@sellable/mcp 0.1.295 → 0.1.297

package/dist/tools/rows.js

@@ -97,7 +97,25 @@ export async function getTableRowsMinimal(tableId, options) {
     return api.get(path);
 }
 export function normalizeRowIds(rowIds) {
-    const rawIds = Array.isArray(rowIds) ? rowIds : rowIds.split(",");
+    if (Array.isArray(rowIds)) {
+        return rowIds.map((rowId) => rowId.trim()).filter(Boolean);
+    }
+    const trimmed = rowIds.trim();
+    if (trimmed.startsWith("[") && trimmed.endsWith("]")) {
+        try {
+            const parsed = JSON.parse(trimmed);
+            if (Array.isArray(parsed)) {
+                return parsed
+                    .filter((rowId) => typeof rowId === "string")
+                    .map((rowId) => rowId.trim())
+                    .filter(Boolean);
+            }
+        }
+        catch {
+            // Fall through to comma-splitting for malformed JSON-like input.
+        }
+    }
+    const rawIds = rowIds.split(",");
     return rawIds.map((rowId) => rowId.trim()).filter(Boolean);
 }
 export async function getRows(tableId, rowIds) {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sellable/mcp",
-  "version": "0.1.295",
+  "version": "0.1.297",
   "type": "module",
   "description": "Sellable MCP server for Claude Code and Codex campaign workflows",
   "main": "dist/index.js",

package/skills/create-campaign-v2/references/validation-criteria.md

@@ -87,6 +87,9 @@ Required:
   the brief justifies absence with reference to a specific archived winner.
   If a candidate uses `two options:`, option `a)` and option `b)` must be
   separated by a blank line so the CTA scans cleanly on mobile.
+- **Template spacing enforcement.** The Selected Winner and Approved Message
+  Template must use real blank lines between beats/sentences. Reject any body
+  with 3+ consecutive non-empty prose lines separated only by single newlines.
 - **All Sellable cleanup rules, including all 8 substance filters from
   `sellable-cleanup-rules.md`, MUST PASS per candidate.** A candidate that fails
   any cleanup rule or substance filter is BLOCKED. The Finalizer Pass CANNOT

package/skills/create-campaign-v2-tail/SKILL.md

@@ -237,7 +237,7 @@ headlineICPCriteria })` ->
      re-run a narrow campaign-scoped `search_signals` call to recover current
      post rows, or ask the user to promote the desired posts in the UI and then
      retry `import_leads`.
-	     Start Import approval is the explicit confirmation for this selected-post
+     Start Import approval is the explicit confirmation for this selected-post
      scrape; do not ask for a second yes/no gate between
      `select_promising_posts` and `import_leads`.
    - Sales Nav: `get_provider_prompt({ provider: "sales-nav", campaignOfferId,
@@ -387,6 +387,26 @@ templateRevision: "current" })` until the first current-revision generated
 6. On success, keep `currentStep: "auto-execute-messaging"` and ask the user to
    approve the generated message before continuing to Settings. Only that
    approval may move the campaign to Settings / `awaiting-user-greenlight`.
+7. When approval is given — or auto-approved in YOLO when the Recommendation is
+   `approve-message` — you MUST actually mark the reviewed passing rows approved
+   by calling `update_cell({ cellId: <approveCellId>, value: true })` for at
+   least one generated-message row, preferably two when available (read each
+   `approveCellId` from `get_rows`). The campaign UI gates "Next: Settings" on
+   at least one row whose `Approved` cell is true:
+   moving `currentStep` to `settings`/`awaiting-user-greenlight` with zero
+   approved rows desyncs the watch UI, which stays stuck on Generate Messages
+   showing "Approve at least one draft to continue." Setting the `Approved`
+   flag via `update_cell({ cellId: approveCellId, value: true })` is explicitly
+   allowed; the "do not use `update_cell`" rule below applies ONLY to message
+   bodies, never to the `Approved` flag. Advance `currentStep` only after the
+   approve writes succeed.
+   If any Settings/sequence/send/start step call returns
+   `error: "approved_message_required"` with
+   `requiredAction: "approve_generated_message"`, recover by reading rows with
+   `get_rows`, writing `update_cell({ cellId: approveCellId, value: true })`
+   for a completed generated-message row, confirming the approved count is at
+   least 1, then retrying the blocked action. Do not ignore or route around
+   that error with a different currentStep write.
 
 **Do NOT hand-write message bodies via `update_cell`.** `update_cell`
 is reachable for legitimate operator overrides AFTER the tail hands
@@ -435,9 +455,15 @@ strings, which is why Step 16 requires Step 15 to be complete.
    `maxRevisionRounds` cap.
 7. On success, keep `currentStep: "auto-execute-messaging"`, show that the
    first passing generated message is ready in Messages, and ask for approval
-   before Settings. Only after the user approves the generated message should
-   `update_campaign({ campaignId, currentStep: "awaiting-user-greenlight" })`
-   run.
+   before Settings. When the user approves (or YOLO auto-approves on an
+   `approve-message` recommendation), first write the approval to the rows with
+   `update_cell({ cellId: <approveCellId>, value: true })` for at least one
+   reviewed passing row, preferably two when available, confirm the table now
+   reports `approved >= 1`, and only then run
+   `update_campaign({ campaignId, currentStep: "awaiting-user-greenlight" })`.
+   Never advance to Settings while the table still reports `approved: 0` — the
+   builder UI will refuse to leave Generate Messages and the watch step will
+   desync from the headless step.
 
