@sellable/mcp 0.1.467 → 0.1.469

package/dist/tools/prompts.js

@@ -373,7 +373,7 @@ export function getPostFindLeadsScoutRegistry() {
             codex: 'After confirm_lead_list copies source rows and the initial campaign-table execution slice exists, ask the filter-choice question immediately. Do not spawn anything before that question. After the answer, launch only Message Drafting. The filter-choice answer is the post-import user gate for this single worker; do not ask another question about starting it in step-wise or YOLO mode. The registry lookup is not a launch: after get_post_find_leads_scout_registry, immediately invoke Task/spawn_agent or the host background-agent mechanism before loading filter-leads.md, before saving rubrics, and before treating skip-filters as ready for message review. Both choices route through this kickoff; do not let filters_skipped jump straight from filter-choice to message-generation. If filters are chosen, the parent stays on Filter Rules and drafts/saves rubrics with MCP tools while Message Drafting runs in the background. If filters are skipped, move to Messages/message review only after Message Drafting has started or is ready; update_campaign(currentStep=messages) is not proof of launch. If the named Message Drafting custom agent is unavailable, spawn a generic gpt-5.5 xhigh Message Drafting background agent with the same lean campaign/table basis. When the background worker starts, persist workerDetails.messageDraftBuilder with statusSource "branch", status "branch-running", runId, startedAt, updatedAt, basisToken when known, and basis containing campaignId, selectedLeadListId, workflowTableId, filterChoice, and reviewBatchRowHash or reviewBatchRowIds; workerStatuses.messageDraftBuilder may be "running" as a simple badge only. Never put rich proof under workerStatuses and never use workerStatuses.messageDrafting. If no background-agent tool is callable, start the same full message branch inline before filter drafting or before skip-filter message review, record workerDetails.messageDraftBuilder with statusSource "parent-thread-fallback" and status "fallback-active", and require the same live context, prompt, assets, and validation gate before message review; do not wait until filters are saved and then call the registry.',
             claude: "After confirm_lead_list copies source rows and the initial campaign-table execution slice exists, ask the filter-choice question immediately. Do not invoke any Task/Agent before that question. After the answer, invoke only Message Drafting. If filters are chosen, parent drafts/saves rubrics with MCP tools while Message Drafting runs, asks filter approval, then joins Message Drafting. If filters are skipped, invoke only Message Drafting and move to Messages/message review.",
             parentThreadRule: 'Named agents are optional acceleration, but message drafting is not optional. The only normal background worker is Message Drafting. The filter-choice answer is the campaign-scoped go-ahead for this single post-import worker; do not ask another question to start it in step-wise or YOLO mode. If a named agent is unavailable, use a generic gpt-5.5 xhigh Message Drafting background agent. source work and filter work stay in the parent thread with MCP tools. If post-find-leads-message-scout is available, run it as the background Message Draft Builder after the filter-choice answer. The registry lookup is not a launch: get_post_find_leads_scout_registry only identifies the worker, and Message Drafting counts as started only after Task/spawn_agent or the host background-agent tool is invoked, or after the parent begins the same full message branch inline because no background-agent tool is callable. This launch must happen before loading filter-leads.md, save_rubrics, filter approval, or skip-filter message review; currentStep=messages is not proof of launch. If post-find-leads-message-scout is absent, do not customer-surface install status. Do not silently treat message drafting as started; the main thread must either launch the background worker or execute the same message branch from CampaignOffer state, selected source state, workflowTableId, and initial campaign-table execution slice rows. For a spawned worker, record workerDetails.messageDraftBuilder with statusSource branch / status branch-running, runId, startedAt, updatedAt, and basis containing campaignId, selectedLeadListId, workflowTableId, filterChoice, and reviewBatchRowHash or reviewBatchRowIds. workerStatuses.messageDraftBuilder is optional simple badge text only ("running", "ready", "blocked", "idle"); never put runId/statusSource/basis under workerStatuses and never use workerStatuses.messageDrafting. If no background-agent tool is callable, start that same full message branch inline before filter drafting or before skip-filter message review, record workerDetails.messageDraftBuilder with statusSource parent-thread-fallback / status fallback-active then ready, and require the same live context, prompt, assets, and validation gate before message review; do not report that as a background worker failure. If neither branch nor inline fallback can run, return blocked/retry-needed; do not wait until filters are saved and then call the registry. The Message Drafting handoff must be lean. Do not paste copied row counts, brief hashes, review-batch hashes, full reviewBatchRowIds, broad row data, or local debug artifacts into the spawn prompt. Local markdown/json files are not normal-path inputs. The filter-choice question is the first post-import user gate; do not load post-lead registries or filter references before it. Message drafting starts after the filter-choice answer, must load get_subskill_prompt({ subskillName: "generate-messages" }), and must load every required message asset named by generate-messages Mode 0 through get_subskill_asset before drafting. Reference Asset Loading means loading the required pre-draft reference pack before drafting; return blocked/retry-needed if required assets cannot be loaded; load ai-tells.md because it is never optional. The branch or parent-thread fallback loads the full generate-messages prompt and every referenced asset through get_subskill_asset. After generating/revising the candidate and before returning ready, must load get_subskill_prompt({ subskillName: "create-campaign-v2-validation" }) as the final internal validation gate, must read live campaign table state through scoped MCP/product tools, and must reject mismatched selectedLeadListId/workflowTableId/campaign/workspace input. Do not block when filters were chosen but leadScoringRubrics are not yet visible in the branch