@elitedcs/ghl-mcp 3.84.0 → 3.84.2

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 CHANGED
@@ -2,6 +2,87 @@
2
2
 
3
3
  ## Unreleased
4
4
 
5
+ ## 3.84.2 — done means read back, not echoed
6
+
7
+ Every tool that reports a thing as done, verified, ready or published was checked against a second,
8
+ independent read of what GoHighLevel actually holds. Thirteen places were claiming an outcome from
9
+ the write's own response, a counter, or the wrong field. Each now derives the claim from a read taken
10
+ after the write, or says plainly what could not be confirmed.
11
+
12
+ **A build report no longer says "Published N workflows live" for a workflow GoHighLevel kept as a
13
+ draft.** The publish step already read the workflow back and said NOT LIVE when it was not; the
14
+ build threw that answer away and counted it anyway. It is counted now, and a workflow that published
15
+ with every trigger still inactive is named as such rather than called running. The publish tool's
16
+ step and trigger counts come from the read after the write, with the number of active triggers
17
+ beside them.
18
+
19
+ **The workflow audit no longer says "ok" while dropping four kinds of warning.** Steps GoHighLevel
20
+ will not accept on save, waits in the unit it no longer takes, an alert set to notify a specific
21
+ person with nobody chosen, and steps needing a social account that is not connected were computed
22
+ for every workflow and then left out of the roll-up. They are in it, and in the client-facing report,
23
+ in plain words.
24
+
25
+ **"Trained." means the pages are trained.** Training a knowledge base settled on a status shared
26
+ with discovery, so it said Trained the moment discovery finished, for a failed run, and for pages
27
+ queued behind an earlier batch. It now settles only when every requested page is in the trained
28
+ bucket, and a crawl GoHighLevel stopped says so instead of "Discovery finished".
29
+
30
+ **The morning brief no longer calls a morning quiet when your own calendar could not be read.**
31
+ A connected Google Calendar that failed to open produced the same "Nothing needs you this morning"
32
+ as an empty one. The headline now says the calendar could not be read.
33
+
34
+ **Readiness, calendars, smart lists, keys and pages tell the truth.** A phone-agent readiness check
35
+ no longer says READY on a number pool whose numbers it cannot read. Renaming a calendar carries the
36
+ assigned staff back in the shape GoHighLevel validates and reports the stored team-member count from
37
+ a read after the update. A contact smart list is refused on the opportunity service instead of being
38
+ created where the Contacts screen never shows it. "Removed" for a sub-account key is said only when
39
+ the key really left this computer's file. A page save whose baseline could not be read is reported
40
+ as unverified rather than visible, and a page build is verified on the pointer GoHighLevel serves
41
+ the page from. Switching accounts says the workflow-builder credentials were found, not tested.
42
+
43
+ **Also in this release:** the eleven small findings deferred from the 3.84.1 reviews. Among them:
44
+ a survey trigger is checked against the account instead of refused as a dead end; three more trigger
45
+ slots are read back; a plan handed back by hand is held to the same confirmed selection as a saved
46
+ one; a half-applied older build is told to keep its undo and plan only the rest; a number an agent
47
+ held only in the old non-routing shape is named when a bind starts routing it; and the brand repaint
48
+ leaves a tint or tone as it was only when that makes the text readable, saying so honestly, and
49
+ repaints every spelling of a colour, not only the six-digit hex.
50
+
51
+ ## 3.84.1 — the phone agent answers, the repaint tells the truth, and the build waits to be told
52
+
53
+ **A phone agent you connect now actually answers.** Connecting a number to a voice agent wrote a
54
+ setting GoHighLevel stores but does not route calls by: the tool said the number was connected and
55
+ the readiness check said READY, while the number itself rang out to voicemail. The number is now
56
+ written the way GoHighLevel's own screen writes it, proven by a real call, and "connected" is only
57
+ claimed when the agent reads back that way. An agent still carrying the old setting is named, with
58
+ the two ways to repair it. Disconnecting clears the number for real; it used to leave it behind.
59
+
60
+ **Branding a GoHighLevel design says what changed, in what a visitor sees.** The report used to
61
+ count colour substitutions, which said "a full repaint" on a page where only the button changed.
62
+ It now compares the page GoHighLevel stored before and after, resolved through the design's own
63
+ colour settings, and says plainly when the visible palette barely moved. It also picks the colours
64
+ the page really paints with: the big bands a design is made of, rather than colours that only touch
65
+ a border. Headline and body faces no longer get swapped the wrong way round. Any text that was
66
+ readable and no longer meets the 4.5:1 standard is named, colour by colour, on the page result and
67
+ at the top of the run.
68
+
69
+ **The client document only offers what the build leaves out.** Ticking every feature used to clear
70
+ the record, and the document then offered features the build includes as "available next", priced.
71
+ A feature that was bought and then unticked disappeared from the document altogether. Both are
72
+ fixed, and ticking everything is now kept as a confirmation rather than as no answer at all.
73
+
74
+ **Nothing is built until you confirm what to build.** Saving what a client bought used to create
75
+ the build selection too. It now records the purchase only; the review screen is ticked from it, and
76
+ the build stops and asks until you confirm. Re-running a build from a saved plan follows the
77
+ selection as it stands now, instead of building what you removed.
78
+
79
+ **A plan aimed at something that does not exist is refused before it runs.** Every id a plan
80
+ carries is read back from the account first, as the kind the step says it is, including the ids
81
+ inside workflow steps, triggers, if/else branches and contact fields. A list the account cannot
82
+ page through is never treated as proof that an id is missing. A plan checked against one
83
+ sub-account cannot be approved or run against another. An id this cannot check is refused by name,
84
+ with the node it sits in and what to do about it.
85
+
5
86
  ## 3.84.0 — the brief reaches past GoHighLevel, Slack arrives, the build follows what the client bought
6
87
 
7
88
  **The morning brief now asks your own Gmail, Google Calendar, Drive and Slack.** It ends with each
package/README.md CHANGED
@@ -897,7 +897,7 @@ Built by **[Elite DCs, LLC](https://elitedcs.com)** — a digital marketing and
897
897
 
898
898
  **Tech stack:** TypeScript, Node.js, esbuild, MCP SDK, Zod, GHL API v2, Firebase Auth
899
899
 
900
- **Version:** 3.84.0
900
+ **Version:** 3.84.2
901
901
 
902
902
  ---
903
903