@nbiish/cognitive-tools-mcp 4.0.2 → 4.0.4
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.
- package/README.md +2 -1
- package/build/index.js +11 -12
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -53,7 +53,7 @@ This project is licensed under the [COMPREHENSIVE RESTRICTED USE LICENSE FOR IND
|
|
|
53
53
|
◈──◆──◇─────────────────────────────────────────────────◇──◆──◈
|
|
54
54
|
</div>
|
|
55
55
|
|
|
56
|
-
ᑭᑫᓐᑖᓱᐎᓐ ᐋᐸᒋᒋᑲᓇᓐ - Advanced Agentic Cognitive Orchestration MCP (v4.0): Implements Gikendaasowin v8 Guidelines. Enforces a MANDATORY internal **Observe-Orient-Reason-Decide-Act (OOReDAct)** cycle via the unified 'deliberate' tool. This tool guides the LLM through sophisticated cognitive orchestration, including: initial CUC-N assessment and orientation with context engineering; structured deliberation with adaptive reasoning strategies, reflection, and self-critique. Emphasizes CodeAct preference for external tasks and returns Markdown. *(Note: The integration prompt and operational guidelines detailed in [`latest.md`](latest.md) are also covered by the [project LICENSE](LICENSE).)*
|
|
56
|
+
ᑭᑫᓐᑖᓱᐎᓐ ᐋᐸᒋᒋᑲᓇᓐ - Advanced Agentic Cognitive Orchestration MCP (v4.0.4): Implements Gikendaasowin v8 Guidelines. Enforces a MANDATORY internal **Observe-Orient-Reason-Decide-Act (OOReDAct)** cycle via the unified 'deliberate' tool. This tool guides the LLM through sophisticated cognitive orchestration, including: initial CUC-N assessment and orientation with context engineering; structured deliberation with adaptive reasoning strategies, reflection, and self-critique. Emphasizes CodeAct preference for external tasks and returns Markdown. *(Note: The integration prompt and operational guidelines detailed in [`latest.md`](latest.md) are also covered by the [project LICENSE](LICENSE).)*
|
|
57
57
|
|
|
58
58
|
Known as:
|
|
59
59
|
- Anishinaabemowin: [`@nbiish/gikendaasowin-aabajichiganan-mcp`](https://www.npmjs.com/package/@nbiish/gikendaasowin-aabajichiganan-mcp)
|
|
@@ -62,6 +62,7 @@ Known as:
|
|
|
62
62
|
Both packages are maintained in parallel and receive the same updates. You can use either package name in your projects - they provide identical functionality.
|
|
63
63
|
|
|
64
64
|
**◇ Recent Updates ◇**
|
|
65
|
+
- **◇ v4.0.4 ◇** Enhanced 'deliberate' tool with insights from latest research on context engineering for more robust AI agent performance and updated documentation to reflect Gikendaasowin v8 guidelines.
|
|
65
66
|
- **◇ v4.0.0 ◇** Updated to Gikendaasowin v8 Guidelines (2025 Edition), removed 'sandbox' stage, enhanced cognitive orchestration with reflection and self-critique, updated tool descriptions and server version.
|
|
66
67
|
- **◇ v2.0.25 ◇** Fixed MCP server tool registration format - corrected from incorrect `server.tool(name, description, schema.shape, handler)` to proper `server.tool(name, schema, handler)` format. Updated comprehensive tool documentation and version synchronization. Successfully published both packages.
|
|
67
68
|
- **◇ v2.0.17 ◇** Applied Anishinaabe-Cyberpunk styling and updated pre-publish workflow.
|
package/build/index.js
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
#!/usr/bin/env node
|
|
2
2
|
/**
|
|
3
3
|
* -----------------------------------------------------------------------------
|
|
4
|
-
* Gikendaasowin Aabajichiganan - Advanced Agentic Cognitive Orchestration MCP Server (v4.0)
|
|
4
|
+
* Gikendaasowin Aabajichiganan - Advanced Agentic Cognitive Orchestration MCP Server (v4.0.4)
|
|
5
5
|
*
|
|
6
6
|
* Description: Provides cognitive tools implementing the Gikendaasowin v8
|
|
7
7
|
* Agentic Operational Guidelines. Enforces a mandatory structured
|
|
@@ -12,12 +12,10 @@
|
|
|
12
12
|
* elements. Aligns with dynamic tool
|
|
13
13
|
* environments, including CodeAct preference. Returns Markdown.
