@sellable/mcp 0.1.360 → 0.1.362

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sellable/mcp",
-  "version": "0.1.360",
+  "version": "0.1.362",
   "type": "module",
   "description": "Sellable MCP server for Claude Code and Codex campaign workflows",
   "main": "dist/index.js",

package/skills/create-evergreen-campaigns/SKILL.md

@@ -183,9 +183,10 @@ not a parent-thread summary. The receipt must include:
   workflowTableId, brief hash or updated-at marker, delivery format, token
   rules, hard avoids, source-use rules, and first-message template state.
 - `sourceDecisionReceipt`: selected source/list id, provider, cursor/inventory
-  state, import/copy caps, dedupe/DNC/provider exclusions, row ids or row-count
-  evidence, and the reason no colder source was used before the current source
-  was proven exhausted or insufficient.
+  state, import/copy caps, explicit `dedupeDncProviderExclusions:true` or an
+  equivalent exclusions object, row ids or row-count evidence (`rowCount`,
+  `readyRowCount`, or `rowEvidence`), and the reason no colder source was used
+  before the current source was proven exhausted or insufficient.
 - `filterDecisionReceipt`: saved/applied filter ids or explicit skip-filter
   decision with current campaign/table basis.
 - `messageDraftingReceipt`: the Message Drafting proof described below,
@@ -206,6 +207,92 @@ not a parent-thread summary. The receipt must include:
   planRevision, selectedActionIds, receipts })` call/result used before the
   parent reports completion.
 
+Use these canonical receipt leaf names exactly. Do not substitute looser aliases
+like `generateMessagesPromptLoad`, `requiredAssetLoads`,
+`validationPromptLoad`, `reviewBatchBasisHash`, `reviewRowIds`,
+`sequenceActionTypes`, or `pass:true` unless you also include the canonical
+fields below:
+
+```json
+{
+  "status": "succeeded",
+  "planRevision": "<original planRevision>",
+  "laneKey": "<lane key>",
+  "laneType": "<lane type>",
+  "workspaceId": "<workspace id>",
+  "senderIds": ["<sender id>"],
+  "campaignId": "<campaign id>",
+  "tableId": "<workflow table id>",
+  "createCampaignStepReceipt": {
+    "campaignBriefReceipt": {
+      "campaignId": "<campaign id>",
+      "workflowTableId": "<workflow table id>",
+      "briefHash": "<brief/currentApprovedBriefHash>",
+      "deliveryFormat": "single message",
+      "tokenRules": true,
+      "hardAvoids": true,
+      "sourceUseRules": true,
+      "firstMessageTemplate": "<template or template state>"
+    },
+    "sourceDecisionReceipt": {
+      "sourceId": "<source id>",
+      "sourceListId": "<source/list id>",
+      "cursorOrInventoryState": "<cursor/inventory/import state>",
+      "dedupeDncProviderExclusions": true,
+      "sourceLadderReason": "<why the current source is valid before colder sources>"
+    },
+    "filterDecisionReceipt": {
+      "status": "skipped",
+      "workflowTableId": "<workflow table id>"
+    },
+    "messageDraftingReceipt": {
+      "promptLoadedToHasMoreFalse": true,
+      "requiredAssetsLoaded": true,
+      "validationLoaded": true,
+      "campaignId": "<campaign id>",
+      "workflowTableId": "<workflow table id>",
+      "selectedLeadListId": "<source/list id>",
+      "reviewBatchRowHash": "<review row ids hash>",
+      "messageDraftRecommendation": {"basis": "generate-messages"},
+      "sampleMessages[].verdict": "pass",
+      "sampleMessages": [
+        {"rowId": "<row id>", "generatedMessageText": "<message>", "verdict": "pass"}
+      ]
+    },
+    "reviewBatchReceipt": {
+      "rowIdsHash": "<review row ids hash>",
+      "generatedCount": 3
+    },
+    "sequenceReceipt": {
+      "workflowTableId": "<workflow table id>",
+      "hasSequence": true,
+      "sequenceReceipt.actionTypes": ["send_invite"],
+      "sequenceReceipt.nonPaid": true,
+      "actionTypes": ["send_invite"],
+      "nonPaid": true
+    },
+    "finalPausedSendProof": {
+      "currentStep": "send",
+      "campaignStatus": "PAUSED"
+    },
+    "verifyCall": {
+      "mode": "verify",
+      "planRevision": "<original planRevision>",
+      "selectedActionIds": ["<all original selected action ids>"]
+    }
+  }
+}
+```
+
+Verification always uses the original execution planRevision and original
+selectedActionIds from the plan packets that were dispatched before mutation.
+The parent must preserve the original selectedActionIds exactly.
+Do not replace them with a later reuse planRevision/actionIds after the
+campaigns exist. After workers complete, attach or patch `verifyCall` on each
+lane receipt with that original execution planRevision, original
+selectedActionIds, same sender scopes, and the verify result. Only after verify
+succeeds should the parent perform the idempotency rerun.
+
 If any required field is missing, report
 `blocked: missing_create_campaign_step_receipt` for that lane and do not call it
 complete.
@@ -286,12 +373,11 @@ create-campaign Message Drafting branch ran. If this receipt is missing, report
 The parent then calls
 `setup_evergreen_campaigns({ mode:"verify", postEngagerSenderIds,
 sharedSenderIds, planRevision, selectedActionIds, receipts })` using the same
-sender scopes as the plan call, and reports only verified completion. A verify
-call without the same sender scopes can recompute an empty or different plan and
-is invalid proof. After verify succeeds, rerun
+sender scopes as the plan call and the original execution planRevision/actionIds,
+and reports only verified completion. A verify call without the same sender scopes can recompute an empty or different plan and is invalid proof. A verify call that uses a later reuse planRevision instead of the original execution planRevision is also invalid proof. Only after verify succeeds, rerun
 `setup_evergreen_campaigns({ mode:"plan", postEngagerSenderIds,
 sharedSenderIds, yolo:true })` without explicit campaign/table bindings. That
-idempotency plan must return `intent:"reuse"` for every completed lane and no
+idempotency rerun must return `intent:"reuse"` for every completed lane and no
 duplicate-lane blockers before you call the command finished. If verify blocks,
 report the blocker and repair only the missing postconditions from the same
 current plan.