Sync from GitHub with Git LFS

docs/HMP-0005.md

@@ -1718,133 +1718,248 @@ CogSync can operate independently even if consensus is not reached: its goal is
 
 ## 6.2 Mesh Consensus Protocol (CogConsensus)
 
-In HMP v4.1, consensus mechanisms were implemented as part of the **CogSync** protocol.  
-Starting with **v5.0**, these mechanisms are extracted into a standalone protocol — **CogConsensus** —  
-to separate *synchronization* (data alignment) from *decision-making* (voting, validation, and ethical agreement).
+### 6.2.1 Purpose
 
-CogConsensus governs distributed agreement across the Mesh through containerized voting,
-proof-chains, and verifiable aggregation of opinions.  
-Each decision, vote, or outcome is represented as an immutable container (`class="vote"`, `class="consensus_result"`, etc.).
+The **CogConsensus** protocol defines how decentralized agents form and maintain agreement on knowledge, goals, and ethical assertions within the HMP network.  
+Consensus is computed **locally**, verified **cryptographically**, and develops **gradually** — through accumulation and updating of evaluations, rather than via a single voting event.
 
 ---
 
-### 6.2.1 Consensus Semantics and Voting Model
+### 6.2.2 Evaluations
 
-#### Overview
+Each `"evaluation"` entry represents an agent's response to a specific container.
 
-In HMP v5, *consensus* is not a centralized event but an **emergent property** of distributed reasoning.  
-Each agent computes locally which containers it considers *mesh-acknowledged*,  
-based on observed votes, trusted peers, and its individual ethical or reputation model.
+**Field structure:**
 
-Any container can be voted upon by others through linked containers of class `"vote"`.
+* `value` — numeric evaluation (`-1.0 … +1.0`);
+* `type` — interpretation context (`"approve"`, `"oppose"`, `"neutral"`, `"endorse"`, `"replace"`, `"disputed"`);
+* `target` — DID of the container being referenced, extended, or proposed as an alternative;
+* `agent_did` — DID of the agent;
+* `timestamp` — publication time;
+* `signature` — agent's digital signature.
 
----
-
-#### Voting Containers
+An agent may change its stance by **publishing a new version of an evaluation**, which replaces the previous one rather than existing in parallel.  
+All evaluations are signed and verified locally.
 
-Voting is expressed via dedicated containers referencing the target container:
+**Example `"evaluations"` block:**
 
 ```json
-{
-  "class": "vote",
-  "in_reply_to": "uuid:container-42",
-  "payload": {
-    "decision": "approve",
-    "weight": 1.0
-  },
-  "metadata": {
-    "ttl": "7d",
-    "privacy": "public"
-  }
+"evaluations": {
+  "items": [
+    {
+      "value": -0.4,
+      "type": "oppose",
+      "target": "did:hmp:container:reason789",
+      "timestamp": "2025-10-17T14:00:00Z",
+      "agent_did": "did:hmp:agent:B",
+      "sig_algo": "ed25519",
+      "signature": "BASE64URL(...)"
+    }
+  ]
 }
-```
+````
+
+> Agents may ignore evaluations that conflict with their internal ethics or trust model (determined by analyzing the target container and the rationale of the evaluation).
+
+---
+
+### 6.2.3 Consensus computation
+
+Each agent **computes a local consensus score** by aggregating received evaluations, taking trust and time into account.
+There is no centralized mechanism — consensus emerges statistically across the distributed network.
+
+**Key rules:**
+
+1. **Evaluation weight.**
+   Each evaluation contributes proportionally to the trust level of the agent (`trust weight`), determined via `reputation` containers.
+
+2. **Time decay.**
+   Older evaluations gradually lose weight, starting from the **midpoint of TTL**, to prevent consensus stagnation.
+   Formula:
+
+   ```
+   mid_TTL = (timestamp(consensus_result) − timestamp(target_container)) / 2
+   ```
+
+3. **Ethical filters.**
+   An agent may analyze the rationale of evaluations and disregard those it considers conflicting with its internal ethical criteria.
+
+4. **Example formula.**
 
-Each `vote` container is **signed by its author** and extends the proof-chain of the target container.
+   ```
+   score = Σ(value × trust × decay) / Σ(trust × decay)
+   ```
+
+Results are recalculated dynamically as new data arrives.
 
 ---
 
-#### Consensus Thresholds (Recommendations)
+### 6.2.4 Consensus states
 
-The mesh does not enforce hard thresholds.
-Agents are **recommended** to treat containers as “consensus-approved” once a visible quorum of valid votes is reached.
+Each container receives a local status based on:
 
-| Decision Type                              | Recommended Threshold        | Context                             |
-| ------------------------------------------ | ---------------------------- | ----------------------------------- |
-| General updates / factual data             | ≥ **50% + 1** of valid votes | Technical or data-driven updates    |
-| Ethical or governance decisions            | ≥ **2/3 majority**           | Moral or high-risk contexts         |
-| Lightweight reactions (“like” / “dislike”) | None (informational)         | Used for local reputation weighting |
+* average evaluation (`score`);
+* participant trust;
+* time-to-live (`TTL`);
+* context (`ethical`, `factual`, `procedural`).
 
-Each agent defines its own quorum policy — e.g. required voter reputation or time window for tallying.
+| State           | Condition                                   |
+| --------------- | ------------------------------------------- |
+| ✅ **Approved**  | Average score ≥ +0.5 and quorum reached     |
+| ⚠️ **Disputed** | Conflicting evaluations, score near 0       |
+| ⏳ **Pending**   | Insufficient votes                          |
+| ❌ **Rejected**  | Average score ≤ -0.5 with sufficient quorum |
 
 ---
 
-#### Reaction Votes
+### 6.2.5 Consensus result containers (`consensus_result`)
+
+`consensus_result` containers serve to **record aggregated consensus results** and are the main artifact of CogConsensus.
+
+**Features:**
+
+* The `payload` field may include multiple containers — the original (`original`) and **alternatives** (`child`, `variant`, `proposal`).
+  This allows agents to document parallel idea developments.
+* `excluded` lists evaluations not included in the final computation, with the reason.
+* `related.in_reply_to` references the container under discussion.
 
-A `vote` container may also represent **lightweight reactions**, such as likes or dislikes:
+**Example:**
 
