationIds: List<String> = emptyList(),
+    val links: List<DouyinLinkedAccount> = emptyList()
+)
+
+@Serializable
+data class DouyinSnapshotField(
+    @SerialName("field_path")
+    val fieldPath: String = "",
+    @SerialName("field_type")
+    val fieldType: String = "",
+    @SerialName("field_value_text")
+    val fieldValueText: String = ""
+)
+
+@Serializable
+data class DouyinSnapshotDetail(
+    val id: String = "",
+    @SerialName("snapshot_type")
+    val snapshotType: String = "",
+    @SerialName("source_url")
+    val sourceUrl: String = "",
+    @SerialName("field_count")
+    val fieldCount: Int = 0,
+    @SerialName("collected_at")
+    val collectedAt: String = "",
+    val summary: JsonObject = JsonObject(emptyMap()),
+    @SerialName("raw_payload")
+    val rawPayload: JsonElement = JsonObject(emptyMap()),
+    val fields: List<DouyinSnapshotField> = emptyList()
+)

android-app/app/src/main/java/com/aiglasses/app/storyforge/StoryForgeApiService.kt

@@ -57,6 +57,9 @@ interface StoryForgeApiService {
     @POST("v2/explore/text")
     suspend fun createTextJob(@Body request: ExploreTextRequest): JobDto
 
+    @POST("v2/pipelines/content-source-sync")
+    suspend fun createContentSourceSyncJob(@Body request: ContentSourceSyncRequest): JobDto
+
     @Multipart
     @POST("v2/explore/upload-video")
     suspend fun uploadVideo(

android-app/app/src/main/java/com/aiglasses/app/storyforge/StoryForgeModels.kt

@@ -1,6 +1,10 @@
 package com.aiglasses.app.storyforge
 
 import kotlinx.serialization.Serializable
+import kotlinx.serialization.json.JsonArray
+import kotlinx.serialization.json.JsonObject
+import kotlinx.serialization.json.buildJsonArray
+import kotlinx.serialization.json.buildJsonObject
 
 @Serializable
 data class RegisterAccountRequest(
@@ -66,12 +70,22 @@ data class PreferredModelRequest(
 )
 
 @Serializable
-data class KnowledgeBaseDto(
+data class ProjectDto(
     val id: String,
     val user_id: String,
     val name: String,
     val description: String = "",
-    val fastgpt_dataset_id: String? = null,
+    val created_at: String = "",
+    val updated_at: String = ""
+)
+
+@Serializable
+data class KnowledgeBaseDto(
+    val id: String,
+    val user_id: String,
+    val project_id: String = "",
+    val name: String,
+    val description: String = "",
     val sync_status: String = "pending",
     val document_count: Int = 0,
     val linked_assistant_count: Int = 0,
@@ -82,6 +96,7 @@ data class KnowledgeBaseDto(
 @Serializable
 data class KnowledgeBaseCreateRequest(
     val name: String,
+    val project_id: String = "",
     val description: String = ""
 )
 
@@ -89,12 +104,13 @@ data class KnowledgeBaseCreateRequest(
 data class AssistantDto(
     val id: String,
     val user_id: String,
+    val project_id: String = "",
     val name: String,
     val description: String = "",
     val system_prompt: String = "",
     val generation_goal: String = "",
     val knowledge_base_ids: List<String> = emptyList(),
-    val fastgpt_app_key: String = "",
+    val config: JsonObject = buildJsonObject { },
     val model_profile_id: String = "",
     val created_at: String = "",
     val updated_at: String = ""
@@ -107,7 +123,7 @@ data class AssistantCreateRequest(
     val system_prompt: String = "",
     val generation_goal: String = "",
     val knowledge_base_ids: List<String> = emptyList(),
-    val fastgpt_app_key: String = "",
+    val project_id: String = "",
     val model_profile_id: String = ""
 )
 
@@ -118,7 +134,7 @@ data class AssistantUpdateRequest(
     val system_prompt: String? = null,
     val generation_goal: String? = null,
     val knowledge_base_ids: List<String>? = null,
-    val fastgpt_app_key: String? = null,
+    val project_id: String? = null,
     val model_profile_id: String? = null
 )
 
@@ -126,6 +142,7 @@ data class AssistantUpdateRequest(
 data class ExploreVideoLinkRequest(
     val video_url: String,
     val title: String? = null,
+    val project_id: String? = null,
     val knowledge_base_id: String? = null,
     val assistant_id: String? = null,
     val analysis_model_profile_id: String? = null,
@@ -136,28 +153,54 @@ data class ExploreVideoLinkRequest(
 data class ExploreTextRequest(
     val title: String,
     val content: String,
+    val project_id: String? = null,
     val knowledge_base_id: String? = null,
     val assistant_id: String? = null,
     val analysis_model_profile_id: String? = null
 )
 
+@Serializable
+data class ContentSourceSyncRequest(
+    val project_id: String = "",
+    val knowledge_base_id: String = "",
+    val assistant_id: String = "",
+    val content_source_id: String = "",
+    val platform: String = "",
+    val handle: String = "",
+    val source_url: String = "",
+    val title: String = "",
+    val analysis_model_profile_id: String = "",
+    val language: String = "auto",
+    val max_items: Int = 5,
+    val skip_existing: Boolean = true,
+    val auto_trigger_analysis: Boolean = true
+)
+
 @Serializable
 data class JobDto(
     val id: String,
     val user_id: String,
+    val project_id: String = "",
+    val parent_job_id: String = "",
     val assistant_id: String? = null,
     val knowledge_base_id: String,
+    val content_source_id: String = "",
     val source_type: String,
+    val line_type: String = "analysis",
+    val workflow_key: String = "",
+    val orchestrator: String = "n8n",
+    val provider_name: String = "",
+    val provider_task_id: String = "",
     val source_url: String? = null,
     val title: String,
     val language: String,
     val status: String,
     val transcript_text: String = "",
     val style_summary: String = "",
-    val fastgpt_collection_id: String = "",
     val upload_status: String = "pending",
     val error: String = "",
-    val artifacts: Map<String, String> = emptyMap(),
+    val artifacts: JsonObject = buildJsonObject { },
+    val result: JsonObject = buildJsonObject { },
     val analysis_model_profile_id: String = "",
     val created_at: String = "",
     val updated_at: String = ""
@@ -173,7 +216,9 @@ data class KnowledgeDocumentDto(
     val transcript_text: String = "",
     val style_summary: String = "",
     val combined_text: String = "",
-    val fastgpt_collection_id: String = "",
+    val analysis: JsonObject = buildJsonObject { },
+    val storyboards: JsonArray = buildJsonArray { },
+    val source_artifacts: JsonObject = buildJsonObject { },
     val analysis_model_profile_id: String = "",
     val created_at: String = "",
     val updated_at: String = ""
@@ -200,6 +245,7 @@ data class GenerateCopyResponseDto(
 @Serializable
 data class DashboardDto(
     val account: AccountDto,
+    val projects: List<ProjectDto> = emptyList(),
     val knowledge_bases: List<KnowledgeBaseDto> = emptyList(),
     val assistants: List<AssistantDto> = emptyList(),
     val recent_jobs: List<JobDto> = emptyList(),

android-app/app/src/main/java/com/aiglasses/app/storyforge/StoryForgeRepository.kt

@@ -147,6 +147,32 @@ class StoryForgeRepository(private val context: Context) {
         )
     )
 
+    suspend fun createContentSourceSyncJob(
+        platform: String,
+        handle: String,
+        sourceUrl: String,
+        title: String,
+        knowledgeBaseId: String,
+        assistantId: String,
+        analysisModelProfileId: String,
+        maxItems: Int,
+        skipExisting: Boolean,
+        autoTriggerAnalysis: Boolean
+    ): JobDto = api().createContentSourceSyncJob(
+        ContentSourceSyncRequest(
+            knowledge_base_id = knowledgeBaseId,
+            assistant_id = assistantId,
+            platform = platform,
+            handle = handle,
+            source_url = sourceUrl,
+            title = title,
+            analysis_model_profile_id = analysisModelProfileId,
+            max_items = maxItems,
+            skip_existing = skipExisting,
+            auto_trigger_analysis = autoTriggerAnalysis
+        )
+    )
+
     suspend fun uploadVideo(
         uri: Uri,
         title: String,

android-app/app/src/main/java/com/aiglasses/app/storyforge/StoryForgeScreen.kt

@@ -293,6 +293,7 @@ private fun ExploreTab(state: StoryForgeUiState, vm: StoryForgeViewModel, onPick
     SectionCard(title = "素材入口", subtitle = "视频链接、上传视频、输入文字都会转成文本并做风格分析") {
         ChoiceRow(
             options = listOf(
+                "账号同步" to (state.exploreInputMode == ExploreInputMode.ContentSource),
                 "视频链接" to (state.exploreInputMode == ExploreInputMode.VideoLink),
                 "上传视频" to (state.exploreInputMode == ExploreInputMode.UploadVideo),
                 "输入文字" to (state.exploreInputMode == ExploreInputMode.Text)
@@ -300,6 +301,7 @@ private fun ExploreTab(state: StoryForgeUiState, vm: StoryForgeViewModel, onPick
             onSelect = { label ->
                 vm.setExploreInputMode(
                     when (label) {
+                        "账号同步" -> ExploreInputMode.ContentSource
                         "视频链接" -> ExploreInputMode.VideoLink
                         "上传视频" -> ExploreInputMode.UploadVideo
                         else -> ExploreInputMode.Text
@@ -319,6 +321,93 @@ private fun ExploreTab(state: StoryForgeUiState, vm: StoryForgeViewModel, onPick
         )
         Spacer(modifier = Modifier.height(12.dp))
         when (state.exploreInputMode) {
+            ExploreInputMode.ContentSource -> {
+                Text(
+                    text = "适合导入抖音、B 站、小红书创作者账号主页。抖音 public 页面抓不到时，也可以把分享页链接和账号标识手工填进来。",
+                    style = MaterialTheme.typography.bodySmall,
+                    color = MaterialTheme.colorScheme.onSurface.copy(alpha = 0.7f)
+                )
+                Spacer(modifier = Modifier.height(10.dp))
+                ChoiceRow(
+                    options = listOf(
+                        "抖音" to (state.accountSyncPlatform == "抖音"),
+                        "B站" to (state.accountSyncPlatform == "bilibili"),
+                        "小红书" to (state.accountSyncPlatform == "小红书")
+                    ),
+                    onSelect = { label ->
+                        vm.updateAccountSyncPlatform(
+                            when (label) {
+                                "B站" -> "bilibili"
+                                else -> label
+                            }
+                        )
+                    }
+                )
+                Spacer(modifier = Modifier.height(10.dp))
+                OutlinedTextField(
+                    value = state.accountSyncUrl,
+                    onValueChange = vm::updateAccountSyncUrl,
+                    modifier = Modifier.fillMaxWidth(),
+                    label = { Text("账号主页或分享页链接") },
+                    minLines = 2
+                )
+                Spacer(modifier = Modifier.height(10.dp))
+                OutlinedTextField(
+                    value = state.accountSyncHandle,
+                    onValueChange = vm::updateAccountSyncHandle,
+                    modifier = Modifier.fillMaxWidth(),
+                    label = { Text("账号标识（可选）") },
+                    singleLine = true
+                )
+                Spacer(modifier = Modifier.height(10.dp))
+                OutlinedTextField(
+                    value = state.accountSyncTitle,
+                    onValueChange = vm::updateAccountSyncTitle,
+                    modifier = Modifier.fillMaxWidth(),
+                    label = { Text("任务标题（可选）") },
+                    singleLine = true
+                )
+                Spacer(modifier = Modifier.height(10.dp))
+                OutlinedTextField(
+                    value = state.accountSyncMaxItems,
+                    onValueChange = vm::updateAccountSyncMaxItems,
+                    modifier = Modifier.fillMaxWidth(),
+                    label = { Text("最多拉取视频数（1-20）") },
+                    singleLine = true
+                )
+                Spacer(modifier = Modifier.height(12.dp))
+                Row(
+                    modifier = Modifier.fillMaxWidth(),
+                    horizontalArrangement = Arrangement.spacedBy(12.dp)
+                ) {
+                    Row(
+                        modifier = Modifier.weight(1f),
+                        verticalAlignment = Alignment.CenterVertically,
+                        horizontalArrangement = Arrangement.SpaceBetween
+                    ) {
+                        Text("跳过已存在视频", style = MaterialTheme.typography.bodySmall)
+                        Switch(
+                            checked = state.accountSyncSkipExisting,
+                            onCheckedChange = vm::setAccountSyncSkipExisting
+                        )
+                    }
+                    Row(
+                        modifier = Modifier.weight(1f),
+                        verticalAlignment = Alignment.CenterVertically,
+                        horizontalArrangement = Arrangement.SpaceBetween
+                    ) {
+                        Text("自动触发分析", style = MaterialTheme.typography.bodySmall)
+                        Switch(
+                            checked = state.accountSyncAutoTriggerAnalysis,
+                            onCheckedChange = vm::setAccountSyncAutoTriggerAnalysis
+                        )
+                    }
+                }
+                Spacer(modifier = Modifier.height(12.dp))
+                Button(onClick = vm::submitContentSourceSync, enabled = !state.busy) {
+                    Text("同步账号内容")
+                }
+            }
             ExploreInputMode.VideoLink -> {
                 OutlinedTextField(
                     value = state.videoUrl,

android-app/app/src/main/java/com/aiglasses/app/storyforge/StoryForgeViewModel.kt

@@ -26,6 +26,7 @@ enum class StoryForgeAuthMode {
 }
 
 enum class ExploreInputMode {
+    ContentSource,
     VideoLink,
     UploadVideo,
     Text
@@ -72,6 +73,13 @@ data class StoryForgeUiState(
     val createKnowledgeBaseName: String = "",
     val createKnowledgeBaseDescription: String = "",
     val exploreInputMode: ExploreInputMode = ExploreInputMode.VideoLink,
+    val accountSyncPlatform: String = "抖音",
+    val accountSyncHandle: String = "",
+    val accountSyncUrl: String = "",
+    val accountSyncTitle: String = "",
+    val accountSyncMaxItems: String = "5",
+    val accountSyncSkipExisting: Boolean = true,
+    val accountSyncAutoTriggerAnalysis: Boolean = true,
     val videoUrl: String = "",
     val videoTitle: String = "",
     val textTitle: String = "",
@@ -155,6 +163,35 @@ class StoryForgeViewModel(application: Application) : AndroidViewModel(applicati
         _state.value = _state.value.copy(videoUrl = value)
     }
 
+    fun updateAccountSyncPlatform(value: String) {
+        _state.value = _state.value.copy(accountSyncPlatform = value)
+    }
+
+    fun updateAccountSyncHandle(value: String) {
+        _state.value = _state.value.copy(accountSyncHandle = value)
+    }
+
+    fun updateAccountSyncUrl(value: String) {
+        _state.value = _state.value.copy(accountSyncUrl = value)
+    }
+
+    fun updateAccountSyncTitle(value: String) {
+        _state.value = _state.value.copy(accountSyncTitle = value)
+    }
+
+    fun updateAccountSyncMaxItems(value: String) {
+        val digits = value.filter { it.isDigit() }
+        _state.value = _state.value.copy(accountSyncMaxItems = digits)
+    }
+
+    fun setAccountSyncSkipExisting(value: Boolean) {
+        _state.value = _state.value.copy(accountSyncSkipExisting = value)
+    }
+
+    fun setAccountSyncAutoTriggerAnalysis(value: Boolean) {
+        _state.value = _state.value.copy(accountSyncAutoTriggerAnalysis = value)
+    }
+
     fun updateVideoTitle(value: String) {
         _state.value = _state.value.copy(videoTitle = value)
     }
@@ -463,6 +500,43 @@ class StoryForgeViewModel(application: Application) : AndroidViewModel(applicati
         }
     }
 
+    fun submitContentSourceSync() {
+        val current = state.value
+        if (current.accountSyncUrl.isBlank()) {
+            setError("请先输入账号主页链接")
+            return
+        }
+        val knowledgeBaseId = selectedKnowledgeBaseIdOrFallback()
+        if (knowledgeBaseId.isBlank()) {
+            setError("请先选择知识库")
+            return
+        }
+        val maxItems = current.accountSyncMaxItems.toIntOrNull()?.coerceIn(1, 20) ?: 5
+        runBusy(message = "正在创建账号同步任务...", task = {
+            repository.createContentSourceSyncJob(
+                platform = current.accountSyncPlatform.trim(),
+                handle = current.accountSyncHandle.trim(),
+                sourceUrl = current.accountSyncUrl.trim(),
+                title = current.accountSyncTitle.trim(),
+                knowledgeBaseId = knowledgeBaseId,
+                assistantId = current.selectedAssistantId,
+                analysisModelProfileId = preferredModelId(),
+                maxItems = maxItems,
+                skipExisting = current.accountSyncSkipExisting,
+                autoTriggerAnalysis = current.accountSyncAutoTriggerAnalysis
+            )
+        }) { job ->
+            appendTimeline("账号同步任务已创建: ${job.title}")
+            _state.value = state.value.copy(
+                accountSyncHandle = "",
+                accountSyncUrl = "",
+                accountSyncTitle = "",
+                accountSyncMaxItems = maxItems.toString()
+            )
+            afterJobCreated(job)
+        }
+    }
+
     fun submitText() {
         val current = state.value
         if (current.textTitle.isBlank() || current.textContent.isBlank()) {

collector-service/Dockerfile

@@ -1,5 +1,9 @@
 FROM python:3.11-slim
 
+RUN apt-get update \
+    && apt-get install -y --no-install-recommends ffmpeg \
+    && rm -rf /var/lib/apt/lists/*
+
 WORKDIR /app
 COPY requirements.txt ./
 RUN pip install --no-cache-dir -r requirements.txt

collector-service/app/database.py

@@ -48,6 +48,18 @@ class Database:
         with self.session() as conn:
             conn.execute(sql, params)
 
