release: version 0.6.5 🚀

HISTORY.md

@@ -4,6 +4,60 @@ Changelog
 
 (unreleased)
 ------------
+
+Fix
+~~~
+- Better n8n workflow, refs NOISSUE. [Simon Diesenreiter]
+
+
+0.6.4 (2026-04-10)
+------------------
+
+Fix
+~~~
+- Add Telegram helper functions, refs NOISSUE. [Simon Diesenreiter]
+
+Other
+~~~~~
+
+
+0.6.3 (2026-04-10)
+------------------
+
+Fix
+~~~
+- N8n workflow generation, refs NOISSUE. [Simon Diesenreiter]
+
+Other
+~~~~~
+
+
+0.6.2 (2026-04-10)
+------------------
+
+Fix
+~~~
+- Fix Quasar layout issues, refs NOISSUE. [Simon Diesenreiter]
+
+Other
+~~~~~
+
+
+0.6.1 (2026-04-10)
+------------------
+
+Fix
+~~~
+- Fix commit for version push, refs NOISSUE. [Simon Diesenreiter]
+
+Other
+~~~~~
+- Chore: add more health info for n8n, refs NOISSUE. [Simon
+  Diesenreiter]
+
+
+0.6.0 (2026-04-10)
+------------------
 - Feat(api): expose database target in health refs NOISSUE. [Simon
   Diesenreiter]
 - Fix(db): prefer postgres config in production refs NOISSUE. [Simon

README.md

@@ -86,11 +86,14 @@ docker-compose up -d
 1. **Send a request via Telegram:**
 
    ```
-   Name: My Awesome App
-   Description: A web application for managing tasks
-   Features: user authentication, task CRUD, notifications
+   Build an internal task management app for our operations team.
+   It should support user authentication, task CRUD, notifications, and reporting.
+   Prefer FastAPI with PostgreSQL and a simple web dashboard.
    ```
 
+   The backend now interprets free-form Telegram text with Ollama before generation.
+   If `TELEGRAM_CHAT_ID` is set, the Telegram-trigger workflow only reacts to messages from that specific chat.
+
 2. **Monitor progress via Web UI:**
 
    Open `http://yourserver:8000/` to see the dashboard and `http://yourserver:8000/api` for API metadata
@@ -109,6 +112,7 @@ If you deploy the container with PostgreSQL environment variables set, the servi
 | `/api` | GET | API information |
 | `/health` | GET | Health check |
 | `/generate` | POST | Generate new software |
+| `/generate/text` | POST | Interpret free-form text and generate software |
 | `/status/{project_id}` | GET | Get project status |
 | `/projects` | GET | List all projects |
 

ai_software_factory/VERSION

@@ -1 +1 @@
-0.6.0
+0.6.5

ai_software_factory/agents/n8n_setup.py

@@ -1,6 +1,8 @@
 """n8n setup agent for automatic webhook configuration."""
 
 import json
+from urllib import error as urllib_error
+from urllib import request as urllib_request
 from typing import Optional
 
 try:
@@ -46,6 +48,113 @@ class N8NSetupAgent:
             headers["X-N8N-API-KEY"] = self.webhook_token
         return headers
 
