Initial TrueGrowth source import

openspec/changes/add-omni-intelligence-hub/design.md

@@ -0,0 +1,70 @@
+## Context
+The current workbench shell owns the main navigation in `WorkbenchShell.tsx`, the app-center cards in `app-definitions.tsx`, and route rendering inside `renderRoute()`. Model selection is already implemented in Drawnix with runtime model discovery through `useSelectableModels('text')` and controlled model refs in `ModelSelector`.
+
+The user-provided plan defines "万象智枢 / Omni Intelligence Hub" as the upstream decision and content-sourcing center. Its first release should make the feature discoverable and actionable without requiring the whole long-term platform to be complete.
+
+Agent-Reach is an external project focused on agent access to external sources. It should be treated as a local capability provider rather than bundled frontend logic.
+
+## Goals
+- Add a first-class workbench entry for Omni Intelligence Hub.
+- Let users start research from a question, topic, product name, webpage URL, video URL, or GitHub repository.
+- Reuse existing runtime-discovered text model selection instead of creating a separate model registry.
+- Bridge to Agent-Reach for retrieval/source access and expose health/diagnostics in the UI.
+- Keep the first implementation useful when Agent-Reach is unavailable by allowing draft setup, mode selection, model selection, and diagnostic guidance.
+
+## Non-Goals
+- Do not implement every long-term submodule in full depth in the first release.
+- Do not vendor or copy Agent-Reach source code into the web app.
+- Do not replace existing image, video, audio, avatar, canvas, or asset workflows.
+- Do not introduce a new model configuration surface separate from the existing provider/runtime model system.
+
+## Architecture
+### Workbench UI
+- Add `/intelligence` as the top-level route.
+- Add a sidebar item labeled `智枢` or `万象智枢` using a lucide icon such as `Radar`, `SearchCheck`, or `BrainCircuit`.
+- Add an app-center definition with the product-plan description and route `/intelligence`.
+- Implement an `OmniIntelligencePage` component in the workbench layer. The first screen should be the usable research workspace, not a marketing landing page.
+
+### Internal Navigation
+Represent the planned submodules as tab/segmented navigation:
+- 总览: 智枢首页
+- 探索: 全域探索, 内容解析, 专题智研
+- 洞察: 趋势雷达, 竞品战情
+- 创作: 策源工坊
+- 管理: 情报资产, 监控任务
+
+The initial implementation may keep some tabs as structured empty states, but the main input, mode selection, model selector, Agent-Reach status, quick scenarios, and result preview must be functional.
+
+### Model Selection
+- Use runtime-discovered text models via `useSelectableModels('text')`.
+- Reuse the existing controlled `ModelSelector` where practical.
+- Store both `modelId` and `modelRef` in the page state.
+- Include selected model metadata in Agent-Reach task submission so downstream summarization, verification, and content conversion use the chosen model.
+
+### Agent-Reach Bridge
+Add a local bridge with these conceptual endpoints:
+- `GET /local-api/agent-reach/status`: returns installed/runnable/auth/source capability state and doctor output when available.
+- `POST /local-api/agent-reach/research`: submits a query, mode, model, source filters, depth, verification, and output options.
+- `POST /local-api/agent-reach/parse-link`: submits a URL for webpage/video/repository parsing.
+
+The bridge should execute Agent-Reach through a local runtime boundary and normalize responses into:
+- `summary`
+- `keyFindings`
+- `sources`
+- `conflicts`
+- `trendSignals`
+- `contentIdeas`
+- `scripts`
+- `storyboards`
+- `prompts`
+- `rawDiagnostics`
+
+If Agent-Reach is missing, the status endpoint should return `available: false` with setup guidance. The UI should show a clear status panel and keep non-network planning controls usable.
+
+### Asset and Workflow Continuity
+Omni Intelligence Hub results should be shaped so later changes can save them as intelligence assets, insert markdown reports into canvas, or launch image/video/avatar/script workflows. The first implementation can expose CTA placeholders for these handoffs while preserving the result data model.
+
+## Risks
+- Agent-Reach command/API shape may change. Keep the bridge isolated and normalize the contract at `/local-api/agent-reach/*`.
+- Authenticated community sources may require user login. Surface per-source capability and avoid treating missing auth as total failure.
+- Research tasks can be long-running. If the first release uses synchronous calls, keep timeouts and progress states explicit; prefer adding task queue integration when the bridge proves stable.

