agent-enderun 1.1.1 → 1.1.3

package/.enderun/knowledge/token_economy_and_memory.md

@@ -1,129 +0,0 @@
-# Token Economy & Agent Memory
-
-This document defines the operating rules for managing token consumption while preserving full agent capabilities and maintaining a usable, persistent memory across sessions.
-
-## Purpose
-
-- Reduce prompt cost and improve response speed by delivering only the relevant context to each agent.
-- Preserve a persistent project memory and per-agent private context so agents can recall prior actions and decisions without re-reading the entire codebase.
-- Keep all agents fully capable: do not shrink agent roles or rules to save tokens.
-- Use memory as a structured retrieval layer, not as a replacement for agent intelligence.
-
-## Key Principles
-
-### 1. Memory First, Not Memory Only
-
-- Agents must always start by checking the persistent project memory and agent context before taking action.
-- If the required information is already stored, the agent should use the stored summary instead of reading the full history or code again.
-- Memory retrieval reduces repeated context, but agents still keep their full capability set intact.
-
-### 2. Separate Persistent Memory from Live Context
-
-- `PROJECT_MEMORY.md` is the shared project brain: phase, active tasks, decisions, release tracking.
-- `memory-graph/shared-facts.json` is the shared facts store: tech stack, policy roster, contract location, active policies.
-- `memory-graph/agent-contexts/{agent}.json` is private context for each agent.
-- Use `get_agent_context` and `update_agent_context` for agent-specific memory.
-- Use `read_project_memory` and `get_memory_insights` for project-wide state.
-
-### 3. Keep Memory Summaries Short and Relevant
-
-- Store only the essence of what changed, why it changed, and what remains pending.
-- Do not duplicate entire logs or every code snippet.
-- For long histories, preserve the last 3–5 key decisions in active memory and archive older details in a separate file if needed.
-
-### 4. Use Tools, Not Manual Copying
-
-- The available tools are the only safe way to read or write memory:
-  - `read_project_memory`
-  - `update_project_memory`
-  - `get_agent_context`
-  - `update_agent_context`
-  - `get_memory_insights`
-  - `update_shared_facts`
-- Do not bypass them with raw file reads or writes.
-
-### 5. Token Economy Rules
-
-- Always `search_codebase` or `get_project_gaps` before reading large files.
-- Prefer summaries over raw content.
-- Only include the minimum relevant file snippets in prompts.
-- Do not resend the same context multiple times in one session.
-- Use `get_memory_insights` to extract the latest active tasks and decisions rather than reading the full `PROJECT_MEMORY.md` every time.
-
-## Memory and Token Flow
-
-### Session Startup
-
-1. `read_project_memory` to restore the active phase, trace, tasks, and history.
-2. `get_agent_context` for the current agent.
-3. `get_memory_insights` for a compact summary of recent activity.
-4. If the previous session is not fresh, use the agent context summary instead of reloading full histories.
-
-### During Work
-
-- When a user asks a question, first determine whether the answer depends on:
-  - current project status,
-  - active trace,
-  - recent decisions,
-  - per-agent execution state.
-- If yes, retrieve the appropriate memory object and include only the relevant summary.
-- If code context is needed, fetch only the directly impacted file or function.
-
-### End of Session
-
-- `update_project_memory` for `HISTORY` and `ACTIVE TASKS`.
-- `update_agent_context` with a short summary of the work performed and the current agent state.
-- Optionally `update_shared_facts` if the change affects shared policies, tech stack, or contract status.
-
-## Agent Context Format
-
-Agents should keep their private context small and specific.
-
-Example file: `.enderun/memory-graph/agent-contexts/manager.json`
-
-```json
-{
-  "lastSession": "2026-05-28T12:00:00Z",
-  "lastTraceId": "01H7G8K5TJ5S6MF9Z7H8N4C2P",
-  "recentDecisions": [
-    "Release 0.8.8 metadata synchronization",
-    "Do not reduce agent capability for token economy"
-  ],
-  "pendingReview": [
-    "Token economy memory protocol draft",
-    "Project phase transition strategy"
-  ],
-  "updatedAt": "2026-05-28T12:00:00Z"
-}
-```
-
-## Memory Usage Guidelines
-
-- `@manager`: stores strategic decisions, active task summaries, and phase transitions.
-- `@orchestrator`: stores DAG state, task dependencies, and agent handoff summaries.
-- `@analyst`: stores verification findings, rejected issues, and quality gate status.
-- `@frontend`, `@backend`, `@security`, `@qa`: store recent implementation context, verification outcomes, and compliance notes.
-
-## Avoiding Token Inefficiency
-
-- Do not send the whole `PROJECT_MEMORY.md` in every prompt.
-- Only include the relevant `ACTIVE TASKS`, `CRITICAL DECISIONS`, and the current trace if necessary.
-- Use `get_memory_insights` to get a compact summary rather than full data.
-- Avoid attaching full file contents unless the task requires precise code changes.
-
-## When to Archive History
-
-- If `PROJECT_MEMORY.md` history grows beyond 10 entries, move older entries into `.enderun/memory-graph/archive/`.
-- Keep the active history list focused on recent strategic changes and release-critical decisions.
-- The archive is still part of the project brain, but not part of every prompt.
-
-## Summary
-
-Token economy in Agent Enderun is not about limiting agent power.
-It is about using structured memory, summaries, and retrieval tools so every agent can remember prior work and still operate at full capability.
-
-- Keep agent rules intact.
-- Use `PROJECT_MEMORY.md` for shared state.
-- Use `agent-contexts` for private agent memory.
-- Use the memory tools to read and update memory.
-- Only include what is relevant in prompts.