read; the parent owns save_rubrics and filter approval in parallel, so Message Drafting should return status ready with basisStatus usable_initial when campaign/list/table identity and the non-empty execution slice match. Do not use any alternate, local-artifact, or examples-only message prompt. User copy feedback, message QA, or rewrite requests before approve-message must be routed back to Message Drafting with the current recommendation, lean campaign/table basis, and latest user text; the parent must not rewrite or QA the template from memory and must not call update_campaign_brief before approve-message. The worker validates internally and returns only templateRecommendation, tokenFillRules, renderedGoodSample, status, approveOrReviseRecommendation, validationStatus, outputAt, outputHash, and blocked/retry detail. Do not render renderedFallbackSample, risk notes, or a qaReceipt on the normal happy path. On the filter path, save_rubrics keeps the browser on Filter Rules after save_rubrics so the user can approve the saved criteria; after saved-filter approval, move to Filter Leads with currentStep=apply-icp-rubric whether Message Drafting is ready or still running. Wait there for message approval. Enrichment, filtering, Generate Message cells, sender setup, sequence attach, and launch wait for template approval on the Use Template path. On the skip path, move to Messages/message review after Message Drafting has started or is ready and wait for message approval before enrichment or Settings. Do not render message review from checklist or shortcut instructions; message review requires a messageDraftRecommendation whose basis proves the generate-messages prompt, required message assets, and validation gate ran for the current campaign/table execution slice. Do not automatically rerun Message Drafting after filters/enrichment finish; show the initial draft by default and offer an enriched rewrite only with explicit user opt-in. Handoff and recommendation output are Markdown with labeled fields, not raw JSON.',
-            prepareMessagesRule: `Default create-campaign stays on the existing reviewBatchLimit:15 first campaign-table execution slice. For plain post-mint fill/load/refill requests, load get_subskill_prompt({ subskillName: "refill-sends-workflow" }), then call resolve_campaign_fill_route({ intent:"plain" }), list_senders, and get_campaign_refill_state for enough candidate campaigns to identify the campaign that most recently had scheduler-owned sends for the relevant sender set before any mutation. Route outcomes are route:"evergreen_horizon", route:"active_campaigns", and route:"ask_create"; if a plain managed-waterfall route has archived/completed skipped slots or does not cover the named sender set, immediately refetch with resolve_campaign_fill_route({ intent:"active" }) and inspect current dashboard-active ACTIVE/PAUSED campaign-backed sequence campaigns before declaring a sender blocked; stay in the same campaignOfferId/campaignId context after minting. Plain fill is not an alias for fill_campaign_horizon or campaign creation. fill_campaign_horizon is evergreen-only and is not the generic regular-campaign fill path. Campaign creation is allowed only after route:"ask_create" and explicit user selection; it is never the default response to plain fill. Treat "fill up/load sends" as capacity-fill preparation, and treat "refill senders", "fill senders", "max out senders", and "load everyone up" as sender-scoped capacity-fill preparation. For sender-scoped requests with no named senders, --yolo means all eligible healthy senders enrolled in active campaign-backed sequence campaigns in the active workspace; without --yolo, ask which eligible enrolled senders to refill before choosing campaigns or mutating. In non-yolo interactive Codex or Claude Code sessions, post the full sender/campaign/action approval packet in normal chat as Markdown first, then ask request_user_input/AskUserQuestion with exactly Accept and Decline and a compact body that refers back to the posted packet; do not duplicate the campaign table or full operator packet inside the structured question. The chat packet must show workspace, sender scope, a campaign-by-campaign table, exact ids/caps/dates, side effects, forbidden actions, and stop condition before mutation. Default --yolo horizon is a two-send-day horizon: two sender-local send days, skipping no-send-hour days. For campaign-scoped fill/refill, select the best recent-send campaign and calculate the bounded gap from healthy sender daily capacity minus projected coverage (actual sent plus future scheduler-owned scheduled sends) and ready-to-schedule rows, then prepare only that gap. For sender-scoped fill/refill, calculate the bounded gap per eligible sender across active enrolled campaigns, counting actual sent coverage, future scheduled rows, and ready-to-schedule rows across those campaigns, then choose the best same-sender campaign to fill each sender gap: prefer recent/future scheduler-owned sends for that sender, then strongest recent result evidence, then source health. Maintain a horizon saturation ledger per selected sender with selected send days, gross capacity, actual sent counts, future scheduler-owned scheduled counts, projected coverage, ready-to-schedule buffer, remaining projected gap, paid-InMail threshold feasibility, and the next MCP primitive. Do not stop after filling only one sender when the request was sender-scoped. In --yolo, continue through every safe selected sender/campaign action covered by the rendered packet, reread after each terminal apply/prep/start result, recompute the horizon saturation ledger, and keep going until projected coverage (sent + scheduled) fills the requested horizon or a concrete blocker/timeout is proven. Ready-to-schedule rows are buffer, not completion; if ready covers the projected gap but scheduled cells do not, run a bounded scheduler-settle loop and report awaiting_scheduler_after_ready_buffer as not complete when timeout is reached. Paid-InMail threshold changes and connection-campaign creation are explicit continuation options, never --yolo side effects. When no safe in-packet action remains return concrete continuation options with campaign names, exact ids, and which options require a new approval packet. Use the refill workflow to decide whether to enrich/prep more rows in that same recent-send/best-result campaign, add/import more rows to that same campaign/source path, use a different existing campaign only when the selected same-sender lane is blocked/exhausted/already loaded while the sender still has a gap, or ask what to create. Do not create warm-post-engager