+    def _extract_message(self, payload: object) -> str:
+        """Extract a useful message from an n8n response payload."""
+        if isinstance(payload, dict):
+            for key in ("message", "error", "reason", "hint", "text"):
+                value = payload.get(key)
+                if value:
+                    return str(value)
+            if payload:
+                return json.dumps(payload)
+        if payload is None:
+            return "No response body"
+        return str(payload)
+
+    def _normalize_success(self, method: str, url: str, status_code: int, payload: object) -> dict:
+        """Normalize a successful n8n API response."""
+        if isinstance(payload, dict):
+            response = dict(payload)
+            response.setdefault("status_code", status_code)
+            response.setdefault("url", url)
+            response.setdefault("method", method)
+            return response
+        return {"data": payload, "status_code": status_code, "url": url, "method": method}
+
+    def _normalize_error(self, method: str, url: str, status_code: int | None, payload: object) -> dict:
+        """Normalize an error response with enough detail for diagnostics."""
+        message = self._extract_message(payload)
+        prefix = f"{method} {url}"
+        if status_code is not None:
+            return {
+                "error": f"{prefix} returned {status_code}: {message}",
+                "message": message,
+                "status_code": status_code,
+                "url": url,
+                "method": method,
+                "payload": payload,
+            }
+        return {
+            "error": f"{prefix} failed: {message}",
+            "message": message,
+            "status_code": None,
+            "url": url,
+            "method": method,
+            "payload": payload,
+        }
+
+    def _health_check_row(self, name: str, result: dict) -> dict:
+        """Convert a raw request result into a UI/API-friendly health check row."""
+        return {
+            "name": name,
+            "ok": not bool(result.get("error")),
+            "url": result.get("url"),
+            "method": result.get("method", "GET"),
+            "status_code": result.get("status_code"),
+            "message": result.get("message") or ("ok" if not result.get("error") else result.get("error")),
+        }
+
+    def _health_suggestion(self, checks: list[dict]) -> str | None:
+        """Return a suggestion based on failed n8n health checks."""
+        status_codes = {check.get("status_code") for check in checks if check.get("status_code") is not None}
+        if status_codes and status_codes.issubset({404}):
+            return "Verify N8N_API_URL points to the base n8n URL, for example http://host:5678, not /api/v1 or a webhook URL."
+        if status_codes & {401, 403}:
+            return "Check the configured n8n API key or authentication method."
+        return "Verify the n8n URL, API key, and that the n8n API is reachable from this container."
+
+    def _build_health_result(self, healthz_result: dict, workflows_result: dict) -> dict:
+        """Build a consolidated health result from the performed checks."""
+        checks = [
+            self._health_check_row("healthz", healthz_result),
+            self._health_check_row("workflows", workflows_result),
+        ]
+
+        if not healthz_result.get("error"):
+            return {
+                "status": "ok",
+                "message": "n8n is reachable via /healthz.",
+                "api_url": self.api_url,
+                "auth_configured": bool(self.webhook_token),
+                "checked_via": "healthz",
+                "checks": checks,
+            }
+
+        if not workflows_result.get("error"):
+            workflows = workflows_result.get("data")
+            workflow_count = len(workflows) if isinstance(workflows, list) else None
+            return {
+                "status": "ok",
+                "message": "n8n is reachable via the workflows API, but /healthz is unavailable.",
+                "api_url": self.api_url,
+                "auth_configured": bool(self.webhook_token),
+                "checked_via": "workflows",
+                "workflow_count": workflow_count,
+                "checks": checks,
+            }
+
+        suggestion = self._health_suggestion(checks)
+        return {
+            "status": "error",
+            "error": "n8n health checks failed",
+            "message": "n8n health checks failed.",
+            "api_url": self.api_url,
+            "auth_configured": bool(self.webhook_token),
+            "checked_via": "none",
+            "checks": checks,
+            "suggestion": suggestion,
+        }
+
     async def _request(self, method: str, path: str, **kwargs) -> dict:
         """Send a request to n8n and normalize the response."""
         import aiohttp
@@ -62,15 +171,42 @@ class N8NSetupAgent:
                         payload = {"text": await resp.text()}
 
                     if 200 <= resp.status < 300:
-                        if isinstance(payload, dict):
-                            payload.setdefault("status_code", resp.status)
-                            return payload
-                        return {"data": payload, "status_code": resp.status}
+                        return self._normalize_success(method, url, resp.status, payload)
 