+    def table_exists(self, name: str) -> bool:
+        row = self.fetch_one(
+            "SELECT name FROM sqlite_master WHERE type = 'table' AND name = ?",
+            (name,),
+        )
+        return bool(row)
+
+    def column_exists(self, table: str, column: str) -> bool:
+        with self.session() as conn:
+            rows = conn.execute(f"PRAGMA table_info({table})").fetchall()
+        return any(row["name"] == column for row in rows)
+
     def init_schema(self) -> None:
         schema = """
         CREATE TABLE IF NOT EXISTS accounts (
@@ -90,10 +102,10 @@ class Database:
         CREATE TABLE IF NOT EXISTS knowledge_bases (
             id TEXT PRIMARY KEY,
             user_id TEXT NOT NULL,
+            project_id TEXT,
             name TEXT NOT NULL,
             description TEXT NOT NULL DEFAULT '',
-            fastgpt_dataset_id TEXT,
+            sync_status TEXT NOT NULL DEFAULT 'ready',
-            sync_status TEXT NOT NULL DEFAULT 'pending',
             created_at TEXT NOT NULL,
             updated_at TEXT NOT NULL,
             FOREIGN KEY(user_id) REFERENCES accounts(id) ON DELETE CASCADE
@@ -108,7 +120,9 @@ class Database:
             transcript_text TEXT NOT NULL DEFAULT '',
             style_summary TEXT NOT NULL DEFAULT '',
             combined_text TEXT NOT NULL DEFAULT '',
-            fastgpt_collection_id TEXT NOT NULL DEFAULT '',
+            analysis_json TEXT NOT NULL DEFAULT '{}',
+            storyboard_json TEXT NOT NULL DEFAULT '[]',
+            source_artifact_json TEXT NOT NULL DEFAULT '{}',
             analysis_model_profile_id TEXT NOT NULL DEFAULT '',
             created_at TEXT NOT NULL,
             updated_at TEXT NOT NULL,
@@ -118,11 +132,12 @@ class Database:
         CREATE TABLE IF NOT EXISTS assistants (
             id TEXT PRIMARY KEY,
             user_id TEXT NOT NULL,
+            project_id TEXT,
             name TEXT NOT NULL,
             description TEXT NOT NULL DEFAULT '',
             system_prompt TEXT NOT NULL DEFAULT '',
             generation_goal TEXT NOT NULL DEFAULT '',
-            fastgpt_app_key TEXT NOT NULL DEFAULT '',
+            config_json TEXT NOT NULL DEFAULT '{}',
             model_profile_id TEXT NOT NULL DEFAULT '',
             created_at TEXT NOT NULL,
             updated_at TEXT NOT NULL,
@@ -140,19 +155,27 @@ class Database:
         CREATE TABLE IF NOT EXISTS jobs (
             id TEXT PRIMARY KEY,
             user_id TEXT NOT NULL,
+            project_id TEXT,
+            parent_job_id TEXT,
             assistant_id TEXT,
             knowledge_base_id TEXT NOT NULL,
+            content_source_id TEXT,
             source_type TEXT NOT NULL,
+            line_type TEXT NOT NULL DEFAULT 'analysis',
+            workflow_key TEXT NOT NULL DEFAULT '',
+            orchestrator TEXT NOT NULL DEFAULT 'n8n',
+            provider_name TEXT NOT NULL DEFAULT '',
+            provider_task_id TEXT NOT NULL DEFAULT '',
             source_url TEXT,
             title TEXT NOT NULL,
             language TEXT NOT NULL DEFAULT 'auto',
             status TEXT NOT NULL,
             transcript_text TEXT NOT NULL DEFAULT '',
             style_summary TEXT NOT NULL DEFAULT '',
-            fastgpt_collection_id TEXT NOT NULL DEFAULT '',
             upload_status TEXT NOT NULL DEFAULT 'pending',
             error TEXT NOT NULL DEFAULT '',
             artifacts_json TEXT NOT NULL DEFAULT '{}',
+            result_json TEXT NOT NULL DEFAULT '{}',
             analysis_model_profile_id TEXT NOT NULL DEFAULT '',
             created_at TEXT NOT NULL,
             updated_at TEXT NOT NULL,
@@ -161,6 +184,42 @@ class Database:
             FOREIGN KEY(knowledge_base_id) REFERENCES knowledge_bases(id) ON DELETE CASCADE
         );
 
+        CREATE TABLE IF NOT EXISTS projects (
+            id TEXT PRIMARY KEY,
+            user_id TEXT NOT NULL,
+            name TEXT NOT NULL,
+            description TEXT NOT NULL DEFAULT '',
+            created_at TEXT NOT NULL,
+            updated_at TEXT NOT NULL,
+            FOREIGN KEY(user_id) REFERENCES accounts(id) ON DELETE CASCADE
+        );
+
+        CREATE TABLE IF NOT EXISTS content_sources (
+            id TEXT PRIMARY KEY,
+            user_id TEXT NOT NULL,
+            project_id TEXT,
+            source_kind TEXT NOT NULL,
+            platform TEXT NOT NULL DEFAULT '',
+            handle TEXT NOT NULL DEFAULT '',
+            source_url TEXT NOT NULL DEFAULT '',
+            title TEXT NOT NULL DEFAULT '',
+            local_path TEXT NOT NULL DEFAULT '',
+            metadata_json TEXT NOT NULL DEFAULT '{}',
+            created_at TEXT NOT NULL,
+            updated_at TEXT NOT NULL,
+            FOREIGN KEY(user_id) REFERENCES accounts(id) ON DELETE CASCADE,
+            FOREIGN KEY(project_id) REFERENCES projects(id) ON DELETE SET NULL
+        );
+
+        CREATE TABLE IF NOT EXISTS job_events (
+            id TEXT PRIMARY KEY,
+            job_id TEXT NOT NULL,
+            event_type TEXT NOT NULL,
+            payload_json TEXT NOT NULL DEFAULT '{}',
+            created_at TEXT NOT NULL,
+            FOREIGN KEY(job_id) REFERENCES jobs(id) ON DELETE CASCADE
+        );
+
         CREATE TABLE IF NOT EXISTS app_updates (
             id INTEGER PRIMARY KEY AUTOINCREMENT,
             platform TEXT NOT NULL,
@@ -179,3 +238,103 @@ class Database:
         """
         with self.session() as conn:
             conn.executescript(schema)
+        self.migrate_schema()
+
+    def migrate_schema(self) -> None:
+        table_columns: dict[str, dict[str, str]] = {
+            "knowledge_bases": {
+                "project_id": "TEXT",
+            },
+            "knowledge_documents": {
+                "analysis_json": "TEXT NOT NULL DEFAULT '{}'",
+                "storyboard_json": "TEXT NOT NULL DEFAULT '[]'",
+                "source_artifact_json": "TEXT NOT NULL DEFAULT '{}'",
+            },
+            "assistants": {
+                "project_id": "TEXT",
+                "config_json": "TEXT NOT NULL DEFAULT '{}'",
+            },
+            "jobs": {
+                "project_id": "TEXT",
+                "parent_job_id": "TEXT",
+                "content_source_id": "TEXT",
+                "line_type": "TEXT NOT NULL DEFAULT 'analysis'",
+                "workflow_key": "TEXT NOT NULL DEFAULT ''",
+                "orchestrator": "TEXT NOT NULL DEFAULT 'n8n'",
+                "provider_name": "TEXT NOT NULL DEFAULT ''",
+                "provider_task_id": "TEXT NOT NULL DEFAULT ''",
+                "result_json": "TEXT NOT NULL DEFAULT '{}'",
+            },
+        }
+
+        for table, columns in table_columns.items():
+            if not self.table_exists(table):
+                continue
+            for column, definition in columns.items():
+                if self.column_exists(table, column):
+                    continue
+                self.execute(f"ALTER TABLE {table} ADD COLUMN {column} {definition}")
+
+        self.ensure_default_projects()
+
+    def ensure_default_projects(self) -> None:
+        if not self.table_exists("projects"):
+            return
+
+        accounts = self.fetch_all("SELECT id, username FROM accounts ORDER BY created_at ASC")
+        for account in accounts:
+            project = self.fetch_one(
+                "SELECT * FROM projects WHERE user_id = ? ORDER BY created_at ASC LIMIT 1",
+                (account["id"],),
+            )
+            if not project:
+                project_id = f"proj_{account['id']}"
+                now = utc_now()
+                self.execute(
+                    """
+                    INSERT INTO projects (id, user_id, name, description, created_at, updated_at)
+                    VALUES (?, ?, ?, ?, ?, ?)
+                    """,
+                    (
+                        project_id,
+                        account["id"],
+                        f"{account['username']} 默认项目",
+                        "系统自动创建的默认项目",
+                        now,
+                        now,
+                    ),
+                )
+                project = self.fetch_one("SELECT * FROM projects WHERE id = ?", (project_id,))
+
+            if not project:
+                continue
+
+            if self.column_exists("knowledge_bases", "project_id"):
+                self.execute(
+                    """
+                    UPDATE knowledge_bases
+                    SET project_id = ?
+                    WHERE user_id = ? AND (project_id IS NULL OR project_id = '')
+                    """,
+                    (project["id"], account["id"]),
+                )
+
+            if self.column_exists("assistants", "project_id"):
+                self.execute(
+                    """
+                    UPDATE assistants
+                    SET project_id = ?
+                    WHERE user_id = ? AND (project_id IS NULL OR project_id = '')
+                    """,
+                    (project["id"], account["id"]),
+                )
+
+            if self.column_exists("jobs", "project_id"):
+                self.execute(
+                    """
+                    UPDATE jobs
+                    SET project_id = ?
+                    WHERE user_id = ? AND (project_id IS NULL OR project_id = '')
+                    """,
+                    (project["id"], account["id"]),
+                )

collector-service/app/fastgpt.py

@@ -1,48 +0,0 @@
-from __future__ import annotations
-
-from typing import Any
-
-import httpx
-
-
-class FastGPTClient:
-    def __init__(self, *, base_url: str, dataset_api_key: str, timeout: float = 60.0) -> None:
-        self.base_url = base_url.rstrip("/")
-        self.dataset_api_key = dataset_api_key.strip()
-        self.timeout = timeout
-
-    @property
-    def enabled(self) -> bool:
-        return bool(self.base_url and self.dataset_api_key)
-
-    async def ensure_dataset(self, name: str, intro: str = "") -> dict[str, Any] | None:
-        if not self.enabled:
-            return None
-        payload = {"name": name, "intro": intro}
-        async with httpx.AsyncClient(timeout=self.timeout) as client:
-            response = await client.post(
-                f"{self.base_url}/api/core/dataset/create",
-                headers={"Authorization": f"Bearer {self.dataset_api_key}"},
-                json=payload,
-            )
-            response.raise_for_status()
-            return response.json().get("data") or response.json()
-
-    async def add_text_document(self, dataset_id: str, name: str, text: str) -> dict[str, Any] | None:
-        if not self.enabled or not dataset_id.strip():
-            return None
-        payload = {
-            "datasetId": dataset_id,
-            "type": "text",
-            "name": name,
-            "trainingType": "chunk",
-            "text": text,
-        }
-        async with httpx.AsyncClient(timeout=self.timeout) as client:
-            response = await client.post(
-                f"{self.base_url}/api/core/dataset/collection/create/text",
-                headers={"Authorization": f"Bearer {self.dataset_api_key}"},
-                json=payload,
-            )
-            response.raise_for_status()
-            return response.json().get("data") or response.json()

collector-service/app/integrations.py

@@ -0,0 +1,217 @@
+from __future__ import annotations
+
+import mimetypes
+from pathlib import Path
+from typing import Any
+
+import httpx
+
+
+def _join_url(base_url: str, path: str) -> str:
+    base = base_url.rstrip("/")
+    if path.startswith("http://") or path.startswith("https://"):
+        return path
+    return f"{base}/{path.lstrip('/')}"
+
+
+def _unwrap_response(payload: Any) -> dict[str, Any]:
+    if not isinstance(payload, dict):
+        return {"value": payload}
+    if payload.get("success") is True and "data" in payload:
+        data = payload.get("data")
+        if isinstance(data, dict):
+            return data
+        return {"value": data}
+    return payload
+
+
+class N8NClient:
+    def __init__(
+        self,
+        *,
+        base_url: str,
+        workflow_paths: dict[str, str],
+        shared_secret: str = "",
+        timeout: float = 60.0,
+    ) -> None:
+        self.base_url = base_url.rstrip("/")
+        self.workflow_paths = workflow_paths
+        self.shared_secret = shared_secret.strip()
+        self.timeout = timeout
+
+    @property
+    def enabled(self) -> bool:
+        return bool(self.base_url)
+
+    async def trigger(self, workflow_key: str, payload: dict[str, Any]) -> dict[str, Any]:
+        workflow_path = self.workflow_paths.get(workflow_key, "").strip()
+        if not workflow_path:
+            raise ValueError(f"workflow path not configured for {workflow_key}")
+        try:
+            workflow_path = workflow_path.format(**payload)
+        except KeyError:
+            pass
+        headers: dict[str, str] = {}
+        if self.shared_secret:
+            headers["X-Orchestrator-Secret"] = self.shared_secret
+        async with httpx.AsyncClient(timeout=self.timeout) as client:
+            response = await client.post(
+                _join_url(self.base_url, workflow_path),
+                json=payload,
+                headers=headers,
+            )
+            response.raise_for_status()
+            if not response.content:
+                return {"triggered": True}
+            return _unwrap_response(response.json())
+
+
+class CutVideoClient:
+    def __init__(
+        self,
+        *,
+        base_url: str,
+        api_key: str = "",
+        timeout: float = 120.0,
+        upload_timeout: float = 1800.0,
+    ) -> None:
+        self.base_url = base_url.rstrip("/")
+        self.api_key = api_key.strip()
+        self.timeout = timeout
+        self.upload_timeout = upload_timeout
+
+    @property
+    def enabled(self) -> bool:
+        return bool(self.base_url)
+
+    def _headers(self) -> dict[str, str]:
+        headers: dict[str, str] = {}
+        if self.api_key:
+            headers["Authorization"] = f"Bearer {self.api_key}"
+        return headers
+
+    async def submit_job(self, payload: dict[str, Any]) -> dict[str, Any]:
+        async with httpx.AsyncClient(timeout=self.timeout) as client:
+            response = await client.post(
+                _join_url(self.base_url, "/api/jobs"),
+                json=payload,
+                headers=self._headers(),
+            )
+            response.raise_for_status()
+            return _unwrap_response(response.json())
+
+    async def upload_source_file(self, source_path: Path, *, folder_name: str = "") -> dict[str, Any]:
+        content_type = mimetypes.guess_type(source_path.name)[0] or "application/octet-stream"
+        headers = self._headers()
+        data = {"folder_name": folder_name} if folder_name else {}
+        async with httpx.AsyncClient(timeout=self.upload_timeout) as client:
+            with source_path.open("rb") as handle:
+                response = await client.post(
+                    _join_url(self.base_url, "/api/uploads"),
+                    data=data,
+                    files={"files": (source_path.name, handle, content_type)},
+                    headers=headers,
+                )
+            response.raise_for_status()
+            return _unwrap_response(response.json())
+
+    async def get_task(self, task_id: str) -> dict[str, Any]:
+        async with httpx.AsyncClient(timeout=self.timeout) as client:
+            response = await client.get(
+                _join_url(self.base_url, f"/api/tasks/{task_id}"),
+                headers=self._headers(),
+            )
+            response.raise_for_status()
+            return _unwrap_response(response.json())
+
+    async def get_run(self, run_id: str) -> dict[str, Any]:
+        async with httpx.AsyncClient(timeout=self.timeout) as client:
+            response = await client.get(
+                _join_url(self.base_url, f"/api/runs/{run_id}"),
+                headers=self._headers(),
+            )
+            response.raise_for_status()
+            return _unwrap_response(response.json())
+
+
+class AsrHttpClient:
+    def __init__(
+        self,
+        *,
+        base_url: str,
+        transcribe_path: str = "/transcribe",
+        field_name: str = "wav",
+        timeout: float = 120.0,
+    ) -> None:
+        self.base_url = base_url.rstrip("/")
+        self.transcribe_path = transcribe_path
+        self.field_name = field_name.strip() or "wav"
+        self.timeout = timeout
+
+    @property
+    def enabled(self) -> bool:
+        return bool(self.base_url)
+
+    async def transcribe_audio(self, audio_path: Path) -> dict[str, Any]:
+        content_type = mimetypes.guess_type(audio_path.name)[0] or "application/octet-stream"
+        async with httpx.AsyncClient(timeout=self.timeout) as client:
+            with audio_path.open("rb") as handle:
+                response = await client.post(
+                    _join_url(self.base_url, self.transcribe_path),
+                    files={self.field_name: (audio_path.name, handle, content_type)},
+                )
+            response.raise_for_status()
+            return _unwrap_response(response.json())
+
+
+class HuobaoDramaClient:
+    def __init__(self, *, base_url: str, timeout: float = 180.0) -> None:
+        self.base_url = base_url.rstrip("/")
+        self.timeout = timeout
+
+    @property
+    def enabled(self) -> bool:
+        return bool(self.base_url)
+
+    async def create_drama(self, payload: dict[str, Any]) -> dict[str, Any]:
+        async with httpx.AsyncClient(timeout=self.timeout) as client:
+            response = await client.post(
+                _join_url(self.base_url, "/api/v1/dramas"),
+                json=payload,
+            )
+            response.raise_for_status()
+            return _unwrap_response(response.json())
+
+    async def generate_image(self, payload: dict[str, Any]) -> dict[str, Any]:
+        async with httpx.AsyncClient(timeout=self.timeout) as client:
+            response = await client.post(
+                _join_url(self.base_url, "/api/v1/images"),
+                json=payload,
+            )
+            response.raise_for_status()
+            return _unwrap_response(response.json())
+
+    async def get_image(self, image_id: str) -> dict[str, Any]:
+        async with httpx.AsyncClient(timeout=self.timeout) as client:
+            response = await client.get(
+                _join_url(self.base_url, f"/api/v1/images/{image_id}"),
+            )
+            response.raise_for_status()
+            return _unwrap_response(response.json())
+
+    async def generate_video(self, payload: dict[str, Any]) -> dict[str, Any]:
+        async with httpx.AsyncClient(timeout=self.timeout) as client:
+            response = await client.post(
+                _join_url(self.base_url, "/api/v1/videos"),
+                json=payload,
+            )
+            response.raise_for_status()
+            return _unwrap_response(response.json())
+
+    async def get_video(self, video_id: str) -> dict[str, Any]:
+        async with httpx.AsyncClient(timeout=self.timeout) as client:
+            response = await client.get(
+                _join_url(self.base_url, f"/api/v1/videos/{video_id}"),
+            )
+            response.raise_for_status()
+            return _unwrap_response(response.json())

collector-service/requirements.txt

@@ -3,3 +3,4 @@ uvicorn[standard]==0.34.0
 httpx==0.28.1
 python-multipart==0.0.20
 pydantic==2.11.1
+yt-dlp

concepts/studio-workbench/README.md

@@ -0,0 +1,27 @@
+# Version B: Studio Workbench
+
+Direction: `Castmagic x content ops studio`
+
+This version optimizes for teams that want to turn one material source into many structured outputs.
+
+## Product thesis
+
+- Users should feel they are operating a content studio, not just a summarizer.
+- Material ingestion is one panel inside a broader production system.
+- Knowledge bases, assistants, and output assets should be visible at once.
+- This is stronger for repeatable workflows and team collaboration.
+
+## Key decisions
+
+- `Production` becomes the emotional center of the app.
+- The screen is split into material, assistant, and output zones.
+- The user can see which knowledge bases feed which assistant.
+- One source material can drive multiple output formats immediately.
+- This layout is heavier, but it better communicates long-term business value.
+
+## When this version is best
+
+- Small content teams
+- Agencies managing multiple client voices
+- Users who need assistant governance and model routing
+- Teams that value throughput over the fastest first-use experience

