@sellable/mcp 0.1.477 → 0.1.479

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 target is the scheduler-forward 48-hour target window: sender-local send days whose configured sending windows overlap the rolling target window, 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 target-window 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. The structured packet lives in target.senderRefillPlans[] with target.eligibleSenderLedger, campaignRanking.options, sourcePlan, nextActions, manualAlternates, and target.globalActionQueue; preserve Need to prepare, Goal, Already sent, Scheduled, Ready and waiting to be scheduled, and Still need labels. In --yolo, execute exactly one globally ranked primitive from the post-refresh target.globalActionQueue[0], then rerun get_refill_target_plan before choosing another action. Refill action ladder: approve generated rows only when an explicit bounded approval gate exists, process all existing same-campaign unenriched/unprepared rows in bounded batches before any source work, then copy bounded net-new rows from the selected source (selectedLeadListId, provider, and source fingerprint preserved), then use provider-aligned source-more. A new source or provider switch changes the reply-rate baseline and is a manual alternate, not a --yolo side effect. The refill_sends MCP command maintains a run-local refreshedPaidInmailSenderIds set: if the first target plan contains refresh_paid_inmail_credits for stale/missing paid-InMail facts, refill_sends refreshes each selected paid-InMail sender at most once, reruns get_refill_target_plan, and returns autoPaidInmailRefresh plus the post-refresh targetPlan before the operator chooses prep/source-copy/read-only wait. Do not present paid-credit refresh as the next operator action after refill_sends has returned a post-refresh targetPlan. 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/source-copy/read-only wait result, recompute the target-window saturation ledger, and keep going until projected coverage (sent + scheduled) fills the scheduler-forward target window 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, report loaded, awaiting scheduler and 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. Trust schedulerGate.sendable and scheduler blockers over raw unipileAccountStatus labels alone. For long-running prep use compact prep status checks, reread target plans after prep or cancel, avoid huge parallel target-plan reads when output is large, and if prepared/ready rows grow but sender-level projected coverage does not move after one bounded settle loop, pivot to compact prep status or a scheduler-proven lane instead of waiting on campaign-level ready counts. 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 scheduler-forward target window. 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.`,
+            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 target is the scheduler-forward 48-hour target window: sender-local send days whose configured sending windows overlap the rolling target window, 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 target-window 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. The structured packet lives in target.senderRefillPlans[] with target.eligibleSenderLedger, campaignRanking.options, sourcePlan, nextActions, manualAlternates, and target.globalActionQueue; preserve Need to prepare, Goal, Already sent, Scheduled, Ready and waiting to be scheduled, and Still need labels. In --yolo, execute exactly one globally ranked primitive from the post-refresh target.globalActionQueue[0], then rerun get_refill_target_plan before choosing another action. Refill action ladder: approve generated rows only when an explicit bounded approval gate exists, process all existing same-campaign unenriched/unprepared rows in bounded batches before any source work, then copy bounded net-new rows from the selected source (selectedLeadListId, provider, and source fingerprint preserved), then use provider-aligned source-more. A new source or provider switch changes the reply-rate baseline and is a manual alternate, not a --yolo side effect. The refill_sends MCP command maintains a run-local refreshedPaidInmailSenderIds set: if the first target plan contains refresh_paid_inmail_credits for stale/missing paid-InMail facts, refill_sends refreshes each selected paid-InMail sender at most once, reruns get_refill_target_plan, and returns autoPaidInmailRefresh plus the post-refresh targetPlan before the operator chooses prep/source-copy/bounded-approval/read-only wait. Do not present paid-credit refresh as the next operator action after refill_sends has returned a post-refresh targetPlan. 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/source-copy/bounded-approval/read-only wait result, recompute the target-window saturation ledger, and keep going until projected coverage (sent + scheduled) fills the scheduler-forward target window 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, report loaded, awaiting scheduler and 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. Trust schedulerGate.sendable and scheduler blockers over raw unipileAccountStatus labels alone. For long-running prep use compact prep status checks, reread target plans after prep or cancel, avoid huge parallel target-plan reads when output is large, and if prepared/ready rows grow but sender-level projected coverage does not move after one bounded settle loop, pivot to compact prep status or a scheduler-proven lane instead of waiting on campaign-level ready counts. 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 scheduler-forward target window. 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