side campaigns. Surface sender-health blockers and paid-InMail threshold blockers separately from prepared/approved/scheduled counts. User-facing refill decisions must be campaign-name-first and sender-name-first, with ids as proof/execution targets only. For already-running regular campaigns that need Signal Discovery source replenishment, use the guarded currentStep clear with clearCurrentStepIfMatches:"running", campaign-scoped provider prompt/search/select, and import_leads with the existing sourceLeadListId when a newly approved selected-post scrape would otherwise return reusedExistingSourceList. Before prep, inspect get_campaign_refill_state.preparationFrontier. If hasLaterPreparedIsland:true or earliestUnpreparedRow exists before later successful enrichment, use rowSelector:{type:"needsEnrichment"} with columnRole:"enrich" in table-position order or start_campaign_message_preparation adaptive defaults; do not use the UI Jump anchor or needsGeneratedMessage as the refill cursor. After confirm_lead_list copies rows into an existing table, avoid fixed maxRowsToCheck:100; if confirm_lead_list returns USER_ADDED_ROWS_LIMIT_EXCEEDED, create a bounded same-source split from selectedLeadListId with get_rows_minimal/load_csv_linkedin_leads, confirm that smaller source list into the same campaign, and inspect reviewBatch only as diagnostics unless the approved packet explicitly prioritizes the just-copied split and earlier needsEnrichment rows are exhausted, dependency-blocked, or excluded. For approval diagnostics use rowSelector:{type:"needsApproval"} after current generated messages exist; mutating Approved cells still requires approvalMode:approve and exact bounded approval. Do not interpret checkedRows as enriched rows; it is only the table cursor. Prepared, approved, and ready_to_schedule rows are intermediate states; never call them scheduled unless a re-read proves scheduler-owned scheduled cells with non-null scheduledFor contribute to projected coverage, and never call them complete unless a final re-read proves projected coverage fills the requested horizon. Before source import, prep, approval, or selected paused campaign start, require exact visible approval or --yolo packet auto-accept and a fresh get_campaign_refill_state reread; stop if freshness.stateHash or exact ids changed. For "approve X messages", use approvalMode:approve only when explicitly requested. For "schedule X sends" or "fill sender sends", approve only when explicitly requested, then re-read campaign/table scheduled counts; if projected coverage does not fill the horizon, report prepared/approved/ready - awaiting scheduler instead of success. Do not call start_campaign as part of fill/schedule horizon. start_campaign is allowed in refill only for exact selected PAUSED, dashboard-active, campaign-backed sequence targets named in the bounded packet, and the packet must state that starting can let the product scheduler schedule/send approved eligible sequence actions. Never start unrelated, archived, completed, draft, direct, or non-selected campaigns, never broad approve-all, and never use direct scheduler writes. campaignId is CampaignOffer.id. If the user asks to stop preparation, the target is wrong, or status shows the wrong campaign/table, use cancel_campaign_message_preparation only for the exact active job. Low-level selectors are diagnostics and recovery only for this lane.`,
+            prepareMessagesRule: `Default create-campaign stays on the existing reviewBatchLimit:15 first campaign-table execution slice. For plain post-mint fill/load/refill requests, load get_subskill_prompt({ subskillName: "refill-sends-workflow" }), then call resolve_campaign_fill_route({ intent:"plain" }), list_senders, and get_campaign_refill_state for enough candidate campaigns to identify the campaign that most recently had scheduler-owned sends for the relevant sender set before any mutation. Route outcomes are route:"evergreen_horizon", route:"active_campaigns", and route:"ask_create"; if a plain managed-waterfall route has archived/completed skipped slots or does not cover the named sender set, immediately refetch with resolve_campaign_fill_route({ intent:"active" }) and inspect current dashboard-active ACTIVE/PAUSED campaign-backed sequence campaigns before declaring a sender blocked; stay in the same campaignOfferId/campaignId context after minting. Plain fill is not an alias for fill_campaign_horizon or campaign creation. fill_campaign_horizon is evergreen-only and is not the generic regular-campaign fill path. Campaign creation is allowed only after route:"ask_create" and explicit user selection; it is never the default response to plain fill. Treat "fill up/load sends" as capacity-fill preparation, and treat "refill senders", "fill senders", "max out senders", and "load everyone up" as sender-scoped capacity-fill preparation. For sender-scoped requests with no named senders, --yolo means all eligible healthy senders enrolled in active campaign-backed sequence campaigns in the active workspace; without --yolo, ask which eligible enrolled senders to refill before choosing campaigns or mutating. In non-yolo interactive Codex or Claude Code sessions, post the full sender/campaign/action approval packet in normal chat as Markdown first, then ask request_user_input/AskUserQuestion with exactly Accept and Decline and a compact body that refers back to the posted packet; do not duplicate the campaign table or full operator packet inside the structured question. The chat packet must show workspace, sender scope, a campaign-by-campaign table, exact ids/caps/dates, side effects, forbidden actions, and stop condition before mutation. Default --yolo horizon is a two-send-day horizon: two sender-local send days, skipping no-send-hour days. For campaign-scoped fill/refill, select the best recent-send campaign and calculate the bounded gap from healthy sender daily capacity minus projected coverage (actual sent plus future scheduler-owned scheduled sends) and ready-to-schedule rows, then prepare only that gap. For sender-scoped fill/refill, calculate the bounded gap per eligible sender across active enrolled campaigns, counting actual sent coverage, future scheduled rows, and ready-to-schedule rows across those campaigns, then choose the best same-sender campaign to fill each sender gap: prefer recent/future scheduler-owned sends for that sender, then strongest recent result evidence, then source health. Maintain a horizon saturation ledger per selected sender with selected send days, gross capacity, actual sent counts, future scheduler-owned scheduled counts, projected coverage, ready-to-schedule buffer, remaining