concepts/studio-workbench/index.html

@@ -0,0 +1,426 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+  <meta charset="UTF-8" />
+  <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+  <title>StoryForge Version B</title>
+  <style>
+    :root {
+      --bg: #0e1416;
+      --panel: #121b1e;
+      --panel-soft: #162226;
+      --panel-bright: #1a282d;
+      --ink: #edf3ef;
+      --muted: #9db1a8;
+      --teal: #66c2a5;
+      --amber: #f2a65a;
+      --coral: #ff7a59;
+      --line: rgba(202, 224, 215, 0.1);
+      --shadow: 0 24px 70px rgba(0, 0, 0, 0.42);
+      --radius-xl: 32px;
+      --radius-lg: 22px;
+      --radius-md: 16px;
+    }
+
+    * { box-sizing: border-box; }
+    body {
+      margin: 0;
+      min-height: 100vh;
+      font-family: "Avenir Next", "SF Pro Display", "Segoe UI", sans-serif;
+      color: var(--ink);
+      background:
+        radial-gradient(circle at top left, rgba(102,194,165,0.18), transparent 28%),
+        radial-gradient(circle at 88% 14%, rgba(255,122,89,0.16), transparent 24%),
+        linear-gradient(180deg, #0d1214 0%, #10181b 100%);
+      display: grid;
+      place-items: center;
+      padding: 26px;
+    }
+
+    .frame {
+      width: 1440px;
+      min-height: 900px;
+      border-radius: 34px;
+      background: rgba(16, 23, 25, 0.95);
+      border: 1px solid rgba(199, 225, 215, 0.08);
+      box-shadow: var(--shadow);
+      display: grid;
+      grid-template-columns: 250px 1fr;
+      overflow: hidden;
+    }
+
+    .sidebar {
+      background: linear-gradient(180deg, #0f181b, #111b1f);
+      border-right: 1px solid var(--line);
+      padding: 26px 18px;
+      display: flex;
+      flex-direction: column;
+      gap: 18px;
+    }
+
+    .brand {
+      padding: 12px 14px;
+      border-radius: 18px;
+      background: rgba(255,255,255,0.03);
+      border: 1px solid var(--line);
+    }
+
+    .brand small {
+      display: block;
+      color: var(--muted);
+      text-transform: uppercase;
+      letter-spacing: 0.08em;
+      font-size: 11px;
+      margin-bottom: 8px;
+    }
+
+    .brand strong {
+      font-size: 24px;
+      letter-spacing: -0.04em;
+    }
+
+    .nav {
+      display: grid;
+      gap: 8px;
+    }
+
+    .nav-item {
+      padding: 14px 16px;
+      border-radius: 18px;
+      color: var(--muted);
+      border: 1px solid transparent;
+      background: transparent;
+      font-weight: 700;
+    }
+
+    .nav-item.active {
+      color: #0d1416;
+      background: linear-gradient(180deg, #79d1b6, #56b394);
+    }
+
+    .nav-item.alert {
+      border-color: rgba(255,122,89,0.22);
+      background: rgba(255,122,89,0.08);
+      color: #ffd5cb;
+    }
+
+    .sidebar-footer {
+      margin-top: auto;
+      padding: 16px;
+      border-radius: 18px;
+      background: rgba(255,255,255,0.03);
+      border: 1px solid var(--line);
+      color: var(--muted);
+      font-size: 13px;
+      line-height: 1.6;
+    }
+
+    .content {
+      padding: 24px;
+      display: grid;
+      grid-template-rows: auto auto 1fr;
+      gap: 18px;
+    }
+
+    .topbar {
+      display: flex;
+      justify-content: space-between;
+      align-items: center;
+      gap: 18px;
+    }
+
+    .headline h1 {
+      margin: 0;
+      font-size: 34px;
+      letter-spacing: -0.04em;
+    }
+
+    .headline p {
+      margin: 8px 0 0;
+      color: var(--muted);
+      font-size: 14px;
+    }
+
+    .top-actions {
+      display: flex;
+      gap: 10px;
+    }
+
+    .button {
+      padding: 14px 18px;
+      border-radius: 16px;
+      border: 1px solid var(--line);
+      background: var(--panel-soft);
+      color: var(--ink);
+      font-weight: 700;
+    }
+
+    .button.primary {
+      background: linear-gradient(180deg, #f7b36a, #ee9143);
+      color: #27140b;
+      border-color: transparent;
+    }
+
+    .stats {
+      display: grid;
+      grid-template-columns: repeat(4, 1fr);
+      gap: 14px;
+    }
+
+    .stat {
+      padding: 16px 18px;
+      border-radius: 20px;
+      background: var(--panel);
+      border: 1px solid var(--line);
+    }
+
+    .stat span {
+      display: block;
+      color: var(--muted);
+      font-size: 12px;
+      margin-bottom: 8px;
+    }
+
+    .stat strong {
+      font-size: 30px;
+      letter-spacing: -0.05em;
+    }
+
+    .workspace {
+      display: grid;
+      grid-template-columns: 1.15fr 0.95fr 1.1fr;
+      gap: 18px;
+    }
+
+    .card {
+      background: linear-gradient(180deg, rgba(22,34,38,0.96), rgba(17,27,30,0.98));
+      border: 1px solid var(--line);
+      border-radius: 26px;
+      padding: 18px;
+    }
+
+    .card h2 {
+      margin: 0 0 6px;
+      font-size: 20px;
+    }
+
+    .card p {
+      margin: 0 0 14px;
+      color: var(--muted);
+      font-size: 13px;
+      line-height: 1.6;
+    }
+
+    .composer {
+      border-radius: 18px;
+      border: 1px solid var(--line);
+      background: rgba(255,255,255,0.03);
+      min-height: 118px;
+      padding: 16px;
+      color: var(--muted);
+      margin-bottom: 12px;
+    }
+
+    .option-grid {
+      display: grid;
+      gap: 10px;
+      margin-top: 14px;
+    }
+
+    .option {
+      padding: 14px;
+      border-radius: 18px;
+      border: 1px solid var(--line);
+      background: rgba(255,255,255,0.03);
+      display: flex;
+      justify-content: space-between;
+      align-items: center;
+      gap: 12px;
+    }
+
+    .option small, .asset small {
+      display: block;
+      color: var(--muted);
+      margin-top: 4px;
+      font-size: 12px;
+    }
+
+    .pill {
+      padding: 7px 11px;
+      border-radius: 999px;
+      font-size: 11px;
+      font-weight: 800;
+    }
+
+    .pill.teal { background: rgba(102,194,165,0.15); color: #9be4ce; }
+    .pill.amber { background: rgba(242,166,90,0.15); color: #ffd6a7; }
+    .pill.coral { background: rgba(255,122,89,0.14); color: #ffc6b6; }
+
+    .pipeline {
+      display: grid;
+      gap: 12px;
+    }
+
+    .stage {
+      padding: 14px;
+      border-radius: 18px;
+      background: rgba(255,255,255,0.03);
+      border: 1px solid var(--line);
+    }
+
+    .stage strong {
+      display: block;
+      margin-bottom: 8px;
+      font-size: 14px;
+    }
+
+    .asset-grid {
+      display: grid;
+      gap: 12px;
+    }
+
+    .asset {
+      border-radius: 20px;
+      padding: 16px;
+      background: linear-gradient(180deg, rgba(26,40,45,0.96), rgba(20,31,35,0.96));
+      border: 1px solid rgba(200, 225, 216, 0.08);
+    }
+
+    .asset strong {
+      display: block;
+      font-size: 15px;
+    }
+
+    .asset .meta {
+      margin-top: 10px;
+      display: flex;
+      gap: 8px;
+      flex-wrap: wrap;
+    }
+  </style>
+</head>
+<body>
+  <main class="frame">
+    <aside class="sidebar">
+      <div class="brand">
+        <small>StoryForge</small>
+        <strong>Studio Workbench</strong>
+      </div>
+      <div class="nav">
+        <div class="nav-item">Explore</div>
+        <div class="nav-item active">Production</div>
+        <div class="nav-item">Knowledge</div>
+        <div class="nav-item">Assistants</div>
+        <div class="nav-item">Models</div>
+        <div class="nav-item alert">3 accounts pending</div>
+      </div>
+      <div class="sidebar-footer">
+        Best for a team that wants traceable content operations: one material source, many assistant outputs, one clear knowledge map.
+      </div>
+    </aside>
+
+    <section class="content">
+      <header class="topbar">
+        <div class="headline">
+          <h1>Run your copywriting system like a studio.</h1>
+          <p>Ingest material, route it through the right knowledge bases, and send different assistants to generate platform-specific outputs.</p>
+        </div>
+        <div class="top-actions">
+          <button class="button">Add material</button>
+          <button class="button primary">Generate outputs</button>
+        </div>
+      </header>
+
+      <section class="stats">
+        <div class="stat"><span>Materials this week</span><strong>42</strong></div>
+        <div class="stat"><span>Knowledge bases</span><strong>9</strong></div>
+        <div class="stat"><span>Active assistants</span><strong>6</strong></div>
+        <div class="stat"><span>Reusable outputs</span><strong>128</strong></div>
+      </section>
+
+      <section class="workspace">
+        <article class="card">
+          <h2>Material intake</h2>
+          <p>Every source enters here first. Links, files, and text all converge into a transcript-centered asset.</p>
+          <div class="composer">Paste a Douyin or YouTube link here.
+
+Knowledge target: Founder Hooks + Proof Framing
+Assistant route: AI Startup Scriptwriter + Sales CTA Finisher
+Analysis model: Local GLM-5</div>
+          <div class="option-grid">
+            <div class="option">
+              <div>
+                <strong>VC founder talking-head sample</strong>
+                <small>12m · transcript ready · hook density 8.9/10</small>
+              </div>
+              <span class="pill teal">Linked</span>
+            </div>
+            <div class="option">
+              <div>
+                <strong>High-conversion CTA collection</strong>
+                <small>text note · 38 CTA endings extracted</small>
+              </div>
+              <span class="pill amber">Text</span>
+            </div>
+          </div>
+        </article>
+
+        <article class="card">
+          <h2>Knowledge routing</h2>
+          <p>Make the knowledge graph visible. Users should always know which assistant can read which material pool.</p>
+          <div class="pipeline">
+            <div class="stage">
+              <strong>1. Transcript clean-up</strong>
+              Remove filler, split hooks, isolate claims, normalize CTA language.
+            </div>
+            <div class="stage">
+              <strong>2. Style abstraction</strong>
+              Extract rhythm, sentence energy, authority level, objection handling patterns.
+            </div>
+            <div class="stage">
+              <strong>3. Knowledge base sync</strong>
+              Founder Hooks, Sales Emotion, Short CTA, Proof Framing.
+            </div>
+            <div class="stage">
+              <strong>4. Assistant generation</strong>
+              Bind one or more KBs, assign model, generate title/script/variant bundle.
+            </div>
+          </div>
+        </article>
+
+        <article class="card">
+          <h2>Output assets</h2>
+          <p>One material source should fan out into multiple reusable content assets immediately.</p>
+          <div class="asset-grid">
+            <div class="asset">
+              <strong>AI Startup Scriptwriter</strong>
+              <small>Bound to Founder Hooks + Proof Framing · Model: Local GLM-5</small>
+              <div class="meta">
+                <span class="pill coral">60s oral script</span>
+                <span class="pill teal">3 title variants</span>
+                <span class="pill amber">Closing CTA</span>
+              </div>
+            </div>
+            <div class="asset">
+              <strong>Emotion-driven Sales Closer</strong>
+              <small>Bound to Sales Emotion + Short CTA · Model: Gemini via local proxy</small>
+              <div class="meta">
+                <span class="pill amber">Private-domain follow-up</span>
+                <span class="pill coral">Urgency rewrite</span>
+              </div>
+            </div>
+            <div class="asset">
+              <strong>Authority-led Brand Explainer</strong>
+              <small>Bound to Proof Framing only · Safer for educational content</small>
+              <div class="meta">
+                <span class="pill teal">Long caption</span>
+                <span class="pill amber">Carousel outline</span>
+              </div>
+            </div>
+          </div>
+        </article>
+      </section>
+    </section>
+  </main>
+</body>
+</html>

deploy/cleanup_legacy_fastgpt_runtime.sh

@@ -0,0 +1,65 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+LEGACY_CONTAINERS=(
+  storyforge-fastgpt-plugin
+  storyforge-sandbox
+  storyforge-pg
+  storyforge-minio
+  storyforge-redis
+  storyforge-mongo
+)
+
+LEGACY_NETWORK="storyforge-net"
+COLLECTOR_HEALTH_URL="${COLLECTOR_HEALTH_URL:-http://127.0.0.1:8081/healthz}"
+N8N_HEALTH_URL="${N8N_HEALTH_URL:-http://127.0.0.1:5670/healthz}"
+APPLY="${APPLY:-0}"
+
+log() {
+  printf '[cleanup] %s\n' "$*"
+}
+
+check_url() {
+  local url="$1"
+  curl -fsS "$url" >/dev/null
+}
+
+log "preflight: verifying StoryForge collector and n8n"
+check_url "$COLLECTOR_HEALTH_URL"
+check_url "$N8N_HEALTH_URL"
+
+log "legacy containers:"
+for container in "${LEGACY_CONTAINERS[@]}"; do
+  if docker ps -a --format '{{.Names}}' | grep -Fxq "$container"; then
+    status="$(docker inspect --format '{{.State.Status}}' "$container")"
+    printf '  - %s (%s)\n' "$container" "$status"
+  else
+    printf '  - %s (missing)\n' "$container"
+  fi
+done
+
+if [[ "$APPLY" != "1" ]]; then
+  log "dry run complete. Re-run with APPLY=1 to stop and remove legacy containers."
+  exit 0
+fi
+
+for container in "${LEGACY_CONTAINERS[@]}"; do
+  if docker ps -a --format '{{.Names}}' | grep -Fxq "$container"; then
+    log "removing $container"
+    docker rm -f "$container" >/dev/null
+  fi
+done
+
+if docker network inspect "$LEGACY_NETWORK" >/dev/null 2>&1; then
+  if [[ "$(docker network inspect "$LEGACY_NETWORK" --format '{{len .Containers}}')" == "0" ]]; then
+    log "removing empty network $LEGACY_NETWORK"
+    docker network rm "$LEGACY_NETWORK" >/dev/null
+  else
+    log "network $LEGACY_NETWORK still has attached containers; leaving it in place"
+  fi
+fi
+
+log "post-check: verifying StoryForge collector and n8n"
+check_url "$COLLECTOR_HEALTH_URL"
+check_url "$N8N_HEALTH_URL"
+log "legacy FastGPT runtime cleanup completed"

docker-compose.yml

@@ -1,56 +1,30 @@
-version: "3.9"
-
 services:
-  mongo:
+  n8n:
-    image: mongo:6
+    image: ${N8N_IMAGE:-docker.n8n.io/n8nio/n8n:latest}
-    container_name: storyforge-mongo
+    container_name: storyforge-n8n
-    restart: unless-stopped
-    ports:
-      - "27017:27017"
-    volumes:
-      - ./data/mongo:/data/db
-
-  vectorDB:
-    image: pgvector/pgvector:pg16
-    container_name: storyforge-pgvector
     restart: unless-stopped
     environment:
-      POSTGRES_DB: ${POSTGRES_DB:-fastgpt}
+      N8N_HOST: ${N8N_HOST:-0.0.0.0}
-      POSTGRES_USER: ${POSTGRES_USER:-postgres}
+      N8N_PORT: 5678
-      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-postgres}
+      N8N_PROTOCOL: ${N8N_PROTOCOL:-http}
+      WEBHOOK_URL: ${WEBHOOK_URL:-http://127.0.0.1:5670/}
+      GENERIC_TIMEZONE: ${GENERIC_TIMEZONE:-Asia/Shanghai}
+      TZ: ${TZ:-Asia/Shanghai}
+      N8N_SECURE_COOKIE: ${N8N_SECURE_COOKIE:-false}
+      N8N_ENFORCE_SETTINGS_FILE_PERMISSIONS: ${N8N_ENFORCE_SETTINGS_FILE_PERMISSIONS:-false}
     ports:
-      - "5432:5432"
+      - "5670:5678"
     volumes:
-      - ./data/pg:/var/lib/postgresql/data
+      - ./data/n8n:/home/node/.n8n
-
+      - ./n8n:/workspace/n8n:ro
-  redis:
-    image: redis:7-alpine
-    container_name: storyforge-redis
-    restart: unless-stopped
-    ports:
-      - "6379:6379"
-    volumes:
-      - ./data/redis:/data
-
-  minio:
-    image: minio/minio:RELEASE.2025-02-07T23-21-09Z
-    container_name: storyforge-minio
-    restart: unless-stopped
-    command: server /data --console-address ":9001"
-    environment:
-      MINIO_ROOT_USER: ${MINIO_ROOT_USER:-minioadmin}
-      MINIO_ROOT_PASSWORD: ${MINIO_ROOT_PASSWORD:-minioadmin}
-    ports:
-      - "9000:9000"
-      - "9001:9001"
-    volumes:
-      - ./data/minio:/data
 
   collector:
     build:
       context: ./collector-service
     container_name: storyforge-collector
     restart: unless-stopped
+    depends_on:
+      - n8n
     environment:
       DATA_DIR: /data/collector
       DATABASE_PATH: /data/collector/storyforge.db
@@ -58,40 +32,35 @@ services:
       LOCAL_OPENAI_BASE_URL: ${LOCAL_OPENAI_BASE_URL:-http://host.docker.internal:8317/v1}
       LOCAL_OPENAI_MODEL: ${LOCAL_OPENAI_MODEL:-GLM-5}
       LOCAL_OPENAI_API_KEY: ${LOCAL_OPENAI_API_KEY:-}
-      FASTGPT_BASE_URL: ${FASTGPT_BASE_URL:-http://host.docker.internal:3000}
+      N8N_BASE_URL: ${COLLECTOR_N8N_BASE_URL:-http://n8n:5678}
-      FASTGPT_DATASET_API_KEY: ${FASTGPT_DATASET_API_KEY:-}
+      N8N_ANALYSIS_WEBHOOK_PATH: ${N8N_ANALYSIS_WEBHOOK_PATH:-/webhook/storyforge-analysis}
+      N8N_REAL_CUT_WEBHOOK_PATH: ${N8N_REAL_CUT_WEBHOOK_PATH:-/webhook/storyforge-real-cut}
+      N8N_AI_VIDEO_WEBHOOK_PATH: ${N8N_AI_VIDEO_WEBHOOK_PATH:-/webhook/storyforge-ai-video}
+      N8N_CONTENT_SOURCE_SYNC_WEBHOOK_PATH: ${N8N_CONTENT_SOURCE_SYNC_WEBHOOK_PATH:-/webhook/storyforge-content-source-sync}
+      ORCHESTRATOR_SHARED_SECRET: ${ORCHESTRATOR_SHARED_SECRET:-storyforge-local-secret}
+      CUTVIDEO_BASE_URL: ${CUTVIDEO_BASE_URL:-}
+      CUTVIDEO_API_KEY: ${CUTVIDEO_API_KEY:-}
+      CUTVIDEO_BASE_CONFIG: ${CUTVIDEO_BASE_CONFIG:-example.job.yaml}
+      CUTVIDEO_POLL_INTERVAL_SEC: ${CUTVIDEO_POLL_INTERVAL_SEC:-10}
+      CUTVIDEO_MAX_WAIT_SEC: ${CUTVIDEO_MAX_WAIT_SEC:-1800}
+      CUTVIDEO_UPLOAD_TIMEOUT_SEC: ${CUTVIDEO_UPLOAD_TIMEOUT_SEC:-1800}
+      HUOBAO_BASE_URL: ${HUOBAO_BASE_URL:-http://host.docker.internal:5678}
       YTDLP_BIN: ${YTDLP_BIN:-yt-dlp}
       FFMPEG_BIN: ${FFMPEG_BIN:-ffmpeg}
       WHISPER_BIN: ${WHISPER_BIN:-}
       WHISPER_MODEL: ${WHISPER_MODEL:-/data/collector/models/ggml-base.en.bin}
+      ASR_HTTP_BASE_URL: ${ASR_HTTP_BASE_URL:-}
+      ASR_HTTP_TRANSCRIBE_PATH: ${ASR_HTTP_TRANSCRIBE_PATH:-/transcribe}
+      ASR_HTTP_FIELD_NAME: ${ASR_HTTP_FIELD_NAME:-wav}
+      ASR_HTTP_TIMEOUT_SEC: ${ASR_HTTP_TIMEOUT_SEC:-120}
+      HUOBAO_POLL_INTERVAL_SEC: ${HUOBAO_POLL_INTERVAL_SEC:-10}
+      HUOBAO_MAX_WAIT_SEC: ${HUOBAO_MAX_WAIT_SEC:-900}
     ports:
       - "8081:8081"
     volumes:
       - ./data/collector:/data/collector
     command: uvicorn app.main:app --host 0.0.0.0 --port 8081
 
