@sellable/mcp 0.1.309 → 0.1.311

package/agents/post-find-leads-message-scout.md

@@ -165,10 +165,15 @@ When reporting branch runtime proof, use this shape under
 - `runId` or `fallbackId`
 - `startedAt` and `updatedAt`
 - `basisToken` and `basis`
+- `basis.selectedLeadListId`, `basis.workflowTableId`, and either
+  `basis.reviewBatchRowHash` or non-empty `basis.reviewBatchRowIds`
 - optional `messageDraftOutputRef`, `messageDraftOutput`, and `error`
 
 Do not tell the UI to show Message Draft Builder as running unless this proof
 exists and points at the current non-empty campaign-table execution slice.
+Use `workerStatuses.messageDraftBuilder` only for simple badge text such as
+`running`; never put `runId`, `statusSource`, `status`, or `basis` under
+`workerStatuses`, and never use a `messageDrafting` key.
 If the host cannot launch a background branch and the parent thread runs this
 same contract inline, report `statusSource: "parent-thread-fallback"` and
 `status: "fallback-active"` while working, then `status: "ready"` when the

package/dist/tools/campaigns.d.ts

@@ -416,6 +416,90 @@ export declare const campaignToolDefinitions: ({
                     };
                     workerStatuses: {
                         type: string;
+                        description: string;
+                        properties: {
+                            leadFitBuilder: {
+                                type: string[];
+                                enum: (string | null)[];
+                            };
+                            messageDraftBuilder: {
+                                type: string[];
+                                enum: (string | null)[];
+                            };
+                        };
+                        additionalProperties: boolean;
+                    };
+                    workerDetails: {
+                        type: string;
+                        description: string;
+                        properties: {
+                            messageDraftBuilder: {
+                                type: string[];
+                                description: string;
+                                properties: {
+                                    statusSource: {
+                                        type: string;
+                                        enum: string[];
+                                    };
+                                    status: {
+                                        type: string;
+                                        enum: string[];
+                                    };
+                                    runId: {
+                                        type: string[];
+                                    };
+                                    fallbackId: {
+                                        type: string[];
+                                    };
+                                    startedAt: {
+                                        type: string;
+                                    };
+                                    updatedAt: {
+                                        type: string;
+                                    };
+                                    basisToken: {
+                                        type: string[];
+                                    };
+                                    basis: {
+                                        type: string;
+                                        properties: {
+                                            campaignId: {
+                                                type: string[];
+                                            };
+                                            selectedLeadListId: {
+                                                type: string[];
+                                            };
+                                            workflowTableId: {
+                                                type: string[];
+                                            };
+                                            reviewBatchRowHash: {
+                                                type: string[];
+                                            };
+                                            reviewBatchRowIds: {
+                                                type: string[];
+                                                items: {
+                                                    type: string;
+                                                };
+                                            };
+                                            filterChoice: {
+                                                type: string[];
+                                            };
+                                        };
+                                    };
+                                    messageDraftOutputRef: {
+                                        type: string[];
+                                    };
+                                    messageDraftOutput: {
+                                        type: string[];
+                                    };
+                                    error: {
+                                        type: string[];
+                                    };
+                                };
+                                required: string[];
+                            };
+                        };
+                        additionalProperties: boolean;
                     };
                 };
                 required: string[];
@@ -531,6 +615,90 @@ export declare const campaignToolDefinitions: ({
                     };
                     workerStatuses: {
                         type: string;
+                        description: string;
+                        properties: {
+                            leadFitBuilder: {
+                                type: string[];
+                                enum: (string | null)[];
+                            };
+                            messageDraftBuilder: {
+                                type: string[];
+                                enum: (string | null)[];
+                            };
+                        };
+                        additionalProperties: boolean;
+                    };
+                    workerDetails: {
+                        type: string;
+                        description: string;
+                        properties: {
+                            messageDraftBuilder: {
+                                type: string[];
+                                description: string;
+                                properties: {
+                                    statusSource: {
+                                        type: string;
+                                        enum: string[];
+                                    };
+                                    status: {
+                                        type: string;
+                                        enum: string[];
+                                    };
+                                    runId: {
+                                        type: string[];
+                                    };
+                                    fallbackId: {
+                                        type: string[];
+                                    };
+                                    startedAt: {
+                                        type: string;
+                                    };
+                                    updatedAt: {
+                                        type: string;
+                                    };
+                                    basisToken: {
+                                        type: string[];
+                                    };
+                                    basis: {
+                                        type: string;
+                                        properties: {
+                                            campaignId: {
+                                                type: string[];
+                                            };
+                                            selectedLeadListId: {
+                                                type: string[];
+                                            };
+                                            workflowTableId: {
+                                                type: string[];
+                                            };
+                                            reviewBatchRowHash: {
+                                                type: string[];
+                                            };
+                                            reviewBatchRowIds: {
+                                                type: string[];
+                                                items: {
+                                                    type: string;
+                                                };
+                                            };
+                                            filterChoice: {
+                                                type: string[];
+                                            };
+                                        };
+                                    };
+                                    messageDraftOutputRef: {
+                                        type: string[];
+                                    };
+                                    messageDraftOutput: {
+                                        type: string[];
+                                    };
+                                    error: {
+                                        type: string[];
+                                    };
+                                };
+                                required: string[];
+                            };
+                        };
+                        additionalProperties: boolean;
                     };
                 };
                 required: string[];