@@ -2,6 +2,7 @@ import { getRefillTargetPlan } from "./refill-target-plan.js";
 import { refreshPaidInmailCredits } from "./senders.js";
 import { startPrepareCampaignMessages } from "./campaign-message-preparation.js";
 import { confirmLeadList } from "./leads.js";
+import { getApi } from "../api.js";
 const DEFAULT_SCHEDULER_FORWARD_HOURS = 48;
 function normalizeStrings(values) {
     if (!Array.isArray(values))
@@ -60,7 +61,7 @@ function normalizeTargetDate(value) {
 export const refillSendsToolDefinitions = [
     {
         name: "refill_sends",
-        description: "Typed command entrypoint for Sellable refill sends. Accepts --yolo semantics and optional sender selectors, then returns the bounded execution contract for the skill-led refill workflow. In --yolo, it may refresh stale paid InMail credit cache facts once, or execute exactly one safe primitive from target.globalActionQueue[0] (bounded existing-row preparation, bounded same-source copy, or read-only wait) and reread. It does not approve messages without the bounded approval gate, lower paid InMail thresholds, switch source families, create campaigns, schedule sends, launch, archive, delete, or write scheduler rows.",
+        description: "Typed command entrypoint for Sellable refill sends. Accepts --yolo semantics and optional sender selectors, then returns the bounded execution contract for the skill-led refill workflow. In --yolo, it may refresh stale paid InMail credit cache facts once, or execute exactly one safe primitive from target.globalActionQueue[0] (bounded existing-row preparation, bounded same-source copy, bounded generated-message approval, or read-only wait) and reread. It does not run unbounded approval, lower paid InMail thresholds, switch source families, create campaigns, schedule sends, launch, archive, delete, or write scheduler rows.",
         inputSchema: {
             type: "object",
             properties: {
@@ -215,14 +216,14 @@ export function refillSendsCommand(input = {}) {
             "Treat current dashboard-active PAUSED campaign-backed sequence campaigns as start-eligible candidates: read refill state before deciding whether to prep, approve, start, or skip.",
             "Fresh reread get_campaign_refill_state immediately before any import, prep, approval, or horizon-fill mutation.",
             "Maintain a target-window 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.",
-            "In --yolo, this tool automatically maintains a run-local refreshedPaidInmailSenderIds set: when the first target plan returns refresh_paid_inmail_credits candidates for selected paid-InMail lanes, it refreshes each exact sender at most once, reruns get_refill_target_plan, and returns the post-refresh targetPlan before any prep/source-copy/read-only wait action is chosen.",
+            "In --yolo, this tool automatically maintains a run-local refreshedPaidInmailSenderIds set: when the first target plan returns refresh_paid_inmail_credits candidates for selected paid-InMail lanes, it refreshes each exact sender at most once, reruns get_refill_target_plan, and returns the post-refresh targetPlan before any prep/source-copy/bounded-approval/read-only wait action is chosen.",
             "Do not present paid-credit refresh as the next operator action after refill_sends returns autoPaidInmailRefresh and the post-refresh targetPlan.",
             "If paid InMail feasibility remains below threshold after that automatic refresh, report the exact sender/campaign/table/column threshold action or same-campaign 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 scheduler-forward target window. Treat awaiting_scheduler_after_ready_buffer as loaded, awaiting scheduler when ready buffer covers the gap; do not import/prep more rows in that state, and 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. Execute one globally ranked primitive from target.globalActionQueue at a time, then rerun get_refill_target_plan before taking another action. Continue through every safe prep/source-copy/read-only wait action inside that packet. Approval, start_campaign, source-family switches, threshold changes, and campaign creation require their own explicit gates. After each safe 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."
+            ? "Auto-accept only the rendered bounded refill target packet after get_refill_target_plan and fresh reread. Execute one globally ranked primitive from target.globalActionQueue at a time, then rerun get_refill_target_plan before taking another action. Continue through every safe prep/source-copy/bounded-approval/read-only wait action inside that packet. Unbounded approval, start_campaign, source-family switches, threshold changes, and campaign creation require their own explicit gates. After each safe 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 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.",
@@ -396,6 +397,36 @@ function actionSourceLeadListId(action) {
         stringValue(ids.sourceLeadListId) ??
         stringValue(action.sourceLeadListId));
 }
+function boundedApprovalLimit(action) {
+    const toolInput = actionToolInput(action);
+    const rowSelector = recordValue(toolInput.rowSelector);
+    const selectorLimit = numberValue(rowSelector?.limit);
+    const inputLimit = numberValue(toolInput.limit);
+    const limit = selectorLimit ?? inputLimit;
+    if (!limit || limit <= 0)
+        return null;
+    return Math.floor(limit);
+}
+async function approveGeneratedMessagesBatch(action) {
+    const tableId = actionTableId(action);
+    const toolInput = actionToolInput(action);
+    const columnId = stringValue(toolInput.columnId) ?? stringValue(actionIds(action).columnId);
+    const limit = boundedApprovalLimit(action);
+    if (!tableId || !limit) {
+        return {
+            status: "refused",
+            refusalReason: "approve_messages action is missing tableId or a bounded rowSelector.limit",
+        };
+    }
+    const api = getApi();
+    const result = await api.post("/api/v3/workflow-tables/cells/approve-batch", {
+        tableId,
+        ...(columnId ? { columnId } : {}),
+        limit,
+        scope: "generated_unapproved",
+    });
+    return { status: "executed_and_reread", result };
+}
 async function executeOneYoloPrimitive(action) {
     if (!action)
         return { status: "no_action" };
@@ -463,10 +494,7 @@ async function executeOneYoloPrimitive(action) {
             return { status: "executed_and_reread", result };
         }
         case "approve_messages":
-            return {
-                status: "refused",
-                refusalReason: "approve_messages requires the bounded approval mutation gate; refill_sends yolo will not treat select_campaign_cells as approval",
-            };
+            return approveGeneratedMessagesBatch(action);
         default:
             return {
                 status: "refused",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sellable/mcp",
-  "version": "0.1.477",
+  "version": "0.1.479",
   "type": "module",
   "description": "Sellable MCP server for Claude Code and Codex campaign workflows",
   "main": "dist/index.js",