projected gap, paid-InMail threshold feasibility, and the next MCP primitive. Do not stop after filling only one sender when the request was sender-scoped. In --yolo, continue through every safe selected sender/campaign action covered by the rendered packet, reread after each terminal apply/prep/start result, recompute the horizon saturation ledger, and keep going until projected coverage (sent + scheduled) fills the requested horizon or a concrete non-scheduler blocker is proven. Ready-to-schedule rows are buffer, not completion; if ready covers the projected gap but scheduled cells do not, run a persistent read-only scheduler wait/reread loop and keep the run open while awaiting_scheduler_after_ready_buffer is the only remaining state. Paid-InMail threshold changes and connection-campaign creation are explicit continuation options, never --yolo side effects. When no safe in-packet action remains return concrete continuation options with campaign names, exact ids, and which options require a new approval packet; do not return final completion for scheduler wait unless Christian explicitly asks for status or stops the run. Use the refill workflow to decide whether to enrich/prep more rows in that same recent-send/best-result campaign, add/import more rows to that same campaign/source path, use a different existing campaign only when the selected same-sender lane is blocked/exhausted/already loaded while the sender still has a gap, or ask what to create. Do not create warm-post-engager side campaigns. Surface sender-health blockers and paid-InMail threshold blockers separately from prepared/approved/scheduled counts. User-facing refill decisions must be campaign-name-first and sender-name-first, with ids as proof/execution targets only. For already-running regular campaigns that need Signal Discovery source replenishment, use the guarded currentStep clear with clearCurrentStepIfMatches:"running", campaign-scoped provider prompt/search/select, and import_leads with the existing sourceLeadListId when a newly approved selected-post scrape would otherwise return reusedExistingSourceList. Before prep, inspect get_campaign_refill_state.preparationFrontier. If hasLaterPreparedIsland:true or earliestUnpreparedRow exists before later successful enrichment, use rowSelector:{type:"needsEnrichment"} with columnRole:"enrich" in table-position order or start_campaign_message_preparation adaptive defaults; do not use the UI Jump anchor or needsGeneratedMessage as the refill cursor. After confirm_lead_list copies rows into an existing table, avoid fixed maxRowsToCheck:100; if confirm_lead_list returns USER_ADDED_ROWS_LIMIT_EXCEEDED, create a bounded same-source split from selectedLeadListId with get_rows_minimal/load_csv_linkedin_leads, confirm that smaller source list into the same campaign, and inspect reviewBatch only as diagnostics unless the approved packet explicitly prioritizes the just-copied split and earlier needsEnrichment rows are exhausted, dependency-blocked, or excluded. For approval diagnostics use rowSelector:{type:"needsApproval"} after current generated messages exist; mutating Approved cells still requires approvalMode:approve and exact bounded approval. Do not interpret checkedRows as enriched rows; it is only the table cursor. Prepared, approved, and ready_to_schedule rows are intermediate states; never call them scheduled unless a re-read proves scheduler-owned scheduled cells with non-null scheduledFor contribute to projected coverage, and never call them complete unless a final re-read proves projected coverage fills the requested horizon. Before source import, prep, approval, or selected paused campaign start, require exact visible approval or --yolo packet auto-accept and a fresh get_campaign_refill_state reread; stop if freshness.stateHash or exact ids changed. For "approve X messages", use approvalMode:approve only when explicitly requested. For "schedule X sends" or "fill sender sends", approve only when explicitly requested, then re-read campaign/table scheduled counts; if projected coverage does not fill the horizon, keep polling when ready buffer covers the gap and report only interim prepared/approved/ready - awaiting scheduler status if Christian asks. Do not call start_campaign as part of fill/schedule horizon. start_campaign is allowed in refill only for exact selected PAUSED, dashboard-active, campaign-backed sequence targets named in the bounded packet, and the packet must state that starting can let the product scheduler schedule/send approved eligible sequence actions. Never start unrelated, archived, completed, draft, direct, or non-selected campaigns, never broad approve-all, and never use direct scheduler writes. campaignId is CampaignOffer.id. If the user asks to stop preparation, the target is wrong, or status shows the wrong campaign/table, use cancel_campaign_message_preparation only for the exact active job. Low-level selectors are diagnostics and recovery only for this lane.`,
         },
     };
 }

package/dist/tools/refill-sends.js

@@ -142,6 +142,7 @@ export function refillSendsCommand(input = {}) {
         },
         firstOperationalSteps: [
             'Load get_subskill_prompt({ subskillName: "refill-sends-workflow" }) before any product operation.',
+            "A skill cannot create or invoke /goal by itself. If this refill is already running inside an active Codex goal, keep that goal open until every selected sender lane is horizon-filled by projected coverage (sent + scheduled), Christian explicitly stops/statuses the run, or a concrete non-scheduler blocker appears.",
             `Call get_refill_target_plan({ intent: "${intent}"${input.campaignId ? `, campaignId: "${input.campaignId}"` : ""}${input.tableId ? `, tableId: "${input.tableId}"` : ""}${senderIds.length > 0
                 ? `, senderIds: ${JSON.stringify(senderIds)}`
                 : ""}${senderNames.length > 0
@@ -151,7 +152,7 @@ export function refillSendsCommand(input = {}) {
                 : `, horizonSendDays: ${horizonSendDays}`}, approvalMode: "${approvalMode}" }) before any import, prep, approval, start, or schedule-affecting action.`,
             "If get_refill_target_plan returns status complete, report eligible sender ledger, gross target, selected days, sent count, scheduled count, projected count, campaign ids, targetShapeRevision, and no-op proof without asking for approval.",
             "Refill target lanes are only connection invites (send_invite) or paid InMails (send_inmail_closed). Do not count send_dm or send_inmail_open as horizon target capacity; they may exist in sequences, but the planner must pick the refill lane from the most recent active campaign-backed send evidence for each sender.",
