agent-enderun 0.6.1 → 0.6.5
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.enderun/PROJECT_MEMORY.md +110 -2
- package/.enderun/STATUS.md +3 -3
- package/.enderun/agents/analyst.md +97 -10
- package/.enderun/agents/backend.md +258 -14
- package/.enderun/agents/explorer.md +67 -2
- package/.enderun/agents/frontend.md +404 -66
- package/.enderun/agents/git.md +19 -2
- package/.enderun/agents/manager.md +412 -45
- package/.enderun/agents/mobile.md +62 -18
- package/.enderun/agents/native.md +60 -10
- package/.enderun/blueprints/backend/errors/blueprint.json +11 -0
- package/.enderun/blueprints/backend/errors/domain-error.ts +34 -55
- package/.enderun/knowledge/framework_vs_user_project_boundary.md +52 -0
- package/.enderun/knowledge/frontend_professionalization_guidelines.md +108 -0
- package/.enderun/knowledge/hermes_live_test_guidelines.md +90 -0
- package/.enderun/knowledge/manager_authority_audit_enforcement.md +104 -0
- package/.enderun/knowledge/project_scaffold_guidelines.md +99 -0
- package/.enderun/knowledge/reference_application_guidelines.md +90 -0
- package/.enderun/messages/2026-05-23-backend-to-manager-auth-errors-reply.json +23 -0
- package/.enderun/messages/2026-05-23-manager-to-backend-auth-errors.json +26 -0
- package/ENDERUN.md +10 -3
- package/README.md +185 -625
- package/antigravity.md +15 -0
- package/bin/cli.js +92 -27
- package/docs/README.md +33 -3
- package/docs/getting-started.md +497 -0
- package/docs/roadmap.md +200 -0
- package/framework-mcp/README.md +1 -1
- package/framework-mcp/dist/index.js +0 -0
- package/framework-mcp/dist/tools/academy.js +6 -8
- package/framework-mcp/dist/tools/codebase.js +6 -6
- package/framework-mcp/dist/tools/contract.js +94 -4
- package/framework-mcp/dist/tools/database.js +1 -1
- package/framework-mcp/dist/tools/framework.js +8 -12
- package/framework-mcp/dist/tools/git.js +2 -2
- package/framework-mcp/dist/tools/knowledge.js +4 -4
- package/framework-mcp/dist/tools/memory.js +5 -7
- package/framework-mcp/dist/tools/messages.js +6 -6
- package/framework-mcp/dist/tools/repository.js +4 -4
- package/framework-mcp/dist/tools/scaffold.js +6 -3
- package/framework-mcp/dist/tools/security.js +4 -4
- package/framework-mcp/dist/utils.js +1 -1
- package/framework-mcp/package.json +1 -1
- package/framework-mcp/src/schemas.ts +7 -0
- package/framework-mcp/src/tools/academy.ts +5 -9
- package/framework-mcp/src/tools/codebase.ts +6 -6
- package/framework-mcp/src/tools/contract.ts +114 -4
- package/framework-mcp/src/tools/database.ts +1 -1
- package/framework-mcp/src/tools/framework.ts +9 -12
- package/framework-mcp/src/tools/git.ts +2 -2
- package/framework-mcp/src/tools/knowledge.ts +5 -6
- package/framework-mcp/src/tools/memory.ts +5 -6
- package/framework-mcp/src/tools/messages.ts +94 -28
- package/framework-mcp/src/tools/repository.ts +5 -6
- package/framework-mcp/src/tools/scaffold.ts +9 -6
- package/framework-mcp/src/tools/security.ts +4 -4
- package/framework-mcp/src/utils.ts +2 -2
- package/gemini.md +4 -4
- package/package.json +11 -7
- package/panda.config.ts +3 -1
- package/.enderun/benchmarks/.gitkeep +0 -0
- package/.enderun/blueprints/backend/middleware/error-handler.ts +0 -24
- package/.enderun/blueprints/backend/types/api.ts +0 -20
- package/.enderun/blueprints/backend/types/brands.ts +0 -12
- package/.enderun/blueprints/backend/types/constants.ts +0 -34
- package/.enderun/blueprints/backend/types/index.ts +0 -49
- package/.enderun/blueprints/backend/types/logs.ts +0 -16
- package/.enderun/blueprints/backend/types/models.ts +0 -65
- package/.enderun/blueprints/frontend/ui/Button.tsx +0 -60
- package/.enderun/blueprints/frontend/ui/Input.tsx +0 -43
- package/.enderun/monitoring/.gitkeep +0 -0
- package/gemini-extension.json +0 -13
|
@@ -0,0 +1,497 @@
|
|
|
1
|
+
# 🚀 Getting Started — Sıfırdan Agent Enderun ile Proje Kurma Rehberi / Quickstart Guide
|
|
2
|
+
|
|
3
|
+
[English](#english) | [Türkçe](#türkçe)
|
|
4
|
+
|
|
5
|
+
---
|
|
6
|
+
|
|
7
|
+
# English
|
|
8
|
+
|
|
9
|
+
This guide is prepared for developers and engineering teams who want to set up Agent Enderun **from scratch** on a new project. It provides a step-by-step, practical walkthrough.
|
|
10
|
+
|
|
11
|
+
> **Primary recommended installation command from v0.6.5:** **`npx agent-enderun init` (generic framework setup)**
|
|
12
|
+
|
|
13
|
+
---
|
|
14
|
+
|
|
15
|
+
## 1. Introduction
|
|
16
|
+
|
|
17
|
+
Agent Enderun is a yapay zeka/AI governance framework that provides **control, discipline, and traceability** in software development processes.
