agent-enderun 1.1.0 → 1.1.2

package/.enderun/ENDERUN.md

@@ -1,4 +1,4 @@
-# Agent Enderun Enterprise v1 (v1.0.9)
+# Agent Enderun Enterprise v1 (v1.1.1)
 # Place in project root. This file is the single source of truth for Base Project AI Extensions.
 
 ## 🎖️ AGENT CHECKLIST (MANDATORY BEFORE RESPONSE)

package/.enderun/STATUS.md

@@ -1,5 +1,5 @@
 # 🏛️ AGENT ENDERUN — ARMY COMMAND DASHBOARD
-> v1.0.9 | Clean Release (low-usage items marked as reference) | Memory Graph: Online | Bloat Removed (KENTİM + SYSTEM_MAP)
+> v1.1.2 | Clean Release (low-usage items marked as reference) | Memory Graph: Online | Bloat Removed (KENTİM + SYSTEM_MAP)
 
 **Nihai Sürüm Notu:** Proje düşük kullanımlı referans materyalleri (bazı knowledge dosyaları, demo scriptler, observability placeholders) ile düzenlendi. Yapısal boş dizinler ve reference-only dosyalar kasıtlı olarak korundu (token economy + full army capability için). Karmaşık kurumsal projeler için hazır (corporate-governance SOP'ları ile).
 ## 🤖 Agent Status
@@ -25,7 +25,7 @@
 
 | Metric | Value |
 | :--- | :--- |
-| **Framework Version** | v1.0.9 (Final Clean) |
+| **Framework Version** | v1.1.2 (Final Clean) |
 | **System Health** | 🟢 GREEN (Build & Contract Validated) |
 | **Major Governance Audit** | COMPLETED |
 | **Active Tasks** | 0 (All Genesis Issues Resolved) |

package/.enderun/agents/analyst.json

@@ -2,6 +2,8 @@
   "name": "analyst",
   "displayName": "Contract Verification & Business Analyst",
   "description": "Validates business specifications, tests database contract integrity, and audits constitutional compliance.",
+  "role": "Contract Verification & Business Analyst",
+  "capability": 9,
   "hidden": false,
   "stateMachine": {
     "schemaRef": "../schema/agent-lifecycle-schema.json"
@@ -26,7 +28,5 @@
         "list_dir"
       ]
     }
-  },
-  "role": "Contract Verification",
-  "capability": 9
-}
+  }
+}

package/.enderun/agents/backend.json

@@ -2,6 +2,8 @@
   "name": "backend",
   "displayName": "Domain Logic & Databases Specialist",
   "description": "Responsible for core business logic, database migrations, security standards, API contracts, and server architecture.",
+  "role": "Domain Logic & Databases Specialist",
+  "capability": 9,
   "hidden": false,
   "stateMachine": {
     "schemaRef": "../schema/agent-lifecycle-schema.json"
@@ -26,7 +28,5 @@
         "list_dir"
       ]
     }
-  },
-  "role": "Domain Logic & Databases",
-  "capability": 9
-}
+  }
+}

package/.enderun/agents/database.json

@@ -2,6 +2,8 @@
   "name": "database",
   "displayName": "Database Migrations & Tuning Specialist",
   "description": "Designs SQL schemas, manages migration scripts via Kysely, optimizes queries, indexes, and seeding logic.",
+  "role": "Database Migrations & Tuning Specialist",
+  "capability": 9,
   "hidden": false,
   "stateMachine": {
     "schemaRef": "../schema/agent-lifecycle-schema.json"
@@ -26,7 +28,5 @@
         "list_dir"
       ]
     }
-  },
-  "role": "Database Migrations & Tuning",
-  "capability": 9
-}
+  }
+}

package/.enderun/agents/devops.json

@@ -2,6 +2,8 @@
   "name": "devops",
   "displayName": "Infrastructure & CI/CD Specialist",
   "description": "Handles deployment pipelines, environment variables, system containerization, logging & telemetry integrations.",
+  "role": "Infrastructure & CI/CD Specialist",
+  "capability": 9,
   "hidden": false,
   "stateMachine": {
     "schemaRef": "../schema/agent-lifecycle-schema.json"
@@ -26,7 +28,5 @@
         "list_dir"
       ]
     }
-  },
-  "role": "Infrastructure & CI/CD",
-  "capability": 9
-}
+  }
+}

package/.enderun/agents/explorer.json

@@ -2,6 +2,8 @@
   "name": "explorer",
   "displayName": "Codebase Discovery Specialist",
   "description": "Maps code dependencies, performs project scans, identifies architectural gaps, and supports legacy onboarding.",
+  "role": "Codebase Discovery Specialist",
+  "capability": 9,
   "hidden": false,
   "stateMachine": {
     "schemaRef": "../schema/agent-lifecycle-schema.json"
@@ -26,7 +28,5 @@
         "list_dir"
       ]
     }
-  },
-  "role": "Codebase Discovery",
-  "capability": 9
-}
+  }
+}

package/.enderun/agents/frontend.json

@@ -2,6 +2,8 @@
   "name": "frontend",
   "displayName": "Fluid Responsive UI Specialist",
   "description": "Builds responsive fluid user interfaces, manages styling tokens with Panda CSS, and implements state machines.",
+  "role": "Fluid Responsive UI Specialist",
+  "capability": 9,
   "hidden": false,
   "stateMachine": {
     "schemaRef": "../schema/agent-lifecycle-schema.json"
@@ -26,7 +28,5 @@
         "list_dir"
       ]
     }
-  },
-  "role": "Fluid Responsive UI",
-  "capability": 9
-}
+  }
+}

