@kadoa/mcp 0.5.22 → 0.5.23

package/README.md

@@ -63,15 +63,15 @@ Point your client to `https://mcp.kadoa.com/mcp` with OAuth authentication.
 |------|-------------|
 | `scrape` | Immediately fetch one URL as markdown or raw HTML (shown only for enabled workspaces) |
 | `create_workflow` | Create an agentic navigation workflow from a prompt |
-| `create_realtime_monitor` | Create an asynchronous Julie realtime monitor after persisting notification channels; returns workflow/session/thread/job IDs |
+| `create_realtime_monitor` | Create an asynchronous realtime monitoring workflow after persisting notification channels; returns workflow/session/thread/job IDs |
 | `list_workflows` | List all workflows with status |
 | `get_workflow` | Get canonical intent, Assistant/session, template ownership, run health, schedule, location, monitoring, and validation details |
 | `request_workflow_update` | Ask the workflow Assistant to change extraction intent, navigation, sourcing, pagination, or generated behavior without changing the workflow ID |
 | `get_workflow_assistant` | Get the workflow Assistant's current activity and any pending clarification question |
-| `get_workflow_assistant_timeline` | Read paginated customer-visible Assistant messages and questions for Lighthouse or Julie |
+| `get_workflow_assistant_timeline` | Read paginated customer-visible Assistant messages and questions for one-time, scheduled, or realtime workflows |
 | `answer_workflow_assistant_question` | Answer the workflow Assistant's current clarification question and resume it |
 | `interrupt_workflow_assistant` | Safely interrupt active Assistant work without pausing the workflow schedule |
-| `resume_workflow_assistant` | Resume an idle/interrupted Lighthouse or Julie session with its persisted persona |
+| `resume_workflow_assistant` | Resume an idle/interrupted workflow Assistant with its persisted role and conversation |
 | `stop_workflow_assistant` | Stop active Assistant work without deleting or replacing the workflow |
 | `get_workflow_strategy` | Get the current customer-safe extraction/build strategy for an Assistant or custom-script workflow |
 | `get_workflow_history` | Get the workflow's configuration revision history (audit log) — who changed it, when, from which channel, and a `changedFields` summary per revision |
@@ -168,14 +168,14 @@ in `America/New_York`, monitoring fields/conditions, and `limit: null` for all
 rows.
 ```
 
-### Create a Julie realtime monitor
+### Create a realtime monitoring workflow
 
 ```
 > You: Watch https://example-shop.com/products for price changes and alert me by webhook.
 
-Claude calls create_realtime_monitor with the URL, schema/change intent, and notification settings. Kadoa persists reusable notification channels first, then Julie asynchronously accepts creation and returns workflow, session, thread, job, and dashboard identifiers.
+Claude calls create_realtime_monitor with the URL, schema/change intent, and notification settings. Kadoa persists reusable notification channels first, then asynchronously accepts creation and returns workflow, session, thread, job, and dashboard identifiers.
 
-> You: Does Julie need anything from me?
+> You: Does the workflow Assistant need anything from me?
 
 Claude uses get_workflow_assistant and the other workflow Assistant tools for follow-up status, questions, interrupts, resumes, or stops. It does not poll or sleep-wait.
 ```
@@ -206,9 +206,9 @@ navigation, and extraction approach.
 > You: Interrupt the Assistant for now, then resume it later.
 
 Claude calls interrupt_workflow_assistant. When asked later, it calls
-resume_workflow_assistant, which preserves whether the session is Lighthouse
-or Julie. stop_workflow_assistant cancels active Assistant work without
-pausing or deleting the workflow itself.
+resume_workflow_assistant, which continues the same Assistant role and
+conversation for either workflow mode. stop_workflow_assistant cancels active
+Assistant work without pausing or deleting the workflow itself.
 ```
 
 Use `update_workflow` for deterministic metadata such as name, schedule, tags,

package/dist/index.js

@@ -53129,7 +53129,7 @@ function registerTools(server, ctx, capabilities) {
     return urls.length > 0 ? urls : null;
   }
   function buildRealtimeAssistantInstructions(args, urls) {
-    const lines = ["Create a realtime monitoring workflow with Julie.", "", "Source URLs:"];
+    const lines = ["Create a realtime monitoring workflow.", "", "Source URLs:"];
     for (const url3 of urls)
       lines.push(`- ${url3}`);
     if (args.prompt)
@@ -53229,7 +53229,7 @@ function registerTools(server, ctx, capabilities) {
 
 ` + "Create a data extraction workflow using agentic navigation. Supports one-time or scheduled runs. " + "If entity and schema are provided, they guide the extraction; otherwise the AI agent auto-detects the schema from the page. " + "The workflow runs asynchronously and may take several minutes. Do NOT poll or sleep-wait for completion. " + `Return the workflow ID to the user and let them check back later with get_workflow or fetch_data.
 