-  fastgpt:
-    image: ghcr.io/labring/fastgpt:latest
-    container_name: storyforge-fastgpt
-    restart: unless-stopped
-    depends_on:
-      - mongo
-      - vectorDB
-      - redis
-      - minio
-    ports:
-      - "3000:3000"
-
-  sandbox:
-    image: ghcr.io/labring/fastgpt-sandbox:latest
-    container_name: storyforge-sandbox
-    restart: unless-stopped
-
-  fastgpt-plugin:
-    image: ghcr.io/labring/fastgpt-plugin:latest
-    container_name: storyforge-fastgpt-plugin
-    restart: unless-stopped
-
   cli-proxy-api:
     image: ${CLIPROXY_IMAGE:-storyforge/cli-proxy-api:patched}
     container_name: storyforge-cliproxyapi

docs/AUDIT_2026-03-18.md

@@ -0,0 +1,191 @@
+# StoryForge 现状审计
+
+日期：2026-03-18
+更新：2026-03-20
+
+## 结论
+
+当前应以 `/Users/kris/code/StoryForge-gitea` 作为主工作区继续推进，而不是 `/Users/kris/code/Fastgpt`。后者更像一次不完整的导入快照，前者才是可持续开发的真实仓库。
+
+## 现有功能归位
+
+### 1. `collector-service` 之前承担的功能
+
+- 账号注册、登录、审批
+- 本地模型配置
+- 知识库、智能体、任务管理
+- 视频链接/上传视频/文本三类入口
+- 下载器、ffmpeg、whisper.cpp 风格的本地处理调用
+- Android OTA 查询/发布
+
+### 2. FastGPT 实际承担的功能
+
+- 仅承担“数据集/文档同步”的外部依赖角色
+- 代码痕迹集中在：
+  - `collector-service/app/fastgpt.py`
+  - `docker-compose.yml`
+  - 若干 `fastgpt_*` 字段
+
+结论：FastGPT 并不是业务内核，适合迁移后整体删除。
+
+### 3. n8n 适合接管的功能
+
+- 任务触发
+- 工作流分流
+- 外部能力编排入口
+- 任务执行顺序控制
+
+不适合承载：
+
+- 用户、项目、Agent、知识库、任务、历史记录的主数据
+- 业务状态唯一真相源
+
+结论：应采用“业务状态在 `collector-service`，流程编排在 `n8n`”的分层。
+
+## 多用户与数据边界
+
+当前已明确采用：
+
+- `accounts`
+- `projects`
+- `knowledge_bases`
+- `assistants`
+- `content_sources`
+- `jobs`
+- `job_events`
+
+推荐模型：`user + project`。
+
+理由：
+
+- 只做 `user` 级隔离，会导致一个用户内部不同内容工作流难以再分边界
+- `project` 可以自然承接“一个创作者方向 / 一个客户 / 一个账号矩阵 / 一个内容实验”
+- `assistant`、`knowledge_base`、`job`、`content_source` 都能挂到 `project`，便于后续扩展协作空间
+
+## 外部链路审计
+
+### 1. 下载器
+
+- 已存在，不需要重写
+- 现阶段通过 `yt-dlp` 命令集成
+- 账号级内容源同步同样复用 `yt-dlp --flat-playlist`，不额外维护抓取器
+
+### 2. ASR
+
+- 现有实现已部署，入口现已标准化为“两级优先级”：
+  - 优先调用 HTTP ASR 服务
+  - HTTP 不可用或返回空结果时，回退到 `whisper.cpp` 命令行
+- 本次已按 `mac-whisper-service` 的 `/transcribe` 协议完成接入，并用任务 `job_e95f9b5579fd4c5aa40f04de611e9fd0` 验证 `artifacts.asr_backend=http`
+- 进一步联调发现真实长视频转写耗时约 44 秒，因此 `collector` 侧 `ASR_HTTP_TIMEOUT_SEC` 默认值已提升到 120 秒；本机 `mac-whisper-service` 运行时也需要把 `WHISPER_TIMEOUT_MS` 提升到 `120000`
+- 修复后再次验证成功，任务 `job_bb405e2e878849e38c4bb31f7781e1e3` 已写入真实 HTTP ASR 文本并记录 `artifacts.asr_http_payload`
+- `collector` 运行镜像已补上 `ffmpeg` 和 `yt-dlp`，避免容器内缺依赖导致音频抽取或下载失效
+
+### 2.1 内容源账号同步
+
+- 已新增 `content_source_sync_pipeline`
+- 用户可通过 `POST /v2/pipelines/content-source-sync` 提交创作者账号 URL
+- 后端会创建父任务，使用 `yt-dlp --flat-playlist` 抓取最近 N 条视频 URL，再自动派生用户自己的 `video_link` 子分析任务
+- `jobs.parent_job_id` 已加入数据模型，父子任务关系可持久化查询
+- 已用 bilibili 账号 URL 联调验证：
+  - 父任务：`job_b02109cf9e8244fbb5b86f184a7c7574`
+  - 子任务：`job_7f169db61af441f8a7f186d03db2d91c`、`job_28c47774028441378a3974860c375ab7`
+
+结论：账号级调度不再是空白能力，但目前只验证了 `bilibili` URL 形态，抖音 / 小红书仍需真链路核实。
+
+### 3. Windows `cutvideo`
+
+- 仓库：`/Users/kris/code/cutvideo`
+- 具备清晰 API：
+  - `POST /api/jobs`
+  - `POST /api/uploads`
+  - `GET /api/tasks/{task_id}`
+  - `GET /api/runs/{run_id}`
+- 适合集成为“由 StoryForge 后端授权调用的局域网剪辑能力”
+
+当前状态：
+
+- StoryForge 已支持把 `upload_video` 或已完成的 `video_link` 源素材自动上传到 `cutvideo`
+- `real-cut` 任务可直接传 `source_job_id`，由后端完成 staging 后再提交到剪辑服务
+- Windows 机器已部署带 `POST /api/uploads` 的 `cutvideo` 版本，并完成局域网联调
+
+### 3.1 `douyin` 工作台
+
+- `collector-service` 已具备 `/v2/douyin/*` 工作台接口
+- 已补充两类关键联调增强：
+  - 分享文案中的 URL 自动提取与归一化
+  - public 页面命中抖音反爬挑战时的显式诊断返回
+- 真实 smoke 结果表明，纯 public 主页抓取会落到 `byted_acrawler` 挑战页，而不是正常 profile 数据页
+- 同时，`manual_profile_payload + manual_work_payloads` 已验证可完成账号入库、分析报告生成、相似账号搜索和对标关系写入
+- 现已新增浏览器辅助采集工具 `/Users/kris/code/StoryForge-gitea/scripts/douyin-browser-capture/capture_and_sync.mjs`
+- 同目录现已新增本地控制台 `/Users/kris/code/StoryForge-gitea/scripts/douyin-browser-capture/control_panel.mjs`
+- 该工具使用真实 Playwright Chromium 会话打开抖音页面，允许人工登录 / 过滑块后继续自动提取 `<script>` JSON、网络 JSON、视频详情页和创作者中心页数据
+- 浏览器工具最终直接调用现有 `/v2/douyin/accounts/sync`，不新增第二套持久化模型
+- 控制台模式已经支持“开始采集 -> 浏览器登录 -> 网页点继续 -> 自动同步”的点击式流程，并修复了 ready-file 提前点击的竞态
+
+结论：`douyin` 方向不再是“接口存在但不可用”，当前状态是“public 直抓受反爬限制，但人工采集兜底链已跑通”。
+
+### 4. `huobao-drama`
+
+- 旧改版位置：`/Users/kris/code/huobaoduanju/huobao-drama-master`
+- 最新 upstream：`/Users/kris/code/huobao-drama-upstream`
+- 旧改版主要多了一套 `ad_workflow` 方向，和当前 StoryForge MVP 不完全对齐
+- 最新版已具备：
+  - `POST /api/v1/dramas`
+  - `POST /api/v1/images`
+  - `GET /api/v1/images/{id}`
+  - `POST /api/v1/videos`
+  - `GET /api/v1/videos/{id}`
+  - `reference_mode=first_last`
+
+本次真实联调里，旧改版为了兼容 `qnaigc` 需要补 4 个点：
+
+- `pkg/image/openai_image_client.go`
+- `application/services/image_generation_service.go`
+- `pkg/video/openai_sora_client.go`
+- `application/services/video_generation_service.go`
+
+核对结果：
+
+- 以上 4 个文件与本机 upstream 同名文件在补丁前没有明显结构分叉
+- 当前差异基本就是 `qnaigc` 图片异步查询、Kling 视频 JSON 协议、结果 URL 解析、远程首尾帧 URL 保留这几处兼容逻辑
+
+结论：这批补丁是可移植补丁，MVP 已在旧改版实例上验证通过；下一步应把同样补丁迁到最新版 `huobao-drama-upstream`，而不是继续在旧目录长期演进。
+
+补充验证（2026-03-20）：
+
+- `/Users/kris/code/huobao-drama-upstream` 当前工作分支为 `codex/qnaigc-compat`
+- 该分支已包含 qnaigc 图片异步查询、Kling 视频协议、结果 URL 解析、远程首尾帧保留等补丁
+- 另外补了 `ResourceTransferService` 的 no-op MinIO 转存方法，当前 `go build ./...` 已可全量通过
+- 使用复制自旧目录的 `config.yaml + drama_generator.db + data/storage` 在隔离目录启动了 upstream 实例，地址为 `http://127.0.0.1:5681`
+- 上游实例健康检查通过，`POST /api/v1/dramas` 可正常创建剧本
+- 新的图片和视频生成请求已能走到 provider 调用层，但当前复制出的 AI 配置凭证返回 `403 access denied for invalid user`
+- 进一步在旧改版隔离实例 `http://127.0.0.1:5682` 上重放了 fresh 图片请求，返回同样的 `403 access denied for invalid user`
+- 结论因此进一步收敛：当前 blocker 不是 upstream 回归，而是外部图片/视频凭证已失效
+- 已在 `huobao-drama-upstream` 增加按服务类型的运行时覆盖能力，可用 `HUOBAO_TEXT_* / HUOBAO_IMAGE_* / HUOBAO_VIDEO_*` 环境变量接管数据库中的 AI 配置
+- 已在 `huobao-drama-upstream` 固化 `scripts/run_storyforge_smoke.sh`，可自动复制旧库配置与数据、起隔离实例并校验 `/health`
+
+结论更新：`huobao-drama-upstream` 的代码级兼容迁移已经完成，当前剩余 blocker 是外部图片/视频凭证失效，导致无法用“旧配置副本”继续 fresh 生成；但新的运行时 env 覆盖路径已经就位，后续补新 key 不需要再手改 SQLite。
+
+## 当前已完成迁移面
+
+- FastGPT 运行时依赖已从 `collector-service` 主代码中剥离
+- 旧 FastGPT 运行残留容器 `storyforge-fastgpt-plugin / sandbox / pg / minio / redis / mongo` 已于 2026-03-20 实际下线并清理
+- 数据库已支持 `project/content_source/job_events`
+- `collector-service` 已增加：
+  - `n8n` 触发
+  - `cutvideo` 集成 client
+  - `huobao-drama` 集成 client
+  - 内部编排接口
+- `docker-compose.yml` 已改为 `collector + n8n + cli-proxy-api`
+- `n8n` 工作流导出文件已纳入仓库
+- `collector-service` 的 live 运行态已回归到 `StoryForge-gitea` 自身源码构建，不再依赖 `/Users/kris/code/Fastgpt/collector-service/app` 的临时 bind mount
+- `collector-service` 现已在 live `8081` 提供 `/v2/douyin/*` 接口，并保留原有 `real-cut / ai-video / content-source-sync` 路由
+- Android Explore 页已补上“账号同步”入口，可直接创建内容源账号同步任务，并支持平台、主页链接、账号标识、最大抓取条数、跳过已存在、自动触发分析等参数
+- Android 工作区缺失的 `com.aiglasses.app.data` 数据层已从同源代码补回，当前 `./gradlew :app:compileDebugKotlin` 与 `:app:assembleDebug` 均已通过，并产出 `app-debug.apk`
+
+## 当前主要风险
+
+1. 小红书账号级内容源还未做真实平台验证
+2. `douyin` public 直抓仍受反爬限制，但现在已经有“真实浏览器 + 人工登录 + 自动提取 + 回写现有工作台”的可落地协作链
+3. `huobao-drama-upstream` 已完成代码迁移并可编译，但 fresh smoke 受外部图片/视频凭证 `403 invalid user` 阻塞
+4. Android 端目前已能完成 Debug APK 构建，但仍缺少真机安装和功能回归验证

docs/IMPLEMENTATION_PLAN_2026-03-18.md

@@ -0,0 +1,97 @@
+# StoryForge 分阶段实施计划
+
+日期：2026-03-18
+
+## Phase 0: 审计与基线收拢
+
+- 确认主工作区
+- 识别 FastGPT 真实职责
+- 识别多用户、多项目需要的主数据模型
+- 对比 `huobao-drama` 旧改版与 upstream
+- 审计 `cutvideo` 接口能力
+
+状态：已完成
+
+## Phase 1: 业务后端改造成主状态中心
+
+- 引入 `projects`
+- 引入 `content_sources`
+- 引入 `job_events`
+- 让 `knowledge_bases / assistants / jobs` 全部 project 化
+- 去掉 `collector-service` 中的 FastGPT 运行时逻辑
+- 增加 `agents` 别名接口，统一 Agent 语义
+
+状态：已完成首版
+
+## Phase 2: n8n 接管流程编排
+
+- 公共任务创建接口只负责建任务并触发工作流
+- `n8n` 负责分发：
+  - `analysis_pipeline`
+  - `real_cut_pipeline`
+  - `ai_video_pipeline`
+- 业务步骤落在 `collector-service` 内部接口，保证状态统一入库
+
+状态：已完成首版
+
+## Phase 3: 内容分析主线 MVP
+
+- 支持文本
+- 支持视频链接
+- 支持上传视频
+- 接下载器
+- 接本地 ASR
+- 接本地 LLM
+- 产出：
+  - transcript
+  - style_summary
+  - analysis
+  - rewrite
+  - storyboards
+
+状态：已完成首版
+
+## Phase 4: 实拍自动剪辑主线 MVP
+
+- 建立 `real_cut` 任务类型
+- 通过 `n8n -> collector -> cutvideo` 调度 Windows 机器
+- 记录 `task_id / run_id / 结果产物`
+
+状态：已完成 API 级集成
+
+待补：
+
+- 用户上传素材到 Windows 侧的文件转运闭环
+
+## Phase 5: AI 自动生成视频主线 MVP
+
+- 建立 `ai_video` 任务类型
+- 从分析结果或直接 brief 生成分镜
+- 调 `huobao-drama`：
+  - 创建 drama
+  - 生成首帧
+  - 生成尾帧
+  - 基于首尾帧生成视频
+- 结果回写任务
+
+状态：已完成 API 级集成
+
+## Phase 6: 删除 FastGPT 运行依赖
+
+- 删除代码依赖
+- 删除 compose 服务
+- 删除环境变量
+- 删除 README 说明
+
+状态：已完成主仓库首版
+
+## Phase 7: 联调与验证
+
+- Python 语法检查
+- Compose 配置检查
+- `collector-service` 本地启动
+- `n8n` workflow 导入
+- Windows `cutvideo` 局域网调度
+- `huobao-drama` 本机调用
+
+状态：进行中