 Critique failure modes NEVER escalate. A critic timeout, a total
 timeout, a budget trip, a fake-proof rejection, or an unsupported-
@@ -470,7 +496,7 @@ Shape:
    sender to attach. Attach only after the user chooses. In explicit UAT safe
    mode, use only the safe mock sender; never pick a real sender.
 7. Call `update_campaign({ campaignId, senderIds: [selectedSenderId],
-currentStep: "sequence" })` to attach the sender through the v3 senders
+   currentStep: "sequence" })` to attach the sender through the v3 senders
    route and describe the Sequence view.
 8. Call `attach_recommended_sequence({ campaignId, currentStep: "send" })`
    (bind the tier-recommended sequence to the campaign). Explain the sequence
@@ -482,12 +508,12 @@ currentStep: "sequence" })` to attach the sender through the v3 senders
    `update_campaign({ campaignId, currentStep: "send" })`.
 9. Surface the `handoff.orientation` string from `auto-execute.yaml` without
    repeating the watch URL.
-11. Ask the final launch greenlight with the structured question function:
+10. Ask the final launch greenlight with the structured question function:
     Start campaign, Review campaign first, or Pause here.
-12. STOP unless the user explicitly chooses Start campaign. Do NOT call
+11. STOP unless the user explicitly chooses Start campaign. Do NOT call
     `start_campaign` from Step 16 itself; that belongs only to the Claude
     greenlight path. The autonomous tail ends here.
-13. Make the credit boundary explicit in the handoff: only the first review
+12. Make the credit boundary explicit in the handoff: only the first review
     batch has been enriched/messaged; expanding to more leads requires a
     separate user instruction.
 
@@ -558,7 +584,7 @@ runs.
 | `references/final-handoff-contract.md`           | Step 16, and every Claude greenlight turn                                 |
 | `references/parallel-critique-protocol.md`       | Step 15 when `messaging.critique.enabled` is true                         |
 | `references/thomas-variant-selection.md`         | Step 15 when `messaging.critique.opus.enabled` is true                    |
-| `references/sellable-cleanup-rules.md`          | Any critique rewrite, before persisting                                   |
+| `references/sellable-cleanup-rules.md`           | Any critique rewrite, before persisting                                   |
 | `core/auto-execute.yaml`                         | Start of Step 13, load once; all tail steps read parsed values            |
 | `core/auto-execute.README.md`                    | When tuning `auto-execute.yaml` knobs or reviewing threshold-trip logs    |
 

package/skills/create-campaign-v2-validation/SKILL.md

@@ -252,6 +252,11 @@ Orchestration requirements:
   product/problem -> next step. If two adjacent lines could be swapped, deleted,
   or connected with `anyway` without changing the meaning, the transition is
   fake and the draft must be revised.
+- pass the template-spacing gate before writing findings. The Selected Winner
+  and any Approved Message Template must use actual blank lines between message
+  beats/sentences. If there are 3+ consecutive non-empty prose lines separated
+  only by single newlines, the draft is blocked until rewritten with double
+  newlines.
 - pass the final-line/PS "so what?" gate before writing findings. The final
   line must lower commitment, preview a specific next step, answer a
   trust/category objection, tie proof to buyer value, or be omitted.

package/skills/generate-messages/SKILL.md

@@ -2118,6 +2118,15 @@ signoff is a talk-at shape).
 
 - **each sentence is its own paragraph** — put a blank line between every sentence in the body, even short ones
 - literally: the body should render as a sequence of one-line paragraphs separated by blank lines, not as multi-sentence paragraphs
+- the approved template must contain the literal blank lines. Do not fake
+  paragraph spacing by putting each sentence on adjacent single-newline lines.
+  If the template or Selected Winner has 3+ consecutive non-empty prose lines
+  with no blank line between them, mark it `revise-message` / `blocked` and
+  rewrite before approval.
+- bad shape:
+  `saw you in a few conversations about corporate comms, so may be off, but this seemed relevant.\nyour team probably puts a lot of work into getting people on webinars.\nArbor turns those recordings into ready-to-publish content.`
+- good shape:
+  `saw you in a few conversations about corporate comms, so may be off, but this seemed relevant.\n\nyour team probably puts a lot of work into getting people on webinars.\n\nArbor turns those recordings into ready-to-publish content.`
 - this matches the archived winners (Revvix, Galley, Superposition all paragraph-break per sentence). It gives the reader one idea at a time and lets short sentences breathe
 - mobile scanability is a hard requirement. The winner should read cleanly in a one-thumb scroll on a phone
 - keep most sentences in the **6-14 word** range. If a sentence is above ~18 words or has more than one comma, split it
@@ -2913,6 +2922,7 @@ research → condense → 10 angle agents in parallel → finalizer combines bes
 - Flow skeleton: opener → pain → **what the product IS** → **what it DOES** (one action per line, up to three; prefer short bullets for 3 repeated-subject product actions) → deployment ease → CTA → optional PS
 - A cold reader must be able to state what the product does in one sentence after reading. Require a crisp `Product is an X that does Y` anchor before any action breakdown. Do not gesture at "that chain" / "the stack" / "that work"
 - Blank line between every sentence in the body. The body renders as a sequence of one-line paragraphs separated by blank lines, not as multi-sentence paragraphs. Target 6-10 one-line paragraphs
+- The approved template must include actual double-newline paragraph breaks. Never approve or return a body with 3+ consecutive non-empty prose lines separated only by single newlines.
 - 5th-grade reading level by default. Cut glue language (handoff, order-to-cash, rip-and-replace). Keep brief-native product/tool names (Shopify, HubSpot)
 - No feature/benefit marketing bullet lists, no "I noticed...", no compliment sandwiches, no em dashes unless the canonical example uses one. Exception: use a short bullet stack when 3 adjacent product actions repeat the same subject pattern and bullets improve mobile readability.
 - No synthesized framing ("at your stage", "in a setup like yours", "running X means...", "X means you're likely...")