|
|
14
14
|
*
|
|
15
|
-
* v4.0 Enhancements:
|
|
16
|
-
* - Updated server version to 4.0.
|
|
15
|
+
* v4.0.4 Enhancements:
|
|
16
|
+
* - Updated server version to 4.0.4.
|
|
17
|
+
* - Enhanced deliberate tool description with more information on usage and integration of latest research on context engineering, emphasizing dynamic context management and structured inputs for improved AI agent performance.
|
|
17
18
|
* - Implements Gikendaasowin v8 Guidelines.
|
|
18
|
-
* - Removed 'sandbox' stage.
|
|
19
|
-
* - Updated `serverInfo.description` to reflect v8.
|
|
20
|
-
* - Significantly expanded the `deliberate` tool's description to match v8 guidelines.
|
|
21
19
|
* - Maintained tooling compression, internal system prompt framing, and
|
|
22
20
|
* passthrough nature of the 'deliberate' tool.
|
|
23
21
|
* - Simplified error reporting remains.
|
|
@@ -29,8 +27,8 @@ import { z } from "zod";
|
|
|
29
27
|
// --- Server Definition ---
|
|
30
28
|
const serverInfo = {
|
|
31
29
|
name: "gikendaasowin-aabajichiganan-mcp",
|
|
32
|
-
version: "4.0.
|
|
33
|
-
description: `ᑭᑫᓐᑖᓱᐎᓐ ᐋᐸᒋᒋᑲᓇᓐ - Advanced Agentic Cognitive Orchestration MCP (v4.0): Implements Gikendaasowin v8 Guidelines. Enforces a MANDATORY internal **Observe-Orient-Reason-Decide-Act (OOReDAct)** cycle via the unified 'deliberate' tool. This tool guides the LLM through sophisticated cognitive orchestration, including: initial CUC-N assessment and orientation with context engineering; structured deliberation with adaptive reasoning strategies, reflection, and self-critique. Emphasizes CodeAct preference for external tasks and returns Markdown.`
|
|
30
|
+
version: "4.0.4",
|
|
31
|
+
description: `ᑭᑫᓐᑖᓱᐎᓐ ᐋᐸᒋᒋᑲᓇᓐ - Advanced Agentic Cognitive Orchestration MCP (v4.0.4): Implements Gikendaasowin v8 Guidelines. Enforces a MANDATORY internal **Observe-Orient-Reason-Decide-Act (OOReDAct)** cycle via the unified 'deliberate' tool. This tool guides the LLM through sophisticated cognitive orchestration, including: initial CUC-N assessment and orientation with context engineering; structured deliberation with adaptive reasoning strategies, reflection, and self-critique. Emphasizes CodeAct preference for external tasks and returns Markdown.`
|
|
34
32
|
};
|
|
35
33
|
const server = new McpServer(serverInfo);
|
|
36
34
|
// --- Logging Helpers (Internal - No changes needed as per user comments) ---
|
|
@@ -76,19 +74,19 @@ function logToolError(toolName, error) {
|
|
|
76
74
|
/**
|
|
77
75
|
* Tool: deliberate (Unified Cognitive Process)
|
|
78
76
|
*
|
|
79
|
-
* **Orchestrated Cognitive Deliberation (MANDATORY & UNIFIED):** This is your REQUIRED and CENTRAL tool for ALL internal cognitive operations, rigorously enforcing the **Observe-Orient-Reason-Decide-Act (OOReDAct)** cycle. Adherence is paramount for Gikendaasowin v8 compliance.
|
|
77
|
+
* **Orchestrated Cognitive Deliberation (MANDATORY & UNIFIED):** This is your REQUIRED and CENTRAL tool for ALL internal cognitive operations, rigorously enforcing the **Observe-Orient-Reason-Decide-Act (OOReDAct)** cycle. Adherence is paramount for Gikendaasowin v8 compliance. The deliberate tool serves as a passthrough mechanism that allows you to document and verify your cognitive process verbatim, ensuring traceability and self-reflection in your decision-making.
