As a meeting participant, I want to provide images (via upload, camera, or paste) and PDFs during a session so Hedy can offer insights, and ensure all these assets are bundled into the final session data sent via webhook.

* AC 1.1: The chat interface must support Cmd+V / Ctrl+V to allow users to paste images directly from their clipboard (e.g., from a screenshot tool).

* AC 1.2: Users must be able to upload files in PDF, PNG, and JPEG formats via a file picker.

* AC 1.3: On mobile, the interface must allow capturing a photo via the system camera for immediate upload.

* AC 1.4: The UI must show a "processing" state or thumbnail preview while the file is being analyzed by the AI.

* AC 2.1: Hedy must use the uploaded/pasted content as primary context for subsequent chat queries.

* AC 2.2: Hedy must be able to perform OCR (Optical Character Recognition) and data extraction to answer specific questions about the shared file.

* AC 2.3: If multiple files are uploaded, Hedy must maintain a "session memory" of all files shared within that specific meeting.

* AC 3.1: The system must trigger a session_ended webhook only after the meeting is concluded.

* AC 3.2: The webhook payload must include a files array containing all assets shared during the session.

* AC 3.3: Each object in the files array must contain:

* original_filename

* file_type (MIME type)

* storage_url (A secure link to the file)

* timestamp_pasted (When it was introduced to the chat)

* AC 3.4: The webhook must also include the full_transcript and ai_summary alongside the file data to provide a complete historical record.