package/dist/tools/campaigns.js

@@ -10,6 +10,99 @@ const LEAD_SOURCE_PROVIDERS = {
     PROSPEO: "prospeo",
     SIGNAL_DISCOVERY: "signal-discovery",
 };
+const WATCH_NARRATION_TOOL_SCHEMA = {
+    type: "object",
+    description: "Single structured watch-guide narration object to send with currentStep changes. Include what just happened, what the browser is showing now, what Codex is doing next, and nextAction so the browser guide mirrors Codex progress. Do not send separate guideHeadline/guideBody fields. Use workerStatuses only for simple string badges; put Message Drafting runtime proof under workerDetails.messageDraftBuilder.",
+    properties: {
+        stage: {
+            type: "string",
+            enum: [
+                "brief-review",
+                "find-leads",
+                "review-batch",
+                "fit-message",
+                "review-ready",
+            ],
+        },
+        headline: { type: "string" },
+        visibleState: { type: "string" },
+        agentIntent: { type: "string" },
+        nextAction: { type: ["string", "null"] },
+        safety: { type: ["string", "null"] },
+        progressLabel: { type: ["string", "null"] },
+        blockedReason: { type: ["string", "null"] },
+        workerStatuses: {
+            type: "object",
+            description: 'Simple display badges only. Allowed keys are leadFitBuilder and messageDraftBuilder; values are "idle", "running", "ready", "blocked", or null. Do not put runId, statusSource, basis, or rich worker proof here.',
+            properties: {
+                leadFitBuilder: {
+                    type: ["string", "null"],
+                    enum: ["idle", "running", "ready", "blocked", null],
+                },
+                messageDraftBuilder: {
+                    type: ["string", "null"],
+                    enum: ["idle", "running", "ready", "blocked", null],
+                },
+            },
+            additionalProperties: false,
+        },
+        workerDetails: {
+            type: "object",
+            description: "Rich runtime proof for background workers. Message Drafting proof must use workerDetails.messageDraftBuilder, not workerStatuses.messageDrafting.",
+            properties: {
+                messageDraftBuilder: {
+                    type: ["object", "null"],
+                    description: 'Runtime proof that Message Drafting actually started or fell back inline. For a spawned background worker use statusSource "branch" and status "branch-running"; for inline fallback use statusSource "parent-thread-fallback" and status "fallback-active". The basis must include selectedLeadListId, workflowTableId, and either reviewBatchRowHash or reviewBatchRowIds so the watched UI can trust the current execution slice.',
+                    properties: {
+                        statusSource: {
+                            type: "string",
+                            enum: ["branch", "parent-thread-fallback"],
+                        },
+                        status: {
+                            type: "string",
+                            enum: [
+                                "branch-running",
+                                "fallback-active",
+                                "spawn-failed",
+                                "fallback-superseded",
+                                "branch-superseded",
+                                "ready",
+                                "blocked",
+                                "retry-needed",
+                                "stale",
+                            ],
+                        },
+                        runId: { type: ["string", "null"] },
+                        fallbackId: { type: ["string", "null"] },
+                        startedAt: { type: "string" },
+                        updatedAt: { type: "string" },
+                        basisToken: { type: ["string", "null"] },
+                        basis: {
+                            type: "object",
+                            properties: {
+                                campaignId: { type: ["string", "null"] },
+                                selectedLeadListId: { type: ["string", "null"] },
+                                workflowTableId: { type: ["string", "null"] },
+                                reviewBatchRowHash: { type: ["string", "null"] },
+                                reviewBatchRowIds: {
+                                    type: ["array", "null"],
+                                    items: { type: "string" },
+                                },
+                                filterChoice: { type: ["string", "null"] },
+                            },
+                        },
