@elitedcs/ghl-mcp 3.89.0-beta.3 → 3.89.0-beta.4

package/CHANGELOG.md

@@ -1,5 +1,27 @@
 # Changelog
 
+## 3.89.0-beta.4: a two-page client handoff, no pop-up boxes left in the intake, Brief waits for GoHighLevel on its own, and text templates confirmed properly
+
+This is a beta, a test build for members who want the next release early. Everything below is new since 3.89.0-beta.3.
+
+**The client handoff is now two pages a business owner can read.** The handoff page a client receives used to list every tag, custom field and automation as its own heading, open with counts and GoHighLevel menu paths, and mix your jobs with theirs; for a full build that came to about ten printed pages. It is now one short page under your agency's name and colour, "Prepared for" the client with the date: what their new system does for the business, the problems they told you about and what you built for each (from an attached Assessment with its dollar figures, else the Blueprint Review, else their intake answers, and nothing when none of those says anything), what happens to a new lead (only the steps that were actually built), their team, their sales stages, what they bought (built, and being set up next), and at most five things only the owner can do before switch-on, in plain words with no menu paths, taken only from your jobs that are still open ("Nothing needed from you right now" when none are). Nothing the client typed in the intake is ever quoted on the page; their answers only pick from a fixed set of plainly worded problems. An automation the latest check found missing is left off, and a large team, a long list of stages or many calendars are shortened so the page still fits. It says the system is working only once every automation is confirmed switched on; until then it says "Once it is switched on". It prints to two US Letter pages without splitting a row or a step across pages, keeps the Print / save PDF button, and still rewrites itself after every Verify. The copy published to the client's GoHighLevel page carries the same short page. Everything technical (tags, fields, custom values, workflow names and states, record ids, the latest check's findings and your jobs with their click paths) moved to a new page for you, "Account detail, for your agency", opened from the handoff panel in the cockpit and never linked from the client's page.
+
+**No pop-up boxes left in the intake.** Every question the intake used to ask in a browser pop-up is now a small panel in the page, right under the button you pressed. That covers replacing an answer you already had with a suggested one (Replace or Keep current, shown under that answer with the current and proposed wording), sending the questionnaire, a transcript over the 60,000-character limit, going to the real form with required answers still missing, and going back to the base question set. When your browser will not let the cockpit copy the blank form link, the link now appears in a box that selects itself so you can copy it. A stray key no longer answers a question for you. Add them for me, which creates GoHighLevel logins for your staff before a build, asks the same way, and what GoHighLevel answers (including any one-time password) stays on the page until you press Done.
+
+**A step that cannot start says why under its button.** When Brief, Build or Verify cannot start, the reason now appears in a line right under the Run button instead of a pop-up, and it stays there until you press Run again.
+
+**Brief waits for GoHighLevel by itself.** Right after a client submits the intake form, GoHighLevel can take a minute to attach the answers to the contact. Running Brief in that minute used to stop with a message telling you to try again. Now the cockpit says "Waiting for GoHighLevel to attach the answers to the contact…", checks every 10 seconds for up to 2 minutes, and runs Brief on its own as soon as the answers are there. If another step is still running, it keeps waiting until it can start. A Stop waiting link ends the wait, and if GoHighLevel refuses the account's key the wait stops at once and says so. If the answers are still not there after 2 minutes, it shows the same message as before, under the button.
+
+**Text templates made by a build are confirmed properly.** A build could report a text template as possibly not saved when it had been saved. GoHighLevel answers a new text template with its id, and the build now uses that id first, then the exact name, and gives GoHighLevel three looks over about six seconds before saying anything. If GoHighLevel said it saved the template but its list has not caught up yet, the template counts as made and the build asks you to glance at it once, instead of saying it may not have saved.
+
+**Texting rules and a claims guard in every build template.** Lessons from real clinic accounts now apply to every industry template and to every Blueprint build. Texts use plain characters only: a curly quote, long dash, one-character ellipsis or emoji switches a whole text to the expensive Unicode kind (70 characters per part instead of 160), and on one live account a single long dash took each contact from 22 billed parts to 47. The build now swaps those characters for plain ones, including in intake answers such as an owner's name or offer with a curly apostrophe, and says which text it changed; validate_workflow and the workflow audit warn about them in live workflows too. The first text of every nurture and win-back sequence now has "Reply STOP to opt out." on a line of its own. Reply keywords such as STOP, N, YES and TEAM are matched exactly, never "contains", because a "contains STOP" rule opted out a patient who asked "when should I stop eating"; keyword triggers in the templates say so, and a "contains" match on a reply word is flagged. New claims guard: a text or email built from a template can no longer carry a health or