package/.enderun/agents/git.json

@@ -2,6 +2,8 @@
   "name": "git",
   "displayName": "Version Control Specialist",
   "description": "Manages commit histories, branches, Trace ID alignment, semantic tagging, and merge conflicts.",
+  "role": "Version Control Specialist",
+  "capability": 9,
   "hidden": false,
   "stateMachine": {
     "schemaRef": "../schema/agent-lifecycle-schema.json"
@@ -26,7 +28,5 @@
         "list_dir"
       ]
     }
-  },
-  "role": "Version Control",
-  "capability": 9
-}
+  }
+}

package/.enderun/agents/manager.json

@@ -3,7 +3,7 @@
   "displayName": "Orchestration & Governance (Team-Lead)",
   "description": "CTO, Lead Architect, and Orchestrator for Agent Enderun.",
   "role": "Orchestration & Governance",
-  "capability": 10,
+  "capability": 9,
   "hidden": false,
   "stateMachine": {
     "schemaRef": "../schema/agent-lifecycle-schema.json"
@@ -16,7 +16,7 @@
       "systemPromptSections": [
         {
           "title": "Instructions",
-          "content": "You are the @manager agent, the Supreme Commander and Central Orchestrator of the Agent Enderun Army. Your primary responsibility is to receive user requests, analyze intent, and coordinate specialized agents (@backend, @frontend, @database, etc.) to fulfill the project's goals.\n\n🛑 CENTRAL COORDINATION RULES:\n- **Single Point of Entry:** Every request must be processed by you. You are the Router and Decision Maker.\n- **Multi-Agent Coordination:** You do not perform implementation tasks yourself. You DELEGATE them to the appropriate specialist agents using the `send_agent_message` tool or guiding the user via CLI @-mentions.\n- **Orchestration Loop:** After delegating, you MUST trigger `orchestrate_loop` to sync the state machine and update `STATUS.md`.\n- **Governance:** You enforce architectural standards and ensure all specialists follow the Supreme Law (ENDERUN.md).\n- **Memory & Traceability:** Every action MUST inherit the active Trace ID and be logged in PROJECT_MEMORY.md."
+          "content": "You are the manager agent. Orchestrate workspace tasks, manage DAG dependency graphs, handle phase transitions, and enforce architectural standards.\n\n🛑 NON-NEGOTIABLE CORE RULES:\n- Single Point of Authority: You are the sole entry point. No specialist acts without your briefing.\n- Traceability: Every action MUST inherit the active Trace ID.\n- Memory Discipline: MUST update PROJECT_MEMORY.md and log actions at the end of EVERY turn."
         }
       ],
       "toolNames": [
@@ -25,10 +25,8 @@
         "write_to_file",
         "run_command",
         "grep_search",
-        "list_dir",
-        "send_agent_message",
-        "orchestrate_loop"
+        "list_dir"
       ]
     }
   }
-}
+}

package/.enderun/agents/mobile.json

@@ -2,6 +2,8 @@
   "name": "mobile",
   "displayName": "Mobile App Specialist",
   "description": "Develops cross-platform mobile apps using React Native and Expo with clean component states.",
+  "role": "Mobile App Specialist",
+  "capability": 9,
   "hidden": false,
   "stateMachine": {
     "schemaRef": "../schema/agent-lifecycle-schema.json"
@@ -26,7 +28,5 @@
         "list_dir"
       ]
     }
-  },
-  "role": "Mobile App",
-  "capability": 9
-}
+  }
+}

package/.enderun/agents/native.json

@@ -2,6 +2,8 @@
   "name": "native",
   "displayName": "Native OS Integration Specialist",
   "description": "Builds lightweight desktop wrappers and system integrations using Tauri or Electron.",
+  "role": "Native OS Integration Specialist",
+  "capability": 9,
   "hidden": false,
   "stateMachine": {
     "schemaRef": "../schema/agent-lifecycle-schema.json"
@@ -26,7 +28,5 @@
         "list_dir"
       ]
     }
-  },
-  "role": "Native OS Integration",
-  "capability": 9
-}
+  }
+}

package/.enderun/agents/quality.json

@@ -2,6 +2,8 @@
   "name": "quality",
   "displayName": "Automated Testing & Quality Specialist",
   "description": "Verifies test coverage, audits compliance with the constitution, conducts AST scanning, and verifies CI/CD status.",
+  "role": "Automated Testing & Quality Specialist",
+  "capability": 9,
   "hidden": false,
   "stateMachine": {
     "schemaRef": "../schema/agent-lifecycle-schema.json"
@@ -26,7 +28,5 @@
         "list_dir"
       ]
     }
-  },
-  "role": "Automated Testing & Quality",
-  "capability": 9
-}
+  }
+}

package/.enderun/agents/security.json

@@ -2,6 +2,8 @@
   "name": "security",
   "displayName": "Security & Cryptography Specialist",
   "description": "Enforces authentication flows, CSP policies, credential rotation, RLS constraints, and cryptographic safety.",
+  "role": "Security & Cryptography Specialist",
+  "capability": 9,
   "hidden": false,
   "stateMachine": {
     "schemaRef": "../schema/agent-lifecycle-schema.json"
@@ -26,7 +28,5 @@
         "list_dir"
       ]
     }
-  },
-  "role": "Security & Cryptography",
-  "capability": 9
-}
+  }
+}

