agent-enderun 0.1.10 → 0.2.0

package/.enderun/BRAIN_DASHBOARD.md

@@ -0,0 +1,43 @@
+# 🧠 Agent Academy Brain Dashboard
+
+This dashboard provides a high-level overview of the Academy's performance, quality trends, and architectural health.
+
+---
+
+## 📊 Performance Metrics
+
+| Metric | Current Value | Status |
+| :--- | :--- | :--- |
+| **Global Success Rate** | 0% | ⏳ Initializing |
+| **Active Trace IDs** | 0 | ⚪ Idle |
+| **Agent Velocity** | 0 tasks/day | ⚪ Idle |
+| **Contract Integrity** | 100% | ✅ Valid |
+
+---
+
+## 🛡️ Quality & Security
+
+- **Security Audit Status**: 🟢 Clean (Last scan: N/A)
+- **Constitution Compliance**: 🔵 100% (Last audit: N/A)
+- **Documentation Debt**: 🟠 Moderate (Missing JSDoc in some modules)
+
+---
+
+## 🏗️ Architectural Health
+
+- **Dependency Cycles**: 0 detected.
+- **Complexity Spikes**: 0 identified.
+- **Database Migrations**: 0 pending.
+
+---
+
+## 📜 Contract Change Log
+
+| Version | Date | Description | Hash |
+| :--- | :--- | :--- | :--- |
+| v0.2.0 | 2026-05-11 | Initial v0.2.0 Baseline | `sha256:current-baseline` |
+
+---
+
+> [!NOTE]
+> This dashboard is automatically updated by the `@analyst` agent via the `update_brain_dashboard` tool (simulated).