|
|
18
|
+
|
|
19
|
+
By completing this guide, you will:
|
|
20
|
+
- Install the framework in your project
|
|
21
|
+
- Configure the basic components and environment
|
|
22
|
+
- Create your first tracked task and start working with specialist agents
|
|
23
|
+
|
|
24
|
+
---
|
|
25
|
+
|
|
26
|
+
## 2. Prerequisites
|
|
27
|
+
|
|
28
|
+
- **Node.js** 20+ (LTS recommended)
|
|
29
|
+
- **npm** 9+
|
|
30
|
+
- **Git** (must be initialized in the project directory)
|
|
31
|
+
|
|
32
|
+
To check your local environment:
|
|
33
|
+
|
|
34
|
+
```bash
|
|
35
|
+
node --version
|
|
36
|
+
npm --version
|
|
37
|
+
git --version
|
|
38
|
+
```
|
|
39
|
+
|
|
40
|
+
---
|
|
41
|
+
|
|
42
|
+
## 3. Step-by-Step Installation
|
|
43
|
+
|
|
44
|
+
### Step 1: Create a New Project Directory
|
|
45
|
+
|
|
46
|
+
```bash
|
|
47
|
+
mkdir my-new-project
|
|
48
|
+
cd my-new-project
|
|
49
|
+
git init
|
|
50
|
+
```
|
|
51
|
+
|
|
52
|
+
### Step 2: Initialize the Framework
|
|
53
|
+
|
|
54
|
+
To initialize the core framework cleanly (without hardcoding any AI/adapter-specific files before installation):
|
|
55
|
+
|
|
56
|
+
```bash
|
|
57
|
+
npx agent-enderun init
|
|
58
|
+
```
|
|
59
|
+
|
|
60
|
+
This command:
|
|
61
|
+
- Creates the `.enderun/` directory by default
|
|
62
|
+
- Installs all core governance files (`ENDERUN.md`, `PROJECT_MEMORY.md`, agents, knowledge, etc.)
|
|
63
|
+
- Adds the default framework configuration files
|
|
64
|
+
|
|
65
|
+
#### 💡 Optional: Installing with a Specific Adapter
|
|
66
|
+
If you want to configure the framework for a specific AI assistant or editor environment (e.g. Antigravity, Claude, Cursor, Codex, Gemini), you can specify it as an option:
|
|
67
|
+
|
|
68
|
+
```bash
|
|
69
|
+
npx agent-enderun init antigravity
|
|
70
|
+
# or
|
|
71
|
+
npx agent-enderun init claude
|
|
72
|
+
# or
|
|
73
|
+
npx agent-enderun init cursor
|
|
74
|
+
# or
|
|
75
|
+
npx agent-enderun init codex
|
|
76
|
+
# or
|
|
77
|
+
npx agent-enderun init gemini
|
|
78
|
+
```
|
|
79
|
+
|
|
80
|
+
- If you run `init antigravity`, it will create `.antigravitycli/` instead of `.enderun/` and place `antigravity.md` at the project root.
|
|
81
|
+
- If you run `init claude`, it will create `.claude/` and automatically configure the Claude Desktop MCP settings.
|
|
82
|
+
- If you run `init cursor`, it will create `.cursor/` and copy the cursor rules configuration.
|
|
83
|
+
- If you run `init gemini`, it will create `.gemini/` and place `gemini.md` at the project root.
|
|
84
|
+
|
|
85
|
+
---
|
|
86
|
+
|
|
87
|
+
### Step 3: Install Dependencies and Build
|
|
88
|
+
|
|
89
|
+
```bash
|
|
90
|
+
npm install
|
|
91
|
+
npm run enderun:build
|
|
92
|
+
```
|
|
93
|
+
|
|
94
|
+
### Step 4: Verify the Installation
|
|
95
|
+
|
|
96
|
+
```bash
|
|
97
|
+
npx agent-enderun check
|
|
98
|
+
```
|
|
99
|
+
|
|
100
|
+
Expected output:
|
|
101
|
+
|
|
102
|
+
```
|
|
103
|
+
✅ Framework active (v0.6.5)
|
|
104
|
+
✅ MCP Server ready
|
|
105
|
+
✅ Shared types compiled
|
|
106
|
+
✅ Agent logs initialized
|
|
107
|
+
✅ PROJECT_MEMORY.md found
|
|
108
|
+
```
|
|
109
|
+
|
|
110
|
+
---
|
|
111
|
+
|
|
112
|
+
## 4. Basic Configuration (Most Critical Step)
|
|
113
|
+
|
|
114
|
+
Once initialized, you **must** update the following files to describe your project. Ajanlar (agents) learn your technology stack and target domain from here.
|
|
115
|
+
|
|
116
|
+
### 4.1 `docs/tech-stack.md`
|
|
117
|
+
|
|
118
|
+
This file is **mandatory**. Agents rely on it to make technical decisions.
|
|
119
|
+
|
|
120
|
+
Example:
|
|
121
|
+
|
|
122
|
+
```markdown
|
|
123
|
+
# TECH STACK
|
|
124
|
+
|
|
125
|
+
## Platform
|
|
126
|
+
- Web (React + Vite)
|
|
127
|
+
- Backend (Node.js + Fastify)
|
|
128
|
+
|
|
129
|
+
## Database
|
|
130
|
+
- PostgreSQL + Kysely
|
|
131
|
+
|
|
132
|
+
## Auth
|
|
133
|
+
- JWT + Refresh Token
|
|
134
|
+
|
|
135
|
+
## Deployment
|
|
136
|
+
- Vercel (Frontend) + Railway (Backend)
|
|
137
|
+
```
|
|
138
|
+
|
|
139
|
+
> **Warning:** If this file is empty, the agents will not be able to operate.
|
|
140
|
+
|
|
141
|
+
### 4.2 `docs/project-docs.md`
|
|
142
|
+
|
|
143
|
+
Write your project's goals, business requirements, and primary features here.