package/.enderun/knowledge/zero_ui_library_policy.md

@@ -1,13 +0,0 @@
----
-title: Zero UI Library Policy
-tags: [design, security, compliance]
-related: [responsive_design_standards]
-last_updated: 2026-05-15
----
-
-The project strictly follows the Zero UI Library Policy. Importing external UI frameworks like shadcn/ui, MUI, or Chakra UI is forbidden. All styling must be implemented using Panda CSS to ensure zero-runtime overhead and complete control over the design system.
-
-## Rationale
-- **Performance:** Zero-runtime CSS extraction.
-- **Type Safety:** Type-safe styles and tokens.
-- **Originality:** Unique and premium aesthetics without "library look".

package/.enderun/logs/manager.json

@@ -1,48 +0,0 @@
-[
-  {
-    "timestamp": "2026-06-03T15:16:49.000Z",
-    "agent": "@manager",
-    "action": "project-inspection-report",
-    "requestId": "01HGT8J5E2N0W0W0W0W0W0W0W5",
-    "status": "SUCCESS",
-    "summary": "Inspected the entire framework structure, confirmed purpose of empty apps directory, and updated the project analysis report in docs.",
-    "findings": ["empty apps folder verified", "docs/project_analysis_report.md created", "AL state machine structure audited"]
-  },
-  {
-    "timestamp": "2026-06-03T15:17:49.000Z",
-    "agent": "@manager",
-    "action": "cli-ide-capability-audit",
-    "requestId": "01HGT8J5E2N0W0W0W0W0W0W0W5",
-    "status": "SUCCESS",
-    "summary": "Guided the user on CLI command usage, adapter execution, and IDE integration capabilities.",
-    "findings": ["CLI commands audited", "IDE adapter configurations checked", "cross-compatibility confirmed"]
-  },
-  {
-    "timestamp": "2026-06-03T15:20:21.000Z",
-    "agent": "@manager",
-    "action": "mcp-env-project-root-fix",
-    "requestId": "01HGT8J5E2N0W0W0W0W0W0W0W5",
-    "status": "SUCCESS",
-    "summary": "Identified and corrected a bug in MCP server entry generation where ENDERUN_PROJECT_ROOT was missing from the env block during init, resolving connection issues with external IDEs.",
-    "findings": ["fixed buildMcpServerEntry in adapters.ts to map absolute path in environment variables"]
-  },
-  {
-    "timestamp": "2026-06-03T15:23:06.000Z",
-    "agent": "@manager",
-    "action": "version-synchronization",
-    "requestId": "01HGT8J5E2N0W0W0W0W0W0W0W5",
-    "status": "SUCCESS",
-    "summary": "Synchronized framework package, source, config, and status versions to v1.1.0 to match the root package version.",
-    "findings": ["framework-mcp package version bumped", "framework-mcp source version bumped", "apps/web package version bumped", "enderun config version bumped", "STATUS.md version bumped"]
-  },
-  {
-    "timestamp": "2026-06-03T15:26:11.000Z",
-    "agent": "@manager",
-    "action": "init-adapter-scaffolding-fix",
-    "requestId": "01HGT8J5E2N0W0W0W0W0W0W0W5",
-    "status": "SUCCESS",
-    "summary": "Surgically updated initCommand to dynamically resolve the agent folder name (e.g. skills for antigravity, plugins for grok) when running scaffoldCoreAgents.",
-    "findings": ["dynamic resolution of agent directory implemented in init command to align scaffolding with configured adapter patterns"]
-  }
-]
-{"timestamp":"2026-06-03T15:36:38.637Z","agent":"@manager","action":"v1.1.1-release-synchronization","requestId":"01HGT8J5E2N0W0W0W0W0W0W0W5","status":"SUCCESS","summary":"Synchronized all package descriptors, source codes, configurations, dashboards, memory, and README files to release version 1.1.1.","findings":["root package.json bumped","mcp package and source bumped","apps/web package bumped","config.json and STATUS.md bumped","README.md all mentions updated","PROJECT_MEMORY.md updated"]}

