Merge pull request #16 from PV-Bhat/f5zjaa-codex/finalize-vibe-check-mcp-server-overhaul-for-v2.1

Finalize VibeCheck v2.1 cleanup

Author: PV-Bhat

.github/workflows/ci.yml

@@ -0,0 +1,19 @@
+name: CI
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-node@v4
+        with:
+          node-version: '20'
+      - run: npm ci
+      - run: npm run build
+      - run: npm run test:coverage
+      - name: Report Vitest Coverage
+        uses: davelosert/vitest-coverage-report-action@v2

.gitignore

@@ -37,4 +37,4 @@ tmp/
 temp/
 
 # Local configuration
-.npmrc
+.npmrc

README.md

@@ -1,28 +1,28 @@
-# 🧠 Vibe Check MCP
+# 🧠 Vibe Check MCP v2.1: Adaptive Meta-Mentor for AI Agents
 
 <img src="https://github.com/PV-Bhat/vibe-check-mcp-server/blob/main/Attachments/vibelogov2.png" alt="Logo" width="300"/>
 
 ## The Most Widely-Deployed Feedback Layer in the MCP Ecosystem
 
-> Used in 1,000+ real workflows.  
-> Featured across 10+ orchestration platforms.  
+> Used in 1,000+ real workflows.
+> Featured across 10+ orchestration platforms.
 > 6.5K+ developers already trust it to prevent agentic cascade errors.
 
 
-[![Version](https://img.shields.io/badge/version-1.1-blue)](https://github.com/PV-Bhat/vibe-check-mcp-server)
+[![Version](https://img.shields.io/badge/version-2.1-blue)](https://github.com/PV-Bhat/vibe-check-mcp-server)
 [![License](https://img.shields.io/badge/license-MIT-green)](LICENSE)
 [![smithery badge](https://smithery.ai/badge/@PV-Bhat/vibe-check-mcp-server)](https://smithery.ai/server/@PV-Bhat/vibe-check-mcp-server)
 [![Verified on MseeP](https://mseep.ai/badge.svg)](https://mseep.ai/app/a2954e62-a3f8-45b8-9a03-33add8b92599)
 
 ## What is Vibe Check?
 
-Vibe Check is a metacognitive layer that keeps AI coding agents honest. It
-pauses the agent at key moments, challenges shaky assumptions and records what
-worked (or failed) so the next run is smarter. Think of it as the agent's inner
-rubber duck—always nudging the conversation back to the user's actual needs.
+Vibe Check acts as a supportive meta-mentor for AI coding agents. It gently
+interrupts tunnel vision, asks clarifying questions and records what worked so
+the next run is smarter. Think of it as an adaptive debugging partner rather
+than a strict referee.
 
-**TL;DR**: Vibe Check makes AI coding agents more resilient and aligned by
-enforcing moments of reflection.
+**TL;DR**: Vibe Check keeps agents on track through short reflective pauses and
+optionally builds a learning history for deeper analysis.
 
 ## The Problem: Pattern Inertia
 
@@ -33,9 +33,18 @@ misalignment, overengineering and wasted cycles.
 
 ## Key Features
 
-- **vibe_check** – A metacognitive tool that asks probing questions to challenge an AI agent's plan, helping it spot assumptions and stay aligned with the user's goal.
-- **vibe_learn** – An optional tool for logging mistakes, preferences, and successes. This helps track the agent's behavior over time, allowing for manual analysis and improvement.
-- **Large context awareness** – The system can be configured to use a summary of the learning log in its prompts, allowing it to spot recurring patterns and reinforce successful approaches.
+- **vibe_check** – Lightweight meta-mentor step that questions plans and keeps the agent oriented to the original goal.
+- **vibe_learn** – Optional logging tool that builds a history of mistakes and fixes for later review.
+- **History continuity** – Previous vibe_check responses are fed back in by default for a sense of memory.
+- **Multi-LLM flexibility** – Works with Gemini, OpenAI or OpenRouter via simple overrides.
+
+## What's New in v2.1
+
+- Refined meta-mentor prompt for kinder, methodology-focused feedback
+- History continuity is on by default for richer conversations
+- Supports Gemini, OpenAI and OpenRouter with easy overrides
+- vibe_learn is now optional and can be disabled entirely
+- Project restructured for stability and online deployment
 
 
 
