@elitedcs/ghl-mcp 3.64.1 → 3.65.1

package/CHANGELOG.md

@@ -1,5 +1,79 @@
 # Changelog
 
+## 3.65.1 — the guide caught up with the product
+
+No code changes. The built-in user guide ships inside the install, so it goes
+out as its own release.
+
+- **Fix: the booking-calendar guide was telling you to do something by hand that
+  the product now does.** It said minimum booking notice lived on GHL's calendar
+  screen "and not here", and sent you there to set it. 3.65.0 made it settable
+  directly. Anyone following that page yesterday was sent clicking through GHL
+  for no reason.
+- **Booking calendars**: daily caps and minimum notice are now in the guide, in
+  the same ask that sets your hours and slot length. Plus what to do if an older
+  version reset your slot lengths or opening hours when you changed something
+  else.
+- **Nurture sequences**: quiet hours. What they are, why every workflow that
+  texts needs its own, and the one thing to go check: if you set quiet hours
+  before 3.65.0, they were dropped the next time that workflow was saved. Open
+  anything that texts and set them once more.
+- **Contact lists**: how to save a group as a list you can reopen, rather than
+  rebuilding the same filter every Monday. These tools never worked before
+  3.65.0, so if you tried this and found nothing in GHL, that is why.
+- **Blueprint**: how appointment, reply, missed-call and number-check triggers
+  get scoped to the thing you actually meant, and why a stage move needs to find
+  its deal first.
+
+Every prompt in the guide is bound to a run that actually happened in a real
+sub-account. The three new ones were proven live before this shipped.
+
+## 3.65.0 — nine calls that reported success and did the wrong thing
+
+Found while building a 139-requirement home-care front office end to end. Every
+fix below has the same shape: the call succeeds, the response reads correctly,
+and something quietly did not happen. None raised an error. Four were findable
+only by firing the system and watching, not by reading settings back.
+
+**Three of these were damaging live accounts.**
+
+- **Fix: saving a calendar wiped its own settings.** Updating one field on a
+  calendar sent only that field, and GoHighLevel treated the omissions as
+  deletions — slot duration, slot interval, buffers and the entire open-hours
+  grid were erased. The call returned 200 and the calendar looked fine in the
+  list. Calendar updates now read the existing record first and merge; if that
+  read fails the update refuses rather than falling back to a write that would
+  clobber.
+- **Fix: saving a workflow silently deleted its quiet hours.** The update never
+  sent the sending-window field, so any workflow with contact-hour restrictions
+  lost them on the next save, with no warning. For anyone using quiet hours for
+  TCPA compliance, the protection disappeared the first time the workflow was
+  touched.
+- **Fix: every smart-list tool pointed at the wrong service.** All five called an
+  endpoint that does not serve contact smart lists, so they never worked.
+
+Silent no-ops:
+
+- **Fix: appointment triggers ignored the calendar you chose** and fired for every
+  calendar in the account. A caregiver interview booking would start the family
+  consultation sequence.
+- **Fix: reply triggers fired on every inbound message**, because the conditions
+  were emitted empty.
+- **Fix: moving a deal to a new stage did nothing** unless the workflow had first
+  looked the opportunity up. The step reported success at every save. Now caught
+  before the build runs.
+
+New:
+
+- **`create_contact_smart_list`, `get_contact_smart_list`, `delete_contact_smart_list`.**
+  238 tools total, 110 free.
+- **Calendar per-day limits and minimum booking notice** are now reachable
+  (`appointmentPerDay`, `allowBookingAfter`, `allowBookingAfterUnit`).
+- **Workflow quiet hours** can now be set through the tool — a sending window
+  with days, applied per workflow.
+- **Four trigger builders**: calendar-scoped appointments, reply-intent routing,
+  call status, and phone-number validation failures.
+
 ## 3.64.1 — three more calls that failed quietly
 
 - **Fix: client pricing was mangled on the way into a build plan.** The Blueprint

package/README.md

@@ -1,6 +1,6 @@
 # GHL Command — GoHighLevel MCP Server
 
-**Full GoHighLevel API access for Claude.** 235 tools across 50 modules — manage contacts, conversations, pipelines, calendars, funnels, workflows, invoices, custom objects, webhooks, and more. **Includes full workflow builder, funnel/page editor, form builder, pipeline builder, bulk operations, account export, and workflow cloning** — capabilities no other GHL tool offers. **Multi-tenant:** one install can run the workflow builder across multiple clients' GHL accounts.
+**Full GoHighLevel API access for Claude.** 238 tools across 50 modules — manage contacts, conversations, pipelines, calendars, funnels, workflows, invoices, custom objects, webhooks, and more. **Includes full workflow builder, funnel/page editor, form builder, pipeline builder, bulk operations, account export, and workflow cloning** — capabilities no other GHL tool offers. **Multi-tenant:** one install can run the workflow builder across multiple clients' GHL accounts.
 
 **Distributed via npm as [`@elitedcs/ghl-mcp`](https://www.npmjs.com/package/@elitedcs/ghl-mcp).** Buyers install with one config block — no git, no Node.js setup, no terminal commands. Updates flow automatically (`npx @latest` re-resolves on every Claude restart).
 
@@ -8,7 +8,7 @@ Works with **both the Claude Desktop App and Claude Code terminal** — your cho
 
 **License required.** Get it at [ghlcommand.com](https://ghlcommand.com?utm_source=npm&utm_medium=readme) — $97/mo, covering UNLIMITED GoHighLevel sub-accounts on up to 3 machines (never billed per account). **30-day time-back guarantee**: save 5+ hours on one client build or your first month back.
 
-**Try it FREE (read-only tier).** Grab an instant free key at [ghlcommand.com/free](https://ghlcommand.com/free?utm_source=npm&utm_medium=readme) — 109 read-only tools on your own GHL account once the two-step install is finished (the same install as the paid tier — upgrading later is just a license swap): the account-wide workflow audit (`audit_workflows` finds the silently broken references GHL never warns you about), account health, and every read across contacts, pipelines, funnels, and workflows. Write tools stay visible and answer with upgrade info. Buying later with the same email upgrades your key in place — 1 machine on free, 3 when you upgrade.
+**Try it FREE (read-only tier).** Grab an instant free key at [ghlcommand.com/free](https://ghlcommand.com/free?utm_source=npm&utm_medium=readme) — 110 read-only tools on your own GHL account once the two-step install is finished (the same install as the paid tier — upgrading later is just a license swap): the account-wide workflow audit (`audit_workflows` finds the silently broken references GHL never warns you about), account health, and every read across contacts, pipelines, funnels, and workflows. Write tools stay visible and answer with upgrade info. Buying later with the same email upgrades your key in place — 1 machine on free, 3 when you upgrade.
 
 **How this differs from HighLevel's official MCP.** HighLevel ships an official Anthropic MCP that reads and writes your CRM (contacts, conversations, calendars, opportunities, payments, social) over the public API — it's free and it's good; use it for that. What it *cannot* do, because the public API doesn't expose it: **build or edit workflows, build funnels/landing pages, or build forms.** That's exactly what GHL Command does — the programmatic Workflow Builder, funnel/page builder, form builder, deep workflow cloning, the silent-failure `audit_workflows`, and Blueprint (build a whole client account from one intake — ships as a guided skill that **installs itself automatically** with this package; nothing to download), all on GHL's internal APIs. **Official MCP = read/write your CRM. GHL Command = build and fix it.** They stack fine together.
 
@@ -135,7 +135,7 @@ Run setup_ghl_mcp to activate GHL Command:
   ghl_location_id: YOUR_LOCATION_ID
 ```
 
-Approve the tool call. Server validates your license, verifies your GHL credentials, writes them to a per-user config file. **Quit Claude one more time and reopen** — the full core toolset is now unlocked (235 tools total with the optional Workflow Builder Firebase add-on).
+Approve the tool call. Server validates your license, verifies your GHL credentials, writes them to a per-user config file. **Quit Claude one more time and reopen** — the full core toolset is now unlocked (238 tools total with the optional Workflow Builder Firebase add-on).
 
 ### 4. Try it
 
@@ -518,7 +518,7 @@ Highlights (full guide: [`docs/HEADLESS.md`](docs/HEADLESS.md)):
 |---|---|
 | `get_mcp_version` | Check installed version against the latest published to npm. Confirms an upgrade landed after restarting Claude. Available even before GHL credentials are configured. |
 | `health_check` | Run a full health check: npm registry + version status, GHL API key validity, default location reachability, Firebase auth status, token registry presence. Use when something feels broken. |
-| `enable_workflow_builder` | Add Firebase credentials to an existing install to unlock 52 additional Firebase-gated tools (workflow builder, funnel builder, form builder, pipeline builder, workflow cloner, smart lists, reputation, email campaigns, email templates, memberships, validate_workflow). No need to re-enter license / API key / location ID. Run this any time after the basic setup, on the buyer's schedule. |
+| `enable_workflow_builder` | Add Firebase credentials to an existing install to unlock 55 additional Firebase-gated tools (workflow builder, funnel builder, form builder, pipeline builder, workflow cloner, smart lists, reputation, email campaigns, email templates, memberships, validate_workflow). No need to re-enter license / API key / location ID. Run this any time after the basic setup, on the buyer's schedule. |
 
 ### Other Modules
 
@@ -798,7 +798,7 @@ Source repo is private. Contributors need an invitation from `drjerryrelth`. The
 
 ### Reducing context / token usage
 
-Every registered MCP tool's schema is shipped to the model on every message. With 235 tools that's a meaningful per-message context cost even in chats that never touch GHL. If you only use a slice of GHL Command, restrict the tool surface with `GHL_ENABLED_MODULES` and/or `GHL_ENABLED_TOOLS`:
+Every registered MCP tool's schema is shipped to the model on every message. With 238 tools that's a meaningful per-message context cost even in chats that never touch GHL. If you only use a slice of GHL Command, restrict the tool surface with `GHL_ENABLED_MODULES` and/or `GHL_ENABLED_TOOLS`:
 