-` + "PREFER TEMPLATES: If the user's request matches an existing template, instantiate it via `templateId` instead of writing a fresh prompt/schema. " + "Use `list_templates` to discover available templates and `get_template` to inspect schemas before deciding. " + "When creating from a template, call this tool with the template's `templateId`, the source `urls`, and optional `templateVersion` only. Never copy the template prompt, entity, or schema into standalone creation, and never silently match or rewrite inline configuration.\n\n" + "NOTE: This tool is for one-time or scheduled extraction ONLY. " + "For continuous Julie realtime monitoring (watching a page for data changes and alerting), use the create_realtime_monitor tool instead.",
+` + "PREFER TEMPLATES: If the user's request matches an existing template, instantiate it via `templateId` instead of writing a fresh prompt/schema. " + "Use `list_templates` to discover available templates and `get_template` to inspect schemas before deciding. " + "When creating from a template, call this tool with the template's `templateId`, the source `urls`, and optional `templateVersion` only. Never copy the template prompt, entity, or schema into standalone creation, and never silently match or rewrite inline configuration.\n\n" + "NOTE: This tool is for one-time or scheduled extraction ONLY. " + "For continuous realtime monitoring that watches a page for data changes and sends alerts, use the create_realtime_monitor tool instead.",
     inputSchema: strictSchema({
       ...extractionInputShape,
       ...urlInputShape,
@@ -53340,9 +53340,9 @@ function registerTools(server, ctx, capabilities) {
     });
   }));
   server.registerTool("create_realtime_monitor", {
-    description: "Create a Julie realtime monitoring workflow that continuously watches a page for data changes and sends alerts. " + "Use this when the user wants to monitor, track, or watch a page in realtime. " + "At least one notification channel (email, webhook, slack, or websocket) is required; notification settings are persisted before Julie is dispatched. " + `Realtime monitors CANNOT be converted to/from regular extraction workflows after creation.
+    description: "Create a realtime monitoring workflow that continuously watches a page for data changes and sends alerts. " + "Use this when the user wants to monitor, track, or watch a page in realtime. " + "At least one notification channel (email, webhook, slack, or websocket) is required; notification settings are persisted before Assistant creation is dispatched. " + `Realtime monitors CANNOT be converted to/from one-time or scheduled extraction workflows after creation.
 