package/.enderun/memory/BUSINESS_CONTEXT.md

@@ -1,17 +0,0 @@
-# 💼 Business Context & Domain Rules (BUSINESS_CONTEXT.md)
-
-This file defines the core business logic, domain vocabulary, and functional requirements of the project. It ensures agents understand the "Why" and the "Who" behind the code.
-
-## 🏗️ Domain Core
-- **Project Name:** Agent Enderun
-- **Target Audience:** Enterprise AI Teams, Autonomous Agent Developers.
-- **Primary Goal:** Provide a supreme governance layer for multi-agent software construction.
-
-## 📖 Glossary
-- **Trace ID:** A unique ULID assigned to every task for 100% traceability.
-- **Surgical Edit:** A precise change using the `replace` tool instead of file overwriting.
-- **Army:** The collection of 12 specialized agents managed by @manager.
-
-## ⚖️ Business Rules
-- **Contract-First:** No feature can be implemented until its API contract is verified in `contract.version.json`.
-- **Zero UI Library:** All UI must be built from scratch using Panda CSS to maintain full design sovereignty.

package/.enderun/memory/DECISIONS.md

@@ -1,24 +0,0 @@
-# 🧠 Architectural Decisions (DECISIONS.md)
-
-This log tracks every critical architectural decision made during the project. It ensures that agents (Commander, Architect, etc.) maintain consistency and do not repeat past discussions.
-
-## Decision Log Template
-- **ID:** AD-[YYYYMMDD]-[SEQ]
-- **Status:** [Proposed | Accepted | Superseded | Deprecated]
-- **Title:** Summary of the decision.
-- **Context:** Why was this decision necessary?
-- **Decision:** What was chosen?
-- **Consequences:** Impact on the project (positive/negative).
-- **Owner:** [Role: Architect | Commander]
-
----
-
-## 📜 Active Log
-
-### AD-20260531-001
-- **Status:** Accepted
-- **Title:** Enterprise Capability-Based Architecture (v2.0)
-- **Context:** Need for a model-agnostic, scalable orchestration system that works across multiple AI platforms (Gemini, Claude, Cursor, Grok).
-- **Decision:** Shift from model-tied roles to capability-based roles (Commander, Architect, Implementer, Researcher). Fragmented memory into specialized logs.
-- **Consequences:** Increased behavior consistency, better security through tool capability control, and long-term sustainability.
-- **Owner:** Commander

