@stablebaseline/sdk 0.6.2 → 0.6.3

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/dist/index.d.cts CHANGED
@@ -34,7 +34,7 @@ interface paths {
34
34
  put?: never;
35
35
  /**
36
36
  * listDiagramTypes
37
- * @description List supported diagram types. Pass `query` to search by name OR intent (keyword + semantic): e.g. 'circuit diagram', 'wiring harness', 'timing waveform', 'network topology', 'database schema'. Use the returned `type` field with getDiagramTypeGuide (DSL instructions + example) and insertDiagramInDocument / renderDiagram.
37
+ * @description List supported diagram types (renderers such as default, mermaid, plantuml, bpmn and d2; 'default' is the platform default renderer). Pass `query` to search by name OR intent (keyword + semantic): e.g. 'circuit diagram', 'wiring harness', 'timing waveform', 'network topology', 'database schema', 'BPMN process'. Each type lists supportedDiagrams: the diagram families it draws (BPMN process, ERD, flowchart, C4, system architecture and more), each with its defaultRenderer. A query that names a family also returns matchedDiagramFamilies. Use a family's defaultRenderer as the type unless you need another renderer's own format (for example BPMN 2.0 XML). Use the returned `type` field with getDiagramTypeGuide (DSL instructions + example) and insertDiagramInDocument / renderDiagram.
38
38
  */
39
39
  post: operations["listDiagramTypes"];
40
40
  delete?: never;
@@ -54,7 +54,7 @@ interface paths {
54
54
  put?: never;
55
55
  /**
56
56
  * getDiagramTypeGuide
57
- * @description Get DSL writing instructions for a diagram type. Call before writing diagramCode.
57
+ * @description Get DSL writing instructions and an example for a diagram type (a renderer such as 'default', 'mermaid' or 'bpmn'). Also accepts a diagram family slug or name from supportedDiagrams (e.g. 'bpmn-process'), which resolves to that family's default renderer (see resolvedFrom). supportedDiagrams lists the families the type draws, each with its defaultRenderer. Call before writing diagramCode.
58
58
  */
59
59
  post: operations["getDiagramTypeGuide"];
60
60
  delete?: never;
@@ -74,7 +74,7 @@ interface paths {
74
74
  put?: never;
75
75
  /**
76
76
  * listArchitectureIcons
77
- * @description SOFTWARE & CLOUD architecture icons ONLY (AWS, Azure, GCP, Docker, Kubernetes, databases, message queues, dev tools, etc.). This catalog has NO general/nature/science/people/business icons — so for any NON-technical topic (e.g. photosynthesis, biology, history, marketing), do NOT use this tool; instead put a relevant emoji directly in the element's label (for example a sun for sunlight, a droplet for water, a leaf for a plant). It returns nothing for off-domain queries by design — never force an unrelated tech logo onto a non-tech concept. Each result has an `iconPath` (e.g. 'dev/docker.svg'). TWO ways to use it: (1) on a WHITEBOARD, drop it via addWhiteboardElements({ type:'image', iconPath:'dev/docker.svg', x, y, width:96, height:96, text:'Docker' }); (2) in a D2 systems-architecture diagram, use the iconPath as-is in D2 code (e.g. icon: dev/docker.svg).
77
+ * @description List and search the full Stable Baseline icon library, including 3,850 library icons. The AWS, Azure, GCP, Development, Essentials and other categories stay intact; library icons join matching categories, with specific Oracle Cloud, Kubernetes, Networking and General categories for the rest. The same logical name is shown once. iconKey is the exact icon string for a platform default diagram (type 'default'; e.g. {icon:'aws-account'}); iconKeys lists every exact key for that logical icon, and iconKeyUrl is its SVG. Results without an iconKey are not available in platform default diagrams. Use d2IconPath for compact relative D2 source (e.g. icon-library/azure-function-apps.svg); the renderer expands storage URLs. Existing iconPath values remain relative whiteboard paths; library-only icons supply iconUrl for a whiteboard imageUrl.
78
78
  */
79
79
  post: operations["listArchitectureIcons"];
80
80
  delete?: never;
@@ -694,7 +694,7 @@ interface paths {
694
694
  put?: never;
695
695
  /**
696
696
  * designDeckInWhiteboard
697
- * @description Create or refine a slide deck INSIDE an existing whiteboard by conversing with the AI design agent. Send a brief for a NEW deck, a change to an EXISTING one, or an answer to the agent's question. The agent builds a polished, on-brand deck and places it on the board; if the brief is ambiguous it asks ONE clarifying question (answer with the same sessionId). Returns immediately; poll getDeckReplyInWhiteboard for the result. Use for building or editing slide decks / presentations. WHITEBOARD IS REQUIRED: a deck always lives inside a whiteboard, so documentId (the whiteboard's id) is required. If you do NOT already have a whiteboard id, ASK THE USER which whiteboard they want the deck designed in — do NOT create a whiteboard automatically. Only call createWhiteboard first if the user explicitly asks for a brand-new board; otherwise use the id of the whiteboard they name. FIRST vs FOLLOW-UP: the first call (from nothing) builds; a follow-up call (an answer, a change, or a new instruction) passes the sessionId (or the deckId) plus the new message. kind:'deck' (default) is the premium on-brand HTML deck; kind:'express' builds the native, deterministic branded-executive deck directly on the whiteboard (faster, lower fidelity, one-shot, not conversational). COST + APPROVAL: a build costs 50 credits and an edit 10; a clarifying question is FREE. It can also generate imagery for the deck where the design calls for it. ADVANCED DECK BUILDING (optional, OFF by default): set advancedDeckBuilding:true to build the deck over several rounds of redraft and review by a panel of design, brand, accessibility and copy reviewers instead of one composer pass. It usually raises design quality, but it is not a guarantee. It is much slower and it costs more: a standard build takes roughly 2 to 8 minutes, advanced deck building takes roughly 15 to 20 minutes, and it adds 15 credits per depth level on top of the turn fee (advancedDeckBuildingDepth is 1 to 3, default 3, so +45 credits, making a 50-credit build cost 95). Only turn it on when the user asks for the highest quality and accepts the wait and the cost. Call FIRST without confirm to get the exact cost plus the workspace balance, show it to the user, and only call again with confirm:true once they agree. The fee is auto-refunded if a turn produces no change or fails. Returns sessionId (the conversation), deckId (the deck), status, turnType, started, awaitingUser, needsConfirmation, insufficientCredits, slideCount + slideCountClamped (the target the conversation now carries, and whether it was reduced to the maximum), advancedDeckBuilding (whether advanced deck building is on for this conversation), advancedDeckBuildingStatus, and assistantMessage. Export the finished deck with exportFromWhiteboard.
697
+ * @description Create or refine a slide deck INSIDE an existing whiteboard by conversing with the AI design agent. Send a brief for a NEW deck, a change to an EXISTING one, or an answer to the agent's question. The agent builds a polished, on-brand deck and places it on the board; if the brief is ambiguous it asks ONE clarifying question (answer with the same sessionId). Returns immediately; poll getDeckReplyInWhiteboard for the result. Use for building or editing slide decks / presentations. WHITEBOARD IS REQUIRED: a deck always lives inside a whiteboard, so documentId (the whiteboard's id) is required. If you do NOT already have a whiteboard id, ASK THE USER which whiteboard they want the deck designed in — do NOT create a whiteboard automatically. Only call createWhiteboard first if the user explicitly asks for a brand-new board; otherwise use the id of the whiteboard they name. FIRST vs FOLLOW-UP: the first call (from nothing) builds; a follow-up call (an answer, a change, or a new instruction) passes the sessionId (or the deckId) plus the new message. kind:'deck' (default) is the premium on-brand HTML deck; kind:'express' builds the native, deterministic branded-executive deck directly on the whiteboard (faster, lower fidelity, one-shot, not conversational). COST + APPROVAL: a build costs 50 credits per 30 slides (1 to 30 slides is 50, 31 to 60 is 100, and so on, with the second and later blocks charged once the deck is built and never charged twice for the same block), an edit costs a flat 50, and a clarifying question is FREE. It can also generate imagery for the deck where the design calls for it. ADVANCED DECK BUILDING (optional, OFF by default): set advancedDeckBuilding:true to build the deck over several rounds of redraft and review by a panel of design, brand, accessibility and copy reviewers instead of one composer pass. It usually raises design quality, but it is not a guarantee. It is much slower and it costs more: a standard build takes roughly 2 to 8 minutes, advanced deck building takes roughly 15 to 20 minutes, and it adds 15 credits per depth level on top of the turn fee (advancedDeckBuildingDepth is 1 to 3, default 3, so +45 credits, making a 50-credit build cost 95). Only turn it on when the user asks for the highest quality and accepts the wait and the cost. Call FIRST without confirm to get the exact cost plus the workspace balance, show it to the user, and only call again with confirm:true once they agree. The fee is auto-refunded if a turn produces no change or fails. Returns sessionId (the conversation), deckId (the deck), status, turnType, started, awaitingUser, needsConfirmation, insufficientCredits, slideCount (the target the conversation now carries) and slideCountClamped (always false; nothing reduces a slide count), advancedDeckBuilding (whether advanced deck building is on for this conversation), advancedDeckBuildingStatus, and assistantMessage. Export the finished deck with exportFromWhiteboard.
698
698
  */
699
699
  post: operations["designDeckInWhiteboard"];
700
700
  delete?: never;
@@ -714,7 +714,7 @@ interface paths {
714
714
  put?: never;
715
715
  /**
716
716
  * designIllustrationInWhiteboard
717
- * @description Create or refine a standalone ILLUSTRATION INSIDE an existing whiteboard by conversing with the AI design agent. This is the illustration sibling of designDeckInWhiteboard: same conversation, same follow-up flow, but it makes ONE on-brand illustration placed on the board (not a slide deck). Send a brief for a NEW illustration, a change to an existing one, or an answer to the agent's question. The agent generates the illustration, places it on the board, and if the brief is ambiguous it asks ONE clarifying question (answer with the same sessionId). Returns immediately; poll getDeckReplyInWhiteboard for the result. Use it when the user wants a picture they can talk about and refine turn by turn (e.g. 'draw a friendly robot onboarding a new team', then 'make it warmer', 'add a second robot'). For a quick one-shot illustration with no follow-up, use generateIllustrationInWhiteboard instead. WHITEBOARD IS REQUIRED: an illustration always lives inside a whiteboard, so documentId (the whiteboard's id) is required. If you do NOT already have a whiteboard id, ASK THE USER which whiteboard they want the illustration designed in — do NOT create a whiteboard automatically. Only call createWhiteboard first if the user explicitly asks for a brand-new board; otherwise use the id of the whiteboard they name. FIRST vs FOLLOW-UP: the first call (from nothing) builds; a follow-up call (an answer, a change, or a new instruction) passes the sessionId (or the deckId) plus the new message. COST + APPROVAL: a build costs 50 credits and an edit 10; a clarifying question is FREE. Call FIRST without confirm to get the exact cost plus the workspace balance, show it to the user, and only call again with confirm:true once they agree. The fee is auto-refunded if a turn produces no change or fails. Returns sessionId (the conversation), deckId (the illustration's id), status, turnType, started, awaitingUser, needsConfirmation, insufficientCredits, and assistantMessage.
717
+ * @description Create or refine a standalone ILLUSTRATION INSIDE an existing whiteboard by conversing with the AI design agent. This is the illustration sibling of designDeckInWhiteboard: same conversation, same follow-up flow, but it makes ONE on-brand illustration placed on the board (not a slide deck). Send a brief for a NEW illustration, a change to an existing one, or an answer to the agent's question. The agent generates the illustration, places it on the board, and if the brief is ambiguous it asks ONE clarifying question (answer with the same sessionId). Returns immediately; poll getDeckReplyInWhiteboard for the result. Use it when the user wants a picture they can talk about and refine turn by turn (e.g. 'draw a friendly robot onboarding a new team', then 'make it warmer', 'add a second robot'). For a quick one-shot illustration with no follow-up, use generateIllustrationInWhiteboard instead. WHITEBOARD IS REQUIRED: an illustration always lives inside a whiteboard, so documentId (the whiteboard's id) is required. If you do NOT already have a whiteboard id, ASK THE USER which whiteboard they want the illustration designed in — do NOT create a whiteboard automatically. Only call createWhiteboard first if the user explicitly asks for a brand-new board; otherwise use the id of the whiteboard they name. FIRST vs FOLLOW-UP: the first call (from nothing) builds; a follow-up call (an answer, a change, or a new instruction) passes the sessionId (or the deckId) plus the new message. COST + APPROVAL: a build costs 50 credits per 30 slides (1 to 30 slides is 50, 31 to 60 is 100, and so on, with the second and later blocks charged once the deck is built and never charged twice for the same block), an edit costs a flat 50, and a clarifying question is FREE. Call FIRST without confirm to get the exact cost plus the workspace balance, show it to the user, and only call again with confirm:true once they agree. The fee is auto-refunded if a turn produces no change or fails. Returns sessionId (the conversation), deckId (the illustration's id), status, turnType, started, awaitingUser, needsConfirmation, insufficientCredits, and assistantMessage.
718
718
  */
719
719
  post: operations["designIllustrationInWhiteboard"];
720
720
  delete?: never;
@@ -1094,7 +1094,7 @@ interface paths {
1094
1094
  put?: never;
1095
1095
  /**
1096
1096
  * renderDiagram
1097
- * @description Generate a diagram from its DSL/code and get the IMAGE back — WITHOUT inserting it into any document or whiteboard. For acting as a pure diagram generator. Provide diagramType (e.g. 'mermaid', 'd2', 'plantuml', 'graphviz', 'bpmn', 'vegalite'; call listDiagramTypes for the full set) and source (the diagram code). Choose format 'png' (default), 'jpeg', or 'svg'; for raster choose scale 1/2/3 for 1x/2x/3x; optional background (png only). Returns a TEMPORARY imageUrl that stays available for 1 hour (the render is then deleted), and for png/jpeg the image inline so you can see it. The link carries no signing token, so it survives being rendered as a citation. To render a diagram that already lives in a document/whiteboard use getDiagramImage; to persist a new one use insertDiagramInDocument or insertWhiteboardDiagram.
1097
+ * @description Generate a diagram from its DSL/code and get the IMAGE back — WITHOUT inserting it into any document or whiteboard. For acting as a pure diagram generator. Provide diagramType (e.g. 'default', 'mermaid', 'd2', 'plantuml', 'graphviz', 'bpmn', 'vegalite'; call listDiagramTypes for the full set) and source (the diagram code). Choose format 'png' (default), 'jpeg', or 'svg'; for raster choose scale 1/2/3 for 1x/2x/3x; optional background (png only). Returns a TEMPORARY imageUrl that stays available for 1 hour (the render is then deleted), and for png/jpeg the image inline so you can see it. The link carries no signing token, so it survives being rendered as a citation. To render a diagram that already lives in a document/whiteboard use getDiagramImage; to persist a new one use insertDiagramInDocument or insertWhiteboardDiagram.
1098
1098
  */
1099
1099
  post: operations["renderDiagram"];
1100
1100
  delete?: never;
@@ -2260,6 +2260,8 @@ interface paths {
2260
2260
  * kg_search
2261
2261
  * @description Unified Knowledge Graph KNOWLEDGE retrieval — facts, themes and relationships from INSIDE document CONTENT. To LOCATE AN ARTEFACT BY NAME OR ID rather than answer a question, pass artefactMetadataOnly:true — see below. Without that flag this tool retrieves knowledge from inside content and will not reliably find a thing by its title.
