Initial TrueGrowth source import

openspec/changes/add-comfyui-image-engine/design.md

@@ -0,0 +1,17 @@
+## Context
+The existing local image provider can register models and route to OpenAI-compatible `/images/generations`, but it cannot execute ComfyUI workflows or inspect ComfyUI model/node availability.
+
+## Goals / Non-Goals
+- Goals: connect to local `127.0.0.1:8188`, inspect ComfyUI status and nodes, run built-in text-to-image workflows, and return generated images to TrueGrowth tasks/assets.
+- Non-Goals: bundling ComfyUI, silently installing models/custom nodes, replacing TrueGrowth business workflows, or exposing remote LAN ComfyUI by default.
+
+## Decisions
+- Treat ComfyUI as a local image engine behind TrueGrowth APIs.
+- Keep online text/script providers and existing avatar/voice/video runtimes unchanged.
+- Start with polling `/history/{prompt_id}` after `POST /prompt`; websocket can be added later without changing the public TrueGrowth API.
+- Use API-format workflow JSON templates for SDXL and Flux Schnell.
+
+## Risks / Trade-offs
+- Workflow templates depend on node availability and model filenames in ComfyUI.
+- Some Flux installs require custom nodes or newer ComfyUI versions; missing nodes are reported instead of hidden.
+- Model downloads and licenses remain user-confirmed.

openspec/changes/add-comfyui-image-engine/proposal.md

@@ -0,0 +1,14 @@
+# Change: Add ComfyUI local image engine
+
+## Why
+TrueGrowth needs local image generation that can actually execute downloaded models while keeping business workflows, canvas generation, task center, and media library under TrueGrowth control.
+
+## What Changes
+- Add ComfyUI as a local image engine, not as the full business workflow engine.
+- Add local API endpoints for ComfyUI status, model inspection, templates, and image generation.
+- Route ComfyUI generation results into the existing local task and media asset flow.
+- Surface ComfyUI status and templates in Model Center so users can understand missing models or nodes.
+
+## Impact
+- Affected specs: image-generation, runtime-model-discovery
+- Affected code: local runtime API bridge, workbench runtime client, Model Center, image engine entry points

openspec/changes/add-comfyui-image-engine/specs/image-generation/spec.md

@@ -0,0 +1,20 @@
+## ADDED Requirements
+### Requirement: Generate Images Through ComfyUI Local Engine
+The system SHALL allow image generation tasks to run through a local ComfyUI engine while preserving the existing task and media result flow.
+
+#### Scenario: ComfyUI image generation succeeds
+- **GIVEN** ComfyUI is reachable on the configured local base URL
+- **AND** a supported workflow template is selected
+- **WHEN** the user submits a prompt
+- **THEN** the system SHALL submit a ComfyUI prompt
+- **AND** collect output images
+- **AND** expose the completed task and generated image assets through the existing task center and media library.
+
+### Requirement: Keep Business Workflow Outside ComfyUI
+The system SHALL use ComfyUI only as a local image engine, not as the full TrueGrowth business workflow engine.
+
+#### Scenario: Business workflow uses multiple capabilities
+- **WHEN** a workflow includes text/script generation, image generation, and avatar/video creation
+- **THEN** text/script generation SHALL continue using configured text providers
+- **AND** image generation MAY use ComfyUI
+- **AND** avatar/video/voice steps SHALL continue using their existing providers.

openspec/changes/add-comfyui-image-engine/specs/runtime-model-discovery/spec.md

@@ -0,0 +1,9 @@
+## ADDED Requirements
+### Requirement: Inspect ComfyUI Runtime Availability
+The system SHALL inspect local ComfyUI availability, node metadata, and model choices for image workflows.
+
+#### Scenario: User opens local image engine settings
+- **WHEN** the system checks ComfyUI
+- **THEN** it SHALL probe the local ComfyUI status endpoint
+- **AND** read node/model metadata where available
+- **AND** report missing nodes or missing model choices for built-in templates.

openspec/changes/add-comfyui-image-engine/tasks.md

@@ -0,0 +1,12 @@
+## 1. Implementation
+- [x] 1.1 Add OpenSpec proposal and spec deltas for ComfyUI local image engine.
+- [x] 1.2 Add local ComfyUI status, models, templates, and generate-image APIs.
+- [x] 1.3 Add ComfyUI task runner that submits workflow JSON and collects output images.
+- [x] 1.4 Add frontend runtime client types/functions.
+- [x] 1.5 Add Model Center ComfyUI engine status and template controls.
+- [x] 1.6 Add a workbench entry for ComfyUI image generation that writes to task center and media library.
+
+## 2. Validation
+- [x] 2.1 Run `node --check scripts/truegrowth-local-api.mjs`.
+- [x] 2.2 Run `pnpm nx run web:typecheck`.
+- [x] 2.3 Record build status or known blockers.