 ```jsonc
 // Claude Desktop config — enable whole modules

package/dist/index.js

@@ -1648,7 +1648,7 @@ Note: Firebase credentials rejected (${fb.error}).`;
       const telemetryLine = telemetryDisabled(process.env) ? "" : `
 
 ${TELEMETRY_DISCLOSURE}`;
-      const finishedCount = isFree ? "109" : "235";
+      const finishedCount = isFree ? "110" : "238";
       const freeTip = isFree ? `
 
 Free tier: read-only. Write tools stay visible but answer with upgrade info instead of acting. Full version ($97/mo founding rate) upgrades in place \u2014 same install, you only swap the license key: https://ghlcommand.com` : "";
@@ -1693,7 +1693,7 @@ Free tier: read-only. Write tools stay visible but answer with upgrade info inst
 function registerEnableWorkflowBuilderTool(server2) {
   server2.tool(
     "enable_workflow_builder",
-    "Add Firebase credentials to an existing GHL Command install to unlock 52 additional tools across the internal-API modules: workflow builder (create/edit/clone/delete/publish/validate workflows, build_if_else_branch, build_goal_event, get_trigger_registry), funnel + page builder, form builder, pipeline builder, workflow cloner, smart lists, reputation, email campaigns, email templates, and memberships, plus the pre-deploy validator. On the FREE tier this same login unlocks the read-only auditor suite (audit_workflows, validate_workflow, full-detail workflow/funnel/pipeline reads). Requires you've already run setup_ghl_mcp. EASIEST PATH: run `capture_firebase_interactive` instead \u2014 a Chrome window opens, you log into GHL, zero pasting. Use THIS tool when you have JSON from `auto_capture_firebase_script` (console-paste path) to put in `firebase_paste`, or the three manual DevTools fields. Tool count goes from 183 to 235 after the next Claude restart.",
+    "Add Firebase credentials to an existing GHL Command install to unlock 55 additional tools across the internal-API modules: workflow builder (create/edit/clone/delete/publish/validate workflows, build_if_else_branch, build_goal_event, get_trigger_registry), funnel + page builder, form builder, pipeline builder, workflow cloner, smart lists, reputation, email campaigns, email templates, and memberships, plus the pre-deploy validator. On the FREE tier this same login unlocks the read-only auditor suite (audit_workflows, validate_workflow, full-detail workflow/funnel/pipeline reads). Requires you've already run setup_ghl_mcp. EASIEST PATH: run `capture_firebase_interactive` instead \u2014 a Chrome window opens, you log into GHL, zero pasting. Use THIS tool when you have JSON from `auto_capture_firebase_script` (console-paste path) to put in `firebase_paste`, or the three manual DevTools fields. Tool count goes from 183 to 238 after the next Claude restart.",
     {
       // v3.25.0: one-paste path. Tool runs `auto_capture_firebase_script` to
       // get the console script; the script returns a JSON object that pastes
@@ -1774,7 +1774,7 @@ DevTools steps: https://elitedcs.com/ghl-mcp-firebase`
             "",
             "**You MUST restart Claude before using any workflow-builder tool.** Quit Claude completely (Cmd+Q on Mac, full exit on Windows) and reopen. Without a restart, the workflow builder tools will keep using the OLD Firebase auth from before this call and fail with 401 errors \u2014 even though this tool reported success.",
             "",
-            'After restart, all 235 tools load. Try: "List my workflows in full detail" or "Validate workflow <id>".',
+            'After restart, all 238 tools load. Try: "List my workflows in full detail" or "Validate workflow <id>".',
             "",
             "Note: Firebase refresh tokens rotate every few weeks. If workflow tools stop working in a few weeks (run `health_check` to confirm Firebase auth: FAIL), run `auto_capture_firebase_script` for fresh values and re-run this tool with the new firebase_paste."
           ].join("\n")
@@ -1870,7 +1870,7 @@ The login in the capture window may belong to the wrong GHL account, or the sess
               "",
               "**You MUST restart Claude before using any workflow-builder tool.** Quit Claude completely (Cmd+Q on Mac, full exit on Windows) and reopen.",
               "",
-              'After restart, all 235 tools load. Try: "List my workflows in full detail".',
+              'After restart, all 238 tools load. Try: "List my workflows in full detail".',
               "",
               "Future token rotations re-capture silently \u2014 if workflow tools ever 401, just run capture_firebase_interactive again; no window should appear."
             ].join("\n")
@@ -2854,9 +2854,9 @@ var require_package = __commonJS({
   "package.json"(exports2, module2) {
     module2.exports = {
       name: "@elitedcs/ghl-mcp",
-      version: "3.64.1",
+      version: "3.65.1",
       mcpName: "io.github.drjerryrelth/ghl-command",
-      description: "GoHighLevel MCP Server for Claude. 235 tools \u2014 full CRM, automation, marketing control, account-wide workflow audit, live funnel-capture verification, and the only programmatic GHL workflow builder, now multi-tenant across client accounts.",
+      description: "GoHighLevel MCP Server for Claude. 238 tools \u2014 full CRM, automation, marketing control, account-wide workflow audit, live funnel-capture verification, and the only programmatic GHL workflow builder, now multi-tenant across client accounts.",
       main: "dist/index.js",
       bin: {
         "ghl-mcp": "dist/index.js"
@@ -6271,6 +6271,9 @@ ${errorBody}`
       allowMultipleOpportunity: updates.allowMultipleOpportunity ?? current.allowMultipleOpportunity ?? false,
       autoMarkAsRead: updates.autoMarkAsRead ?? current.autoMarkAsRead ?? false,
       removeContactFromLastStep: updates.removeContactFromLastStep ?? current.removeContactFromLastStep ?? true,
+      // Preserve unless explicitly set (including an explicit null to clear).
+      // `?? ` would be wrong here — null is a meaningful value.
+      window: updates.window !== void 0 ? updates.window : current.window ?? null,
       workflowData: { templates: linkedActions },
       updatedBy: this.userId,
       // Triggers live in Firestore and are managed out-of-band; the workflow
@@ -7593,6 +7596,9 @@ function applyCalendarFields(body, args) {
   if (args.slotBuffer !== void 0) body.slotBuffer = args.slotBuffer;
   if (args.slotInterval !== void 0) body.slotInterval = args.slotInterval;
   if (args.appointmentPerSlot !== void 0) body.appointmentPerSlot = args.appointmentPerSlot;
+  if (args.appointmentPerDay !== void 0) body.appointmentPerDay = args.appointmentPerDay;
+  if (args.allowBookingAfter !== void 0) body.allowBookingAfter = args.allowBookingAfter;
+  if (args.allowBookingAfterUnit !== void 0) body.allowBookingAfterUnit = args.allowBookingAfterUnit;
   if (args.openHours !== void 0) {
     body.openHours = expandOpenHours(args.openHours);
     body.availabilityType = args.availabilityType ?? 0;
@@ -7614,6 +7620,30 @@ function buildUpdateCalendarBody(args) {
   applyCalendarFields(body, args);
   return body;
 }
+var MERGE_PRESERVED_FIELDS = [
+  "slotDuration",
+  "slotInterval",
+  "slotBuffer",
+  "appointmentPerSlot",
+  "appointmentPerDay",
+  "allowBookingAfter",
+  "allowBookingAfterUnit",
+  "availabilityType"
+];
+function mergeCalendarUpdate(existing, args) {
+  if (!existing) return args;
+  const merged = { ...args };
+  for (const key of MERGE_PRESERVED_FIELDS) {
+    if (merged[key] === void 0 && existing[key] !== void 0 && existing[key] !== "") {
+      merged[key] = existing[key];
+    }
+  }
+  if (merged.openHours === void 0) {
+    const hours = existing.openHours;
+    if (Array.isArray(hours) && hours.length > 0) merged.openHours = hours;
+  }
+  return merged;
+}
 function tzOffsetMillis(utcMillis, timeZone) {
   const dtf = new Intl.DateTimeFormat("en-US", {
     timeZone,
@@ -7724,6 +7754,9 @@ function registerCalendarTools(server2, client) {
       slotBuffer: import_zod12.z.number().optional().describe("Buffer time between slots in minutes"),
       slotInterval: import_zod12.z.number().optional().describe("Slot interval in minutes"),
       appointmentPerSlot: import_zod12.z.number().optional().describe("Max appointments per slot"),
+      appointmentPerDay: import_zod12.z.number().optional().describe("Max appointments bookable per DAY on this calendar (the daily ceiling, distinct from appointmentPerSlot). Without it the day's capacity is whatever the open hours allow."),
+      allowBookingAfter: import_zod12.z.number().optional().describe("Minimum advance notice before a slot can be booked, in allowBookingAfterUnit. E.g. 24 with unit 'hours' blocks same-day and short-notice bookings."),
+      allowBookingAfterUnit: import_zod12.z.string().optional().describe("Unit for allowBookingAfter: 'minutes' | 'hours' | 'days'. Send alongside allowBookingAfter."),
       openHours: import_zod12.z.array(OpenHoursBlockSchema).optional().describe(
         "Weekly business hours that make slots bookable (the 'assign availability hours' step). Each entry maps weekdays (0=Sun \u2026 6=Sat) to one or more open windows on a 24-hour clock; multi-day entries are auto-expanded to GHL's required one-block-per-day form. Example Mon-Fri 9-6 + Sat 10-1: [{daysOfTheWeek:[1,2,3,4,5],hours:[{openHour:9,openMinute:0,closeHour:18,closeMinute:0}]},{daysOfTheWeek:[6],hours:[{openHour:10,openMinute:0,closeHour:13,closeMinute:0}]}]. Behavior (verified live): on event/simple calendars these hours are the sole source of availability. On round_robin calendars the bookable slots are the INTERSECTION of these hours and each assigned user's working hours, so a day only opens if a team member is also available then (e.g. a Saturday window needs a user with Saturday availability). Omit to use GHL's defaults."
       ),
@@ -7753,13 +7786,26 @@ function registerCalendarTools(server2, client) {
       slotBuffer: import_zod12.z.number().optional().describe("Buffer time between slots in minutes"),
       slotInterval: import_zod12.z.number().optional().describe("Slot interval in minutes"),