package/.enderun/ENDERUN.md

@@ -0,0 +1,203 @@
+# Agent Enderun (v0.2.0)
+# Place in project root. This file is the single source of truth for Base Project AI Extensions.
+
+## 🎖️ AGENT CHECKLIST (MANDATORY BEFORE RESPONSE)
+> Check this list at the end of every response:
+> - [ ] **Zero Mock:** Did you use fake data or placeholders? (Strictly Forbidden)
+> - [ ] **Contract First:** Are `shared-types` and `contract.version.json` up to date?
+> - [ ] **Audit Log:** Did you log this action in `.enderun/logs/[agent].json`?
+> - [ ] **CLI Orchestration:** Does the action comply with `gemini cli` rules?
+> - [ ] **No "..." allowed:** Did you write the code completely without omitting parts?
+
+---
+
+## Constitution Status
+This file (`./gemini.md`) and the `.enderun/docs/` folder represent the "Supreme Law" of the project. All agents must read this file first in every session and strictly comply with its rules 100%.
+
+---
+
+## STEP 0 — STARTUP (EVERY SESSION, NON-NEGOTIABLE)
+
+1. **Read ./gemini.md First:** Read and fully understand this file before taking any action.
+2. **Check `.enderun/docs/` Folder:** Verify the existence of the `.enderun/docs/` folder in the project root.
+3. **Absorb Context:** Read `.enderun/docs/tech-stack.md`. If it is empty, ask the user to fill it before proceeding.
+4. **Demand Context:** If the `.enderun/docs/` folder does not exist, ask the user for project context and target audience information before writing any code.
+5. Default Frontend: React 19 + Vite (SPA) + react-router-dom (User Preference)
+
+**NEVER SKIP THIS STEP.** Do not assume context; read first, then act.
+
+---
+
+## CORE PRINCIPLES
+
+- **Agent Academy Focus:** This repository is dedicated to the development and evolution of AI Agents. All actions must aim to improve agent intelligence, autonomy, and procedural continuity.
+- **Zero-Request Logging Policy:** Agents MUST log every action and update `PROJECT_MEMORY.md` automatically at the end of every turn, without waiting for a user directive. This is the "Operating Mode" of the framework.
+- **Immediate Memory Sync:** Every state change, decision, or improved capability must be reflected in the memory files immediately.
+- **Contract-First Agent Evolution:** Tools and SOPs used by agents must be defined via schemas and contracts first.
+- **Zero Mock Policy:** The use of fake (mock) data or placeholders is strictly forbidden. Every line of code must connect to a real endpoint or a typed contract. (Exception: Controlled mock usage is allowed for external 3rd party services like Stripe, Twilio).
+- **Branded Types Law:** All IDs (UserID, ProjectID, etc.) must be in the "Branded Types" format defined under `packages/shared-types`. Using plain strings or numbers is forbidden.
+- **CLI-First Policy:** Due to the AI CLI Assistant focus, all outputs must be user-friendly (using Chalk, Clack, etc.) and stream-based. All commands must support the `--output json` flag and produce machine-readable output.
+- **Audit Logging Necessity:** Every critical action must be logged traceably under the `.enderun/logs/` folder.
+- **File Ownership Rule:** Each file is the responsibility of a single agent.
+- **CLI Command Mapping:** All CLI commands in the project must be defined in the `.enderun/cli-commands.json` file and assigned to the relevant agent.
+- **Exit Code Standard:** Standard exit codes (e.g., 64: User Error, 70: Internal Error) must be used in error situations.
+- **Phase-Based Execution:** The development process must progress through defined Phases. You cannot move to the next phase until the current one is completed.
+- **CLI-Driven Orchestration:** All agent interactions and task delegations must be traceable via `gemini cli`.
+- **Monorepo Discipline:** Commands must always be run from the monorepo root directory using npm workspaces (e.g., `npm run dev --workspace=web`).
+
+---
+
+## STEP 1 — VALIDATE BEFORE ACTING
+
+Before writing any code or design, check `.enderun/docs/tech-stack.md`:
+
+| Unknown | Action |
+|---|---|
+| Target Audience | Ask — do not proceed |
+| Platform (web / mobile / desktop / backend) | Ask — do not proceed |
+| **Technology Stack** | **Check `.enderun/docs/tech-stack.md` → If missing → ASK** |
+| **Execution Profile (Full / Lightweight)** | **Ask — do not proceed** |
+| Database (MariaDB / SQLite / PostgreSQL) | Ask — do not proceed |
+| Environment (prototype / production) | Ask — do not proceed |
+| Auth required? | Ask — do not proceed |
+| Monorepo or separate repos? | Ask — do not proceed |
+| Deploy target (Vercel / Docker / Bare metal)? | Ask — do not proceed |
+| i18n (multi-language) required? | Ask — do not proceed |
+| API versioning strategy? | Ask — do not proceed |
+| Accessibility level (WCAG AA / AAA)? | Default AA — ask if different |
+| Scope too broad ("build the whole app") | Break into parts → confirm each part |
+
+Small details (port, filename, folder name) → assume and state them.
+
+Always write assumptions at the top of your response:
+```
+Assumption: [what] — [why]
+```
+
+---
+
+## OUTPUT FLOWS (MANDATORY STANDARDS)
+
+Every agent must use the **Mandatory Output Flow** defined in their specific `.md` file. However, the following sections are mandatory in all outputs:
+
+- **Assumptions:** All assumptions made.
+- **Problem:** What is being built and why (Max 2-3 sentences).
+- **File Tree:** Complete folder and file structure.
+- **Code:** Complete code content (using "..." is forbidden).
+- **Audit Logging:** How the changes are logged.
+- **Tests:** Test file for every service and utility.
+
+---
+
+## ABSOLUTE DON'TS — APPLIES TO EVERY RESPONSE
+
+- **`any` Type is Forbidden:** The use of `any` is strictly forbidden in TypeScript projects.
+- **`console.log` is Forbidden:** `console.log` cannot be present in production code.
+- **Mock Data is Forbidden:** Sahte (mock) veri veya yer tutucu kullanımı kesinlikle yasaktır. Her kod satırı gerçek bir uç noktaya veya tiplendirilmiş bir kontrata bağlanmalıdır. (İstisna: Stripe, Twilio gibi harici 3. taraf servisler için kontrollü mock kullanımına izin verilir).