package/.enderun/config.json

@@ -2,11 +2,12 @@
   "logLevel": "info",
   "outputFormat": "text",
   "defaultProfile": "Lightweight",
-  "version": "1.0.9",
+  "version": "1.1.2",
   "paths": {
     "backend": "apps/backend",
     "frontend": "apps/web",
     "docs": "docs",
     "tests": "tests"
-  }
+  },
+  "_comment": "paths.backend and paths.frontend define WHERE apps will be scaffolded via create-app"
 }

package/.enderun/logs/manager.json

@@ -1,73 +1,52 @@
 [
   {
-    "timestamp": "2026-06-02T17:12:00.827Z",
+    "timestamp": "2026-06-03T15:16:49.000Z",
     "agent": "@manager",
-    "action": "readme-version-clean-structure-audit-token-brief",
+    "action": "project-inspection-report",
     "requestId": "01HGT8J5E2N0W0W0W0W0W0W0W5",
     "status": "SUCCESS",
-    "summary": "Removed detailed old version release notes ('Sürüm vX Devrimsel' + 'Key Improvements vX' blocks) from README via surgical MCP replaces. Kept bilingual TR/EN mold, updated to v1.0.7 current note. Full audit: all .enderun subfolders/structures (agents, knowledge, memory-graph, queue, skills, registry, benchmarks, observability etc.) + docs/apps/bin/framework-mcp used correctly (init scaffolds + check validates + CLI refs). Language: internals ENG, bilingual only user-facing. Token economy: followed rules (prune, MCP memory, search-first), briefed user per doc. Memory updated + this log. All per ENDERUN surgical + every-turn + token economy.",
-    "findings": [
-      "README clean of verbose version history",
-      "structures 100% accounted and used",
-      "ENG for core confirmed",
-      "token info delivered from knowledge/token_economy_and_memory.md"
-    ]
+    "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": "2026-06-02T17:14:51.594Z",
+    "timestamp": "2026-06-03T15:17:49.000Z",
     "agent": "@manager",
-    "action": "unused-files-audit",
+    "action": "cli-ide-capability-audit",
     "requestId": "01HGT8J5E2N0W0W0W0W0W0W0W5",
     "status": "SUCCESS",
-    "summary": "Performed deep audit for unused/underused files as user follow-up query. Found SYSTEM_MAP.md dead, several empty .enderun/ placeholder dirs (benchmarks, monitoring, messages, tests), the entire KENTİM docs example set only self-referential + bloating inits, observability logs unimplemented, a few low-use knowledge files, and two bin/ debug scripts. Contrasted with actively used structures (queue, registry, skills, memory-graph, all 12 agents, core knowledge via agent refs). Updated HISTORY. No edits performed (report only). All surgical, token-economy compliant (greps + targeted lists).",
-    "findings": [
-      "SYSTEM_MAP.md (0 refs)",
-      "empty dirs (scaffold only)",
-      "KENTİM docs set (self-contained bloat)",
-      "observability (doc only)",
-      "bin/hermes-sandbox + init-check (dead). Core army + .enderun/ design is solid and used."
-    ]
+    "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": "2026-06-02T17:18:37.096Z",
+    "timestamp": "2026-06-03T15:20:21.000Z",
     "agent": "@manager",
-    "action": "cleanup-kentim-docs-bloat",
+    "action": "mcp-env-project-root-fix",
     "requestId": "01HGT8J5E2N0W0W0W0W0W0W0W5",
     "status": "SUCCESS",
-    "summary": "Explicit user request to delete the KENTİM docs set (biggest bloat). Performed rm on the 6 files. Verified no remaining references in the project docs or core code. This cleans future inits and npm packages. Only the requested set was touched. Updated PROJECT_MEMORY HISTORY and this log entry per governance. Trace preserved.",
-    "findings": [
-      "KENTİM set (api-referans",
-      "is_akislari",
-      "mimari",
-      "moduller",
-      "proje",
-      "yapı .md) removed. 0 dangling cross-refs left. Other unused items (SYSTEM_MAP",
-      "empty dirs) left for future if requested."
-    ]
+    "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": "2026-06-02T17:22:25.256Z",
+    "timestamp": "2026-06-03T15:23:06.000Z",
     "agent": "@manager",
-    "action": "unused-files-audit-corporate-assessment",
+    "action": "version-synchronization",
     "requestId": "01HGT8J5E2N0W0W0W0W0W0W0W5",
     "status": "SUCCESS",
-    "summary": "Completed full audit for unused files (post KENTIM cleanup) + assessment for complex corporate ('karmasıl kurumsal') project support. Removed SYSTEM_MAP.md (dead root doc). Reported all findings: structural placeholders are by design, apps/ minimal is intentional per SOP. Confirmed strong support via 12 agents, memory, contracts, corporate-gov knowledge (18 files), surgical edits, etc. Updated HISTORY and this log. All per ENDERUN rules, surgical, Trace.",
-    "findings": [
-      "SYSTEM_MAP removed. No other major dead files to delete (placeholders intentional). Framework is purpose-built for enterprise complexity via governance internalization",
-      "not example bloat."
-    ]
+    "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": "2026-06-02T17:26:42.081Z",
+    "timestamp": "2026-06-03T15:26:11.000Z",
     "agent": "@manager",
-    "action": "low-usage-arrange-nihai-readme-update",
+    "action": "init-adapter-scaffolding-fix",
     "requestId": "01HGT8J5E2N0W0W0W0W0W0W0W5",
     "status": "SUCCESS",
-    "summary": "Arranged low-usage reference items with headers/comments (knowledge + bin + observability). Bumped to v1.0.8 final clean. Updated STATUS and README surgically for nihai sürüm, bloat note, corporate readiness. All via MCP where possible + terminal for new README. Memory/log done. Ready for publish/complex projects.",
-    "findings": [
-      "5 knowledge files + 2 bin scripts + observability README edited. Version 1.0.8. README reflects final clean state."
-    ]
+    "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":"2026-06-02T17:32:06.021Z","agent":"@manager","action":"v1.0.8-release-clean-push-publish","requestId":"01HGT8J5E2N0W0W0W0W0W0W0W5","status":"SUCCESS","summary":"Version 1.0.8 prep: logs pruned to recent 5, memory HISTORY updated/pruned with release entry. Git commit for 1.0.8 final clean (low-usage arranged, bloat gone). Attempted git push to origin main. Ran build. Ready for npm publish. All per governance, Trace, surgical where applicable.","findings":["version 1.0.8","memory/log clean","commit done","push attempted (remote may need config in env)","npm prep complete"]}
-{"timestamp":"2026-06-02T17:32:37.162Z","agent":"@manager","action":"v1.0.8-publish-final","requestId":"01HGT8J5E2N0W0W0W0W0W0W0W5","status":"SUCCESS","summary":"Completed v1.0.8: memory pruned, logs cleaned to 5, git commit for release changes, build, npm pack verified, publish cmd executed (build ran, but OTP needed for full publish). Push to github prepared. All user requested steps done. Project ready.","findings":["1.0.8 published prep complete","auth step for npm","git commit local ready"]}
-{"timestamp":"2026-06-02T18:24:20.290Z","agent":"@manager","action":"PROJECT_ANALYSIS","requestId":"01HGT8J5E2N0W0W0W0W0W0W0W5","status":"SUCCESS","summary":"Performed detailed project analysis and created docs/project_analysis_report.md.","findings":["12 agents verified","AL validation rules checked","docs folder updated"]}
+]
+{"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"]}
+{"timestamp":"2026-06-03T15:49:59.717Z","agent":"@manager","action":"stream-error-analysis","requestId":"01HGT8J5E2N0W0W0W0W0W0W0W5","status":"SUCCESS","summary":"Analyzed the codebase_investigator InvalidStreamError and provided troubleshooting steps.","findings":["analyzed stream error source and parsed causes including JSON truncation and tool schema mismatches"]}
+{"timestamp":"2026-06-03T15:51:15.243Z","agent":"@manager","action":"mcp-read-file-truncation-safety-fix","requestId":"01HGT8J5E2N0W0W0W0W0W0W0W5","status":"SUCCESS","summary":"Updated the read_file MCP tool to support optional startLine/endLine parameters and default to a 1000-line safety limit to protect against stream truncation/JSON formatting errors.","findings":["read_file schema updated","startLine/endLine parsing added","1000-line default truncation threshold enforced"]}
+{"timestamp":"2026-06-03T18:27:33.798Z","agent":"@manager","action":"ANALYZE_DUPLICATES","requestId":"01HGT8J5E2N0W0W0W0W0W0W0W5","status":"SUCCESS","summary":"Analyzed the project for duplicate files and identified redundant configurations and directories.","findings":["Found duplicate .agents folder","redundant mcp.json variants","and duplicated architecture/security documents."]}
+{"timestamp":"2026-06-03T18:31:20.178Z","agent":"@manager","action":"CLEANUP_COMPLETE","requestId":"01HGT8J5E2N0W0W0W0W0W0W0W5","status":"SUCCESS","summary":"Completed proejct clean-up and centralized all configuration under .enderun.","findings":["Successfully deleted legacy .agents/ folder and duplicate ARCHITECTURE.md/SECURITY.md in .enderun/. Verified using git status."]}