|
|
144
|
+
|
|
145
|
+
### 4.3 `.enderun/PROJECT_MEMORY.md`
|
|
146
|
+
|
|
147
|
+
Automatically created during initial setup. Review its content. *(Note: If you initialized with a custom adapter, this file will be located inside your adapter's folder, e.g., `.antigravitycli/PROJECT_MEMORY.md`)*.
|
|
148
|
+
|
|
149
|
+
---
|
|
150
|
+
|
|
151
|
+
## 5. Creating Your First Task
|
|
152
|
+
|
|
153
|
+
You are now ready to create your first real task:
|
|
154
|
+
|
|
155
|
+
```bash
|
|
156
|
+
npx agent-enderun trace:new "User Registration and Login System" backend P1
|
|
157
|
+
```
|
|
158
|
+
|
|
159
|
+
This command:
|
|
160
|
+
- Generates a unique Trace ID
|
|
161
|
+
- Updates the **ACTIVE TASKS** section in `PROJECT_MEMORY.md`
|
|
162
|
+
- Assigns the `@manager` agent to lead the task
|
|
163
|
+
|
|
164
|
+
---
|
|
165
|
+
|
|
166
|
+
## 6. Basics of Working with Agents
|
|
167
|
+
|
|
168
|
+
### Automatic @manager Behavior
|
|
169
|
+
|
|
170
|
+
At the start of every session (when a conversation begins), agents will automatically:
|
|
171
|
+
|
|
172
|
+
1. Read `ENDERUN.md`
|
|
173
|
+
2. Read `PROJECT_MEMORY.md`
|
|
174
|
+
3. Load the active phase and current Trace ID
|
|
175
|
+
|
|
176
|
+
### How to Direct Specialist Agents
|
|
177
|
+
|
|
178
|
+
- Normally, **`@manager`** coordinates the process.
|
|
179
|
+
- If you need to address a specialist agent directly, include their tag:
|
|
180
|
+
|
|
181
|
+
```markdown
|
|
182
|
+
@backend Implement the user model and auth services using Kysely.
|
|
183
|
+
```
|
|
184
|
+
|
|
185
|
+
### Critical Rules
|
|
186
|
+
|
|
187
|
+
- Keep `docs/tech-stack.md` updated at all times.
|
|
188
|
+
- When new key decisions are made, update the **CRITICAL DECISIONS** table in `PROJECT_MEMORY.md`.
|
|
189
|
+
- Use a unique Trace ID for every task.
|
|
190
|
+
|
|
191
|
+
---
|
|
192
|
+
|
|
193
|
+
## 7. First Real-World Scenario Example
|
|
194
|
+
|
|
195
|
+
Try this quick workflow:
|
|
196
|
+
|
|
197
|
+
1. Populate `docs/tech-stack.md`
|
|
198
|
+
2. Write a simple requirement in `docs/project-docs.md`
|
|
199
|
+
3. Run the following command:
|
|
200
|
+
|
|
201
|
+
```bash
|
|
202
|
+
npx agent-enderun trace:new "User Registration and Login" backend P1
|
|
203
|
+
```
|
|
204
|
+
|
|
205
|
+
4. Then write to the assistant:
|
|
206
|
+
|
|
207
|
+
> @manager Please analyze this requirement and propose the backend architecture.
|
|
208
|
+
|
|
209
|
+
The agents will automatically:
|
|
210
|
+
- Scan your codebase
|
|
211
|
+
- Propose type contracts
|
|
212
|
+
- Scaffold code using blueprints if necessary
|
|
213
|
+
|
|
214
|
+
---
|
|
215
|
+
|
|
216
|
+
## 8. Common Mistakes and Tips
|
|
217
|
+
|
|
218
|
+
| Mistake | Consequence | Solution |
|
|
219
|
+
| :--- | :--- | :--- |
|
|
220
|
+
| Leaving `docs/tech-stack.md` empty | Agents will not know how to proceed | Ensure it is populated immediately |
|
|
221
|
+
| Prompting for direct code generation | Messy and unmonitored code | Always have `@manager` plan first |
|
|
222
|
+
| Not using Trace ID | Chaos and lost traceability | Use `trace:new` for every new feature |
|
|
223
|
+
| Not updating `PROJECT_MEMORY.md` | Agents remember old state | Update memory with every key decision |
|
|
224
|
+
|
|
225
|
+
---
|
|
226
|
+
|
|
227
|
+
## 9. Next Steps
|
|
228
|
+
|
|
229
|
+
After completing the guide, explore:
|
|
230
|
+
|
|
231
|
+
- **Contract-First Development** → Check `apps/backend/src/types`
|
|
232
|
+
- **Blueprint Scaffolding** → Look inside `.enderun/blueprints/`
|
|
233
|
+
- **Security & Compliance** → Run `npx agent-enderun check:security`
|
|
234
|
+
- **Inter-Agent Communication** → Hermes protocol (`messages/` directory)
|
|
235
|
+
|
|
236
|
+
---
|
|
237
|
+
|
|
238
|
+
## 10. Help and Support
|
|
239
|
+
|
|
240
|
+
If you encounter issues:
|
|
241
|
+
|
|
242
|
+
1. Run `npx agent-enderun status`
|
|
243
|
+
2. Check `PROJECT_MEMORY.md`
|
|
244
|
+
3. Inspect the error logs and the last 3 HISTORY entries
|
|
245
|
+
|
|
246
|
+
---
|
|
247
|
+
|
|
248
|
+
**Congratulations!** You can now develop software with discipline, structure, and governance using Agent Enderun.
|
|
249
|
+
|
|
250
|
+
As a next step, we recommend defining **the core contracts of your first real project**.
|
|
251
|
+
|
|
252
|
+
---
|
|
253
|
+
|
|
254
|
+
# Türkçe
|
|
255
|
+
|
|
256
|
+
Bu rehber, Agent Enderun'u **sıfırdan** yeni bir projeye kurmak isteyen geliştiriciler ve ekipler için hazırlanmıştır. Adım adım, net ve uygulanabilir şekilde anlatılmaktadır.