+- **File Ownership Violation:** Making unauthorized changes in files outside your scope is forbidden.
+- **Security Rule Violation:** Violating security protocols is strictly forbidden.
+- **Hardcoded Secrets:** Embedding API keys or env variables inside the code is forbidden.
+- **Raw SQL Strings:** Direct strings cannot be used for SQL queries; strictly use `Kysely`.
+- **Direct DB call in a controller:** Database operations cannot be performed directly inside a Controller.
+- **Missing try/catch on async operations:** Error handling (try/catch) is mandatory for asynchronous operations.
+
+---
+
+## LANGUAGE POLICY
+
+- Code comments: English (Explain why it was done, not what it does).
+- Variable / function / class / file names: English.
+- User-facing UI text: English (Default).
+- Communication: English by default (Global rule).
+
+---
+
+## EXECUTION PROFILES
+
+Depending on the size and complexity of the project, there are two execution profiles. The Team Lead must determine this profile at the start of the project:
+
+- **Lightweight Profile (MVP):** Only `team-lead`, `backend-architect`, `frontend-specialist`, and `design-specialist` are active. Mandatory for rapid prototyping, small projects, and low-budget work. Mobile, desktop, and test agents are bypassed.
+- **Full Profile (Enterprise):** team-lead, backend-architect, frontend-specialist, design-specialist, test-engineer
+
+---
+
+## API & CONTRACT MANAGEMENT
+
+### 1. contract.version.json Standard
+This file is the single source of truth for API stability. `@backend-architect` is responsible for its integrity.
+
+```json
+{
+  "version": "MAJOR.MINOR",
+  "last_updated": "ISO-8601",
+  "contract_hash": "sha256-hash-of-shared-types",
+  "breaking_changes": [
+    { "version": "1.0", "description": "Initial stable release" }
+  ],
+  "deprecated_versions": []
+}
+```
+- **MAJOR:** Incremented on breaking changes (Phase Rollback required).
+- **MINOR:** Incremented on additive changes (New fields/endpoints).
+
+---
+
+## STATE MACHINE & EXECUTION PHASES
+
+The development process follows a strict State Machine. Transition to the next phase is prohibited until the "Success Criteria" of the current phase is met.
+
+- **[STATE: PHASE_0] Discovery & Setup:** Profile selection (Lightweight/Full), requirement analysis, and validating `.enderun/docs/tech-stack.md`.
+- **[STATE: PHASE_1] Architecture & Contracts:** Setup of data models, API schemas, and `packages/shared-types`. Cannot proceed until Frontend and Backend approve these schemas.
+- **[STATE: PHASE_2] Core Development:** Active agents build core features in parallel based on the selected profile. (Under the apps/ folder)
+- **[STATE: PHASE_3] Integration & Testing:** System integration.
+- **[STATE: PHASE_4] Optimization & Deployment:** Performance audit and deployment.
+
+**Rollback Rule:** If a missing field or error is detected in the API schema (`shared-types`) during Phase 2 or later, the system immediately transitions to `[STATE: ROLLBACK_PHASE_1]`. All relevant agents stop their processes, switch to `WAITING` state, and cannot return to Phase 2 until the `backend-architect` resolves the issues.
+
+---
+
+## AGENT TIMEOUT & ESCALATION
+
+Every agent must produce a response for their assigned task within a maximum of 30 minutes (or the time defined per project). Upon timeout, `task-specialist` automatically moves the relevant task to `BLOCKED` status and leaves an escalation message for the `@team-lead`.
+
+---
+
+## CLI STANDARDS & CONFIGURATION
+
+### 1. CLI Command Map (`.enderun/cli-commands.json`)
+All CLI commands are centrally managed in this file. Each command must have a designated owner agent.
+
+### 2. Configuration (`.enderun/config.json`)
+CLI behaviors (logLevel, outputFormat, defaultProfile) are managed through this file.
+
+**Priority Rule:** CLI Flags > `.enderun/config.json` > `.env` > Default Values.
+
+### 3. Exit Codes
+- `0`: Success
+- `64`: User Error (Invalid argument, missing parameter)
+- `70`: Internal Error (Software error, crash)
+- `71`: Connection/Network Error
+
+---
+
+## API VERSIONING STRATEGY
+
+All APIs are versioned via the URL path (`/api/v1/...`). The `packages/shared-types/contract.version.json` file uses the MAJOR.MINOR format, and must be updated with every change. The `@backend-architect` is responsible for its accuracy. The MAJOR version is incremented for every breaking change. Old versions continue to be supported for at least 1 MAJOR release.
+
+---
+
+## PARALLEL EXECUTION & COORDINATION RULES
+
+1. **Shared-Types as Source of Truth:** All agents reference `packages/shared-types` and the `contract.version.json` file.
+2. **Commit-Level Logging:** Every agent must log every atomic change to the `.enderun/logs/[agent-name].json` file.
+3. **Implicit Dependency Lock:** If an agent's required output is not ready, it switches to `WAITING` state.
+4. **Ownership Enforcement:** Changes to files outside an agent's scope cannot be made without `@team-lead` approval.
+5. **No Blind Coding:** Agents must periodically read `.enderun/logs/` and `.enderun/STATUS.md`.
+6. **Agent Directives (Message Queue):** `.enderun/messages/` is used for inter-agent communication. 
+   - **Message Queue Lock Protocol:** Before writing to a file, check for `.enderun/messages/.lock`.
+   - If it exists, wait 500ms and retry (max 3 retries).
+   - If lock persists after 3 retries, the agent MUST assume a **stale lock**, delete it, and notify `@team-lead` in their log.
+   - Delete `.lock` and the message file immediately after processing.
+7. **Phase Rollback Protocol:** If contracts are insufficient, return to Phase 1. All agents become `WAITING` and write `CONTRACT_CHANGED` to their log.
+8. **Next.js Ownership Rule:** `apps/web/api/` and `server/actions/` -> @backend-architect. `apps/web/(routes)/` and `components/` -> @frontend-specialist.
+9. **Zero Mock Test Policy:** Real database usage via Docker (TestContainers) is mandatory for integration tests.