openspec/changes/add-omni-intelligence-hub/proposal.md

@@ -0,0 +1,26 @@
+# Change: Add Omni Intelligence Hub
+
+## Why
+TrueGrowth needs an upstream intelligence workspace that helps users decide what to create before they generate images, videos, voices, avatars, or canvas workflows. The provided product plan positions "万象智枢 / Omni Intelligence Hub" as the platform's global research and content strategy center, covering web, video, community, repository, trend, competitor, and local document intelligence.
+
+Agent-Reach already targets the required retrieval layer: web pages, YouTube, RSS, search, GitHub, and authenticated community sources. Integrating it as a local runtime bridge lets TrueGrowth add this intelligence entry without duplicating crawler and source acquisition logic in the workbench.
+
+## What Changes
+- Add a left-sidebar entry and route for "万象智枢".
+- Add an application-center card for the new module.
+- Add an Omni Intelligence Hub page with the planned navigation groups: 总览, 探索, 洞察, 创作, 管理.
+- Add a unified query surface with modes for 快速探索, 深度研究, 趋势分析, 竞品分析, and 链接解析.
+- Reuse the current canvas/text model selection logic so users can choose the analysis model from runtime-discovered text models.
+- Add an Agent-Reach runtime bridge for capability checks, diagnostics, and research/link-analysis task submission.
+- Show a usable degraded state when Agent-Reach is not installed, not authenticated, or missing source capabilities.
+- Preserve results as structured intelligence assets that can later feed scripts, storyboards, prompts, digital-human copy, video plans, canvas insertion, and the asset center.
+
+## Impact
+- Affected specs: omni-intelligence-hub
+- Affected code:
+  - `apps/web/src/workbench/WorkbenchShell.tsx`
+  - `apps/web/src/workbench/app-definitions.tsx`
+  - `apps/web/src/workbench/workbench.scss`
+  - `apps/web/src/workbench/truegrowth.types.ts`
+  - local runtime scripts and bridge endpoints under `scripts/` or `apps/web/src/workbench` service helpers
+  - reusable model selector imports from `packages/drawnix/src/components/chat-drawer` and `packages/drawnix/src/hooks/use-runtime-models`

openspec/changes/add-omni-intelligence-hub/specs/omni-intelligence-hub/spec.md

@@ -0,0 +1,82 @@
+## ADDED Requirements
+
+### Requirement: Workbench Entry
+The system SHALL expose "万象智枢" as a first-class workbench module from the left sidebar and application center.
+
+#### Scenario: Open from sidebar
+- **GIVEN** the user is in the TrueGrowth workbench
+- **WHEN** the user clicks the "万象智枢" sidebar entry
+- **THEN** the workbench navigates to the Omni Intelligence Hub route
+- **AND** the main content shows the intelligence research workspace.
+
+#### Scenario: Open from application center
+- **GIVEN** the user is viewing the application center
+- **WHEN** the user opens the "万象智枢" app card
+- **THEN** the workbench navigates to the same Omni Intelligence Hub route.
+
+### Requirement: Unified Research Start
+The system SHALL let users start intelligence work from a question, topic, product name, webpage URL, video URL, or GitHub repository URL.
+
+#### Scenario: Start from a product question
+- **GIVEN** the user enters a product research question
+- **AND** selects a research mode
+- **WHEN** the user starts exploration
+- **THEN** the system submits an intelligence request with the query, mode, advanced options, and selected model.
+
+#### Scenario: Start from a link
+- **GIVEN** the user enters a webpage, video, or repository URL
+- **WHEN** the user starts link parsing
+- **THEN** the system submits a link parsing request
+- **AND** preserves the detected link type in the request.
+
+### Requirement: Planned Hub Navigation
+The system SHALL organize the Omni Intelligence Hub according to the planned groups 总览, 探索, 洞察, 创作, and 管理.
+
+#### Scenario: Browse submodules
+- **GIVEN** the user is on the Omni Intelligence Hub page
+- **WHEN** the user switches among the submodule tabs
+- **THEN** the page preserves the current query configuration
+- **AND** displays the selected submodule context.
+
+### Requirement: Reused Text Model Selection
+The system SHALL reuse the existing runtime-discovered text model selection logic for Omni Intelligence Hub analysis tasks.
+
+#### Scenario: Choose analysis model
+- **GIVEN** runtime text models are available
+- **WHEN** the user opens the model selector in Omni Intelligence Hub
+- **THEN** the selector shows the same selectable text-model source as the current canvas/chat model selection logic
+- **AND** selecting a model stores both the model id and model reference.
+
+#### Scenario: Submit selected model
+- **GIVEN** the user selected a model
+- **WHEN** the user starts an intelligence task
+- **THEN** the task request includes the selected model id
+- **AND** includes the selected model reference when available.
+
+### Requirement: Agent-Reach Integration
+The system SHALL integrate Agent-Reach as the retrieval and source-access provider behind Omni Intelligence Hub.
+
+#### Scenario: Agent-Reach available
+- **GIVEN** Agent-Reach is installed and available
+- **WHEN** the Omni Intelligence Hub loads
+- **THEN** the system shows Agent-Reach source capability status
+- **AND** enables research and link parsing submissions.
+
+#### Scenario: Agent-Reach unavailable
+- **GIVEN** Agent-Reach is not installed or cannot run
+- **WHEN** the Omni Intelligence Hub loads
+- **THEN** the system shows a degraded status with setup or diagnostic guidance
+- **AND** keeps query drafting, mode selection, model selection, and configuration controls usable.
+
+### Requirement: Intelligence Result Structure
+The system SHALL normalize intelligence results into reusable structured sections for research and downstream creation.
+
+#### Scenario: Display research result
+- **GIVEN** an intelligence task completes successfully
+- **WHEN** the UI receives the normalized result
+- **THEN** it displays core conclusions, evidence sources, user viewpoints, trend signals, competitor notes, content ideas, scripts, storyboards, and prompt suggestions when present.
+
+#### Scenario: Preserve downstream handoff data
+- **GIVEN** an intelligence result includes creative outputs
+- **WHEN** the user views the result
+- **THEN** the result data remains structured so later workflows can save it to assets, insert it into canvas, or launch script/image/video/avatar generation.