2262
2262
  *
2263
+ * DATED FACTS: the response also carries `datedFacts` for the entities the query names: what holds now by default, what held on a day with asOf, or the whole history with history:true, each fact with its dates, how it ended if it has, and its sources. Prefer them for "who owns X now", "what was X in March", "when did X change".
2264
+ *
2263
2265
  * PICK THE MODE THAT FITS THE QUERY:
2264
2266
  *
2265
2267
  * • mode='local' (default) — for SPECIFIC factual questions ("what does section 15 say about deposits?", "who is the Chief Counsel?"). FTS+vector RRF over individual document chunks. Returns precise excerpts with citations.
@@ -2320,7 +2322,7 @@ interface paths {
2320
2322
  put?: never;
2321
2323
  /**
2322
2324
  * kg_get_entity
2323
- * @description Fetch a KG entity by id or name, with 1-hop neighbours.
2325
+ * @description Fetch a KG entity by id or name, with 1-hop neighbours. The response also carries `datedFacts`: what holds now about the entity by default, what held on a day with asOf, or the whole history with history:true, each fact with its dates, how it ended if it has, and the sources that state it.
2324
2326
  */
2325
2327
  post: operations["kg_get_entity"];
2326
2328
  delete?: never;
@@ -4072,12 +4074,12 @@ interface operations {
4072
4074
  requestBody?: {
4073
4075
  content: {
4074
4076
  "application/json": {
4075
- /** @description Keyword or intent, e.g. 'circuit', 'wiring harness', 'timing'. Semantic-backed: matches descriptions, not just names. */
4077
+ /** @description Keyword or intent, e.g. 'circuit', 'wiring harness', 'timing', 'BPMN process'. Semantic-backed: matches descriptions and diagram family names, not just type names. */
4076
4078
  query?: string;
4077
4079
  enabledOnly?: boolean;
4078
4080
  limit?: number;
4079
4081
  offset?: number;
4080
- /** @description Field projection. Valid fields: type, label, description, whenToUse, dslLanguage, dslInstructions, exampleDsl, enabled, availableOnFree, sortOrder, updatedAt. */
4082
+ /** @description Field projection. Valid fields: type, label, description, whenToUse, dslLanguage, dslInstructions, exampleDsl, enabled, availableOnFree, sortOrder, updatedAt, supportedDiagrams. */
4081
4083
  fields?: string[];
4082
4084
  };
4083
4085
  };
@@ -4160,6 +4162,7 @@ interface operations {
4160
4162
  requestBody?: {
4161
4163
  content: {
4162
4164
  "application/json": {
4165
+ /** @description A diagram type from listDiagramTypes (e.g. 'default', 'mermaid', 'bpmn'), or a diagram family slug or name (e.g. 'bpmn-process'), which resolves to the family's default renderer. */
4163
4166
  type: string;
4164
4167
  /** @description Field projection. Valid fields: type, label, description, whenToUse, dslLanguage, dslInstructions, exampleDsl, enabled, sortOrder, updatedAt. */
4165
4168
  fields?: string[];
@@ -4244,13 +4247,13 @@ interface operations {
4244
4247
  requestBody?: {
4245
4248
  content: {
4246
4249
  "application/json": {
4247
- /** @description Search by name, category, vendor, or description. */
4250
+ /** @description Search by icon name, exact iconKey, category, vendor, description or aliases. */
4248
4251
  query?: string;
4249
- /** @description Filter by category (e.g. AWS, Azure, GCP, dev, essentials). */
4252
+ /** @description Filter by category, e.g. AWS, Azure, GCP, Technology, Oracle Cloud, Kubernetes, Networking, General. */
4250
4253
  category?: string;
4251
4254
  limit?: number;
4252
4255
  offset?: number;
4253
- /** @description Field projection. Valid fields: id, iconPath, iconName, category, subcategory, vendor, description, searchTerms, tags, useCases, aliases, isFeatured, displayOrder. */
4256
+ /** @description Field projection. Valid fields: id, iconPath (existing relative paths only), iconUrl, iconName, category, categories, sources, iconKey, iconKeys, iconKeyUrl, d2IconPath, subcategory, vendor, description, searchTerms, tags, useCases, aliases, isFeatured, displayOrder. */
4254
4257
  fields?: string[];
4255
4258
  };
4256
4259
  };
@@ -6351,9 +6354,9 @@ interface operations {
6351
6354
  documentId: string;
6352
6355
  /** @description Optimistic-lock token: the document's versionTimestamp from getDocument() or any mutating tool's response. (Alias accepted: versionTimestamp.) */
6353
6356
  documentVersionTimestamp?: number;
6354
- /** @description Diagram type (e.g. mermaid, plantuml, bpmn, d2). Call listDiagramTypes for all types. */
6357
+ /** @description Diagram type, meaning the renderer (e.g. default, mermaid, plantuml, bpmn, d2; 'default' is the platform default renderer). For a diagram family such as a BPMN process, an ERD or a flowchart, use the family's defaultRenderer from listDiagramTypes or getDiagramTypeGuide. Call listDiagramTypes for all types. */
6355
6358
  type: string;
6356
- /** @description Diagram DSL code. Call getDiagramTypeGuide for syntax. EXCEPTION — for type 'infographic', put a plain-English DESCRIPTION of the infographic here (NOT code); the system designs the AntV spec and renders it. */
6359
+ /** @description Diagram DSL code. Call getDiagramTypeGuide for syntax. For 'default', provide MDP JSON with stable IDs and omit every entity x/y for automatic layout; fully positioned manual diagrams are also supported, and icons must be exact iconKey values from listArchitectureIcons. EXCEPTION — for type 'infographic', put a plain-English DESCRIPTION of the infographic here (NOT code); the system designs the AntV spec and renders it. */
6357
6360
  diagramCode: string;
6358
6361
  /** @description Short description of what the diagram shows (1-2 sentences). */
6359
6362
  prompt: string;
@@ -6476,7 +6479,7 @@ interface operations {
6476
6479
  "application/json": {
6477
6480
  /** @description Diagram ID from DIAGRAM_OMITTED markers. */
6478
6481
  diagramId: string;
6479
- /** @description New diagram DSL source code. REQUIRED to change what the diagram visually renders. Call getDiagramTypeGuide for syntax. Must provide the COMPLETE updated DSL, not just the changed parts. EXCEPTION — for type 'infographic', pass either a plain-English DESCRIPTION of the new infographic (the system designs, renders, and stores the AntV spec, same as insert) or complete AntV Infographic DSL (first line `infographic <template-name>`). */
6482
+ /** @description New diagram DSL source code. REQUIRED to change what the diagram visually renders. Call getDiagramTypeGuide for syntax. Must provide the COMPLETE updated DSL, not just the changed parts. For 'default', provide complete MDP JSON and preserve stable IDs; omit entity x/y for automatic layout, or preserve all x/y in a manually positioned legacy diagram. Root layout.mode='auto' can explicitly rearrange an existing diagram. Its icons must be exact iconKey values from listArchitectureIcons. EXCEPTION — for type 'infographic', pass either a plain-English DESCRIPTION of the new infographic (the system designs, renders, and stores the AntV spec, same as insert) or complete AntV Infographic DSL (first line `infographic <template-name>`). */
6480
6483
  diagramCode?: string;
6481
6484
  /** @description New short description (metadata only — does NOT change the rendered diagram). */
6482
6485
  prompt?: string;
@@ -7154,7 +7157,7 @@ interface operations {
7154
7157
  title?: string;
7155
7158
  /** @description Optional brand kit id (from listBrandKits) to theme the deck. If omitted, the organisation's effective brand is used. */
7156
7159
  brandKitId?: string;
7157
- /** @description The number of slides to build — a hard requirement: the deck is built with exactly this many slides. SET THIS whenever the user states or implies a count, EXACT OR APPROXIMATE: '12 slides' → 12, 'about 15' / '15 or so' → 15, 'no more than 10' → 10. Never expand the user's number: if they said 'about 15', pass 15 and shape the brief to fit 15 — outlining 19 sections in the message does not raise the count, it just fights this parameter. It is PERSISTED on the conversation, so send it ONCE (on the turn that states it) and every later build turn of the same conversation carries it automatically; send it again only to CHANGE the target. It is honoured on edit turns too ('cut it to 8 slides'). Anything above the 30-slide maximum is reduced to 30 and the reduction is stated back in the response. Omit ONLY when the user gave no count at all; the designer then chooses (typical 6 to 12). */
7160
+ /** @description The number of slides to build — a hard requirement: the deck is built with exactly this many slides. SET THIS whenever the user states or implies a count, EXACT OR APPROXIMATE: '12 slides' → 12, 'about 15' / '15 or so' → 15, 'no more than 10' → 10. Never expand the user's number: if they said 'about 15', pass 15 and shape the brief to fit 15 — outlining 19 sections in the message does not raise the count, it just fights this parameter. It is PERSISTED on the conversation, so send it ONCE (on the turn that states it) and every later build turn of the same conversation carries it automatically; send it again only to CHANGE the target. It is honoured on edit turns too ('cut it to 8 slides'). THERE IS NO MAXIMUM: ask for 40, 60 or 100 slides and that is what gets built. Longer decks cost proportionally more (50 credits per 30 slides) and take proportionally longer. Omit ONLY when the user gave no count at all; the designer then chooses (typical 6 to 12). */
7158
7161
  slideCount?: number;
7159
7162
  /** @description Deprecated and ignored. Still accepted so existing callers do not break; passing it changes nothing. */
7160
7163
  imageCount?: number;
@@ -8563,9 +8566,9 @@ interface operations {
8563
8566
  "application/json": {
8564
8567
  /** @description The whiteboard's documentId. */
8565
8568
  documentId: string;
8566
- /** @description Diagram language, e.g. 'bpmn', 'mermaid', 'd2', 'plantuml', 'graphviz'. See listDiagramTypes. */
8569
+ /** @description Diagram language, e.g. 'default', 'bpmn', 'mermaid', 'd2', 'plantuml', 'graphviz'. For a diagram family, use its defaultRenderer from listDiagramTypes. */
8567
8570
  diagramType: string;
8568
- /** @description The diagram DSL / code. For type 'infographic', provide a plain-English description instead (the system designs the AntV infographic spec). */
8571
+ /** @description The diagram DSL / code. For 'default', provide MDP JSON with stable IDs and omit entity x/y for automatic layout; fully positioned manual sources remain valid; icons must be exact iconKey values from listArchitectureIcons. For 'infographic', provide a plain-English description instead (the system designs the AntV infographic spec). */
8569
8572
  source: string;
8570
8573
  /** @description Optional caption shown beneath the diagram. */
8571
8574
  caption?: string;
@@ -9155,12 +9158,12 @@ interface operations {
9155
9158
  requestBody?: {
9156
9159
  content: {
9157
9160
  "application/json": {
9158
- /** @description Diagram language, e.g. 'mermaid', 'd2', 'plantuml', 'graphviz', 'bpmn', 'vegalite'. See listDiagramTypes. */
9161
+ /** @description Diagram language, e.g. 'default', 'mermaid', 'd2', 'plantuml', 'graphviz', 'bpmn', 'vegalite'. For a diagram family, use its defaultRenderer from listDiagramTypes. */
9159
9162
  diagramType: string;
9160
- /** @description The diagram DSL / code to render. For type 'infographic', provide a plain-English description instead (the system designs the AntV infographic spec). */
9163
+ /** @description The diagram DSL / code to render. For 'default', provide MDP JSON with stable IDs and omit entity x/y for automatic layout; fully positioned manual sources remain valid; icons must be exact iconKey values from listArchitectureIcons. For 'infographic', provide a plain-English description instead (the system designs the AntV infographic spec). */
9161
9164
  source: string;
9162
9165
  /**
9163
- * @description png (default) or jpeg = raster; svg = vector.
9166
+ * @description png (default) or jpeg = raster; svg is scalable. A platform default diagram's SVG contains a browser foreignObject scene, so use PNG/JPEG where foreignObject SVG is unsupported.
9164
9167
  * @enum {string}
9165
9168
  */
9166
9169
  format?: "png" | "jpeg" | "svg";
@@ -9261,7 +9264,7 @@ interface operations {
9261
9264
  /** @description The diagram's id (from getDocument markers / getDiagramInDocument). */
9262
9265
  diagramId: string;
9263
9266
  /**
9264
- * @description png (default) or jpeg = raster; svg = vector.
9267
+ * @description png (default) or jpeg = raster; svg is scalable. A platform default diagram's SVG contains a browser foreignObject scene, so use PNG/JPEG where foreignObject SVG is unsupported.
9265
9268
  * @enum {string}
9266
9269
  */
9267
9270
  format?: "png" | "jpeg" | "svg";
@@ -14778,6 +14781,12 @@ interface operations {
14778
14781
  depth?: number;
14779
14782
  /** @default 20 */
14780
14783
  limit?: number;
14784
+ /** @description Dated facts: return what held on this day (YYYY-MM-DD) instead of what holds now. For example the owner, status or supplier as it was on a past date. */
14785
+ asOf?: string;
14786
+ /** @description Dated facts: return every fact with its dates, including facts that have ended (and how they ended) and planned ones, oldest first. Use for "how did X change" or "what was X before". */
14787
+ history?: boolean;
14788
+ /** @description Dated facts: the IANA time zone to give days in (for example Australia/Sydney, Asia/Kolkata, America/New_York). Defaults to the user's saved time zone, else UTC. Pass the user's zone when you know it, so "today" and dates match their calendar. */
14789
+ timeZone?: string;
14781
14790
  };
14782
14791
  };
14783
14792
  };
@@ -14946,6 +14955,12 @@ interface operations {
14946
14955
  name?: string;
14947
14956
  /** @description Scope the lookup to one project. Recommended when resolving by `name`, since the same entity name can exist in several projects. */
14948
14957
  projectId?: string;
14958
+ /** @description Dated facts: return what held on this day (YYYY-MM-DD) instead of what holds now. For example the owner, status or supplier as it was on a past date. */
14959
+ asOf?: string;
14960
+ /** @description Dated facts: return every fact with its dates, including facts that have ended (and how they ended) and planned ones, oldest first. Use for "how did X change" or "what was X before". */
14961
+ history?: boolean;
14962
+ /** @description Dated facts: the IANA time zone to give days in (for example Australia/Sydney, Asia/Kolkata, America/New_York). Defaults to the user's saved time zone, else UTC. */
14963
+ timeZone?: string;
14949
14964
  };
14950
14965
  };
14951
14966
  };
package/dist/index.d.ts CHANGED
@@ -34,7 +34,7 @@ interface paths {
34
34
  put?: never;
35
35
  /**
36
36
  * listDiagramTypes
37
- * @description List supported diagram types. Pass `query` to search by name OR intent (keyword + semantic): e.g. 'circuit diagram', 'wiring harness', 'timing waveform', 'network topology', 'database schema'. Use the returned `type` field with getDiagramTypeGuide (DSL instructions + example) and insertDiagramInDocument / renderDiagram.
37
+ * @description List supported diagram types (renderers such as default, mermaid, plantuml, bpmn and d2; 'default' is the platform default renderer). Pass `query` to search by name OR intent (keyword + semantic): e.g. 'circuit diagram', 'wiring harness', 'timing waveform', 'network topology', 'database schema', 'BPMN process'. Each type lists supportedDiagrams: the diagram families it draws (BPMN process, ERD, flowchart, C4, system architecture and more), each with its defaultRenderer. A query that names a family also returns matchedDiagramFamilies. Use a family's defaultRenderer as the type unless you need another renderer's own format (for example BPMN 2.0 XML). Use the returned `type` field with getDiagramTypeGuide (DSL instructions + example) and insertDiagramInDocument / renderDiagram.