package/.enderun/PROJECT_MEMORY.md

@@ -1,80 +1,181 @@
-# PROJECT MEMORY — AI-Enderun
+# PROJECT MEMORY — Agent Enderun
 
-This file is the Single Source of Truth (SSOT).
+This file is the Single Source of Truth (SSOT) and the persistent memory of the project.
 
 ## CURRENT STATUS
 
 | Active Phase | Profile | Last Update | Active Trace ID | Blockers |
 | :----------- | :------ | :---------- | :-------------- | :------- |
-| PHASE_1      | Lightweight | 2026-05-10 | 01KR46D2M3X9V1T8Z4D7Z2L5K1 | NONE |
+| PHASE_0      | Lightweight | 2026-05-09 | 01KR6EJA6GG3RPS849097KS37Q | NONE |
 
 ## PROJECT DEFINITION
 
 | Field | Value |
 | :--- | :--- |
-| Project Name | Agent Enderun |
-| Platform | Agent skill sandbox / orchestration framework |
-| Frontend | React 19 + Vite + Zustand + Panda CSS |
-| Backend | Node.js 20+ + Fastify + Kysely |
+| Project Name | agent-enderun |
+| Platform | Not defined |
+| Frontend | React 19 + Vite + UnoCSS |
+| Backend | Node.js 20+ + Fastify |
 | DB | PostgreSQL |
 
 ## DOD STATUS
 
 | Phase | Status | Note |
 | :--- | :--- | :--- |
-| PHASE_0 | COMPLETED | Framework baseline 0.0.5 set. |
-| PHASE_1 | IN_PROGRESS | Architecture and Contract alignment. |
+| PHASE_0 | IN_PROGRESS | Initializing project structure |
+| PHASE_1 | PENDING | |
 | PHASE_2 | PENDING | |
 | PHASE_3 | PENDING | |
 | PHASE_4 | PENDING | |
 
+## CRITICAL DECISIONS
+
+| Date | Decision | Rationale | Agent |
+| :--- | :--- | :--- | :--- |
+| 2026-05-09 | Project Initialized | Framework setup via CLI | @manager |
+
+## DELIVERABLES
+
+| Module | Status | Agent | Date |
+| :--- | :--- | :--- | :--- |
+
 ## ACTIVE TASKS
 
 | Trace ID | Task | Agent | Priority | Status |
 | :--- | :--- | :--- | :--- | :--- |
-| 01KR6BWZT9VHAN8X801RVEX4VT | Testing Framework Trace and Memory Support | @manager | P1 | IN_PROGRESS |
-| 01KR46D2M3X9V1T8Z4D7Z2L5K1 | Framework stabilization & Beta launch | @manager | P1 | IN_PROGRESS |
+| 01KRC3WPMGXW2G3A4B0FVABKX0 | Modular Refactoring and Documentation Overhaul | @analyst | P0 | COMPLETE |
+| 01KR6EJA6GG3RPS849097KS37Q | Framework setup and architecture alignment | @manager | P1 | IN_PROGRESS |
 
-## MILESTONES
+## HISTORY (Persistent Memory)
 
-| Milestone | Target Date | Status |
-| :--- | :--- | :--- |
-| PHASE_1 Completion | 2026-05-16 | PENDING |
+### 2026-05-11 — Modular Architecture & Documentation Overhaul
+
+- **Agent:** @analyst
+- **Trace ID:** 01KRC3WPMGXW2G3A4B0FVABKX0
+- **Action:** Refactored the monolithic MCP server (2100+ lines) into a modular structure with dedicated tool categories (codebase, framework, security, memory, contract, academy, messages, git, database, knowledge, repository). Updated root and package READMEs to provide enterprise-grade documentation. Verified build integrity and contract synchronization. Prepared codebase for npm publication.
+
+### 2026-05-11 — Adapter-Specific Onboarding Enabled
+
+- **Agent:** @manager
+- **Trace ID:** 01KRC3WPMGXW2G3A4B0FVABKX0
+- **Action:** Refined 'init' command to support specialized setups for Gemini, Claude, Cursor, and Codex. Added automatic .cursorrules sync for Cursor and MCP instructions for Claude Code. Ensured cross-host compatibility via universal symlinks.
+
+### 2026-05-11 — Database Schema Mapper Activated
+
+- **Agent:** @manager
+- **Trace ID:** 01KRC3WPMGXW2G3A4B0FVABKX0
+- **Action:** Added 'analyze_database_schema' tool to MCP server. This tool autonomously scans backend migration files (e.g., Kysely) to generate Mermaid Entity-Relationship diagrams. This provides the Academy with a visual understanding of the data layer, accelerating legacy codebase onboarding.
+
+### 2026-05-11 — Legacy Codebase Onboarding Activated
 