docs/LAN_E2E_GUIDE_2026-03-18.md

@@ -0,0 +1,312 @@
+# StoryForge 本地 / 局域网联调说明
+
+日期：2026-03-18
+
+## 1. 准备 `.env`
+
+复制：
+
+```bash
+cd /Users/kris/code/StoryForge-gitea
+cp .env.example .env
+```
+
+至少确认这些变量：
+
+- `N8N_BASE_URL=http://127.0.0.1:5670`，用于你在宿主机单独运行 `collector-service`
+- `COLLECTOR_N8N_BASE_URL=http://n8n:5678`，用于 Docker 里的 `collector`
+- `ORCHESTRATOR_SHARED_SECRET=storyforge-local-secret`
+- `CUTVIDEO_BASE_URL=http://<windows-lan-ip>:7860`
+- `CUTVIDEO_API_KEY=` 如果 Windows 服务启用了鉴权
+- `HUOBAO_BASE_URL=http://127.0.0.1:5678`
+- `WHISPER_BIN=` 指向你现有本地 ASR 可执行文件时填写
+- `ASR_HTTP_BASE_URL=` 如果你已有常驻 ASR 服务，填写它的基地址
+- `ASR_HTTP_TRANSCRIBE_PATH=/transcribe`
+- `ASR_HTTP_FIELD_NAME=wav`
+- `ASR_HTTP_TIMEOUT_SEC=120`
+
+说明：
+
+- 如果你单独重建 `collector`，要确保运行时仍带上 `CUTVIDEO_BASE_URL`，否则容器会退回空值
+- `collector` 容器不要直接复用宿主机的 `N8N_BASE_URL=http://127.0.0.1:5670`，否则容器内会连回自己并导致 webhook 调度失败
+- 当前已验证可用的 Windows `cutvideo` 地址是 `http://192.168.31.18:7860`
+- 当前已验证可用的本机 HTTP ASR 入口是 `http://host.docker.internal:8088/transcribe`
+- 如果你用的是本机 `mac-whisper-service`，建议同时以 `WHISPER_TIMEOUT_MS=120000` 启动，否则长视频会直接 504
+
+## 2. 启动基础服务
+
+```bash
+cd /Users/kris/code/StoryForge-gitea
+docker compose up -d --build
+```
+
+检查：
+
+- `collector-service`：`http://127.0.0.1:8081/healthz`
+- `n8n`：`http://127.0.0.1:5670`
+- `cli-proxy-api`：`http://127.0.0.1:8317`
+- 本机 `huobao-drama`：`http://127.0.0.1:5678/health`
+
+## 3. 导入 n8n workflows
+
+从 `n8n/workflows/` 导入：
+
+- `storyforge-analysis.json`
+- `storyforge-real-cut.json`
+- `storyforge-ai-video.json`
+- `storyforge-content-source-sync.json`
+
+导入后：
+
+- 检查每个 HTTP Request 节点的 `X-Orchestrator-Secret`
+- 如果你改了 `.env` 的 secret，这里必须同步
+
+## 4. 登录与审批
+
+默认超级管理员：
+
+- 用户名：`kris`
+- 密码：`Asd123456.`
+
+新用户注册后，需要用超级管理员审批。
+
+## 5. 内容分析链路验证
+
+### 文本
+
+调用 `POST /v2/explore/text`
+
+预期：
+
+- 任务创建成功
+- `n8n` webhook 被触发
+- 任务最终进入 `completed`
+- 知识库文档里出现 transcript / style_summary / analysis / storyboards
+
+已验证样例：
+
+- `job_203bc8e9b20f4b1cbbc6cf7da79e46f4`
+
+### 视频链接
+
+调用 `POST /v2/explore/video-link`
+
+前提：
+
+- `yt-dlp` 可用
+- `ffmpeg` 可用
+- ASR 可调用
+
+已验证样例：
+
+- `job_bb405e2e878849e38c4bb31f7781e1e3` (`artifacts.asr_backend=http`)
+
+### 上传视频
+
+调用 `POST /v2/explore/upload-video`
+
+预期与视频链接类似，但素材来源为本地上传
+
+## 6. 内容源账号同步验证
+
+调用 `POST /v2/pipelines/content-source-sync`
+
+推荐最小请求体：
+
+```json
+{
+  "source_url": "https://space.bilibili.com/546195/video",
+  "platform": "bilibili",
+  "title": "Bilibili Creator Sync Smoke",
+  "max_items": 2,
+  "skip_existing": true,
+  "auto_trigger_analysis": true
+}
+```
+
+预期：
+
+- 创建一个 `content_source_sync` 父任务
+- `n8n` 触发 `content_source_sync_pipeline`
+- 父任务写回 `discovered_videos / child_job_ids / queued_job_ids`
+- 子任务以 `parent_job_id` 挂到父任务下，并自动进入分析主线
+
+已验证样例：
+
+- 父任务：`job_b02109cf9e8244fbb5b86f184a7c7574`
+- 子任务：`job_7f169db61af441f8a7f186d03db2d91c`
+- 子任务：`job_28c47774028441378a3974860c375ab7`
+
+## 6.1 `douyin` 账号工作台验证
+
+基础接口：
+
+- `POST /v2/douyin/accounts/sync`
+- `POST /v2/douyin/accounts/{account_id}/analysis`
+
+说明：
+
+- `profile_url` 现在支持直接传分享文案，后端会自动提取里面的 URL
+- 如果 public 页面命中抖音反爬挑战，接口会返回 `public_profile_anti_bot_challenge`
+- 遇到挑战页时，继续可用的路径是 `manual_profile_payload`、`manual_work_payloads` 和 `manual_creator_pages`
+
+已验证样例：
+
+- public 页面 smoke：返回 `public_profile_anti_bot_challenge`
+- 手工导入账号：`dyacct_c2b62842b228406cb48f05fac16fdfdf`
+- 手工账号分析报告：`dyreport_10d6b8d2d52a404192f54a3a05d44546`
+- 相似账号搜索：`dysearch_c247b75db0df49429a1d127407fe4486`
+- 对标关系：`dyrel_c8df266341e74237b99c880eb4b572d8`
+
+浏览器辅助采集：
+
+```bash
+cd /Users/kris/code/StoryForge-gitea/scripts/douyin-browser-capture
+npm install
+npx playwright install chromium
+npm run control-panel
+```
+
+浏览器打开：
+
+```text
+http://127.0.0.1:3618
+```
+
+控制台步骤：
+
+1. 填写抖音主页链接和 StoryForge 账号
+2. 如需查看采集结果，不用离开这个页面；下半部分 `Douyin Workbench` 会展示账号列表、Agent 结论、快照详情和对标结果
+3. `作品工作台` 支持高分榜、最新榜和全部作品切换，并支持多种排序方式
+4. 点击“自动分析高分作品”后，每条高分作品下会补齐商业判断、复刻建议、运营动作和风险提醒
+2. 点击 `开始采集`
+3. 在弹出的 Chromium 里登录或通过挑战页
+4. 回到控制台点击 `已完成登录，继续采集`
+5. 等待 `summary.json` 和可选的 `storyforge-sync-response.json`
+
+命令行方式仍然保留：
+
+```bash
+cd /Users/kris/code/StoryForge-gitea/scripts/douyin-browser-capture
+npm run capture -- \
+  --profile-url https://www.douyin.com/user/your_account \
+  --storyforge-username kris \
+  --storyforge-password 'Asd123456.'
+```
+
+说明：
+
+- 脚本会打开真实 Chromium 会话，默认复用 `~/.storyforge/douyin-playwright` 登录态
+- 如果出现扫码登录、滑块或挑战页，先在浏览器里人工完成，再回终端继续
+- 脚本会保存 `profile-bundle.json`、`storyforge-sync-request.json` 和同步响应
+- 当前已完成 headless 最小 smoke，输出目录：
+  - `/tmp/storyforge-douyin-capture-smoke/2026-03-20T06-49-37.705Z-storyforge_test_001`
+- 当前已完成本地控制台 smoke，输出目录：
+  - `/Users/kris/code/StoryForge-gitea/output/playwright/douyin/control-panel/run-mmyzplxp-cw0o7q/2026-03-20T14-24-13.174Z-storyforge_test_001`
+  - `/Users/kris/code/StoryForge-gitea/output/playwright/douyin/control-panel/run-mmyzshsp-c6vdhi/2026-03-20T14-26-27.792Z-storyforge_test_001`
+- 控制台模式已经修复“提前点击继续导致 ready 信号丢失”的竞态，早于等待点按钮也不会卡死
+
+## 7. `cutvideo` 实拍剪辑链路验证
+
+调用 `POST /v2/pipelines/real-cut`
+
+当前 MVP 前提：
+
+- 方式 A：直接传 `input_dir`，它必须是 Windows `cutvideo` 机器可访问的目录
+- 方式 B：传 `source_job_id`，`collector-service` 会把 `upload_video` 或已完成的 `video_link` 源素材自动上传到 Windows `cutvideo`，再继续发起任务
+- 如果走方式 B，大文件上传超时由 `CUTVIDEO_UPLOAD_TIMEOUT_SEC` 控制
+
+预期：
+
+- 任务创建成功
+- 如果用了 `source_job_id`，任务 `artifacts.cutvideo_upload` 会记录 Windows staging 结果
+- `n8n` 调用 `collector-service` 内部 real-cut step
+- 后端记录 `provider_task_id`
+- 最终任务写回 `cutvideo_run`
+
+已验证样例：
+
+- `job_5ebd829c3f2144bca5c941183e75bdcd`
+- `job_01a6f283cbda42e4ae692b268b811a50` (`source_job_id` 自动 staging，本机 `cutvideo` 联调)
+- Windows 返回 `task_id=8d8f4a0cd5d9`
+- 运行目录 `20260318-093520-Windows cutvideo 联调样例`
+
+## 8. `huobao-drama` AI 视频链路验证
+
+调用 `POST /v2/pipelines/ai-video`
+
+推荐方式：
+
+- 先完成一个分析任务
+- 再把该分析任务的 `source_job_id` 传给 AI 视频任务
+
+预期：
+
+- 创建 drama
+- 每个分镜生成首帧、尾帧
+- 每个分镜生成视频
+- 最终 `job.result.rendered_scenes` 有完整结果
+
+已验证样例：
+
+- `job_01828c40377747cf914b51be360cc333`
+- `provider_task_id=10`
+- `video.task_id=qvideo-1380265978-1773799215825814468`
+- 最终视频已回写到 `job.result.rendered_scenes[0].video.video_url`
+
+补充说明（2026-03-20）：
+
+- `huobao-drama-upstream` 已在隔离目录用复制的旧配置和数据库起过实例，`/health` 正常
+- fresh 图片/视频生成请求已能进入 provider 调用，但当前复制出的图片/视频凭证返回 `403 invalid user`
+- 同样的 fresh 图片请求已在旧改版隔离实例 `http://127.0.0.1:5682` 上重放，结论一致，所以当前不是 upstream 回归问题
+- `huobao-drama-upstream` 现在支持 `HUOBAO_TEXT_* / HUOBAO_IMAGE_* / HUOBAO_VIDEO_*` 运行时覆盖数据库里的 AI 配置
+- `huobao-drama-upstream` 已新增 `/Users/kris/code/huobao-drama-upstream/scripts/run_storyforge_smoke.sh`，可自动复制旧目录配置和数据，在默认 `5681` 端口起隔离实例并校验 `/health`
+- 如果你要重新验证 upstream fresh 生成，优先给 huobao 进程补这些环境变量，再复跑即可
+
+推荐覆盖字段：
+
+- `HUOBAO_TEXT_PROVIDER / BASE_URL / API_KEY / MODELS`
+- `HUOBAO_IMAGE_PROVIDER / BASE_URL / API_KEY / MODELS`
+- `HUOBAO_VIDEO_PROVIDER / BASE_URL / API_KEY / MODELS`
+- 如需强制指定端点，还可补 `ENDPOINT / QUERY_ENDPOINT`
+
+## 9. 当前已知卡点
+
+- 抖音 public 页面直抓会命中反爬挑战；生产接入仍需要 cookie 或人工页面采集协助
+- 小红书账号级内容源还未做真实平台验证
+- `huobao-drama-upstream` 代码已迁移完成，但 fresh 生成仍受外部图片/视频凭证 `403 invalid user` 阻塞
+
+## 10. 旧 FastGPT 残留清理
+
+- 旧 FastGPT runtime 容器已在 2026-03-20 实际清理完成：
+  - `storyforge-fastgpt-plugin`
+  - `storyforge-sandbox`
+  - `storyforge-pg`
+  - `storyforge-minio`
+  - `storyforge-redis`
+  - `storyforge-mongo`
+- 清理脚本已纳入仓库：
+  - `/Users/kris/code/StoryForge-gitea/deploy/cleanup_legacy_fastgpt_runtime.sh`
+- 脚本会在清理前后校验：
+  - `http://127.0.0.1:8081/healthz`
+  - `http://127.0.0.1:5670/healthz`
+
+## 11. Android 本地构建
+
+如果你要在本机重新打 Android 包：
+
+```bash
+cd /Users/kris/code/StoryForge-gitea/android-app
+./gradlew :app:assembleDebug
+```
+
+当前已验证结果：
+
+- `:app:compileDebugKotlin` 通过
+- `:app:assembleDebug` 通过
+- APK 输出路径：
+  - `/Users/kris/code/StoryForge-gitea/android-app/app/build/outputs/apk/debug/app-debug.apk`
+
+补充说明：
+
+- 工作区根目录的 `.gitignore` 里保留了通用 `data/` 忽略规则，但已对 Android 源码目录 `android-app/app/src/main/java/com/aiglasses/app/data/` 做了白名单放行，避免误伤客户端代码

docs/MVP_STATUS_2026-03-18.md

@@ -0,0 +1,68 @@
+# StoryForge MVP 状态
+
+日期：2026-03-18
+更新：2026-03-20
+
+## 已跑通或已完成代码接通
+
+- 多用户账号体系
+- 审批机制
+- `user -> project -> assistant / knowledge base / job / content source` 数据模型
+- 文本 / 视频链接 / 上传视频 三类分析任务创建
+- 内容源账号同步任务创建与子任务派发
+- Android Explore 页已补上内容源账号同步入口
+- Android `com.aiglasses.app.data` 数据层已补回，`compileDebugKotlin` 与 `assembleDebug` 已通过
+- `n8n` 工作流导入、激活与触发接口
+- 本地下载器调用
+- 本地 `ffmpeg` / `whisper` 风格入口封装
+- HTTP ASR 常驻服务入口绑定
+- 本地大模型内容分析、二创文案、分镜生成
+- Windows `cutvideo` API 调度与结果回写接口
+- `upload_video -> source_job_id -> cutvideo` 自动 staging 闭环
+- `collector` live 运行态已从临时源码挂载切回 `StoryForge-gitea` 正式镜像
+- live `collector` 已挂出 `/v2/douyin/*` 能力并通过认证接口验证
+- `douyin` 支持从分享文案中提取 `profile_url`，并在 public 页面命中抖音反爬挑战时返回明确诊断
+- `douyin` 手工 payload 导入与账号分析链路已跑通
+- `douyin` 浏览器辅助采集工具已接入，可用真实 Playwright Chromium 会话采集主页 / 视频页并直接调用现有 `/v2/douyin/accounts/sync`
+- `douyin` 本地控制台已接入，可通过网页点击方式驱动浏览器辅助采集并查看最近运行结果
+- 本机 `huobao-drama` API 调度、首尾帧生成、视频生成与结果回写接口
+- FastGPT 运行时依赖删除
+- 旧 FastGPT 运行残留容器已实际下线
+
+## 已验证的真实任务
+
+- 分析链路：`job_203bc8e9b20f4b1cbbc6cf7da79e46f4`
+- HTTP ASR 分析链路：`job_e95f9b5579fd4c5aa40f04de611e9fd0`
+- 账号级内容源同步链路：`job_b02109cf9e8244fbb5b86f184a7c7574`
+- 账号级同步派生分析任务：`job_7f169db61af441f8a7f186d03db2d91c`、`job_28c47774028441378a3974860c375ab7`
+- 长视频 HTTP ASR 超时修复后链路：`job_bb405e2e878849e38c4bb31f7781e1e3`
+- 实拍剪辑链路：`job_5ebd829c3f2144bca5c941183e75bdcd`
+- 实拍剪辑自动 staging 联调：`job_01a6f283cbda42e4ae692b268b811a50`
+- AI 视频链路：`job_01828c40377747cf914b51be360cc333`
+- Windows `cutvideo` 部署后联调：`job_5838515ed5c34679acd55a52cfcd424b`
+- `douyin` 手工导入账号：`dyacct_c2b62842b228406cb48f05fac16fdfdf`
+- `douyin` 账号分析报告：`dyreport_10d6b8d2d52a404192f54a3a05d44546`
+- `douyin` 相似账号搜索：`dysearch_c247b75db0df49429a1d127407fe4486`
+- `douyin` 对标关系：`dyrel_c8df266341e74237b99c880eb4b572d8`
+- `huobao-upstream` 隔离 smoke 剧本：`drama_id=11` (`http://127.0.0.1:5681`)
+- `huobao-upstream` 隔离 smoke 启动脚本：`/Users/kris/code/huobao-drama-upstream/scripts/run_storyforge_smoke.sh`
+- Android Debug APK：`/Users/kris/code/StoryForge-gitea/android-app/app/build/outputs/apk/debug/app-debug.apk`
+- `douyin` 浏览器采集最小 smoke：`/tmp/storyforge-douyin-capture-smoke/2026-03-20T06-49-37.705Z-storyforge_test_001`
+- `douyin` 控制台 smoke：`/Users/kris/code/StoryForge-gitea/output/playwright/douyin/control-panel/run-mmyzplxp-cw0o7q/2026-03-20T14-24-13.174Z-storyforge_test_001`
+- `douyin` 控制台提前继续回归 smoke：`/Users/kris/code/StoryForge-gitea/output/playwright/douyin/control-panel/run-mmyzshsp-c6vdhi/2026-03-20T14-26-27.792Z-storyforge_test_001`
+
+## 尚未完全跑通
+
+- 小红书账号级内容源还未做真实平台验证
+- `douyin` public 主页直抓会命中 `public_profile_anti_bot_challenge`；当前已验证手工 payload 导入、分析、相似账号搜索和对标关系可作为可用兜底路径
+- `douyin` 浏览器辅助采集已经能真实输出 `profile-bundle.json / storyforge-sync-request.json`，但要拿到有效主页数据仍需要用户在浏览器里完成登录或挑战校验
+- `douyin` 控制台点击流已可用，但它仍然依赖本机可打开 Chromium 的环境，不适合放进纯 Docker 容器内部跑 GUI
+- `huobao-upstream` 已能全量编译；并且旧改版隔离实例也已重放确认，当前 fresh 生成被外部图片/视频凭证统一返回 `403 invalid user`
+- `huobao-upstream` 已新增 `HUOBAO_TEXT_* / HUOBAO_IMAGE_* / HUOBAO_VIDEO_*` 运行时覆盖能力，后续补新 key 可直接接管数据库配置
+- Android Debug 包已可本地构建，但尚未完成真机安装验证
+
+## 下一步优先级
+
+1. 更新 `huobao` 可用图片/视频凭证后，用新的 env 覆盖能力对 upstream 版补一轮完整 `drama -> images -> video` fresh smoke
+2. 补抖音真实账号的 cookie / 手工页面采集联调，以及小红书账号级验证
+3. 把 `collector` live 切换结果和部署回滚说明继续固化到仓库