38
38
  */
39
39
  post: operations["listDiagramTypes"];
40
40
  delete?: never;
@@ -54,7 +54,7 @@ interface paths {
54
54
  put?: never;
55
55
  /**
56
56
  * getDiagramTypeGuide
57
- * @description Get DSL writing instructions for a diagram type. Call before writing diagramCode.
57
+ * @description Get DSL writing instructions and an example for a diagram type (a renderer such as 'default', 'mermaid' or 'bpmn'). Also accepts a diagram family slug or name from supportedDiagrams (e.g. 'bpmn-process'), which resolves to that family's default renderer (see resolvedFrom). supportedDiagrams lists the families the type draws, each with its defaultRenderer. Call before writing diagramCode.
58
58
  */
59
59
  post: operations["getDiagramTypeGuide"];
60
60
  delete?: never;
@@ -74,7 +74,7 @@ interface paths {
74
74
  put?: never;
75
75
  /**
76
76
  * listArchitectureIcons
77
- * @description SOFTWARE & CLOUD architecture icons ONLY (AWS, Azure, GCP, Docker, Kubernetes, databases, message queues, dev tools, etc.). This catalog has NO general/nature/science/people/business icons — so for any NON-technical topic (e.g. photosynthesis, biology, history, marketing), do NOT use this tool; instead put a relevant emoji directly in the element's label (for example a sun for sunlight, a droplet for water, a leaf for a plant). It returns nothing for off-domain queries by design — never force an unrelated tech logo onto a non-tech concept. Each result has an `iconPath` (e.g. 'dev/docker.svg'). TWO ways to use it: (1) on a WHITEBOARD, drop it via addWhiteboardElements({ type:'image', iconPath:'dev/docker.svg', x, y, width:96, height:96, text:'Docker' }); (2) in a D2 systems-architecture diagram, use the iconPath as-is in D2 code (e.g. icon: dev/docker.svg).
77
+ * @description List and search the full Stable Baseline icon library, including 3,850 library icons. The AWS, Azure, GCP, Development, Essentials and other categories stay intact; library icons join matching categories, with specific Oracle Cloud, Kubernetes, Networking and General categories for the rest. The same logical name is shown once. iconKey is the exact icon string for a platform default diagram (type 'default'; e.g. {icon:'aws-account'}); iconKeys lists every exact key for that logical icon, and iconKeyUrl is its SVG. Results without an iconKey are not available in platform default diagrams. Use d2IconPath for compact relative D2 source (e.g. icon-library/azure-function-apps.svg); the renderer expands storage URLs. Existing iconPath values remain relative whiteboard paths; library-only icons supply iconUrl for a whiteboard imageUrl.
78
78
  */
79
79
  post: operations["listArchitectureIcons"];
80
80
  delete?: never;
@@ -694,7 +694,7 @@ interface paths {
694
694
  put?: never;
695
695
  /**
696
696
  * designDeckInWhiteboard
697
- * @description Create or refine a slide deck INSIDE an existing whiteboard by conversing with the AI design agent. Send a brief for a NEW deck, a change to an EXISTING one, or an answer to the agent's question. The agent builds a polished, on-brand deck and places it on the board; if the brief is ambiguous it asks ONE clarifying question (answer with the same sessionId). Returns immediately; poll getDeckReplyInWhiteboard for the result. Use for building or editing slide decks / presentations. WHITEBOARD IS REQUIRED: a deck always lives inside a whiteboard, so documentId (the whiteboard's id) is required. If you do NOT already have a whiteboard id, ASK THE USER which whiteboard they want the deck designed in — do NOT create a whiteboard automatically. Only call createWhiteboard first if the user explicitly asks for a brand-new board; otherwise use the id of the whiteboard they name. FIRST vs FOLLOW-UP: the first call (from nothing) builds; a follow-up call (an answer, a change, or a new instruction) passes the sessionId (or the deckId) plus the new message. kind:'deck' (default) is the premium on-brand HTML deck; kind:'express' builds the native, deterministic branded-executive deck directly on the whiteboard (faster, lower fidelity, one-shot, not conversational). COST + APPROVAL: a build costs 50 credits and an edit 10; a clarifying question is FREE. It can also generate imagery for the deck where the design calls for it. ADVANCED DECK BUILDING (optional, OFF by default): set advancedDeckBuilding:true to build the deck over several rounds of redraft and review by a panel of design, brand, accessibility and copy reviewers instead of one composer pass. It usually raises design quality, but it is not a guarantee. It is much slower and it costs more: a standard build takes roughly 2 to 8 minutes, advanced deck building takes roughly 15 to 20 minutes, and it adds 15 credits per depth level on top of the turn fee (advancedDeckBuildingDepth is 1 to 3, default 3, so +45 credits, making a 50-credit build cost 95). Only turn it on when the user asks for the highest quality and accepts the wait and the cost. Call FIRST without confirm to get the exact cost plus the workspace balance, show it to the user, and only call again with confirm:true once they agree. The fee is auto-refunded if a turn produces no change or fails. Returns sessionId (the conversation), deckId (the deck), status, turnType, started, awaitingUser, needsConfirmation, insufficientCredits, slideCount + slideCountClamped (the target the conversation now carries, and whether it was reduced to the maximum), advancedDeckBuilding (whether advanced deck building is on for this conversation), advancedDeckBuildingStatus, and assistantMessage. Export the finished deck with exportFromWhiteboard.
697
+ * @description Create or refine a slide deck INSIDE an existing whiteboard by conversing with the AI design agent. Send a brief for a NEW deck, a change to an EXISTING one, or an answer to the agent's question. The agent builds a polished, on-brand deck and places it on the board; if the brief is ambiguous it asks ONE clarifying question (answer with the same sessionId). Returns immediately; poll getDeckReplyInWhiteboard for the result. Use for building or editing slide decks / presentations. WHITEBOARD IS REQUIRED: a deck always lives inside a whiteboard, so documentId (the whiteboard's id) is required. If you do NOT already have a whiteboard id, ASK THE USER which whiteboard they want the deck designed in — do NOT create a whiteboard automatically. Only call createWhiteboard first if the user explicitly asks for a brand-new board; otherwise use the id of the whiteboard they name. FIRST vs FOLLOW-UP: the first call (from nothing) builds; a follow-up call (an answer, a change, or a new instruction) passes the sessionId (or the deckId) plus the new message. kind:'deck' (default) is the premium on-brand HTML deck; kind:'express' builds the native, deterministic branded-executive deck directly on the whiteboard (faster, lower fidelity, one-shot, not conversational). COST + APPROVAL: a build costs 50 credits per 30 slides (1 to 30 slides is 50, 31 to 60 is 100, and so on, with the second and later blocks charged once the deck is built and never charged twice for the same block), an edit costs a flat 50, and a clarifying question is FREE. It can also generate imagery for the deck where the design calls for it. ADVANCED DECK BUILDING (optional, OFF by default): set advancedDeckBuilding:true to build the deck over several rounds of redraft and review by a panel of design, brand, accessibility and copy reviewers instead of one composer pass. It usually raises design quality, but it is not a guarantee. It is much slower and it costs more: a standard build takes roughly 2 to 8 minutes, advanced deck building takes roughly 15 to 20 minutes, and it adds 15 credits per depth level on top of the turn fee (advancedDeckBuildingDepth is 1 to 3, default 3, so +45 credits, making a 50-credit build cost 95). Only turn it on when the user asks for the highest quality and accepts the wait and the cost. Call FIRST without confirm to get the exact cost plus the workspace balance, show it to the user, and only call again with confirm:true once they agree. The fee is auto-refunded if a turn produces no change or fails. Returns sessionId (the conversation), deckId (the deck), status, turnType, started, awaitingUser, needsConfirmation, insufficientCredits, slideCount (the target the conversation now carries) and slideCountClamped (always false; nothing reduces a slide count), advancedDeckBuilding (whether advanced deck building is on for this conversation), advancedDeckBuildingStatus, and assistantMessage. Export the finished deck with exportFromWhiteboard.
698
698
  */
699
699
  post: operations["designDeckInWhiteboard"];
700
700
  delete?: never;
@@ -714,7 +714,7 @@ interface paths {
714
714
  put?: never;
715
715
  /**
716
716
  * designIllustrationInWhiteboard
717
- * @description Create or refine a standalone ILLUSTRATION INSIDE an existing whiteboard by conversing with the AI design agent. This is the illustration sibling of designDeckInWhiteboard: same conversation, same follow-up flow, but it makes ONE on-brand illustration placed on the board (not a slide deck). Send a brief for a NEW illustration, a change to an existing one, or an answer to the agent's question. The agent generates the illustration, places it on the board, and if the brief is ambiguous it asks ONE clarifying question (answer with the same sessionId). Returns immediately; poll getDeckReplyInWhiteboard for the result. Use it when the user wants a picture they can talk about and refine turn by turn (e.g. 'draw a friendly robot onboarding a new team', then 'make it warmer', 'add a second robot'). For a quick one-shot illustration with no follow-up, use generateIllustrationInWhiteboard instead. WHITEBOARD IS REQUIRED: an illustration always lives inside a whiteboard, so documentId (the whiteboard's id) is required. If you do NOT already have a whiteboard id, ASK THE USER which whiteboard they want the illustration designed in — do NOT create a whiteboard automatically. Only call createWhiteboard first if the user explicitly asks for a brand-new board; otherwise use the id of the whiteboard they name. FIRST vs FOLLOW-UP: the first call (from nothing) builds; a follow-up call (an answer, a change, or a new instruction) passes the sessionId (or the deckId) plus the new message. COST + APPROVAL: a build costs 50 credits and an edit 10; a clarifying question is FREE. Call FIRST without confirm to get the exact cost plus the workspace balance, show it to the user, and only call again with confirm:true once they agree. The fee is auto-refunded if a turn produces no change or fails. Returns sessionId (the conversation), deckId (the illustration's id), status, turnType, started, awaitingUser, needsConfirmation, insufficientCredits, and assistantMessage.
717
+ * @description Create or refine a standalone ILLUSTRATION INSIDE an existing whiteboard by conversing with the AI design agent. This is the illustration sibling of designDeckInWhiteboard: same conversation, same follow-up flow, but it makes ONE on-brand illustration placed on the board (not a slide deck). Send a brief for a NEW illustration, a change to an existing one, or an answer to the agent's question. The agent generates the illustration, places it on the board, and if the brief is ambiguous it asks ONE clarifying question (answer with the same sessionId). Returns immediately; poll getDeckReplyInWhiteboard for the result. Use it when the user wants a picture they can talk about and refine turn by turn (e.g. 'draw a friendly robot onboarding a new team', then 'make it warmer', 'add a second robot'). For a quick one-shot illustration with no follow-up, use generateIllustrationInWhiteboard instead. WHITEBOARD IS REQUIRED: an illustration always lives inside a whiteboard, so documentId (the whiteboard's id) is required. If you do NOT already have a whiteboard id, ASK THE USER which whiteboard they want the illustration designed in — do NOT create a whiteboard automatically. Only call createWhiteboard first if the user explicitly asks for a brand-new board; otherwise use the id of the whiteboard they name. FIRST vs FOLLOW-UP: the first call (from nothing) builds; a follow-up call (an answer, a change, or a new instruction) passes the sessionId (or the deckId) plus the new message. COST + APPROVAL: a build costs 50 credits per 30 slides (1 to 30 slides is 50, 31 to 60 is 100, and so on, with the second and later blocks charged once the deck is built and never charged twice for the same block), an edit costs a flat 50, and a clarifying question is FREE. Call FIRST without confirm to get the exact cost plus the workspace balance, show it to the user, and only call again with confirm:true once they agree. The fee is auto-refunded if a turn produces no change or fails. Returns sessionId (the conversation), deckId (the illustration's id), status, turnType, started, awaitingUser, needsConfirmation, insufficientCredits, and assistantMessage.
718
718
  */
719
719
  post: operations["designIllustrationInWhiteboard"];
720
720
  delete?: never;
@@ -1094,7 +1094,7 @@ interface paths {
1094
1094
  put?: never;
1095
1095
  /**
1096
1096
  * renderDiagram
1097
- * @description Generate a diagram from its DSL/code and get the IMAGE back — WITHOUT inserting it into any document or whiteboard. For acting as a pure diagram generator. Provide diagramType (e.g. 'mermaid', 'd2', 'plantuml', 'graphviz', 'bpmn', 'vegalite'; call listDiagramTypes for the full set) and source (the diagram code). Choose format 'png' (default), 'jpeg', or 'svg'; for raster choose scale 1/2/3 for 1x/2x/3x; optional background (png only). Returns a TEMPORARY imageUrl that stays available for 1 hour (the render is then deleted), and for png/jpeg the image inline so you can see it. The link carries no signing token, so it survives being rendered as a citation. To render a diagram that already lives in a document/whiteboard use getDiagramImage; to persist a new one use insertDiagramInDocument or insertWhiteboardDiagram.
1097
+ * @description Generate a diagram from its DSL/code and get the IMAGE back — WITHOUT inserting it into any document or whiteboard. For acting as a pure diagram generator. Provide diagramType (e.g. 'default', 'mermaid', 'd2', 'plantuml', 'graphviz', 'bpmn', 'vegalite'; call listDiagramTypes for the full set) and source (the diagram code). Choose format 'png' (default), 'jpeg', or 'svg'; for raster choose scale 1/2/3 for 1x/2x/3x; optional background (png only). Returns a TEMPORARY imageUrl that stays available for 1 hour (the render is then deleted), and for png/jpeg the image inline so you can see it. The link carries no signing token, so it survives being rendered as a citation. To render a diagram that already lives in a document/whiteboard use getDiagramImage; to persist a new one use insertDiagramInDocument or insertWhiteboardDiagram.
1098
1098
  */
1099
1099
  post: operations["renderDiagram"];
1100
1100
  delete?: never;
@@ -2260,6 +2260,8 @@ interface paths {
2260
2260
  * kg_search
2261
2261
  * @description Unified Knowledge Graph KNOWLEDGE retrieval — facts, themes and relationships from INSIDE document CONTENT. To LOCATE AN ARTEFACT BY NAME OR ID rather than answer a question, pass artefactMetadataOnly:true — see below. Without that flag this tool retrieves knowledge from inside content and will not reliably find a thing by its title.
2262
2262
  *
2263
+ * DATED FACTS: the response also carries `datedFacts` for the entities the query names: what holds now by default, what held on a day with asOf, or the whole history with history:true, each fact with its dates, how it ended if it has, and its sources. Prefer them for "who owns X now", "what was X in March", "when did X change".
2264
+ *
2263
2265
  * PICK THE MODE THAT FITS THE QUERY:
2264
2266
  *
2265
2267
  * • mode='local' (default) — for SPECIFIC factual questions ("what does section 15 say about deposits?", "who is the Chief Counsel?"). FTS+vector RRF over individual document chunks. Returns precise excerpts with citations.
@@ -2320,7 +2322,7 @@ interface paths {
2320
2322
  put?: never;
2321
2323
  /**
2322
2324
  * kg_get_entity
2323
- * @description Fetch a KG entity by id or name, with 1-hop neighbours.
2325
+ * @description Fetch a KG entity by id or name, with 1-hop neighbours. The response also carries `datedFacts`: what holds now about the entity by default, what held on a day with asOf, or the whole history with history:true, each fact with its dates, how it ended if it has, and the sources that state it.