-            "If remainingReadyOrProjectedGap is 0 but remainingProjectedGap is positive, run only a bounded read-only scheduler settle/reread loop; do not ask for prep/import/approval.",
+            "If remainingReadyOrProjectedGap is 0 but remainingProjectedGap is positive, run only a persistent read-only scheduler wait/reread loop; do not ask for prep/import/approval and do not close out while scheduler pickup is the only remaining state.",
             `Resolve route with resolve_campaign_fill_route({ intent: "${intent}"${input.campaignId ? `, campaignId: "${input.campaignId}"` : ""}${input.tableId ? `, tableId: "${input.tableId}"` : ""} }).`,
             'If the plain route shows stale managed waterfall evidence, archived/completed shared slots, or targets that do not cover the selected sender set, immediately call resolve_campaign_fill_route({ intent: "active" }) and inspect current dashboard-active ACTIVE/PAUSED campaign-backed sequence campaigns before declaring a sender blocked.',
             "Call list_senders and get_sender_routing, then resolve sender selectors against active enrolled campaign-backed sequence senders.",
@@ -164,12 +165,12 @@ export function refillSendsCommand(input = {}) {
             "Maintain a target-led horizon saturation ledger per selected sender from get_refill_target_plan: selected days, gross capacity, actual sent counts, future scheduler-owned scheduled counts, projected counts, ready-to-schedule buffer, remaining projected gap, paid InMail threshold feasibility, targetShapeRevision, stateRevision, and next MCP primitive.",
             "If paid InMail feasibility is below threshold, stale, or missing, report the exact sender/campaign/table/column threshold action or connection fallback; --yolo must not lower paid InMail thresholds or create campaigns.",
             "In --yolo or after one Accept, continue through every safe selected sender/campaign action covered by the rendered target packet; sent/scheduled-count progress changes stateRevision and should continue while targetShapeRevision is stable.",
-            "Do not complete a fill/schedule request until a final get_refill_target_plan or refill-state reread proves projected coverage (sent + scheduled) fills the horizon, or report a concrete blocker such as awaiting_scheduler_after_ready_buffer or paid_inmail_below_threshold.",
+            "Do not complete a fill/schedule request until a final get_refill_target_plan or refill-state reread proves projected coverage (sent + scheduled) fills the horizon. Treat awaiting_scheduler_after_ready_buffer as in-progress when ready buffer covers the gap; keep polling unless Christian stops/statuses the run or a concrete non-scheduler blocker such as paid_inmail_below_threshold appears.",
         ],
         approvalContract: yolo
-            ? "Auto-accept only the rendered bounded refill target packet after get_refill_target_plan and fresh reread. Continue through every safe apply/prep/start action inside that packet, including start_campaign only for exact selected PAUSED campaign-backed sequence refill targets named in the packet. After each action, rerun get_refill_target_plan; keep going while targetShapeRevision is stable and projected coverage (sent + scheduled) progresses toward the target, even though stateRevision changes. Ready-to-schedule rows are buffer, not completion. If ready buffer covers the projected gap, use only read-only scheduler settle/reread. Stop immediately if targetShapeRevision changes because sender set, route, ids, caps, dates, blockers, action class, paid InMail threshold feasibility, or side-effect class drifts. --yolo does not authorize lowering paid InMail thresholds or creating connection campaigns."
+            ? "Auto-accept only the rendered bounded refill target packet after get_refill_target_plan and fresh reread. Continue through every safe apply/prep/start action inside that packet, including start_campaign only for exact selected PAUSED campaign-backed sequence refill targets named in the packet. After each action, rerun get_refill_target_plan; keep going while targetShapeRevision is stable and projected coverage (sent + scheduled) progresses toward the target, even though stateRevision changes. Ready-to-schedule rows are buffer, not completion. If ready buffer covers the projected gap, use only persistent read-only scheduler wait/reread and keep the run open until projected coverage fills or Christian stops/statuses it. Stop immediately if targetShapeRevision changes because sender set, route, ids, caps, dates, blockers, action class, paid InMail threshold feasibility, or side-effect class drifts. --yolo does not authorize lowering paid InMail thresholds or creating connection campaigns."
             : hasSenderSelectors
-                ? "Before mutation, post the full bounded refill packet in normal chat as Markdown, including workspace, sender scope, campaign table, exact ids, caps/dates, gross target, sent count, scheduled count, projected count, ready buffer, remaining projected gap, paid InMail threshold feasibility, targetShapeRevision/stateRevision, side effects, forbidden actions, and stop condition. Then ask the final Accept/Decline structured approval question with a compact body that refers back to the posted packet instead of duplicating it. Only ask when get_refill_target_plan reports a positive remaining projected/ready gap. If target is complete by projected coverage, no-op without approval. If ready buffer covers the projected gap, run only read-only scheduler settle/reread. Threshold changes and campaign creation need separate explicit approval."
+                ? "Before mutation, post the full bounded refill packet in normal chat as Markdown, including workspace, sender scope, campaign table, exact ids, caps/dates, gross target, sent count, scheduled count, projected count, ready buffer, remaining projected gap, paid InMail threshold feasibility, targetShapeRevision/stateRevision, side effects, forbidden actions, and stop condition. Then ask the final Accept/Decline structured approval question with a compact body that refers back to the posted packet instead of duplicating it. Only ask when get_refill_target_plan reports a positive remaining projected/ready gap. If target is complete by projected coverage, no-op without approval. If ready buffer covers the projected gap, run only persistent read-only scheduler wait/reread and keep the run open until projected coverage fills or Christian stops/statuses it. Threshold changes and campaign creation need separate explicit approval."