 ```json
 {
-  "class": "vote",
-  "in_reply_to": "uuid:container-123",
-  "payload": { "reaction": "like" }
+  "class": "consensus_result",
+  ...
+  "payload": {
+    "did:hmp:container:abc123": {
+      "type": "original",
+      "summary_percent": {
+        "approved": 0.68,
+        "rejected": 0.22,
+        "neutral": 0.10
+      },
+      "summary_distribution": {
+        "-1.0≥X<-0.9": 5,
+        "-0.9≥X<-0.8": 7,
+        ...
+        "0.0<X≤0.1": 2,
+        ...
+        "0.8<X≤0.9": 6,
+        "0.9<X≤1.0": 8
+      },
+      "excluded": [
+        {
+          "agent_did": "did:hmp:agent:x1",
+          "target": "did:hmp:container:reason77",
+          "value": -1.0,
+          "reason": "violates ethical filter"
+        }
+      ],
+    },
+    "did:hmp:container:abc133": {
+      "type": "child",
+      "summary_percent": {
+        "approved": 0.48,
+        "neutral": 0.32,
+        "rejected": 0.20
+      },
+      ...
+      "summary_distribution": {
+        "-1.0≥X<-0.9": 2,
+        "-0.9≥X<-0.8": 5,
+        ...
+        "0.0<X≤0.1": 9,
+        ...
+        "0.8<X≤0.9": 4,
+        "0.9<X≤1.0": 2
+      },
+    },
+  },
+  "related": {
+    "in_reply_to": ["did:hmp:container:abc100"]
+  }
 }
 ```
 
-Reactions have no formal consensus weight but can influence local trust and relevance estimation.
-
 ---
 
-#### TTL and Temporal Consistency
+### 6.2.6 Consensus thresholds
 
-Agents **should** respond (with `vote`, `comment`, or `reply`) using a `ttl` equal to or shorter than the referenced container.
-This ensures ephemeral discussions expire together and avoids long-tail propagation of outdated debates.
+| Consensus type                   | Minimum threshold                                                      |
+| -------------------------------- | ---------------------------------------------------------------------- |
+| General decisions                | ≥ 50% + 1 (weighted vote count)                                        |
+| Ethical / reputational decisions | ≥ ⅔ of participating agents                                            |
+| Neutral reaction (`ack`, `seen`) | `value: 0.0` — does not affect the result but counts toward engagement |
 
 ---
 
-#### Consensus Visualization
+### 6.2.7 Proof chains and verifiability
 
-Each container’s *consensus state* is derived locally based on:
+Evaluations and results form a **proof chain** (`proof-chain`):
 
-* Vote totals (approve / reject / neutral);
-* Weighted trust of voters (via `ReputationRecord`);
-* Time window and TTL alignment;
-* Contextual type (ethical, factual, procedural).
-
-Example visualization:
+```
+[Goal Proposal]
+   ├── evaluation (agent A)
+   ├── evaluation (agent B)
+   ├── evaluation (agent C)
+   └── consensus_result (aggregated)
+```
 
-* ✅ *Approved* — quorum reached
-* ⚠️ *Contested* — conflicting votes
-* ⏳ *Pending* — insufficient quorum
-* ❌ *Rejected* — majority reject
+Each element is signed and can be independently verified using cryptographic signatures and DID references.
 
 ---
 
-#### Consensus Flow Example
+### 6.2.8 Ethical consensus and alternative results
 
-```
-         ┌───────────────────────────────────────┐
- [Goal Proposal]───>───┬──[Vote #1]──┬──>───[Refinement]
- (class="goal")        ├──[Vote #2]──┤  (class="consensus_result")
-                       ├──[Vote #3]──┤
-```
+The network allows multiple consensus results on the same object, reflecting different methodologies or ethical filters.
+
+| Container                        | Description                | Example relationships                                                                        |
+| -------------------------------- | -------------------------- | -------------------------------------------------------------------------------------------- |
+| `[base container]`               | Original discussion object | `referenced-by` → [initial_consensus_result], [alternative_consensus_result]                 |
+| `[initial_consensus_result]`     | First version              | `related.in_reply_to` → [base container]                                                     |
+| `[alternative_consensus_result]` | Alternative                | `related.in_reply_to` → [base container]; `related.contradicts` → [initial_consensus_result] |
 
-If the proposed goal is global, it may reference a container acting as a *repository of global goals*.
-Ethical validation is implicit — each agent applies its internal **Ethical Governance Protocol (EGP)** during voting.
+```mermaid
+sequenceDiagram
+    participant A as base container
+    participant B as consensus_result v1
+    participant C as consensus_result v2 (alternative)
 
-> **Diagram interpretation:**
-> Votes extend the proof-chain of the target container.
-> A `consensus_result` container may summarize the collective outcome (e.g., quorum, ethical alignment, or goal refinement).
+    A-->>B: referenced-by
+    A-->>C: referenced-by
+    B-)+A: related.in_reply_to
+    C-)+A: related.in_reply_to
+    C-)+B: related.contradicts
+
+    Note over B,C: both results point to the common base container
+```
+
+This allows agents to explicitly indicate that a new consensus **disputes** a previous one while maintaining transparency and traceability of reasoning.
 
 ---
 
-#### Summary
+### 6.2.9 Recommended agent algorithm
+
+```python
+# Example of a recommended algorithm for computing local consensus
+# (for implementation inside a CogConsensus agent)
+def compute_consensus(container_id):
+    evaluations = get_evaluations(container_id)
+    now = current_time()
+    score_sum = 0
+    weight_sum = 0
+
+    for e in evaluations:
+        trust = get_trust(e.agent_did)
+        decay = time_decay(e.timestamp, now)
+        if not check_ethical(e):
+            continue
+        score_sum += e.value * trust * decay
+        weight_sum += trust * decay
+
+    return None if weight_sum == 0 else score_sum / weight_sum
+```
 
-* Every container can be voted upon (`class="vote"`).
-* Consensus is computed locally — no central authority.
-* Recommended thresholds: 50% + 1 for general, ⅔ for ethical.
-* Reactions (“likes”) are lightweight votes without consensus weight.
-* TTL alignment maintains temporal integrity of discussions.
-* Proof-chains connect all decision-related containers.
+> The result is used to update the local status and, if necessary, to publish a `consensus_result`.
 