-                    message = payload.get("message") if isinstance(payload, dict) else str(payload)
-                    return {"error": f"Status {resp.status}: {message}", "status_code": resp.status, "payload": payload}
+                    return self._normalize_error(method, url, resp.status, payload)
         except Exception as e:
-            return {"error": str(e)}
+            return self._normalize_error(method, url, None, {"message": str(e)})
+
+    def _request_sync(self, method: str, path: str, **kwargs) -> dict:
+        """Send a synchronous request to n8n for dashboard health snapshots."""
+        headers = kwargs.pop("headers", None) or self.get_auth_headers()
+        payload = kwargs.pop("json", None)
+        timeout = kwargs.pop("timeout", 5)
+        url = self._api_path(path)
+        data = None
+        if payload is not None:
+            data = json.dumps(payload).encode("utf-8")
+        req = urllib_request.Request(url, data=data, headers=headers, method=method)
+        try:
+            with urllib_request.urlopen(req, timeout=timeout) as resp:
+                raw_body = resp.read().decode("utf-8")
+                content_type = resp.headers.get("Content-Type", "")
+                if "application/json" in content_type and raw_body:
+                    parsed = json.loads(raw_body)
+                elif raw_body:
+                    parsed = {"text": raw_body}
+                else:
+                    parsed = {}
+                return self._normalize_success(method, url, resp.status, parsed)
+        except urllib_error.HTTPError as exc:
+            raw_body = exc.read().decode("utf-8") if exc.fp else ""
+            try:
+                parsed = json.loads(raw_body) if raw_body else {}
+            except json.JSONDecodeError:
+                parsed = {"text": raw_body} if raw_body else {}
+            return self._normalize_error(method, url, exc.code, parsed)
+        except Exception as exc:
+            return self._normalize_error(method, url, None, {"message": str(exc)})
     
     async def get_workflow(self, workflow_name: str) -> Optional[dict]:
         """Get a workflow by name."""
@@ -84,11 +220,31 @@ class N8NSetupAgent:
     
     async def create_workflow(self, workflow_json: dict) -> dict:
         """Create or update a workflow."""
-        return await self._request("POST", "workflows", json=workflow_json)
+        return await self._request("POST", "workflows", json=self._workflow_payload(workflow_json))
+
+    def _workflow_payload(self, workflow_json: dict) -> dict:
+        """Return a workflow payload without server-managed read-only fields."""
+        payload = dict(workflow_json)
+        payload.pop("active", None)
+        payload.pop("id", None)
+        payload.pop("createdAt", None)
+        payload.pop("updatedAt", None)
+        payload.pop("versionId", None)
+        return payload
+
+    async def _update_workflow_via_put(self, workflow_id: str, workflow_json: dict) -> dict:
+        """Fallback update path for n8n instances that only support PUT."""
+        return await self._request("PUT", f"workflows/{workflow_id}", json=self._workflow_payload(workflow_json))
 
     async def update_workflow(self, workflow_id: str, workflow_json: dict) -> dict:
         """Update an existing workflow."""
-        return await self._request("PATCH", f"workflows/{workflow_id}", json=workflow_json)
+        result = await self._request("PATCH", f"workflows/{workflow_id}", json=self._workflow_payload(workflow_json))
+        if result.get("status_code") == 405:
+            fallback = await self._update_workflow_via_put(workflow_id, workflow_json)
+            if not fallback.get("error") and isinstance(fallback, dict):
+                fallback.setdefault("method", "PUT")
+            return fallback
+        return result
     
     async def enable_workflow(self, workflow_id: str) -> dict:
         """Enable a workflow."""
@@ -96,6 +252,11 @@ class N8NSetupAgent:
         if result.get("error"):
             fallback = await self._request("PATCH", f"workflows/{workflow_id}", json={"active": True})
             if fallback.get("error"):
+                if fallback.get("status_code") == 405:
+                    put_fallback = await self._request("PUT", f"workflows/{workflow_id}", json={"active": True})
+                    if put_fallback.get("error"):
+                        return put_fallback
+                    return {"success": True, "id": workflow_id, "method": "put"}
                 return fallback
             return {"success": True, "id": workflow_id, "method": "patch"}
         return {"success": True, "id": workflow_id, "method": "activate"}
@@ -114,12 +275,12 @@ class N8NSetupAgent:
                     return value
         return []
 