|
|
257
|
+
|
|
258
|
+
> **v0.6.5 itibarıyla önerilen birincil başlatma komutu:** **`npx agent-enderun init` (genel framework kurulumu)**
|
|
259
|
+
|
|
260
|
+
---
|
|
261
|
+
|
|
262
|
+
## 1. Giriş
|
|
263
|
+
|
|
264
|
+
Agent Enderun, yapay zeka destekli yazılım geliştirme süreçlerinde **kontrol, disiplin ve izlenebilirlik** sağlayan bir yönetişim framework'üdür.
|
|
265
|
+
|
|
266
|
+
Bu rehberi tamamladığınızda:
|
|
267
|
+
- Framework'ü projenize kurmuş olacaksınız
|
|
268
|
+
- Temel yapılandırmayı yapmış olacaksınız
|
|
269
|
+
- İlk görevinizi oluşturmuş ve ajanlarla çalışmaya başlamış olacaksınız
|
|
270
|
+
|
|
271
|
+
---
|
|
272
|
+
|
|
273
|
+
## 2. Ön Gereksinimler
|
|
274
|
+
|
|
275
|
+
- **Node.js** 20+ (LTS önerilir)
|
|
276
|
+
- **npm** 9+
|
|
277
|
+
- **Git** (proje klasöründe başlatılmış olmalı)
|
|
278
|
+
|
|
279
|
+
Kontrol etmek için:
|
|
280
|
+
|
|
281
|
+
```bash
|
|
282
|
+
node --version
|
|
283
|
+
npm --version
|
|
284
|
+
git --version
|
|
285
|
+
```
|
|
286
|
+
|
|
287
|
+
---
|
|
288
|
+
|
|
289
|
+
## 3. Adım Adım Kurulum
|
|
290
|
+
|
|
291
|
+
### Adım 1: Yeni Proje Klasörü Oluştur
|
|
292
|
+
|
|
293
|
+
```bash
|
|
294
|
+
mkdir my-new-project
|
|
295
|
+
cd my-new-project
|
|
296
|
+
git init
|
|
297
|
+
```
|
|
298
|
+
|
|
299
|
+
### Adım 2: Framework'ü Başlat
|
|
300
|
+
|
|
301
|
+
Temel framework yapısını temiz bir şekilde kurmak için (kurulumdan önce herhangi bir yapay zeka veya adaptör adı hardcode edilmeden):
|
|
302
|
+
|
|
303
|
+
```bash
|
|
304
|
+
npx agent-enderun init
|
|
305
|
+
```
|
|
306
|
+
|
|
307
|
+
Bu komut:
|
|
308
|
+
- Varsayılan olarak `.enderun/` klasörünü oluşturur
|
|
309
|
+
- Tüm yönetişim dosyalarını (`ENDERUN.md`, `PROJECT_MEMORY.md`, ajanlar, knowledge vb.) kurar
|
|
310
|
+
- Temel framework yapısını projenize ekler
|
|
311
|
+
|
|
312
|
+
#### 💡 İsteğe Bağlı: Özel Bir Adaptör ile Kurulum
|
|
313
|
+
Eğer belirli bir yapay zeka asistan ortamını veya adaptörünü (örneğin Antigravity, Claude, Cursor, Codex, Gemini) yapılandırmak istiyorsanız, bunu parametre olarak belirtebilirsiniz:
|
|
314
|
+
|
|
315
|
+
```bash
|
|
316
|
+
npx agent-enderun init antigravity
|
|
317
|
+
# veya
|
|
318
|
+
npx agent-enderun init claude
|
|
319
|
+
# veya
|
|
320
|
+
npx agent-enderun init cursor
|
|
321
|
+
# veya
|
|
322
|
+
npx agent-enderun init codex
|
|
323
|
+
# veya
|
|
324
|
+
npx agent-enderun init gemini
|
|
325
|
+
```
|
|
326
|
+
|
|
327
|
+
- Eğer `init antigravity` çalıştırırsanız, `.enderun/` yerine `.antigravitycli/` klasörünü oluşturur ve proje köküne `antigravity.md` ekler.
|
|
328
|
+
- Eğer `init claude` çalıştırırsanız, `.enderun/` yerine `.claude/` klasörünü oluşturur ve Claude Desktop MCP ayarlarını otomatik yapılandırır.
|
|
329
|
+
- Eğer `init cursor` çalıştırırsanız, `.cursor/` klasörünü oluşturur ve cursor kurallarını kopyalar.
|
|
330
|
+
- Eğer `init gemini` çalıştırırsanız, `.enderun/` yerine `.gemini/` klasörünü oluşturur ve proje köküne `gemini.md` ekler.
|
|
331
|
+
|
|
332
|
+
---
|
|
333
|
+
|
|
334
|
+
### Adım 3: Bağımlılıkları Yükle ve Derle
|
|
335
|
+
|
|
336
|
+
```bash
|
|
337
|
+
npm install
|
|
338
|
+
npm run enderun:build
|
|
339
|
+
```
|
|
340
|
+
|
|
341
|
+
### Adım 4: Kurulumu Doğrula
|
|
342
|
+
|
|
343
|
+
```bash
|
|
344
|
+
npx agent-enderun check
|
|
345
|
+
```
|
|
346
|
+
|
|
347
|
+
Beklenen çıktı:
|
|
348
|
+
|
|
349
|
+
```
|
|
350
|
+
✅ Framework active (v0.6.5)
|
|
351
|
+
✅ MCP Server ready
|
|
352
|
+
✅ Shared types compiled
|
|
353
|
+
✅ Agent logs initialized
|
|
354
|
+
✅ PROJECT_MEMORY.md found
|
|
355
|
+
```
|
|
356
|
+
|
|
357
|
+
---
|
|
358
|
+
|
|
359
|
+
## 4. Temel Yapılandırma (En Kritik Adım)
|
|
360
|
+
|
|
361
|
+
Framework kurulduktan sonra **mutlaka** aşağıdaki dosyaları doldurmalısınız.