2324
2326
  */
2325
2327
  post: operations["kg_get_entity"];
2326
2328
  delete?: never;
@@ -4072,12 +4074,12 @@ interface operations {
4072
4074
  requestBody?: {
4073
4075
  content: {
4074
4076
  "application/json": {
4075
- /** @description Keyword or intent, e.g. 'circuit', 'wiring harness', 'timing'. Semantic-backed: matches descriptions, not just names. */
4077
+ /** @description Keyword or intent, e.g. 'circuit', 'wiring harness', 'timing', 'BPMN process'. Semantic-backed: matches descriptions and diagram family names, not just type names. */
4076
4078
  query?: string;
4077
4079
  enabledOnly?: boolean;
4078
4080
  limit?: number;
4079
4081
  offset?: number;
4080
- /** @description Field projection. Valid fields: type, label, description, whenToUse, dslLanguage, dslInstructions, exampleDsl, enabled, availableOnFree, sortOrder, updatedAt. */
4082
+ /** @description Field projection. Valid fields: type, label, description, whenToUse, dslLanguage, dslInstructions, exampleDsl, enabled, availableOnFree, sortOrder, updatedAt, supportedDiagrams. */
4081
4083
  fields?: string[];
4082
4084
  };
4083
4085
  };
@@ -4160,6 +4162,7 @@ interface operations {
4160
4162
  requestBody?: {
4161
4163
  content: {
4162
4164
  "application/json": {
4165
+ /** @description A diagram type from listDiagramTypes (e.g. 'default', 'mermaid', 'bpmn'), or a diagram family slug or name (e.g. 'bpmn-process'), which resolves to the family's default renderer. */
4163
4166
  type: string;
4164
4167
  /** @description Field projection. Valid fields: type, label, description, whenToUse, dslLanguage, dslInstructions, exampleDsl, enabled, sortOrder, updatedAt. */
4165
4168
  fields?: string[];
@@ -4244,13 +4247,13 @@ interface operations {
4244
4247
  requestBody?: {
4245
4248
  content: {
4246
4249
  "application/json": {
4247
- /** @description Search by name, category, vendor, or description. */
4250
+ /** @description Search by icon name, exact iconKey, category, vendor, description or aliases. */
4248
4251
  query?: string;
4249
- /** @description Filter by category (e.g. AWS, Azure, GCP, dev, essentials). */
4252
+ /** @description Filter by category, e.g. AWS, Azure, GCP, Technology, Oracle Cloud, Kubernetes, Networking, General. */
4250
4253
  category?: string;
4251
4254
  limit?: number;
4252
4255
  offset?: number;
4253
- /** @description Field projection. Valid fields: id, iconPath, iconName, category, subcategory, vendor, description, searchTerms, tags, useCases, aliases, isFeatured, displayOrder. */
4256
+ /** @description Field projection. Valid fields: id, iconPath (existing relative paths only), iconUrl, iconName, category, categories, sources, iconKey, iconKeys, iconKeyUrl, d2IconPath, subcategory, vendor, description, searchTerms, tags, useCases, aliases, isFeatured, displayOrder. */
4254
4257
  fields?: string[];
4255
4258
  };
4256
4259
  };
@@ -6351,9 +6354,9 @@ interface operations {
6351
6354
  documentId: string;
6352
6355
  /** @description Optimistic-lock token: the document's versionTimestamp from getDocument() or any mutating tool's response. (Alias accepted: versionTimestamp.) */
6353
6356
  documentVersionTimestamp?: number;
6354
- /** @description Diagram type (e.g. mermaid, plantuml, bpmn, d2). Call listDiagramTypes for all types. */
6357
+ /** @description Diagram type, meaning the renderer (e.g. default, mermaid, plantuml, bpmn, d2; 'default' is the platform default renderer). For a diagram family such as a BPMN process, an ERD or a flowchart, use the family's defaultRenderer from listDiagramTypes or getDiagramTypeGuide. Call listDiagramTypes for all types. */
6355
6358
  type: string;
6356
- /** @description Diagram DSL code. Call getDiagramTypeGuide for syntax. EXCEPTION — for type 'infographic', put a plain-English DESCRIPTION of the infographic here (NOT code); the system designs the AntV spec and renders it. */
6359
+ /** @description Diagram DSL code. Call getDiagramTypeGuide for syntax. For 'default', provide MDP JSON with stable IDs and omit every entity x/y for automatic layout; fully positioned manual diagrams are also supported, and icons must be exact iconKey values from listArchitectureIcons. EXCEPTION — for type 'infographic', put a plain-English DESCRIPTION of the infographic here (NOT code); the system designs the AntV spec and renders it. */
6357
6360
  diagramCode: string;
6358
6361
  /** @description Short description of what the diagram shows (1-2 sentences). */
6359
6362
  prompt: string;
@@ -6476,7 +6479,7 @@ interface operations {
6476
6479
  "application/json": {
6477
6480
  /** @description Diagram ID from DIAGRAM_OMITTED markers. */
6478
6481
  diagramId: string;
6479
- /** @description New diagram DSL source code. REQUIRED to change what the diagram visually renders. Call getDiagramTypeGuide for syntax. Must provide the COMPLETE updated DSL, not just the changed parts. EXCEPTION — for type 'infographic', pass either a plain-English DESCRIPTION of the new infographic (the system designs, renders, and stores the AntV spec, same as insert) or complete AntV Infographic DSL (first line `infographic <template-name>`). */
6482
+ /** @description New diagram DSL source code. REQUIRED to change what the diagram visually renders. Call getDiagramTypeGuide for syntax. Must provide the COMPLETE updated DSL, not just the changed parts. For 'default', provide complete MDP JSON and preserve stable IDs; omit entity x/y for automatic layout, or preserve all x/y in a manually positioned legacy diagram. Root layout.mode='auto' can explicitly rearrange an existing diagram. Its icons must be exact iconKey values from listArchitectureIcons. EXCEPTION — for type 'infographic', pass either a plain-English DESCRIPTION of the new infographic (the system designs, renders, and stores the AntV spec, same as insert) or complete AntV Infographic DSL (first line `infographic <template-name>`). */
6480
6483
  diagramCode?: string;
6481
6484
  /** @description New short description (metadata only — does NOT change the rendered diagram). */
6482
6485
  prompt?: string;
@@ -7154,7 +7157,7 @@ interface operations {
7154
7157
  title?: string;
7155
7158
  /** @description Optional brand kit id (from listBrandKits) to theme the deck. If omitted, the organisation's effective brand is used. */
7156
7159
  brandKitId?: string;
7157
- /** @description The number of slides to build — a hard requirement: the deck is built with exactly this many slides. SET THIS whenever the user states or implies a count, EXACT OR APPROXIMATE: '12 slides' → 12, 'about 15' / '15 or so' → 15, 'no more than 10' → 10. Never expand the user's number: if they said 'about 15', pass 15 and shape the brief to fit 15 — outlining 19 sections in the message does not raise the count, it just fights this parameter. It is PERSISTED on the conversation, so send it ONCE (on the turn that states it) and every later build turn of the same conversation carries it automatically; send it again only to CHANGE the target. It is honoured on edit turns too ('cut it to 8 slides'). Anything above the 30-slide maximum is reduced to 30 and the reduction is stated back in the response. Omit ONLY when the user gave no count at all; the designer then chooses (typical 6 to 12). */
7160
+ /** @description The number of slides to build — a hard requirement: the deck is built with exactly this many slides. SET THIS whenever the user states or implies a count, EXACT OR APPROXIMATE: '12 slides' → 12, 'about 15' / '15 or so' → 15, 'no more than 10' → 10. Never expand the user's number: if they said 'about 15', pass 15 and shape the brief to fit 15 — outlining 19 sections in the message does not raise the count, it just fights this parameter. It is PERSISTED on the conversation, so send it ONCE (on the turn that states it) and every later build turn of the same conversation carries it automatically; send it again only to CHANGE the target. It is honoured on edit turns too ('cut it to 8 slides'). THERE IS NO MAXIMUM: ask for 40, 60 or 100 slides and that is what gets built. Longer decks cost proportionally more (50 credits per 30 slides) and take proportionally longer. Omit ONLY when the user gave no count at all; the designer then chooses (typical 6 to 12). */
7158
7161
  slideCount?: number;
7159
7162
  /** @description Deprecated and ignored. Still accepted so existing callers do not break; passing it changes nothing. */
7160
7163
  imageCount?: number;
@@ -8563,9 +8566,9 @@ interface operations {
8563
8566
  "application/json": {
8564
8567
  /** @description The whiteboard's documentId. */
8565
8568
  documentId: string;
8566
- /** @description Diagram language, e.g. 'bpmn', 'mermaid', 'd2', 'plantuml', 'graphviz'. See listDiagramTypes. */
8569
+ /** @description Diagram language, e.g. 'default', 'bpmn', 'mermaid', 'd2', 'plantuml', 'graphviz'. For a diagram family, use its defaultRenderer from listDiagramTypes. */
8567
8570
  diagramType: string;
8568
- /** @description The diagram DSL / code. For type 'infographic', provide a plain-English description instead (the system designs the AntV infographic spec). */
8571
+ /** @description The diagram DSL / code. For 'default', provide MDP JSON with stable IDs and omit entity x/y for automatic layout; fully positioned manual sources remain valid; icons must be exact iconKey values from listArchitectureIcons. For 'infographic', provide a plain-English description instead (the system designs the AntV infographic spec). */
8569
8572
  source: string;
8570
8573
  /** @description Optional caption shown beneath the diagram. */
8571
8574
  caption?: string;
@@ -9155,12 +9158,12 @@ interface operations {
9155
9158
  requestBody?: {
9156
9159
  content: {
9157
9160
  "application/json": {
9158
- /** @description Diagram language, e.g. 'mermaid', 'd2', 'plantuml', 'graphviz', 'bpmn', 'vegalite'. See listDiagramTypes. */
9161
+ /** @description Diagram language, e.g. 'default', 'mermaid', 'd2', 'plantuml', 'graphviz', 'bpmn', 'vegalite'. For a diagram family, use its defaultRenderer from listDiagramTypes. */
9159
9162
  diagramType: string;
9160
- /** @description The diagram DSL / code to render. For type 'infographic', provide a plain-English description instead (the system designs the AntV infographic spec). */
9163
+ /** @description The diagram DSL / code to render. For 'default', provide MDP JSON with stable IDs and omit entity x/y for automatic layout; fully positioned manual sources remain valid; icons must be exact iconKey values from listArchitectureIcons. For 'infographic', provide a plain-English description instead (the system designs the AntV infographic spec). */
9161
9164
  source: string;
9162
9165
  /**
9163
- * @description png (default) or jpeg = raster; svg = vector.
9166
+ * @description png (default) or jpeg = raster; svg is scalable. A platform default diagram's SVG contains a browser foreignObject scene, so use PNG/JPEG where foreignObject SVG is unsupported.
9164
9167
  * @enum {string}
9165
9168
  */
9166
9169
  format?: "png" | "jpeg" | "svg";
@@ -9261,7 +9264,7 @@ interface operations {
9261
9264
  /** @description The diagram's id (from getDocument markers / getDiagramInDocument). */
9262
9265
  diagramId: string;
9263
9266
  /**
9264
- * @description png (default) or jpeg = raster; svg = vector.
9267
+ * @description png (default) or jpeg = raster; svg is scalable. A platform default diagram's SVG contains a browser foreignObject scene, so use PNG/JPEG where foreignObject SVG is unsupported.
9265
9268
  * @enum {string}
9266
9269
  */
9267
9270
  format?: "png" | "jpeg" | "svg";
@@ -14778,6 +14781,12 @@ interface operations {
14778
14781
  depth?: number;
14779
14782
  /** @default 20 */
14780
14783
  limit?: number;
14784
+ /** @description Dated facts: return what held on this day (YYYY-MM-DD) instead of what holds now. For example the owner, status or supplier as it was on a past date. */
14785
+ asOf?: string;
14786
+ /** @description Dated facts: return every fact with its dates, including facts that have ended (and how they ended) and planned ones, oldest first. Use for "how did X change" or "what was X before". */
14787
+ history?: boolean;
14788
+ /** @description Dated facts: the IANA time zone to give days in (for example Australia/Sydney, Asia/Kolkata, America/New_York). Defaults to the user's saved time zone, else UTC. Pass the user's zone when you know it, so "today" and dates match their calendar. */
14789
+ timeZone?: string;
14781
14790
  };
14782
14791
  };
14783
14792
  };
@@ -14946,6 +14955,12 @@ interface operations {
14946
14955
  name?: string;
14947
14956
  /** @description Scope the lookup to one project. Recommended when resolving by `name`, since the same entity name can exist in several projects. */
14948
14957
  projectId?: string;
14958
+ /** @description Dated facts: return what held on this day (YYYY-MM-DD) instead of what holds now. For example the owner, status or supplier as it was on a past date. */
14959
+ asOf?: string;
14960
+ /** @description Dated facts: return every fact with its dates, including facts that have ended (and how they ended) and planned ones, oldest first. Use for "how did X change" or "what was X before". */
14961
+ history?: boolean;
14962
+ /** @description Dated facts: the IANA time zone to give days in (for example Australia/Sydney, Asia/Kolkata, America/New_York). Defaults to the user's saved time zone, else UTC. */
14963
+ timeZone?: string;
14949
14964
  };
14950
14965
  };
14951
14966
  };
package/openapi.json CHANGED
@@ -266,7 +266,7 @@
266
266
  "/tools/listDiagramTypes": {
267
267
  "post": {
268
268
  "summary": "listDiagramTypes",
269
- "description": "List supported diagram types. Pass `query` to search by name OR intent (keyword + semantic): e.g. 'circuit diagram', 'wiring harness', 'timing waveform', 'network topology', 'database schema'. Use the returned `type` field with getDiagramTypeGuide (DSL instructions + example) and insertDiagramInDocument / renderDiagram.",
269
+ "description": "List supported diagram types (renderers such as default, mermaid, plantuml, bpmn and d2; 'default' is the platform default renderer). Pass `query` to search by name OR intent (keyword + semantic): e.g. 'circuit diagram', 'wiring harness', 'timing waveform', 'network topology', 'database schema', 'BPMN process'. Each type lists supportedDiagrams: the diagram families it draws (BPMN process, ERD, flowchart, C4, system architecture and more), each with its defaultRenderer. A query that names a family also returns matchedDiagramFamilies. Use a family's defaultRenderer as the type unless you need another renderer's own format (for example BPMN 2.0 XML). Use the returned `type` field with getDiagramTypeGuide (DSL instructions + example) and insertDiagramInDocument / renderDiagram.",
270
270
  "operationId": "listDiagramTypes",
271
271
  "tags": [
272
272
  "diagrams"
@@ -280,7 +280,7 @@
280
280
  "properties": {
281
281
  "query": {
282
282
  "type": "string",
283
- "description": "Keyword or intent, e.g. 'circuit', 'wiring harness', 'timing'. Semantic-backed: matches descriptions, not just names."
283
+ "description": "Keyword or intent, e.g. 'circuit', 'wiring harness', 'timing', 'BPMN process'. Semantic-backed: matches descriptions and diagram family names, not just type names."
284
284
  },
285
285
  "enabledOnly": {
286
286
  "type": "boolean"
@@ -296,7 +296,7 @@
296
296
  "items": {
297
297
  "type": "string"
298
298
  },
299
- "description": "Field projection. Valid fields: type, label, description, whenToUse, dslLanguage, dslInstructions, exampleDsl, enabled, availableOnFree, sortOrder, updatedAt."
299
+ "description": "Field projection. Valid fields: type, label, description, whenToUse, dslLanguage, dslInstructions, exampleDsl, enabled, availableOnFree, sortOrder, updatedAt, supportedDiagrams."