-` + "If entity and schema are provided, they guide what Julie should monitor; otherwise Julie auto-detects what to watch. " + "Creation is asynchronous and the response includes workflow, session, thread, and job IDs plus a dashboard URL. " + "Use generic workflow Assistant tools (get_workflow_assistant, answer_workflow_assistant_question, interrupt_workflow_assistant, resume_workflow_assistant, stop_workflow_assistant) for follow-up status, questions, and controls. " + "Do NOT poll or sleep-wait for completion.",
+` + "If entity and schema are provided, they guide what the Assistant should monitor; otherwise the Assistant determines what to watch. " + "Creation is asynchronous and the response includes workflow, session, thread, and job IDs plus a dashboard URL. " + "Use generic workflow Assistant tools (get_workflow_assistant, answer_workflow_assistant_question, interrupt_workflow_assistant, resume_workflow_assistant, stop_workflow_assistant) for follow-up status, questions, and controls. " + "Do NOT poll or sleep-wait for completion.",
     inputSchema: strictSchema({
       ...extractionInputShape,
       ...urlInputShape,
@@ -53387,7 +53387,7 @@ function registerTools(server, ctx, capabilities) {
       threadId: result.threadId,
       jobId: result.jobId,
       dashboardUrl: workflowDashboardUrl(result.workflowId),
-      message: "Julie realtime workflow creation accepted. Notification settings were persisted before Julie dispatch. Creation is asynchronous; use get_workflow_assistant for status, questions, or controls, and do not poll or sleep-wait."
+      message: "Realtime monitoring workflow creation accepted. Notification settings were persisted before Assistant dispatch. Creation is asynchronous; use get_workflow_assistant for status, questions, or controls, and do not poll or sleep-wait."
     });
   }));
   server.registerTool("list_workflows", {
@@ -53545,7 +53545,7 @@ function registerTools(server, ctx, capabilities) {
     });
   }));
   server.registerTool("get_workflow_assistant", {
-    description: "Get the current Assistant lifecycle for a workflow, including whether it is working, waiting for input, idle, interrupted, or closed and any pending customer question. Works for both Shelly/Lighthouse and Julie workflows.",
+    description: "Get the current Assistant lifecycle for a workflow, including whether it is working, waiting for input, idle, interrupted, or closed and any pending customer question. Works for one-time or scheduled extraction workflows and realtime monitoring workflows.",
     inputSchema: strictSchema({
       workflowId: exports_external.string().min(1).describe("The workflow ID")
     }),
@@ -53583,7 +53583,7 @@ function registerTools(server, ctx, capabilities) {
     });
   }));
   server.registerTool("get_workflow_assistant_timeline", {
-    description: "Read the customer-visible conversation history for a workflow Assistant, including user messages, Assistant messages, and clarification questions with answers. " + "Works for both Shelly/Lighthouse and Julie workflows. Use get_workflow_history instead for configuration revisions. Results are chronological within each page; use nextCursor to request older items when hasMore is true.",
+    description: "Read the customer-visible conversation history for a workflow Assistant, including user messages, Assistant messages, and clarification questions with answers. " + "Use this when the user asks what the Assistant said or asked, how a clarification was answered, or to show the latest conversation for a workflow. " + "Supports one-time or scheduled extraction workflows and realtime monitoring workflows. Use get_workflow_history instead for configuration revisions. " + "Results are chronological within each page; use nextCursor to request older items when hasMore is true.",
     inputSchema: strictSchema({
       workflowId: exports_external.string().min(1).describe("The workflow ID"),
       cursor: exports_external.string().min(1).optional().describe("Opaque nextCursor from the previous page"),
@@ -53685,7 +53685,7 @@ function registerTools(server, ctx, capabilities) {
     });
   }));
   server.registerTool("resume_workflow_assistant", {
-    description: "Resume an idle or interrupted workflow Assistant using the persona and conversation persisted on its session. Works for both Lighthouse and Julie. This does not resume a paused workflow schedule; use approve_workflow for that.",
+    description: "Resume an idle or interrupted workflow Assistant using the role and conversation persisted on its session. Works for one-time or scheduled extraction workflows and realtime monitoring workflows. This does not resume a paused workflow schedule; use approve_workflow for that.",
     inputSchema: strictSchema({
       workflowId: exports_external.string().min(1).describe("Workflow whose Assistant session should resume")
     }),
@@ -53937,7 +53937,7 @@ function registerTools(server, ctx, capabilities) {
     });
   }));
   server.registerTool("list_changes", {
-    description: "List detected data changes across one or more Julie realtime monitoring workflows. " + "Returns structured diffs showing added, removed, and changed records. " + "Only works for workflows with realtime monitoring enabled.",
+    description: "List detected data changes across one or more realtime monitoring workflows. " + "Returns structured diffs showing added, removed, and changed records. " + "Only works for workflows with realtime monitoring enabled.",
     inputSchema: {
       workflowIds: exports_external.preprocess(coerceArray(true), exports_external.array(exports_external.string())).optional().describe("Workflow IDs to filter by. If omitted, returns changes for all ACTIVE monitoring workflows."),
       startDate: exports_external.string().optional().describe("Start date filter (ISO format, e.g. 2025-01-01)"),
@@ -54047,9 +54047,9 @@ function registerTools(server, ctx, capabilities) {
   server.registerTool("update_workflow", {
     description: `Update a workflow's configuration. All fields are optional - only provided fields will be updated. Use this to change the name, URLs, extraction schema, entity, prompt, schedule, or other metadata.
 
-` + `IMPORTANT: You cannot change a workflow's interval to or from REAL_TIME. Julie realtime workflows are architecturally different from scheduled workflows and must be created with create_realtime_monitor from the start. Existing workflows cannot be converted between these modes in place; do not delete and recreate a workflow as an update workaround.
+` + `IMPORTANT: You cannot change a workflow's interval to or from REAL_TIME. Realtime monitoring workflows are architecturally different from one-time or scheduled extraction workflows and must be created with create_realtime_monitor from the start. Existing workflows cannot be converted between these modes in place; do not delete and recreate a workflow as an update workaround.
 