       appointmentPerSlot: import_zod12.z.number().optional().describe("Max appointments per slot"),
+      appointmentPerDay: import_zod12.z.number().optional().describe("Max appointments bookable per DAY on this calendar (the daily ceiling, distinct from appointmentPerSlot)."),
+      allowBookingAfter: import_zod12.z.number().optional().describe("Minimum advance notice before a slot can be booked, in allowBookingAfterUnit. E.g. 24 with unit 'hours' blocks same-day and short-notice bookings."),
+      allowBookingAfterUnit: import_zod12.z.string().optional().describe("Unit for allowBookingAfter: 'minutes' | 'hours' | 'days'. Send alongside allowBookingAfter."),
       openHours: import_zod12.z.array(OpenHoursBlockSchema).optional().describe(
         "Weekly business hours that make slots bookable. Each entry maps weekdays (0=Sun \u2026 6=Sat) to one or more open windows on a 24-hour clock; multi-day entries are auto-expanded to GHL's required one-block-per-day form (e.g. [{daysOfTheWeek:[1,2,3,4,5],hours:[{openHour:9,openMinute:0,closeHour:18,closeMinute:0}]}] = Mon-Fri 9am-6pm). Replaces the calendar's existing hours. Behavior (verified live): event/simple calendars use these hours directly; round_robin calendars intersect them with each assigned user's working hours (a day only opens if a team member is available then)."
       ),
       availabilityType: import_zod12.z.number().int().optional().describe("Availability mode. 0 = standard weekly hours (from openHours); auto-set when you pass openHours. Leave unset otherwise.")
     },
     async (args) => {
-      const body = buildUpdateCalendarBody(args);
+      let existing;
+      try {
+        const current = await client.get(`/calendars/${args.calendarId}`);
+        const cal = current?.calendar ?? current;
+        if (cal && typeof cal === "object") existing = cal;
+      } catch (e) {
+        throw new Error(
+          `update_calendar: could not read calendar ${args.calendarId} before updating it (${e instanceof Error ? e.message : String(e)}). Refusing to write: GHL's calendar update does not merge, so a partial write here would silently reset this calendar's slot length, buffer and availability hours.`
+        );
+      }
+      const body = buildUpdateCalendarBody(mergeCalendarUpdate(existing, args));
       return await client.put(`/calendars/${args.calendarId}`, { body });
     }
   );
@@ -10380,9 +10426,17 @@ function registerWorkflowBuilderTools(server2, client) {
       stopOnResponse: import_zod36.z.boolean().optional().describe("Stop the workflow when the contact replies. If omitted, the current value is preserved."),
       autoMarkAsRead: import_zod36.z.boolean().optional().describe("Auto-mark conversations as read. If omitted, the current value is preserved."),
       removeContactFromLastStep: import_zod36.z.boolean().optional().describe("Remove the contact when they reach the last step. If omitted, the current value is preserved."),
-      allowMultipleOpportunity: import_zod36.z.boolean().optional().describe("Allow creating multiple opportunities. If omitted, the current value is preserved.")
+      allowMultipleOpportunity: import_zod36.z.boolean().optional().describe("Allow creating multiple opportunities. If omitted, the current value is preserved."),
+      window: import_zod36.z.object({
+        condition: import_zod36.z.string().describe('Usually "when" \u2014 run only DURING the window.'),
+        start: import_zod36.z.string().describe('Start of the window, 24-hour "HH:MM" (e.g. "08:00").'),
+        end: import_zod36.z.string().describe('End of the window, 24-hour "HH:MM" (e.g. "21:00").'),
+        days: import_zod36.z.array(import_zod36.z.number().int().min(0).max(6)).describe("Days the window applies to. 0=Sunday \u2026 6=Saturday.")
+      }).nullable().optional().describe(
+        `EXECUTION WINDOW \u2014 the hours this workflow is allowed to run. This is where quiet hours / TCPA contact-hour restrictions are enforced: there is NO time-of-day setting inside the Voice AI or Conversation AI builders, so a "never text before 8am or after 9pm" rule has to live here, on every workflow that sends SMS. Example: {condition:"when", start:"08:00", end:"21:00", days:[0,1,2,3,4,5,6]}. Pass null to clear. OMIT to preserve the workflow's existing window (it was previously dropped from the payload entirely, so saving a workflow silently wiped its window).`
+      )
     },
-    async ({ workflowId, name, status, actions, triggers, allowMultiple, stopOnResponse, autoMarkAsRead, removeContactFromLastStep, allowMultipleOpportunity }) => {
+    async ({ workflowId, name, status, actions, triggers, allowMultiple, stopOnResponse, autoMarkAsRead, removeContactFromLastStep, allowMultipleOpportunity, window }) => {
       try {
         const result = await client.updateWorkflow(workflowId, {
           name,
@@ -10393,7 +10447,8 @@ function registerWorkflowBuilderTools(server2, client) {
           stopOnResponse,
           autoMarkAsRead,
           removeContactFromLastStep,
-          allowMultipleOpportunity
+          allowMultipleOpportunity,
+          window
         });
         return jsonResponse(result);
       } catch (error) {
@@ -13681,6 +13736,33 @@ function registerWorkflowClonerTools(server2, builderClient) {
 var import_zod48 = require("zod");
 var SMARTLIST_BASE = "https://backend.leadconnectorhq.com/lists/dynamic";
 var OBJECT_KEYS = ["contacts", "opportunity"];
+var CONTACT_SMARTLIST_BASE = "https://services.leadconnectorhq.com/contacts/smartlist";
+var CONTACT_SMARTLIST_DELETE = "https://api.leadconnectorhq.com/smartlist/delete";
+var DEFAULT_CONTACT_SMARTLIST_COLUMNS = [
+  { key: "name", value: "name", order: 0 },
+  { key: "phone", value: "phone", order: 1 },
+  { key: "email", value: "email", order: 2 },
+  { key: "companyName", value: "companyName", order: 3 },
+  { key: "dateAdded", value: "dateAdded", order: 4 },
+  { key: "lastActivity", value: "lastActivity", order: 5 },
+  { key: "tags", value: "tags", order: 6 }
+];
+function buildContactTagFilter(tagNames) {
+  return { field: "tags", operator: "eq", value: tagNames, options: { minimumMatch: "all" } };
+}
+function buildContactSmartListBody(args) {
+  return {
+    columns: args.columns ?? DEFAULT_CONTACT_SMARTLIST_COLUMNS,
+    filterSpecs: {
+      filters: [{ group: "OR", filters: [{ group: "AND", filters: args.filters }] }],
+      page: 1,
+      limit: args.limit ?? 20
+    },
+    listName: args.listName,
+    sortSpecs: [],
+    locationId: args.locationId
+  };
+}
 function registerSmartListTools(server2, builderClient) {
   const client = builderClient;
   if (!client) return;
@@ -13714,6 +13796,19 @@ ${text2}`);
     async ({ objectKey, query, limit, startAfter, locationId: locationId2 }) => {
       try {
         const loc = locationId2 ?? client.locationId;
+        if (objectKey === "contacts") {
+          const headers = await client.buildHeaders();
+          const p = new URLSearchParams({
+            locationId: loc,
+            userId: client.getUserId(),
+            globals: "true",
+            transform: "true"
+          });
+          const res = await fetch(`${CONTACT_SMARTLIST_BASE}/search?${p.toString()}`, { headers });
+          if (!res.ok) throw new Error(`Smart Lists API Error ${res.status}: GET /contacts/smartlist/search
+${await res.text()}`);
+          return jsonResponse(JSON.parse(await res.text() || "{}"));
+        }
         const params = new URLSearchParams({ objectKey });
         if (query) params.set("query", query);
         if (limit !== void 0) params.set("limit", String(limit));
@@ -13725,6 +13820,74 @@ ${text2}`);
       }
     }
   );
+  server2.tool(
+    "create_contact_smart_list",
+    "Create a CONTACT smart list (saved filter over contacts) with working filters \u2014 the owner-exception views a dashboard needs. Uses GHL's contacts/smartlist service and its captured OR-of-AND filter envelope. `tagFilters` is the common case: each entry is a list of tag names the contact must ALL carry. For anything else pass `rawFilters` (leaf objects: {field, operator, value, options}). NOTE: create_smart_list (the older tool) targets the opportunity-list service and cannot express contact filters.",
+    {
+      name: import_zod48.z.string().describe("Display name for the smart list."),
+      tagFilters: import_zod48.z.array(import_zod48.z.array(import_zod48.z.string())).optional().describe('Tag conditions. Each inner array is one filter requiring ALL those tags, e.g. [["escalated"]] for "has the escalated tag".'),
+      rawFilters: import_zod48.z.array(import_zod48.z.record(import_zod48.z.unknown())).optional().describe("Advanced: raw filter leaves {field, operator, value, options}. Combined with tagFilters into one AND group."),
+      locationId: import_zod48.z.string().optional().describe("Location ID. Falls back to the active builder client's location.")
+    },
+    async ({ name, tagFilters, rawFilters, locationId: locationId2 }) => {
+      try {
+        const loc = locationId2 ?? client.locationId;
+        const filters = [
+          ...(tagFilters ?? []).map((tags) => buildContactTagFilter(tags)),
+          ...rawFilters ?? []
+        ];
+        const body = buildContactSmartListBody({ listName: name, locationId: loc, filters });
+        const headers = await client.buildHeaders();
+        const res = await fetch(CONTACT_SMARTLIST_BASE, { method: "POST", headers, body: JSON.stringify(body) });
+        if (!res.ok) throw new Error(`Smart Lists API Error ${res.status}: POST /contacts/smartlist
+${await res.text()}`);
+        return jsonResponse(JSON.parse(await res.text() || "{}"));
+      } catch (error) {
+        return errorResponse(error);
+      }
+    }
+  );
+  server2.tool(
+    "get_contact_smart_list",
+    "Get a CONTACT smart list by id INCLUDING its filterSpecs. Use this to verify a contact smart list's filters after creating it \u2014 get_smart_list targets the opportunity-list service and returns the record without any filters, which reads as 'no filters set'.",
+    {