+                        messageDraftOutputRef: { type: ["string", "null"] },
+                        messageDraftOutput: { type: ["object", "null"] },
+                        error: { type: ["string", "null"] },
+                    },
+                    required: ["statusSource", "status", "startedAt", "updatedAt", "basis"],
+                },
+            },
+            additionalProperties: false,
+        },
+    },
+    required: ["stage", "headline", "visibleState", "agentIntent", "nextAction"],
+};
 function normalizeLeadSourceProvider(input) {
     if (!input)
         return null;
@@ -236,37 +329,7 @@ export const campaignToolDefinitions = [
                     type: ["string", "null"],
                     description: "Workflow step ID (headless or UI step ID such as filter-rules)",
                 },
-                watchNarration: {
-                    type: "object",
-                    description: "Single structured watch-guide narration object to send with currentStep changes. Include what just happened, what the browser is showing now, what Codex is doing next, and nextAction so the browser guide mirrors Codex progress.",
-                    properties: {
-                        stage: {
-                            type: "string",
-                            enum: [
-                                "brief-review",
-                                "find-leads",
-                                "review-batch",
-                                "fit-message",
-                                "review-ready",
-                            ],
-                        },
-                        headline: { type: "string" },
-                        visibleState: { type: "string" },
-                        agentIntent: { type: "string" },
-                        nextAction: { type: ["string", "null"] },
-                        safety: { type: ["string", "null"] },
-                        progressLabel: { type: ["string", "null"] },
-                        blockedReason: { type: ["string", "null"] },
-                        workerStatuses: { type: "object" },
-                    },
-                    required: [
-                        "stage",
-                        "headline",
-                        "visibleState",
-                        "agentIntent",
-                        "nextAction",
-                    ],
-                },
+                watchNarration: WATCH_NARRATION_TOOL_SCHEMA,
                 leadSourceType: {
                     type: ["string", "null"],
                     description: "Lead source type (existing | new)",
@@ -344,37 +407,7 @@ export const campaignToolDefinitions = [
                     type: "string",
                     description: "Guarded manual recovery clear. currentStep:null is accepted only when this matches the durable step being cleared.",
                 },
-                watchNarration: {
-                    type: "object",
-                    description: "Single structured watch-guide narration object to send with currentStep changes. Include what just happened, what the browser is showing now, what Codex is doing next, and nextAction so the browser guide mirrors Codex progress. Do not send separate guideHeadline/guideBody fields.",
-                    properties: {
-                        stage: {
-                            type: "string",
-                            enum: [
-                                "brief-review",
-                                "find-leads",
-                                "review-batch",
-                                "fit-message",
-                                "review-ready",
-                            ],
-                        },
-                        headline: { type: "string" },
-                        visibleState: { type: "string" },
-                        agentIntent: { type: "string" },
-                        nextAction: { type: ["string", "null"] },
-                        safety: { type: ["string", "null"] },
-                        progressLabel: { type: ["string", "null"] },
-                        blockedReason: { type: ["string", "null"] },
-                        workerStatuses: { type: "object" },
-                    },
-                    required: [
-                        "stage",
-                        "headline",
-                        "visibleState",
-                        "agentIntent",
-                        "nextAction",
-                    ],
-                },
+                watchNarration: WATCH_NARRATION_TOOL_SCHEMA,
                 interactionMode: {
                     type: "string",
                     enum: ["step-by-step", "autonomous", "ask-when-needed"],