package/skills/refill-sends/SKILL.md

@@ -94,7 +94,7 @@ non-yolo mode it does not mutate. In `--yolo`, it may execute exactly one safe
 bounded primitive from the fresh `target.globalActionQueue[0]`, then reread and
 return the new target plan; currently safe primitives are paid-credit refresh,
 existing-row message preparation, same-source row copy, and read-only wait
-rereads. It does not approve messages without the bounded approval gate, lower
+rereads. It does not run unbounded approval, lower
 paid-InMail thresholds, switch source families, create campaigns, launch, send,
 or write scheduler rows. Continue with the workflow below for route selection,
 state rereads, approval gating, source import, preparation, and bounded
@@ -183,7 +183,7 @@ automatically maintains a `refreshedPaidInmailSenderIds` set for the current
 command call. If its first target plan has stale/missing paid-InMail credit
 facts, it refreshes each selected sender at most once, reruns
 `get_refill_target_plan`, and returns the post-refresh `targetPlan` before
-choosing the next prep/source-copy/read-only wait action. If fresh facts are still below
+choosing the next prep/source-copy/bounded-approval/read-only wait action. If fresh facts are still below
 threshold, below-threshold paid-InMail facts fall back to an existing connection
 lane, the same Sales Nav cascade campaign's connection branch, or a manual
 continuation.
@@ -272,7 +272,7 @@ they change `stateRevision`, not `targetShapeRevision`, and do not require a
 second approval.
 
 In `--yolo`, continue as far as the rendered packet safely allows. After each
-apply/prep/source-copy/read-only wait result, reread state, settle processing when needed, and move to
+apply/prep/source-copy/bounded-approval/read-only wait result, reread state, settle processing when needed, and move to
 the next selected sender or start-eligible same-packet campaign instead of
 stopping after the first partial result. If no in-packet safe action remains,
 return concrete continuation options with campaign names, exact ids, which option
@@ -286,7 +286,7 @@ selected sender: selected send days, gross capacity, actual sent cells, future
 scheduler-owned scheduled cells with non-null `scheduledFor`, projected count,
 ready-to-schedule buffer, remaining projected gap, paid-InMail feasibility,
 `targetShapeRevision`, `stateRevision`, and the next MCP primitive that can
-reduce the gap. After every apply/prep/source-copy/read-only wait result, wait for processing, reread
+reduce the gap. After every apply/prep/source-copy/bounded-approval/read-only wait result, wait for processing, reread
 the target plan/refill state, recompute the ledger, then keep applying safe
 bounded actions until projected coverage fills the target window or a concrete
 non-scheduler blocker is proven.

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

@@ -120,7 +120,7 @@ in-progress wait state, not a reason to mark the goal complete or blocked.
    command call. If its first target plan has stale/missing paid-InMail credit
    facts, it refreshes each selected sender at most once, reruns
    `get_refill_target_plan`, and returns the post-refresh `targetPlan` before
-   choosing the next prep/source-copy/read-only wait action. If fresh facts are still below
+   choosing the next prep/source-copy/bounded-approval/read-only wait action. If fresh facts are still below
    threshold, below-threshold paid-InMail facts fall back to an existing
    connection lane, the same Sales Nav cascade campaign's connection branch, or
    a manual continuation.
@@ -559,7 +559,7 @@ same refill request, do not ask the `Accept` / `Decline` question. Instead:
    caps/dates, approval mode, blockers, and side-effect class still match the
    packet;
 4. execute only the exact packet;
-5. after each terminal credit-refresh/apply/prep/source-copy/read-only wait result, rerun
+5. after each terminal credit-refresh/apply/prep/source-copy/bounded-approval/read-only wait result, rerun
    `get_refill_target_plan`, reread state, settle processing when needed,
    recompute the target-window saturation ledger, and continue with the next smallest
    safe action inside the same bounded packet until every selected sender is