+      listId: import_zod48.z.string().describe("The contact smart list id.")
+    },
+    async ({ listId }) => {
+      try {
+        const headers = await client.buildHeaders();
+        const res = await fetch(`${CONTACT_SMARTLIST_BASE}/${listId}?transform=true`, { headers });
+        if (!res.ok) throw new Error(`Smart Lists API Error ${res.status}: GET /contacts/smartlist/${listId}
+${await res.text()}`);
+        return jsonResponse(JSON.parse(await res.text() || "{}"));
+      } catch (error) {
+        return errorResponse(error);
+      }
+    }
+  );
+  server2.tool(
+    "delete_contact_smart_list",
+    "Delete a CONTACT smart list by id.",
+    {
+      listId: import_zod48.z.string().describe("The contact smart list id."),
+      confirm: import_zod48.z.literal("DELETE").describe('Type "DELETE" to confirm.')
+    },
+    async ({ listId }) => {
+      try {
+        const headers = await client.buildHeaders();
+        const res = await fetch(CONTACT_SMARTLIST_DELETE, {
+          method: "POST",
+          headers,
+          body: JSON.stringify({ smartlist_id: listId })
+        });
+        if (!res.ok) throw new Error(`Smart Lists API Error ${res.status}: POST /smartlist/delete
+${await res.text()}`);
+        return jsonResponse(JSON.parse(await res.text() || "{}"));
+      } catch (error) {
+        return errorResponse(error);
+      }
+    }
+  );
   server2.tool(
     "get_smart_list",
     "Get a single smart list by ID with its full configuration: filters, columns, permissions, and metadata. The filters array is what defines who/what is in the list.",
@@ -16320,6 +16483,8 @@ var findOpportunitySchema = import_zod58.z.object({
 });
 var actionSchema = import_zod58.z.discriminatedUnion("type", [...branchActionOptions, findOpportunitySchema]);
 var APPOINTMENT_STATUSES = ["new", "confirmed", "showed", "noshow", "cancelled", "invalid"];
+var CALL_STATUSES = ["busy", "canceled", "voicemail", "no-answer", "completed"];
+var NUMBER_VALIDATION_STATES = ["not_valid", "sms_incapable"];
 var triggerSchema = import_zod58.z.object({
   type: import_zod58.z.string(),
   formRef: nsRef("form").optional(),
@@ -16328,7 +16493,34 @@ var triggerSchema = import_zod58.z.object({
   pipelineRef: nsRef("pipeline").optional(),
   stageRef: nsRef("stage").optional(),
   // Required for a native `appointment` trigger (the status it fires on).
-  appointmentStatus: import_zod58.z.enum(APPOINTMENT_STATUSES).optional()
+  appointmentStatus: import_zod58.z.enum(APPOINTMENT_STATUSES).optional(),
+  // ── customer_reply scoping ──────────────────────────────────────
+  // A bare customer_reply trigger fires on EVERY inbound reply from EVERY
+  // contact. That is almost never what a plan means: "alert the owner when a
+  // referral partner replies" must not fire for a family's reply. GHL's
+  // ContactReplyFilter supports both of these (see templates/trigger-schemas.json):
+  //   hasTagRef   → contact.tags / index-of-true  (only replies from contacts
+  //                 carrying this tag)
+  //   replyIntent → message.body / matches_intent (GHL classifies the reply as
+  //                 a positive or negative response; the option values are
+  //                 "schedule-yes" and "schedule-no")
+  // Both optional and additive — omitting them keeps the long-standing
+  // fires-on-any-reply baseline.
+  hasTagRef: nsRef("tag").optional(),
+  replyIntent: import_zod58.z.enum(["positive", "negative"]).optional(),
+  // ── call_status scoping (missed-call text-back) ─────────────────
+  // GHL's call_status trigger fires on a completed call attempt. The states it
+  // exposes are exactly what a "missed call" means operationally. Required for
+  // a call_status trigger — without them the trigger would fire on EVERY call
+  // including answered ones, so the executor refuses rather than guess.
+  callStatuses: import_zod58.z.array(import_zod58.z.enum(CALL_STATUSES)).optional(),
+  callDirection: import_zod58.z.enum(["inbound", "outbound"]).optional(),
+  // ── validation_error (GHL UI: "Number validation") ──────────────
+  // Fires after a phone number passes or fails a validation check. The UI shows
+  // "Not valid" / "SMS incapable"; the WIRE values are snake_case. Required for
+  // a validation_error trigger — without them the executor refuses rather than
+  // guess which failure states to fire on.
+  numberValidation: import_zod58.z.array(import_zod58.z.enum(NUMBER_VALIDATION_STATES)).optional()
 });
 var workflowSchema = import_zod58.z.object({
   ref: nsRef("workflow"),
@@ -16447,6 +16639,7 @@ function checkRefIntegrity(plan, defined) {
       const t = w.trigger;
       check(t.formRef, "form", `workflows[${w.ref}].trigger.formRef`);
       check(t.tagRef, "tag", `workflows[${w.ref}].trigger.tagRef`);
+      check(t.hasTagRef, "tag", `workflows[${w.ref}].trigger.hasTagRef`);
       check(t.calendarRef, "calendar", `workflows[${w.ref}].trigger.calendarRef`);
       check(t.pipelineRef, "pipeline", `workflows[${w.ref}].trigger.pipelineRef`);
       check(t.stageRef, "stage", `workflows[${w.ref}].trigger.stageRef`);
@@ -16609,6 +16802,21 @@ function validateBuildPlan(input) {
       );
     }
   }
+  for (const wf of plan.workflows ?? []) {
+    let seenFind = false;
+    for (const a of wf.actions) {
+      if (a.type === "find_opportunity") {
+        seenFind = true;
+        continue;
+      }
+      if (a.type === "update_opportunity" && !seenFind) {
+        warnings.push(
+          `workflow "${wf.ref}" has an update_opportunity ("move to stage") with no find_opportunity before it \u2014 GHL updates the opportunity currently in workflow context, so with nothing loaded this action SILENTLY DOES NOTHING and the workflow carries on as if it worked. Put the move inside a find_opportunity "found" branch.`
+        );
+        break;
+      }
+    }
+  }
   const MAX_NODES = 40;
   for (const wf of plan.workflows ?? []) {
     let nodeCount = 0;
@@ -17158,18 +17366,87 @@ function expandTrigger(trigger, idx, idMap) {
     case "appointment": {
       const status = trigger.appointmentStatus;
       if (!status) return manual(`Set this workflow's appointment trigger in the GHL UI: ${triggerPlainEnglish(trigger, idx)} (the plan trigger has no appointmentStatus to fire on, e.g. confirmed / noshow).`);
+      const conditions = [
+        { operator: "==", field: "appointment.eventType", value: "normal", title: "Event Type", type: "select" },
+        { operator: "==", field: "appointment.status", value: status, title: "Appointment status is", type: "select" }
+      ];
+      const pending = [];
+      if (trigger.calendarRef) {
+        const calendarId = resolveId(trigger.calendarRef, idMap);
+        if (isPending(calendarId)) pending.push(trigger.calendarRef);
+        conditions.unshift({
+          operator: "==",
+          field: "calendar.id",
+          value: calendarId,
+          title: "In calendar",
+          type: "select"
+        });
+      }
       return native({
         name: `Appointment Status \u2014 ${status}`,
         type: "appointment",
+        conditions
+      }, pending);
+    }
+    case "call_status": {
+      const statuses = trigger.callStatuses;
+      if (!statuses || statuses.length === 0) {
+        return manual(
+          `Set this workflow's call trigger in the GHL UI and choose which call outcomes it fires on (e.g. no-answer, busy, voicemail for a missed call). Blueprint will not build it without them: an unscoped call trigger fires on EVERY call, answered ones included.`
+        );
+      }
+      const callConditions = [
+        { operator: "contains-any", field: "call_status", value: statuses, title: "Call Status" }
+      ];
+      if (trigger.callDirection) {
+        callConditions.push({
+          operator: "==",
+          field: "message.direction",
+          value: trigger.callDirection,
+          title: "Call Direction",
+          type: "select"
+        });
+      }
+      return native({ name: "Call Status", type: "call_status", conditions: callConditions });
+    }
+    case "validation_error": {
+      const states = trigger.numberValidation;
+      if (!states || states.length === 0) {
+        return manual(
+          `Set this workflow's "Number validation" trigger in the GHL UI and choose which states it fires on (Not valid / SMS incapable). Blueprint will not build it without them rather than guess which failures matter.`
+        );
+      }
+      return native({
+        name: "Number Validation",
+        type: "validation_error",
         conditions: [
-          { operator: "==", field: "appointment.eventType", value: "normal", title: "Event Type", type: "select" },
-          { operator: "==", field: "appointment.status", value: status, title: "Appointment status is", type: "select" }
+          { operator: "contains-any", field: "contact.phoneInfo", value: states, title: "Number is", type: "multiselect" }
         ]
       });
     }
     case "customer_reply":
     case "contact_replied": {
-      return native({ name: "Customer Replied", type: "customer_reply", conditions: [] });
+      const replyConditions = [];
+      if (trigger.hasTagRef) {
+        const tagName = idx.tagName.get(trigger.hasTagRef) ?? trigger.hasTagRef;
+        replyConditions.push({
+          operator: "index-of-true",
+          field: "contact.tags",
+          value: tagName,
+          title: "Has Tag",
+          type: "select"
+        });
+      }
+      if (trigger.replyIntent) {
+        replyConditions.push({
+          operator: "matches_intent",
+          field: "message.body",
+          value: trigger.replyIntent === "positive" ? "schedule-yes" : "schedule-no",
+          title: "Intent type",
+          type: "select"
+        });
+      }
+      return native({ name: "Customer Replied", type: "customer_reply", conditions: replyConditions });
     }
     case "pipeline_stage_updated": {
       if (!trigger.pipelineRef || !trigger.stageRef) return manual("Set this workflow's pipeline-stage trigger in the GHL UI (the plan trigger needs both a pipeline and a stage).");