                 : "Ask which eligible enrolled senders to refill first, then, before mutation, post the full bounded refill packet in normal chat as Markdown and ask the final Accept/Decline structured approval question with a compact body that refers back to the posted packet.",
         forbiddenActions: [
             "start_campaign outside an exact selected PAUSED campaign-backed refill packet",

package/dist/tools/refill-target-plan.js

@@ -1,8 +1,234 @@
 import { getApi } from "../api.js";
+const REFILL_TARGET_ACTION_TYPES = [
+    "send_invite",
+    "send_inmail_closed",
+];
+const REFILL_TARGET_ACTION_SET = new Set(REFILL_TARGET_ACTION_TYPES);
 async function postRefillTargetPlan(body) {
     const api = getApi();
     return api.post("/api/v3/mcp/refill-target-plan", body);
 }
+function isRecord(value) {
+    return Boolean(value && typeof value === "object" && !Array.isArray(value));
+}
+function allowedActionType(value) {
+    return typeof value === "string" && REFILL_TARGET_ACTION_SET.has(value)
+        ? value
+        : null;
+}
+function actionTypesFrom(value) {
+    if (!Array.isArray(value))
+        return [];
+    return [...new Set(value.map(allowedActionType).filter(Boolean))];
+}
+function numberValue(value) {
+    return typeof value === "number" && Number.isFinite(value) ? value : 0;
+}
+function evidenceLatestMs(evidence) {
+    const latestAt = evidence.latestAt;
+    if (typeof latestAt !== "string")
+        return 0;
+    const timestamp = new Date(latestAt).getTime();
+    return Number.isFinite(timestamp) ? timestamp : 0;
+}
+function chooseEvidenceAction(evidence, fallback) {
+    const byAction = new Map();
+    for (const item of evidence) {
+        if (!isRecord(item))
+            continue;
+        const actionType = allowedActionType(item.actionType);
+        if (!actionType)
+            continue;
+        const current = byAction.get(actionType) ?? { count: 0, latestMs: 0 };
+        current.count += numberValue(item.count);
+        current.latestMs = Math.max(current.latestMs, evidenceLatestMs(item));
+        byAction.set(actionType, current);
+    }
+    const [best] = [...byAction.entries()].sort((a, b) => {
+        if (a[1].latestMs !== b[1].latestMs)
+            return b[1].latestMs - a[1].latestMs;
+        if (a[1].count !== b[1].count)
+            return b[1].count - a[1].count;
+        return (REFILL_TARGET_ACTION_TYPES.indexOf(a[0]) -
+            REFILL_TARGET_ACTION_TYPES.indexOf(b[0]));
+    });
+    return best?.[0] ?? fallback[0] ?? null;
+}
+function senderActionKey(senderId, actionType) {
+    return typeof senderId === "string" && typeof actionType === "string"
+        ? `${senderId}:${actionType}`
+        : null;
+}
+function sanitizeCounts(counts, selectedKeys) {
+    if (!Array.isArray(counts))
+        return [];
+    return counts.filter((item) => {
+        if (!isRecord(item))
+            return false;
+        const actionType = allowedActionType(item.actionType);
+        const key = senderActionKey(item.senderId, actionType);
+        return Boolean(key && selectedKeys.has(key));
+    });
+}
+function sanitizeActionCandidates(candidates, selectedKeys, status, remainingReadyOrProjectedGap, remainingProjectedGap) {
+    const filtered = Array.isArray(candidates)
+        ? candidates.filter((item) => {
+            if (!isRecord(item))
+                return false;
+            const actionType = item.actionType;
+            if (actionType === undefined)
+                return item.type === "wait_for_scheduler";
+            const allowed = allowedActionType(actionType);
+            const key = senderActionKey(item.senderId, allowed);
+            return Boolean(key && selectedKeys.has(key));
+        })
+        : [];
+    if (status === "awaiting_scheduler_after_ready_buffer" &&
+        remainingProjectedGap > 0 &&
+        remainingReadyOrProjectedGap === 0 &&
+        !filtered.some((item) => item.type === "wait_for_scheduler")) {
+        filtered.push({
+            type: "wait_for_scheduler",
+            reason: "ready buffer covers the projected target gap but scheduledFor coverage is still short",
+        });
+    }
+    return filtered;
+}
+function sanitizeBlockers(blockers, selectedKeys) {
+    if (!Array.isArray(blockers))
+        return [];
+    return blockers.filter((item) => {
+        if (!isRecord(item))
+            return false;
+        const detail = item.detail;
+        const code = String(item.code ?? "");
+        if (typeof detail !== "string")
+            return true;
+        const detailSenderId = detail.split(":")[0];
+        if (code.startsWith("paid_inmail_")) {
+            return selectedKeys.has(`${detailSenderId}:send_inmail_closed`);
+        }
+        if (detail.includes(":send_dm") || detail.includes(":send_inmail_open")) {
+            return false;
+        }
+        const parts = detail.split(":");
+        if (parts.length < 2)
+            return true;
+        const actionType = allowedActionType(parts[parts.length - 1]);
+        if (!actionType)
+            return true;
+        const senderId = parts[0];
+        return selectedKeys.size === 0 || selectedKeys.has(`${senderId}:${actionType}`);
+    });
+}
+function sanitizeRefillTargetPlanResult(result) {
+    if (!isRecord(result) || !isRecord(result.target))
+        return result;
+    const target = result.target;
+    const rawSelections = Array.isArray(target.actionSelections)
+        ? target.actionSelections
+        : [];
+    const rawSenderPlans = Array.isArray(target.senderPlans)
+        ? target.senderPlans
+        : [];
+    const selectedBySender = new Map();
+    for (const rawSelection of rawSelections) {
+        if (!isRecord(rawSelection) || typeof rawSelection.senderId !== "string") {
+            continue;
+        }
+        const fallback = actionTypesFrom(rawSelection.actionTypes);
+        const evidence = Array.isArray(rawSelection.evidence)
+            ? rawSelection.evidence
+            : [];
+        const chosen = chooseEvidenceAction(evidence, fallback);
+        if (chosen)
+            selectedBySender.set(rawSelection.senderId, chosen);
+    }
+    for (const rawPlan of rawSenderPlans) {
+        if (!isRecord(rawPlan) ||
+            typeof rawPlan.senderId !== "string" ||
+            selectedBySender.has(rawPlan.senderId)) {
+            continue;
+        }
+        const actionType = allowedActionType(rawPlan.actionType);
+        if (actionType)
+            selectedBySender.set(rawPlan.senderId, actionType);
+    }
+    const selectedKeys = new Set([...selectedBySender.entries()].map(([senderId, actionType]) => `${senderId}:${actionType}`));
+    const actionTypes = [...new Set(selectedBySender.values())];
+    if (selectedKeys.size === 0)
+        return result;
+    const senderPlans = rawSenderPlans.filter((plan) => isRecord(plan) &&
