Inspect Assistant

Read your chats with Vruum and the workspace's Agent work. Read-only.

• list: no id; optional payload={before_updated_at, before_id, limit}. Your chats in this workspace, newest first. For the next page pass the last item's updated_at and id.

• read: id=chat UUID; optional payload={before_sequence, limit}. The chat's messages with full text (newest page first), its turns with their state, and its record changes (items) with their Undo state and each answer's current rating. Use next_before_sequence for earlier messages.

• browser_source: id=snapshot UUID; optional payload={offset, link_offset, element_offset}. Read saved browser text in 12,000-character pages, links in groups of 10, and controls in groups of 20. Follow next_offset, next_link_offset and next_element_offset independently. This is private observed evidence, not browsing authority.

• jobs: no id; optional payload={scope: everyone|mine, view: current|history}. The workspace's Agent work as outcomes: one row per objective with agent work (kinds Outreach, Content, Plan inside; contributing objectives under their parent) or per one-off request. Each row has progress, what each kind is doing now, and the decisions it waits for: needs_you are yours to make, waiting_for names who else decides.

• job: id=row key (objective:<id> or request:<id>) or a Delegation UUID. The row plus what each kind was handed, the newest 20 journal entries (recorded facts and the agent's labelled notes) and, for a request, its saved steps and result (the analysis and drafts it prepared, each with its own approval). Every member reads it; reading never resumes work.

A turn in state running is still working; read again for its answer. Messages, changes and ratings are the same ones the app's chat panel shows.