Initial TrueGrowth source import

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.