package/.enderun/memory/LESSONS_LEARNED.md

@@ -1,12 +0,0 @@
-# 💡 Lessons Learned & Anti-Patterns (LESSONS_LEARNED.md)
-
-This file tracks mistakes, hard-won insights, and critical anti-patterns discovered during the project life cycle. All agents MUST read this before proposing changes.
-
-## 🚫 Anti-Patterns (Never Do These)
-- **Blind Overwrites:** Never replace an entire file if `replace_text` can do a surgical edit.
-- **Mocking Without Permission:** Never use mock data in Phase 2+ unless explicitly approved for 3rd party services.
-- **Hardcoding IDs:** Never use plain strings for IDs. Use Branded Types.
-
-## 🎓 Lessons Learned
-- **2026-06-01:** Moving `.cursorrules` to `.cursor/rules/global.mdc` significantly improves Cursor's agentic behavior in modern environments.
-- **2026-06-01:** Centralizing governance in `.enderun/` while using root shim files is the most robust way to support 5+ AI platforms simultaneously.

package/.enderun/memory/PATTERNS.md

@@ -1,17 +0,0 @@
-# 📚 Architectural Patterns (PATTERNS.md)
-
-This library defines the approved architectural patterns and coding idioms for the project. Agents MUST use these patterns to ensure consistency.
-
-## 🏗️ Structural Patterns
-
-### 1. Repository Pattern
-- **Usage:** All database operations must be abstracted behind a Repository class.
-- **Rules:** No raw Kysely calls in Services. No business logic in Repositories.
-
-### 2. Branded Types (The Law)
-- **Usage:** Every ID must be branded.
-- **Example:** `type UserID = string & { readonly __brand: "UserID" }`
-
-### 3. Result Wrapper (Error Handling)
-- **Usage:** Async operations should return a `Result<T, E>` or use the standard `DomainError` hierarchy.
-- **Standard:** Use `try/catch` at the boundary, not everywhere.