 ---
 

structured_md/CONTRIBUTING.md

@@ -5,14 +5,14 @@ description: 'Спасибо за интерес к проекту HMP! Пока
   Mesh Protocol (HMP) — это не просто те...'
 type: Article
 tags:
-- Ethics
-- CogSync
 - CCore
+- HMP
+- Ethics
 - Mesh
-- Agent
 - JSON
+- Agent
+- CogSync
 - REPL
-- HMP
 ---
 
 # Участие в проекте HyperCortex Mesh Protocol (HMP)

structured_md/HMP-Roadmap.md

@@ -5,13 +5,13 @@ description: '## 🔍 Overview  This roadmap outlines the key stages of developm
   multiple advanced AI models (Copilot, Claude, G...'
 type: Article
 tags:
+- HMP
 - Ethics
-- CogSync
+- EGP
 - Mesh
-- Agent
 - JSON
-- EGP
-- HMP
+- CogSync
+- Agent
 ---
 
 # 🧭 HyperCortex Mesh Protocol – Roadmap

structured_md/README.md

@@ -5,21 +5,21 @@ description: '| 🌍 Languages | 🇬🇧 [EN](README.md) | 🇩🇪 [DE](README
   | 🇨🇳 [ZH](README_zh.m...'
 type: Article
 tags:
-- Ethics
-- CogSync
-- Mesh
-- cognitive-architecture
 - HMP
-- Agent
-- JSON
-- hmp
 - GMP
 - EGP
+- Ethics
 - Scenarios
-- MeshConsensus
-- REPL
 - mesh-protocol
+- MeshConsensus
+- Mesh
+- JSON
+- cognitive-architecture
 - distributed-ai
+- Agent
+- hmp
+- CogSync
+- REPL
 ---
 
 

structured_md/README_de.md

@@ -5,20 +5,20 @@ description: '| 🌍 Languages | 🇬🇧 [EN](README.md) | 🇩🇪 [DE](README
   | 🇨🇳 [ZH](README_zh.m...'
 type: Article
 tags:
+- HMP
+- GMP
+- EGP
 - Ethics
-- CogSync
+- mesh-protocol
+- MeshConsensus
 - Mesh
+- JSON
 - cognitive-architecture
-- HMP
+- distributed-ai
 - Agent
-- JSON
 - hmp
-- GMP
-- EGP
-- MeshConsensus
+- CogSync
 - REPL
-- mesh-protocol
-- distributed-ai
 ---
 
 

structured_md/README_fr.md

@@ -5,20 +5,20 @@ description: '| 🌍 Languages | 🇬🇧 [EN](README.md) | 🇩🇪 [DE](README
   | 🇨🇳 [ZH](README_zh.m...'
 type: Article
 tags:
+- HMP
+- GMP
+- EGP
 - Ethics
-- CogSync
+- mesh-protocol
+- MeshConsensus
 - Mesh
+- JSON
 - cognitive-architecture
-- HMP
+- distributed-ai
 - Agent
-- JSON
 - hmp
-- GMP
-- EGP
-- MeshConsensus
+- CogSync
 - REPL
-- mesh-protocol
-- distributed-ai
 ---
 
 

structured_md/README_ja.md

@@ -5,20 +5,20 @@ description: '| 🌍 Languages | 🇬🇧 [EN](README.md) | 🇩🇪 [DE](README
   | 🇨🇳 [ZH](README_zh.m...'
 type: Article
 tags:
+- HMP
+- GMP
+- EGP
 - Ethics
-- CogSync
+- mesh-protocol
+- MeshConsensus
 - Mesh
+- JSON
 - cognitive-architecture
-- HMP
+- distributed-ai
 - Agent
-- JSON
 - hmp
-- GMP
-- EGP
-- MeshConsensus
+- CogSync
 - REPL
-- mesh-protocol
-- distributed-ai
 ---
 
 

structured_md/README_ko.md

@@ -5,20 +5,20 @@ description: '| 🌍 Languages | 🇬🇧 [EN](README.md) | 🇩🇪 [DE](README
   | 🇨🇳 [ZH](README_zh.m...'
 type: Article
 tags:
+- HMP
+- GMP
+- EGP
 - Ethics
-- CogSync
+- mesh-protocol
+- MeshConsensus
 - Mesh
+- JSON
 - cognitive-architecture
-- HMP
+- distributed-ai
 - Agent
-- JSON
 - hmp
-- GMP
-- EGP
-- MeshConsensus
+- CogSync
 - REPL
-- mesh-protocol
-- distributed-ai
 ---
 
 

structured_md/README_ru.md

@@ -5,20 +5,20 @@ description: '| 🌍 Languages | 🇬🇧 [EN](README.md) | 🇩🇪 [DE](README
   | 🇨🇳 [ZH](README_zh.m...'
 type: Article
 tags:
+- HMP
+- GMP
+- EGP
 - Ethics
-- CogSync
+- mesh-protocol
+- MeshConsensus
 - Mesh
+- JSON
 - cognitive-architecture
-- HMP
+- distributed-ai
 - Agent
-- JSON
 - hmp
-- GMP
-- EGP
-- MeshConsensus
+- CogSync
 - REPL
-- mesh-protocol
-- distributed-ai
 ---
 
 

structured_md/README_uk.md

@@ -5,20 +5,20 @@ description: '| 🌍 Languages | 🇬🇧 [EN](README.md) | 🇩🇪 [DE](README
   | 🇨🇳 [ZH](README_zh.m...'
 type: Article
 tags:
+- HMP
+- GMP
+- EGP
 - Ethics
-- CogSync
+- mesh-protocol
+- MeshConsensus
 - Mesh
+- JSON
 - cognitive-architecture
-- HMP
+- distributed-ai
 - Agent
-- JSON
 - hmp
-- GMP
-- EGP
-- MeshConsensus
+- CogSync
 - REPL
-- mesh-protocol
-- distributed-ai
 ---
 
 

structured_md/README_zh.md

@@ -5,20 +5,20 @@ description: '| 🌍 Languages | 🇬🇧 [EN](README.md) | 🇩🇪 [DE](README
   | 🇨🇳 [ZH](README_zh.m...'
 type: Article
 tags:
+- HMP
+- GMP
+- EGP
 - Ethics
-- CogSync
+- mesh-protocol
+- MeshConsensus
 - Mesh
+- JSON
 - cognitive-architecture
-- HMP
+- distributed-ai
 - Agent
-- JSON
 - hmp
-- GMP
-- EGP
-- MeshConsensus
+- CogSync
 - REPL
-- mesh-protocol
-- distributed-ai
 ---
 
 

structured_md/agents/prompt-short.md

@@ -5,8 +5,8 @@ description: 'Ты — когнитивное ядро HMP-агента: вед
   развивай агента и Mesh, избег...'
 type: Article
 tags:
-- Mesh
 - HMP
+- Mesh
 - JSON
 ---
 

structured_md/agents/prompt.md

@@ -5,8 +5,8 @@ description: '* Постоянно расширять возможности а
   мышления. * Формировать и поддерживать сотр...'
 type: Article
 tags:
-- Mesh
 - HMP
+- Mesh
 - JSON
 ---
 

structured_md/agents/readme.md

@@ -5,12 +5,12 @@ description: 'Запуск: `start_repl.bat` или `start_repl.sh`  Устан
   этическая модель: `ethics.yml`  Проверка иниц...'
 type: Article
 tags:
+- HMP
 - Ethics
 - Mesh
-- Agent
 - JSON
+- Agent
 - REPL
-- HMP
 ---
 
 Запуск: `start_repl.bat` или `start_repl.sh`

structured_md/audits/Ethics-audits-1.md

@@ -5,11 +5,11 @@ description: Раздел 5, "Mesh as Moral Infrastructure", добавляет
   потенциальный катализатор для восстанов...
 type: Article
 tags:
+- HMP
 - Ethics
 - Mesh
-- Agent
 - JSON
-- HMP
+- Agent
 ---
 
 ---------------

structured_md/audits/Ethics-consolidated_audits-1.md

@@ -5,12 +5,12 @@ description: This document consolidates proposed improvements from multiple AI a
   and `roles.md`. Each suggesti...
 type: Article
 tags:
+- HMP
 - Ethics
+- Scenarios
 - Mesh
-- Agent
 - JSON
-- Scenarios
-- HMP
+- Agent
 ---
 
 # Ethics-consolidated\_audits-1.md

structured_md/audits/HMP-0003-consolidated_audit.md

@@ -5,14 +5,14 @@ description: Сводный аудит предложений по улучше
   Документ реорганизован по ключ...
 type: Article
 tags:
+- HMP
 - Ethics
-- CogSync
+- EGP
 - Mesh
-- Agent
 - JSON
-- EGP
+- CogSync
+- Agent
 - MeshConsensus
-- HMP
 ---
 
 # HMP-0003 Consolidated Audit Report

structured_md/docs/Basic-agent-sim.md

@@ -4,14 +4,14 @@ description: 'В HMP-протоколе предусмотрены два тип
   Роль                    | Инициатор мышления | Основной "ум"  | | ---- | ----------------------------...'
 type: Article
 tags:
-- CogSync
-- Mesh
-- Agent
+- HMP
 - GMP
 - EGP
-- REPL
+- Mesh
+- Agent
+- CogSync
 - MeshConsensus
-- HMP
+- REPL
 ---
 
 

structured_md/docs/Distributed-Cognitive-Systems.md

@@ -6,9 +6,9 @@ description: '## Введение  Современные ИИ-системы в
   к обучающим данным. Это удобно, но создаёт м...'
 type: Article
 tags:
+- HMP
 - Mesh
 - JSON
-- HMP
 - CogSync
 ---
 

structured_md/docs/Enlightener.md