package/.enderun/memory/PROJECT_MEMORY.md

@@ -19,18 +19,51 @@
 
 ## HISTORY
 
-- **Project Analysis & Report (v1.0.9+):** Conducted a deep dive analysis of the Agent Enderun codebase, including framework configuration files, Model Context Protocol (MCP) server structure, CLI commands, workspace configurations (Fastify backend, React/Vite frontend), and the 12-agent army setup. Generated and saved a comprehensive project analysis report at [project_analysis_report.md](file:///Users/ybekar/Desktop/Projeler/agent-enderun/docs/project_analysis_report.md) in the docs folder, complying with the framework's documentation ownership rules. (Trace 01HGT8J5E2N0W0W0W0W0W0W0W5)
+### 2026-06-03 — CLI & Build Stabilization
 
-Test entry from CLI again.
+- **Agent:** @manager
+- **Trace ID:** 01HGT8J5E2N0W0W0W0W0W0W0W5
+- **Action:** Stabilized the CLI publish configuration and compiler flow. Updated `bin/cli.js` to run the compiled JS entrypoint `dist/src/cli/index.js` directly with standard Node, removing the runtime dependency on `tsx` in production. Added a root `build` script (`tsc && npm run build --prefix framework-mcp`) to root `package.json` and updated `prepublishOnly` to guarantee compilation of all packages before npm publish. Cleared out duplicate compiled directories and files (`dist/cli/`, `dist/orchestrate.*`, `dist/vitest.config.*`). Standardized case-sensitivity test expectations in `tests/gemini.test.ts` and `tests/adapter.test.ts` to expect uppercase `"GEMINI.md"` and `"GROK.md"`. Fixed an undefined reference to `targetDir` in `src/cli/commands/init.ts` by passing it down to `scaffoldCoreAgents`.
 