package/.enderun/memory/PROJECT_MEMORY.md

@@ -1,31 +0,0 @@
-## CURRENT STATUS
-
-- Phase: PHASE_0 (Genesis)
-- Trace ID: 01HGT8J5E2N0W0W0W0W0W0W0W5
-- @manager state: ENTERPRISE_FULL_PROFILE_ACTIVE
-
-## ACTIVE TASKS
-
-| Trace ID | Task | Agent | Priority | Status |
-| :--- | :--- | :--- | :--- | :--- |
-
-## CRITICAL DECISIONS
-
-- **Tech Stack:** Node.js/Fastify, React/Vite, PostgreSQL, Kysely.
-- **Surgical Standard:** replace_text/patch_file is mandatory for all edits.
-- **Contract First:** All developments must start with type definitions.
-- **Memory Standard:** Auto-pruning active (max 10 entries).
-- **Sovereign Backend Structure:** Every backend service MUST maintain its own database logic (schema, migrations, seeds) within `src/database/` to ensure full isolation.
-
-## HISTORY
-
-- **Dynamic Scaffold Path Resolution Fix (v1.1.1):** Updated `initCommand` in `src/cli/commands/init.ts` to dynamically map the target folder name for `scaffoldCoreAgents` (e.g., `skills` for `antigravity`, `plugins` for `grok`). This prevents folder clutter by keeping agent profiles inside the adapter's expected subdirectories. (Trace 01HGT8J5E2N0W0W0W0W0W0W0W5)
-- **Monorepo Version Synchronization (v1.1.1):** Synchronized framework configurations, server code, status boards, and package descriptors across all workspace packages (`framework-mcp`, `apps/web`, `.enderun/config.json`, and `.enderun/STATUS.md`) to align with the root version `1.1.1`. (Trace 01HGT8J5E2N0W0W0W0W0W0W0W5)
-- **MCP Project Root Configuration Fix (v1.1.1):** Surgically updated `buildMcpServerEntry` in `src/cli/adapters.ts` to include the absolute `ENDERUN_PROJECT_ROOT` environment variable in the generated configurations during `init`, resolving relative path mismatches for external AI runtimes. (Trace 01HGT8J5E2N0W0W0W0W0W0W0W5)
-- **CLI & IDE Capability Audit (v1.1.1):** Audited and documented CLI execution capabilities and IDE adapter mappings (Gemini/Antigravity, Cursor, Claude Code, Grok). Verified cross-compatibility for developer and autonomous agent interaction. (Trace 01HGT8J5E2N0W0W0W0W0W0W0W5)
-- **Framework Inspection & Analysis (v1.1.1):** Inspected the framework structure, custom agent army settings, Hermes messaging loop, and MCP server. Verified that the `apps` directory is intentionally kept empty of business code to act as a clean canvas for enterprise projects. Created and documented findings in `docs/project_analysis_report.md`. (Trace 01HGT8J5E2N0W0W0W0W0W0W0W5)
-- **AL NPM Consumption Fix (v1.0.7+):** Root cause of 'kuraları npm den' AL validation FAILED (the exact error: 'Run manually: node bin/validate-agent-army.js' after init with remap adapters like antigravity) was execSync("node bin/...") assuming source cwd. Fixed by adding robust getPackageRoot() + getValidatorPath() in pkg.ts (walks import.meta.url to locate the agent-enderun package's bin/ regardless of install location or cwd). Updated check.ts, init.ts, index.ts to use resolved path + cwd-respecting exec. Updated error suggestions to `agent-enderun validate`. Reproduced with real npm pack + tgz install into isolated tests/init-adapters/.../consume/, ran installed CLI init+check+validate for antigravity remap case: now ✅ "Agent Army AL validation PASSED" (no FAILED branch). Source validate still 12/12. Docs/README surgically updated. Meets surgical + Trace + every-turn memory. (Trace 01HGT8J5E2N0W0W0W0W0W0W0W5)
-- **Enterprise v1.0.6 Sürüm Revizyonu:** Mimari Enterprise 2.1 (Yetenek Tabanlı) olarak korundu, marka ismi `Agent Enderun Enterprise v1` olarak güncellendi ve tüm paket sürümleri `1.0.6` olarak mühürlendi.
-- **Agent Lifecycle (AL) Tam Entegrasyon:** Tüm agent `.md` tanımları `stateMachine` ve `tags` alanları ile AL şemasına uygun hale getirildi. `bin/validate-agent-army.js` aracı bu yeni alanları denetleyecek şekilde güncellendi ve tüm ordu (12 agent) %100 başarıyla doğrulandı. CLI orkestrasyon mantığı AL durum geçişlerini (BRIEFED, EXECUTING, BLOCKED) destekleyecek şekilde zenginleştirildi.
-- **Monorepo Sürüm Senkronizasyonu:** Tüm monorepo paketlerinin (`@agent-enderun/mcp`, `@agent-enderun/backend`, `@agent-enderun/web`) sürümleri ana sürüm olan `1.0.5` ile senkronize edildi.
-- **Kalite Kapısı Kontrolleri:** ESLint otomatik kod formatlama ve hizalama düzeltmeleri uygulandı, TS derleme build'i sıfır hata ile tamamlandı ve vitest birim testlerinin tümü (%100 başarı) başarıyla geçti.

package/.enderun/memory-graph/agent-contexts/analyst.json

@@ -1 +0,0 @@
-{"agent": "analyst", "version": "1.0.0", "lastUpdated": "2026-05-31T14:20:00Z", "sessionHistory": [], "notes": "Initial clean state."}

package/.enderun/memory-graph/agent-contexts/backend.json

@@ -1 +0,0 @@
-{"agent": "backend", "version": "1.0.0", "lastUpdated": "2026-05-29T15:41:37Z", "sessionHistory": [], "notes": "Initial clean state."}

package/.enderun/memory-graph/agent-contexts/devops.json

@@ -1 +0,0 @@
-{"agent": "devops", "version": "1.0.0", "lastUpdated": "2026-05-29T15:41:37Z", "sessionHistory": [], "notes": "Initial clean state."}