package/dist/tools/prompts.js

@@ -331,8 +331,8 @@ export function getPostFindLeadsScoutRegistry() {
                 "basis.campaignId",
                 "basis.selectedLeadListId",
                 "basis.workflowTableId",
-                "basis.currentExecutionSliceNonEmpty",
-                "basis.sampleRows or basis.sampleRowSummary",
+                "basis.reviewBatchRowHash or basis.reviewBatchRowIds",
+                "basis.filterChoice",
             ],
             promptRequired: 'Load current campaign brief/table state through scoped tools. Before drafting: get_subskill_prompt({ subskillName: "generate-messages" }); every required message asset named by generate-messages Mode 0 through get_subskill_asset, including gold-standard-message-examples.md, gold-standard-message-patterns.md, ai-tells.md, sellable-cleanup-rules.md, ai-native-tokens.md, and token-fill-examples.md. Do not use shell/local filesystem reads, repo paths, plugin-cache paths, /Users paths, local artifacts, alternate prompts, or examples-only prompts. After candidate generation/revision and before returning ready: get_subskill_prompt({ subskillName: "create-campaign-v2-validation" }) as the final internal validation gate. If required prompts/assets cannot load through MCP tools, return blocked/retry-needed instead of drafting from memory.',
             basisFields: [
@@ -342,6 +342,7 @@ export function getPostFindLeadsScoutRegistry() {
                 "selectedLeadListId",
                 "workflowTableId",
                 "filter choice",
+                "runtime proof row identity: reviewBatchRowHash or reviewBatchRowIds",
                 "concise brief summary: offer, buyer, safe proof, blocked claims",
                 "concise source summary and source-use rule",
                 "3-5 sample campaign-table rows with name, title, company when available, and signal",
@@ -363,9 +364,9 @@ export function getPostFindLeadsScoutRegistry() {
             reusePolicy: "The first completed Message Drafting recommendation remains the default review candidate. Later Lead Fit Builder, Filter Leads, enrichment, or rubric completion may make an enriched rewrite available, but does not automatically retry or replace the initial draft unless campaign/brief/source/list/table/execution-slice identity mismatches or the initial output failed. If filters were chosen but leadScoringRubrics are not yet visible when the branch reads campaign state, Message Drafting must not wait, retry, or return blocked; missing saved rubrics are parent-owned filter setup, and the branch should return status ready with basisStatus usable_initial when campaign/list/table identity and the non-empty execution slice match. User copy feedback before approve-message is an explicit Message Drafting revision and must be routed back through the message branch with the current recommendation and basis.",
         },
         usage: {
-            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. If no background-agent tool is callable, start the same full message branch inline before filter drafting or before skip-filter message review, record it as statusSource parent-thread-fallback, 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.",
+            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. If no background-agent tool is callable, start that same full message branch inline before filter drafting or before skip-filter message review, record 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 the campaign/list/table and 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.',
+            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. Only call start_campaign_message_preparation when the user explicitly asks for more prepared messages or a send count. For "prepare/generate X messages", set targetPreparedMessages:X, omit maxRowsToCheck so the backend calibrates on at least 100 rows, estimates the row budget from observed rubric/pass yield, caps maxRowsToCheck at 2500, and use approvalMode:mark_ready. After the calibration sample settles, the backend adapts later batches up to 250 rows while recalculating yield. Poll get_campaign_message_preparation_status and summarize preparation-job status: checked rows, passed/prepared/approved count, target, estimated row budget remaining, and stop reason. For "approve X messages", use approvalMode:approve but still do not launch. For "schedule X sends", use approvalMode:approve to approve exactly the bounded X-message cohort during preparation, then continue through sender, sequence, and final launch greenlight; final launch must verify that bounded cohort and must not broad approve-all. campaignId is CampaignOffer.id. If the user asks to stop preparation, the target is wrong, or status shows the wrong campaign/table, call cancel_campaign_message_preparation; otherwise do not cancel a healthy prepare run. cancel_campaign_message_preparation cancels the same pending workflow-table cells as the UI Cancel Pending Cells action. Low-level selectors are diagnostics and recovery only for this lane. start_campaign remains forbidden until final launch greenlight.',
         },
     };