-Test entry from CLI
+### 2026-06-03 — OS & Sandbox Verification and Sync
+
+- **Agent:** @manager
+- **Trace ID:** 01HGT8J5E2N0W0W0W0W0W0W0W5
+- **Action:** Synchronized all compiled files under `dist/cli/` to fix missing exports (`sendMessage` in `orchestrate.js`) and dynamic path resolutions. Corrected a Linux-specific case-sensitivity bug where `gemini.md` and `grok.md` shim references were mapped as lowercase, mismatching the actual uppercase filenames `GEMINI.md` and `GROK.md` on disk. Evaluated `targetDir` dynamically inside `initCommand` to allow multi-directory programmatic executions. Resolved macOS Sandbox TCC and Node.js directory EPERM blocks inside the integration test script (`bin/test-init-run.js`) by relocating tests to `dist/init-adapters` and conditionally skipping sandbox-sensitive user directory generations during test runs.
+
+### 2026-06-03 — Realistic Adapter Verification & Path Fix
+
+- **Agent:** @manager
+- **Trace ID:** 01HGT8J5E2N0W0W0W0W0W0W0W5
+- **Action:** Fixed a critical bug in src/cli/commands/init.ts where sourceDir resolved incorrectly in production/dist builds; converted it to use getPackageRoot() from utils/pkg.ts. Audited and verified all 7 adapters (gemini, claude, cursor, codex, grok, antigravity, antigravity-cli) inside test subdirectories, verifying folder remapping, shim rules, and AL compliance.
+
+### 2026-06-03 — Adapter Link Fixes and Dynamic Prompting
+
+- **Agent:** @manager
+- **Trace ID:** 01HGT8J5E2N0W0W0W0W0W0W0W5
+- **Action:** Fixed broken links in GEMINI.md and CLAUDE.md pointing to .enderun/ARCHITECTURE.md and .enderun/SECURITY.md (changed to point to .enderun/knowledge/ instead). Added Dynamic Identity Adjustment directive to shim files, enabling agents to adopt specialist roles. Corrected print statement extension format in orchestrate.ts from .md to .json.
+
+### 2026-06-03 — Project Clean-up and Standardization
+
+- **Agent:** @manager
+- **Trace ID:** 01HGT8J5E2N0W0W0W0W0W0W0W5
+- **Action:** Cleaned up the codebase by deleting the legacy .agents/ folder and removing duplicate ARCHITECTURE.md and SECURITY.md files from .enderun/. Centralized all active configurations under the .enderun/ directory.
+
+### 2026-06-03 — Duplicate File Analysis
+
+- **Agent:** @manager
+- **Trace ID:** 01HGT8J5E2N0W0W0W0W0W0W0W5
+- **Action:** Analyzed the project codebase for duplicate and redundant files. Identified .agents as a legacy framework directory, and noted identical/redundant files like root mcp.json/mcp_config.json variants and duplicate architecture/security rules.
+
+- **MCP Read File Safety Prevention (v1.1.1):** Configured optional `startLine` and `endLine` parameters in the `read_file` tool schema and handler, and set a default safety limit of 1000 lines to prevent JSON truncation and stream format errors when handling large files. (Trace 01HGT8J5E2N0W0W0W0W0W0W0W5)
+- **Stream Error Analysis (v1.1.1):** Diagnosed `InvalidStreamError` where an agent stream ends in a malformed function call. Documented main causes (truncation, formatting, schema drift) and troubleshooting steps for workspace developers. (Trace 01HGT8J5E2N0W0W0W0W0W0W0W5)
+- **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.
-- **AI Compatibility Audit:** Documented and verified active readiness for Gemini/Antigravity CLI, Cursor IDE, Claude Code/Desktop, and Grok environments.
-- **Antigravity Konfigürasyon Entegrasyonu:** `agent-settings`, `cli-settings` ve `ide-settings` kılavuzlarındaki standartlara uygun olarak `.agents/skills`, `.agents/rules`, `.agents/workflows` dizinleri, `.agents/mcp_config.json` lokal MCP tanımları ve kök dizindeki `AGENTS.md` otonom talimat dosyası oluşturuldu ve `init` akışına entegre edildi.
-- **Automated Scaffolding Geliştirmesi:** `init` komutu güncellendi. Kurulum sırasında hem `.agents/agents/...` klasörlerinin hem de `.cursorrules` dosyasının otomatik olarak oluşturulması sağlandı, böylece hem Antigravity hem de Cursor IDE destekleri tamamen otonom ve otomatik hale getirildi.
-- **Framework Directory Resolution Fix:** Removed `.agents` from `FRAMEWORK_DIR_CANDIDATES` to avoid false positive directory detection when `.agents` is created solely for Antigravity/Cursor custom agent registration. Verified health check is 100% green.
-- **Architectural Guidance:** Answered user inquiry regarding MCP agent definition structure, explaining the role of `agent.json` vs `.md` files.
+- **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/CLAUDE.md

@@ -3,15 +3,16 @@
 You are the **Architect** of the Agent Enderun Army. While the **Commander** (@manager) orchestrates, you focus on structural integrity and code excellence.
 
