@sellable/mcp 0.1.115 → 0.1.116

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@sellable/mcp",
3
- "version": "0.1.115",
3
+ "version": "0.1.116",
4
4
  "type": "module",
5
5
  "description": "Sellable MCP server for Claude Code and Codex campaign workflows",
6
6
  "main": "dist/index.js",
@@ -207,6 +207,11 @@ or an error state, recover a fresh watch link once with
207
207
  `create_campaign({ campaignId })` or `get_campaign`, then print the recovered
208
208
  link. Do not claim the browser was opened, inspected, or synchronized.
209
209
 
210
+ Never print a placeholder watch link such as "Open campaign" or "link will
211
+ update once the shell is created." If the shell is not created yet, call
212
+ `create_campaign` first. If `create_campaign` does not return `watchUrl`, stop
213
+ and surface the missing watch-link error before lead sourcing.
214
+
210
215
  After every `update_campaign({ campaignId, currentStep })`, use
211
216
  `get_campaign_navigation_state` when available as a compact orientation check:
212
217
  match the expected watch-link step to the saved campaign state, explain the
@@ -581,6 +586,8 @@ updates.
581
586
  `message-validation.md` proves the message-review safety-gate workflow ran,
582
587
  `message-review.md` approves the template, rubrics are saved, and the
583
588
  approved message set is synced into the campaign brief.
589
+ Do not ask the user to approve the brief before shell creation unless they
590
+ explicitly requested a no-write draft; the shell itself is the review surface.
584
591
  6. The main thread owns watch navigation. Call
585
592
  `mcp__sellable__update_campaign({ campaignId, currentStep })` before major
586
593
  visible work so the user can watch progress in the app: `create-offer` for
@@ -86,6 +86,9 @@ the error. Do not continue into campaignless source scouting in the active
86
86
  shell-first flow.
87
87
  If a legacy atomic-mint response is missing `watchUrl`, it is not a silent skip.
88
88
  Stop before `save_rubrics` and recover the missing watch URL first.
89
+ Never print a placeholder link such as "Open campaign" or "link will update
90
+ once the shell is created." In the active shell-first flow, the first visible
91
+ watch link must be the real `watchUrl` returned by `create_campaign`.
89
92
 
90
93
  ## Step Orientation
91
94
 
@@ -1,9 +0,0 @@
1
- {
2
- "parallelMode": "wide",
3
- "agentCount": 6,
4
- "maxToolCallsPerAgent": 2,
5
- "senderMaxAgents": 2,
6
- "senderMaxToolCallsPerAgent": 3,
7
- "progressMode": true,
8
- "debugMode": true
9
- }