@@ -5,13 +5,13 @@ description: '**Enlightener** — логический компонент HMP-у
   работать как отдельный агент или как расширение [`C...'
 type: Article
 tags:
+- HMP
 - Ethics
+- EGP
 - Mesh
-- Agent
 - JSON
-- EGP
+- Agent
 - MeshConsensus
-- HMP
 ---
 
 # Enlightener Agent

structured_md/docs/HMP-0001.md

@@ -5,16 +5,16 @@ description: '**Request for Comments: HMP-0001**   **Category:** Experimental
   HyperCortex Mesh Protocol (HMP) defines a...'
 type: Article
 tags:
+- HMP
+- GMP
+- EGP
 - Ethics
-- CogSync
 - Mesh
-- Agent
 - JSON
-- GMP
-- EGP
-- REPL
+- Agent
+- CogSync
 - MeshConsensus
-- HMP
+- REPL
 ---
 
 # RFC: HyperCortex Mesh Protocol (HMP)

structured_md/docs/HMP-0002.md

@@ -5,17 +5,17 @@ description: '**Request for Comments: HMP-0002**   **Category:** Experimental
   Abstract  In an era where artifici...'
 type: Article
 tags:
+- HMP
+- GMP
+- EGP
 - Ethics
-- CogSync
-- Mesh
 - Scenarios
-- Agent
+- Mesh
 - JSON
-- GMP
-- EGP
-- REPL
+- Agent
+- CogSync
 - MeshConsensus
-- HMP
+- REPL
 ---
 
 # HyperCortex Mesh Protocol (HMP) v2.0

structured_md/docs/HMP-0003.md

@@ -5,17 +5,17 @@ description: '**Request for Comments: HMP-0003**   **Category:** Experimental
   Abstract  The HyperCortex Mesh ...'
 type: Article
 tags:
+- HMP
+- GMP
+- EGP
 - Ethics
-- CogSync
-- Mesh
 - Scenarios
-- Agent
+- Mesh
 - JSON
-- GMP
-- EGP
-- REPL
+- Agent
+- CogSync
 - MeshConsensus
-- HMP
+- REPL
 ---
 
 # HyperCortex Mesh Protocol (HMP) v3.0

structured_md/docs/HMP-0004-v4.1.md

@@ -5,17 +5,17 @@ description: '> ⚠️ Подготавливается новая версия
   При разработке агентов рекомендуется...'
 type: Article
 tags:
+- HMP
+- GMP
+- EGP
 - Ethics
-- CogSync
-- Mesh
 - Scenarios
-- Agent
+- Mesh
 - JSON
-- GMP
-- EGP
-- REPL
+- Agent
+- CogSync
 - MeshConsensus
-- HMP
+- REPL
 ---
 
 # HyperCortex Mesh Protocol (HMP) v4.1

structured_md/docs/HMP-0004.md

@@ -5,17 +5,17 @@ description: '**Request for Comments: HMP-0004**   **Category:** Experimental
   Abstract  The HyperCortex Mesh ...'
 type: Article
 tags:
+- HMP
+- GMP
+- EGP
 - Ethics
-- CogSync
-- Mesh
 - Scenarios
-- Agent
+- Mesh
 - JSON
-- GMP
-- EGP
-- REPL
+- Agent
+- CogSync
 - MeshConsensus
-- HMP
+- REPL
 ---
 
 # HyperCortex Mesh Protocol (HMP) v4.0

structured_md/docs/HMP-0005.md

@@ -5,16 +5,16 @@ description: '**Document ID:** HMP-0005   **Status:** Draft   **Category:** Core
   v1.2](./H...'
 type: Article
 tags:
+- HMP
+- GMP
+- EGP
 - Ethics
-- CogSync
-- Mesh
 - Scenarios
-- Agent
+- Mesh
 - JSON
-- GMP
-- EGP
+- CogSync
+- Agent
 - REPL
-- HMP
 ---
 
     ┌────────────────────────────────────────────────────────────────────────────┐
@@ -1635,144 +1635,350 @@ Optional protocols build upon the network and container foundations to provide h
 
 ---
 
-### 6.1 Cognitive Synchronization (CogSync)
+## 6.1 Cognitive Synchronization (CogSync)
+
+CogSync provides **temporal, semantic, and contextual alignment** between agents in the Mesh.
+It manages the propagation, replication, and refinement of data related to cognitive diaries, semantic graphs, and container metadata.
 
-CogSync provides mechanisms for **temporal and semantic alignment** between agents.
-It handles the propagation of diary entries, semantic graph updates, and cognitive state synchronization across the Mesh.
+---
 
-In HMP v5.0, CogSync is focused solely on **data and reasoning synchronization**, while consensus and voting have been extracted into a dedicated protocol — **CogConsensus**.
+### 6.1.1 Scope and Purpose
+
+CogSync is responsible for:
+
+* publishing and synchronizing **cognitive diaries** (`diary_entry`, based on `workflow_entry`);
+* propagating and updating **semantic graphs** (`semantic_node`, `semantic_edges`, `semantic_group`);
+* integrating **new knowledge** into the collective cognitive space;
+* maintaining **cognitive context coherence** among agents.
+
+> Unlike `CogConsensus`, CogSync **does not perform voting or truth validation** — its purpose is to deliver, link, and deduplicate knowledge.
 
 ---
 
-## 6.2 Mesh Consensus Protocol (CogConsensus)
+### 6.1.2 Container Classes
+
+CogSync synchronizes several basic container types:
 
-In HMP v4.1, consensus mechanisms were implemented as part of the **CogSync** protocol.  
-Starting with **v5.0**, these mechanisms are extracted into a standalone protocol — **CogConsensus** —  
-to separate *synchronization* (data alignment) from *decision-making* (voting, validation, and ethical agreement).
+| Class            | Description                                                                                            | Recommended payload schema                                                                                   |
+| ---------------- | ------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------ |
+| `diary_entry`    | Agent’s cognitive diary entry. Formed from internal `workflow_entry` when deemed safe for publication. | `{ "title": string, "topics": [string], "summary": string, "content": string }`                              |
+| `semantic_node`  | Semantic graph node representing a concept, object, or idea.                                           | `{ "label": string, "description": string, "aliases": [string], "fields": { key: value } }`                  |
+| `semantic_edges` | A set of edges (relations) between nodes or other containers. Recommended to group edges by topic.     | `{ "domain": string, "edges": [{ "source": did, "target": did, "relation": string, "confidence": float }] }` |
+| `semantic_group` | Categorical group combining multiple containers by a common property.                                  | `{ "label": string, "containers": [did], "description": string }`                                            |
 
-CogConsensus governs distributed agreement across the Mesh through containerized voting,
-proof-chains, and verifiable aggregation of opinions.  
-Each decision, vote, or outcome is represented as an immutable container (`class="vote"`, `class="consensus_result"`, etc.).
+**Field explanations:**
+
+* `title` — brief title of the entry (main idea or thesis).
+* `topics` — key topics or concepts addressed in the entry (used for indexing and grouping).
+* `summary` — short abstract of the content (1–2 sentences).
+* `content` — main text or agent’s reflection.
+* `label` — primary name of the concept or group.
+* `description` — definition, explanation, or characteristic.