|
|
362
|
+
|
|
363
|
+
### 4.1 `docs/tech-stack.md`
|
|
364
|
+
|
|
365
|
+
Bu dosya **zorunludur**. Ajanlar projenizin hangi teknolojileri kullandığını buradan öğrenir.
|
|
366
|
+
|
|
367
|
+
Örnek doldurma:
|
|
368
|
+
|
|
369
|
+
```markdown
|
|
370
|
+
# TECH STACK
|
|
371
|
+
|
|
372
|
+
## Platform
|
|
373
|
+
- Web (React + Vite)
|
|
374
|
+
- Backend (Node.js + Fastify)
|
|
375
|
+
|
|
376
|
+
## Database
|
|
377
|
+
- PostgreSQL + Kysely
|
|
378
|
+
|
|
379
|
+
## Auth
|
|
380
|
+
- JWT + Refresh Token
|
|
381
|
+
|
|
382
|
+
## Deployment
|
|
383
|
+
- Vercel (Frontend) + Railway (Backend)
|
|
384
|
+
```
|
|
385
|
+
|
|
386
|
+
> **Uyarı:** Bu dosya boş bırakılırsa ajanlar çalışamaz.
|
|
387
|
+
|
|
388
|
+
### 4.2 `docs/project-docs.md`
|
|
389
|
+
|
|
390
|
+
Projenizin amacını, hedef kitlesini ve ana gereksinimleri buraya yazın.
|
|
391
|
+
|
|
392
|
+
### 4.3 `.enderun/PROJECT_MEMORY.md`
|
|
393
|
+
|
|
394
|
+
İlk kurulumda otomatik oluşturulur. İçeriğini inceleyin. *(Not: Özel bir adaptör ile kurulum yaptıysanız bu dosya o adaptörün klasöründe olacaktır, örn. `.antigravitycli/PROJECT_MEMORY.md`)*
|
|
395
|
+
|
|
396
|
+
---
|
|
397
|
+
|
|
398
|
+
## 5. İlk Görev Oluşturma
|
|
399
|
+
|
|
400
|
+
Artık ilk gerçek görevinizi oluşturabilirsiniz:
|
|
401
|
+
|
|
402
|
+
```bash
|
|
403
|
+
npx agent-enderun trace:new "User Registration and Login System" backend P1
|
|
404
|
+
```
|
|
405
|
+
|
|
406
|
+
Bu komut:
|
|
407
|
+
- Yeni bir Trace ID üretir
|
|
408
|
+
- `PROJECT_MEMORY.md` içindeki **ACTIVE TASKS** bölümünü günceller
|
|
409
|
+
- @manager ajanını göreve atar
|
|
410
|
+
|
|
411
|
+
---
|
|
412
|
+
|
|
413
|
+
## 6. Ajanlarla Çalışma Temelleri
|
|
414
|
+
|
|
415
|
+
### Otomatik @manager Davranışı
|
|
416
|
+
|
|
417
|
+
Her yeni oturumda (sohbet başladığında) ajanlar otomatik olarak:
|
|
418
|
+
|
|
419
|
+
1. `ENDERUN.md` dosyasını okur
|
|
420
|
+
2. `PROJECT_MEMORY.md` dosyasını okur
|
|
421
|
+
3. Aktif fazı ve görevi öğrenir
|
|
422
|
+
|
|
423
|
+
### Ajanlara Nasıl Yönlendirilir?
|
|
424
|
+
|
|
425
|
+
- Normalde **@manager** her şeyi yönetir.
|
|
426
|
+
- İsterseniz doğrudan bir uzmana hitap edebilirsiniz:
|
|
427
|
+
|
|
428
|
+
```markdown
|
|
429
|
+
@backend Implement the user model and auth services using Kysely.
|
|
430
|
+
```
|
|
431
|
+
|
|
432
|
+
### Önemli Kurallar
|
|
433
|
+
|
|
434
|
+
- Her zaman `docs/tech-stack.md` dosyasını güncel tutun.
|
|
435
|
+
- Yeni kararlar aldığınızda `PROJECT_MEMORY.md` içindeki **CRITICAL DECISIONS** bölümünü güncelleyin.
|
|
436
|
+
- Her görev için Trace ID kullanın.
|
|
437
|
+
|
|
438
|
+
---
|
|
439
|
+
|
|
440
|
+
## 7. İlk Gerçek Senaryo Örneği
|
|
441
|
+
|
|
442
|
+
Aşağıdaki akışı deneyebilirsiniz:
|
|
443
|
+
|
|
444
|
+
1. `docs/tech-stack.md` dosyasını doldurun
|
|
445
|
+
2. `docs/project-docs.md` içine basit bir gereksinim yazın
|
|
446
|
+
3. Şu komutu çalıştırın:
|
|
447
|
+
|
|
448
|
+
```bash
|
|
449
|
+
npx agent-enderun trace:new "User Registration and Login" backend P1
|
|
450
|
+
```
|
|
451
|
+
|
|
452
|
+
4. Sonra şunu yazın:
|
|
453
|
+
|
|
454
|
+
> @manager Lütfen bu gereksinimi analiz et ve gerekli backend yapısını öner.