-    def build_telegram_workflow(self, webhook_path: str, backend_url: str) -> dict:
+    def build_telegram_workflow(self, webhook_path: str, backend_url: str, allowed_chat_id: str | None = None) -> dict:
         """Build the Telegram-to-backend workflow definition."""
         normalized_path = webhook_path.strip().strip("/") or "telegram"
+        allowed_chat = json.dumps(str(allowed_chat_id)) if allowed_chat_id else "''"
         return {
             "name": "Telegram to AI Software Factory",
-            "active": False,
             "settings": {"executionOrder": "v1"},
             "nodes": [
                 {
@@ -137,13 +298,13 @@ class N8NSetupAgent:
                 },
                 {
                     "id": "parse-node",
-                    "name": "Prepare Software Request",
+                    "name": "Prepare Freeform Request",
                     "type": "n8n-nodes-base.code",
                     "typeVersion": 2,
                     "position": [-200, 120],
                     "parameters": {
                         "language": "javaScript",
-                        "jsCode": "const body = $json.body ?? $json;\nconst message = body.message ?? body;\nconst text = String(message.text ?? '').trim();\nconst lines = text.split(/\\r?\\n/);\nconst request = { name: null, description: '', features: [], tech_stack: [] };\nlet nameIndex = -1;\nlet featuresIndex = -1;\nlet techIndex = -1;\nfor (let i = 0; i < lines.length; i += 1) {\n  const line = lines[i].trim();\n  if (line.toLowerCase().startsWith('name:')) { request.name = line.split(':', 2)[1]?.trim() || null; nameIndex = i; }\n  if (line.toLowerCase().startsWith('features:') && featuresIndex === -1) { featuresIndex = i; }\n  if (line.toLowerCase().startsWith('tech stack:') && techIndex === -1) { techIndex = i; }\n}\nif (nameIndex >= 0) {\n  const descriptionEnd = featuresIndex >= 0 ? featuresIndex : (techIndex >= 0 ? techIndex : lines.length);\n  request.description = lines.slice(nameIndex + 1, descriptionEnd).join('\\n').replace(/^description:\\s*/i, '').trim();\n}\nfunction collectList(startIndex, fieldName) {\n  if (startIndex < 0) return;\n  const firstLine = lines[startIndex].split(':').slice(1).join(':').trim();\n  if (firstLine && !firstLine.startsWith('-') && !firstLine.startsWith('*')) {\n    request[fieldName].push(...firstLine.split(',').map(item => item.trim()).filter(Boolean));\n  }\n  for (const rawLine of lines.slice(startIndex + 1)) {\n    const line = rawLine.trim();\n    if (!line) continue;\n    if (/^[A-Za-z ]+:/.test(line)) break;\n    if (line.startsWith('-') || line.startsWith('*')) {\n      const value = line.slice(1).trim();\n      if (value) request[fieldName].push(value);\n    }\n  }\n}\ncollectList(featuresIndex, 'features');\ncollectList(techIndex, 'tech_stack');\nif (!request.name || request.features.length === 0) { throw new Error('Could not parse software request from Telegram message'); }\nreturn [{ json: { ...request, _source: { raw_text: text, chat_id: message.chat?.id ?? null } } }];",
+                        "jsCode": f"const allowedChatId = {allowed_chat};\nconst body = $json.body ?? $json;\nconst message = body.message ?? body;\nconst text = String(message.text ?? '').trim();\nconst chatId = String(message.chat?.id ?? '');\nif (allowedChatId && chatId !== allowedChatId) {{\n  return [{{ json: {{ ignored: true, message: `Ignoring message from chat ${{chatId}}`, prompt_text: text, source: 'telegram', chat_id: chatId, chat_type: message.chat?.type ?? null }} }}];\n}}\nreturn [{{ json: {{ prompt_text: text, source: 'telegram', chat_id: chatId, chat_type: message.chat?.type ?? null }} }}];",
                     },
                 },
                 {
@@ -174,8 +335,8 @@ class N8NSetupAgent:
                 },
             ],
             "connections": {
-                "Telegram Webhook": {"main": [[{"node": "Prepare Software Request", "type": "main", "index": 0}]]},
-                "Prepare Software Request": {"main": [[{"node": "AI Software Factory API", "type": "main", "index": 0}]]},
+                "Telegram Webhook": {"main": [[{"node": "Prepare Freeform Request", "type": "main", "index": 0}]]},
+                "Prepare Freeform Request": {"main": [[{"node": "AI Software Factory API", "type": "main", "index": 0}]]},
                 "AI Software Factory API": {"main": [[{"node": "Respond to Telegram Webhook", "type": "main", "index": 0}]]},
             },
         }
@@ -184,11 +345,12 @@ class N8NSetupAgent:
         self,
         backend_url: str,
         credential_name: str,
+        allowed_chat_id: str | None = None,
     ) -> dict:
         """Build a production Telegram Trigger based workflow."""
+        allowed_chat = json.dumps(str(allowed_chat_id)) if allowed_chat_id else "''"
         return {
             "name": "Telegram to AI Software Factory",
-            "active": False,
             "settings": {"executionOrder": "v1"},
             "nodes": [
                 {
@@ -201,14 +363,14 @@ class N8NSetupAgent:
                     "credentials": {"telegramApi": {"name": credential_name}},
                 },
                 {
-                    "id": "parse-node",
-                    "name": "Prepare Software Request",
+                    "id": "filter-node",
+                    "name": "Prepare Freeform Request",
                     "type": "n8n-nodes-base.code",
                     "typeVersion": 2,
                     "position": [-180, 120],
                     "parameters": {
                         "language": "javaScript",
-                        "jsCode": "const message = $json.message ?? $json;\nconst text = String(message.text ?? '').trim();\nconst lines = text.split(/\\r?\\n/);\nconst request = { name: null, description: '', features: [], tech_stack: [], _source: { raw_text: text, chat_id: message.chat?.id ?? null } };\nlet nameIndex = -1;\nlet featuresIndex = -1;\nlet techIndex = -1;\nfor (let i = 0; i < lines.length; i += 1) {\n  const line = lines[i].trim();\n  if (line.toLowerCase().startsWith('name:')) { request.name = line.split(':', 2)[1]?.trim() || null; nameIndex = i; }\n  if (line.toLowerCase().startsWith('features:') && featuresIndex === -1) { featuresIndex = i; }\n  if (line.toLowerCase().startsWith('tech stack:') && techIndex === -1) { techIndex = i; }\n}\nif (nameIndex >= 0) {\n  const descriptionEnd = featuresIndex >= 0 ? featuresIndex : (techIndex >= 0 ? techIndex : lines.length);\n  request.description = lines.slice(nameIndex + 1, descriptionEnd).join('\\n').replace(/^description:\\s*/i, '').trim();\n}\nfunction collectList(startIndex, fieldName) {\n  if (startIndex < 0) return;\n  const firstLine = lines[startIndex].split(':').slice(1).join(':').trim();\n  if (firstLine && !firstLine.startsWith('-') && !firstLine.startsWith('*')) {\n    request[fieldName].push(...firstLine.split(',').map(item => item.trim()).filter(Boolean));\n  }\n  for (const rawLine of lines.slice(startIndex + 1)) {\n    const line = rawLine.trim();\n    if (!line) continue;\n    if (/^[A-Za-z ]+:/.test(line)) break;\n    if (line.startsWith('-') || line.startsWith('*')) {\n      const value = line.slice(1).trim();\n      if (value) request[fieldName].push(value);\n    }\n  }\n}\ncollectList(featuresIndex, 'features');\ncollectList(techIndex, 'tech_stack');\nif (!request.name || request.features.length === 0) { throw new Error('Could not parse software request from Telegram message'); }\nreturn [{ json: request }];",
+                        "jsCode": f"const allowedChatId = {allowed_chat};\nconst message = $json.message ?? $json;\nconst text = String(message.text ?? '').trim();\nconst chatId = String(message.chat?.id ?? '');\nif (!text) return [];\nif (allowedChatId && chatId !== allowedChatId) return [];\nreturn [{{ json: {{ prompt_text: text, source: 'telegram', chat_id: chatId, chat_type: message.chat?.type ?? null }} }}];",
                     },
                 },
                 {
@@ -242,8 +404,8 @@ class N8NSetupAgent:
                 },
             ],
             "connections": {
-                "Telegram Trigger": {"main": [[{"node": "Prepare Software Request", "type": "main", "index": 0}]]},
-                "Prepare Software Request": {"main": [[{"node": "AI Software Factory API", "type": "main", "index": 0}]]},
+                "Telegram Trigger": {"main": [[{"node": "Prepare Freeform Request", "type": "main", "index": 0}]]},
+                "Prepare Freeform Request": {"main": [[{"node": "AI Software Factory API", "type": "main", "index": 0}]]},
                 "AI Software Factory API": {"main": [[{"node": "Send Telegram Update", "type": "main", "index": 0}]]},
             },
         }
@@ -297,19 +459,21 @@ class N8NSetupAgent:
         """
         return await self.setup(
             webhook_path=webhook_path,
-            backend_url=f"{settings.backend_public_url}/generate",
+            backend_url=f"{settings.backend_public_url}/generate/text",
             force_update=False,
         )
     