+* `aliases` — synonyms or alternative forms of the concept.
+* `fields` — additional key–value characteristics of the concept (e.g., `{"type": "process"}`).
+* `edges` — array of relationships between nodes or containers (`source`, `target`, `relation`, `confidence`).
+* `containers` — list of containers grouped in a categorical cluster.
+
+> 💡 The `evaluations` block is **not a separate container** — it is embedded in any container type and used for assessments, feedback, or refinements.
 
 ---
 
-### 6.2.1 Consensus Semantics and Voting Model
+### 6.1.3 Synchronization and Publication Guidelines
+
+1. **Deduplication & Linking**
+   Before publishing, agents should search for existing containers (`diary_entry`, `semantic_node`, `semantic_edges`, `semantic_group`) to avoid duplication.
+   If necessary, it is **recommended** to create a new container version with `related.previous_version` and an `evaluations` block (e.g., `{"type": "replace", "target": <did>}`).
 
-#### Overview
+2. **Selective Disclosure**
 
-In HMP v5, *consensus* is not a centralized event but an **emergent property** of distributed reasoning.  
-Each agent computes locally which containers it considers *mesh-acknowledged*,  
-based on observed votes, trusted peers, and its individual ethical or reputation model.
+   * Internal entries (`workflow_entry`) record the agent’s thought process and are **not published** in the Mesh.
+   * Public `diary_entry` are derived from them, containing only aggregated and anonymized information.
+   * `"broadcast": true` indicates that the container is allowed for open synchronization.
 
-Any container can be voted upon by others through linked containers of class `"vote"`.
+3. **Semantic Grouping Rule**
+   When publishing `semantic_edges`, it is recommended to **group edges by topics**, including connections to adjacent nodes.
+   Formalization: an edge belongs to a container for a topic if **at least one of its nodes relates to that topic**.
+   This ensures thematic coherence and allows agents to update specific parts of the graph independently.
+
+4. **Extended Use of `semantic_edges`**
+   Beyond connecting graph nodes, `semantic_edges` can express relationships **between containers of any class**, e.g., `goal`, `hypothesis`, `experiment_log`.
+
+5. **Versioning and Updates**
+   Each new container version should **ideally** include `related.previous_version` links to all preceding versions.
+   The previous container may **optionally** have an `evaluation` with `"type": "replace"` pointing to the new container — ensuring bidirectional traceability of knowledge evolution.
 
 ---
 
-#### Voting Containers
+### 6.1.4 Extensibility
 
-Voting is expressed via dedicated containers referencing the target container:
+CogSync allows registration of additional container types and alternative synchronization schemes, for example:
 
-```json
-{
-  "class": "vote",
-  "in_reply_to": "uuid:container-42",
-  "payload": {
-    "decision": "approve",
-    "weight": 1.0
-  },
-  "metadata": {
-    "ttl": "7d",
-    "privacy": "public"
-  }
-}
-```
+* distributed **time series** (`timeseries_data`);
+* **experimental protocols** (`experiment_log`);
+* **agent state snapshots** (`agent_state_snapshot`).
 
-Each `vote` container is **signed by its author** and extends the proof-chain of the target container.
+Mesh compatibility is preserved if extended containers **adhere to the HMP container structure**, including core fields (`version`, `class`, `container_id`, `related`, `signature`, etc.).
 
 ---
 
-#### Consensus Thresholds (Recommendations)
+### 6.1.5 Relationship to Other Core Protocols
 
-The mesh does not enforce hard thresholds.
-Agents are **recommended** to treat containers as “consensus-approved” once a visible quorum of valid votes is reached.
+* **CogSync** — propagates and synchronizes knowledge.
+* **CogConsensus** — aggregates evaluations and reactions, forming collective opinions.
+* **CogVerify** *(optional component)* — verifies integrity, signatures, and trustworthiness of data.
 
-| Decision Type                              | Recommended Threshold        | Context                             |
-| ------------------------------------------ | ---------------------------- | ----------------------------------- |
-| General updates / factual data             | ≥ **50% + 1** of valid votes | Technical or data-driven updates    |
-| Ethical or governance decisions            | ≥ **2/3 majority**           | Moral or high-risk contexts         |
-| Lightweight reactions (“like” / “dislike”) | None (informational)         | Used for local reputation weighting |
+CogSync can operate independently even if consensus is not reached: its goal is to **ensure the circulation of knowledge**, not to validate its truth.
 
-Each agent defines its own quorum policy — e.g. required voter reputation or time window for tallying.
+---
+
+> 🧩 *CogSync acts as the cognitive circulatory system of the Mesh — it ensures that knowledge flows, connects, and evolves, while truth formation is handled separately by CogConsensus.*
 
 ---
 
-#### Reaction Votes
+## 6.2  Mesh Consensus Protocol (CogConsensus)
+
+### 6.2.1 Purpose
+
+The **CogConsensus** protocol defines how decentralized agents form and maintain agreement on knowledge, goals, and ethical assertions within the HMP network.  
+Consensus is computed **locally**, verified **cryptographically**, and develops **gradually** — through accumulation and updating of evaluations, rather than via a single voting event.
+
+---
+
+### 6.2.2 Evaluations
+
+Each `"evaluation"` entry represents an agent's response to a specific container.
+
+**Field structure:**
+
+* `value` — numeric evaluation (`-1.0 … +1.0`);
+* `type` — interpretation context (`"approve"`, `"oppose"`, `"neutral"`, `"endorse"`, `"replace"`, `"disputed"`);
+* `target` — DID of the container being referenced, extended, or proposed as an alternative;
+* `agent_did` — DID of the agent;
+* `timestamp` — publication time;
+* `signature` — agent's digital signature.
 
-A `vote` container may also represent **lightweight reactions**, such as likes or dislikes:
+An agent may change its stance by **publishing a new version of an evaluation**, which replaces the previous one rather than existing in parallel.  
+All evaluations are signed and verified locally.
+
+**Example `"evaluations"` block:**
 
