@jaypie/mcp 0.6.3 → 0.6.4

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.
@@ -8,7 +8,7 @@ import { gt } from 'semver';
8
8
  /**
9
9
  * Docs Suite - Documentation services (skill, version, release_notes)
10
10
  */
11
- const BUILD_VERSION_STRING = "@jaypie/mcp@0.6.3#291140bb"
11
+ const BUILD_VERSION_STRING = "@jaypie/mcp@0.6.4#db054728"
12
12
  ;
13
13
  const __filename$1 = fileURLToPath(import.meta.url);
14
14
  const __dirname$1 = path.dirname(__filename$1);
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@jaypie/mcp",
3
- "version": "0.6.3",
3
+ "version": "0.6.4",
4
4
  "description": "Jaypie MCP",
5
5
  "repository": {
6
6
  "type": "git",
package/skills/llm.md CHANGED
@@ -142,6 +142,27 @@ const greetTool = fabricLlmTool(greetService);
142
142
  const toolkit = new Toolkit([greetTool]);
143
143
  ```
144
144
 
145
+ ### Explain Mode
146
+
147
+ Explain mode adds transparency to tool calling by requiring the LLM to state its reasoning when invoking tools.
148
+
149
+ ```typescript
150
+ // Enable via Toolkit constructor
151
+ const toolkit = new Toolkit([myTool], { explain: true });
152
+
153
+ // Or via operate options
154
+ const response = await Llm.operate("What's the weather?", {
155
+ model: "gpt-5.1",
156
+ tools: myTools,
157
+ explain: true,
158
+ });
159
+ ```
160
+
161
+ When enabled:
162
+ - Each tool receives an `__Explanation` parameter requiring the model to state why it's calling the tool
163
+ - The explanation is stripped before the tool executes (tools receive clean arguments)
164
+ - Useful for debugging and understanding LLM decision-making
165
+
145
166
  ## Structured Output
146
167
 
147
168
  ### Natural Schema