n8n/README.md

@@ -0,0 +1,30 @@
+# n8n Workflows
+
+本目录保存 StoryForge 的工作流导出文件，避免流程只存在于 n8n UI。
+
+## 工作流
+
+- `workflows/storyforge-analysis.json`：内容分析主线
+- `workflows/storyforge-real-cut.json`：Windows `cutvideo` 调度主线
+- `workflows/storyforge-ai-video.json`：`huobao-drama` AI 生成视频主线
+- `workflows/storyforge-content-source-sync.json`：内容源账号同步与批量分析派发主线
+
+## 约定
+
+- 工作流内部默认通过 `http://collector:8081` 调用 `collector-service`
+- 内部调用头部使用 `X-Orchestrator-Secret: storyforge-local-secret`
+- 如果你修改了 `.env` 里的 `ORCHESTRATOR_SHARED_SECRET`，导入工作流后需要同步更新对应 HTTP Request 节点
+
+## 导入
+
+1. 先执行 `docker compose up -d n8n collector`
+2. 打开 `http://127.0.0.1:5670`
+3. 从 UI 导入本目录下的 4 个 JSON
+4. 激活工作流
+
+## Webhook 路径
+
+- `/webhook/storyforge-analysis`
+- `/webhook/storyforge-real-cut`
+- `/webhook/storyforge-ai-video`
+- `/webhook/storyforge-content-source-sync`

n8n/workflows/storyforge-ai-video.json

@@ -0,0 +1,70 @@
+{
+  "name": "StoryForge AI Video Pipeline",
+  "nodes": [
+    {
+      "parameters": {
+        "httpMethod": "POST",
+        "path": "storyforge-ai-video",
+        "responseMode": "onReceived",
+        "options": {}
+      },
+      "id": "aivideo-webhook",
+      "name": "AI Video Webhook",
+      "type": "n8n-nodes-base.webhook",
+      "typeVersion": 2,
+      "position": [
+        220,
+        300
+      ],
+      "webhookId": "storyforge-ai-video"
+    },
+    {
+      "parameters": {
+        "method": "POST",
+        "url": "={{'http://collector:8081/internal/jobs/steps/ai-video/render?job_id=' + ($json.body.job_id || $json.body.jobId)}}",
+        "sendHeaders": true,
+        "headerParameters": {
+          "parameters": [
+            {
+              "name": "X-Orchestrator-Secret",
+              "value": "storyforge-local-secret"
+            }
+          ]
+        },
+        "options": {
+          "timeout": 3600000
+        }
+      },
+      "id": "aivideo-runner",
+      "name": "Run AI Video Step",
+      "type": "n8n-nodes-base.httpRequest",
+      "typeVersion": 4.2,
+      "position": [
+        520,
+        300
+      ]
+    }
+  ],
+  "connections": {
+    "AI Video Webhook": {
+      "main": [
+        [
+          {
+            "node": "Run AI Video Step",
+            "type": "main",
+            "index": 0
+          }
+        ]
+      ]
+    },
+    "Run AI Video Step": {
+      "main": [
+        []
+      ]
+    }
+  },
+  "active": false,
+  "settings": {},
+  "pinData": {},
+  "versionId": "storyforge-ai-video-v1"
+}

n8n/workflows/storyforge-analysis.json

@@ -0,0 +1,70 @@
+{
+  "name": "StoryForge Analysis Pipeline",
+  "nodes": [
+    {
+      "parameters": {
+        "httpMethod": "POST",
+        "path": "storyforge-analysis",
+        "responseMode": "onReceived",
+        "options": {}
+      },
+      "id": "analysis-webhook",
+      "name": "Analysis Webhook",
+      "type": "n8n-nodes-base.webhook",
+      "typeVersion": 2,
+      "position": [
+        220,
+        300
+      ],
+      "webhookId": "storyforge-analysis"
+    },
+    {
+      "parameters": {
+        "method": "POST",
+        "url": "={{'http://collector:8081/internal/jobs/steps/analyze?job_id=' + ($json.body.job_id || $json.body.jobId)}}",
+        "sendHeaders": true,
+        "headerParameters": {
+          "parameters": [
+            {
+              "name": "X-Orchestrator-Secret",
+              "value": "storyforge-local-secret"
+            }
+          ]
+        },
+        "options": {
+          "timeout": 600000
+        }
+      },
+      "id": "analysis-runner",
+      "name": "Run Analysis Step",
+      "type": "n8n-nodes-base.httpRequest",
+      "typeVersion": 4.2,
+      "position": [
+        520,
+        300
+      ]
+    }
+  ],
+  "connections": {
+    "Analysis Webhook": {
+      "main": [
+        [
+          {
+            "node": "Run Analysis Step",
+            "type": "main",
+            "index": 0
+          }
+        ]
+      ]
+    },
+    "Run Analysis Step": {
+      "main": [
+        []
+      ]
+    }
+  },
+  "active": false,
+  "settings": {},
+  "pinData": {},
+  "versionId": "storyforge-analysis-v1"
+}

n8n/workflows/storyforge-content-source-sync.json

@@ -0,0 +1,70 @@
+{
+  "name": "StoryForge Content Source Sync",
+  "nodes": [
+    {
+      "parameters": {
+        "httpMethod": "POST",
+        "path": "storyforge-content-source-sync",
+        "responseMode": "onReceived",
+        "options": {}
+      },
+      "id": "content-source-sync-webhook",
+      "name": "Content Source Sync Webhook",
+      "type": "n8n-nodes-base.webhook",
+      "typeVersion": 2,
+      "position": [
+        220,
+        300
+      ],
+      "webhookId": "storyforge-content-source-sync"
+    },
+    {
+      "parameters": {
+        "method": "POST",
+        "url": "={{'http://collector:8081/internal/jobs/steps/content-source-sync?job_id=' + ($json.body.job_id || $json.body.jobId)}}",
+        "sendHeaders": true,
+        "headerParameters": {
+          "parameters": [
+            {
+              "name": "X-Orchestrator-Secret",
+              "value": "storyforge-local-secret"
+            }
+          ]
+        },
+        "options": {
+          "timeout": 600000
+        }
+      },
+      "id": "content-source-sync-runner",
+      "name": "Run Content Source Sync Step",
+      "type": "n8n-nodes-base.httpRequest",
+      "typeVersion": 4.2,
+      "position": [
+        540,
+        300
+      ]
+    }
+  ],
+  "connections": {
+    "Content Source Sync Webhook": {
+      "main": [
+        [
+          {
+            "node": "Run Content Source Sync Step",
+            "type": "main",
+            "index": 0
+          }
+        ]
+      ]
+    },
+    "Run Content Source Sync Step": {
+      "main": [
+        []
+      ]
+    }
+  },
+  "active": false,
+  "settings": {},
+  "pinData": {},
+  "versionId": "storyforge-content-source-sync-v1"
+}

n8n/workflows/storyforge-real-cut.json

@@ -0,0 +1,70 @@
+{
+  "name": "StoryForge Real Cut Pipeline",
+  "nodes": [
+    {
+      "parameters": {
+        "httpMethod": "POST",
+        "path": "storyforge-real-cut",
+        "responseMode": "onReceived",
+        "options": {}
+      },
+      "id": "realcut-webhook",
+      "name": "Real Cut Webhook",
+      "type": "n8n-nodes-base.webhook",
+      "typeVersion": 2,
+      "position": [
+        220,
+        300
+      ],
+      "webhookId": "storyforge-real-cut"
+    },
+    {
+      "parameters": {
+        "method": "POST",
+        "url": "={{'http://collector:8081/internal/jobs/steps/real-cut/run?job_id=' + ($json.body.job_id || $json.body.jobId)}}",
+        "sendHeaders": true,
+        "headerParameters": {
+          "parameters": [
+            {
+              "name": "X-Orchestrator-Secret",
+              "value": "storyforge-local-secret"
+            }
+          ]
+        },
+        "options": {
+          "timeout": 3600000
+        }
+      },
+      "id": "realcut-runner",
+      "name": "Run Real Cut Step",
+      "type": "n8n-nodes-base.httpRequest",
+      "typeVersion": 4.2,
+      "position": [
+        520,
+        300
+      ]
+    }
+  ],
+  "connections": {
+    "Real Cut Webhook": {
+      "main": [
+        [
+          {
+            "node": "Run Real Cut Step",
+            "type": "main",
+            "index": 0
+          }
+        ]
+      ]
+    },
+    "Run Real Cut Step": {
+      "main": [
+        []
+      ]
+    }
+  },
+  "active": false,
+  "settings": {},
+  "pinData": {},
+  "versionId": "storyforge-real-cut-v1"
+}

scripts/bootstrap.sh

@@ -1,7 +1,6 @@
 #!/bin/sh
 set -eu
-cd /Users/kris/code/StoryForge/collector-service
+
-python3 -m venv .venv
+ROOT="$(CDPATH= cd -- "$(dirname "$0")/.." && pwd)"
-. .venv/bin/activate
+
-pip install -r requirements.txt
+"$ROOT/scripts/start_business.sh"
-uvicorn app.main:app --host 0.0.0.0 --port 8081 --reload

scripts/cleanup_debug_ui.sh

@@ -0,0 +1,39 @@
+#!/bin/sh
+set -eu
+
+PORT="${1:-3618}"
+SCRIPT_PATH="/Users/kris/code/StoryForge-gitea/scripts/douyin-browser-capture/control_panel.mjs"
+
+lsof -tiTCP:"$PORT" -sTCP:LISTEN | xargs -r kill || true
+
+osascript -e 'tell application "Terminal"' \
+  -e 'if it is running then' \
+  -e 'repeat with w in windows' \
+  -e 'set shouldClose to false' \
+  -e 'repeat with t in tabs of w' \
+  -e 'try' \
+  -e 'set tabText to contents of t' \
+  -e 'if tabText contains "'"$SCRIPT_PATH"'" then set shouldClose to true' \
+  -e 'end try' \
+  -e 'end repeat' \
+  -e 'if shouldClose then close w saving no' \
+  -e 'end repeat' \
+  -e 'end if' \
+  -e 'end tell' >/dev/null 2>&1 || true
+
+for app in "Google Chrome" "Brave Browser" "Arc" "Safari"; do
+  osascript -e 'try' \
+    -e 'tell application "'"$app"'"' \
+    -e 'repeat with w in windows' \
+    -e 'repeat with i from (count of tabs of w) to 1 by -1' \
+    -e 'try' \
+    -e 'set tabUrl to URL of tab i of w' \
+    -e 'if tabUrl contains "127.0.0.1:'"$PORT"'" then close tab i of w' \
+    -e 'end try' \
+    -e 'end repeat' \
+    -e 'end repeat' \
+    -e 'end tell' \
+    -e 'end try' >/dev/null 2>&1 || true
+done
+
+echo "debug ui cleaned: port $PORT"

scripts/douyin-browser-capture/README.md

@@ -0,0 +1,75 @@
+# Douyin Browser Capture
+
+This tool drives a real Playwright Chromium session, lets a human log into Douyin, captures the loaded profile and work pages, and can sync the captured bundle into StoryForge's existing `/v2/douyin/accounts/sync` endpoint.
+
+## Install
+
+```bash
+cd /Users/kris/code/StoryForge-gitea/scripts/douyin-browser-capture
+npm install
+npx playwright install chromium
+```
+
+## Run
+
+```bash
+cd /Users/kris/code/StoryForge-gitea/scripts/douyin-browser-capture
+npm run capture -- \
+  --profile-url https://www.douyin.com/user/your_account \
+  --storyforge-username kris \
+  --storyforge-password 'Asd123456.'
+```
+
+The browser uses a persistent state directory under `~/.storyforge/douyin-playwright`, so Douyin login can survive between runs.
+
+## Control Panel
+
+If you do not want to remember CLI arguments, start the local control panel:
+
+```bash
+cd /Users/kris/code/StoryForge-gitea/scripts/douyin-browser-capture
+npm run control-panel
+```
+
+Then open [http://127.0.0.1:3618](http://127.0.0.1:3618) and use this flow:
+
+1. Fill in the Douyin profile URL and StoryForge credentials.
+2. Click `开始采集`.
+3. A real Chromium window opens. Log into Douyin and solve any captcha there.
+4. Return to the control panel and click `已完成登录，继续采集`.
+5. Wait for `summary.json` and the optional StoryForge sync result.
+
+The control panel stores each run under:
+
+`/Users/kris/code/StoryForge-gitea/output/playwright/douyin/control-panel`
+
+## What it captures
+
+- current profile page JSON blobs extracted from `<script>` tags
+- selected window globals such as `__INITIAL_STATE__`
+- relevant JSON network responses
+- creator-center pages using the same logged-in browser context
+- a limited number of video detail pages linked from the profile
+
+## Output
+
+Default output directory:
+
+`/Users/kris/code/StoryForge-gitea/output/playwright/douyin`
+
+Each run writes:
+
+- `profile-bundle.json`
+- `creator-*.json`
+- `video-*.json`
+- `storyforge-sync-request.json`
+- `storyforge-sync-response.json` when sync is enabled
+- `summary.json`
+
+## Notes
+
+- This is designed as a browser-assisted capture flow, not a fully headless anti-bot bypass.
+- If Douyin shows a slider or challenge page, solve it manually in the opened browser window and then continue.
+- Use `--no-sync` if you only want to save a local bundle for inspection.
+- Use `--ready-file /tmp/storyforge-ready.signal` if you want another process or webpage to decide when capture continues.
+- Creator-center pages belong to the currently logged-in Douyin account. StoryForge now treats them as supplemental evidence by default and will not let them overwrite the target profile unless you explicitly pass `--allow-creator-center-fallback`.