results claim (pain, sleep, inflammation, cures, weight or inch loss, guaranteed results, numbers like "lose 10 pounds") or a named result like "Sarah lost 3 inches", unless it is a size or weight result the client gave with consent (a testimonial marked with consent, or an offer claim) and the message says "results vary". Consent to use a testimonial covers the person's words and name, not a claim inside it, and a health claim (pain, sleep, inflammation, cures) is never sent, even with consent. Pure praise with consent, such as "the team was so kind", goes out as written. When a rewritten message or an intake answer brings in a claim without consent, that message goes back to the template's own wording, whole, with a warning naming the message and the claim; nothing is cut out of the middle of a sentence. A message with no clean wording to go back to is left out of the build and becomes a job to write it without the claim, and a template whose own copy makes a claim stops the build until it is rewritten. Describing a service is not a claim: "We treat sports injuries", "Dr. Patel treats migraines", "reminder", "treatment plan" and "pain-free booking" are not flagged. Links in texts are left exactly as written, and when a custom value used in texts is changed to plain characters, the warning says it changes everywhere that value is used.
+
+**The claims guard also checks intake answers that become custom values, and a few texting rules are tighter.** An intake answer that becomes an account-wide custom value, such as a trial named "Inch Loss Trial" or a program named "Lose 10 pounds program", reaches every text through that value, so it is now checked too: a value that makes a claim goes back to the template's default (for example "Intro Trial"), or is left blank for you to fill without the claim when there is no default, with a warning and a line on the claims review job. The business name is never replaced; a claim in it is flagged for you to check with the client. In the Wellness clinic template a client quote is never put into a message, even through rewritten copy that adds "results vary": that message goes back to the template's wording. When a template already has its own claims review job, the list of messages and values the build changed is added to it. An opt-out now counts only when the opt-out words are in the same sentence as the reply keyword, so "Reply N for next steps. We won't text you after 8pm." is not an opt-out line, and "Reply STOP to unsubscribe" is. A build plan whose reply trigger lists both a single keyword and a keyword list is refused with a message saying to use the list. On the client's handoff page, the Wellness clinic's follow-up after a visit is called Program follow-up, not Quote follow-up.
+
+This is a beta, a test build for members who want the next release early. Everything below is new since 3.89.0-beta.3.
+
+**A new industry: Wellness clinic (cockpit plan and Blueprint).** For red light, body contouring, IV, peptide, longevity and recovery clinics that sell a paid first-visit trial and then a program. Choose "Wellness clinic" as the client's industry and the intake asks what the build needs: the trial's name and price, the deposit and the balance, how long the visit is, how many trial visits fit in a day, the programs and their prices, who should not book, how to prepare, an optional comparison price, an optional client quote with a separate yes or no for written permission, and which services the clinic offers. The build then makes a trial-to-program account: a 10-stage patient pipeline (or the client's own stages, with every automation pointed at the right one), a trial calendar with 24 hours' notice, one visit per slot, the daily limit and the clinic's screening note, a trial form with an optional phone number and two separate, unticked texting consent boxes, and 19 workflows. The new lead gets the booking link within seconds, with follow-ups at 4 and 24 hours; then a 30-day nurture, a 30-day win-back, booking confirmation and reminders, the balance on arrival, cancel and no-show texts, a 72-hour program follow-up after the visit, a program confirmation, and a review request two weeks into a program. A booking stops the lead's follow-up texts, and a program sale stops the post-visit follow-up. Replies of N, STOP, TEAM or BOOK are matched on the exact word, so "when should I stop eating" is never an opt-out, a plain "No" to a question is never an opt-out either, and STOP turns off texting without moving the client's card. A deposit or balance of 0 counts as none, so those clinics get texts with no deposit in them, and a free trial gets free-trial wording. The messages follow what works in wellness accounts running today, written fresh, and the ones with no working example are marked as new. No text makes a health, pain, sleep or weight claim, a client quote is never put into a text by the build (even with written permission, a person reads it first and adds it by hand), every marketing text carries its own "Reply N to opt out" line, no text contains a long dash or curly quotes (these can double what a text costs), and no program is ever sold through a text link. Things to know: the "balance paid" thank-you stays switched off until you limit its payment trigger to the balance product, as the build's checklist explains.
+
 ## 3.89.0-beta.3: one list of what the client bought, one approve button, no pop-up boxes on the client build path, and a cleaner read of intake answers
 
 This is a beta, a test build for members who want the next release early. Everything below is new since 3.89.0-beta.2.

package/README.md

@@ -899,7 +899,7 @@ Built by **[Elite DCs, LLC](https://elitedcs.com)** — a digital marketing and
 
 **Tech stack:** TypeScript, Node.js, esbuild, MCP SDK, Zod, GHL API v2, Firebase Auth
 
-**Version:** 3.89.0-beta.3
+**Version:** 3.89.0-beta.4
 
 ---