Previous value: -"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. Omit to keep the workbook's current mode."New value: +"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."

Previous value: -[
-  "harnessroom",
-  "latticeroom",
-  "graphroom"
-]New value: +[
+  "harnessroom",
+  "latticeroom",
+  "graphroom",
+  "flashroom"
+]

Added value: +{
+  "description": "What it is shown by, over its name. Need not be unique. An empty string clears it.",
+  "type": "string"
+}

Removed value: -{
-  "description": "Whether the methods the instruction names are put into a harnessroom run before it starts. On by default; false is for measuring what that does.",
-  "type": "boolean"
-}

Added value: +{
+  "description": "Whether the methods the instruction names are put into a harnessroom run before it starts. On by default; false is for measuring what that does.",
+  "type": "boolean"
+}

Added value: +{
+  "description": "The same in seconds, for a run a person waits on: stopped there, it delivers the draft it has written. Give this or time_limit_minutes, not both.",
+  "maximum": 14400,
+  "minimum": 20,
+  "type": "integer"
+}

Previous value: -"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); 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. Omit to keep the workbook's current mode."New value: +"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. Omit to keep the workbook's current mode."

Previous value: -"How a research run keeps its transcript small: compaction (the default), steering, delegation, or unbounded."New value: +"How a harnessroom run keeps its transcript small: compaction (the default), steering, delegation, or unbounded."

Previous value: -"The coding harness that drives a research run."New value: +"The coding harness that drives a harnessroom run."

Previous value: -"What this workbook's runs do, from now on. `research` (a new workbook's default): the instruction is a request, and the run finds sources and writes the document. `ground`: the instruction is a draft someone already wrote, whole — markdown, its links kept — and the run leaves every word as written and marks each claim cited (with the passage quoted), self-reported, secondary only, contradicted or with no source. Link data files on the account's drive (/dropbox/...json, .csv) in the draft to settle its own figures. Omit to keep the workbook's current mode."New value: +"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); 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. Omit to keep the workbook's current mode."

Previous value: -[
-  "research",
-  "ground"
-]New value: +[
+  "harnessroom",
+  "latticeroom",
+  "graphroom"
+]

Previous value: -"The model research runs think with: a `node` from this tool's answer."New value: +"The model a harnessroom's runs think with: a `node` from this tool's answer."

Previous value: -"How long a research run may take before it is stopped."New value: +"How long a harnessroom run may take before it is stopped."