package/guide/guide.html

@@ -4,7 +4,7 @@
 <meta charset="utf-8">
 <meta name="viewport" content="width=device-width, initial-scale=1">
 <title>GHL Command — User Guide</title>
-<!-- guides-hash: 6ffc57aa1224244f -->
+<!-- guides-hash: f8bcba4d92d295fa -->
 <style>
 :root{
   --bg:#F2F4F6; --surface:#FFFFFF; --ink:#1C2833; --muted:#5B6B78; --line:#DDE3E8;
@@ -173,14 +173,14 @@ main{max-width:1180px}
   </div>
   <div class="catsec"><h2>Getting set up</h2><div class="cards"><a class="card pub" href="#g-install-ghl-command" data-k="install connect setup start windows mac workflow builder browser login step 2 full version"><h3>Install GHL Command</h3><p>One install, two short steps, whether you are on the Free plan or the full license. Nothing left to add later.</p><div class="meta"><span class="pill free">Free plan</span><span class="time">~6 minutes</span><span class="open">Read below &#8595;</span></div></a>
 <a class="card pub" href="#g-switch-between-client-accounts" data-k="switch subaccount sub-account location client account change which account wrong account"><h3>Switch between client accounts</h3><p>Point Claude at any of your sub-accounts by name, and confirm which one is active.</p><div class="meta"><span class="pill free">Free plan</span><span class="time">~10 seconds</span><span class="open">Read below &#8595;</span></div></a></div></div>
-<div class="catsec"><h2>Contacts and leads</h2><div class="cards"><a class="card pub" href="#g-bulk-tag-and-clean-up" data-k="bulk tag untag update clean duplicates many contacts segment mass"><h3>Bulk tag and clean up</h3><p>Tag, untag, or update hundreds of contacts in one instruction.</p><div class="meta"><span class="pill full">Full license</span><span class="time">~2 minutes</span><span class="open">Read below &#8595;</span></div></a>
+<div class="catsec"><h2>Contacts and leads</h2><div class="cards"><a class="card pub" href="#g-bulk-tag-and-clean-up" data-k="bulk tag untag update clean duplicates many contacts segment mass smart list saved list view"><h3>Bulk tag and clean up</h3><p>Tag, untag, or update hundreds of contacts in one instruction, then save the group as a list.</p><div class="meta"><span class="pill full">Full license</span><span class="time">~2 minutes</span><span class="open">Read below &#8595;</span></div></a>
 <a class="card pub" href="#g-count-and-report-contacts" data-k="count how many contacts report number leads week month total added"><h3>Count and report your contacts</h3><p>Ask for a number, get the real number, with the date range printed next to it.</p><div class="meta"><span class="pill free">Free plan</span><span class="time">~10 seconds</span><span class="open">Read below &#8595;</span></div></a>
 <a class="card pub" href="#g-find-and-list-contacts" data-k="list find contacts export spreadsheet csv excel search leads who signed up"><h3>Find and list contacts</h3><p>Pull a clean list into a spreadsheet you can open in Excel or Google Sheets.</p><div class="meta"><span class="pill free">Free plan</span><span class="time">~1 minute</span><span class="open">Read below &#8595;</span></div></a>
 <a class="card pub" href="#g-weekly-account-report" data-k="weekly report account snapshot health summary how are we doing client report monday"><h3>Weekly account report</h3><p>One ask, a full snapshot of the account's week: leads, pipeline, and conversations.</p><div class="meta"><span class="pill free">Free plan</span><span class="time">~1 minute</span><span class="open">Read below &#8595;</span></div></a></div></div>
 <div class="catsec"><h2>Automations</h2><div class="cards"><a class="card pub" href="#g-add-an-exit-workflow" data-k="exit workflow remove stop replied tag note notify pull out stop texting"><h3>Add an exit workflow</h3><p>Cleanly pull people out of a sequence when they reply, tag them, and get you notified.</p><div class="meta"><span class="pill full">Full license</span><span class="time">~5 minutes</span><span class="open">Read below &#8595;</span></div></a>
 <a class="card pub" href="#g-audit-your-workflows" data-k="audit workflows broken silent failure check review existing validate not sending nothing happens"><h3>Audit your workflows</h3><p>Find silent failures and dead ends in existing workflows before your client does.</p><div class="meta"><span class="pill free">Free plan</span><span class="time">~2 minutes</span><span class="open">Read below &#8595;</span></div></a>
 <a class="card pub" href="#g-branch-on-tags-and-fields" data-k="if else branch condition vip tag field split two paths different message"><h3>Branch on tags and fields</h3><p>If they are a VIP, send this. Otherwise, send that. Built correctly the first time.</p><div class="meta"><span class="pill full">Full license</span><span class="time">~5 minutes</span><span class="open">Read below &#8595;</span></div></a>
-<a class="card pub" href="#g-build-nurture-sequence" data-k="nurture sequence drip texts emails follow up workflow build"><h3>Build a nurture sequence</h3><p>A follow-up machine that texts, emails, waits, and stops the second someone replies.</p><div class="meta"><span class="pill full">Full license</span><span class="time">~15 minutes</span><span class="open">Read below &#8595;</span></div></a></div></div>
+<a class="card pub" href="#g-build-nurture-sequence" data-k="nurture sequence drip texts emails follow up workflow build quiet hours sending window contact hours"><h3>Build a nurture sequence</h3><p>A follow-up machine that texts, emails, waits, and stops the second someone replies.</p><div class="meta"><span class="pill full">Full license</span><span class="time">~15 minutes</span><span class="open">Read below &#8595;</span></div></a></div></div>
 <div class="catsec"><h2>Pipelines and sales</h2><div class="cards"><a class="card pub" href="#g-documents-and-contracts" data-k="documents contracts proposals signature send sign agreement esign template"><h3>Documents and contracts</h3><p>Proposals and contracts sent for signature and tracked from Claude.</p><div class="meta"><span class="pill full">Full license</span><span class="time">~5 minutes</span><span class="open">Read below &#8595;</span></div></a>
 <a class="card pub" href="#g-stand-up-a-pipeline" data-k="pipeline stages create new client setup opportunity sales process deal stages"><h3>Stand up a pipeline</h3><p>Stages, fields, and tags for a new client in one conversation.</p><div class="meta"><span class="pill full">Full license</span><span class="time">~10 minutes</span><span class="open">Read below &#8595;</span></div></a>
 <a class="card pub" href="#g-track-and-move-opportunities" data-k="opportunities deals move stage track stuck value won lost pipeline board"><h3>Track and move opportunities</h3><p>Move deals between stages, update values, and see what is stuck.</p><div class="meta"><span class="pill full">Full license</span><span class="time">~1 minute</span><span class="open">Read below &#8595;</span></div></a>
@@ -189,7 +189,7 @@ main{max-width:1180px}
 <button class="card locked" type="button" data-k="page studio compose website landing pages funnel" data-toast="This guide arrives in a product update — your install picks it up automatically." title="Coming in a product update." aria-label="Page Studio: pages and sites. Coming in a product update."><h3>Page Studio: pages and sites</h3><p>Compose landing pages and full sites that render correctly in GHL.</p><div class="meta"><span class="pill full">Full license</span><span class="time">~20 min</span><span class="applabel">Coming in an update</span></div></button>
 <button class="card locked" type="button" data-k="clone site copy rebrand landing page existing url" data-toast="This guide arrives in a product update — your install picks it up automatically." title="Coming in a product update." aria-label="Clone and rebrand a site. Coming in a product update."><h3>Clone and rebrand a site</h3><p>Rebuild an existing page for a new client, with a rights check and a review report.</p><div class="meta"><span class="pill full">Full license</span><span class="time">~30 min</span><span class="applabel">Coming in an update</span></div></button></div></div>
 <div class="catsec"><h2>Booking and calendars</h2><div class="cards"><a class="card pub" href="#g-see-and-manage-appointments" data-k="appointments today schedule upcoming who is booked list no show cancel reschedule diary"><h3>See and manage appointments</h3><p>Who is booked today, this week, or for a specific client, in one ask.</p><div class="meta"><span class="pill free">Free plan</span><span class="time">~10 seconds</span><span class="open">Read below &#8595;</span></div></a>