package/.enderun/memory-graph/agent-contexts/explorer.json

@@ -1 +0,0 @@
-{"agent": "explorer", "version": "1.0.0", "lastUpdated": "2026-05-29T15:41:37Z", "sessionHistory": [], "notes": "Initial clean state."}

package/.enderun/memory-graph/agent-contexts/frontend.json

@@ -1 +0,0 @@
-{"agent": "frontend", "version": "1.0.0", "lastUpdated": "2026-05-29T15:41:37Z", "sessionHistory": [], "notes": "Initial clean state."}

package/.enderun/memory-graph/agent-contexts/git.json

@@ -1 +0,0 @@
-{"agent": "git", "version": "1.0.0", "lastUpdated": "2026-05-29T15:41:37Z", "sessionHistory": [], "notes": "Initial clean state."}

package/.enderun/memory-graph/agent-contexts/manager.json

@@ -1 +0,0 @@
-{"agent": "manager", "version": "1.0.0", "lastUpdated": "2026-05-29T15:41:37Z", "sessionHistory": [], "notes": "Initial clean state."}

package/.enderun/memory-graph/agent-contexts/mobile.json

@@ -1 +0,0 @@
-{"agent": "mobile", "version": "1.0.0", "lastUpdated": "2026-05-29T15:41:37Z", "sessionHistory": [], "notes": "Initial clean state."}

package/.enderun/memory-graph/agent-contexts/native.json

@@ -1 +0,0 @@
-{"agent": "native", "version": "1.0.0", "lastUpdated": "2026-05-29T15:41:37Z", "sessionHistory": [], "notes": "Initial clean state."}

package/.enderun/memory-graph/agent-contexts/quality.json

@@ -1 +0,0 @@
-{"agent": "quality", "version": "1.0.0", "lastUpdated": "2026-05-29T15:41:37Z", "sessionHistory": [], "notes": "Merged from analyst, qa, and security agents."}

package/.enderun/memory-graph/agent-contexts/security.json

@@ -1 +0,0 @@
-{"agent": "security", "version": "1.0.0", "lastUpdated": "2026-05-31T14:20:00Z", "sessionHistory": [], "notes": "Initial clean state."}

package/.enderun/memory-graph/graph.json

@@ -1,133 +0,0 @@
-{
-  "version": "1.0.0",
-  "description": "Agent Enderun Army Memory Graph. Tracks all agent interactions, delegations, and communication edges across the entire army.",
-  "generatedAt": "2026-05-25T17:00:00Z",
-  "updatedAt": "2026-05-25T17:00:00Z",
-  "nodes": [
-    {
-      "id": "@manager",
-      "state": "IDLE",
-      "lastAction": "Framework initialized",
-      "activeTrace": null,
-      "healthScore": 9.5,
-      "totalActionsThisSession": 0
-    },
-    {
-      "id": "@orchestrator",
-      "state": "IDLE",
-      "lastAction": null,
-      "activeTrace": null,
-      "healthScore": 9.8,
-      "totalActionsThisSession": 0
-    },
-    {
-      "id": "@backend",
-      "state": "IDLE",
-      "lastAction": null,
-      "activeTrace": null,
-      "healthScore": 9.2,
-      "totalActionsThisSession": 0
-    },
-    {
-      "id": "@frontend",
-      "state": "IDLE",
-      "lastAction": null,
-      "activeTrace": null,
-      "healthScore": 9,
-      "totalActionsThisSession": 0
-    },
-    {
-      "id": "@security",
-      "state": "IDLE",
-      "lastAction": null,
-      "activeTrace": null,
-      "healthScore": 9.3,
-      "totalActionsThisSession": 0
-    },
-    {
-      "id": "@qa",
-      "state": "IDLE",
-      "lastAction": null,
-      "activeTrace": null,
-      "healthScore": 9.1,
-      "totalActionsThisSession": 0
-    },
-    {
-      "id": "@devops",
-      "state": "IDLE",
-      "lastAction": null,
-      "activeTrace": null,
-      "healthScore": 9,
-      "totalActionsThisSession": 0
-    },
-    {
-      "id": "@analyst",
-      "state": "IDLE",
-      "lastAction": null,
-      "activeTrace": null,
-      "healthScore": 9.6,
-      "totalActionsThisSession": 0
-    },
-    {
-      "id": "@explorer",
-      "state": "IDLE",
-      "lastAction": null,
-      "activeTrace": null,
-      "healthScore": 9.4,
-      "totalActionsThisSession": 0
-    },
-    {
-      "id": "@git",
-      "state": "IDLE",
-      "lastAction": null,
-      "activeTrace": null,
-      "healthScore": 9.1,
-      "totalActionsThisSession": 0
-    },
-    {
-      "id": "@mobile",
-      "state": "IDLE",
-      "lastAction": null,
-      "activeTrace": null,
-      "healthScore": 8.8,
-      "totalActionsThisSession": 0
-    },
-    {
-      "id": "@native",
-      "state": "IDLE",
-      "lastAction": null,
-      "activeTrace": null,
-      "healthScore": 8.9,
-      "totalActionsThisSession": 0
-    }
-  ],
-  "edges": [],
-  "schema": {
-    "nodeFields": [
-      "id",
-      "state",
-      "lastAction",
-      "activeTrace",
-      "healthScore",
-      "totalActionsThisSession"
-    ],
-    "edgeFields": [
-      "id",
-      "from",
-      "to",
-      "type",
-      "traceId",
-      "timestamp",
-      "metadata"
-    ],
-    "edgeTypes": [
-      "DELEGATED",
-      "ESCALATED",
-      "BLOCKED_BY",
-      "UNBLOCKED_BY",
-      "BROADCAST",
-      "COLLABORATED",
-      "REVIEWED"
-    ]
-  }
-}