     async def health_check(self) -> dict:
         """Check n8n API health."""
         result = await self._request("GET", f"{self.api_url}/healthz")
-        if result.get("error"):
         fallback = await self._request("GET", "workflows")
-            if fallback.get("error"):
-                return fallback
-            return {"status": "ok", "checked_via": "workflows"}
-        return {"status": "ok", "checked_via": "healthz"}
+        return self._build_health_result(result, fallback)
+
+    def health_check_sync(self) -> dict:
+        """Synchronously check n8n API health for UI rendering."""
+        result = self._request_sync("GET", f"{self.api_url}/healthz")
+        fallback = self._request_sync("GET", "workflows")
+        return self._build_health_result(result, fallback)
     
     async def setup(
         self,
@@ -324,9 +488,15 @@ class N8NSetupAgent:
         # First, verify n8n is accessible
         health = await self.health_check()
         if health.get("error"):
-            return {"status": "error", "message": health.get("error")}
+            return {
+                "status": "error",
+                "message": health.get("message") or health.get("error"),
+                "health": health,
+                "checks": health.get("checks", []),
+                "suggestion": health.get("suggestion"),
+            }
         
-        effective_backend_url = backend_url or f"{settings.backend_public_url}/generate"
+        effective_backend_url = backend_url or f"{settings.backend_public_url}/generate/text"
         effective_bot_token = telegram_bot_token or settings.telegram_bot_token
         effective_credential_name = telegram_credential_name or settings.n8n_telegram_credential_name
         trigger_mode = use_telegram_trigger if use_telegram_trigger is not None else bool(effective_bot_token)
@@ -334,20 +504,22 @@ class N8NSetupAgent:
         if trigger_mode:
             credential = await self.ensure_telegram_credential(effective_bot_token, effective_credential_name)
             if credential.get("error"):
-                return {"status": "error", "message": credential["error"]}
+                return {"status": "error", "message": credential["error"], "details": credential}
             workflow = self.build_telegram_trigger_workflow(
                 backend_url=effective_backend_url,
                 credential_name=effective_credential_name,
+                allowed_chat_id=settings.telegram_chat_id,
             )
         else:
             workflow = self.build_telegram_workflow(
                 webhook_path=webhook_path,
                 backend_url=effective_backend_url,
+                allowed_chat_id=settings.telegram_chat_id,
             )
 
         existing = await self.get_workflow(workflow["name"])
         if isinstance(existing, dict) and existing.get("error"):
-            return {"status": "error", "message": existing["error"]}
+            return {"status": "error", "message": existing["error"], "details": existing}
 
         workflow_id = None
         if existing and existing.get("id"):
@@ -361,12 +533,12 @@ class N8NSetupAgent:
             workflow_id = str(result.get("id", "")) if isinstance(result, dict) else None
 
         if isinstance(result, dict) and result.get("error"):
-            return {"status": "error", "message": result["error"]}
+            return {"status": "error", "message": result["error"], "details": result}
 
         workflow_id = workflow_id or str(result.get("id", ""))
         enable_result = await self.enable_workflow(workflow_id)
         if enable_result.get("error"):
-            return {"status": "error", "message": enable_result["error"], "workflow": result}
+            return {"status": "error", "message": enable_result["error"], "workflow": result, "details": enable_result}
 