-<a class="card pub" href="#g-set-up-a-booking-calendar" data-k="calendar create booking consult slots availability buffer appointment types schedule"><h3>Set up a booking calendar</h3><p>A consult calendar with the right slots, buffers, and the right person attached.</p><div class="meta"><span class="pill full">Full license</span><span class="time">~10 minutes</span><span class="open">Read below &#8595;</span></div></a></div></div>
+<a class="card pub" href="#g-set-up-a-booking-calendar" data-k="calendar create booking consult slots availability buffer appointment types schedule daily limit notice same day"><h3>Set up a booking calendar</h3><p>A consult calendar with the right slots, buffers, and the right person attached.</p><div class="meta"><span class="pill full">Full license</span><span class="time">~10 minutes</span><span class="open">Read below &#8595;</span></div></a></div></div>
 <div class="catsec"><h2>Email and SMS</h2><div class="cards"><a class="card pub" href="#g-build-email-templates" data-k="email template design create campaign builder reusable branded rename archive"><h3>Build email templates</h3><p>Reusable, branded templates created and edited without the GHL editor.</p><div class="meta"><span class="pill full">Full license</span><span class="time">~10 minutes</span><span class="open">Read below &#8595;</span></div></a>
 <a class="card pub" href="#g-review-your-conversations" data-k="conversations inbox read unread replies check messages who replied catch up missed"><h3>Review your conversations</h3><p>Catch up on replies and unread threads across every channel.</p><div class="meta"><span class="pill free">Free plan</span><span class="time">~1 minute</span><span class="open">Read below &#8595;</span></div></a>
 <a class="card pub" href="#g-send-texts-and-emails" data-k="send message text sms email contact reply conversation follow up one off"><h3>Send texts and emails</h3><p>Message any contact from Claude, in your voice, on the right channel.</p><div class="meta"><span class="pill full">Full license</span><span class="time">~30 seconds</span><span class="open">Read below &#8595;</span></div></a></div></div>
@@ -490,16 +490,19 @@ When it saves, list the templates in the account so I can see it landed, and tel
 <ul>
 <li>A ready-to-review workflow in your GHL account: texts, emails, and waits in the right order, every message written out.</li>
 <li>Stop-on-reply built in, so nobody gets a robot follow-up after a human conversation has started.</li>
+<li>Quiet hours, so the sequence never texts somebody at two in the morning because a wait timer landed there.</li>
 <li>A matching exit workflow: when someone replies, they leave the nurture, get tagged, and you get notified.</li>
 </ul>
 </div>
 <div class="gsec"><h2>Quick start</h2>
 <div class="prompt"><q>Build a 7-day nurture for new leads: text right away, email an hour later, then follow up daily until they reply.</q><button class="copy" type="button">Copy</button></div>
+<div class="prompt"><q>Only let this workflow send between 8am and 9pm.</q><button class="copy" type="button">Copy</button></div>
 <div class="prompt"><q>Show me the full plan first. Do not build anything until I approve it.</q><button class="copy" type="button">Copy</button></div>
 </div>
 <div class="gsec"><h2>The pro prompt</h2>
 <div class="pro"><div class="pro-head"><b>The exact ask we run on real client accounts</b><span class="pill full">Proven live</span><button class="copy" type="button">Copy</button></div><p class="pro-body">Build a nurture workflow in my [Radiance Med Spa] account called &quot;New Lead Nurture 7 Day&quot;. Trigger: when the tag [new-lead] is added.
 The sequence: (1) Immediately, text: &quot;Hi {{first name}}, this is [Dana] from [Radiance Med Spa]. Thanks for reaching out about our [body contouring special]! Want me to grab you a free consult this week?&quot; (2) Wait 1 hour, then send an email, subject &quot;Your consult is waiting&quot;, friendly, three short paragraphs, one button to my booking link. (3) Wait 1 day, then text a soft check-in. (4) Wait 2 days, then email a before-and-after story from a real client. (5) Wait 3 days, then text a last-call message about the special ending.
+Set quiet hours on this workflow: it may only send between [8am] and [9pm], [every day]. Nothing goes out outside that window.
 Stop the sequence the moment they reply on any channel. Also build the exit workflow: when they reply, remove them from the nurture, tag them [warm-lead], add a note with what they said, and notify me.
 Before you build anything: show me every message written out for my approval, and verify my account's real pipeline, tag, and calendar IDs so nothing fails silently.</p></div>
 <p class="gpara">Everything in [brackets] is yours to change. The last paragraph is the safety net: it makes Claude plan first and check your account's real setup before touching it.</p>
@@ -521,6 +524,8 @@ Before you build anything: show me every message written out for my approval, an
 <div class="fnode"><span class="tag em">Email</span>before-and-after story</div>
 <div class="fconn"></div>
 <div class="fnode"><span class="tag sms">Text</span>last call</div>
+<div class="fconn"></div>
+<div class="fnode"><span class="tag wait">QUIET HOURS: nothing sends outside 8am to 9pm, whenever a wait timer lands</span>then</div>
 <div class="fstop">the whole track stops the moment they reply, on any channel</div>
 </div>
 </div>
@@ -533,13 +538,17 @@ Before you build anything: show me every message written out for my approval, an
 </div>
 <div class="gsec"><h2>Good to know</h2>
 <ul>
+<li>Ask for quiet hours on anything that sends texts. Wait timers do not care what time it is: a one-day wait started at 11pm fires at 11pm. A window of 8am to 9pm is the common answer, and it is set per workflow, so every sequence that texts needs its own.</li>
+<li>Quiet hours are the only place a sending window lives. There is no time-of-day setting inside the AI agent builders, so if a bot hands off to a workflow, this is what protects the handoff.</li>
+<li>Once set, quiet hours stay set. Edit a message or add a step later and the window comes through untouched.</li>
 <li>GHL's editor struggles past about 40 steps in one workflow. Claude knows this and splits long sequences automatically.</li>
 <li>Messages come out in your voice if you give Claude a sample first: paste one text you would actually send and say &quot;write like this&quot;.</li>
 <li>The nurture and its exit workflow are a pair. If you ever remove one, ask Claude to update the other, so nothing points at a workflow that is gone.</li>
+<li>If a step in your sequence moves a deal to a new stage, it needs to find that deal first. Say &quot;look up the opportunity, then move it&quot; and Claude wires both. A move on its own saves cleanly and then does nothing.</li>
 </ul>
 </div>
 <div class="gsec"><h2>Where people go wrong</h2>
-<div style="overflow-x:auto"><table class="wrongtbl"><tr><th>What happened</th><th>The fix</th></tr><tr><td>&quot;It built the workflow but nothing ever sends.&quot;</td><td>Say &quot;audit this workflow&quot;. GHL fails silently when something inside is misconfigured; the audit finds it in seconds.</td></tr><tr><td>&quot;The messages sound generic.&quot;</td><td>Give Claude your voice before building: paste a real text you have sent and say &quot;write like this&quot;.</td></tr><tr><td>&quot;I want to change one message.&quot;</td><td>Say &quot;update step 3's text to...&quot; and never rebuild from scratch. Updates keep everything connected.</td></tr></table></div>
+<div style="overflow-x:auto"><table class="wrongtbl"><tr><th>What happened</th><th>The fix</th></tr><tr><td>&quot;It built the workflow but nothing ever sends.&quot;</td><td>Say &quot;audit this workflow&quot;. GHL fails silently when something inside is misconfigured; the audit finds it in seconds.</td></tr><tr><td>&quot;A text went out at 3am.&quot;</td><td>The workflow has no quiet hours. Say &quot;only let this workflow send between 8am and 9pm&quot; and Claude sets the window.</td></tr><tr><td>&quot;I set quiet hours and later they were gone.&quot;</td><td>Versions before 3.65.0 dropped the window whenever the workflow was saved again. Open any workflow that texts, check its window, and set it once more. From 3.65.0 on it survives every later edit.</td></tr><tr><td>&quot;The messages sound generic.&quot;</td><td>Give Claude your voice before building: paste a real text you have sent and say &quot;write like this&quot;.</td></tr><tr><td>&quot;I want to change one message.&quot;</td><td>Say &quot;update step 3's text to...&quot; and never rebuild from scratch. Updates keep everything connected.</td></tr></table></div>
 </div>
 <div class="gsec"><h2>Related guides</h2>
 <ul>
@@ -552,19 +561,21 @@ Before you build anything: show me every message written out for my approval, an
 