package/.enderun/memory-graph/shared-facts.json

@@ -1,46 +0,0 @@
-{
-  "version": "1.0.0",
-  "description": "Shared facts available to ALL agents in the Enderun Army. This is the single source of truth for project-wide knowledge that every agent must know.",
-  "updatedAt": "2026-05-29T15:00:00Z",
-  "updatedBy": "@manager",
-  "techStack": {
-    "backend": "Node.js 22+ + Fastify (RCSR Architecture)",
-    "frontend": "React 19 + Vite + Panda CSS",
-    "database": "PostgreSQL (Multi-Tenant RLS + PostGIS)",
-    "orm": "Kysely",
-    "testing": "Vitest",
-    "typeSystem": "TypeScript 6 (strict mode, no any, branded types)",
-    "monorepo": "npm workspaces",
-    "cicd": "GitHub Actions"
-  },
-  "criticalDecisions": [
-    {
-      "date": "2026-05-29",
-      "decision": "Grand Governance Audit Completed",
-      "rationale": "Restored CLI, updated paths to .enderun/, and enforced autonomous MCP tools.",
-      "decidedBy": "@manager"
-    },
-    {
-      "date": "2026-05-29",
-      "decision": "Cursor IDE Deprecation",
-      "rationale": "Claude Code selected as primary operational surgery tool.",
-      "decidedBy": "@manager"
-    },
-    {
-      "date": "2026-05-21",
-      "decision": "Zero Mock Policy",
-      "rationale": "All analytical UIs connected to real APIs",
-      "decidedBy": "@manager"
-    }
-  ],
-  "activePolicies": [
-    "Zero Mock Policy — no fake data anywhere in the codebase",
-    "Branded Types Law — all IDs must use branded types",
-    "Surgical Edit Standard — use replace_text via MCP",
-    "Autonomous Growth — agents authorized to use create_app",
-    "Hermes Messaging Protocol — mandatory for inter-agent traffic",
-    "Audit Log Mandatory — every agent action must be logged"
-  ],
-  "frameworkVersion": "1.0.0",
-  "constitutionFile": "ENDERUN.md"
-}