package/dist/tools/registry.d.ts

@@ -1110,6 +1110,90 @@ export declare const allTools: ({
                     };
                     workerStatuses: {
                         type: string;
+                        description: string;
+                        properties: {
+                            leadFitBuilder: {
+                                type: string[];
+                                enum: (string | null)[];
+                            };
+                            messageDraftBuilder: {
+                                type: string[];
+                                enum: (string | null)[];
+                            };
+                        };
+                        additionalProperties: boolean;
+                    };
+                    workerDetails: {
+                        type: string;
+                        description: string;
+                        properties: {
+                            messageDraftBuilder: {
+                                type: string[];
+                                description: string;
+                                properties: {
+                                    statusSource: {
+                                        type: string;
+                                        enum: string[];
+                                    };
+                                    status: {
+                                        type: string;
+                                        enum: string[];
+                                    };
+                                    runId: {
+                                        type: string[];
+                                    };
+                                    fallbackId: {
+                                        type: string[];
+                                    };
+                                    startedAt: {
+                                        type: string;
+                                    };
+                                    updatedAt: {
+                                        type: string;
+                                    };
+                                    basisToken: {
+                                        type: string[];
+                                    };
+                                    basis: {
+                                        type: string;
+                                        properties: {
+                                            campaignId: {
+                                                type: string[];
+                                            };
+                                            selectedLeadListId: {
+                                                type: string[];
+                                            };
+                                            workflowTableId: {
+                                                type: string[];
+                                            };
+                                            reviewBatchRowHash: {
+                                                type: string[];
+                                            };
+                                            reviewBatchRowIds: {
+                                                type: string[];
+                                                items: {
+                                                    type: string;
+                                                };
+                                            };
+                                            filterChoice: {
+                                                type: string[];
+                                            };
+                                        };
+                                    };
+                                    messageDraftOutputRef: {
+                                        type: string[];
+                                    };
+                                    messageDraftOutput: {
+                                        type: string[];
+                                    };
+                                    error: {
+                                        type: string[];
+                                    };
+                                };
+                                required: string[];
+                            };
+                        };
+                        additionalProperties: boolean;
                     };
                 };
                 required: string[];
@@ -1225,6 +1309,90 @@ export declare const allTools: ({
                     };
                     workerStatuses: {
                         type: string;
+                        description: string;
+                        properties: {
+                            leadFitBuilder: {
+                                type: string[];
+                                enum: (string | null)[];
+                            };
+                            messageDraftBuilder: {
+                                type: string[];
+                                enum: (string | null)[];
+                            };
+                        };
+                        additionalProperties: boolean;
+                    };
+                    workerDetails: {
+                        type: string;
+                        description: string;
+                        properties: {
+                            messageDraftBuilder: {
+                                type: string[];
+                                description: string;
+                                properties: {
+                                    statusSource: {
+                                        type: string;
+                                        enum: string[];
+                                    };
+                                    status: {
+                                        type: string;
+                                        enum: string[];
+                                    };
+                                    runId: {
+                                        type: string[];
+                                    };
+                                    fallbackId: {
+                                        type: string[];
+                                    };
+                                    startedAt: {
+                                        type: string;
+                                    };
+                                    updatedAt: {
+                                        type: string;
+                                    };
+                                    basisToken: {
+                                        type: string[];
+                                    };
+                                    basis: {
+                                        type: string;
+                                        properties: {
+                                            campaignId: {
+                                                type: string[];
+                                            };
+                                            selectedLeadListId: {
+                                                type: string[];
+                                            };
+                                            workflowTableId: {
+                                                type: string[];
+                                            };
+                                            reviewBatchRowHash: {
+                                                type: string[];
+                                            };
+                                            reviewBatchRowIds: {
+                                                type: string[];
+                                                items: {
+                                                    type: string;
+                                                };
+                                            };
+                                            filterChoice: {
+                                                type: string[];
+                                            };
+                                        };
+                                    };
+                                    messageDraftOutputRef: {
+                                        type: string[];
+                                    };
+                                    messageDraftOutput: {
+                                        type: string[];
+                                    };
+                                    error: {
+                                        type: string[];
+                                    };
+                                };
+                                required: string[];
+                            };
+                        };
+                        additionalProperties: boolean;
                     };
                 };
                 required: string[];

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sellable/mcp",
-  "version": "0.1.309",
+  "version": "0.1.311",
   "type": "module",
   "description": "Sellable MCP server for Claude Code and Codex campaign workflows",
   "main": "dist/index.js",

package/skills/create-campaign/SKILL.md

@@ -965,6 +965,13 @@ updates.
    background-agent tool is callable, start the same full message branch inline
    before filter drafting or skip-filter message review and record it as
    `statusSource: "parent-thread-fallback"`.
+   After a spawned branch starts, persist rich proof under
+   `watchNarration.workerDetails.messageDraftBuilder` with
+   `statusSource: "branch"`, `status: "branch-running"`, `runId`, timestamps,
+   selectedLeadListId, workflowTableId, filterChoice, and reviewBatchRowHash or
+   reviewBatchRowIds. `workerStatuses.messageDraftBuilder` is only the optional
+   simple badge (`running`); never put rich proof under `workerStatuses` or use
+   a `messageDrafting` key.
    Do not use any alternate, examples-only, or local-artifact message prompt. Message review and
    message QA require Message Drafting output:
    do not draft from a checklist, local markdown artifact, or parent-thread

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

@@ -273,7 +273,7 @@ customer-facing source-choice labels.
 