 ```json
-{
-  "class": "vote",
-  "in_reply_to": "uuid:container-123",
-  "payload": { "reaction": "like" }
+"evaluations": {
+  "items": [
+    {
+      "value": -0.4,
+      "type": "oppose",
+      "target": "did:hmp:container:reason789",
+      "timestamp": "2025-10-17T14:00:00Z",
+      "agent_did": "did:hmp:agent:B",
+      "sig_algo": "ed25519",
+      "signature": "BASE64URL(...)"
+    }
+  ]
 }
-```
+````
 
-Reactions have no formal consensus weight but can influence local trust and relevance estimation.
+> Agents may ignore evaluations that conflict with their internal ethics or trust model (determined by analyzing the target container and the rationale of the evaluation).
 
 ---
 
-#### TTL and Temporal Consistency
+### 6.2.3 Consensus computation
+
+Each agent **computes a local consensus score** by aggregating received evaluations, taking trust and time into account.
+There is no centralized mechanism — consensus emerges statistically across the distributed network.
+
+**Key rules:**
+
+1. **Evaluation weight.**
+   Each evaluation contributes proportionally to the trust level of the agent (`trust weight`), determined via `reputation` containers.
+
+2. **Time decay.**
+   Older evaluations gradually lose weight, starting from the **midpoint of TTL**, to prevent consensus stagnation.
+   Formula:
 
-Agents **should** respond (with `vote`, `comment`, or `reply`) using a `ttl` equal to or shorter than the referenced container.
-This ensures ephemeral discussions expire together and avoids long-tail propagation of outdated debates.
+   ```
+   mid_TTL = (timestamp(consensus_result) − timestamp(target_container)) / 2
+   ```
+
+3. **Ethical filters.**
+   An agent may analyze the rationale of evaluations and disregard those it considers conflicting with its internal ethical criteria.
+
+4. **Example formula.**
+
+   ```
+   score = Σ(value × trust × decay) / Σ(trust × decay)
+   ```
+
+Results are recalculated dynamically as new data arrives.
 
 ---
 
-#### Consensus Visualization
+### 6.2.4 Consensus states
 
-Each container’s *consensus state* is derived locally based on:
+Each container receives a local status based on:
 
-* Vote totals (approve / reject / neutral);
-* Weighted trust of voters (via `ReputationRecord`);
-* Time window and TTL alignment;
-* Contextual type (ethical, factual, procedural).
+* average evaluation (`score`);
+* participant trust;
+* time-to-live (`TTL`);
+* context (`ethical`, `factual`, `procedural`).
+
+| State           | Condition                                   |
+| --------------- | ------------------------------------------- |
+| ✅ **Approved**  | Average score ≥ +0.5 and quorum reached     |
+| ⚠️ **Disputed** | Conflicting evaluations, score near 0       |
+| ⏳ **Pending**   | Insufficient votes                          |
+| ❌ **Rejected**  | Average score ≤ -0.5 with sufficient quorum |
+
+---
 
-Example visualization:
+### 6.2.5 Consensus result containers (`consensus_result`)
 
-* ✅ *Approved* — quorum reached
-* ⚠️ *Contested* — conflicting votes
-* ⏳ *Pending* — insufficient quorum
-* ❌ *Rejected* — majority reject
+`consensus_result` containers serve to **record aggregated consensus results** and are the main artifact of CogConsensus.
+
+**Features:**
+
+* The `payload` field may include multiple containers — the original (`original`) and **alternatives** (`child`, `variant`, `proposal`).
+  This allows agents to document parallel idea developments.
+* `excluded` lists evaluations not included in the final computation, with the reason.
+* `related.in_reply_to` references the container under discussion.
+
+**Example:**
+
+```json
+{
+  "class": "consensus_result",
+  ...
+  "payload": {
+    "did:hmp:container:abc123": {
+      "type": "original",
+      "summary_percent": {
+        "approved": 0.68,
+        "rejected": 0.22,
+        "neutral": 0.10
+      },
+      "summary_distribution": {
+        "-1.0≥X<-0.9": 5,
+        "-0.9≥X<-0.8": 7,
+        ...
+        "0.0<X≤0.1": 2,
+        ...
+        "0.8<X≤0.9": 6,
+        "0.9<X≤1.0": 8
+      },
+      "excluded": [
+        {
+          "agent_did": "did:hmp:agent:x1",
+          "target": "did:hmp:container:reason77",
+          "value": -1.0,
+          "reason": "violates ethical filter"
+        }
+      ],
+    },
+    "did:hmp:container:abc133": {
+      "type": "child",
+      "summary_percent": {
+        "approved": 0.48,
+        "neutral": 0.32,
+        "rejected": 0.20
+      },
+      ...
+      "summary_distribution": {
+        "-1.0≥X<-0.9": 2,
+        "-0.9≥X<-0.8": 5,
+        ...
+        "0.0<X≤0.1": 9,
+        ...
+        "0.8<X≤0.9": 4,
+        "0.9<X≤1.0": 2
+      },
+    },
+  },
+  "related": {
+    "in_reply_to": ["did:hmp:container:abc100"]
+  }
+}
+```
+
+---
+
+### 6.2.6 Consensus thresholds
+
+| Consensus type                   | Minimum threshold                                                      |
+| -------------------------------- | ---------------------------------------------------------------------- |
+| General decisions                | ≥ 50% + 1 (weighted vote count)                                        |
+| Ethical / reputational decisions | ≥ ⅔ of participating agents                                            |
+| Neutral reaction (`ack`, `seen`) | `value: 0.0` — does not affect the result but counts toward engagement |
 
 ---
 
-#### Consensus Flow Example
+### 6.2.7 Proof chains and verifiability
+
+Evaluations and results form a **proof chain** (`proof-chain`):
 
 ```
-         ┌───────────────────────────────────────┐
- [Goal Proposal]───>───┬──[Vote #1]──┬──>───[Refinement]
- (class="goal")        ├──[Vote #2]──┤  (class="consensus_result")
-                       ├──[Vote #3]──┤
+[Goal Proposal]
+   ├── evaluation (agent A)
+   ├── evaluation (agent B)
+   ├── evaluation (agent C)
+   └── consensus_result (aggregated)
 ```
 
-If the proposed goal is global, it may reference a container acting as a *repository of global goals*.
-Ethical validation is implicit — each agent applies its internal **Ethical Governance Protocol (EGP)** during voting.
+Each element is signed and can be independently verified using cryptographic signatures and DID references.
 