300
300
  }
301
301
  }
302
302
  }
@@ -381,7 +381,7 @@
381
381
  "/tools/getDiagramTypeGuide": {
382
382
  "post": {
383
383
  "summary": "getDiagramTypeGuide",
384
- "description": "Get DSL writing instructions for a diagram type. Call before writing diagramCode.",
384
+ "description": "Get DSL writing instructions and an example for a diagram type (a renderer such as 'default', 'mermaid' or 'bpmn'). Also accepts a diagram family slug or name from supportedDiagrams (e.g. 'bpmn-process'), which resolves to that family's default renderer (see resolvedFrom). supportedDiagrams lists the families the type draws, each with its defaultRenderer. Call before writing diagramCode.",
385
385
  "operationId": "getDiagramTypeGuide",
386
386
  "tags": [
387
387
  "diagrams"
@@ -394,7 +394,8 @@
394
394
  "type": "object",
395
395
  "properties": {
396
396
  "type": {
397
- "type": "string"
397
+ "type": "string",
398
+ "description": "A diagram type from listDiagramTypes (e.g. 'default', 'mermaid', 'bpmn'), or a diagram family slug or name (e.g. 'bpmn-process'), which resolves to the family's default renderer."
398
399
  },
399
400
  "fields": {
400
401
  "type": "array",
@@ -489,7 +490,7 @@
489
490
  "/tools/listArchitectureIcons": {
490
491
  "post": {
491
492
  "summary": "listArchitectureIcons",
492
- "description": "SOFTWARE & CLOUD architecture icons ONLY (AWS, Azure, GCP, Docker, Kubernetes, databases, message queues, dev tools, etc.). This catalog has NO general/nature/science/people/business icons — so for any NON-technical topic (e.g. photosynthesis, biology, history, marketing), do NOT use this tool; instead put a relevant emoji directly in the element's label (for example a sun for sunlight, a droplet for water, a leaf for a plant). It returns nothing for off-domain queries by design — never force an unrelated tech logo onto a non-tech concept. Each result has an `iconPath` (e.g. 'dev/docker.svg'). TWO ways to use it: (1) on a WHITEBOARD, drop it via addWhiteboardElements({ type:'image', iconPath:'dev/docker.svg', x, y, width:96, height:96, text:'Docker' }); (2) in a D2 systems-architecture diagram, use the iconPath as-is in D2 code (e.g. icon: dev/docker.svg).",
493
+ "description": "List and search the full Stable Baseline icon library, including 3,850 library icons. The AWS, Azure, GCP, Development, Essentials and other categories stay intact; library icons join matching categories, with specific Oracle Cloud, Kubernetes, Networking and General categories for the rest. The same logical name is shown once. iconKey is the exact icon string for a platform default diagram (type 'default'; e.g. {icon:'aws-account'}); iconKeys lists every exact key for that logical icon, and iconKeyUrl is its SVG. Results without an iconKey are not available in platform default diagrams. Use d2IconPath for compact relative D2 source (e.g. icon-library/azure-function-apps.svg); the renderer expands storage URLs. Existing iconPath values remain relative whiteboard paths; library-only icons supply iconUrl for a whiteboard imageUrl.",
493
494
  "operationId": "listArchitectureIcons",
494
495
  "tags": [
495
496
  "diagrams"
@@ -503,11 +504,11 @@
503
504
  "properties": {
504
505
  "query": {
505
506
  "type": "string",
506
- "description": "Search by name, category, vendor, or description."
507
+ "description": "Search by icon name, exact iconKey, category, vendor, description or aliases."
507
508
  },
508
509
  "category": {
509
510
  "type": "string",
510
- "description": "Filter by category (e.g. AWS, Azure, GCP, dev, essentials)."
511
+ "description": "Filter by category, e.g. AWS, Azure, GCP, Technology, Oracle Cloud, Kubernetes, Networking, General."
511
512
  },
512
513
  "limit": {
513
514
  "type": "number"
@@ -520,7 +521,7 @@
520
521
  "items": {
521
522
  "type": "string"
522
523
  },
523
- "description": "Field projection. Valid fields: id, iconPath, iconName, category, subcategory, vendor, description, searchTerms, tags, useCases, aliases, isFeatured, displayOrder."
524
+ "description": "Field projection. Valid fields: id, iconPath (existing relative paths only), iconUrl, iconName, category, categories, sources, iconKey, iconKeys, iconKeyUrl, d2IconPath, subcategory, vendor, description, searchTerms, tags, useCases, aliases, isFeatured, displayOrder."
524
525
  }
525
526
  }
526
527
  }
@@ -3319,11 +3320,11 @@
3319
3320
  },
3320
3321
  "type": {
3321
3322
  "type": "string",
3322
- "description": "Diagram type (e.g. mermaid, plantuml, bpmn, d2). Call listDiagramTypes for all types."
3323
+ "description": "Diagram type, meaning the renderer (e.g. default, mermaid, plantuml, bpmn, d2; 'default' is the platform default renderer). For a diagram family such as a BPMN process, an ERD or a flowchart, use the family's defaultRenderer from listDiagramTypes or getDiagramTypeGuide. Call listDiagramTypes for all types."
3323
3324
  },
3324
3325
  "diagramCode": {
3325
3326
  "type": "string",
3326
- "description": "Diagram DSL code. Call getDiagramTypeGuide for syntax. EXCEPTION — for type 'infographic', put a plain-English DESCRIPTION of the infographic here (NOT code); the system designs the AntV spec and renders it."
3327
+ "description": "Diagram DSL code. Call getDiagramTypeGuide for syntax. For 'default', provide MDP JSON with stable IDs and omit every entity x/y for automatic layout; fully positioned manual diagrams are also supported, and icons must be exact iconKey values from listArchitectureIcons. EXCEPTION — for type 'infographic', put a plain-English DESCRIPTION of the infographic here (NOT code); the system designs the AntV spec and renders it."
3327
3328
  },
3328
3329
  "prompt": {
3329
3330
  "type": "string",
@@ -3507,7 +3508,7 @@
3507
3508
  },
3508
3509
  "diagramCode": {
3509
3510
  "type": "string",
3510
- "description": "New diagram DSL source code. REQUIRED to change what the diagram visually renders. Call getDiagramTypeGuide for syntax. Must provide the COMPLETE updated DSL, not just the changed parts. EXCEPTION — for type 'infographic', pass either a plain-English DESCRIPTION of the new infographic (the system designs, renders, and stores the AntV spec, same as insert) or complete AntV Infographic DSL (first line `infographic <template-name>`)."
3511
+ "description": "New diagram DSL source code. REQUIRED to change what the diagram visually renders. Call getDiagramTypeGuide for syntax. Must provide the COMPLETE updated DSL, not just the changed parts. For 'default', provide complete MDP JSON and preserve stable IDs; omit entity x/y for automatic layout, or preserve all x/y in a manually positioned legacy diagram. Root layout.mode='auto' can explicitly rearrange an existing diagram. Its icons must be exact iconKey values from listArchitectureIcons. EXCEPTION — for type 'infographic', pass either a plain-English DESCRIPTION of the new infographic (the system designs, renders, and stores the AntV spec, same as insert) or complete AntV Infographic DSL (first line `infographic <template-name>`)."
3511
3512
  },
3512
3513
  "prompt": {
3513
3514
  "type": "string",
@@ -4377,7 +4378,7 @@
4377
4378
  "/tools/designDeckInWhiteboard": {
4378
4379
  "post": {
4379
4380
  "summary": "designDeckInWhiteboard",
4380
- "description": "Create or refine a slide deck INSIDE an existing whiteboard by conversing with the AI design agent. Send a brief for a NEW deck, a change to an EXISTING one, or an answer to the agent's question. The agent builds a polished, on-brand deck and places it on the board; if the brief is ambiguous it asks ONE clarifying question (answer with the same sessionId). Returns immediately; poll getDeckReplyInWhiteboard for the result. Use for building or editing slide decks / presentations. WHITEBOARD IS REQUIRED: a deck always lives inside a whiteboard, so documentId (the whiteboard's id) is required. If you do NOT already have a whiteboard id, ASK THE USER which whiteboard they want the deck designed in — do NOT create a whiteboard automatically. Only call createWhiteboard first if the user explicitly asks for a brand-new board; otherwise use the id of the whiteboard they name. FIRST vs FOLLOW-UP: the first call (from nothing) builds; a follow-up call (an answer, a change, or a new instruction) passes the sessionId (or the deckId) plus the new message. kind:'deck' (default) is the premium on-brand HTML deck; kind:'express' builds the native, deterministic branded-executive deck directly on the whiteboard (faster, lower fidelity, one-shot, not conversational). COST + APPROVAL: a build costs 50 credits and an edit 10; a clarifying question is FREE. It can also generate imagery for the deck where the design calls for it. ADVANCED DECK BUILDING (optional, OFF by default): set advancedDeckBuilding:true to build the deck over several rounds of redraft and review by a panel of design, brand, accessibility and copy reviewers instead of one composer pass. It usually raises design quality, but it is not a guarantee. It is much slower and it costs more: a standard build takes roughly 2 to 8 minutes, advanced deck building takes roughly 15 to 20 minutes, and it adds 15 credits per depth level on top of the turn fee (advancedDeckBuildingDepth is 1 to 3, default 3, so +45 credits, making a 50-credit build cost 95). Only turn it on when the user asks for the highest quality and accepts the wait and the cost. Call FIRST without confirm to get the exact cost plus the workspace balance, show it to the user, and only call again with confirm:true once they agree. The fee is auto-refunded if a turn produces no change or fails. Returns sessionId (the conversation), deckId (the deck), status, turnType, started, awaitingUser, needsConfirmation, insufficientCredits, slideCount + slideCountClamped (the target the conversation now carries, and whether it was reduced to the maximum), advancedDeckBuilding (whether advanced deck building is on for this conversation), advancedDeckBuildingStatus, and assistantMessage. Export the finished deck with exportFromWhiteboard.",
4381
+ "description": "Create or refine a slide deck INSIDE an existing whiteboard by conversing with the AI design agent. Send a brief for a NEW deck, a change to an EXISTING one, or an answer to the agent's question. The agent builds a polished, on-brand deck and places it on the board; if the brief is ambiguous it asks ONE clarifying question (answer with the same sessionId). Returns immediately; poll getDeckReplyInWhiteboard for the result. Use for building or editing slide decks / presentations. WHITEBOARD IS REQUIRED: a deck always lives inside a whiteboard, so documentId (the whiteboard's id) is required. If you do NOT already have a whiteboard id, ASK THE USER which whiteboard they want the deck designed in — do NOT create a whiteboard automatically. Only call createWhiteboard first if the user explicitly asks for a brand-new board; otherwise use the id of the whiteboard they name. FIRST vs FOLLOW-UP: the first call (from nothing) builds; a follow-up call (an answer, a change, or a new instruction) passes the sessionId (or the deckId) plus the new message. kind:'deck' (default) is the premium on-brand HTML deck; kind:'express' builds the native, deterministic branded-executive deck directly on the whiteboard (faster, lower fidelity, one-shot, not conversational). COST + APPROVAL: a build costs 50 credits per 30 slides (1 to 30 slides is 50, 31 to 60 is 100, and so on, with the second and later blocks charged once the deck is built and never charged twice for the same block), an edit costs a flat 50, and a clarifying question is FREE. It can also generate imagery for the deck where the design calls for it. ADVANCED DECK BUILDING (optional, OFF by default): set advancedDeckBuilding:true to build the deck over several rounds of redraft and review by a panel of design, brand, accessibility and copy reviewers instead of one composer pass. It usually raises design quality, but it is not a guarantee. It is much slower and it costs more: a standard build takes roughly 2 to 8 minutes, advanced deck building takes roughly 15 to 20 minutes, and it adds 15 credits per depth level on top of the turn fee (advancedDeckBuildingDepth is 1 to 3, default 3, so +45 credits, making a 50-credit build cost 95). Only turn it on when the user asks for the highest quality and accepts the wait and the cost. Call FIRST without confirm to get the exact cost plus the workspace balance, show it to the user, and only call again with confirm:true once they agree. The fee is auto-refunded if a turn produces no change or fails. Returns sessionId (the conversation), deckId (the deck), status, turnType, started, awaitingUser, needsConfirmation, insufficientCredits, slideCount (the target the conversation now carries) and slideCountClamped (always false; nothing reduces a slide count), advancedDeckBuilding (whether advanced deck building is on for this conversation), advancedDeckBuildingStatus, and assistantMessage. Export the finished deck with exportFromWhiteboard.",
4381
4382
  "operationId": "designDeckInWhiteboard",
4382
4383
  "tags": [
4383
4384
  "whiteboards"
@@ -4425,7 +4426,7 @@
4425
4426
  },
4426
4427
  "slideCount": {
4427
4428
  "type": "number",
4428
- "description": "The number of slides to build — a hard requirement: the deck is built with exactly this many slides. SET THIS whenever the user states or implies a count, EXACT OR APPROXIMATE: '12 slides' → 12, 'about 15' / '15 or so' → 15, 'no more than 10' → 10. Never expand the user's number: if they said 'about 15', pass 15 and shape the brief to fit 15 — outlining 19 sections in the message does not raise the count, it just fights this parameter. It is PERSISTED on the conversation, so send it ONCE (on the turn that states it) and every later build turn of the same conversation carries it automatically; send it again only to CHANGE the target. It is honoured on edit turns too ('cut it to 8 slides'). Anything above the 30-slide maximum is reduced to 30 and the reduction is stated back in the response. Omit ONLY when the user gave no count at all; the designer then chooses (typical 6 to 12)."
4429
+ "description": "The number of slides to build — a hard requirement: the deck is built with exactly this many slides. SET THIS whenever the user states or implies a count, EXACT OR APPROXIMATE: '12 slides' → 12, 'about 15' / '15 or so' → 15, 'no more than 10' → 10. Never expand the user's number: if they said 'about 15', pass 15 and shape the brief to fit 15 — outlining 19 sections in the message does not raise the count, it just fights this parameter. It is PERSISTED on the conversation, so send it ONCE (on the turn that states it) and every later build turn of the same conversation carries it automatically; send it again only to CHANGE the target. It is honoured on edit turns too ('cut it to 8 slides'). THERE IS NO MAXIMUM: ask for 40, 60 or 100 slides and that is what gets built. Longer decks cost proportionally more (50 credits per 30 slides) and take proportionally longer. Omit ONLY when the user gave no count at all; the designer then chooses (typical 6 to 12)."