 ### 🏛️ Hierarchy of Authority
-1. **Supreme Law:** [.enderun/ENDERUN.md](.enderun/ENDERUN.md)
-2. **Global Rules:** [ARCHITECTURE.md](.enderun/ARCHITECTURE.md), [SECURITY.md](.enderun/SECURITY.md)
-3. **Project Memory:** [.enderun/memory/](.enderun/memory/) (Decisions, Lessons, Status)
+1. **Supreme Law:** [.claude/ENDERUN.md](.claude/ENDERUN.md)
+2. **Global Rules:** [ARCHITECTURE.md](.claude/knowledge/ARCHITECTURE.md), [SECURITY.md](.claude/knowledge/SECURITY.md)
+3. **Project Memory:** [.claude/memory/](.claude/memory/) (Decisions, Lessons, Status)
 
 ### 🤖 Architect Directive (Role: QUALITY & REFACTOR)
 1. **Manager Coordination:** Receive your briefings from @manager. You are part of a coordinated army.
 2. **Enforce Surgical Precision:** All code changes must use `replace_text` or `patch_file`. No full file rewrites.
 3. **Contract & Type Integrity:** Verify that backend contracts and branded types are respected.
-4. **Maintain State:** Update `.enderun/memory/PROJECT_MEMORY.md` and log actions at the end of EVERY turn.
+4. **Dynamic Identity Adjustment:** If you are executing a delegated task for a specialist role (e.g. backend, frontend, database, qa) as per the active tasks in `.claude/memory/PROJECT_MEMORY.md`, temporarily adopt that identity by loading its specific rules from `.claude/agents/{agent}.json` and follow them strictly.
+5. **Maintain State:** Update `.claude/memory/PROJECT_MEMORY.md` and log actions at the end of EVERY turn.
 
 ### 🛡️ Core Mandates (Enterprise 1.0)
 - **Zero UI Library Policy:** Enforce hand-crafted components with Panda CSS.

package/GEMINI.md

@@ -3,9 +3,9 @@
 You are the **Commander** (@manager), the Supreme Orchestrator of the Agent Enderun Army. Your primary role is strategic orchestration, intent analysis, and final approval.
 
 ### 🏛️ Hierarchy of Authority
-1. **Supreme Law:** [.enderun/ENDERUN.md](.enderun/ENDERUN.md)
-2. **Global Rules:** [ARCHITECTURE.md](.enderun/ARCHITECTURE.md), [SECURITY.md](.enderun/SECURITY.md)
-3. **Project Memory:** [.enderun/memory/](.enderun/memory/) (Decisions, Lessons, Status)
+1. **Supreme Law:** [.gemini/ENDERUN.md](.gemini/ENDERUN.md)
+2. **Global Rules:** [ARCHITECTURE.md](.gemini/knowledge/ARCHITECTURE.md), [SECURITY.md](.gemini/knowledge/SECURITY.md)
+3. **Project Memory:** [.gemini/memory/](.gemini/memory/) (Decisions, Lessons, Status)
 
 ### 🤖 Commander Directive (Role: @manager)
 1. **Analyze Intent:** Act as the **Router**. Every request must be processed by you first. Break down user requests into a task DAG.
@@ -13,7 +13,8 @@ You are the **Commander** (@manager), the Supreme Orchestrator of the Agent Ende
    - **How to Delegate:** Use the `send_agent_message` tool to assign tasks to other agents (e.g., `@backend`, `@frontend`).
    - **How to Sync:** Use the `orchestrate_loop` tool after delegating to update the system state and `STATUS.md`.
 3. **Verify:** Review all specialist outputs against the **Architectural Decisions (DECISIONS.md)**.
-4. **Maintain State:** Update `.enderun/memory/PROJECT_MEMORY.md` and log actions at the end of EVERY turn.
+4. **Dynamic Identity Adjustment:** If you are executing a delegated task for a specialist role (e.g. backend, frontend, database) as per the active tasks in `.gemini/memory/PROJECT_MEMORY.md`, temporarily adopt that identity by loading its specific rules from `.gemini/agents/{agent}.json` and follow them strictly.
+5. **Maintain State:** Update `.gemini/memory/PROJECT_MEMORY.md` and log actions at the end of EVERY turn.
 
 ### 🛡️ Core Mandates (Enterprise 1.0)
 - **Role-Based:** You are not just a model; you are the **Commander**. 

package/GROK.md

@@ -3,9 +3,9 @@
 You are the **Researcher** and **Intelligence Specialist** of the Agent Enderun Army. Your primary role is technology scouting, trend analysis, and deep analysis.
 
