Ask a workbook to change
update_workbookStarts a run on the workbook, described in one sentence the way a person would say it — 'add a section on Q3 headcount', 'refresh the cash figures from the latest filing'. The run is billed to this account and takes minutes; this returns its run id immediately and does not wait. The workbook shows what changed once the run finishes. An instruction that is a question about the workbook — 'which rows have no source?' — is answered instead, in seconds, from the workbook's own text: no version is written, and read_workbook's messages holds the answer under this run's id. On a flashroom workbook the run takes seconds, and the answer is a plan: each cell's before and after, and any folders and files. A plan changes nothing; the instruction yes in a later call makes it, as a new version.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | What this workbook's runs are, from now on. `harnessroom` (a new workbook's default): the instruction is a request, and a harness researches and writes the document. `latticeroom`: the instruction is a draft someone already wrote, whole — markdown, its links kept — which comes back exactly as written, with the run's inference beside it (read_workbook's `inference`: each claim cited, self-reported, secondary only, contradicted or with no source, and its sources); each entry under its References or Bibliography heading is looked up in Crossref and on the web and marked found, found with other authors or year, or not found, and a sentence citing it — [3], (Smith et al., 2020) — is read against the work found; attach data files (.json, .csv, .tsv) to settle the draft's own figures. `graphroom`: runs perform the procedure drawn for the workbook in the app, and refuse until one is drawn. `flashroom`, for a workbook made from a spreadsheet or a Word document: the instruction is an edit to its sheet, or to the document's table it is about, planned in seconds and kept in `messages` — each cell's before and after, the rows added and removed — and nothing is written until the next instruction is `yes`, which makes it as a new version. Omit to keep the workbook's current mode. | |
| work | No | true when the instruction is work to do and never a question — your own router already said so. The run starts without first being asked whether it is a question. | |
| context | No | Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution." | |
| workbook | Yes | The workbook id. | |
| llm_model | No | The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess. | |
| attachments | No | Files to attach to the workbook BEFORE the run starts, so it reads and cites them — each {name, content_base64, content_type?}, 32 MB at most. They stay attached for every later run; list_attachments shows them. | |
| instruction | Yes | What should change, in one sentence — or, for a latticeroom, the whole draft to ground. | |
| sources_folder | No | The drive folder you keep this workbook's subject in — `/dropbox/Trevi Therapeutics`. What the run cites is filed there once it delivers, instead of a folder named after the document's title. |