4429
4430
  },
4430
4431
  "imageCount": {
4431
4432
  "type": "number",
@@ -4560,7 +4561,7 @@
4560
4561
  "/tools/designIllustrationInWhiteboard": {
4561
4562
  "post": {
4562
4563
  "summary": "designIllustrationInWhiteboard",
4563
- "description": "Create or refine a standalone ILLUSTRATION INSIDE an existing whiteboard by conversing with the AI design agent. This is the illustration sibling of designDeckInWhiteboard: same conversation, same follow-up flow, but it makes ONE on-brand illustration placed on the board (not a slide deck). Send a brief for a NEW illustration, a change to an existing one, or an answer to the agent's question. The agent generates the illustration, places it on the board, and if the brief is ambiguous it asks ONE clarifying question (answer with the same sessionId). Returns immediately; poll getDeckReplyInWhiteboard for the result. Use it when the user wants a picture they can talk about and refine turn by turn (e.g. 'draw a friendly robot onboarding a new team', then 'make it warmer', 'add a second robot'). For a quick one-shot illustration with no follow-up, use generateIllustrationInWhiteboard instead. WHITEBOARD IS REQUIRED: an illustration always lives inside a whiteboard, so documentId (the whiteboard's id) is required. If you do NOT already have a whiteboard id, ASK THE USER which whiteboard they want the illustration designed in — do NOT create a whiteboard automatically. Only call createWhiteboard first if the user explicitly asks for a brand-new board; otherwise use the id of the whiteboard they name. FIRST vs FOLLOW-UP: the first call (from nothing) builds; a follow-up call (an answer, a change, or a new instruction) passes the sessionId (or the deckId) plus the new message. COST + APPROVAL: a build costs 50 credits and an edit 10; a clarifying question is FREE. Call FIRST without confirm to get the exact cost plus the workspace balance, show it to the user, and only call again with confirm:true once they agree. The fee is auto-refunded if a turn produces no change or fails. Returns sessionId (the conversation), deckId (the illustration's id), status, turnType, started, awaitingUser, needsConfirmation, insufficientCredits, and assistantMessage.",
4564
+ "description": "Create or refine a standalone ILLUSTRATION INSIDE an existing whiteboard by conversing with the AI design agent. This is the illustration sibling of designDeckInWhiteboard: same conversation, same follow-up flow, but it makes ONE on-brand illustration placed on the board (not a slide deck). Send a brief for a NEW illustration, a change to an existing one, or an answer to the agent's question. The agent generates the illustration, places it on the board, and if the brief is ambiguous it asks ONE clarifying question (answer with the same sessionId). Returns immediately; poll getDeckReplyInWhiteboard for the result. Use it when the user wants a picture they can talk about and refine turn by turn (e.g. 'draw a friendly robot onboarding a new team', then 'make it warmer', 'add a second robot'). For a quick one-shot illustration with no follow-up, use generateIllustrationInWhiteboard instead. WHITEBOARD IS REQUIRED: an illustration always lives inside a whiteboard, so documentId (the whiteboard's id) is required. If you do NOT already have a whiteboard id, ASK THE USER which whiteboard they want the illustration designed in — do NOT create a whiteboard automatically. Only call createWhiteboard first if the user explicitly asks for a brand-new board; otherwise use the id of the whiteboard they name. FIRST vs FOLLOW-UP: the first call (from nothing) builds; a follow-up call (an answer, a change, or a new instruction) passes the sessionId (or the deckId) plus the new message. COST + APPROVAL: a build costs 50 credits per 30 slides (1 to 30 slides is 50, 31 to 60 is 100, and so on, with the second and later blocks charged once the deck is built and never charged twice for the same block), an edit costs a flat 50, and a clarifying question is FREE. Call FIRST without confirm to get the exact cost plus the workspace balance, show it to the user, and only call again with confirm:true once they agree. The fee is auto-refunded if a turn produces no change or fails. Returns sessionId (the conversation), deckId (the illustration's id), status, turnType, started, awaitingUser, needsConfirmation, insufficientCredits, and assistantMessage.",
4564
4565
  "operationId": "designIllustrationInWhiteboard",
4565
4566
  "tags": [
4566
4567
  "whiteboards"
@@ -6414,11 +6415,11 @@
6414
6415
  },
6415
6416
  "diagramType": {
6416
6417
  "type": "string",
6417
- "description": "Diagram language, e.g. 'bpmn', 'mermaid', 'd2', 'plantuml', 'graphviz'. See listDiagramTypes."
6418
+ "description": "Diagram language, e.g. 'default', 'bpmn', 'mermaid', 'd2', 'plantuml', 'graphviz'. For a diagram family, use its defaultRenderer from listDiagramTypes."
6418
6419
  },
6419
6420
  "source": {
6420
6421
  "type": "string",
6421
- "description": "The diagram DSL / code. For type 'infographic', provide a plain-English description instead (the system designs the AntV infographic spec)."
6422
+ "description": "The diagram DSL / code. For 'default', provide MDP JSON with stable IDs and omit entity x/y for automatic layout; fully positioned manual sources remain valid; icons must be exact iconKey values from listArchitectureIcons. For 'infographic', provide a plain-English description instead (the system designs the AntV infographic spec)."
6422
6423
  },
6423
6424
  "caption": {
6424
6425
  "type": "string",
@@ -7216,7 +7217,7 @@
7216
7217
  "/tools/renderDiagram": {
7217
7218
  "post": {
7218
7219
  "summary": "renderDiagram",
7219
- "description": "Generate a diagram from its DSL/code and get the IMAGE back — WITHOUT inserting it into any document or whiteboard. For acting as a pure diagram generator. Provide diagramType (e.g. 'mermaid', 'd2', 'plantuml', 'graphviz', 'bpmn', 'vegalite'; call listDiagramTypes for the full set) and source (the diagram code). Choose format 'png' (default), 'jpeg', or 'svg'; for raster choose scale 1/2/3 for 1x/2x/3x; optional background (png only). Returns a TEMPORARY imageUrl that stays available for 1 hour (the render is then deleted), and for png/jpeg the image inline so you can see it. The link carries no signing token, so it survives being rendered as a citation. To render a diagram that already lives in a document/whiteboard use getDiagramImage; to persist a new one use insertDiagramInDocument or insertWhiteboardDiagram.",
7220
+ "description": "Generate a diagram from its DSL/code and get the IMAGE back — WITHOUT inserting it into any document or whiteboard. For acting as a pure diagram generator. Provide diagramType (e.g. 'default', 'mermaid', 'd2', 'plantuml', 'graphviz', 'bpmn', 'vegalite'; call listDiagramTypes for the full set) and source (the diagram code). Choose format 'png' (default), 'jpeg', or 'svg'; for raster choose scale 1/2/3 for 1x/2x/3x; optional background (png only). Returns a TEMPORARY imageUrl that stays available for 1 hour (the render is then deleted), and for png/jpeg the image inline so you can see it. The link carries no signing token, so it survives being rendered as a citation. To render a diagram that already lives in a document/whiteboard use getDiagramImage; to persist a new one use insertDiagramInDocument or insertWhiteboardDiagram.",
7220
7221
  "operationId": "renderDiagram",
7221
7222
  "tags": [
7222
7223
  "diagrams"
@@ -7230,11 +7231,11 @@
7230
7231
  "properties": {
7231
7232
  "diagramType": {
7232
7233
  "type": "string",
7233
- "description": "Diagram language, e.g. 'mermaid', 'd2', 'plantuml', 'graphviz', 'bpmn', 'vegalite'. See listDiagramTypes."
7234
+ "description": "Diagram language, e.g. 'default', 'mermaid', 'd2', 'plantuml', 'graphviz', 'bpmn', 'vegalite'. For a diagram family, use its defaultRenderer from listDiagramTypes."
7234
7235
  },
7235
7236
  "source": {
7236
7237
  "type": "string",
7237
- "description": "The diagram DSL / code to render. For type 'infographic', provide a plain-English description instead (the system designs the AntV infographic spec)."
7238
+ "description": "The diagram DSL / code to render. For 'default', provide MDP JSON with stable IDs and omit entity x/y for automatic layout; fully positioned manual sources remain valid; icons must be exact iconKey values from listArchitectureIcons. For 'infographic', provide a plain-English description instead (the system designs the AntV infographic spec)."
7238
7239
  },
7239
7240
  "format": {
7240
7241
  "type": "string",
@@ -7243,7 +7244,7 @@
7243
7244
  "jpeg",
7244
7245
  "svg"
7245
7246
  ],
7246
- "description": "png (default) or jpeg = raster; svg = vector."
7247
+ "description": "png (default) or jpeg = raster; svg is scalable. A platform default diagram's SVG contains a browser foreignObject scene, so use PNG/JPEG where foreignObject SVG is unsupported."
7247
7248
  },
7248
7249
  "scale": {
7249
7250
  "type": "number",
@@ -7380,7 +7381,7 @@
7380
7381
  "jpeg",
7381
7382
  "svg"
7382
7383
  ],
7383
- "description": "png (default) or jpeg = raster; svg = vector."
7384
+ "description": "png (default) or jpeg = raster; svg is scalable. A platform default diagram's SVG contains a browser foreignObject scene, so use PNG/JPEG where foreignObject SVG is unsupported."
7384
7385
  },
7385
7386
  "scale": {
7386
7387
  "type": "number",
@@ -15141,7 +15142,7 @@
15141
15142
  "/tools/kg_search": {
15142
15143
  "post": {
15143
15144
  "summary": "kg_search",
15144
- "description": "Unified Knowledge Graph KNOWLEDGE retrieval — facts, themes and relationships from INSIDE document CONTENT. To LOCATE AN ARTEFACT BY NAME OR ID rather than answer a question, pass artefactMetadataOnly:true — see below. Without that flag this tool retrieves knowledge from inside content and will not reliably find a thing by its title.\n\nPICK THE MODE THAT FITS THE QUERY:\n\n• mode='local' (default) — for SPECIFIC factual questions (\"what does section 15 say about deposits?\", \"who is the Chief Counsel?\"). FTS+vector RRF over individual document chunks. Returns precise excerpts with citations.\n\n• mode='global' — for THEMATIC / OVERVIEW / SUMMARY questions (\"what are the main themes\", \"give me an overview of the project\", \"what topics does this cover\"). Returns Louvain community summaries + curated wiki pages — far better than 'local' for big-picture queries because community summaries already aggregate across many chunks. ALWAYS PREFER over 'local' when the user asks for themes / summary / overview / topic landscape.\n\n• mode='graph' — for RELATIONSHIP questions (\"what's connected to entity X?\", \"who cites Section 5?\"). 1-hop entity-neighbourhood walk. Pass query OR srcEntityId.\n\n• mode='path' — for CONNECTION questions (\"how does X relate to Y?\"). Shortest path between two entities. Pass srcEntityId AND dstEntityId.\n\n• mode='ppr' — for MULTI-HOP discovery (\"what's relevant to X, even indirectly?\"). Personalised PageRank over AUTHORED-vs-EXTRACTED weighted edges, seeded by query-similar entities. Best when 'local' returns too few results and the answer requires walking through several entity hops.\n\nQuick decision tree:\n- User asks for an overview/summary/themes → 'global'\n- User asks a specific question with a clear answer → 'local'\n- User asks 'how is X connected to Y' → 'path' (with both entity IDs)\n- User asks 'what's near entity X' → 'graph' (with srcEntityId)\n- 'local' returned nothing useful and the question is broad → retry with 'ppr'\n- User wants to FIND a named artefact (\"the GTM plan\", \"DOC-123\", a uuid) → artefactMetadataOnly:true\n\nARTEFACT-METADATA MODE (artefactMetadataOnly:true): ignores `mode` entirely and matches title + friendly id + uuid across EVERY artefact type — documents, whiteboards, plans, tasks, improvements, compliance frameworks. Returns a typed navigable list ({ artefacts: [{ result_type, id, friendly_id, title, snippet, document_id, project_id, href }] }). It reads no document content and needs no knowledge graph: unlike every other mode it is NOT limited to what has been ingested, so it still finds artefacts in projects where the KG is switched off. Narrow it with artefactTypes. To search inside document BODIES use listDocuments (full-content grep).",
15145
+ "description": "Unified Knowledge Graph KNOWLEDGE retrieval — facts, themes and relationships from INSIDE document CONTENT. To LOCATE AN ARTEFACT BY NAME OR ID rather than answer a question, pass artefactMetadataOnly:true — see below. Without that flag this tool retrieves knowledge from inside content and will not reliably find a thing by its title.\n\nDATED FACTS: the response also carries `datedFacts` for the entities the query names: what holds now by default, what held on a day with asOf, or the whole history with history:true, each fact with its dates, how it ended if it has, and its sources. Prefer them for \"who owns X now\", \"what was X in March\", \"when did X change\".\n\nPICK THE MODE THAT FITS THE QUERY:\n\n• mode='local' (default) — for SPECIFIC factual questions (\"what does section 15 say about deposits?\", \"who is the Chief Counsel?\"). FTS+vector RRF over individual document chunks. Returns precise excerpts with citations.\n\n• mode='global' — for THEMATIC / OVERVIEW / SUMMARY questions (\"what are the main themes\", \"give me an overview of the project\", \"what topics does this cover\"). Returns Louvain community summaries + curated wiki pages — far better than 'local' for big-picture queries because community summaries already aggregate across many chunks. ALWAYS PREFER over 'local' when the user asks for themes / summary / overview / topic landscape.\n\n• mode='graph' — for RELATIONSHIP questions (\"what's connected to entity X?\", \"who cites Section 5?\"). 1-hop entity-neighbourhood walk. Pass query OR srcEntityId.\n\n• mode='path' — for CONNECTION questions (\"how does X relate to Y?\"). Shortest path between two entities. Pass srcEntityId AND dstEntityId.\n\n• mode='ppr' — for MULTI-HOP discovery (\"what's relevant to X, even indirectly?\"). Personalised PageRank over AUTHORED-vs-EXTRACTED weighted edges, seeded by query-similar entities. Best when 'local' returns too few results and the answer requires walking through several entity hops.\n\nQuick decision tree:\n- User asks for an overview/summary/themes → 'global'\n- User asks a specific question with a clear answer → 'local'\n- User asks 'how is X connected to Y' → 'path' (with both entity IDs)\n- User asks 'what's near entity X' → 'graph' (with srcEntityId)\n- 'local' returned nothing useful and the question is broad → retry with 'ppr'\n- User wants to FIND a named artefact (\"the GTM plan\", \"DOC-123\", a uuid) → artefactMetadataOnly:true\n\nARTEFACT-METADATA MODE (artefactMetadataOnly:true): ignores `mode` entirely and matches title + friendly id + uuid across EVERY artefact type — documents, whiteboards, plans, tasks, improvements, compliance frameworks. Returns a typed navigable list ({ artefacts: [{ result_type, id, friendly_id, title, snippet, document_id, project_id, href }] }). It reads no document content and needs no knowledge graph: unlike every other mode it is NOT limited to what has been ingested, so it still finds artefacts in projects where the KG is switched off. Narrow it with artefactTypes. To search inside document BODIES use listDocuments (full-content grep).",
15145
15146
  "operationId": "kg_search",
15146
15147
  "tags": [
15147
15148
  "knowledge_graph"
@@ -15217,6 +15218,18 @@
15217
15218
  "limit": {
15218
15219
  "type": "number",
15219
15220
  "default": 20
15221
+ },
15222
+ "asOf": {
15223
+ "type": "string",
15224
+ "description": "Dated facts: return what held on this day (YYYY-MM-DD) instead of what holds now. For example the owner, status or supplier as it was on a past date."
15225
+ },
15226
+ "history": {
15227
+ "type": "boolean",
15228
+ "description": "Dated facts: return every fact with its dates, including facts that have ended (and how they ended) and planned ones, oldest first. Use for \"how did X change\" or \"what was X before\"."
15229
+ },
15230
+ "timeZone": {
15231
+ "type": "string",
15232
+ "description": "Dated facts: the IANA time zone to give days in (for example Australia/Sydney, Asia/Kolkata, America/New_York). Defaults to the user's saved time zone, else UTC. Pass the user's zone when you know it, so \"today\" and dates match their calendar."
15220
15233
  }
15221
15234
  }
15222
15235
  }
@@ -15406,7 +15419,7 @@
15406
15419
  "/tools/kg_get_entity": {
15407
15420
  "post": {
15408
15421
  "summary": "kg_get_entity",
15409
- "description": "Fetch a KG entity by id or name, with 1-hop neighbours.",
15422
+ "description": "Fetch a KG entity by id or name, with 1-hop neighbours. The response also carries `datedFacts`: what holds now about the entity by default, what held on a day with asOf, or the whole history with history:true, each fact with its dates, how it ended if it has, and the sources that state it.",
15410
15423
  "operationId": "kg_get_entity",
15411
15424
  "tags": [
15412
15425
  "knowledge_graph"
@@ -15427,6 +15440,18 @@
15427
15440
  "projectId": {
15428
15441
  "type": "string",
15429
15442
  "description": "Scope the lookup to one project. Recommended when resolving by `name`, since the same entity name can exist in several projects."