|
|
455
|
+
|
|
456
|
+
Ajanlar otomatik olarak:
|
|
457
|
+
- Kod analizi yapacak
|
|
458
|
+
- Kontrat önerecek
|
|
459
|
+
- Gerekirse blueprint kullanacak
|
|
460
|
+
|
|
461
|
+
---
|
|
462
|
+
|
|
463
|
+
## 8. Sık Yapılan Hatalar ve İpuçları
|
|
464
|
+
|
|
465
|
+
| Hata | Sonuç | Çözüm |
|
|
466
|
+
| :--- | :--- | :--- |
|
|
467
|
+
| `docs/tech-stack.md` dosyasını boş bırakmak | Ajanlar ne yapacağını bilemez | Mutlaka doldurun |
|
|
468
|
+
| Doğrudan kod yazdırmak | Düzensiz ve denetimsiz kod | Önce @manager ile plan yaptırın |
|
|
469
|
+
| Trace ID kullanmamak | İşler karışır | Her yeni özellik için `trace:new` kullanın |
|
|
470
|
+
| PROJECT_MEMORY.md'yi güncellememek | Ajanlar eski durumu hatırlar | Yeni kararları mutlaka yazın |
|
|
471
|
+
|
|
472
|
+
---
|
|
473
|
+
|
|
474
|
+
## 9. Sonraki Adımlar
|
|
475
|
+
|
|
476
|
+
Rehberi tamamladıktan sonra şu konuları inceleyin:
|
|
477
|
+
|
|
478
|
+
- **Contract-First Geliştirme** → `apps/backend/src/types` yapısını inceleyin
|
|
479
|
+
- **Blueprint Kullanımı** → `.enderun/blueprints/` klasörüne bakın
|
|
480
|
+
- **Güvenlik ve Denetim** → `npx agent-enderun check:security`
|
|
481
|
+
- **Ajanlar Arası İletişim** → Hermes protokolü (`messages/` klasörü)
|
|
482
|
+
|
|
483
|
+
---
|
|
484
|
+
|
|
485
|
+
## 10. Yardım ve Destek
|
|
486
|
+
|
|
487
|
+
Sorun yaşarsanız:
|
|
488
|
+
|
|
489
|
+
1. `npx agent-enderun status` komutunu çalıştırın
|
|
490
|
+
2. `PROJECT_MEMORY.md` dosyasını kontrol edin
|
|
491
|
+
3. Hata mesajlarını ve son 3 HISTORY girdisini inceleyin
|
|
492
|
+
|
|
493
|
+
---
|
|
494
|
+
|
|
495
|
+
**Tebrikler!** Artık Agent Enderun ile disiplinli ve yönetilebilir bir şekilde yazılım geliştirmeye başlayabilirsiniz.
|
|
496
|
+
|
|
497
|
+
Bir sonraki adım olarak **ilk gerçek projenizin temel kontratlarını** tanımlamayı öneririz.
|
package/docs/roadmap.md
ADDED
|
@@ -0,0 +1,200 @@
|
|
|
1
|
+
# Agent Enderun — Development Roadmap (v0.6.5+) / Geliştirme Yol Haritası
|
|
2
|
+
|
|
3
|
+
**Last Updated / Son Güncelleme:** 23 May 2026 / 23 Mayıs 2026
|
|
4
|
+
**Owner / Sorumlu:** @manager
|
|
5
|
+
|
|
6
|
+
[English](#english) | [Türkçe](#türkçe)
|
|
7
|
+
|
|
8
|
+
---
|
|
9
|
+
|
|
10
|
+
# English
|
|
11
|
+
|
|
12
|
+
This document outlines the development roadmap for the Agent Enderun framework **v0.6.5 and beyond**. All items are prioritized logically based on actual project needs and corporate governance principles.
|
|
13
|
+
|
|
14
|
+
## Current Status (23 May 2026)
|
|
15
|
+
|
|
16
|
+
- **Version:** v0.6.5 (ready for npm release)
|
|
17
|
+
- **System Health:** 🟢 GREEN
|
|
18
|
+
- **Key Accomplishments:**
|
|
19
|
+
- Full support for the Antigravity adapter (primary recommended adapter)
|
|
20
|
+
- Gemini adapter completely removed
|
|
21
|
+
- Lint technical debt resolved (reduced from 43 to 0 issues)
|
|
22
|
+
- Published `docs/getting-started.md` guide
|
|
23
|
+
- Updated memory structures and workspace hygiene
|
|
24
|
+
|
|
25
|
+
- **Active Challenge:** Memory and task tracking need reinforcement (ACTIVE TASKS section is empty)
|
|
26
|
+
|
|
27
|
+
---
|
|
28
|
+
|
|
29
|
+
## Agent Maturity & Professionalization Program (Highest Strategic Initiative)
|
|
30
|
+
|
|
31
|
+
To make Agent Enderun truly production-grade for enterprise use, agents must be professionalized to meet the standards of senior software engineers.
|
|
32
|
+
|
|
33
|
+
This program systematically audits current agent maturity levels and runs structured improvements to elevate each agent to enterprise readiness.
|
|
34
|
+
|
|
35
|
+
### Agent Maturity Targets
|
|
36
|
+
|
|
37
|
+
| Agent Persona | Current Level | Target Level | Priority / Risk Status |
|
|
38
|
+
| :--- | :--- | :--- | :--- |
|
|
39
|
+
| **@manager** | 8.0 | 9.5 | High / Stable. Leadership and project management capabilities are excellent. |
|
|
40
|
+
| **@backend** | 7.5 | 9.0 | High / Stable. Deeply understands Kysely and Fastify patterns; testing discipline needs reinforcement. |
|
|
41
|
+
| **@frontend** | 6.5 | 9.0 | **Critical / High Risk**. Needs major reinforcement in component slots, composition patterns, WCAG 2.2 accessibility, and performance engineering. |
|
|
42
|
+
| **@explorer** | 6.5 | 8.5 | High / Stable. Highly capable in dependency analysis and codebase intelligence. |
|
|
43
|
+
| **@analyst** | 6.5 | 8.5 | Medium / Stable. Handles system health metrics and compliance audits. |
|
|
44
|
+
| **@git** | 6.0 | 8.0 | Medium / Stable. Coordinates PRs, semantic commits, and version compliance. |
|
|
45
|
+
| **@mobile & @native** | 2.0 | 7.5 | Low / Draft state. Currently stubbed and requires dedicated maturity runs. |
|
|
46
|
+
|
|
47
|
+
> **Note:** `@frontend` is currently the highest risk to enterprise onboarding and is the top priority.