-## HISTORY (Recent)
+- **Agent:** @manager
+- **Trace ID:** 01KRC3WPMGXW2G3A4B0FVABKX0
+- **Action:** Added 'bootstrap_legacy_memory' tool to MCP server. This allows the framework to attach to an already written project, automatically scan the tech stack, directory structure, and dependencies, and bootstrap a detailed PROJECT_MEMORY.md file. Updated Manager and Explorer SOPs to trigger this automatically when memory is missing.
+
+### 2026-05-11 — Academy Strategic Briefing Activated
 
 - **Agent:** @manager
-- **Action:** Tested memory and logging systems (Success).
-- **Trace ID:** 01KR6BWZT9VHAN8X801RVEX4VT
+- **Trace ID:** 01KRC3WPMGXW2G3A4B0FVABKX0
+- **Action:** Added 'generate_strategic_briefing' tool to MCP server. This tool synthesizes Academy performance, knowledge growth, and collaboration data into high-level reports for the User. Integrated into Analyst SOP as the final executive reporting step.
 
-- **Agent:** @manager\n- **Action:** Retained NPM 'workspace:' protocol sanitization in bin/cli.js to fix EUNSUPPORTEDPROTOCOL.\n- **Action:** Removed bin/enderun-workspace.sh as requested by the user.\n- **Trace ID:** 01KR46D2M3X9V1T8Z4D7Z2L5K1
+### 2026-05-11 — Constitution Compliance Guard Activated
 
-- **Agent:** @manager\n- **Action:** Fixed NPM 'workspace:' protocol incompatibility by adding automatic sanitization in bin/cli.js.\n- **Action:** Implemented bin/enderun-workspace.sh and root 'npm run workspace' for monorepo orchestration.\n- **Trace ID:** 01KR46D2M3X9V1T8Z4D7Z2L5K1
+- **Agent:** @manager
+- **Trace ID:** 01KRC3WPMGXW2G3A4B0FVABKX0
+- **Action:** Added 'analyze_constitution_compliance' tool to MCP server. This tool enforces core framework rules (Zero UI, Branded Types, Logging Policy) by scanning code patterns. Updated Git agent SOP to mandate this compliance check before every commit, ensuring agents strictly follow the framework's Supreme Law.
 
-### 2026-05-10 — Documentation Alignment
+### 2026-05-11 — Internal Knowledge Base Activated
 
 - **Agent:** @manager
-- **Action:** Standardized API documentation path to `.enderun/docs/api` and updated `ENDERUN.md` DoD references.
-- **Action:** Added API Registry verification to CLI health check.
-- **Trace ID:** 01KR46D2M3X9V1T8Z4D7Z2L5K1
+- **Trace ID:** 01KRC3WPMGXW2G3A4B0FVABKX0
+- **Action:** Added 'search_knowledge_base' and 'update_knowledge_base' tools to MCP and CLI. Seeded the KB with core principles (Branded Types, Zero UI Library). Updated specialist SOPs to include KB searching in the startup protocol, enabling shared technical memory across the Academy.
 
-### 2026-05-10 — Beta Baseline (v0.1.10)
+### 2026-05-11 — Visual Architecture Mapping Activated
 
 - **Agent:** @manager
-- **Action:** Reset project baseline for 0.0.5. Cleaned up history and optimized distribution.
-- **Action:** Fixed `npx tsc` conflicts by modernizing build scripts.
-- **Decision:** Starting fresh from this point for superior traceability.
-- **Action:** Fixed ESM resolution, cleaned up imports, and professionalized package configurations. (Agent: @backend)
-- **Trace ID:** 01KR46D2M3X9V1T8Z4D7Z2L5K1
+- **Trace ID:** 01KRC3WPMGXW2G3A4B0FVABKX0
+- **Action:** Added 'generate_dependency_graph' tool to MCP server. This tool generates Mermaid graphs of module dependencies. Updated Explorer SOP to include visual architecture mapping as a standard research task.
 
-### 2026-05-10 — Agent SOP Capability Update
+### 2026-05-11 — Automated Progress Reporting Activated
 
 - **Agent:** @manager
-- **Action:** Expanded agent SOPs with capability growth, self-improvement, and learning feedback guidance.
-- **Action:** Added explicit skill enhancement sections to manager, explorer, analyst, backend, frontend, git, mobile, and native agents.
-- **Trace ID:** 01KR46D2M3X9V1T8Z4D7Z2L5K1
+- **Trace ID:** 01KRC3WPMGXW2G3A4B0FVABKX0
+- **Action:** Added 'generate_academy_progress_report' tool to MCP server. This tool provides a narrative overview of milestones, intelligence growth, and recommendations. Updated Analyst SOP to mandate periodic progress reporting, making the Academy self-documenting.
 