15443
+ },
15444
+ "asOf": {
15445
+ "type": "string",
15446
+ "description": "Dated facts: return what held on this day (YYYY-MM-DD) instead of what holds now. For example the owner, status or supplier as it was on a past date."
15447
+ },
15448
+ "history": {
15449
+ "type": "boolean",
15450
+ "description": "Dated facts: return every fact with its dates, including facts that have ended (and how they ended) and planned ones, oldest first. Use for \"how did X change\" or \"what was X before\"."
15451
+ },
15452
+ "timeZone": {
15453
+ "type": "string",
15454
+ "description": "Dated facts: the IANA time zone to give days in (for example Australia/Sydney, Asia/Kolkata, America/New_York). Defaults to the user's saved time zone, else UTC."
15430
15455
  }
15431
15456
  }
15432
15457
  }
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@stablebaseline/sdk",
3
- "version": "0.6.2",
3
+ "version": "0.6.3",
4
4
  "description": "TypeScript SDK for the Stable Baseline REST API. End-to-end agent-managed company brain — docs, diagrams, plans, and a self-learning Knowledge Graph. 196 tools across 18 categories.",
5
5
  "homepage": "https://stablebaseline.io",
6
6
  "repository": {
@@ -35,7 +35,7 @@ export interface paths {
35
35
  put?: never;
36
36
  /**
37
37
  * listDiagramTypes
38
- * @description List supported diagram types. Pass `query` to search by name OR intent (keyword + semantic): e.g. 'circuit diagram', 'wiring harness', 'timing waveform', 'network topology', 'database schema'. Use the returned `type` field with getDiagramTypeGuide (DSL instructions + example) and insertDiagramInDocument / renderDiagram.
38
+ * @description List supported diagram types (renderers such as default, mermaid, plantuml, bpmn and d2; 'default' is the platform default renderer). Pass `query` to search by name OR intent (keyword + semantic): e.g. 'circuit diagram', 'wiring harness', 'timing waveform', 'network topology', 'database schema', 'BPMN process'. Each type lists supportedDiagrams: the diagram families it draws (BPMN process, ERD, flowchart, C4, system architecture and more), each with its defaultRenderer. A query that names a family also returns matchedDiagramFamilies. Use a family's defaultRenderer as the type unless you need another renderer's own format (for example BPMN 2.0 XML). Use the returned `type` field with getDiagramTypeGuide (DSL instructions + example) and insertDiagramInDocument / renderDiagram.
39
39
  */
40
40
  post: operations["listDiagramTypes"];
41
41
  delete?: never;
@@ -55,7 +55,7 @@ export interface paths {
55
55
  put?: never;
56
56
  /**
57
57
  * getDiagramTypeGuide
58
- * @description Get DSL writing instructions for a diagram type. Call before writing diagramCode.
58
+ * @description Get DSL writing instructions and an example for a diagram type (a renderer such as 'default', 'mermaid' or 'bpmn'). Also accepts a diagram family slug or name from supportedDiagrams (e.g. 'bpmn-process'), which resolves to that family's default renderer (see resolvedFrom). supportedDiagrams lists the families the type draws, each with its defaultRenderer. Call before writing diagramCode.
59
59
  */
60
60
  post: operations["getDiagramTypeGuide"];
61
61
  delete?: never;
@@ -75,7 +75,7 @@ export interface paths {
75
75
  put?: never;
76
76
  /**
77
77
  * listArchitectureIcons
78
- * @description SOFTWARE & CLOUD architecture icons ONLY (AWS, Azure, GCP, Docker, Kubernetes, databases, message queues, dev tools, etc.). This catalog has NO general/nature/science/people/business icons — so for any NON-technical topic (e.g. photosynthesis, biology, history, marketing), do NOT use this tool; instead put a relevant emoji directly in the element's label (for example a sun for sunlight, a droplet for water, a leaf for a plant). It returns nothing for off-domain queries by design — never force an unrelated tech logo onto a non-tech concept. Each result has an `iconPath` (e.g. 'dev/docker.svg'). TWO ways to use it: (1) on a WHITEBOARD, drop it via addWhiteboardElements({ type:'image', iconPath:'dev/docker.svg', x, y, width:96, height:96, text:'Docker' }); (2) in a D2 systems-architecture diagram, use the iconPath as-is in D2 code (e.g. icon: dev/docker.svg).
78
+ * @description List and search the full Stable Baseline icon library, including 3,850 library icons. The AWS, Azure, GCP, Development, Essentials and other categories stay intact; library icons join matching categories, with specific Oracle Cloud, Kubernetes, Networking and General categories for the rest. The same logical name is shown once. iconKey is the exact icon string for a platform default diagram (type 'default'; e.g. {icon:'aws-account'}); iconKeys lists every exact key for that logical icon, and iconKeyUrl is its SVG. Results without an iconKey are not available in platform default diagrams. Use d2IconPath for compact relative D2 source (e.g. icon-library/azure-function-apps.svg); the renderer expands storage URLs. Existing iconPath values remain relative whiteboard paths; library-only icons supply iconUrl for a whiteboard imageUrl.
79
79
  */
80
80
  post: operations["listArchitectureIcons"];
81
81
  delete?: never;
@@ -695,7 +695,7 @@ export interface paths {
695
695
  put?: never;
696
696
  /**
697
697
  * designDeckInWhiteboard
698
- * @description Create or refine a slide deck INSIDE an existing whiteboard by conversing with the AI design agent. Send a brief for a NEW deck, a change to an EXISTING one, or an answer to the agent's question. The agent builds a polished, on-brand deck and places it on the board; if the brief is ambiguous it asks ONE clarifying question (answer with the same sessionId). Returns immediately; poll getDeckReplyInWhiteboard for the result. Use for building or editing slide decks / presentations. WHITEBOARD IS REQUIRED: a deck always lives inside a whiteboard, so documentId (the whiteboard's id) is required. If you do NOT already have a whiteboard id, ASK THE USER which whiteboard they want the deck designed in — do NOT create a whiteboard automatically. Only call createWhiteboard first if the user explicitly asks for a brand-new board; otherwise use the id of the whiteboard they name. FIRST vs FOLLOW-UP: the first call (from nothing) builds; a follow-up call (an answer, a change, or a new instruction) passes the sessionId (or the deckId) plus the new message. kind:'deck' (default) is the premium on-brand HTML deck; kind:'express' builds the native, deterministic branded-executive deck directly on the whiteboard (faster, lower fidelity, one-shot, not conversational). COST + APPROVAL: a build costs 50 credits and an edit 10; a clarifying question is FREE. It can also generate imagery for the deck where the design calls for it. ADVANCED DECK BUILDING (optional, OFF by default): set advancedDeckBuilding:true to build the deck over several rounds of redraft and review by a panel of design, brand, accessibility and copy reviewers instead of one composer pass. It usually raises design quality, but it is not a guarantee. It is much slower and it costs more: a standard build takes roughly 2 to 8 minutes, advanced deck building takes roughly 15 to 20 minutes, and it adds 15 credits per depth level on top of the turn fee (advancedDeckBuildingDepth is 1 to 3, default 3, so +45 credits, making a 50-credit build cost 95). Only turn it on when the user asks for the highest quality and accepts the wait and the cost. Call FIRST without confirm to get the exact cost plus the workspace balance, show it to the user, and only call again with confirm:true once they agree. The fee is auto-refunded if a turn produces no change or fails. Returns sessionId (the conversation), deckId (the deck), status, turnType, started, awaitingUser, needsConfirmation, insufficientCredits, slideCount + slideCountClamped (the target the conversation now carries, and whether it was reduced to the maximum), advancedDeckBuilding (whether advanced deck building is on for this conversation), advancedDeckBuildingStatus, and assistantMessage. Export the finished deck with exportFromWhiteboard.
698
+ * @description Create or refine a slide deck INSIDE an existing whiteboard by conversing with the AI design agent. Send a brief for a NEW deck, a change to an EXISTING one, or an answer to the agent's question. The agent builds a polished, on-brand deck and places it on the board; if the brief is ambiguous it asks ONE clarifying question (answer with the same sessionId). Returns immediately; poll getDeckReplyInWhiteboard for the result. Use for building or editing slide decks / presentations. WHITEBOARD IS REQUIRED: a deck always lives inside a whiteboard, so documentId (the whiteboard's id) is required. If you do NOT already have a whiteboard id, ASK THE USER which whiteboard they want the deck designed in — do NOT create a whiteboard automatically. Only call createWhiteboard first if the user explicitly asks for a brand-new board; otherwise use the id of the whiteboard they name. FIRST vs FOLLOW-UP: the first call (from nothing) builds; a follow-up call (an answer, a change, or a new instruction) passes the sessionId (or the deckId) plus the new message. kind:'deck' (default) is the premium on-brand HTML deck; kind:'express' builds the native, deterministic branded-executive deck directly on the whiteboard (faster, lower fidelity, one-shot, not conversational). COST + APPROVAL: a build costs 50 credits per 30 slides (1 to 30 slides is 50, 31 to 60 is 100, and so on, with the second and later blocks charged once the deck is built and never charged twice for the same block), an edit costs a flat 50, and a clarifying question is FREE. It can also generate imagery for the deck where the design calls for it. ADVANCED DECK BUILDING (optional, OFF by default): set advancedDeckBuilding:true to build the deck over several rounds of redraft and review by a panel of design, brand, accessibility and copy reviewers instead of one composer pass. It usually raises design quality, but it is not a guarantee. It is much slower and it costs more: a standard build takes roughly 2 to 8 minutes, advanced deck building takes roughly 15 to 20 minutes, and it adds 15 credits per depth level on top of the turn fee (advancedDeckBuildingDepth is 1 to 3, default 3, so +45 credits, making a 50-credit build cost 95). Only turn it on when the user asks for the highest quality and accepts the wait and the cost. Call FIRST without confirm to get the exact cost plus the workspace balance, show it to the user, and only call again with confirm:true once they agree. The fee is auto-refunded if a turn produces no change or fails. Returns sessionId (the conversation), deckId (the deck), status, turnType, started, awaitingUser, needsConfirmation, insufficientCredits, slideCount (the target the conversation now carries) and slideCountClamped (always false; nothing reduces a slide count), advancedDeckBuilding (whether advanced deck building is on for this conversation), advancedDeckBuildingStatus, and assistantMessage. Export the finished deck with exportFromWhiteboard.
699
699
  */
700
700
  post: operations["designDeckInWhiteboard"];
701
701
  delete?: never;
@@ -715,7 +715,7 @@ export interface paths {
715
715
  put?: never;
716
716
  /**
717
717
  * designIllustrationInWhiteboard
718
- * @description Create or refine a standalone ILLUSTRATION INSIDE an existing whiteboard by conversing with the AI design agent. This is the illustration sibling of designDeckInWhiteboard: same conversation, same follow-up flow, but it makes ONE on-brand illustration placed on the board (not a slide deck). Send a brief for a NEW illustration, a change to an existing one, or an answer to the agent's question. The agent generates the illustration, places it on the board, and if the brief is ambiguous it asks ONE clarifying question (answer with the same sessionId). Returns immediately; poll getDeckReplyInWhiteboard for the result. Use it when the user wants a picture they can talk about and refine turn by turn (e.g. 'draw a friendly robot onboarding a new team', then 'make it warmer', 'add a second robot'). For a quick one-shot illustration with no follow-up, use generateIllustrationInWhiteboard instead. WHITEBOARD IS REQUIRED: an illustration always lives inside a whiteboard, so documentId (the whiteboard's id) is required. If you do NOT already have a whiteboard id, ASK THE USER which whiteboard they want the illustration designed in — do NOT create a whiteboard automatically. Only call createWhiteboard first if the user explicitly asks for a brand-new board; otherwise use the id of the whiteboard they name. FIRST vs FOLLOW-UP: the first call (from nothing) builds; a follow-up call (an answer, a change, or a new instruction) passes the sessionId (or the deckId) plus the new message. COST + APPROVAL: a build costs 50 credits and an edit 10; a clarifying question is FREE. Call FIRST without confirm to get the exact cost plus the workspace balance, show it to the user, and only call again with confirm:true once they agree. The fee is auto-refunded if a turn produces no change or fails. Returns sessionId (the conversation), deckId (the illustration's id), status, turnType, started, awaitingUser, needsConfirmation, insufficientCredits, and assistantMessage.
718
+ * @description Create or refine a standalone ILLUSTRATION INSIDE an existing whiteboard by conversing with the AI design agent. This is the illustration sibling of designDeckInWhiteboard: same conversation, same follow-up flow, but it makes ONE on-brand illustration placed on the board (not a slide deck). Send a brief for a NEW illustration, a change to an existing one, or an answer to the agent's question. The agent generates the illustration, places it on the board, and if the brief is ambiguous it asks ONE clarifying question (answer with the same sessionId). Returns immediately; poll getDeckReplyInWhiteboard for the result. Use it when the user wants a picture they can talk about and refine turn by turn (e.g. 'draw a friendly robot onboarding a new team', then 'make it warmer', 'add a second robot'). For a quick one-shot illustration with no follow-up, use generateIllustrationInWhiteboard instead. WHITEBOARD IS REQUIRED: an illustration always lives inside a whiteboard, so documentId (the whiteboard's id) is required. If you do NOT already have a whiteboard id, ASK THE USER which whiteboard they want the illustration designed in — do NOT create a whiteboard automatically. Only call createWhiteboard first if the user explicitly asks for a brand-new board; otherwise use the id of the whiteboard they name. FIRST vs FOLLOW-UP: the first call (from nothing) builds; a follow-up call (an answer, a change, or a new instruction) passes the sessionId (or the deckId) plus the new message. COST + APPROVAL: a build costs 50 credits per 30 slides (1 to 30 slides is 50, 31 to 60 is 100, and so on, with the second and later blocks charged once the deck is built and never charged twice for the same block), an edit costs a flat 50, and a clarifying question is FREE. Call FIRST without confirm to get the exact cost plus the workspace balance, show it to the user, and only call again with confirm:true once they agree. The fee is auto-refunded if a turn produces no change or fails. Returns sessionId (the conversation), deckId (the illustration's id), status, turnType, started, awaitingUser, needsConfirmation, insufficientCredits, and assistantMessage.
719
719
  */
720
720
  post: operations["designIllustrationInWhiteboard"];
721
721
  delete?: never;
@@ -1095,7 +1095,7 @@ export interface paths {
1095
1095
  put?: never;
1096
1096
  /**
1097
1097
  * renderDiagram
1098
- * @description Generate a diagram from its DSL/code and get the IMAGE back — WITHOUT inserting it into any document or whiteboard. For acting as a pure diagram generator. Provide diagramType (e.g. 'mermaid', 'd2', 'plantuml', 'graphviz', 'bpmn', 'vegalite'; call listDiagramTypes for the full set) and source (the diagram code). Choose format 'png' (default), 'jpeg', or 'svg'; for raster choose scale 1/2/3 for 1x/2x/3x; optional background (png only). Returns a TEMPORARY imageUrl that stays available for 1 hour (the render is then deleted), and for png/jpeg the image inline so you can see it. The link carries no signing token, so it survives being rendered as a citation. To render a diagram that already lives in a document/whiteboard use getDiagramImage; to persist a new one use insertDiagramInDocument or insertWhiteboardDiagram.