|
|
48
|
+
|
|
49
|
+
---
|
|
50
|
+
|
|
51
|
+
## Roadmap Overview
|
|
52
|
+
|
|
53
|
+
| Phase | Timeline | Focus | Priority |
|
|
54
|
+
| :--- | :--- | :--- | :--- |
|
|
55
|
+
| **Agent Maturity Program** | 1–4 Months | Elevate all agents to professional enterprise-grade | **Highest** |
|
|
56
|
+
| **Phase 1** | 1–6 Weeks | Usability, automated configurations, and CLI tooling | High |
|
|
57
|
+
| **Phase 2** | 1–3 Months | Hermes messaging stability & multi-agent intelligence | High |
|
|
58
|
+
| **Phase 3** | 3+ Months | Scalability, performance benchmarks, and Reference Application | Medium |
|
|
59
|
+
|
|
60
|
+
---
|
|
61
|
+
|
|
62
|
+
## Agent Maturity Program — Phase 1 (Weeks 1–8)
|
|
63
|
+
|
|
64
|
+
### 1. Professionalize @frontend Agent (Critical)
|
|
65
|
+
- Component Architecture (Compound Components, Slots, Composition Patterns)
|
|
66
|
+
- Accessibility (WCAG 2.2 AA compliance standards)
|
|
67
|
+
- Performance Engineering (Core Web Vitals, virtualization, code splitting)
|
|
68
|
+
- Testing Strategy (Hook + Component + Integration testing)
|
|
69
|
+
- Error Boundaries & Resilience
|
|
70
|
+
- Design System Governance
|
|
71
|
+
|
|
72
|
+
### 2. Reinforce @backend Agent
|
|
73
|
+
- Production Testing Culture (Unit + Integration + Contract + E2E)
|
|
74
|
+
- Observability (Structured Logging + Metrics + Tracing)
|
|
75
|
+
- Resilience Patterns (Idempotency, Retry, Circuit Breaker)
|
|
76
|
+
- Query Optimization and Caching Strategy
|
|
77
|
+
|
|
78
|
+
### 3. Elevate @manager Leadership
|
|
79
|
+
- Technical Debt Auditing & Escalation Register
|
|
80
|
+
- Risk Assessment Framework
|
|
81
|
+
- Capacity Planning & Sustainable Delivery
|
|
82
|
+
- Architecture Decision Records (ADR) Discipline
|
|
83
|
+
|
|
84
|
+
---
|
|
85
|
+
|
|
86
|
+
## Phase 1 — Short-Term (Weeks 1–6)
|
|
87
|
+
|
|
88
|
+
### 1. Fully Automate Claude Configuration
|
|
89
|
+
- **Description:** Remove the manual `claude config add` step after running `init claude`. Automatically patch the Claude Desktop configuration file.
|
|
90
|
+
- **Complexity:** Medium
|
|
91
|
+
- **Status:** Pending
|
|
92
|
+
|
|
93
|
+
### 2. Frontend Blueprint System
|
|
94
|
+
- **Description:** Carry the blueprint generator power of the backend over to the frontend. Establish structured React components, pages, and UI pattern blueprints.
|
|
95
|
+
- **Complexity:** Medium-High
|
|
96
|
+
- **Status:** Pending
|
|
97
|
+
|
|
98
|
+
### 3. Expand Getting Started Documentation
|
|
99
|
+
- **Description:** Enrich the new guide based on developer feedback. Add more real-world scenarios, troubleshooting tips, and best practices.
|
|
100
|
+
- **Complexity:** Low-Medium
|
|
101
|
+
- **Status:** In Progress (Getting started guide updated to v0.6.5)
|
|
102
|
+
|
|
103
|
+
---
|
|
104
|
+
|
|
105
|
+
## Phase 2 — Mid-Term (Months 1–3)
|
|
106
|
+
|
|
107
|
+
### 4. Fully Implement Hermes Messaging Protocol
|
|
108
|
+
- **Description:** Move inter-agent categorized, prioritized, and persistent messaging protocol from "defined on paper" to active code implementation.
|
|
109
|
+
- **Complexity:** High
|
|
110
|
+
- **Status:** Draft defined; implementation pending
|
|
111
|
+
|
|
112
|
+
### 5. Reinforce Academy & Performance System
|
|
113
|
+
- **Description:** Aggregate success metrics, failure tracking, and structured feedback for all agents to report via dashboard.
|
|
114
|
+
- **Complexity:** Medium-High
|
|
115
|
+
- **Status:** Basic tools available; scaling required
|
|
116
|
+
|
|
117
|
+
---
|
|
118
|
+
|
|
119
|
+
## Phase 3 — Long-Term (Months 3+)
|
|
120
|
+
|
|
121
|
+
### 6. Production-Grade Reference Application
|
|
122
|
+
- **Description:** Build a complete end-to-end reference application demonstrating normal CRUD + High-Risk Admin actions + Hermes messaging under Agent Enderun's governance.
|
|
123
|
+
- **Complexity:** Very High
|
|
124
|
+
- **Status:** Planned
|
|
125
|
+
|
|
126
|
+
---
|
|
127
|
+
|
|
128
|
+
# Türkçe
|
|
129
|
+
|
|
130
|
+
Bu belge, Agent Enderun framework'ünün **v0.6.5 sonrası** geliştirme yol haritasını içerir. Tüm maddeler gerçekçi öncelik sırasına göre düzenlenmiştir.
