Implement optional single-image intake, Signal ingestion, and multimodal vision analysis

- Add image intake service with format validation (JPEG, PNG, WebP) and EXIF/GPS stripping
- Enforce strict single-image rule across Web and Signal attachment channels
- Implement token-optimized vision downscaling and JPEG compression
- Add IMAGE_CONTEXT pipeline stage with OmniRoute vision routing and resilient failover
- Seed and manage versioned idea-image-interpreter prompt in catalog
- Update Web UI with responsive image picker, preview chip, and Visual Context tab
- Add comprehensive automated test suite in test_image_intake.py
- Update README and Labyricorn devlog

thinkstorm/models.py

@@ -110,6 +110,32 @@ class Idea:
     updated_at: str = ""
     urls: List[IdeaURL] = field(default_factory=list)
     relationships: List[Dict[str, Any]] = field(default_factory=list)
+    submission_image: Optional[Dict[str, Any]] = None
+    source_channel: str = "web"
+    source_sender_uuid: Optional[str] = None
+    source_group_id: Optional[str] = None
+    source_event_id: Optional[str] = None
+
+@dataclass
+class SubmittedImage:
+    raw_bytes: bytes
+    filename: str
+    content_type: str
+    source: str = "web"  # "web" | "signal"
+
+@dataclass
+class IdeaSubmission:
+    text: str
+    source: str = "web"  # "web" | "signal"
+    image: Optional[SubmittedImage] = None
+    sender_uuid: Optional[str] = None
+    sender_number: Optional[str] = None
+    sender_name: Optional[str] = None
+    group_id: Optional[str] = None
+    message_id: Optional[str] = None
+    event_id: Optional[str] = None
+    reply_to: Optional[str] = None
+    received_at: Optional[str] = None
 
 @dataclass
 class WorkTrackOutput:
@@ -129,7 +155,7 @@ class WorkTrackOutput:
 class WorkTrack:
     id: str  # e.g. WT-0001
     idea_id: str
-    work_type_id: str  # ARTICLE, BLOG_ENTRY, CODING_PROJECT
+    work_type_id: str  # ARTICLE, BLOG_ENTRY, CODING_PROJECT, YOUTUBE_VIDEO
     name: str
     state: WorkTrackState = WorkTrackState.PLANNED
     workflow_id: str = ""