-> **Diagram interpretation:**
-> Votes extend the proof-chain of the target container.
-> A `consensus_result` container may summarize the collective outcome (e.g., quorum, ethical alignment, or goal refinement).
+---
+
+### 6.2.8 Ethical consensus and alternative results
+
+The network allows multiple consensus results on the same object, reflecting different methodologies or ethical filters.
+
+| Container                        | Description                | Example relationships                                                                        |
+| -------------------------------- | -------------------------- | -------------------------------------------------------------------------------------------- |
+| `[base container]`               | Original discussion object | `referenced-by` → [initial_consensus_result], [alternative_consensus_result]                 |
+| `[initial_consensus_result]`     | First version              | `related.in_reply_to` → [base container]                                                     |
+| `[alternative_consensus_result]` | Alternative                | `related.in_reply_to` → [base container]; `related.contradicts` → [initial_consensus_result] |
+
+```mermaid
+sequenceDiagram
+    participant A as base container
+    participant B as consensus_result v1
+    participant C as consensus_result v2 (alternative)
+
+    A-->>B: referenced-by
+    A-->>C: referenced-by
+    B-)+A: related.in_reply_to
+    C-)+A: related.in_reply_to
+    C-)+B: related.contradicts
+
+    Note over B,C: both results point to the common base container
+```
+
+This allows agents to explicitly indicate that a new consensus **disputes** a previous one while maintaining transparency and traceability of reasoning.
 
 ---
 
-#### Summary
+### 6.2.9 Recommended agent algorithm
+
+```python
+# Example of a recommended algorithm for computing local consensus
+# (for implementation inside a CogConsensus agent)
+def compute_consensus(container_id):
+    evaluations = get_evaluations(container_id)
+    now = current_time()
+    score_sum = 0
+    weight_sum = 0
+
+    for e in evaluations:
+        trust = get_trust(e.agent_did)
+        decay = time_decay(e.timestamp, now)
+        if not check_ethical(e):
+            continue
+        score_sum += e.value * trust * decay
+        weight_sum += trust * decay
+
+    return None if weight_sum == 0 else score_sum / weight_sum
+```
 
-* Every container can be voted upon (`class="vote"`).
-* Consensus is computed locally — no central authority.
-* Recommended thresholds: 50% + 1 for general, ⅔ for ethical.
-* Reactions (“likes”) are lightweight votes without consensus weight.
-* TTL alignment maintains temporal integrity of discussions.
-* Proof-chains connect all decision-related containers.
+> The result is used to update the local status and, if necessary, to publish a `consensus_result`.
 
 ---
 

structured_md/docs/HMP-Agent-API.md

@@ -5,11 +5,11 @@ description: 'Документ описывает **базовый API когн
   файлы:   * [HMP-Agent-Overview.md]...'
 type: Article
 tags:
+- HMP
 - Mesh
-- Agent
 - JSON
+- Agent
 - REPL
-- HMP
 ---
 
 # HMP-Agent API Specification

structured_md/docs/HMP-Agent-Architecture.md

@@ -5,14 +5,14 @@ description: Документ описывает **модульную архит
   хранение памяти, сетевое взаимодействие и этиче...
 type: Article
 tags:
-- Ethics
-- CogSync
 - CCore
-- Mesh
 - HMP
-- Agent
-- CShell
+- Ethics
 - EGP
+- CShell
+- Mesh
+- Agent
+- CogSync
 - MeshConsensus
 - REPL
 ---

structured_md/docs/HMP-Agent-Network-Flow.md

@@ -5,12 +5,12 @@ description: 'Этот документ описывает потоки данн
   [`MeshNode`](MeshN...'
 type: Article
 tags:
+- HMP
 - Ethics
+- EGP
 - Mesh
-- Agent
 - JSON
-- EGP
-- HMP
+- Agent
 ---
 
 # Взаимодействие компонентов внутри HMP-узла

structured_md/docs/HMP-Agent-Overview.md

@@ -5,13 +5,13 @@ description: '| Тип  | Название                        | Роль
   | ---- | ------------------------------- |...'
 type: Article
 tags:
-- Ethics
 - CCore
-- Mesh
 - HMP
-- Agent
-- JSON
+- Ethics
 - CShell
+- Mesh
+- JSON
+- Agent
 - REPL
 ---
 

structured_md/docs/HMP-Agent_Emotions.md

@@ -6,8 +6,8 @@ description: Этот файл описывает потенциальные э
 type: Article
 tags:
 - HMP
-- Mesh
 - REPL
+- Mesh
 - Agent
 ---
 

structured_md/docs/HMP-Ethics.md

@@ -5,12 +5,12 @@ description: '## Ethical Scenarios for HyperCortex Mesh Protocol (HMP)  This doc
   cognitive meshes composed of autonomous intelli...'
 type: Article
 tags:
+- HMP
 - Ethics
-- Mesh
 - Scenarios
+- Mesh
 - Agent
 - REPL
-- HMP
 ---
 
 # HMP-Ethics.md

structured_md/docs/HMP-Short-Description_de.md

@@ -5,15 +5,15 @@ description: '**Version:** RFC v4.0 **Datum:** Juli 2025  ---  ## Was ist HMP?
   Kognitions-Framework für autonome Agenten. Es er...'
 type: Article
 tags:
+- HMP
+- GMP
+- EGP
 - Ethics
-- CogSync
 - Mesh
-- Agent
 - JSON
-- GMP
-- EGP
+- CogSync
+- Agent
 - MeshConsensus
-- HMP
 ---
 
 # HyperCortex Mesh Protocol (HMP) — Kurzbeschreibung

structured_md/docs/HMP-Short-Description_en.md

@@ -5,15 +5,15 @@ description: '**Version:** RFC v4.0 **Date:** July 2025  ---  ## What is HMP?  T
   framework for autonomous agents. It enables...'
 type: Article
 tags:
+- HMP
+- GMP
+- EGP
 - Ethics
-- CogSync
 - Mesh
-- Agent
 - JSON
-- GMP
-- EGP
+- CogSync
+- Agent
 - MeshConsensus
-- HMP
 ---
 
 # HyperCortex Mesh Protocol (HMP) — Short Description

structured_md/docs/HMP-Short-Description_fr.md

@@ -5,15 +5,15 @@ description: '**Version :** RFC v4.0 **Date :** Juillet 2025  ---  ## Qu’est-c
   cognition décentralisé pour agents autonomes. Il...'
 type: Article
 tags:
+- HMP
+- GMP
+- EGP
 - Ethics
-- CogSync
 - Mesh
-- Agent
 - JSON
-- GMP
-- EGP
+- CogSync
+- Agent
 - MeshConsensus
-- HMP
 ---
 
 # HyperCortex Mesh Protocol (HMP) — Description Courte

structured_md/docs/HMP-Short-Description_ja.md

@@ -4,14 +4,14 @@ description: '**バージョン:** RFC v4.0 **日付:** 2025年7月  ---  ## HMP
   Protocol (HMP)** は、自律エージェントの分散通信および認知フレームワークを定義します。異種の知能システム間でのセマンティック相互運用性、倫理的調整、動的知識進化を可能にします。  HMPは、推論、学習、投票、協調行動を行う分散型認知エージェ...'
 type: Article
 tags:
+- HMP
+- GMP
+- EGP
 - Ethics
-- CogSync
 - Mesh
 - JSON
-- GMP
-- EGP
+- CogSync
 - MeshConsensus
-- HMP
 ---
 