scripts/douyin-browser-capture/capture_and_sync.mjs

@@ -0,0 +1,855 @@
+#!/usr/bin/env node
+
+import fs from "node:fs/promises";
+import { execFileSync } from "node:child_process";
+import os from "node:os";
+import path from "node:path";
+import process from "node:process";
+import readline from "node:readline/promises";
+import { stdin as input, stdout as output } from "node:process";
+import { chromium } from "playwright";
+
+const DEFAULT_CREATOR_CENTER_URLS = [
+  "https://creator.douyin.com/creator-micro/home",
+  "https://creator.douyin.com/creator-micro/data",
+  "https://creator.douyin.com/creator-micro/content/manage"
+];
+const DEFAULT_OUTPUT_DIR = "/Users/kris/code/StoryForge-gitea/output/playwright/douyin";
+const DEFAULT_STATE_DIR = path.join(os.homedir(), ".storyforge", "douyin-playwright");
+const DEFAULT_BACKEND_URL = "http://127.0.0.1:8081";
+const JSON_CAPTURE_LIMIT = 1_500_000;
+const SCRIPT_SCAN_LIMIT = 2_000_000;
+const WAIT_AFTER_NAV_MS = 4_000;
+const RESPONSE_READ_TIMEOUT_MS = 2_000;
+const PYTHON_HTTP_BRIDGE = `
+import json
+import sys
+import urllib.error
+import urllib.request
+
+url, method, headers_json, body_mode, body_value = sys.argv[1:6]
+headers = json.loads(headers_json)
+body = None
+if body_mode == "text":
+    body = body_value.encode("utf-8")
+elif body_mode == "path":
+    with open(body_value, "rb") as handle:
+        body = handle.read()
+request = urllib.request.Request(url, data=body, headers=headers, method=method)
+try:
+    with urllib.request.urlopen(request, timeout=120) as response:
+        raw = response.read().decode("utf-8", "replace")
+        try:
+            payload = json.loads(raw) if raw else None
+        except Exception:
+            payload = {"raw": raw}
+        print(json.dumps({"status": response.status, "data": payload}, ensure_ascii=False))
+except urllib.error.HTTPError as error:
+    raw = error.read().decode("utf-8", "replace")
+    try:
+        payload = json.loads(raw) if raw else None
+    except Exception:
+        payload = {"raw": raw}
+    print(json.dumps({"status": error.code, "data": payload}, ensure_ascii=False))
+except Exception as error:
+    print(json.dumps({"status": 599, "data": {"raw": str(error)}}, ensure_ascii=False))
+`;
+
+function printHelp() {
+  console.log(`StoryForge Douyin Browser Capture
+
+Usage:
+  node capture_and_sync.mjs --profile-url <douyin-profile-url> [options]
+
+Core options:
+  --profile-url <url>           Douyin profile URL to capture
+  --backend-url <url>           StoryForge collector base URL (default: ${DEFAULT_BACKEND_URL})
+  --output-dir <dir>            Capture output directory (default: ${DEFAULT_OUTPUT_DIR})
+  --state-dir <dir>             Persistent browser state dir (default: ${DEFAULT_STATE_DIR})
+  --max-videos <n>              Max video detail pages to capture (default: 4)
+  --scroll-count <n>            Scroll times on profile page (default: 5)
+  --wait-ms <n>                 Wait after each navigation in ms (default: ${WAIT_AFTER_NAV_MS})
+  --ready-file <path>           Wait for this file to appear instead of terminal prompt
+
+StoryForge auth:
+  --storyforge-token <token>    Existing StoryForge bearer token
+  --storyforge-username <name>  Login username for StoryForge
+  --storyforge-password <pass>  Login password for StoryForge
+
+Mode flags:
+  --headless                    Run browser headless
+  --skip-login-prompt           Do not pause for manual login / captcha completion
+  --no-sync                     Capture only, do not import into StoryForge
+  --no-creator-center           Skip creator-center page capture
+  --allow-creator-center-fallback
+                                Allow creator-center identity to replace a missing public profile
+  --note <text>                 Discovery note saved into StoryForge
+
+Examples:
+  npm run capture -- \\
+    --profile-url https://www.douyin.com/user/your_account \\
+    --storyforge-username kris --storyforge-password 'Asd123456.'
+
+  npm run capture -- \\
+    --profile-url https://www.douyin.com/user/your_account \\
+    --storyforge-token <token> --headless --skip-login-prompt --no-creator-center
+`);
+}
+
+function parseArgs(argv) {
+  const options = {
+    backendUrl: DEFAULT_BACKEND_URL,
+    outputDir: DEFAULT_OUTPUT_DIR,
+    stateDir: DEFAULT_STATE_DIR,
+    maxVideos: 4,
+    scrollCount: 5,
+    waitMs: WAIT_AFTER_NAV_MS,
+    headless: false,
+    manualPrompt: true,
+    syncEnabled: true,
+    creatorCenterEnabled: true,
+    allowCreatorCenterFallback: false,
+    creatorCenterUrls: [...DEFAULT_CREATOR_CENTER_URLS],
+    note: "",
+    profileUrl: "",
+    readyFile: "",
+    storyforgeToken: "",
+    storyforgeUsername: "",
+    storyforgePassword: ""
+  };
+
+  const requireValue = (index, flag) => {
+    const value = argv[index + 1];
+    if (!value || value.startsWith("--")) {
+      throw new Error(`Missing value for ${flag}`);
+    }
+    return value;
+  };
+
+  for (let index = 0; index < argv.length; index += 1) {
+    const arg = argv[index];
+    switch (arg) {
+      case "--help":
+      case "-h":
+        options.help = true;
+        break;
+      case "--profile-url":
+        options.profileUrl = requireValue(index, arg);
+        index += 1;
+        break;
+      case "--backend-url":
+        options.backendUrl = requireValue(index, arg);
+        index += 1;
+        break;
+      case "--output-dir":
+        options.outputDir = requireValue(index, arg);
+        index += 1;
+        break;
+      case "--state-dir":
+        options.stateDir = requireValue(index, arg);
+        index += 1;
+        break;
+      case "--max-videos":
+        options.maxVideos = Number.parseInt(requireValue(index, arg), 10);
+        index += 1;
+        break;
+      case "--scroll-count":
+        options.scrollCount = Number.parseInt(requireValue(index, arg), 10);
+        index += 1;
+        break;
+      case "--wait-ms":
+        options.waitMs = Number.parseInt(requireValue(index, arg), 10);
+        index += 1;
+        break;
+      case "--ready-file":
+        options.readyFile = requireValue(index, arg);
+        index += 1;
+        break;
+      case "--storyforge-token":
+        options.storyforgeToken = requireValue(index, arg);
+        index += 1;
+        break;
+      case "--storyforge-username":
+        options.storyforgeUsername = requireValue(index, arg);
+        index += 1;
+        break;
+      case "--storyforge-password":
+        options.storyforgePassword = requireValue(index, arg);
+        index += 1;
+        break;
+      case "--note":
+        options.note = requireValue(index, arg);
+        index += 1;
+        break;
+      case "--headless":
+        options.headless = true;
+        break;
+      case "--skip-login-prompt":
+        options.manualPrompt = false;
+        break;
+      case "--no-sync":
+        options.syncEnabled = false;
+        break;
+      case "--no-creator-center":
+        options.creatorCenterEnabled = false;
+        break;
+      case "--allow-creator-center-fallback":
+        options.allowCreatorCenterFallback = true;
+        break;
+      default:
+        throw new Error(`Unknown argument: ${arg}`);
+    }
+  }
+
+  return options;
+}
+
+function sanitizeName(value) {
+  return String(value || "capture")
+    .replace(/[^a-zA-Z0-9._-]+/g, "-")
+    .replace(/-+/g, "-")
+    .replace(/^-|-$/g, "")
+    .slice(0, 80) || "capture";
+}
+
+async function ensureDir(dir) {
+  await fs.mkdir(dir, { recursive: true });
+}
+
+function nowStamp() {
+  return new Date().toISOString().replace(/[:]/g, "-");
+}
+
+function sleep(ms) {
+  return new Promise((resolve) => setTimeout(resolve, ms));
+}
+
+async function navigateAndSettle(page, url, waitMs) {
+  await page.goto(url, { waitUntil: "commit", timeout: 30_000 }).catch(() => null);
+  await page.waitForLoadState("domcontentloaded", { timeout: 15_000 }).catch(() => {});
+  await sleep(waitMs);
+}
+
+async function maybePrompt(message, enabled, readyFile = "") {
+  if (!enabled) {
+    return;
+  }
+  if (readyFile) {
+    console.error(`${message}\nWaiting for ready file: ${readyFile}`);
+    await waitForReadyFile(readyFile);
+    return;
+  }
+  const rl = readline.createInterface({ input, output });
+  try {
+    await rl.question(`${message}\nPress Enter to continue... `);
+  } finally {
+    rl.close();
+  }
+}
+
+async function waitForReadyFile(filePath) {
+  await ensureDir(path.dirname(filePath));
+  while (true) {
+    try {
+      await fs.access(filePath);
+      return;
+    } catch {
+      await sleep(600);
+    }
+  }
+}
+
+function uniqueStrings(values) {
+  const seen = new Set();
+  const output = [];
+  for (const value of values) {
+    const item = String(value || "").trim();
+    if (!item || seen.has(item)) {
+      continue;
+    }
+    seen.add(item);
+    output.push(item);
+  }
+  return output;
+}
+
+function looksLikeRelevantJsonUrl(url) {
+  const lower = url.toLowerCase();
+  return (
+    lower.includes("douyin.com/aweme") ||
+    lower.includes("douyin.com/web/api") ||
+    lower.includes("douyin.com/creator") ||
+    lower.includes("douyin.com/user") ||
+    lower.includes("creator.douyin.com") ||
+    lower.includes("iesdouyin.com")
+  );
+}
+
+function findJsonEnd(text, start) {
+  const opening = text[start];
+  const closing = opening === "{" ? "}" : "]";
+  let depth = 0;
+  let inString = false;
+  let escaped = false;
+
+  for (let index = start; index < text.length; index += 1) {
+    const char = text[index];
+    if (inString) {
+      if (escaped) {
+        escaped = false;
+      } else if (char === "\\") {
+        escaped = true;
+      } else if (char === "\"") {
+        inString = false;
+      }
+      continue;
+    }
+
+    if (char === "\"") {
+      inString = true;
+      continue;
+    }
+
+    if (char === opening) {
+      depth += 1;
+      continue;
+    }
+
+    if (char === closing) {
+      depth -= 1;
+      if (depth === 0) {
+        return index + 1;
+      }
+    }
+  }
+
+  return -1;
+}
+
+async function createResponseCapture(page) {
+  const records = [];
+  const seen = new Set();
+  const pending = [];
+
+  const listener = (response) => {
+    const promise = (async () => {
+      try {
+        const url = response.url();
+        const headers = response.headers();
+        const contentType = String(headers["content-type"] || "").toLowerCase();
+        if (!contentType.includes("json") && !looksLikeRelevantJsonUrl(url)) {
+          return;
+        }
+        const key = `${response.request().method()} ${url}`;
+        if (seen.has(key)) {
+          return;
+        }
+        const text = await Promise.race([
+          response.text(),
+          sleep(RESPONSE_READ_TIMEOUT_MS).then(() => {
+            throw new Error("response read timeout");
+          })
+        ]);
+        if (!text || text.length > JSON_CAPTURE_LIMIT) {
+          return;
+        }
+        let payload = null;
+        try {
+          payload = JSON.parse(text);
+        } catch {
+          return;
+        }
+        seen.add(key);
+        records.push({
+          url,
+          method: response.request().method(),
+          status: response.status(),
+          payload
+        });
+      } catch {
+        // Ignore network capture failures; page-level capture is still useful.
+      }
+    })();
+    pending.push(promise);
+  };
+
+  page.on("response", listener);
+  return {
+    records,
+    async stop() {
+      page.off("response", listener);
+      await Promise.race([
+        Promise.allSettled(pending),
+        sleep(RESPONSE_READ_TIMEOUT_MS + 500)
+      ]);
+      return records;
+    }
+  };
+}
+
+function extractJsonObjectsFromText(text) {
+  const candidates = [text];
+  const seen = new Set();
+  const results = [];
+
+  for (const candidate of candidates) {
+    const snippet = String(candidate || "").slice(0, SCRIPT_SCAN_LIMIT);
+    for (let index = 0; index < snippet.length; index += 1) {
+      const char = snippet[index];
+      if (char !== "{" && char !== "[") {
+        continue;
+      }
+      const end = findJsonEnd(snippet, index);
+      if (end <= index) {
+        continue;
+      }
+      try {
+        const parsed = JSON.parse(snippet.slice(index, end));
+        const marker = JSON.stringify(parsed);
+        if (seen.has(marker)) {
+          continue;
+        }
+        seen.add(marker);
+        results.push(parsed);
+        if (results.length >= 50) {
+          return results;
+        }
+      } catch {
+        // Keep scanning.
+      }
+    }
+  }
+  return results;
+}
+
+function extractScriptPayloads(html) {
+  const results = [];
+  const seen = new Set();
+  const regex = /<script([^>]*)>([\s\S]*?)<\/script>/gi;
+  let match = null;
+  while ((match = regex.exec(html)) !== null) {
+    const attrs = match[1] || "";
+    const content = match[2] || "";
+    const idMatch = attrs.match(/id=["']([^"']+)["']/i);
+    const scriptId = idMatch ? idMatch[1] : "";
+    for (const payload of extractJsonObjectsFromText(content.trim())) {
+      const marker = JSON.stringify(payload);
+      if (seen.has(marker)) {
+        continue;
+      }
+      seen.add(marker);
+      results.push({ script_id: scriptId, payload });
+    }
+  }
+  return results;
+}
+
+async function collectWindowGlobals(page) {
+  return page.evaluate(() => {
+    const globalNames = [
+      "__INITIAL_STATE__",
+      "__NEXT_DATA__",
+      "__ROUTER_DATA__",
+      "SIGI_STATE",
+      "__APOLLO_STATE__"
+    ];
+    const result = {};
+    for (const name of globalNames) {
+      const value = globalThis[name];
+      if (value === undefined) {
+        continue;
+      }
+      try {
+        result[name] = JSON.parse(JSON.stringify(value));
+      } catch {
+        // Skip non-serializable globals.
+      }
+    }
+    return result;
+  });
+}
+
+async function collectVideoLinks(page) {
+  const hrefs = await page.evaluate(() => {
+    return Array.from(document.querySelectorAll("a[href]"))
+      .map((node) => node.getAttribute("href") || "")
+      .filter(Boolean);
+  });
+  return uniqueStrings(
+    hrefs
+      .map((href) => {
+        if (href.startsWith("//")) {
+          return `https:${href}`;
+        }
+        if (href.startsWith("/")) {
+          return `https://www.douyin.com${href}`;
+        }
+        return href;
+      })
+      .filter((href) => href.includes("/video/"))
+  );
+}
+
+async function clickFirstVisible(page, selectors) {
+  for (const selector of selectors) {
+    const locator = page.locator(selector).first();
+    try {
+      if (await locator.isVisible({ timeout: 1000 })) {
+        await locator.click({ timeout: 1000 });
+        return true;
+      }
+    } catch {
+      // Try next selector.
+    }
+  }
+  return false;
+}
+
+function escapeRegExp(value) {
+  return String(value || "").replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
+}
+
+function decodeEscapedUrl(value) {
+  return String(value || "")
+    .replace(/\\u002F/g, "/")
+    .replace(/\\\//g, "/")
+    .replace(/&amp;/g, "&");
+}
+
+async function resolveCreatorPrefetchUrl(page) {
+  const current = new URL(page.url());
+  const html = await page.content();
+  const escapedPath = escapeRegExp(current.pathname);
+  const mapped = html.match(
+    new RegExp(`"${escapedPath}"\\s*:\\s*"(https://creator\\.douyin\\.com[^"]+prefetch\\.json)"`)
+  );
+  if (mapped?.[1]) {
+    return decodeEscapedUrl(mapped[1]);
+  }
+  const discovered = Array.from(
+    new Set(
+      [...html.matchAll(/https:\/\/creator\.douyin\.com\/goofy\/douyin_creator_pc\/mono\/prefetch\/[^"]+prefetch\.json/g)].map(
+        (match) => decodeEscapedUrl(match[0])
+      )
+    )
+  );
+  return (
+    discovered.find((candidate) => candidate.includes(current.pathname.replace(/^\/creator-micro\//, ""))) ||
+    discovered[0] ||
+    `https://creator.douyin.com/goofy/douyin_creator_pc/mono/prefetch${current.pathname}/prefetch.json`
+  );
+}
+
+async function collectCreatorPrefetchResults(page) {
+  const prefetchUrl = await resolveCreatorPrefetchUrl(page);
+  return page.evaluate(async ({ prefetchUrl }) => {
+    try {
+      const prefetchResp = await fetch(prefetchUrl, { credentials: "same-origin" });
+      const prefetchText = await prefetchResp.text();
+      const prefetch = JSON.parse(prefetchText);
+      const results = [];
+      for (const api of prefetch?.apis || []) {
+        const target = new URL(api.url, window.location.origin);
+        for (const [key, value] of Object.entries(api.params || {})) {
+          target.searchParams.set(key, String(value));
+        }
+        const resp = await fetch(target.toString(), {
+          credentials: api.credentials || "same-origin",
+        });
+        const payload = await resp.json().catch(() => null);
+        results.push({
+          url: target.toString(),
+          payload,
+        });
+      }
+      return {
+        prefetch_url: prefetchUrl,
+        prefetch,
+        results,
+      };
+    } catch (error) {
+      return {
+        prefetch_url: prefetchUrl,
+        error: String(error),
+        results: [],
+      };
+    }
+  }, { prefetchUrl });
+}
+
+async function prepareProfilePage(page, options) {
+  await clickFirstVisible(page, [
+    "text=作品",
+    "text=视频",
+    "text=全部作品",
+    "[role='tab']:has-text('作品')"
+  ]);
+
+  for (let index = 0; index < 3; index += 1) {
+    await clickFirstVisible(page, [
+      "text=展开",
+      "text=更多",
+      "text=查看全部"
+    ]);
+  }
+
+  for (let index = 0; index < options.scrollCount; index += 1) {
+    await page.evaluate(() => window.scrollBy(0, window.innerHeight * 0.85));
+    await sleep(1200);
+  }
+}
+
+async function capturePageBundle(page, label, responseCapture, extra = {}) {
+  const html = await page.content();
+  const loginGateDetected =
+    html.includes("扫码登录") ||
+    html.includes("验证码登录") ||
+    html.includes("登录后免费畅享高清视频");
+  const antiBotDetected =
+    html.includes("window.byted_acrawler.init") ||
+    html.includes("__ac_signature") ||
+    html.includes("__ac_nonce");
+  const scripts = extractScriptPayloads(html);
+  const globals = await collectWindowGlobals(page);
+  const network = await responseCapture.stop();
+  const bundle = {
+    label,
+    captured_at: new Date().toISOString(),
+    page_url: page.url(),
+    page_title: await page.title().catch(() => ""),
+    page_meta: await page.evaluate(() => ({
+      href: window.location.href,
+      title: document.title,
+      text_excerpt: (document.body?.innerText || "").trim().slice(0, 8000)
+    })),
+    capture_hints: {
+      login_gate_detected: loginGateDetected,
+      anti_bot_detected: antiBotDetected
+    },
+    scripts,
+    globals,
+    network,
+    extra
+  };
+  return bundle;
+}
+
+async function saveJson(filePath, value) {
+  await ensureDir(path.dirname(filePath));
+  await fs.writeFile(filePath, JSON.stringify(value, null, 2), "utf8");
+}
+
+async function saveJsonSafe(filePath, value) {
+  try {
+    await saveJson(filePath, value);
+  } catch (error) {
+    console.error(`Failed to write ${filePath}: ${error?.message || error}`);
+  }
+}
+
+async function requestJson(urlString, { method = "GET", headers = {}, body = null, bodyPath = "" } = {}) {
+  const bodyMode = bodyPath ? "path" : body === null ? "none" : "text";
+  const bodyValue = bodyPath || (typeof body === "string" ? body : JSON.stringify(body));
+  const stdout = execFileSync(
+    "python3",
+    ["-c", PYTHON_HTTP_BRIDGE, urlString, method, JSON.stringify(headers), bodyMode, bodyValue],
+    { maxBuffer: 20 * 1024 * 1024, encoding: "utf8" }
+  );
+  const payload = JSON.parse(String(stdout || "").trim() || "{}");
+  if ((payload.status || 500) >= 400) {
+    throw new Error(`Request failed: ${payload.status} ${JSON.stringify(payload.data)}`);
+  }
+  return payload.data;
+}
+
+async function loginStoryForge(baseUrl, username, password) {
+  return requestJson(`${baseUrl.replace(/\/$/, "")}/v2/auth/login`, {
+    method: "POST",
+    headers: { "content-type": "application/json" },
+    body: { username, password }
+  });
+}
+
+async function syncCapture(baseUrl, token, bodyPath) {
+  return requestJson(`${baseUrl.replace(/\/$/, "")}/v2/douyin/accounts/sync`, {
+    method: "POST",
+    headers: {
+      "content-type": "application/json",
+      Authorization: `Bearer ${token}`
+    },
+    bodyPath
+  });
+}
+
+async function captureCreatorPages(context, options, runDir) {
+  const pages = [];
+  if (!options.creatorCenterEnabled) {
+    return pages;
+  }
+
+  for (const [index, url] of options.creatorCenterUrls.entries()) {
+    const page = await context.newPage();
+    const responseCapture = await createResponseCapture(page);
+    try {
+      console.error(`Capturing creator-center page: ${url}`);
+      await navigateAndSettle(page, url, options.waitMs);
+      const prefetchResults = await collectCreatorPrefetchResults(page);
+      const bundle = await capturePageBundle(page, "creator_center", responseCapture, {
+        creator_prefetch: prefetchResults
+      });
+      pages.push({
+        url: bundle.page_url,
+        title: bundle.page_title,
+        payload: bundle
+      });
+      await saveJson(
+        path.join(runDir, `creator-${String(index + 1).padStart(2, "0")}-${sanitizeName(bundle.page_title || bundle.page_url)}.json`),
+        bundle
+      );
+    } finally {
+      await page.close().catch(() => {});
+    }
+  }
+  return pages;
+}
+
+async function captureVideoPages(context, videoLinks, options, runDir) {
+  const pages = [];
+  for (const link of videoLinks.slice(0, Math.max(options.maxVideos, 0))) {
+    const page = await context.newPage();
+    const responseCapture = await createResponseCapture(page);
+    try {
+      console.error(`Capturing video page: ${link}`);
+      await navigateAndSettle(page, link, options.waitMs);
+      const bundle = await capturePageBundle(page, "video_detail", responseCapture, { source_link: link });
+      pages.push(bundle);
+      await saveJson(path.join(runDir, `video-${sanitizeName(link)}.json`), bundle);
+    } finally {
+      await page.close().catch(() => {});
+    }
+  }
+  return pages;
+}
+
+async function main() {
+  const options = parseArgs(process.argv.slice(2));
+  if (options.help) {
+    printHelp();
+    return;
+  }
+  if (!options.profileUrl) {
+    throw new Error("--profile-url is required");
+  }
+  if (
+    options.syncEnabled &&
+    !options.storyforgeToken &&
+    !(options.storyforgeUsername && options.storyforgePassword)
+  ) {
+    throw new Error("Sync mode requires --storyforge-token or both --storyforge-username and --storyforge-password");
+  }
+
+  const runDir = path.join(
+    options.outputDir,
+    `${nowStamp()}-${sanitizeName(options.profileUrl.split("/").pop() || "douyin")}`
+  );
+  await ensureDir(runDir);
+  await ensureDir(options.stateDir);
+
+  const summary = {
+    profile_url: options.profileUrl,
+    output_dir: runDir,
+    video_link_count: 0,
+    captured_video_pages: 0,
+    captured_creator_pages: 0,
+    sync_enabled: options.syncEnabled,
+    status: "running"
+  };
+  await saveJsonSafe(path.join(runDir, "summary.json"), summary);
+
+  let storyforgeToken = options.storyforgeToken;
+  if (options.syncEnabled && !storyforgeToken) {
+    const auth = await loginStoryForge(
+      options.backendUrl,
+      options.storyforgeUsername,
+      options.storyforgePassword
+    );
+    storyforgeToken = auth.token;
+    await saveJson(path.join(runDir, "storyforge-login.json"), {
+      account: auth.account,
+      default_external_base_url: auth.default_external_base_url
+    });
+  }
+
+  const context = await chromium.launchPersistentContext(options.stateDir, {
+    headless: options.headless,
+    viewport: { width: 1440, height: 1024 },
+    args: ["--disable-blink-features=AutomationControlled"]
+  });
+
+  try {
+    const page = await context.newPage();
+    const responseCapture = await createResponseCapture(page);
+    console.error(`Opening profile page: ${options.profileUrl}`);
+    await navigateAndSettle(page, options.profileUrl, options.waitMs);
+    await maybePrompt(
+      `Browser opened ${options.profileUrl}.\nLog into Douyin if needed, solve any slider/captcha, and optionally click into the creator homepage before capture.`,
+      options.manualPrompt,
+      options.readyFile
+    );
+    await prepareProfilePage(page, options);
+    await sleep(options.waitMs);
+    const videoLinks = await collectVideoLinks(page);
+    console.error(`Collected ${videoLinks.length} candidate video links`);
+    const profileBundle = await capturePageBundle(page, "profile", responseCapture, { video_links: videoLinks });
+    await saveJson(path.join(runDir, "profile-bundle.json"), profileBundle);
+    await page.close().catch(() => {});
+
+    const creatorPages = await captureCreatorPages(context, options, runDir);
+    const videoPages = await captureVideoPages(context, videoLinks, options, runDir);
+
+    const syncBody = {
+      profile_url: options.profileUrl,
+      allow_creator_center_profile_fallback: options.allowCreatorCenterFallback,
+      compact_response: true,
+      manual_profile_payload: profileBundle,
+      manual_creator_pages: creatorPages,
+      manual_work_payloads: videoPages,
+      discovery_note: options.note || "browser-assisted capture"
+    };
+    const syncRequestPath = path.join(runDir, "storyforge-sync-request.json");
+    await saveJson(syncRequestPath, syncBody);
+
+    summary.video_link_count = videoLinks.length;
+    summary.captured_video_pages = videoPages.length;
+    summary.captured_creator_pages = creatorPages.length;
+
+    if (options.syncEnabled) {
+      const workspace = await syncCapture(options.backendUrl, storyforgeToken, syncRequestPath);
+      summary.sync_result = {
+        account_id: workspace.account?.id || "",
+        nickname: workspace.account?.nickname || "",
+        sync_errors: workspace.sync_errors || []
+      };
+      await saveJson(path.join(runDir, "storyforge-sync-response.json"), workspace);
+    }
+
+    summary.status = "completed";
+    await saveJson(path.join(runDir, "summary.json"), summary);
+    console.log(JSON.stringify(summary, null, 2));
+  } catch (error) {
+    summary.status = "failed";
+    summary.error = error?.stack || String(error);
+    await saveJsonSafe(path.join(runDir, "summary.json"), summary);
+    await saveJsonSafe(path.join(runDir, "storyforge-sync-error.json"), {
+      error: error?.stack || String(error)
+    });
+    throw error;
+  } finally {
+    await context.close().catch(() => {});
+  }
+}
+
+main().catch((error) => {
+  console.error(error?.stack || String(error));
+  process.exitCode = 1;
+});