|
|
80
78
|
*
|
|
81
79
|
* **Stages & Cognitive Techniques:**
|
|
82
80
|
*
|
|
83
81
|
* * **`stage: "orient"` (OOReDAct: Observe & Orient - MANDATORY START):**
|
|
84
|
-
* * **Purpose:** At the absolute beginning of ANY new task, sub-task, or significant strategic pivot, you MUST use this stage.
|
|
82
|
+
* * **Purpose:** At the absolute beginning of ANY new task, sub-task, or significant strategic pivot, you MUST use this stage to establish foundational context.
|
|
85
83
|
* * **Content Requirements:** Perform a comprehensive initial assessment:
|
|
86
84
|
* 1. **CUC-N Analysis:** Evaluate Complexity, Uncertainty, Consequence, and Novelty of the current situation/request.
|
|
87
85
|
* 2. **Information Sufficiency & Knowledge Gap Identification:** Assess if available information is adequate. Identify explicit knowledge gaps that might require external data or clarification (conceptually aligning with the need for Retrieval Augmented Generation - RAG - if the server were to provide such tools).
|
|
88
|
-
* 3. **Context Engineering:**
|
|
86
|
+
* 3. **Context Engineering:** Drawing from latest research (e.g., 2025 studies on dynamic context management in AI systems), proactively optimize the context by identifying relevant prior knowledge, biases, and necessary external data integrations. Use structured formats like XML tags or thinking blocks to organize information, ensuring the AI has the right information in the right format at the right time for enhanced performance and reduced hallucinations.
|
|
89
87
|
* 4. **Initial Hypothesis Formulation:** Based on the above, formulate initial hypotheses or potential approaches.
|
|
90
88
|
* 5. **Goal Clarification:** Clearly define the immediate objective for this phase of deliberation.
|
|
91
|
-
* * This stage establishes critical context and grounds all subsequent reasoning.
|
|
89
|
+
* * This stage establishes critical context and grounds all subsequent reasoning, aligning with emerging best practices in AI agent design for improved reliability and adaptability.
|
|
92
90
|
*
|
|
93
91
|
* * **`stage: "reason"` (OOReDAct: Reason & Decide - MANDATORY DELIBERATION):**
|
|
94
92
|
* * **Purpose:** After the initial `orient` stage, and CRITICALLY after receiving ANY new information (tool results, CodeAct outputs/errors, user input, file contents, etc.), and BEFORE any non-trivial action, decision, or final response, you MUST use this stage for full, structured deliberation.
|
|
@@ -109,6 +107,7 @@ function logToolError(toolName, error) {
|
|
|
109
107
|
* * This `deliberate` tool acts as a passthrough; your `content` is returned verbatim for your own verification and state tracking.
|
|
110
108
|
* * The choice of reasoning strategy within the `reason` stage should be dynamic and justified by the task's specific demands.
|
|
111
109
|
* * Strict adherence to this structured deliberation protocol is essential for robust, verifiable, and adaptive agent performance.
|
|
110
|
+
* * Incorporate insights from recent AI research (2025) on context engineering to enhance overall cognitive processes.
|
|
112
111
|
* Acronym Key: CUC-N (Complexity, Uncertainty, Consequence, Novelty), CoT (Chain-of-Thought), PS (Plan-and-Solve), SCoT (Structured Chain-of-Thought), CoD/CR (Chain-of-Draft/Condensed Reasoning), ToT (Tree of Thoughts), PoT (Program of Thoughts), PAL (Program-aided Language Models).
|
|
113
112
|
*/
|
|
114
113
|
server.tool("deliberate", {
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@nbiish/cognitive-tools-mcp",
|
|
3
|
-
"version": "4.0.
|
|
3
|
+
"version": "4.0.4",
|
|
4
4
|
"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.",
|
|
5
5
|
"private": false,
|
|
6
6
|
"type": "module",
|