package/.enderun/observability/AUDIT_LOG.md

@@ -1,9 +0,0 @@
-# 🛡️ Audit Log (AUDIT_LOG.md)
-
-This log tracks all high-risk and state-mutating actions performed by agents. It ensures accountability and provides a clear history for compliance audits.
-
-## 📜 High-Risk Action Log
-
-| Timestamp | Trace ID | Agent | Action | Result | Approved By |
-| :--- | :--- | :--- | :--- | :--- | :--- |
-| 2026-06-01T04:15:00Z | GENESIS-001 | @manager | System Initialization | SUCCESS | User |

package/.enderun/observability/METRICS.md

@@ -1,10 +0,0 @@
-# 📊 Performance Metrics (METRICS.md)
-
-This file tracks the efficiency and reliability of the Agent Army.
-
-| Metric | Goal | Current | Status |
-| :--- | :--- | :--- | :--- |
-| **Task Success Rate** | >95% | 100% | 🟢 |
-| **Avg. Tools per Task** | <10 | 4.2 | 🟢 |
-| **Retry Rate** | <5% | 0% | 🟢 |
-| **Governance Compliance** | 100% | 100% | ✅ |

package/.enderun/observability/README.md

@@ -1,19 +0,0 @@
-# Observability Placeholders
-
-**📌 Low-Usage / Future Reference Structure**
-
-This directory contains template files for enterprise-grade observability:
-
-- `AUDIT_LOG.md` — High-risk action audit trail (who, when, approval).
-- `TRACE_LOG.md` — Trace ID interaction visualization.
-- `METRICS.md` — Performance, token, efficiency metrics.
-
-Per `token_economy_and_memory.md` and corporate governance:
-- These are **structural placeholders** created during init for regulated/corporate projects.
-- Currently low-usage: no active population in core MCP tools or CLI (as of v1.0.9).
-- Intended for future implementation via `@manager` / `@quality` / Hermes flows (see `high-risk-action-approval-flow.md`, `audit-logging-standard.md`).
-- Load only when building audit/compliance features.
-
-Do not delete — part of the full 12-agent army capability for complex kurumsal projects.
-
-See `.enderun/queue/` and `docs/architecture/approval-flows.md` for related protocol.

package/.enderun/observability/TRACE_LOG.md

@@ -1,10 +0,0 @@
-# 📡 Trace Log (TRACE_LOG.md)
-
-This log tracks the flow of tasks between agents across different Trace IDs. It provides a technical timeline of how an intent was fulfilled.
-
-## 🛤️ Active Trace Streams
-
-### Trace ID: GENESIS-001
-- **04:15:00:** [COMMANDER] Initiated Enterprise 2.1 Upgrade.
-- **04:15:10:** [ROUTER] Assigned 'Observability Setup' to System Specialist.
-- **04:15:30:** [IMPLEMENTER] Created `.enderun/observability/` structure.

package/.enderun/queue/README.md

@@ -1,36 +0,0 @@
-# .enderun/queue — Agent Task Queue
-
-This directory contains the file-based asynchronous task queue for the Agent Enderun Army.
-
-## Alt Directoryler
-
-| Directory | Content |
-|---|---|
-| `pending/` | Assigned but not yet started tasks (`{traceId}.json`) |
-| `processing/` | Tasks currently being executed |
-| `completed/` | Successfully completed tasks (archive) |
-| `failed/` | Failed tasks (managed by retry logic) |
-| `pipelines/` | `create_execution_pipeline` MCP tool pipeline JSON files generated by |
-
-## Task File Format
-
-```json
-{
-  "id": "T001",
-  "traceId": "ENR-ARMY-001",
-  "assignedAgent": "@backend",
-  "priority": "HIGH",
-  "briefing": "...",
-  "createdAt": "ISO-8601",
-  "deadline": "ISO-8601",
-  "retryCount": 0,
-  "maxRetries": 3,
-  "status": "PENDING | RUNNING | COMPLETED | FAILED"
-}
-```
-
-## Locking Protocol
-
-Before writing to a file `.lock` check the
-Varsa 500ms bekle, max 3 retry.
-After 3 retries, it is considered a stale lock and reported to @manager.