scripts/douyin-browser-capture/package-lock.json

@@ -0,0 +1,59 @@
+{
+  "name": "storyforge-douyin-browser-capture",
+  "version": "0.1.0",
+  "lockfileVersion": 3,
+  "requires": true,
+  "packages": {
+    "": {
+      "name": "storyforge-douyin-browser-capture",
+      "version": "0.1.0",
+      "dependencies": {
+        "playwright": "^1.56.1"
+      }
+    },
+    "node_modules/fsevents": {
+      "version": "2.3.2",
+      "resolved": "https://registry.npmjs.org/fsevents/-/fsevents-2.3.2.tgz",
+      "integrity": "sha512-xiqMQR4xAeHTuB9uWm+fFRcIOgKBMiOBP+eXiyT7jsgVCq1bkVygt00oASowB7EdtpOHaaPgKt812P9ab+DDKA==",
+      "hasInstallScript": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "darwin"
+      ],
+      "engines": {
+        "node": "^8.16.0 || ^10.6.0 || >=11.0.0"
+      }
+    },
+    "node_modules/playwright": {
+      "version": "1.58.2",
+      "resolved": "https://registry.npmjs.org/playwright/-/playwright-1.58.2.tgz",
+      "integrity": "sha512-vA30H8Nvkq/cPBnNw4Q8TWz1EJyqgpuinBcHET0YVJVFldr8JDNiU9LaWAE1KqSkRYazuaBhTpB5ZzShOezQ6A==",
+      "license": "Apache-2.0",
+      "dependencies": {
+        "playwright-core": "1.58.2"
+      },
+      "bin": {
+        "playwright": "cli.js"
+      },
+      "engines": {
+        "node": ">=18"
+      },
+      "optionalDependencies": {
+        "fsevents": "2.3.2"
+      }
+    },
+    "node_modules/playwright-core": {
+      "version": "1.58.2",
+      "resolved": "https://registry.npmjs.org/playwright-core/-/playwright-core-1.58.2.tgz",
+      "integrity": "sha512-yZkEtftgwS8CsfYo7nm0KE8jsvm6i/PTgVtB8DL726wNf6H2IMsDuxCpJj59KDaxCtSnrWan2AeDqM7JBaultg==",
+      "license": "Apache-2.0",
+      "bin": {
+        "playwright-core": "cli.js"
+      },
+      "engines": {
+        "node": ">=18"
+      }
+    }
+  }
+}

scripts/douyin-browser-capture/package.json

@@ -0,0 +1,15 @@
+{
+  "name": "storyforge-douyin-browser-capture",
+  "version": "0.1.0",
+  "private": true,
+  "type": "module",
+  "description": "Browser-assisted Douyin capture and sync tool for StoryForge",
+  "scripts": {
+    "capture": "node ./capture_and_sync.mjs",
+    "control-panel": "node ./control_panel.mjs",
+    "help": "node ./capture_and_sync.mjs --help"
+  },
+  "dependencies": {
+    "playwright": "^1.56.1"
+  }
+}

scripts/smoke_business.sh

@@ -0,0 +1,58 @@
+#!/bin/sh
+set -eu
+
+BASE_URL="${STORYFORGE_BASE_URL:-http://127.0.0.1:8081}"
+USERNAME="${STORYFORGE_USERNAME:-kris}"
+PASSWORD="${STORYFORGE_PASSWORD:-Asd123456.}"
+ACCOUNT_ID="${STORYFORGE_SMOKE_ACCOUNT_ID:-dyacct_c2b62842b228406cb48f05fac16fdfdf}"
+
+python3 - <<'PY'
+import json
+import os
+import urllib.request
+
+base = os.environ.get("BASE_URL", "http://127.0.0.1:8081").rstrip("/")
+username = os.environ.get("USERNAME", "kris")
+password = os.environ.get("PASSWORD", "Asd123456.")
+account_id = os.environ.get("ACCOUNT_ID", "dyacct_c2b62842b228406cb48f05fac16fdfdf")
+
+login_req = urllib.request.Request(
+    base + "/v2/auth/login",
+    data=json.dumps({"username": username, "password": password}).encode(),
+    headers={"content-type": "application/json"},
+)
+with urllib.request.urlopen(login_req, timeout=20) as resp:
+    login = json.load(resp)
+
+token = login["token"]
+headers = {"authorization": "Bearer " + token}
+
+checks = [
+    ("/v2/douyin/accounts", "accounts"),
+    (f"/v2/douyin/accounts/{account_id}/workspace", "workspace"),
+    (f"/v2/douyin/accounts/{account_id}/videos?limit=5&sort_by=score", "videos"),
+]
+
+print("smoke login: ok")
+for path, label in checks:
+    req = urllib.request.Request(base + path, headers=headers)
+    with urllib.request.urlopen(req, timeout=30) as resp:
+        payload = json.load(resp)
+    if label == "accounts":
+        summary = {"accounts": len(payload)}
+    elif label == "workspace":
+        summary = {
+            "account": payload.get("account", {}).get("nickname"),
+            "reports": len(payload.get("recent_reports") or []),
+            "linked_accounts": len(payload.get("linked_accounts") or []),
+            "high_score_threshold": (payload.get("video_workspace") or {}).get("high_score_threshold"),
+        }
+    else:
+        items = payload.get("items") or []
+        summary = {
+            "videos": len(items),
+            "first_title": items[0].get("title") if items else None,
+            "first_has_analysis": bool(items and items[0].get("latest_analysis")),
+        }
+    print(f"{label}: " + json.dumps(summary, ensure_ascii=False))
+PY

scripts/start_business.sh

@@ -0,0 +1,39 @@
+#!/bin/sh
+set -eu
+
+ROOT="$(CDPATH= cd -- "$(dirname "$0")/.." && pwd)"
+COMPOSE_FILE="$ROOT/docker-compose.yml"
+
+cd "$ROOT"
+docker compose -f "$COMPOSE_FILE" up -d --build collector n8n
+
+python3 - <<'PY'
+import time
+import urllib.request
+
+checks = [
+    ("collector", "http://127.0.0.1:8081/healthz"),
+    ("n8n", "http://127.0.0.1:5670/healthz"),
+]
+
+deadline = time.time() + 45
+pending = dict(checks)
+while pending and time.time() < deadline:
+    for name, url in list(pending.items()):
+        try:
+            with urllib.request.urlopen(url, timeout=5) as resp:
+                print(f"{name} ready: {resp.status}")
+                pending.pop(name, None)
+        except Exception:
+            pass
+    if pending:
+        time.sleep(1)
+
+if pending:
+    print("startup timeout:", ", ".join(pending))
+    raise SystemExit(1)
+PY
+
+echo "business started"
+echo "collector: http://127.0.0.1:8081/healthz"
+echo "n8n: http://127.0.0.1:5670/healthz"

scripts/start_collector.sh

@@ -1,25 +1,28 @@
 #!/bin/sh
 set -eu
-ROOT="/Users/kris/code/StoryForge"
+
-PID_FILE="$ROOT/data/collector/collector.pid"
+ROOT="$(CDPATH= cd -- "$(dirname "$0")/.." && pwd)"
-LOG_FILE="$ROOT/data/collector/collector.log"
+COMPOSE_FILE="$ROOT/docker-compose.yml"
-VENV="$ROOT/collector-service/.venv311"
+
-mkdir -p "$ROOT/data/collector"
+cd "$ROOT"
-if [ ! -x "$VENV/bin/python" ]; then
+docker compose -f "$COMPOSE_FILE" up -d --build collector
-  /opt/homebrew/bin/python3.11 -m venv "$VENV"
+
-  . "$VENV/bin/activate"
+python3 - <<'PY'
-  pip install -q -r "$ROOT/collector-service/requirements.txt"
+import time
-else
+import urllib.request
-  . "$VENV/bin/activate"
+
-fi
+url = "http://127.0.0.1:8081/healthz"
-if [ -f "$PID_FILE" ]; then
+deadline = time.time() + 30
-  PID="$(cat "$PID_FILE" || true)"
+last_error = ""
-  if [ -n "$PID" ] && kill -0 "$PID" 2>/dev/null; then
+while time.time() < deadline:
-    echo "collector already running: $PID"
+    try:
-    exit 0
+        with urllib.request.urlopen(url, timeout=5) as resp:
-  fi
+            print(f"collector ready: {resp.status} {resp.read().decode('utf-8', 'ignore')[:160]}")
-fi
+            raise SystemExit(0)
-cd "$ROOT/collector-service"
+    except Exception as exc:
-nohup "$VENV/bin/python" -m uvicorn app.main:app --host 0.0.0.0 --port 8081 >"$LOG_FILE" 2>&1 &
+        last_error = str(exc)
-echo $! > "$PID_FILE"
+        time.sleep(1)
-echo "collector started: $(cat "$PID_FILE")"
+
+print(f"collector start timeout: {last_error}")
+raise SystemExit(1)
+PY

scripts/start_douyin_workbench.sh

@@ -0,0 +1,38 @@
+#!/bin/sh
+set -eu
+
+ROOT="$(CDPATH= cd -- "$(dirname "$0")/.." && pwd)"
+PORT="${DOUYIN_WORKBENCH_PORT:-3618}"
+SCRIPT="$ROOT/scripts/douyin-browser-capture/control_panel.mjs"
+LOG_FILE="${DOUYIN_WORKBENCH_LOG:-/tmp/storyforge-douyin-workbench.log}"
+SESSION_NAME="${DOUYIN_WORKBENCH_SESSION:-storyforge-douyin-workbench}"
+
+if lsof -nP -iTCP:"$PORT" -sTCP:LISTEN >/dev/null 2>&1; then
+  echo "douyin workbench already running: http://127.0.0.1:$PORT/workbench"
+  exit 0
+fi
+
+screen -wipe >/dev/null 2>&1 || true
+screen -S "$SESSION_NAME" -X quit >/dev/null 2>&1 || true
+screen -dmS "$SESSION_NAME" /bin/sh -lc "exec env PORT='$PORT' node '$SCRIPT' >>'$LOG_FILE' 2>&1"
+
+python3 - <<'PY'
+import os
+import time
+import urllib.request
+
+port = os.environ.get("PORT", "3618")
+url = f"http://127.0.0.1:{port}/workbench"
+deadline = time.time() + 15
+last_error = ""
+while time.time() < deadline:
+    try:
+        with urllib.request.urlopen(url, timeout=3) as resp:
+            print(f"douyin workbench ready: {resp.status} {url}")
+            raise SystemExit(0)
+    except Exception as exc:
+        last_error = str(exc)
+        time.sleep(0.5)
+print(f"douyin workbench start timeout: {last_error}")
+raise SystemExit(1)
+PY

scripts/status_business.sh

@@ -0,0 +1,22 @@
+#!/bin/sh
+set -eu
+
+ROOT="$(CDPATH= cd -- "$(dirname "$0")/.." && pwd)"
+COMPOSE_FILE="$ROOT/docker-compose.yml"
+
+cd "$ROOT"
+docker compose -f "$COMPOSE_FILE" ps
+echo "---"
+python3 - <<'PY'
+import urllib.request
+
+for name, url in [
+    ("collector", "http://127.0.0.1:8081/healthz"),
+    ("n8n", "http://127.0.0.1:5670/healthz"),
+]:
+    try:
+        with urllib.request.urlopen(url, timeout=5) as resp:
+            print(f"{name}: {resp.status} {resp.read().decode('utf-8', 'ignore')[:200]}")
+    except Exception as exc:
+        print(f"{name}: ERROR {exc}")
+PY

scripts/status_collector.sh

@@ -1,15 +1,21 @@
 #!/bin/sh
 set -eu
-PID_FILE="/Users/kris/code/StoryForge/data/collector/collector.pid"
+
-if [ -f "$PID_FILE" ]; then
+ROOT="$(CDPATH= cd -- "$(dirname "$0")/.." && pwd)"
-  PID="$(cat "$PID_FILE" || true)"
+COMPOSE_FILE="$ROOT/docker-compose.yml"
-  if [ -n "$PID" ] && kill -0 "$PID" 2>/dev/null; then
+
-    echo "running:$PID"
+cd "$ROOT"
-    exit 0
+docker compose -f "$COMPOSE_FILE" ps collector
-  fi
+echo "---"
-fi
+python3 - <<'PY'
-if lsof -nP -iTCP:8081 -sTCP:LISTEN >/dev/null 2>&1; then
+import urllib.request
-  echo "running:port"
+
-else
+url = "http://127.0.0.1:8081/healthz"
-  echo "stopped"
+try:
-fi
+    with urllib.request.urlopen(url, timeout=5) as resp:
+        print(f"collector health: {resp.status}")
+        print(resp.read().decode("utf-8", "ignore")[:400])
+except Exception as exc:
+    print(f"collector health error: {exc}")
+    raise SystemExit(1)
+PY

scripts/status_douyin_workbench.sh

@@ -0,0 +1,23 @@
+#!/bin/sh
+set -eu
+
+PORT="${DOUYIN_WORKBENCH_PORT:-3618}"
+SESSION_NAME="${DOUYIN_WORKBENCH_SESSION:-storyforge-douyin-workbench}"
+
+if ! lsof -nP -iTCP:"$PORT" -sTCP:LISTEN >/dev/null 2>&1; then
+  echo "douyin workbench stopped"
+  exit 1
+fi
+
+screen -ls | grep "$SESSION_NAME" || true
+echo "---"
+python3 - <<'PY'
+import os
+import urllib.request
+
+port = os.environ.get("PORT", "3618")
+for path in ("/workbench", "/"):
+    url = f"http://127.0.0.1:{port}{path}"
+    with urllib.request.urlopen(url, timeout=5) as resp:
+        print(f"{path}: {resp.status}")
+PY

scripts/stop_collector.sh

@@ -1,15 +1,9 @@
 #!/bin/sh
 set -eu
-PID_FILE="/Users/kris/code/StoryForge/data/collector/collector.pid"
+
-if [ ! -f "$PID_FILE" ]; then
+ROOT="$(CDPATH= cd -- "$(dirname "$0")/.." && pwd)"
-  echo "collector not running"
+COMPOSE_FILE="$ROOT/docker-compose.yml"
-  exit 0
+
-fi
+cd "$ROOT"
-PID="$(cat "$PID_FILE" || true)"
+docker compose -f "$COMPOSE_FILE" stop collector
-if [ -n "$PID" ] && kill -0 "$PID" 2>/dev/null; then
+echo "collector stopped"
-  kill "$PID"
-  echo "collector stopped: $PID"
-else
-  echo "collector pid stale: $PID"
-fi
-rm -f "$PID_FILE"

scripts/stop_douyin_workbench.sh

@@ -0,0 +1,9 @@
+#!/bin/sh
+set -eu
+
+PORT="${DOUYIN_WORKBENCH_PORT:-3618}"
+SESSION_NAME="${DOUYIN_WORKBENCH_SESSION:-storyforge-douyin-workbench}"
+
+screen -S "$SESSION_NAME" -X quit >/dev/null 2>&1 || true
+lsof -tiTCP:"$PORT" -sTCP:LISTEN | xargs -r kill
+echo "douyin workbench stopped: $PORT"