@elitedcs/ghl-mcp 3.78.1 → 3.80.0
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 +94 -0
- package/README.md +1 -1
- package/dist/index.js +2389 -1495
- package/guide/guide.html +678 -18
- package/package.json +1 -1
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,99 @@
|
|
|
1
1
|
# Changelog
|
|
2
2
|
|
|
3
|
+
## 3.80.0 — the phone side of the AI employee, for Command OS subscribers
|
|
4
|
+
|
|
5
|
+
GoHighLevel's Voice AI answers a client's calls. Until now the only way to set one up
|
|
6
|
+
was by hand in the GoHighLevel screen. This release adds twelve tools that build, wire,
|
|
7
|
+
bind and prove a phone agent from a conversation, and **they belong to the Command OS
|
|
8
|
+
plan**: on a GHL Command licence Claude says they are not included and nothing runs.
|
|
9
|
+
**The $97 product is unchanged at 250 tools, 51 modules, 112 free.**
|
|
10
|
+
|
|
11
|
+
What they do: say whether a call can land on the sub-account at all (the numbers it
|
|
12
|
+
owns, which agent answers each, the backup rota, the number pools); list, read, create,
|
|
13
|
+
change and remove an agent; give it what it may do mid-call (transfer to a person, text
|
|
14
|
+
the caller, fill a contact field from what was said, book on a calendar, start a
|
|
15
|
+
workflow, answer from a knowledge base, call an outside API); and read the call logs
|
|
16
|
+
with their transcripts, which is how "it answered" is shown rather than claimed.
|
|
17
|
+
|
|
18
|
+
What they refuse, because GoHighLevel does not. A new agent is always born unable to
|
|
19
|
+
take a call: no number, no pool, and out of the backup rota. Binding the number is a
|
|
20
|
+
separate, deliberate step, and it checks the number is this sub-account's and that no
|
|
21
|
+
other agent already answers on it, because GoHighLevel will silently let a second agent
|
|
22
|
+
take a live number from the first. A draft workflow set to run after a call is refused:
|
|
23
|
+
GoHighLevel accepts it and it never runs. A custom API action carrying headers or
|
|
24
|
+
parameters is refused before the call, because they crash GoHighLevel's server and the
|
|
25
|
+
action is saved anyway. Every write answers "verified" or "asserted" from an
|
|
26
|
+
independent read after it, including when that read fails, so a write that landed is
|
|
27
|
+
never reported as an error that invites a duplicate.
|
|
28
|
+
|
|
29
|
+
Proven live, not claimed: every shape was read off GoHighLevel on a sandbox before a
|
|
30
|
+
line was written; the finished tools were driven through the built server with every
|
|
31
|
+
object deleted afterwards and the sandbox read back at zero; and a real 67-second test
|
|
32
|
+
call was listed and read back in full by the tools. Six adversarial review rounds to a
|
|
33
|
+
ship verdict, twenty-three findings fixed on the way.
|
|
34
|
+
|
|
35
|
+
Two things are stated as unproven rather than glossed: the shape of a number-pool
|
|
36
|
+
object, because no sandbox holds one, so pools are handled cautiously; and the
|
|
37
|
+
create-then-bind-then-ring path on an agent these tools created, which needs a number
|
|
38
|
+
that is not live to real callers.
|
|
39
|
+
|
|
40
|
+
**Also in this release**
|
|
41
|
+
|
|
42
|
+
The install guide now answers the three things buyers hit in their first ten minutes:
|
|
43
|
+
it names the Claude Code install line beside the Desktop one, says a fresh start is two
|
|
44
|
+
full quits (Cmd+Q on a Mac, the system tray on Windows, not just closing the window),
|
|
45
|
+
and adds three rows to its questions table: the website Claude cannot run the installer,
|
|
46
|
+
tools only load on a fresh start, and API access needs the $297 or $497 GoHighLevel plan.
|
|
47
|
+
|
|
48
|
+
Counts: 250 tools, 51 modules, free tier 112.
|
|
49
|
+
|
|
50
|
+
## 3.79.0 — the automations agencies actually sell, written down
|
|
51
|
+
|
|
52
|
+
The guide library grew by seven, and every one of them is a thing you can sell on a
|
|
53
|
+
call: answer a new lead in seconds, text back every missed call, win back a cold
|
|
54
|
+
list, rescue a no-show, remind people about their appointment, confirm a booking and
|
|
55
|
+
move the deal, and take over an account somebody else built.
|
|
56
|
+
|
|
57
|
+
These are not new capabilities. GHL Command already built every one of them inside
|
|
58
|
+
the Blueprint, and the library only taught one. So an owner who was not running a
|
|
59
|
+
whole Blueprint had no way to find the missed-call text-back or the speed-to-lead,
|
|
60
|
+
which are the two automations most agencies get paid for. Now each is its own guide,
|
|
61
|
+
with a prompt you paste and change.
|
|
62
|
+
|
|
63
|
+
Each was proven by running its own prompt against a real GoHighLevel account and
|
|
64
|
+
deleting the result in the same run. The proofs are deliberately narrow about what
|
|
65
|
+
they show: the workflow saved in the shape asked for, and every pipeline, stage,
|
|
66
|
+
calendar and user id inside it points at something real. That is the failure
|
|
67
|
+
GoHighLevel never warns you about, where a workflow saves cleanly and then quietly
|
|
68
|
+
does nothing. It is not a claim that the sequence was watched running against a real
|
|
69
|
+
person, and the guides say so.
|
|
70
|
+
|
|
71
|
+
The booking guide's proof is the interesting one, because it was allowed to fail. The
|
|
72
|
+
deal-move step was built the wrong way round on purpose, and the validator answered
|
|
73
|
+
with the warning that whole guide exists to prevent.
|
|
74
|
+
|
|
75
|
+
**Also in this release**
|
|
76
|
+
|
|
77
|
+
Two guides came off "Coming in an update" and are now open: **The Blueprint: build a
|
|
78
|
+
client account** and **Page Studio: pages and sites**. Both were rewritten where
|
|
79
|
+
running them proved the old text wrong. The Blueprint guide had been telling you your
|
|
80
|
+
client's intake answers arrive as a form submission; GoHighLevel does not report
|
|
81
|
+
submissions for any form created through the API, so that path never worked. The
|
|
82
|
+
answers are on a contact, and the guide now says so. `install_intake_form` also hands
|
|
83
|
+
back the link to send your client instead of leaving you to find it in the
|
|
84
|
+
GoHighLevel interface.
|
|
85
|
+
|
|
86
|
+
Page Studio's guide had promised a social-proof section that cannot be composed and a
|
|
87
|
+
live URL that needs publishing and a domain first. It now describes what the tool
|
|
88
|
+
actually does and shows you the preview instead.
|
|
89
|
+
|
|
90
|
+
The blog guide has been retired rather than left sitting as a card. GoHighLevel's
|
|
91
|
+
blog feature is not used anywhere we can reach, so it could never be proven, and a
|
|
92
|
+
card promising a guide that is never coming is worse than no card.
|
|
93
|
+
|
|
94
|
+
Library: 41 open guides across 10 categories. Counts unchanged: 250 tools, 51
|
|
95
|
+
modules, free tier 112.
|
|
96
|
+
|
|
3
97
|
## 3.78.1 — the template installer stops guessing which funnel it just made
|
|
4
98
|
|
|
5
99
|
Yesterday's release shipped `install_ghl_template` with the originals kept by default,
|
package/README.md
CHANGED