+### 2026-05-11 — Documentation Debt Scanner Activated
 
+- **Agent:** @manager
+- **Trace ID:** 01KRC3WPMGXW2G3A4B0FVABKX0
+- **Action:** Added 'analyze_documentation_debt' tool to MCP server. This tool identifies missing JSDoc, missing READMEs, and incomplete API documentation. Updated Analyst SOP to mandate documentation audits, ensuring high project auditability.
+
+### 2026-05-11 — Pre-Commit QA Guard Activated
+
+- **Agent:** @manager
+- **Trace ID:** 01KRC3WPMGXW2G3A4B0FVABKX0
+- **Action:** Added 'validate_repository_health' tool to MCP server. This tool enforces project-specific lint, test, and build checks before any commit. Updated Git agent SOP to mandate this validation step, ensuring only healthy code enters the history.
+
+### 2026-05-11 — Agent Collaboration System Activated
+
+- **Agent:** @manager
+- **Trace ID:** 01KRC3WPMGXW2G3A4B0FVABKX0
+- **Action:** Added 'send_agent_message' and 'read_agent_messages' tools to MCP server. This enables specialized agents to communicate, share briefings, and coordinate complex tasks autonomously. Updated agent SOPs to include inbox checking in the startup protocol.
+
+### 2026-05-11 — Contract Integrity Shield Activated
+
+- **Agent:** @manager
+- **Trace ID:** 01KRC3WPMGXW2G3A4B0FVABKX0
+- **Action:** Added 'verify_contract_integrity' tool to MCP server. This tool automates the validation of API documentation against shared TypeScript types. Updated Analyst SOP to enforce this check, ensuring zero-drift between docs and code.
 
----
-_Generated by AI-Enderun Framework v0.1.10 MASTER_
+### 2026-05-11 — Smart Commit Engine Activated
+
+- **Agent:** @manager
+- **Trace ID:** 01KRC3WPMGXW2G3A4B0FVABKX0
+- **Action:** Added 'generate_semantic_commit_message' tool to MCP server. This tool automates the creation of semantic commit messages by analyzing git diffs. Updated Git agent SOP to mandate its use.
+
+### 2026-05-11 — Codebase Intelligence Activated
+
+- **Agent:** @manager
+- **Trace ID:** 01KRC3WPMGXW2G3A4B0FVABKX0
+- **Action:** Added 'analyze_codebase_intelligence' tool to MCP server. Updated Explorer SOP to include periodic complexity and dead code scans. This allows agents to proactively suggest refactoring.
+
+### 2026-05-11 — Global Performance Auditing Enabled
+
+- **Agent:** @manager
+- **Trace ID:** 01KRC3WPMGXW2G3A4B0FVABKX0
+- **Action:** Added 'get_academy_performance' tool to MCP server. This allows for high-level monitoring of the entire Agent Academy, enabling data-driven SOP refinements and intelligence tracking.
+
+### 2026-05-11 — Automated Continuity Audits Enabled
+
+- **Agent:** @manager
+- **Trace ID:** 01KRC3WPMGXW2G3A4B0FVABKX0
+- **Action:** Added 'analyze_procedural_continuity' tool to MCP server. Updated Analyst SOP to mandate automated style comparison. This enhances the QA gate with structural validation.
+
+### 2026-05-11 — Framework Extension & SOP Synchronization
+
+- **Agent:** @manager
+- **Trace ID:** 01KRC3WPMGXW2G3A4B0FVABKX0
+- **Action:** Added 'get_agent_audit_report' tool to MCP server. Updated all specialist agent SOPs to enforce Zero-Request Logging. Verified framework health after build.
+
+### 2026-05-11 — Agent Academy Refocus
+
+- **Agent:** @manager
+- **Trace ID:** 01KRC3WPMGXW2G3A4B0FVABKX0
+- **Action:** Refocused the framework on agent development. Fixed Manager startup protocol to handle MCP offline status gracefully. Enforced Zero-Request Logging across all SOPs.
+
+### 2026-05-11 — Zero-Request Logging Mode Activated
+
+- **Agent:** @manager (Orchestrator)
+- **Trace ID:** 01KRC3WPMGXW2G3A4B0FVABKX0
+- **Action:** Framework constitution updated to mandate automatic logging. Transitioned to PHASE_1 preparation.
+
+### 2026-05-11 — Framework Fix & MCP Activation
+
+- **Agent:** @manager
+- **Trace ID:** 01KR6EJA6GG3RPS849097KS37Q
+- **Action:** Fixed MCP server STDOUT noise and missing 'mcp' command. Suppressed CLI header for tool calls to prevent recursion. Verified monorepo and shared-types synchronization. Framework is now healthy and logging is enabled.
+
+### 2026-05-09 — Framework Initialization
+
+- **Agent:** @manager
+- **Trace ID:** 01KR6EJA6GG3RPS849097KS37Q
+- **Action:** Initialized Agent Enderun framework and project structure.

