@sellable/mcp 0.1.343 → 0.1.344
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.
|
@@ -6,7 +6,7 @@ async function postSetupEvergreenCampaigns(body) {
|
|
|
6
6
|
export const setupEvergreenCampaignsToolDefinitions = [
|
|
7
7
|
{
|
|
8
8
|
name: "setup_evergreen_campaigns",
|
|
9
|
-
description: "Evergreen campaign setup plan/verify command. Use plan mode first to inspect exact workspace/sender/campaign/table/source state and receive immutable lane packets for one Post Engagers lane per selected sender plus shared Signal Discovery and Shared Cold Fallback lanes. yolo is only a parent-skill auto-execution hint for safe lane packets; this backend command remains read-only in plan mode and verifies receipts in verify mode. Lane workers must execute creation, source import, create-campaign workflow steps, generate-messages, sequence attachment, and review readiness through existing create-campaign workflow/subskills, then return receipts here for verification. This command does not launch campaigns, does not schedule sends, does not assign scheduler-owned send fields, does not archive/delete cleanup targets, and does not spend paid credits.",
|
|
9
|
+
description: "Evergreen campaign setup plan/verify command. Use plan mode first to inspect exact workspace/sender/campaign/table/source state and receive immutable lane packets for one Post Engagers lane per selected sender plus shared Signal Discovery and Shared Cold Fallback lanes. yolo is only a parent-skill auto-execution hint for safe lane packets; this backend command remains read-only in plan mode and verifies receipts in verify mode. When safe-yolo needs normal setup work, the parent skill may ask for bounded delegated approval: one approval over the current planRevision, selected action ids, caps, allowed side-effect classes, and stop conditions lets lane workers execute without per-substep approval while staying inside that packet. Lane workers must execute creation, source import, create-campaign workflow steps, generate-messages, sequence attachment, and review readiness through existing create-campaign workflow/subskills, then return receipts here for verification. This command does not launch campaigns, does not schedule sends, does not assign scheduler-owned send fields, does not archive/delete cleanup targets, and does not spend paid credits.",
|
|
10
10
|
inputSchema: {
|
|
11
11
|
type: "object",
|
|
12
12
|
properties: {
|
package/package.json
CHANGED
|
@@ -83,14 +83,34 @@ workspace, cleanup/archive/delete need, stale plan, disconnected sender,
|
|
|
83
83
|
duplicate candidate, unsafe side effect, missing source proof, or missing
|
|
84
84
|
message proof.
|
|
85
85
|
|
|
86
|
-
|
|
87
|
-
|
|
88
|
-
|
|
89
|
-
|
|
90
|
-
|
|
91
|
-
|
|
92
|
-
|
|
93
|
-
|
|
86
|
+
When safe-yolo is blocked only because the plan needs normal setup work, ask
|
|
87
|
+
for a **bounded delegated approval** over the rendered current plan instead of
|
|
88
|
+
asking for each substep. The approval packet must name the workspace id, sender
|
|
89
|
+
ids, lane keys, campaign/table ids or create intents, source/import caps,
|
|
90
|
+
generate-message caps, route-proof approval policy, selectedActionIds,
|
|
91
|
+
planRevision, allowed side-effect classes, and stop conditions. After that one
|
|
92
|
+
approval covers the current planRevision, the parent may act on behalf of the
|
|
93
|
+
operator and execute the selectedActionIds end to end. Do not ask again for
|
|
94
|
+
substep approvals for source import, create-campaign choices, Message Drafting,
|
|
95
|
+
sequence attach/precheck, or exactly one route-proof approval when those actions
|
|
96
|
+
are within the lane packet, approved caps, approved side-effect classes, and
|
|
97
|
+
route-proof approval policy. Stop and re-plan if any fresh reread changes the
|
|
98
|
+
workspace id, sender ids, source/list id, campaign/table id, new campaign/table
|
|
99
|
+
id, planRevision, actionId, selectedActionIds, allowed side effects, caps,
|
|
100
|
+
status, or blocker set outside the approved packet.
|
|
101
|
+
The short rule: one approval covers the current planRevision and selectedActionIds.
|
|
102
|
+
The execution rule: act on behalf of the operator; do not ask again for substep approvals while work stays within the lane packet, approved caps, approved side-effect classes, and route-proof approval policy.
|
|
103
|
+
The drift rule: stop and re-plan when ids, caps, blockers, side-effect classes, or any new campaign/table id leave the approved packet.
|
|
104
|
+
|
|
105
|
+
After bounded delegated approval or safe `--yolo`, fan out lane worker tasks
|
|
106
|
+
only from the current plan. Each worker receives the complete lane packet:
|
|
107
|
+
workspace id, sender ids, lane key/type, existing campaign/table binding or
|
|
108
|
+
create intent, source hints, caps, planRevision, actionId, allowed side effects,
|
|
109
|
+
and postconditions. Workers must use the create-campaign workflow and
|
|
110
|
+
create-campaign workflow/subskills for campaign creation/setup, source/import,
|
|
111
|
+
filter choice, Message Drafting, packaged `generate-messages`, sequence
|
|
112
|
+
attachment, and send-review readiness. Do not rebuild those steps ad hoc in the
|
|
113
|
+
parent thread.
|
|
94
114
|
|
|
95
115
|
Workers return worker receipts. The parent then calls
|
|
96
116
|
`setup_evergreen_campaigns({ mode:"verify", planRevision, selectedActionIds,
|