|
|
131
|
+
|
|
132
|
+
## Mevcut Durum (23 Mayıs 2026)
|
|
133
|
+
|
|
134
|
+
- **Versiyon:** v0.6.5 (npm yayınına hazır)
|
|
135
|
+
- **Sistem Sağlığı:** 🟢 GREEN
|
|
136
|
+
- **Tamamlanan Önemli İşler:**
|
|
137
|
+
- Antigravity adapter tam desteği (birincil adapter)
|
|
138
|
+
- Gemini adapter tamamen kaldırıldı
|
|
139
|
+
- Lint teknik borcu temizlendi (43 → 0 problem)
|
|
140
|
+
- `docs/getting-started.md` rehberi yayınlandı
|
|
141
|
+
- Hafıza ve proje hijyeni güncellendi
|
|
142
|
+
|
|
143
|
+
- **Aktif Sorun:** Hafıza ve görev takibi takviye edilmeli (ACTIVE TASKS bölümü boş)
|
|
144
|
+
|
|
145
|
+
---
|
|
146
|
+
|
|
147
|
+
## Agent Olgunluk ve Profesyonelleşme Programı (En Kritik Stratejik İnisiyatif)
|
|
148
|
+
|
|
149
|
+
Agent Enderun’un kurumsal ve büyük ölçekli projelerde gerçekten kullanılabilir hale gelmesi için ajanların **kıdemli yazılım mühendisi** seviyesine çıkarılması zorunludur.
|
|
150
|
+
|
|
151
|
+
Bu program, mevcut ajanların olgunluk seviyelerini analiz edip her birini sistematik şekilde profesyonel/kurumsal seviyeye taşımayı hedefler.
|
|
152
|
+
|
|
153
|
+
### Ajan Olgunluk Hedefleri
|
|
154
|
+
|
|
155
|
+
| Ajan Personası | Mevcut Seviye | Hedef Seviye | Öncelik / Risk Durumu |
|
|
156
|
+
| :--- | :--- | :--- | :--- |
|
|
157
|
+
| **@manager** | 8.0 | 9.5 | Yüksek / İstikrarlı. Yönetim yeteneği güçlüdür. |
|
|
158
|
+
| **@backend** | 7.5 | 9.0 | Yüksek / Kararlı. Kysely ve Fastify kalıplarını iyi bilir, test yazımı güçlendirilmelidir. |
|
|
159
|
+
| **@frontend** | 6.5 | 9.0 | **Kritik / Yüksek Risk**. Bileşen taslakları, slots, composition pattern'leri, WCAG 2.2 erişilebilirlik ve performans mühendisliğinde büyük takviye gereklidir. |
|
|
160
|
+
| **@explorer** | 6.5 | 8.5 | Yüksek / Bağımlılık analizi ve kod zekasında yetkindir. |
|
|
161
|
+
| **@analyst** | 6.5 | 8.5 | Orta / Sağlık metrikleri ve uygunluk denetiminde rol alır. |
|
|
162
|
+
| **@git** | 6.0 | 8.0 | Orta / PR ve versiyon takibini koordine eder. |
|
|
163
|
+
| **@mobile & @native** | 2.0 | 7.5 | Düşük / Taslak halinde; olgunlaşması gerekecektir. |
|
|
164
|
+
|
|
165
|
+
> **Not:** `@frontend` şu anda kurumsal entegrasyonun önündeki en büyük risktir ve birinci önceliğimizdir.
|
|
166
|
+
|
|
167
|
+
---
|
|
168
|
+
|
|
169
|
+
## Yol Haritası Genel Bakış
|
|
170
|
+
|
|
171
|
+
| Faz | Zaman Dilimi | Odak | Öncelik |
|
|
172
|
+
| :--- | :--- | :--- | :--- |
|
|
173
|
+
| **Agent Maturity Program** | 1–4 Ay | Tüm ajanları profesyonel kurumsal seviyeye çıkarma | **En Yüksek** |
|
|
174
|
+
| **Phase 1** | 1–6 Hafta | Temel Kullanılabilirlik + Otomasyon + CLI | Yüksek |
|
|
175
|
+
| **Phase 2** | 1–3 Ay | Zeka ve Hermes Protokol Olgunluğu | Yüksek |
|
|
176
|
+
| **Phase 3** | 3+ Ay | Ölçeklenebilirlik ve Referans Uygulama | Orta |
|
|
177
|
+
|
|
178
|
+
---
|
|
179
|
+
|
|
180
|
+
## Agent Maturity Program — Phase 1 (1–8 Hafta)
|
|
181
|
+
|
|
182
|
+
### 1. @frontend Ajanının Profesyonelleşmesi (Kritik)
|
|
183
|
+
- Component Architecture (Compound Components, Slots, Composition Patterns)
|
|
184
|
+
- Accessibility (WCAG 2.2 AA standartları)
|
|
185
|
+
- Performance Engineering (Core Web Vitals, virtualization, code splitting)
|
|
186
|
+
- Testing Strategy (Hook + Component + Integration test)
|
|
187
|
+
- Error Boundaries & Resilience
|
|
188
|
+
- Design System Governance
|
|
189
|
+
|
|
190
|
+
### 2. @backend Ajanının Güçlendirilmesi
|
|
191
|
+
- Profesyonel Test Kültürü (Unit + Integration + Contract + E2E)
|
|
192
|
+
- Observability (Structured Logging + Metrics + Tracing)
|
|
193
|
+
- Resilience Patterns (Idempotency, Retry, Circuit Breaker)
|
|
194
|
+
- Query Optimization ve Caching Stratejisi
|
|
195
|
+
|
|
196
|
+
### 3. @manager Ajanının Liderlik Seviyesinin Yükseltilmesi
|
|
197
|
+
- Teknik Borç Yönetimi ve Kayıt Sistemi
|
|
198
|
+
- Risk Değerlendirme Çerçevesi
|
|
199
|
+
- Kapasite Planlaması ve Sürdürülebilir Teslimat
|
|
200
|
+
- Architecture Decision Records (ADR) Disiplini
|
package/framework-mcp/README.md
CHANGED
|
File without changes
|