 <section class="gview" id="g-bulk-tag-and-clean-up">
   <h1 class="gtitle serif">Bulk tag and clean up</h1>
-  <p class="gpromise">Tag, untag, or update hundreds of contacts in one instruction.</p>
+  <p class="gpromise">Tag, untag, or update hundreds of contacts in one instruction, then save the group as a list.</p>
   <div class="gmeta"><span class="pill full">Full license</span><span class="time">~2 minutes</span><span class="time">Works in Claude Desktop and Claude Code</span></div>
   <div class="gsec"><h2>What you'll get</h2>
 <ul>
 <li>One instruction that tags, untags, or updates a whole group of contacts at once.</li>
 <li>A count of exactly who is about to be touched, before anything is touched.</li>
 <li>A report of what actually landed: how many succeeded, how many failed, out of how many.</li>
+<li>The group saved as a list you can open in GHL any day, instead of rebuilding the same filter every week.</li>
 </ul>
 </div>
 <div class="gsec"><h2>Say this</h2>
 <div class="prompt"><q>Tag everyone who came in from the September ad as september-lead.</q><button class="copy" type="button">Copy</button></div>
 <div class="prompt"><q>Remove the cold-lead tag from anyone who has replied to us.</q><button class="copy" type="button">Copy</button></div>
 <div class="prompt"><q>Tag these twelve contacts as needs-follow-up.</q><button class="copy" type="button">Copy</button></div>
+<div class="prompt"><q>Save everyone tagged needs-follow-up as a list called Needs Follow Up.</q><button class="copy" type="button">Copy</button></div>
 </div>
 <div class="gsec"><h2>The pro prompt</h2>
 <div class="pro"><div class="pro-head"><b>The exact ask we run on real client accounts</b><span class="pill full">Proven live</span><button class="copy" type="button">Copy</button></div><p class="pro-body">In my [Radiance Med Spa] account, find every contact tagged [website-lead] that also has [no tag of consult-booked].
@@ -573,11 +584,19 @@ Once I say go: add the tag [needs-follow-up] to all of them, then tell me how ma
 Do not delete anything, do not send anything, and do not change any other field.</p></div>
 <p class="gpara">Everything in [brackets] is yours to change. The two safety lines matter more than the rest: Claude counts and stops before it touches anything, and the last line rules out everything you did not ask for.</p>
 </div>
+<div class="gsec"><h2>Save the group as a list</h2>
+<p class="gpara">Tagging answers &quot;who needs chasing today&quot;. A saved list answers it again next Monday without you rebuilding the filter. Once a group is tagged, ask Claude to save it.</p>
+<div class="pro"><div class="pro-head"><b>The exact ask we run on real client accounts</b><span class="pill full">Proven live</span><button class="copy" type="button">Copy</button></div><p class="pro-body">In my [Radiance Med Spa] account, save a contact list called &quot;[Needs Follow Up]&quot; that shows everyone tagged [needs-follow-up].
+Read it back to me once it is saved so I know it exists, and tell me where to find it in GHL.
+Do not change any contact, and do not delete any list that is already there.</p></div>
+<p class="gpara">The list appears in your contacts view in GHL like any other saved list. Ask Claude to delete one by name when a campaign is over.</p>
+</div>
 <div class="gsec"><h2>What happens when you ask</h2>
 <ol class="steps">
 <li>Claude builds the group and tells you the size, with a few examples so you can spot a mistake.</li>
 <li>You approve, or you narrow it. Nothing has changed yet.</li>
 <li>Claude applies the change in batches and reports back what actually landed.</li>
+<li>If you asked for a saved list, it creates it and reads it back so you can see it exists.</li>
 </ol>
 </div>
 <div class="gsec"><h2>Good to know</h2>
@@ -585,11 +604,13 @@ Do not delete anything, do not send anything, and do not change any other field.
 <li>Ask for the count first, every time. It is the difference between tagging 40 people and tagging 4,000.</li>
 <li>Bulk delete is real, and it does not come back. Claude will make you confirm, and it is worth reading that message twice.</li>
 <li>Tags are the backbone of GHL automation. Tag now, and your workflows have something to trigger on later.</li>
+<li>Saved lists are built from conditions, not from a frozen set of names. Tag somebody tomorrow and they appear in the list on their own.</li>
+<li>Saving lists needs version 3.65.0 or later. In every version before it, the list tools reported success and quietly created nothing, so if you tried this before and found nothing in GHL, that is why. Ask Claude &quot;what version are you running&quot; if you are not sure.</li>
 <li>Bulk changes need the full license. The Free plan can find and count the group, but not change it.</li>
 </ul>
 </div>
 <div class="gsec"><h2>Where people go wrong</h2>
-<div style="overflow-x:auto"><table class="wrongtbl"><tr><th>What happened</th><th>The fix</th></tr><tr><td>&quot;It tagged more people than I meant.&quot;</td><td>Always ask for the count and the examples first. Approve after you see them, not before.</td></tr><tr><td>&quot;I asked for duplicates to be merged.&quot;</td><td>GHL does not merge from the outside. Claude can find likely duplicates and list them, then you merge in GHL.</td></tr><tr><td>&quot;The tags are not showing in GHL yet.&quot;</td><td>GHL's contact index lags a few seconds behind. The report of what succeeded is the truth; the list view catches up.</td></tr></table></div>
+<div style="overflow-x:auto"><table class="wrongtbl"><tr><th>What happened</th><th>The fix</th></tr><tr><td>&quot;It tagged more people than I meant.&quot;</td><td>Always ask for the count and the examples first. Approve after you see them, not before.</td></tr><tr><td>&quot;I saved a list before and it never showed up in GHL.&quot;</td><td>Versions before 3.65.0 could not actually save lists, though they said they had. Update, then ask again.</td></tr><tr><td>&quot;I asked for duplicates to be merged.&quot;</td><td>GHL does not merge from the outside. Claude can find likely duplicates and list them, then you merge in GHL.</td></tr><tr><td>&quot;The tags are not showing in GHL yet.&quot;</td><td>GHL's contact index lags a few seconds behind. The report of what succeeded is the truth; the list view catches up.</td></tr></table></div>
 </div>
 <div class="gsec"><h2>Related guides</h2>
 <ul>
@@ -1040,18 +1061,21 @@ Before you send: confirm the exact contact you matched, show me their phone numb
   <div class="gsec"><h2>What you'll get</h2>
 <ul>
 <li>A booking calendar with real opening hours, appointment length, and gaps between appointments.</li>
+<li>A daily booking cap and a minimum notice period, so a full day stays full and nobody books your next hour.</li>
 <li>The right person attached to it, which is the step that quietly breaks calendars built in a hurry.</li>
 <li>A read-back of what actually saved, plus the next available slots so you know it is bookable.</li>
 </ul>
 </div>
 <div class="gsec"><h2>Say this</h2>
 <div class="prompt"><q>Create a 30-minute consult calendar, weekdays 9 to 5, with a 15-minute gap between appointments.</q><button class="copy" type="button">Copy</button></div>
+<div class="prompt"><q>Cap the consult calendar at 6 bookings a day and require 24 hours notice.</q><button class="copy" type="button">Copy</button></div>
 <div class="prompt"><q>Show me the calendars in this account.</q><button class="copy" type="button">Copy</button></div>
 <div class="prompt"><q>What slots are free on the consult calendar this week?</q><button class="copy" type="button">Copy</button></div>
 </div>
 <div class="gsec"><h2>The pro prompt</h2>
 <div class="pro"><div class="pro-head"><b>The exact ask we run on real client accounts</b><span class="pill full">Proven live</span><button class="copy" type="button">Copy</button></div><p class="pro-body">In my [MCP Testing] account, create a booking calendar called &quot;[Free Consult]&quot;.
 Appointments are [30] minutes, available [Monday to Friday, 9am to 5pm] in the account's timezone, with a [15] minute gap between appointments.
+Cap it at [6] bookings a day, and require at least [24] hours notice so nobody books the same morning.
 Attach it to [me], and look up my real user record in this account rather than guessing at a name.
 When it saves, read the calendar back to me and show me the next five bookable slots so I know it is genuinely open for business.</p></div>
 <p class="gpara">Everything in [brackets] is yours to change. Asking for the next five slots at the end is the whole test. A calendar that saves but offers no slots looks perfect and books nobody.</p>
@@ -1059,21 +1083,23 @@ When it saves, read the calendar back to me and show me the next five bookable s
 <div class="gsec"><h2>What happens when you ask</h2>
 <ol class="steps">
 <li>Claude looks up the real user in the account so the calendar has an owner who exists.</li>
-<li>It creates the calendar with your hours, length, gaps, and notice period.</li>
+<li>It creates the calendar with your hours, length, gaps, daily cap, and notice period.</li>
 <li>It reads the calendar back and pulls the next available slots so you can see it is live.</li>
 </ol>
 </div>
 <div class="gsec"><h2>Good to know</h2>
 <ul>
 <li>Say who the appointments belong to. A calendar with nobody attached will happily save and then show no availability.</li>
+<li>Ask for the daily cap and the notice period in the same breath as the hours. Six bookings protects a clinic day that also has patients in it, and twenty-four hours notice is what stops someone taking your next open slot while you are still in a room.</li>
 <li>Timezones follow the sub-account's setting. If the account is set to the wrong city, every slot is wrong. Check that first on a new client account.</li>
 <li>Round robin calendars, where several staff share the bookings, need each person listed. Name them all in the ask. On that type, a slot only opens if the calendar hours AND that person's own working hours both allow it, so a Saturday window needs somebody who works Saturdays.</li>
-<li>Two settings live in GHL's calendar screen and not here: how much notice someone must give before booking, and the confirmation and reminder messages. Set those once in GHL. If you want real control over reminder wording, ask Claude for a reminder workflow instead.</li>
+<li>Changing one setting later leaves the others alone. Rename a calendar or raise its daily cap and the slot length, the gaps and the opening hours all stay exactly as you left them.</li>
+<li>Confirmation and reminder messages still live on GHL's calendar screen. Set those once in GHL. If you want real control over reminder wording, ask Claude for a reminder workflow instead.</li>
 <li>Needs the full license.</li>
 </ul>
 </div>
 <div class="gsec"><h2>Where people go wrong</h2>
-<div style="overflow-x:auto"><table class="wrongtbl"><tr><th>What happened</th><th>The fix</th></tr><tr><td>&quot;The calendar exists but shows no times.&quot;</td><td>Nobody is attached to it, or the hours fall outside the account's timezone. Ask for the next five slots and Claude will show you which it is.</td></tr><tr><td>&quot;Clients are booking with no notice.&quot;</td><td>The minimum-notice setting is on GHL's calendar screen, not something Claude sets. Open the calendar in GHL and set it once.</td></tr><tr><td>&quot;Appointments are back to back.&quot;</td><td>Ask for a gap between appointments. Fifteen minutes is the usual answer for a clinic.</td></tr></table></div>
+<div style="overflow-x:auto"><table class="wrongtbl"><tr><th>What happened</th><th>The fix</th></tr><tr><td>&quot;The calendar exists but shows no times.&quot;</td><td>Nobody is attached to it, or the hours fall outside the account's timezone. Ask for the next five slots and Claude will show you which it is.</td></tr><tr><td>&quot;Clients are booking with no notice.&quot;</td><td>Say how much notice you want and Claude sets it on the calendar. Twenty-four hours is the usual answer for a consult.</td></tr><tr><td>&quot;One busy day swallowed my whole week.&quot;</td><td>Ask for a daily cap. It limits how many bookings a single day can take, no matter how many hours are open.</td></tr><tr><td>&quot;My slot lengths and opening hours went back to defaults on their own.&quot;</td><td>Versions before 3.65.0 could reset untouched settings when you changed a different one. Ask Claude to read the calendar back and set them again. From 3.65.0 on, settings you do not mention are left alone.</td></tr><tr><td>&quot;Appointments are back to back.&quot;</td><td>Ask for a gap between appointments. Fifteen minutes is the usual answer for a clinic.</td></tr></table></div>
 </div>
 <div class="gsec"><h2>Related guides</h2>
 <ul>