-` + "ASSISTANT-OWNED INTENT: Use request_workflow_update - not `userPrompt` - for agent-built workflow changes to extraction intent, navigation, pagination, data sourcing, repair, or generated scripts. `userPrompt` may be rejected with `SHELLY_INTENT_REQUIRES_EXTRACTION_SPEC` because those workflows' canonical intent is owned by the Assistant. " + "Call get_workflow first. If its template.controlledParts contains the setting, create and apply a template version instead of overriding the workflow directly. NEVER delete and recreate a workflow to work around an update limitation - that changes workflowId, breaks downstream tables/connectors, and discards history.",
+` + "ASSISTANT-OWNED INTENT: Use request_workflow_update - not `userPrompt` - for Assistant-built workflow changes to extraction intent, navigation, pagination, data sourcing, repair, or generated scripts. The API may reject `userPrompt` because these workflows' canonical intent is owned by the Assistant. " + "Call get_workflow first. If its template.controlledParts contains the setting, create and apply a template version instead of overriding the workflow directly. NEVER delete and recreate a workflow to work around an update limitation - that changes workflowId, breaks downstream tables/connectors, and discards history.",
     inputSchema: strictSchema({
       workflowId: exports_external.string().describe("The workflow ID to update"),
       name: exports_external.string().optional().describe("New name for the workflow"),
@@ -54092,10 +54092,10 @@ function registerTools(server, ctx, capabilities) {
       const isCurrentlyRealTime = isRealTimeInterval(workflow.updateInterval);
       const isRequestingRealTime = isRealTimeInterval(updates.updateInterval);
       if (isRequestingRealTime && !isCurrentlyRealTime) {
-        return errorResult("Cannot change a regular workflow's interval to REAL_TIME. " + "Julie realtime workflows cannot replace this workflow in place. " + "The existing workflow was left unchanged.");
+        return errorResult("Cannot change a regular workflow's interval to REAL_TIME. " + "Realtime monitoring workflows cannot replace this workflow in place. " + "The existing workflow was left unchanged.");
       }
       if (!isRequestingRealTime && isCurrentlyRealTime) {
-        return errorResult("Cannot change a Julie realtime workflow's interval to a scheduled interval. " + "Julie realtime workflows are architecturally different and cannot be converted in place. " + "The existing workflow was left unchanged.");
+        return errorResult("Cannot change a realtime monitoring workflow's interval to a scheduled interval. " + "Realtime monitoring workflows are architecturally different and cannot be converted in place. " + "The existing workflow was left unchanged.");
       }
     }
     if (updates.updateInterval === "CUSTOM" && (!updates.schedules || updates.schedules.length === 0)) {
@@ -54961,7 +54961,7 @@ var package_default;
 var init_package = __esm(() => {
   package_default = {
     name: "@kadoa/mcp",
-    version: "0.5.22",
+    version: "0.5.23",
     description: "Kadoa MCP Server — manage workflows from Claude Desktop, Cursor, and other MCP clients",
     type: "module",
     main: "dist/index.js",
@@ -60571,7 +60571,7 @@ async function createServer(auth, options) {
       "",
       "Workflow lifecycle: create_workflow \u2192 get_workflow (check status) \u2192 fetch_data (get results). Workflows run asynchronously - never poll or sleep-wait.",
       "",
-      "Use create_realtime_monitor only when the user wants continuous Julie change detection with alerts. It first persists notification channels, then asynchronously returns workflow/session/thread/job IDs; use the workflow Assistant tools for follow-up status, questions, and controls.",
+      "Use create_realtime_monitor only when the user wants continuous realtime change detection with alerts. It first persists notification channels, then asynchronously returns workflow/session/thread/job IDs; use the workflow Assistant tools for follow-up status, questions, and controls.",
       "For one-time or scheduled extraction, use create_workflow. Use scrape for an immediate raw HTML or markdown fetch from one URL. Use create_workflow for structured extraction, recurring runs, monitoring, or navigation-heavy jobs.",
       "If a one-time or scheduled workflow fails, retry it with run_workflow using the existing workflow ID. Do NOT delete and recreate the workflow just to retry it - preserve its workflow ID and configuration. Realtime workflows cannot be manually run.",
       "Use list_changes and get_change to retrieve detected diffs from realtime monitoring workflows.",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@kadoa/mcp",
-  "version": "0.5.22",
+  "version": "0.5.23",
   "description": "Kadoa MCP Server — manage workflows from Claude Desktop, Cursor, and other MCP clients",
   "type": "module",
   "main": "dist/index.js",