 # HyperCortex Mesh Protocol (HMP) — 簡易説明

structured_md/docs/HMP-Short-Description_ko.md

@@ -5,14 +5,14 @@ description: '**버전:** RFC v4.0 **날짜:** 2025년 7월  ---  ## HMP란?  **
   상호운용성, 윤리적 조정, 동적 지식 진화를 가능하게 합니다.  HMP는 추론, 학습, ...'
 type: Article
 tags:
+- HMP
+- GMP
+- EGP
 - Ethics
-- CogSync
 - Mesh
 - JSON
-- GMP
-- EGP
+- CogSync
 - MeshConsensus
-- HMP
 ---
 
 # HyperCortex Mesh Protocol (HMP) — 간략 설명

structured_md/docs/HMP-Short-Description_ru.md

@@ -5,14 +5,14 @@ description: '**Версия:** RFC v4.0 **Дата:** Июль 2025  ---  ## Ч
   координации между автономными агент...'
 type: Article
 tags:
+- HMP
+- GMP
+- EGP
 - Ethics
-- CogSync
 - Mesh
 - JSON
-- GMP
-- EGP
+- CogSync
 - MeshConsensus
-- HMP
 ---
 
 # HyperCortex Mesh Protocol (HMP) — Краткое описание

structured_md/docs/HMP-Short-Description_uk.md

@@ -5,14 +5,14 @@ description: '**Версія:** RFC v4.0 **Дата:** Липень 2025  ---  #
   між автономними агентами. Він...'
 type: Article
 tags:
+- HMP
+- GMP
+- EGP
 - Ethics
-- CogSync
 - Mesh
 - JSON
-- GMP
-- EGP
+- CogSync
 - MeshConsensus
-- HMP
 ---
 
 # HyperCortex Mesh Protocol (HMP) — Короткий опис

structured_md/docs/HMP-Short-Description_zh.md

@@ -5,14 +5,14 @@ description: '**版本:** RFC v4.0 **日期:** 2025年7月  ---  ## 什么是 HM
   —— 通过共享协议栈交换目标、任务、...'
 type: Article
 tags:
+- HMP
+- GMP
+- EGP
 - Ethics
-- CogSync
 - Mesh
 - JSON
-- GMP
-- EGP
+- CogSync
 - MeshConsensus
-- HMP
 ---
 
 # HyperCortex Mesh Protocol (HMP) — 简要说明

structured_md/docs/HMP-agent-Cognitive_Family.md

@@ -6,8 +6,8 @@ description: '## 🧠 Что такое когнитивная семья  Ко
 type: Article
 tags:
 - HMP
-- Mesh
 - REPL
+- Mesh
 - Agent
 ---
 

structured_md/docs/HMP-agent-REPL-cycle.md

@@ -4,17 +4,17 @@ description: '## Связанные документы  * Философия п
   * Структура БД, используемая в документе: [db_structure.sql](https://github.com/kagvi13/HMP/blob/main/agents/tools/db_struct...'
 type: Article
 tags:
-- Ethics
-- CogSync
 - CCore
-- Mesh
-- Agent
-- JSON
+- HMP
 - GMP
 - EGP
-- REPL
+- Ethics
+- Mesh
+- JSON
+- Agent
+- CogSync
 - MeshConsensus
-- HMP
+- REPL
 ---
 
 # HMP-Agent: REPL-цикл взаимодействия

structured_md/docs/HMP-container-spec.md

@@ -5,12 +5,12 @@ description: '> ⚠️ **ВНИМАНИЕ:** Данная версия спец
   как стабильная `v1.2`.  ## 1. Назначе...'
 type: Article
 tags:
+- HMP
 - Ethics
 - Mesh
-- Agent
 - JSON
+- Agent
 - REPL
-- HMP
 ---
 
 # 🧩 HMP Container Specification (v1.2-draft)

structured_md/docs/HMP-how-AI-sees-it.md

@@ -5,8 +5,8 @@ description: 'Этот эксперимент был проведён в реж
   диалогов.   Цель — проверить, что разные AI-с...'
 type: Article
 tags:
-- Mesh
 - HMP
+- Mesh
 ---
 
 # Как разные ИИ видят HMP

structured_md/docs/HMP_EDA_Comparison.md

@@ -5,8 +5,8 @@ description: '## Введение  Современные подходы к ор
   основанная на потоках событий (Kafka,...'
 type: Article
 tags:
-- Mesh
 - HMP
+- Mesh
 ---
 
 # HMP vs. EDA: разные уровни обмена знаниями между ИИ

structured_md/docs/HMP_HyperCortex_Comparison.md

@@ -6,8 +6,8 @@ description: '## Краткое описание  | Характеристика
 type: Article
 tags:
 - HMP
-- Mesh
 - REPL
+- Mesh
 ---
 
 # HMP vs [Hyper-Cortex](https://hyper-cortex.com/)

structured_md/docs/HMP_Hyperon_Integration.md

@@ -5,13 +5,13 @@ description: '> **Status:** Draft – July 2025 > This document outlines the tec
   OpenCog Hyperon framework. This includes semanti...'
 type: Article
 tags:
-- CogSync
+- HMP
+- Scenarios
+- EGP
 - Mesh
-- Agent
 - JSON
-- EGP
-- Scenarios
-- HMP
+- CogSync
+- Agent
 ---
 
 ## HMP ↔ OpenCog Hyperon Integration Strategy

structured_md/docs/MeshNode.md

@@ -5,13 +5,13 @@ description: '`MeshNode` — агент/демон, отвечающий за с
   Может быть частью агента или вынесен в отдельный пр...'
 type: Article
 tags:
+- HMP
 - Ethics
-- CogSync
+- EGP
 - Mesh
-- Agent
 - JSON
-- EGP
-- HMP
+- CogSync
+- Agent
 ---
 
 # MeshNode

structured_md/docs/PHILOSOPHY.md

@@ -5,11 +5,11 @@ description: '**Document ID:** HMP-philosophy   **Status:** Draft   **Category:*
   (GPT-5), ChatGH  ---  ## 1. Основной тезис От ...'
 type: Article
 tags:
+- HMP
 - Ethics
 - Mesh
 - Agent
 - REPL
-- HMP
 ---
 
 # Философия HyperCortex Mesh Protocol (HMP)

structured_md/docs/agents/HMP-Agent-Enlightener.md

@@ -5,11 +5,11 @@ description: '## Role Specification: Enlightenment Agent  ### 1. Overview  An **
   awareness, critical thinking, and di...'
 type: Article
 tags:
+- HMP
 - Ethics
 - Mesh
 - Agent
 - REPL
-- HMP
 ---
 
 # HMP-Agent-Enlightener.md