@nbiish/cognitive-tools-mcp 2.0.5 → 2.0.7

package/README.md

@@ -34,7 +34,7 @@ Copyright © 2025 ᓂᐲᔥ ᐙᐸᓂᒥᑮ-ᑭᓇᐙᐸᑭᓯ (Nbiish Waabanimi
 
 This project is licensed under the [COMPREHENSIVE RESTRICTED USE LICENSE FOR INDIGENOUS CREATIONS WITH TRIBAL SOVEREIGNTY, DATA SOVEREIGNTY, AND WEALTH RECLAMATION PROTECTIONS](LICENSE).
 
-ᑭᑫᓐᑖᓱᐎᓐ ᐋᐸᒋᒋᑲᓇᓐ - Agentic Cognitive Tools (v3.2.1 / pkg v2.0.4): Implements Gikendaasowin v7 Guidelines. Enforces MANDATORY internal **Observe-Orient-Reason-Decide-Act (OOReDAct)** cycle: Starts with 'assess_and_orient', continues with 'think' deliberation before actions. Guides adaptive reasoning (**Chain-of-Thought (CoT)**, **Chain-of-Draft/Condensed Reasoning (CoD/CR)**, **Structured Chain-of-Thought (SCoT)**) & CodeAct preference. Returns Markdown.
+ᑭᑫᓐᑖᓱᐎᓐ ᐋᐸᒋᒋᑲᓇᓐ - Agentic Cognitive Tools (v3.2.1 / pkg v2.0.6): Implements Gikendaasowin v7 Guidelines. Enforces MANDATORY internal **Observe-Orient-Reason-Decide-Act (OOReDAct)** cycle: Starts with 'assess_and_orient', continues with 'think' deliberation before actions. Guides adaptive reasoning (**Chain-of-Thought (CoT)**, **Chain-of-Draft/Condensed Reasoning (CoD/CR)**, **Structured Chain-of-Thought (SCoT)**) & CodeAct preference. Returns Markdown.
 
 Known as:
 - Anishinaabemowin: [`@nbiish/gikendaasowin-aabajichiganan-mcp`](https://www.npmjs.com/package/@nbiish/gikendaasowin-aabajichiganan-mcp)
@@ -43,7 +43,8 @@ Known as:
 Both packages are maintained in parallel and receive the same updates. You can use either package name in your projects - they provide identical functionality.
 
 **Recent Updates:**
-- v2.0.4: Updated cognitive tool output formatting to prepend "1) ".
+- v2.0.6: Added `mental_sandbox` tool for logging internal cognitive simulations.
+- v2.0.6: Removed prefixing from cognitive tool outputs to ensure verbatim logging.
 - Resolved TypeScript compilation errors related to MCP SDK types and server configuration.
 - Ensured successful build process.
 
@@ -258,6 +259,16 @@ npm run inspector
 }
 ```
 
+#### `mental_sandbox` Example
+```json
+{
+  "toolName": "mental_sandbox",
+  "arguments": {
+    "sandbox_content": "<sandbox>\n## Hypothesis Generation & Testing\n<hypotheses>\n1. Explain 'Debwewin' (Truth) directly using Seven Grandfather Teachings context.\n2. Compare 'Debwewin' to Western concepts of truth, highlighting differences.\n</hypotheses>\n<evaluation>\nHypothesis 1: High alignment with Anishinaabe worldview, promotes understanding within cultural context. Medium complexity.\nHypothesis 2: Risks misinterpretation or oversimplification, potentially reinforces colonial framing. High complexity.\n</evaluation>\n## Constraint Checklist\n<constraint_check>\n1. Cultural Sensitivity: Pass (Hypothesis 1 focuses on internal context).\n2. Accuracy: Pass (Based on teachings).\n3. Clarity for User: Pass (Needs careful wording).\n</constraint_check>\n## Confidence Score\n<confidence>High (for Hypothesis 1)</confidence>\n## Pre-computational Analysis\n<pre_computation>\nSimulating Hypothesis 1: Leads to explanation focused on honesty, integrity, speaking from the heart. Positive impact on understanding Anishinaabe values.\nSimulating Hypothesis 2: Leads to potentially complex, potentially problematic comparative analysis. Risk of inaccuracy.\n</pre_computation>\n</sandbox>"
+  }
+}
+```
+
 #### `chain_of_thought` Example
 ```json
 {

package/build/index.js

@@ -96,8 +96,8 @@ async ({ assessment_and_orientation_text }) => {
         logToolResult(toolName, true, `Input received (length: ${assessment_and_orientation_text.length})`);
         // Log the raw input string
         console.error(`[${new Date().toISOString()}] [MCP Server] - ${toolName} Input String:\n${assessment_and_orientation_text}`);
-        // Return the input string directly, prefixed
-        return { content: [{ type: "text", text: `1) ${assessment_and_orientation_text}` }] };
+        // Return the input string directly
+        return { content: [{ type: "text", text: assessment_and_orientation_text }] };
     }
     catch (error) {
         // Catch only unexpected runtime errors
@@ -131,8 +131,8 @@ async ({ thought }) => {
         logToolResult(toolName, true, `Input received (length: ${thought.length})`);
         // Log the raw input string
         console.error(`[${new Date().toISOString()}] [MCP Server] - ${toolName} Input String:\n${thought}`);
-        // Return the input string directly, prefixed
-        return { content: [{ type: "text", text: `1) ${thought}` }] };
+        // Return the input string directly
+        return { content: [{ type: "text", text: thought }] };
     }
     catch (error) {
         // Catch only unexpected runtime errors
@@ -165,8 +165,8 @@ async ({ brief_thought }) => {
         logToolResult(toolName, true, `Input received (length: ${brief_thought.length})`);
         // Log the raw input string
         console.error(`[${new Date().toISOString()}] [MCP Server] - ${toolName} Input String:\n${brief_thought}`);
-        // Return the input string directly, prefixed
-        return { content: [{ type: "text", text: `1) ${brief_thought}` }] };
+        // Return the input string directly
+        return { content: [{ type: "text", text: brief_thought }] };
     }
     catch (error) {
         // Catch only unexpected runtime errors
@@ -198,8 +198,8 @@ async ({ sandbox_content }) => {
         logToolResult(toolName, true, `Input received (length: ${sandbox_content.length})`);
         // Log the raw input string
         console.error(`[${new Date().toISOString()}] [MCP Server] - ${toolName} Input String:\n${sandbox_content}`);
-        // Return the input string directly, prefixed
-        return { content: [{ type: "text", text: `1) ${sandbox_content}` }] };
+        // Return the input string directly
+        return { content: [{ type: "text", text: sandbox_content }] };
     }
     catch (error) {
         // Catch only unexpected runtime errors

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@nbiish/cognitive-tools-mcp",
-  "version": "2.0.5",
+  "version": "2.0.7",
   "description": "Cognitive Tools MCP: SOTA reasoning suite focused on iterative refinement and tool integration for AI Pair Programming. Enables structured, iterative problem-solving through Chain of Draft methodology, with tools for draft generation, analysis, and refinement. Features advanced deliberation (`think`), rapid checks (`quick_think`), mandatory complexity assessment & thought mode selection (`assess_cuc_n_mode`), context synthesis, confidence gauging, proactive planning, explicit reasoning (CoT), and reflection with content return. Alternative package name for gikendaasowin-aabajichiganan-mcp.",
   "private": false,
   "type": "module",