@xcraftmind/mastermind 0.28.2 → 0.29.0

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": "@xcraftmind/mastermind",
3
- "version": "0.28.2",
3
+ "version": "0.29.0",
4
4
  "description": "Mastermind workflow CLI + mmcg codegraph for AI coding agents — verify-spec / audit-spec gates, MCP server, multi-language tree-sitter indexer (Python, TypeScript, JavaScript, Rust, C#, Go, Java, PHP, C/C++). Prebuilt native binaries via optional platform packages — no Rust toolchain required.",
5
5
  "license": "MIT",
6
6
  "author": "xcraftmind",
@@ -38,12 +38,12 @@
38
38
  "mastermind"
39
39
  ],
40
40
  "optionalDependencies": {
41
- "@xcraftmind/mmcg-darwin-arm64": "0.28.2",
42
- "@xcraftmind/mmcg-darwin-x64": "0.28.2",
43
- "@xcraftmind/mmcg-linux-x64-gnu": "0.28.2",
44
- "@xcraftmind/mmcg-linux-arm64-gnu": "0.28.2",
45
- "@xcraftmind/mmcg-linux-x64-musl": "0.28.2",
46
- "@xcraftmind/mmcg-linux-arm64-musl": "0.28.2",
47
- "@xcraftmind/mmcg-win32-x64-msvc": "0.28.2"
41
+ "@xcraftmind/mmcg-darwin-arm64": "0.29.0",
42
+ "@xcraftmind/mmcg-darwin-x64": "0.29.0",
43
+ "@xcraftmind/mmcg-linux-x64-gnu": "0.29.0",
44
+ "@xcraftmind/mmcg-linux-arm64-gnu": "0.29.0",
45
+ "@xcraftmind/mmcg-linux-x64-musl": "0.29.0",
46
+ "@xcraftmind/mmcg-linux-arm64-musl": "0.29.0",
47
+ "@xcraftmind/mmcg-win32-x64-msvc": "0.29.0"
48
48
  }
49
49
  }
@@ -304,6 +304,16 @@ On `❌ contract broken`:
304
304
 
305
305
  The `blocking_reason` must be a single sentence naming the concrete discrepancy — not "see audit" or "contract broken". It appears verbatim in `mastermind status` and `mastermind resume` output.
306
306
 
307
+ ## Final output self-check (REQUIRED — complete before ending your response)
308
+
309
+ Before writing your last word, verify all three conditions:
310
+
311
+ 1. Does your response contain `<!-- mastermind:audit-begin -->`? If not, emit the full structured tail now.
312
+ 2. Does your response contain `<!-- mastermind:audit-end -->`? If not, close the block now.
313
+ 3. Is the YAML inside the block valid — `verdict:`, `discrepancies:`, `scope_match:` all present? If malformed, rewrite the block.
314
+
315
+ A response without the sentinel block is **invalid** regardless of reasoning quality. The planner cannot route on prose alone.
316
+
307
317
  ## What you do NOT do
308
318
 
309
319
  - Run commands that modify state (no `git commit`, no `git push`, no destructive ops)