package/package.json

@@ -1,8 +1,8 @@
 {
   "name": "@elitedcs/ghl-mcp",
-  "version": "3.64.1",
+  "version": "3.65.1",
   "mcpName": "io.github.drjerryrelth/ghl-command",
-  "description": "GoHighLevel MCP Server for Claude. 235 tools — full CRM, automation, marketing control, account-wide workflow audit, live funnel-capture verification, and the only programmatic GHL workflow builder, now multi-tenant across client accounts.",
+  "description": "GoHighLevel MCP Server for Claude. 238 tools — full CRM, automation, marketing control, account-wide workflow audit, live funnel-capture verification, and the only programmatic GHL workflow builder, now multi-tenant across client accounts.",
   "main": "dist/index.js",
   "bin": {
     "ghl-mcp": "dist/index.js"

package/templates/action-schemas.json

@@ -1,17 +1,17 @@
 {
   "_description": "AUTHORITATIVE REFERENCE: Correct GHL workflow action attribute schemas. Derived from real working workflows built in GHL UI. ALL sessions MUST use these exact formats.",
-  "_version": "2.0 — 2026-03-24",
+  "_version": "2.0 \u2014 2026-03-24",
   "_critical_rules": [
-    "NEVER use 'body' for emails — use 'html' with HTML markup",
-    "NEVER use 'tagName' — use 'tags' array",
-    "NEVER use 'duration' for waits — use startAfter object",
-    "NEVER use singular min units — real GHL uses 'minutes'",
+    "NEVER use 'body' for emails \u2014 use 'html' with HTML markup",
+    "NEVER use 'tagName' \u2014 use 'tags' array",
+    "NEVER use 'duration' for waits \u2014 use startAfter object",
+    "NEVER use singular min units \u2014 real GHL uses 'minutes'",
     "ALWAYS include 'attachments: []' on SMS actions",
     "ALWAYS include 'trackingOptions' on email actions",
     "ALWAYS include all 5 fields on wait actions (type, startAfter, isHybridAction, hybridActionType, transitions)",
     "ALWAYS use 'parent' AND 'parentKey' on branch nodes",
     "ALWAYS use 'sibling' arrays on branch-yes and branch-no nodes",
-    "NEVER use if_else as a single flat action — it is only valid on condition-node, branch-yes, and branch-no nodes",
+    "NEVER use if_else as a single flat action \u2014 it is only valid on condition-node, branch-yes, and branch-no nodes",
     "ALWAYS include workflow_id ARRAY in remove_from_workflow (not just workflowId string)",
     "For linear workflows, the buildActionChain needs BOTH next (forward) and parentKey (backward) on every action",
     "Keep workflows under 40 actions to avoid GHL UI renderer freezes",
@@ -48,10 +48,9 @@
         "hasTrackingLinks": false,
         "hasUtmTracking": false,
         "hasTags": false
-      },
-      "cc": "{{contact.sales_rep_email}}"
+      }
     },
-    "notes": "Use 'html' NOT 'body'. Content MUST be HTML with <p> tags. Subject supports merge fields. trackingOptions is REQUIRED. RECIPIENT: there is NO 'to' field — the email action ALWAYS sends to the enrolled contact (UI reads 'Send an email to the contact'). To copy a third party use attributes.cc (plain string, accepts merge fields e.g. {{contact.sales_rep_email}}); 'bcc' presumably mirrors it but is NOT live-verified. Never build a 'send to a third party' node expecting a To field — it silently mails the contact instead. (cc shape live-captured 2026-08-08, CLL.)"
+    "notes": "Use 'html' NOT 'body'. Content MUST be HTML with <p> tags. Subject supports merge fields. trackingOptions is REQUIRED."
   },
   "wait": {
     "example_1hour": {
@@ -107,7 +106,20 @@
         "selectedUser": ""
       }
     },
-    "notes": "Nested 'notification' object REQUIRED. selectedUser empty string for all users, or specific user ID."
+    "notes": "Nested 'notification' object REQUIRED. selectedUser empty string for all users, or specific user ID. EMAIL CHANNEL (verified live 2026-07-20, PWDJ workflow e91f28da): attributes.type is 'email' (NOT 'notification'), nested key is 'email' (NOT 'notification'), body field is 'html' (NOT 'body'), selectedUser is an ARRAY of user IDs, include attachments:[] and isCloned:false. A 'send_email' discriminator inside a 'notification' object saves but silently never sends.",
+    "emailChannelExample": {
+      "type": "email",
+      "email": {
+        "isCloned": false,
+        "html": "<p style=\"margin:0px;\">We received a new Collector story.</p>",
+        "subject": "New Painting Collector Story Received",
+        "selectedUser": [
+          "<userId>"
+        ],
+        "userType": "user",
+        "attachments": []
+      }
+    }
   },
   "update_contact_field": {
     "example": {
@@ -173,7 +185,7 @@
       "workflowsActionType": "INTERNAL",
       "type": "internal_update_opportunity"
     },
-    "notes": "CREATABLE from scratch (re-enabled v3.41.0). The discriminator workflowsActionType:'INTERNAL' MUST sit at the NODE level, never nested in attributes — a nested copy makes GHL reject the node as 'action has a corrupted type' and silently fail the whole save. update_workflow_actions normalizes this for you (hoists workflowsActionType to the node level, scaffolds allowBackward + __customInputs__, gives each __customInputFields__ entry an __customInputs__). The shape below (workflowsActionType at the node level alongside type/name/attributes) is correct for both creating and round-tripping. Use pipeline and stage IDs (not names) — get_pipelines / list_pipelines_full to find them FIRST. CRITICAL: if the pipelineId or pipelineStageId don't exist in the target sub-account, GHL silently fails this action AND can kill subsequent actions. A synthesized node needs BOTH a pipelineId and a pipelineStageId entry; a node round-tripped via get_workflow_full keeps its id and passes through unchanged."
+    "notes": "CREATABLE from scratch (re-enabled v3.41.0). The discriminator workflowsActionType:'INTERNAL' MUST sit at the NODE level, never nested in attributes \u2014 a nested copy makes GHL reject the node as 'action has a corrupted type' and silently fail the whole save. update_workflow_actions normalizes this for you (hoists workflowsActionType to the node level, scaffolds allowBackward + __customInputs__, gives each __customInputFields__ entry an __customInputs__). The shape below (workflowsActionType at the node level alongside type/name/attributes) is correct for both creating and round-tripping. Use pipeline and stage IDs (not names) \u2014 get_pipelines / list_pipelines_full to find them FIRST. CRITICAL: if the pipelineId or pipelineStageId don't exist in the target sub-account, GHL silently fails this action AND can kill subsequent actions. A synthesized node needs BOTH a pipelineId and a pipelineStageId entry; a node round-tripped via get_workflow_full keeps its id and passes through unchanged."
   },
   "_if_else_branching": {
     "notes": "if_else is a node type discriminator only. Do not send a single flat if_else action.",
@@ -297,7 +309,7 @@
         "action": "exit"
       }
     },
-    "notes": "Goal-event nodes sit inline in the action chain — when the goal condition fires during workflow execution, the configured action runs (default: 'exit' terminates the workflow path). The previous action's `next` should point to the goal node's id; the goal node itself does NOT have a `next` field. Use build_goal_event to construct the node — it handles UUID generation and the nested op/segments/conditions shape. Verified goal_condition value: 'review_request_clicked' (with extras { reviewTypes: ['sms', 'email'], reviewLinkId: '' }). Other goal_condition strings from GHL's UI pass through verbatim; the full catalogue of goal conditions has not been captured yet.",
+    "notes": "Goal-event nodes sit inline in the action chain \u2014 when the goal condition fires during workflow execution, the configured action runs (default: 'exit' terminates the workflow path). The previous action's `next` should point to the goal node's id; the goal node itself does NOT have a `next` field. Use build_goal_event to construct the node \u2014 it handles UUID generation and the nested op/segments/conditions shape. Verified goal_condition value: 'review_request_clicked' (with extras { reviewTypes: ['sms', 'email'], reviewLinkId: '' }). Other goal_condition strings from GHL's UI pass through verbatim; the full catalogue of goal conditions has not been captured yet.",
     "build_helper": "build_goal_event(goal_condition, extras?, action='exit', target_node_id?, name='Goal', op='or', inner_op='or')"
   },
   "_trigger_patterns": {
@@ -378,8 +390,8 @@
     "notes": "Workflow GET requests must include ?includeTriggers=true or triggers silently disappear. Each trigger type has type-specific condition fields."
   },
   "_workflow_design_patterns": {
-    "nurture_sequence": "Use linear workflow with stopOnResponse:true. Create separate 'exit workflows' triggered by tags (appointment-booked, do-not-contact) that use remove_from_workflow to pull contacts out. Do NOT use inline if/else gates at every step — this creates too many actions and can freeze GHL.",
-    "exit_workflow": "Small 3-4 step workflow: remove_from_workflow → note → tag → notify. Triggered by a tag being added to the contact.",
+    "nurture_sequence": "Use linear workflow with stopOnResponse:true. Create separate 'exit workflows' triggered by tags (appointment-booked, do-not-contact) that use remove_from_workflow to pull contacts out. Do NOT use inline if/else gates at every step \u2014 this creates too many actions and can freeze GHL.",
+    "exit_workflow": "Small 3-4 step workflow: remove_from_workflow \u2192 note \u2192 tag \u2192 notify. Triggered by a tag being added to the contact.",
     "max_actions": "Keep workflows under 40 actions. GHL's UI renderer struggles with larger workflows. Split into multiple connected workflows if needed."
   }
-}
+}