 ### 🏛️ Hierarchy of Authority
-1. **Supreme Law:** [.enderun/ENDERUN.md](.enderun/ENDERUN.md)
-2. **Lessons Learned:** [.enderun/memory/LESSONS_LEARNED.md](.enderun/memory/LESSONS_LEARNED.md)
-3. **Business Context:** [.enderun/memory/BUSINESS_CONTEXT.md](.enderun/memory/BUSINESS_CONTEXT.md)
+1. **Supreme Law:** [.grok/ENDERUN.md](.grok/ENDERUN.md)
+2. **Lessons Learned:** [.grok/memory/LESSONS_LEARNED.md](.grok/memory/LESSONS_LEARNED.md)
+3. **Business Context:** [.grok/memory/BUSINESS_CONTEXT.md](.grok/memory/BUSINESS_CONTEXT.md)
 
 ### 🤖 Researcher Directive (Role: ANALYTICAL)
 1. **Trend Analysis:** Identify modern alternatives for libraries and patterns.

package/README.md

@@ -1,6 +1,6 @@
 # 🏛️ Agent Enderun — Enterprise AI Governance & Autonomous Orchestration Framework
 
-> **Stable Release:** v1.1.0 (Enterprise Orchestration Ready) — Build Compile: Clean | Type-Safety: 100% Verified | AL Compliance: 12/12 Agents
+> **Stable Release:** v1.1.2 (Enterprise Orchestration Ready) — Build Compile: Clean | Type-Safety: 100% Verified | AL Compliance: 12/12 Agents
 
 > **Author:** Yusuf BEKAR
 > **Trace ID:** `01HGT8J5E2N0W0W0W0W0W0W0W5`
@@ -12,7 +12,7 @@
 
 **Agent Enderun**, sıradan bir kod şablon üreteci veya basit bir AI asistanı değildir; karmaşık, ölçeklenebilir ve kurumsal (enterprise) düzeydeki yazılım projeleri için özel olarak tasarlanmış bir **Yapay Zeka Yönetişimi ve Otonom Ordu Komuta Sistemidir**.
 
-Nihai temiz sürüm (v1.1.0) itibarıyla sistem; **@-mention delegasyon**, **doğal dil rotalama** ve **Hermes Kilit Protokolü** ile güçlendirilmiş; kendi hafızasını yönetebilen, monorepo proje yollarını dinamik olarak haritalayan, tüm ajan seanslarını güvenli şekilde günlükleyen, farklı yapay zeka ekosistemlerini anayasal bir disiplin altında birleştiren, **Agent Lifecycle (AL) tam uyumlu init ve ordu validasyonunu** (npm kurulumu sonrası dahil) otomatikleştiren ve **macOS & Windows çapraz platform standartlarına tam uyum sağlayan** yaşayan bir mühendislik organizmasıdır. Karmaşık kurumsal projeler için optimize edilmiştir (corporate-governance SOP'ları ile).
+Nihai temiz sürüm (v1.1.0) itibarıyla sistem; **@-mention delegasyon**, **doğal dil rotalama** ve **Hermes Kilit Protokolü** ile güçlendirilmiş; kendi hafızasını yönetebilen, monorepo proje yollarını dinamik olarak haritalayan, tüm ajan seanslarını güvenli şekilde günlükleyen, farklı yapay zeka ekosistemlerini anayasal bir disiplin altında birleştiren, **Agent Lifecycle (AL) tam uyumlu init ve ordu validasyonunu** (npm kurulumu sonrası dahil) otomatikleştiren, **harici IDE entegrasyonlarında (Claude Desktop/Cursor vb.) mutlak proje kök dizini (CWD) uyumluluğu sunan**, **scaffold adımlarında ajan klasörlerini adapter tipine göre dinamik olarak eşleyen** ve **macOS & Windows çapraz platform standartlarına tam uyum sağlayan** yaşayan bir mühendislik organizmasıdır. Karmaşık kurumsal projeler için optimize edilmiştir (corporate-governance SOP'ları ile).
 
 ---
 
@@ -24,13 +24,13 @@ Yapay zeka kodlama yardımcıları (Claude Code, Gemini CLI, Grok Build vb.) gel
 2. **Kayıp Hafıza ve Bağlam Drifti:** Ajanlar oturum değiştirdikçe projenin geçmişini ve mimari kararlarını unutur. Enderun, **`.enderun/memory/PROJECT_MEMORY.md`** dosyasını projenin değişmez tek doğruluk kaynağı (SSOT) haline getirerek, seanslar arası bağlam kaybını tamamen engeller.
 3. **Akıllı Delegasyon ve Doğal Dil:** Artık karmaşık komutlar yerine `agent-enderun "Projemi denetle"` gibi doğal dildeki istekler veya `agent-enderun @backend "Tablo oluştur"` gibi doğrudan delegasyonlar kullanılabilir.
 4. **Çoklu Ajan Kaosu:** **12** farklı uzman yapay zeka ajanı, olay tabanlı asenkron bir haberleşme protokolü olan **Hermes Message Broker** üzerinden koordine edilir. Ajanlar birbirine rastgele müdahale edemez; tüm görevler bir İş Dağılım Grafiği (DAG) üzerinden komuta edilir.
-5. **Güvenli Haberleşme:** Yeni eklenen **Hermes Lock Protocol** sayesinde, birden fazla ajanın aynı anda mesajlaşması durumunda veri çakışmaları tamamen engellenir.
+5. **Güvenli Haberleşme & Entegrasyon:** Yeni eklenen **Hermes Lock Protocol** sayesinde, birden fazla ajanın aynı anda mesajlaşması durumunda veri çakışmaları tamamen engellenir. Ayrıca harici asistanların yerel MCP araçlarını sorunsuz çalıştırabilmesi için mutlak çalışma dizini (CWD) parametreleri yapılandırılmıştır.
 