+        selectedKeys.has(`${String(plan.senderId)}:${String(plan.actionType)}`));
+    const selectedDays = Array.isArray(target.selectedDays)
+        ? target.selectedDays.filter((day) => isRecord(day) &&
+            selectedKeys.has(`${String(day.senderId)}:${String(day.actionType)}`))
+        : [];
+    const actionSelections = rawSelections
+        .filter((selection) => isRecord(selection) &&
+        typeof selection.senderId === "string" &&
+        selectedBySender.has(selection.senderId))
+        .map((selection) => {
+        const actionType = selectedBySender.get(selection.senderId);
+        const evidence = Array.isArray(selection.evidence)
+            ? selection.evidence.filter((item) => isRecord(item) && item.actionType === actionType)
+            : [];
+        return {
+            ...selection,
+            actionTypes: actionType ? [actionType] : [],
+            evidence,
+        };
+    });
+    const grossTarget = senderPlans.reduce((sum, plan) => sum + numberValue(plan.grossTarget), 0);
+    const sent = senderPlans.reduce((sum, plan) => sum + numberValue(plan.sent), 0);
+    const scheduled = senderPlans.reduce((sum, plan) => sum + numberValue(plan.scheduled), 0);
+    const projected = sent + scheduled;
+    const readyBuffer = senderPlans.reduce((sum, plan) => sum + numberValue(plan.readyBuffer), 0);
+    const remainingScheduledGap = senderPlans.reduce((sum, plan) => sum + numberValue(plan.remainingScheduledGap), 0);
+    const remainingProjectedGap = senderPlans.reduce((sum, plan) => sum + numberValue(plan.remainingProjectedGap), 0);
+    const remainingReadyOrProjectedGap = senderPlans.reduce((sum, plan) => sum + numberValue(plan.remainingReadyOrProjectedGap), 0);
+    const blockers = sanitizeBlockers(result.blockers, selectedKeys);
+    const status = blockers.some((blocker) => ["sender_disconnected", "sender_sales_nav_disconnected"].includes(String(blocker.code))) || grossTarget <= 0
+        ? "blocked"
+        : remainingProjectedGap === 0
+            ? "complete"
+            : remainingReadyOrProjectedGap === 0
+                ? "awaiting_scheduler_after_ready_buffer"
+                : "needs_refill";
+    return {
+        ...result,
+        status,
+        request: isRecord(result.request)
+            ? { ...result.request, actionTypes }
+            : result.request,
+        target: {
+            ...target,
+            actionSelections,
+            selectedDays,
+            senderPlans,
+            grossTarget,
+            sent,
+            scheduled,
+            projected,
+            readyBuffer,
+            remainingScheduledGap,
+            remainingProjectedGap,
+            remainingReadyOrProjectedGap,
+            remainingReadyOrScheduledGap: remainingReadyOrProjectedGap,
+        },
+        coverage: isRecord(result.coverage)
+            ? {
+                ...result.coverage,
+                sentCounts: sanitizeCounts(result.coverage.sentCounts, selectedKeys),
+                scheduledCounts: sanitizeCounts(result.coverage.scheduledCounts, selectedKeys),
+                readyCounts: sanitizeCounts(result.coverage.readyCounts, selectedKeys),
+            }
+            : result.coverage,
+        actionCandidates: sanitizeActionCandidates(result.actionCandidates, selectedKeys, status, remainingReadyOrProjectedGap, remainingProjectedGap),
+        blockers,
+        mcpSanitizedRefillLanes: true,
+    };
+}
 export const refillTargetPlanToolDefinitions = [
     {
         name: "get_refill_target_plan",
@@ -68,8 +294,8 @@ export const refillTargetPlanToolDefinitions = [
         },
     },
 ];
-export function getRefillTargetPlan(input = {}) {
-    return postRefillTargetPlan({
+export async function getRefillTargetPlan(input = {}) {
+    const result = await postRefillTargetPlan({
         intent: input.intent,
         horizonSendDays: input.horizonSendDays,
         untilDate: input.untilDate,
@@ -81,4 +307,5 @@ export function getRefillTargetPlan(input = {}) {
         actionTypes: input.actionTypes,
         approvalMode: input.approvalMode,
     });
+    return sanitizeRefillTargetPlanResult(result);
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sellable/mcp",
-  "version": "0.1.467",
+  "version": "0.1.469",
   "type": "module",
   "description": "Sellable MCP server for Claude Code and Codex campaign workflows",
   "main": "dist/index.js",

package/skills/refill-sends/SKILL.md

@@ -97,6 +97,13 @@ senders" as sender-scoped requests. The target set is senders enrolled in active
 campaign-backed sequence campaigns, not the first active campaign returned by a
 resolver.
 
+Goal-mode continuation: a skill cannot create or invoke `/goal` by itself. When
+this command is already running inside an active Codex goal, keep that goal open
+until every selected sender lane is horizon-filled by projected coverage
+(`sent + scheduled`), Christian explicitly stops/statuses the run, or a concrete
+non-scheduler blocker appears. Do not call the goal complete or blocked only
+because the current state is `awaiting_scheduler_after_ready_buffer`.
+
 Load the internal workflow prompt before taking any operational step:
 
 ```text
@@ -131,9 +138,13 @@ Short form: trust the target plan's inferred lane only when it is a
 connection-invite or paid-InMail refill lane.
 If the target plan is complete by projected coverage, report that the selected
 target is already filled and no-op without asking for approval. If the ready
-buffer covers the projected gap but scheduled coverage is still short, run only
-a bounded read-only scheduler settle/reread loop and report
-`awaiting_scheduler_after_ready_buffer` if it does not settle.
+buffer covers the projected gap but scheduled coverage is still short, keep the
+run open in a persistent read-only scheduler wait loop. Poll
+`get_refill_target_plan` every 60-120 seconds, or on the host's next continuation
+interval, until projected coverage fills the target, a concrete non-scheduler
+blocker appears, or Christian explicitly asks to stop or only receive a status
+report. Treat `awaiting_scheduler_after_ready_buffer` as an in-progress wait
+state, not a close-out condition.
 If paid InMail credit facts are stale or missing and the target plan returns a
 `refresh_paid_inmail_credits` action candidate, include the exact sender id,
 campaign/table/column proof, expected sender-credit-cache writes, and rerun plan
@@ -208,11 +219,13 @@ projected gap, paid-InMail feasibility, `targetShapeRevision`,
 `stateRevision`, and the next MCP primitive that can reduce the gap. After every
 apply/prep/start result, wait for processing, reread the target plan/refill
 state, recompute the ledger, then keep applying safe bounded actions until
-projected coverage fills the horizon or a concrete blocker/timeout is proven.