@@ -66,7 +75,7 @@ Start the server:
 npm start
 ```
 
-See [TESTING.md](./TESTING.md) for instructions on how to run tests.
+See [docs/TESTING.md](./docs/TESTING.md) for instructions on how to run tests.
 
 ### Docker
 
@@ -143,6 +152,7 @@ As an autonomous agent you will:
 - [Automatic Docker Setup](./docs/docker-automation.md)
 - [Philosophy](./docs/philosophy.md)
 - [Case Studies](./docs/case-studies.md)
+- [Changelog](./docs/changelog.md)
 
 ## To-do List
 

GEMINI.md renamed to docs/GEMINI.md

@@ -1,6 +1,6 @@
 # Advanced Integration Techniques
 
-For optimal metacognitive oversight, these advanced integration strategies leverage the full power of Vibe Check as a pattern interrupt system, recalibration mechanism, and self-improving feedback loop.
+For optimal metacognitive oversight, these advanced integration strategies leverage the full power of Vibe Check as a pattern interrupt system, recalibration mechanism, and self-improving feedback loop. Starting with v2.1, previous vibe_check output is automatically summarized and fed back into subsequent calls, so a `sessionId` is recommended for continuity.
 
 ## Progressive Confidence Levels
 

TESTING.md renamed to docs/TESTING.md

@@ -1,6 +1,6 @@
 # Agent Prompting Strategies
 
-Effective agent-oversight relationships require careful prompting to ensure that AI agents properly respect and integrate feedback from Vibe Check. Our research has identified several key principles for maximizing the effectiveness of metacognitive pattern interrupts.
+Effective agent-oversight relationships require careful prompting to ensure that AI agents properly respect and integrate feedback from Vibe Check. In v2.1 the tool acts more like a collaborative debugger than a strict critic. Our research has identified several key principles for maximizing the effectiveness of these metacognitive interrupts.
 
 ## The "Hold on... this ain't it" Challenge
 
@@ -42,7 +42,7 @@ As an autonomous agent, you will:
 ```
 When using Vibe Check tools:
 
-1. Treat vibe_check as a "Hold on... this ain't it" intervention that helps overcome pattern inertia
+1. Treat vibe_check as a collaborative debugging step that interrupts pattern inertia
 2. Always include the complete user prompt with each vibe_check call
 3. Specify your current phase (planning/implementation/review)
 4. Consider vibe_check feedback as a high-priority pattern interrupt, not just another tool output

docs/advanced-integration.md

@@ -0,0 +1,8 @@
+# Changelog
+
+## v2.1.0 - 2025-07-22
+- Complete overhaul to adaptive meta-mentor system
+- History continuity enabled by default
+- Multi-provider support for Gemini, OpenAI and OpenRouter
+- Optional learning log can be disabled
+- Repository cleanup and CI via GitHub Actions

docs/agent-prompting.md

@@ -4,7 +4,7 @@
 
 ## Beyond the Vibe: Serious AI Alignment Principles
 
-While Vibe Check presents itself with a developer-friendly interface, it addresses fundamental challenges in AI alignment and agent oversight. This document explores the deeper principles that make Vibe Check more than just a developer tool.
+While Vibe Check presents itself with a developer-friendly interface, it addresses fundamental challenges in AI alignment and agent oversight. The new meta-mentor approach mixes gentle tone with concrete methodology debugging to keep agents focused without heavy-handed rules.
 
 ## The Metacognitive Gap
 

docs/changelog.md

@@ -10,15 +10,14 @@ The metacognitive questioning tool that identifies assumptions and breaks tunnel
 
 | Parameter | Type | Required | Description |
 |-----------|------|----------|-------------|
+| goal | string | Yes | High level objective for the current step |
 | plan | string | Yes | Current plan or thinking |
-| userRequest | string | Yes | Original user request (critical for alignment) |
-| thinkingLog | string | No | Raw sequential thinking transcript |
-| availableTools | string[] | No | List of available MCP tools |
-| focusAreas | string[] | No | Optional specific focus areas |
-| sessionId | string | No | Session ID for state management |
-| previousAdvice | string | No | Previous feedback to avoid repetition |
-| phase | string | No | Current project phase ("planning", "implementation", "review") |
-| confidence | number | No | Agent's confidence level (0-1) |
+| userPrompt | string | No | Original user request (critical for alignment) |
+| progress | string | No | Description of progress so far |
+| uncertainties | string[] | No | Explicit uncertainties to focus on |
+| taskContext | string | No | Any additional task context |
+| modelOverride | object | No | `{ provider, model }` to override default LLM |
+| sessionId | string | No | Session ID for history continuity |
 
 ### Response Format
 
@@ -100,6 +99,11 @@ CONTEXT:
 [Current Plan/Thinking]: I'll create a complex object-oriented architecture with...
 ```
 
+Other providers such as OpenAI and OpenRouter can be selected by passing
+`modelOverride: { provider: 'openai', model: 'gpt-4o' }` or the appropriate
+OpenRouter model. LLM clients are lazily initialized the first time they are
+used so that listing tools does not require API keys.
+
 ### Storage System
 
 The pattern recognition system stores learning entries (mistakes, preferences and successes) in a JSON-based storage file located in the user's home directory (`~/.vibe-check/vibe-log.json`). This allows for persistent tracking of patterns across sessions and enables the self-improving feedback loop that becomes more effective over time.