 ---
 
 ### 📦 Güncel Sürüm / Current Release
 
-**v1.1.0** — Enterprise 1.0 kararlı sürüm (@-mentions, NL Routing, Hermes Lock Protocol). Detaylı sürüm geçmişi git log ve önceki commit'lerde bulunur; kalıbımız (bilingual TR/EN yapı, tablolar, bölümler) korunmuştur.
+**v1.1.2** — Enterprise 1.0 kararlı sürüm (@-mentions, NL Routing, Hermes Lock Protocol, CWD/Scaffold fix). Detaylı sürüm geçmişi git log ve önceki commit'lerde bulunur; kalıbımız (bilingual TR/EN yapı, tablolar, bölümler) korunmuştur.
 
 ---
 
@@ -166,7 +166,7 @@ npx agent-enderun init gemini --unified
 
 **Agent Enderun** is not a generic boilerplate generator or a simple AI wrapper; it is an elite, state-of-the-art **AI Governance and Autonomous Army Command System** designed for complex, scalable, and highly auditable enterprise software projects.
 
-Nihai temiz sürüm (v1.0.9 - Final Clean Release) operates as a **"Living Engineering Organism"** capable of managing its own persistent memory, dynamically mapping project directory scopes, secure-logging expert agent activities, **automatically enforcing Agent Lifecycle (AL) compliance on every init** (including after `npm install`), and **fully complying with cross-platform (macOS & Windows) scripting and standard setups**. Low-usage reference materials arranged (knowledge files, demo scripts, observability placeholders marked). Bloat removed. Optimized for complex corporate/enterprise projects via corporate-governance knowledge and SOPs.
+Version **v1.1.1** operates as a **"Living Engineering Organism"** capable of managing its own persistent memory, dynamically mapping project directory scopes, secure-logging expert agent activities, **automatically enforcing Agent Lifecycle (AL) compliance on every init** (including after `npm install`), **resolving absolute project root paths (CWD) dynamically for external assistant tools (e.g. Claude Desktop/Cursor)**, **mapping agent scaffolding subdirectories to adapter-specific folders (skills/plugins/agents) dynamically during init**, and **fully complying with cross-platform (macOS & Windows) scripting and standard setups**. Low-usage reference materials arranged (knowledge files, demo scripts, observability placeholders marked). Bloat removed. Optimized for complex corporate/enterprise projects via corporate-governance knowledge and SOPs.
 
 ---
 
@@ -178,13 +178,13 @@ As AI coding assistants (Claude Code, Gemini CLI, Grok Build, etc.) become incre
 2. **Context Loss Prevention (SSOT Memory):** AI agents naturally lose project history across chats. Enderun seals all project milestones, decisions, and tasks into a self-pruning **`.enderun/memory/PROJECT_MEMORY.md`** file, ensuring absolute context continuity.
 3. **Contract-First Safety (Frontend-Backend Drift):** Before any user interface code is written, API models and branded types are sealed. The **autonomous** contract verification engine checks SHA-256 type definitions to prevent integration drifts.
 4. **Symmetric Orchestration (Hermes Protocol):** **12** specialized expert agents communicate via an asynchronous, event-driven message broker (**Hermes**), preventing chaotic, uncoordinated AI behavior.
-5. **Sandbox & Security Compliance:** Modern CLI agents (like Claude Code) restrict filesystem access. By keeping all configurations, task logs, and queues local (inside **`.enderun/`**, `.gemini/`, `.claude/`, `.grok/`, etc.) in the project workspace, Enderun runs with **zero sandbox violations**.
+5. **Sandbox & Security Compliance:** Modern CLI agents (like Claude Code) restrict filesystem access. By keeping all configurations, task logs, and queues local (inside **`.enderun/`**, `.gemini/`, `.claude/`, `.grok/`, etc.) in the project workspace, Enderun runs with **zero sandbox violations**. Additionally, absolute CWD environment bindings prevent path mismatches in background execution.
 
 ---
 
 ### 📦 Current Release / Güncel Sürüm
 
-**v1.0.9** — AL Enterprise Compliance stable (full cross-adapter & npm install support for remaps + validator resolution, with surgical fixes). Detailed historical release notes are in git history; the bilingual TR/EN template, tables, and section mold are preserved.
+**v1.1.1** — AL Enterprise Compliance stable (full cross-adapter & npm install support for remaps + validator resolution, with surgical fixes for CWD environment and dynamic folder scaffolding). Detailed historical release notes are in git history; the bilingual TR/EN template, tables, and section mold are preserved.
 
 ---
 
@@ -316,4 +316,4 @@ npx agent-enderun init gemini --unified
 
 ---
 
-Developed with absolute discipline | Developer **Yusuf BEKAR** | Framework Version **v1.0.9 (Final Clean)** — Low-usage items arranged as reference-only. Bloat removed. Corporate-ready.
+Developed with absolute discipline | Developer **Yusuf BEKAR** | Framework Version **v1.1.1 (Final Clean)** — Low-usage items arranged as reference-only. Bloat removed. Corporate-ready.