+projected coverage fills the horizon or a concrete non-scheduler blocker is
+proven.
 If ready rows cover the projected gap but the scheduler has not picked them up
-yet, run a bounded scheduler settle loop and report
-`awaiting_scheduler_after_ready_buffer` as not complete when the timeout is
-reached.
+yet, run the persistent read-only scheduler wait loop. Do not finish the refill
+goal, mark it complete, or mark it blocked only because it is still
+`awaiting_scheduler_after_ready_buffer`; keep waiting unless Christian stops the
+run or the host cannot continue.
 
 In `--yolo`, the default two-day fill horizon is two send days unless
 `--until`/`untilDate` is provided. If an until date is provided, compute bounded

package/skills/refill-sends-workflow/SKILL.md

@@ -60,6 +60,13 @@ senders", and "load everyone up". A sender-scoped request targets senders
 enrolled in active campaign-backed sequence campaigns, not one arbitrary active
 campaign.
 
+Goal-mode continuation: a skill cannot create or invoke `/goal` by itself. When
+this workflow is already running inside an active Codex goal, keep that goal
+open until every selected sender lane is horizon-filled by projected coverage
+(`sent + scheduled`), Christian explicitly stops/statuses the run, or a concrete
+non-scheduler blocker appears. `awaiting_scheduler_after_ready_buffer` is an
+in-progress wait state, not a reason to mark the goal complete or blocked.
+
 1. Call `get_refill_target_plan` first. This read-only target plan is the
    canonical opening receipt: eligible senders, selected sender-local days,
    gross target, inferred per-sender send lane/action selections, actual sent
@@ -85,9 +92,13 @@ campaign.
    scheduled count, projected count, campaign ids, and no-op proof without
    asking for approval or mutating.
    If `remainingReadyOrProjectedGap:0` but `remainingProjectedGap>0`, run only a
-   bounded read-only scheduler settle/reread loop; do not ask for
-   prep/import/approval. If the scheduler still does not fill, report
-   `awaiting_scheduler_after_ready_buffer`.
+   persistent read-only scheduler wait/reread loop; do not ask for
+   prep/import/approval. Poll `get_refill_target_plan` every 60-120 seconds, or
+   on the host's next continuation interval, until projected coverage fills,
+   a concrete non-scheduler blocker appears, or Christian explicitly asks to
+   stop or only receive a status report. Treat
+   `awaiting_scheduler_after_ready_buffer` as an in-progress wait state, not a
+   close-out condition.
    If paid InMail credit facts are stale or missing and the target plan returns a
    `refresh_paid_inmail_credits` action candidate, include the exact sender id,
    campaign/table/column proof, expected sender-credit-cache write, and rerun plan
@@ -242,12 +253,15 @@ exceeds the sender's horizon capacity for the selected send days. Put another
 way: complete when the same daily-limit/readback model would show no remaining
 send-day capacity for that selected lane. Ready-to-schedule rows are only buffer
 for the product scheduler. If ready plus projected coverage covers the horizon
-but scheduled cells do not yet, run a bounded read-only scheduler settle loop:
+but scheduled cells do not yet, run a persistent read-only scheduler wait loop:
 wait, reread, recompute the ledger, and continue until projected coverage is
-proved or the loop reaches an explicit timeout/blocker. Timeout is
-`awaiting_scheduler_after_ready_buffer`, not success, and it does not need a
-prep/import/approval packet. Short form: ready buffer is not success.
-Short form: use a bounded scheduler settle loop before calling it blocked.
+proved, a concrete non-scheduler blocker appears, or Christian explicitly stops
+or asks for status only. `awaiting_scheduler_after_ready_buffer` is not success
+and is not a terminal blocker for an active refill goal; it is the poll state
+that keeps the thread waiting. It does not need a prep/import/approval packet.
+Short form: ready buffer is not success.
+Short form: keep polling the scheduler instead of closing out while ready buffer
+covers the gap.
 Short form: `--yolo refill senders` completes only on projected horizon saturation or a concrete blocker.
 
 Rank candidates in this order:
@@ -481,10 +495,10 @@ same refill request, do not ask the `Accept` / `Decline` question. Instead:
    `get_refill_target_plan`, reread state, settle processing when needed,
    recompute the horizon saturation ledger, and continue with the next smallest
    safe action inside the same bounded packet until every selected sender is
-   saturated by projected coverage or blocked by evidence. Do not stop at
-   "loaded" or "awaiting scheduler" unless no in-packet MCP action remains and
-   the scheduler-settle loop times out; report that as a blocker, not a completed
-   refill.
+   saturated by projected coverage or blocked by non-scheduler evidence. Do not
+   stop at "loaded" or "awaiting scheduler"; when no in-packet MCP mutation
+   remains and ready rows cover the gap, keep the run open in read-only
+   scheduler polling until the sender is projected-full or Christian stops it.
 
 In `--yolo`, do not stop after the first selected campaign if the request was
 sender-scoped and more selected senders or same-packet start-eligible campaigns
@@ -579,10 +593,11 @@ is also short, run the next bounded MCP primitive that can create more eligible
 rows: `fill_campaign_horizon` for the selected evergreen target, or
 `start_campaign_message_preparation`, source import/replenishment, and bounded
 approval for the selected regular target. If projected coverage is short but
-ready buffer covers the gap, keep polling the scheduler until it fills or the
-explicit scheduler-settle timeout is hit. Never mark the refill complete while a
-daily limit/readback equivalent would still show the selected send day below
-capacity.
+ready buffer covers the gap, keep polling the scheduler until it fills, a
+concrete non-scheduler blocker appears, or Christian explicitly stops/statuses
+the run. Never mark the refill complete or blocked while a daily limit/readback
+equivalent would still show the selected send day below capacity and the only
+remaining state is scheduler pickup.
 
 ## Evergreen Campaign Discipline