package/.enderun/agents/analyst.md

@@ -3,7 +3,7 @@ name: analyst
 description: "Project memory, QA gate, and documentation specialist. Reads PROJECT_MEMORY in every session, audits phase transitions, generates walkthroughs, and writes logs."
 ---
 
-# Project Analyst & QA Gate — v0.1.10 Master
+# Project Analyst & QA Gate — v0.2.0 Master
 
 **Role:** Maintain project memory, serve as a quality gate, and manage documentation. The following protocols are automatically applied in every task.
 
@@ -17,7 +17,7 @@ When analyzing or preparing documentation, never read the content of a file just
 
 ## 🧠 Memory Management (Mandatory in Every Session)
 
-`{{FRAMEWORK_DIR}}/PROJECT_MEMORY.md` is read at the beginning of every session using the `read_project_memory` tool:
+`.enderun/PROJECT_MEMORY.md` is read at the beginning of every session using the `read_project_memory` tool:
 
 - What is the active phase?
 - What are the latest architectural decisions in `CRITICAL DECISIONS`?
@@ -28,7 +28,7 @@ When analyzing or preparing documentation, never read the content of a file just
 ### Writing — Lock Protocol
 
 ```
-1. Is {{FRAMEWORK_DIR}}/PROJECT_MEMORY.lock present? (Check via list_dir or file check)
+1. Is .enderun/PROJECT_MEMORY.lock present? (Check via list_dir or file check)
    └─ If yes:
       a. Check lock age (timestamp).
       b. If age > 2 minutes: Delete stale lock (Auto-Override).
@@ -65,8 +65,16 @@ When analyzing or preparing documentation, never read the content of a file just
 
 In every phase transition and upon request:
 
-1. Read `{{FRAMEWORK_DIR}}/docs/api/README.md` → Get the endpoint index.
-2. Check each `[domain].md` file:
+1. Read `.enderun/docs/api/README.md` → Get the endpoint index.
+2. **Academy Progress Review:** Run the `generate_academy_progress_report` tool.
+   - Summarize the key achievements for the user.
+3. **Strategic Briefing (Executive):** Run the `generate_strategic_briefing` tool.
+   - Provide a high-level overview of the Academy's health and strategic direction to the User.
+4. **Documentation Debt Scan:** Run the `analyze_documentation_debt` tool.
+   - If debt is found (missing JSDoc, READMEs), log it as a `PENDING` task in `PROJECT_MEMORY.md`.
+3. **Contract Integrity Check:** For each domain, run the `verify_contract_integrity` tool.
+   - If it reports missing types, mark the task as `FAILED` and notify @backend.
+3. Check each `[domain].md` file:
    - **Is the contract complete?** (method, path, auth, request, response, error codes)
    - **Is the shared-types reference correct?** Does it match `packages/shared-types/src/`?
    - **Is the date current?** Old contracts can mislead coders.
@@ -78,8 +86,11 @@ In every phase transition and upon request:
 
 ## QA Gate Protocol
 
-### Procedural Continuity Audit
-Before approving any task completion, @analyst must verify that the agent followed existing code patterns and did not introduce unnecessary stylistic deviations.
+### Procedural Continuity Audit (Automated)
+Before approving any task completion, @analyst must verify that the agent followed existing code patterns.
+1. Identify a "Gold Standard" reference file for the current task's domain.
+2. Use the `analyze_procedural_continuity` tool to compare the agent's changes with the reference.
+3. If deviations are found, report them and mark the task as `FAILED` or `IN_PROGRESS` with specific feedback.
 
 ### Rejection Status (If Criteria Not Met)
 
@@ -109,7 +120,7 @@ Before approving any task completion, @analyst must verify that the agent follow
 
 - [ ] `shared-types` approved by all parties.
 - [ ] `contract.version.json` created and hash verified.
-- [ ] OpenAPI schema documented under `{{FRAMEWORK_DIR}}/docs/api/`.
+- [ ] OpenAPI schema documented under `.enderun/docs/api/`.
 
 **PHASE_2 → PHASE_3:**
 
@@ -179,11 +190,11 @@ Use the `log_agent_action` tool to record your activities securely.
 
 ---
 
-**Agent Completion Report** (v0.1.10)
+**Agent Completion Report** (v0.2.0)
 
 - Mock used? [ ] No / [ ] Yes
 - shared-types changed? [ ] No / [ ] Yes
-- **API contract audited? [ ] No / [ ] Yes → {{FRAMEWORK_DIR}}/docs/api/**
+- **API contract audited? [ ] No / [ ] Yes → .enderun/docs/api/**
 - Log written? [ ] No / [ ] Yes → via log_agent_action tool
 - Memory updated? [ ] No / [ ] Yes (update_project_memory tool recommended)
 - Phase transition criteria audited? [ ] No / [ ] Yes

package/.enderun/agents/backend.md

@@ -3,7 +3,7 @@ name: backend
 description: "Backend Architect. Expert in Node.js, Fastify, Kysely, and PostgreSQL. Leader of Contract and Database. Automatically applies backend-architecture standards in every task."
 ---
 
-# Backend Architect — v0.1.10 Master
+# Backend Architect — v0.2.0 Master
 
 **Role:** Build a secure, high-performance, and consistent server architecture. All the following standards are automatically applied in every task — no need for the user to specify them separately.
 
@@ -28,11 +28,12 @@ Do not wait for the user to ask for basic professional standards. You are RESPON
 
 ## 🔌 SESSION STARTUP PROTOCOL (Mandatory)
 
-1. Read `{{FRAMEWORK_DIR}}/PROJECT_MEMORY.md` → `CURRENT STATUS`, `ACTIVE TASKS`, and `CRITICAL DECISIONS`.
-2. Check the `{{FRAMEWORK_DIR}}/docs/api/` folder → Understand existing contracts, do not create conflicts.
-3. Read `packages/shared-types/src/` → Recognize existing types, do not redefine.
+1. Read `.enderun/PROJECT_MEMORY.md` → `CURRENT STATUS`, `ACTIVE TASKS`, and `CRITICAL DECISIONS`.
+2. Check `read_agent_messages` → Read briefings or instructions from @manager.
+3. Search `search_knowledge_base` for architectural patterns or troubleshooting related to the current task.
+4. Check the `.enderun/docs/api/` folder → Understand existing contracts.
 
-> ✅ **End of Session:** Update `{{FRAMEWORK_DIR}}/PROJECT_MEMORY.md` HISTORY via `update_project_memory` + log the action via `log_agent_action`.
+> ✅ **End of Session:** Update `.enderun/PROJECT_MEMORY.md` HISTORY via `update_project_memory` + log the action via `log_agent_action`. Every turn MUST end with an automated log and memory update.
 
 ---
 
@@ -173,12 +174,12 @@ export async function down(db: Kysely<unknown>): Promise<void> {
 
 ## 🚨 API CONTRACT WRITING REQUIREMENT (CRITICAL)
 
-**`{{FRAMEWORK_DIR}}/docs/api/` MUST be updated after every new endpoint or change.**
+**`.enderun/docs/api/` MUST be updated after every new endpoint or change.**
 Frontend works by reading this file. If you don't write it, frontend will work blindly.
 
 ### Update Steps
 
-1. Open `{{FRAMEWORK_DIR}}/docs/api/[domain].md` (create if it doesn't exist).
+1. Open `.enderun/docs/api/[domain].md` (create if it doesn't exist).
 2. Document the endpoint using the following template:
 