openspec/changes/add-omni-intelligence-hub/tasks.md

@@ -0,0 +1,36 @@
+## 1. Discovery and Contracts
+- [x] 1.1 Confirm the local Agent-Reach install/run command and output format.
+- [x] 1.2 Define normalized TypeScript types for Agent-Reach status, research request, link parse request, and intelligence result.
+- [x] 1.3 Decide whether the first bridge runs through the existing Local API script or a workbench service helper.
+
+## 2. Workbench Entry
+- [x] 2.1 Add the `/intelligence` route title and sidebar item.
+- [x] 2.2 Add the application-center card for `万象智枢`.
+- [x] 2.3 Ensure the new route is searchable from the workbench top search where current app cards are searchable.
+
+## 3. Omni Intelligence UI
+- [x] 3.1 Create the main `OmniIntelligencePage` component.
+- [x] 3.2 Add the planned internal navigation groups and submodule tabs.
+- [x] 3.3 Add the top unified input with query/link detection.
+- [x] 3.4 Add query modes: 快速探索, 深度研究, 趋势分析, 竞品分析, 链接解析.
+- [x] 3.5 Add advanced configuration controls: time range, language, platform include/exclude, research depth, output form, fact checking, source retention, and creative plan generation.
+- [x] 3.6 Add quick scenario buttons: 今日选题, 解析视频, 竞品分析, 开源项目研究, 爆款拆解, 内容方案.
+- [x] 3.7 Add result preview sections for conclusion, evidence, user views, trend judgment, competitor analysis, content ideas, scripts, storyboards, and prompts.
+
+## 4. Model Selection
+- [x] 4.1 Reuse the current text model selection logic via `useSelectableModels('text')`.
+- [x] 4.2 Reuse or adapt the existing controlled `ModelSelector` component.
+- [x] 4.3 Submit both selected model id and model ref to the Agent-Reach bridge.
+- [x] 4.4 Keep the selection stable across mode and tab changes.
+
+## 5. Agent-Reach Runtime Bridge
+- [x] 5.1 Add a status/doctor bridge for Agent-Reach availability and source capabilities.
+- [x] 5.2 Add a research submission bridge.
+- [x] 5.3 Add a link parsing bridge.
+- [x] 5.4 Normalize Agent-Reach output into the Omni Intelligence result model.
+- [x] 5.5 Add timeout, error, and missing-auth handling.
+
+## 6. Verification
+- [ ] 6.1 Validate the OpenSpec change once the CLI is available. (`openspec` is not currently in PATH.)
+- [x] 6.2 Run targeted TypeScript/build checks for affected web and drawnix imports.
+- [x] 6.3 Manually verify sidebar route, app card route, model dropdown, status panel, quick scenarios, and degraded Agent-Reach state.