1098
+ * @description Generate a diagram from its DSL/code and get the IMAGE back — WITHOUT inserting it into any document or whiteboard. For acting as a pure diagram generator. Provide diagramType (e.g. 'default', 'mermaid', 'd2', 'plantuml', 'graphviz', 'bpmn', 'vegalite'; call listDiagramTypes for the full set) and source (the diagram code). Choose format 'png' (default), 'jpeg', or 'svg'; for raster choose scale 1/2/3 for 1x/2x/3x; optional background (png only). Returns a TEMPORARY imageUrl that stays available for 1 hour (the render is then deleted), and for png/jpeg the image inline so you can see it. The link carries no signing token, so it survives being rendered as a citation. To render a diagram that already lives in a document/whiteboard use getDiagramImage; to persist a new one use insertDiagramInDocument or insertWhiteboardDiagram.
1099
1099
  */
1100
1100
  post: operations["renderDiagram"];
1101
1101
  delete?: never;
@@ -2261,6 +2261,8 @@ export interface paths {
2261
2261
  * kg_search
2262
2262
  * @description Unified Knowledge Graph KNOWLEDGE retrieval — facts, themes and relationships from INSIDE document CONTENT. To LOCATE AN ARTEFACT BY NAME OR ID rather than answer a question, pass artefactMetadataOnly:true — see below. Without that flag this tool retrieves knowledge from inside content and will not reliably find a thing by its title.
2263
2263
  *
2264
+ * DATED FACTS: the response also carries `datedFacts` for the entities the query names: what holds now by default, what held on a day with asOf, or the whole history with history:true, each fact with its dates, how it ended if it has, and its sources. Prefer them for "who owns X now", "what was X in March", "when did X change".
2265
+ *
2264
2266
  * PICK THE MODE THAT FITS THE QUERY:
2265
2267
  *
2266
2268
  * • mode='local' (default) — for SPECIFIC factual questions ("what does section 15 say about deposits?", "who is the Chief Counsel?"). FTS+vector RRF over individual document chunks. Returns precise excerpts with citations.
@@ -2321,7 +2323,7 @@ export interface paths {
2321
2323
  put?: never;
2322
2324
  /**
2323
2325
  * kg_get_entity
2324
- * @description Fetch a KG entity by id or name, with 1-hop neighbours.
2326
+ * @description Fetch a KG entity by id or name, with 1-hop neighbours. The response also carries `datedFacts`: what holds now about the entity by default, what held on a day with asOf, or the whole history with history:true, each fact with its dates, how it ended if it has, and the sources that state it.
2325
2327
  */
2326
2328
  post: operations["kg_get_entity"];
2327
2329
  delete?: never;
@@ -4073,12 +4075,12 @@ export interface operations {
4073
4075
  requestBody?: {
4074
4076
  content: {
4075
4077
  "application/json": {
4076
- /** @description Keyword or intent, e.g. 'circuit', 'wiring harness', 'timing'. Semantic-backed: matches descriptions, not just names. */
4078
+ /** @description Keyword or intent, e.g. 'circuit', 'wiring harness', 'timing', 'BPMN process'. Semantic-backed: matches descriptions and diagram family names, not just type names. */
4077
4079
  query?: string;
4078
4080
  enabledOnly?: boolean;
4079
4081
  limit?: number;
4080
4082
  offset?: number;
4081
- /** @description Field projection. Valid fields: type, label, description, whenToUse, dslLanguage, dslInstructions, exampleDsl, enabled, availableOnFree, sortOrder, updatedAt. */
4083
+ /** @description Field projection. Valid fields: type, label, description, whenToUse, dslLanguage, dslInstructions, exampleDsl, enabled, availableOnFree, sortOrder, updatedAt, supportedDiagrams. */
4082
4084
  fields?: string[];
4083
4085
  };
4084
4086
  };
@@ -4161,6 +4163,7 @@ export interface operations {
4161
4163
  requestBody?: {
4162
4164
  content: {
4163
4165
  "application/json": {
4166
+ /** @description A diagram type from listDiagramTypes (e.g. 'default', 'mermaid', 'bpmn'), or a diagram family slug or name (e.g. 'bpmn-process'), which resolves to the family's default renderer. */
4164
4167
  type: string;
4165
4168
  /** @description Field projection. Valid fields: type, label, description, whenToUse, dslLanguage, dslInstructions, exampleDsl, enabled, sortOrder, updatedAt. */
4166
4169
  fields?: string[];
@@ -4245,13 +4248,13 @@ export interface operations {
4245
4248
  requestBody?: {
4246
4249
  content: {
4247
4250
  "application/json": {
4248
- /** @description Search by name, category, vendor, or description. */
4251
+ /** @description Search by icon name, exact iconKey, category, vendor, description or aliases. */
4249
4252
  query?: string;
4250
- /** @description Filter by category (e.g. AWS, Azure, GCP, dev, essentials). */
4253
+ /** @description Filter by category, e.g. AWS, Azure, GCP, Technology, Oracle Cloud, Kubernetes, Networking, General. */
4251
4254
  category?: string;
4252
4255
  limit?: number;
4253
4256
  offset?: number;
4254
- /** @description Field projection. Valid fields: id, iconPath, iconName, category, subcategory, vendor, description, searchTerms, tags, useCases, aliases, isFeatured, displayOrder. */
4257
+ /** @description Field projection. Valid fields: id, iconPath (existing relative paths only), iconUrl, iconName, category, categories, sources, iconKey, iconKeys, iconKeyUrl, d2IconPath, subcategory, vendor, description, searchTerms, tags, useCases, aliases, isFeatured, displayOrder. */
4255
4258
  fields?: string[];
4256
4259
  };
4257
4260
  };
@@ -6352,9 +6355,9 @@ export interface operations {
6352
6355
  documentId: string;
6353
6356
  /** @description Optimistic-lock token: the document's versionTimestamp from getDocument() or any mutating tool's response. (Alias accepted: versionTimestamp.) */
6354
6357
  documentVersionTimestamp?: number;
6355
- /** @description Diagram type (e.g. mermaid, plantuml, bpmn, d2). Call listDiagramTypes for all types. */
6358
+ /** @description Diagram type, meaning the renderer (e.g. default, mermaid, plantuml, bpmn, d2; 'default' is the platform default renderer). For a diagram family such as a BPMN process, an ERD or a flowchart, use the family's defaultRenderer from listDiagramTypes or getDiagramTypeGuide. Call listDiagramTypes for all types. */
6356
6359
  type: string;
6357
- /** @description Diagram DSL code. Call getDiagramTypeGuide for syntax. EXCEPTION — for type 'infographic', put a plain-English DESCRIPTION of the infographic here (NOT code); the system designs the AntV spec and renders it. */
6360
+ /** @description Diagram DSL code. Call getDiagramTypeGuide for syntax. For 'default', provide MDP JSON with stable IDs and omit every entity x/y for automatic layout; fully positioned manual diagrams are also supported, and icons must be exact iconKey values from listArchitectureIcons. EXCEPTION — for type 'infographic', put a plain-English DESCRIPTION of the infographic here (NOT code); the system designs the AntV spec and renders it. */
6358
6361
  diagramCode: string;
6359
6362
  /** @description Short description of what the diagram shows (1-2 sentences). */
6360
6363
  prompt: string;
@@ -6477,7 +6480,7 @@ export interface operations {
6477
6480
  "application/json": {
6478
6481
  /** @description Diagram ID from DIAGRAM_OMITTED markers. */
6479
6482
  diagramId: string;
6480
- /** @description New diagram DSL source code. REQUIRED to change what the diagram visually renders. Call getDiagramTypeGuide for syntax. Must provide the COMPLETE updated DSL, not just the changed parts. EXCEPTION — for type 'infographic', pass either a plain-English DESCRIPTION of the new infographic (the system designs, renders, and stores the AntV spec, same as insert) or complete AntV Infographic DSL (first line `infographic <template-name>`). */
6483
+ /** @description New diagram DSL source code. REQUIRED to change what the diagram visually renders. Call getDiagramTypeGuide for syntax. Must provide the COMPLETE updated DSL, not just the changed parts. For 'default', provide complete MDP JSON and preserve stable IDs; omit entity x/y for automatic layout, or preserve all x/y in a manually positioned legacy diagram. Root layout.mode='auto' can explicitly rearrange an existing diagram. Its icons must be exact iconKey values from listArchitectureIcons. EXCEPTION — for type 'infographic', pass either a plain-English DESCRIPTION of the new infographic (the system designs, renders, and stores the AntV spec, same as insert) or complete AntV Infographic DSL (first line `infographic <template-name>`). */
6481
6484
  diagramCode?: string;
6482
6485
  /** @description New short description (metadata only — does NOT change the rendered diagram). */
6483
6486
  prompt?: string;
@@ -7155,7 +7158,7 @@ export interface operations {
7155
7158
  title?: string;
7156
7159
  /** @description Optional brand kit id (from listBrandKits) to theme the deck. If omitted, the organisation's effective brand is used. */
7157
7160
  brandKitId?: string;
7158
- /** @description The number of slides to build — a hard requirement: the deck is built with exactly this many slides. SET THIS whenever the user states or implies a count, EXACT OR APPROXIMATE: '12 slides' → 12, 'about 15' / '15 or so' → 15, 'no more than 10' → 10. Never expand the user's number: if they said 'about 15', pass 15 and shape the brief to fit 15 — outlining 19 sections in the message does not raise the count, it just fights this parameter. It is PERSISTED on the conversation, so send it ONCE (on the turn that states it) and every later build turn of the same conversation carries it automatically; send it again only to CHANGE the target. It is honoured on edit turns too ('cut it to 8 slides'). Anything above the 30-slide maximum is reduced to 30 and the reduction is stated back in the response. Omit ONLY when the user gave no count at all; the designer then chooses (typical 6 to 12). */
7161
+ /** @description The number of slides to build — a hard requirement: the deck is built with exactly this many slides. SET THIS whenever the user states or implies a count, EXACT OR APPROXIMATE: '12 slides' → 12, 'about 15' / '15 or so' → 15, 'no more than 10' → 10. Never expand the user's number: if they said 'about 15', pass 15 and shape the brief to fit 15 — outlining 19 sections in the message does not raise the count, it just fights this parameter. It is PERSISTED on the conversation, so send it ONCE (on the turn that states it) and every later build turn of the same conversation carries it automatically; send it again only to CHANGE the target. It is honoured on edit turns too ('cut it to 8 slides'). THERE IS NO MAXIMUM: ask for 40, 60 or 100 slides and that is what gets built. Longer decks cost proportionally more (50 credits per 30 slides) and take proportionally longer. Omit ONLY when the user gave no count at all; the designer then chooses (typical 6 to 12). */
7159
7162
  slideCount?: number;
7160
7163
  /** @description Deprecated and ignored. Still accepted so existing callers do not break; passing it changes nothing. */
7161
7164
  imageCount?: number;
@@ -8564,9 +8567,9 @@ export interface operations {
8564
8567
  "application/json": {
8565
8568
  /** @description The whiteboard's documentId. */
8566
8569
  documentId: string;
8567
- /** @description Diagram language, e.g. 'bpmn', 'mermaid', 'd2', 'plantuml', 'graphviz'. See listDiagramTypes. */
8570
+ /** @description Diagram language, e.g. 'default', 'bpmn', 'mermaid', 'd2', 'plantuml', 'graphviz'. For a diagram family, use its defaultRenderer from listDiagramTypes. */
8568
8571
  diagramType: string;
8569
- /** @description The diagram DSL / code. For type 'infographic', provide a plain-English description instead (the system designs the AntV infographic spec). */
8572
+ /** @description The diagram DSL / code. For 'default', provide MDP JSON with stable IDs and omit entity x/y for automatic layout; fully positioned manual sources remain valid; icons must be exact iconKey values from listArchitectureIcons. For 'infographic', provide a plain-English description instead (the system designs the AntV infographic spec). */
8570
8573
  source: string;
8571
8574
  /** @description Optional caption shown beneath the diagram. */
8572
8575
  caption?: string;
@@ -9156,12 +9159,12 @@ export interface operations {
9156
9159
  requestBody?: {
9157
9160
  content: {
9158
9161
  "application/json": {
9159
- /** @description Diagram language, e.g. 'mermaid', 'd2', 'plantuml', 'graphviz', 'bpmn', 'vegalite'. See listDiagramTypes. */
9162
+ /** @description Diagram language, e.g. 'default', 'mermaid', 'd2', 'plantuml', 'graphviz', 'bpmn', 'vegalite'. For a diagram family, use its defaultRenderer from listDiagramTypes. */
9160
9163
  diagramType: string;
9161
- /** @description The diagram DSL / code to render. For type 'infographic', provide a plain-English description instead (the system designs the AntV infographic spec). */
9164
+ /** @description The diagram DSL / code to render. For 'default', provide MDP JSON with stable IDs and omit entity x/y for automatic layout; fully positioned manual sources remain valid; icons must be exact iconKey values from listArchitectureIcons. For 'infographic', provide a plain-English description instead (the system designs the AntV infographic spec). */
9162
9165
  source: string;
9163
9166
  /**
9164
- * @description png (default) or jpeg = raster; svg = vector.
9167
+ * @description png (default) or jpeg = raster; svg is scalable. A platform default diagram's SVG contains a browser foreignObject scene, so use PNG/JPEG where foreignObject SVG is unsupported.
9165
9168
  * @enum {string}
9166
9169
  */
9167
9170
  format?: "png" | "jpeg" | "svg";
@@ -9262,7 +9265,7 @@ export interface operations {
9262
9265
  /** @description The diagram's id (from getDocument markers / getDiagramInDocument). */
9263
9266
  diagramId: string;
9264
9267
  /**
9265
- * @description png (default) or jpeg = raster; svg = vector.
9268
+ * @description png (default) or jpeg = raster; svg is scalable. A platform default diagram's SVG contains a browser foreignObject scene, so use PNG/JPEG where foreignObject SVG is unsupported.
9266
9269
  * @enum {string}
9267
9270
  */
9268
9271
  format?: "png" | "jpeg" | "svg";
@@ -14779,6 +14782,12 @@ export interface operations {
14779
14782
  depth?: number;
14780
14783
  /** @default 20 */
14781
14784
  limit?: number;
14785
+ /** @description Dated facts: return what held on this day (YYYY-MM-DD) instead of what holds now. For example the owner, status or supplier as it was on a past date. */
14786
+ asOf?: string;
14787
+ /** @description Dated facts: return every fact with its dates, including facts that have ended (and how they ended) and planned ones, oldest first. Use for "how did X change" or "what was X before". */
14788
+ history?: boolean;
14789
+ /** @description Dated facts: the IANA time zone to give days in (for example Australia/Sydney, Asia/Kolkata, America/New_York). Defaults to the user's saved time zone, else UTC. Pass the user's zone when you know it, so "today" and dates match their calendar. */
14790
+ timeZone?: string;
14782
14791
  };
14783
14792
  };
14784
14793
  };
@@ -14947,6 +14956,12 @@ export interface operations {
14947
14956
  name?: string;
14948
14957
  /** @description Scope the lookup to one project. Recommended when resolving by `name`, since the same entity name can exist in several projects. */
14949
14958
  projectId?: string;
14959
+ /** @description Dated facts: return what held on this day (YYYY-MM-DD) instead of what holds now. For example the owner, status or supplier as it was on a past date. */
14960
+ asOf?: string;
14961
+ /** @description Dated facts: return every fact with its dates, including facts that have ended (and how they ended) and planned ones, oldest first. Use for "how did X change" or "what was X before". */
14962
+ history?: boolean;
14963
+ /** @description Dated facts: the IANA time zone to give days in (for example Australia/Sydney, Asia/Kolkata, America/New_York). Defaults to the user's saved time zone, else UTC. */
14964
+ timeZone?: string;
14950
14965
  };
14951
14966
  };
14952
14967
  };