 After `confirm_lead_list` copies source rows and records the review batch, ask the filter-choice question immediately. Do not call `get_post_find_leads_scout_registry`, load filter/message prompts, or spawn Message Drafting before that question. Before it: short setup summary plus add filters, skip filters, or revise source; no extra watch link.
 
-After filter choice, the only normal background worker is Message Drafting (`post-find-leads-message-scout`). The registry lookup is not a launch. Both choices must run this kickoff: call the registry, then start Message Drafting via `Task`/`spawn_agent` before filter refs, `save_rubrics`, or skip review. YOLO follows the same no-extra-question kickoff rule. If no background tool is callable, run the same full branch inline as `parent-thread-fallback`; otherwise return `blocked` / `retry-needed`. `update_campaign({ currentStep: "messages" })` is not proof of kickoff.
+After filter choice, the only normal background worker is Message Drafting (`post-find-leads-message-scout`). The registry lookup is not a launch. Both choices must run this kickoff: call the registry, then start Message Drafting via `Task`/`spawn_agent` before filter refs, `save_rubrics`, or skip review. YOLO follows the same no-extra-question kickoff rule. If no background tool is callable, run the same full branch inline as `parent-thread-fallback`; otherwise return `blocked` / `retry-needed`. `update_campaign({ currentStep: "messages" })` is not proof of kickoff. After launch, persist rich proof under `watchNarration.workerDetails.messageDraftBuilder` with `statusSource: "branch"`, `status: "branch-running"`, `runId`, timestamps, selectedLeadListId, workflowTableId, filterChoice, and reviewBatchRowHash or reviewBatchRowIds; `workerStatuses.messageDraftBuilder` is only the optional simple badge (`running`). Never put rich proof under `workerStatuses` or use a `messageDrafting` key.
 
 Parent thread writes filters. On the filters path, start Message Drafting, load `references/filter-leads.md`, save rubrics, and ask users to approve saved criteria. Keep Filter Rules until criteria approval. After approval, move to `currentStep: "apply-icp-rubric"` so the app shows Filter Leads while Message Drafting finishes; no cells until template approval. Say Message Drafting is preparing it.
 

package/skills/create-campaign-v2/references/watch-guide-narration.md

@@ -202,6 +202,23 @@ After confirmed source rows are copied:
   "workerStatuses": {
     "leadFitBuilder": "idle",
     "messageDraftBuilder": "running"
+  },
+  "workerDetails": {
+    "messageDraftBuilder": {
+      "statusSource": "branch",
+      "status": "branch-running",
+      "runId": "message-drafting-thread-id",
+      "startedAt": "2026-05-09T10:00:00.000Z",
+      "updatedAt": "2026-05-09T10:00:00.000Z",
+      "basisToken": "message-drafting-basis-1",
+      "basis": {
+        "campaignId": "campaign-id",
+        "selectedLeadListId": "source-lead-list-id",
+        "workflowTableId": "campaign-table-id",
+        "reviewBatchRowHash": "review-batch-hash",
+        "filterChoice": "use-filters"
+      }
+    }
   }
 }
 ```
@@ -214,6 +231,9 @@ Any cleanup/manual-review row means recommend light filters by default. This is
 a user decision gate, not active filtering; do not say filtering the batch before
 rubrics are saved. Message Drafting should start after the filter-choice answer;
 mark it running only when that branch actually started.
+`workerStatuses.messageDraftBuilder` is a simple badge only. Put branch runtime
+proof under `workerDetails.messageDraftBuilder`; do not put rich objects under
+`workerStatuses`, and do not use a `messageDrafting` key.
 When the user chooses filters, immediately persist `enableICPFilters: true` and
 move to `create-icp-rubric` so the watched app shows Filter Rules while Codex
 defines the rules in chat. After `save_rubrics`, keep the app on Filter Rules so