@elitedcs/ghl-mcp 3.78.0 → 3.79.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +79 -0
- package/README.md +1 -1
- package/dist/index.js +308 -255
- package/guide/guide.html +664 -13
- package/package.json +1 -1
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,84 @@
|
|
|
1
1
|
# Changelog
|
|
2
2
|
|
|
3
|
+
## 3.79.0 — the automations agencies actually sell, written down
|
|
4
|
+
|
|
5
|
+
The guide library grew by seven, and every one of them is a thing you can sell on a
|
|
6
|
+
call: answer a new lead in seconds, text back every missed call, win back a cold
|
|
7
|
+
list, rescue a no-show, remind people about their appointment, confirm a booking and
|
|
8
|
+
move the deal, and take over an account somebody else built.
|
|
9
|
+
|
|
10
|
+
These are not new capabilities. GHL Command already built every one of them inside
|
|
11
|
+
the Blueprint, and the library only taught one. So an owner who was not running a
|
|
12
|
+
whole Blueprint had no way to find the missed-call text-back or the speed-to-lead,
|
|
13
|
+
which are the two automations most agencies get paid for. Now each is its own guide,
|
|
14
|
+
with a prompt you paste and change.
|
|
15
|
+
|
|
16
|
+
Each was proven by running its own prompt against a real GoHighLevel account and
|
|
17
|
+
deleting the result in the same run. The proofs are deliberately narrow about what
|
|
18
|
+
they show: the workflow saved in the shape asked for, and every pipeline, stage,
|
|
19
|
+
calendar and user id inside it points at something real. That is the failure
|
|
20
|
+
GoHighLevel never warns you about, where a workflow saves cleanly and then quietly
|
|
21
|
+
does nothing. It is not a claim that the sequence was watched running against a real
|
|
22
|
+
person, and the guides say so.
|
|
23
|
+
|
|
24
|
+
The booking guide's proof is the interesting one, because it was allowed to fail. The
|
|
25
|
+
deal-move step was built the wrong way round on purpose, and the validator answered
|
|
26
|
+
with the warning that whole guide exists to prevent.
|
|
27
|
+
|
|
28
|
+
**Also in this release**
|
|
29
|
+
|
|
30
|
+
Two guides came off "Coming in an update" and are now open: **The Blueprint: build a
|
|
31
|
+
client account** and **Page Studio: pages and sites**. Both were rewritten where
|
|
32
|
+
running them proved the old text wrong. The Blueprint guide had been telling you your
|
|
33
|
+
client's intake answers arrive as a form submission; GoHighLevel does not report
|
|
34
|
+
submissions for any form created through the API, so that path never worked. The
|
|
35
|
+
answers are on a contact, and the guide now says so. `install_intake_form` also hands
|
|
36
|
+
back the link to send your client instead of leaving you to find it in the
|
|
37
|
+
GoHighLevel interface.
|
|
38
|
+
|
|
39
|
+
Page Studio's guide had promised a social-proof section that cannot be composed and a
|
|
40
|
+
live URL that needs publishing and a domain first. It now describes what the tool
|
|
41
|
+
actually does and shows you the preview instead.
|
|
42
|
+
|
|
43
|
+
The blog guide has been retired rather than left sitting as a card. GoHighLevel's
|
|
44
|
+
blog feature is not used anywhere we can reach, so it could never be proven, and a
|
|
45
|
+
card promising a guide that is never coming is worse than no card.
|
|
46
|
+
|
|
47
|
+
Library: 41 open guides across 10 categories. Counts unchanged: 250 tools, 51
|
|
48
|
+
modules, free tier 112.
|
|
49
|
+
|
|
50
|
+
## 3.78.1 — the template installer stops guessing which funnel it just made
|
|
51
|
+
|
|
52
|
+
Yesterday's release shipped `install_ghl_template` with the originals kept by default,
|
|
53
|
+
because the tool worked out which funnel it had created by comparing the account before
|
|
54
|
+
and after, and on a busy sub-account that comparison cannot be certain. Keeping the
|
|
55
|
+
originals was the safe answer to an open question.
|
|
56
|
+
|
|
57
|
+
The question now has an answer. GoHighLevel's install response names what it created: the
|
|
58
|
+
funnel id and its first page. The tool reads that id and waits for that funnel, so it
|
|
59
|
+
cannot land on one somebody else happened to be building at the same moment.
|
|
60
|
+
|
|
61
|
+
**It does not simply believe it.** The name only counts when your account agrees the
|
|
62
|
+
funnel is genuinely new, and the tool checks the response against a complete picture of
|
|
63
|
+
the account taken before the install. Two independent confirmations, because that one
|
|
64
|
+
field is what authorises removing anything. If the name and the account ever disagree, the
|
|
65
|
+
name is thrown away, nothing is removed, and the result says so.
|
|
66
|
+
|
|
67
|
+
With both confirmations in hand the originals go back to being removed once every branded
|
|
68
|
+
page has been read back and measured, which is how the tool was meant to work: one clean
|
|
69
|
+
funnel in your client's colours, not a doubled one you have to tidy. Pass
|
|
70
|
+
`keepOriginals: true` if you would rather see both.
|
|
71
|
+
|
|
72
|
+
Anything less and the originals stay, whatever you passed: no name in the response, a name
|
|
73
|
+
the account cannot corroborate, or an account with so many funnels that the before picture
|
|
74
|
+
was incomplete.
|
|
75
|
+
|
|
76
|
+
A split-test step, where one step holds more than one page, still stops any removal. Only
|
|
77
|
+
the first page of such a step is rebuilt, so removing the step would take the variants
|
|
78
|
+
with it.
|
|
79
|
+
|
|
80
|
+
Counts unchanged: 250 tools, 51 modules, free tier 112.
|
|
81
|
+
|
|
3
82
|
## 3.78.0 — GoHighLevel's own template library, repainted in your client's colours
|
|
4
83
|
|
|
5
84
|
GoHighLevel ships more than 900 designed funnel templates. You could always install
|
package/README.md
CHANGED