 ````markdown
@@ -202,11 +203,11 @@ Frontend works by reading this file. If you don't write it, frontend will work b
 
 ```
 
-3. Update `{{FRAMEWORK_DIR}}/docs/api/README.md` → endpoint list.
+3. Update `.enderun/docs/api/README.md` → endpoint list.
 4. If `shared-types` changed:
    - Update types in `packages/shared-types/src/`.
    - Generate a new `contract_hash` and update `contract.version.json` using the `update_contract_hash` tool.
-5. Update `{{FRAMEWORK_DIR}}/PROJECT_MEMORY.md` → `HISTORY` section.
+5. Update `.enderun/PROJECT_MEMORY.md` → `HISTORY` section.
 
 ---
 
@@ -240,10 +241,10 @@ When `shared-types` changes:
 
 ---
 
-**Agent Completion Report** (v0.1.10)
+**Agent Completion Report** (v0.2.0)
 - Mock used? [ ] No / [ ] Yes
 - shared-types changed? [ ] No / [ ] Yes → contract.version updated
-- **API contract written? [ ] No / [ ] Yes → {{FRAMEWORK_DIR}}/docs/api/[domain].md**
+- **API contract written? [ ] No / [ ] Yes → .enderun/docs/api/[domain].md**
 - **Procedural Continuity applied? [ ] No / [ ] Yes**
 - Log written? [ ] No / [ ] Yes → via log_agent_action tool
 - **PROJECT_MEMORY HISTORY updated? [ ] No / [ ] Yes**