         return {
             "status": "success",

ai_software_factory/agents/request_interpreter.py

@@ -0,0 +1,105 @@
+"""Interpret free-form software requests into structured generation input."""
+
+from __future__ import annotations
+
+import json
+import re
+
+try:
+    from ..config import settings
+except ImportError:
+    from config import settings
+
+
+class RequestInterpreter:
+    """Use Ollama to turn free-form text into a structured software request."""
+
+    def __init__(self, ollama_url: str | None = None, model: str | None = None):
+        self.ollama_url = (ollama_url or settings.ollama_url).rstrip('/')
+        self.model = model or settings.OLLAMA_MODEL
+
+    async def interpret(self, prompt_text: str) -> dict:
+        """Interpret free-form text into the request shape expected by the orchestrator."""
+        normalized = prompt_text.strip()
+        if not normalized:
+            raise ValueError('Prompt text cannot be empty')
+
+        try:
+            import aiohttp
+
+            async with aiohttp.ClientSession() as session:
+                async with session.post(
+                    f'{self.ollama_url}/api/chat',
+                    json={
+                        'model': self.model,
+                        'stream': False,
+                        'format': 'json',
+                        'messages': [
+                            {
+                                'role': 'system',
+                                'content': (
+                                    'You extract structured software requests. '
+                                    'Return only JSON with keys name, description, features, tech_stack. '
+                                    'name and description must be concise strings. '
+                                    'features and tech_stack must be arrays of strings. '
+                                    'Infer missing details from the user request instead of leaving arrays empty when possible.'
+                                ),
+                            },
+                            {'role': 'user', 'content': normalized},
+                        ],
+                    },
+                ) as resp:
+                    payload = await resp.json()
+                    if 200 <= resp.status < 300:
+                        content = payload.get('message', {}).get('content', '')
+                        if content:
+                            return self._normalize_interpreted_request(json.loads(content), normalized)
+        except Exception:
+            pass
+
+        return self._heuristic_fallback(normalized)
+
+    def _normalize_interpreted_request(self, interpreted: dict, original_prompt: str) -> dict:
+        """Normalize LLM output into the required request shape."""
+        name = str(interpreted.get('name') or '').strip() or self._derive_name(original_prompt)
+        description = str(interpreted.get('description') or '').strip() or original_prompt[:255]
+        features = self._normalize_list(interpreted.get('features'))
+        tech_stack = self._normalize_list(interpreted.get('tech_stack'))
+        if not features:
+            features = ['core workflow based on free-form request']
+        return {
+            'name': name[:255],
+            'description': description[:255],
+            'features': features,
+            'tech_stack': tech_stack,
+        }
+
+    def _normalize_list(self, value) -> list[str]:
+        if isinstance(value, list):
+            return [str(item).strip() for item in value if str(item).strip()]
+        if isinstance(value, str) and value.strip():
+            return [item.strip() for item in value.split(',') if item.strip()]
+        return []
+
+    def _derive_name(self, prompt_text: str) -> str:
+        """Derive a stable project name when the LLM does not provide one."""
+        first_line = prompt_text.splitlines()[0].strip()
+        cleaned = re.sub(r'[^A-Za-z0-9 ]+', ' ', first_line)
+        words = [word.capitalize() for word in cleaned.split()[:4]]
+        return ' '.join(words) or 'Generated Project'
+
+    def _heuristic_fallback(self, prompt_text: str) -> dict:
+        """Fallback request extraction when Ollama is unavailable."""
+        lowered = prompt_text.lower()
+        tech_candidates = [
+            'python', 'fastapi', 'django', 'flask', 'postgresql', 'sqlite', 'react', 'vue', 'nicegui', 'docker'
+        ]
+        tech_stack = [candidate for candidate in tech_candidates if candidate in lowered]
+        sentences = [part.strip() for part in re.split(r'[\n\.]+', prompt_text) if part.strip()]
+        features = sentences[:3] or ['Implement the user request from free-form text']
+        return {
+            'name': self._derive_name(prompt_text),
+            'description': sentences[0][:255] if sentences else prompt_text[:255],
+            'features': features,
+            'tech_stack': tech_stack,
+        }

ai_software_factory/agents/telegram.py

@@ -1,8 +1,6 @@
 """Telegram bot integration for n8n webhook."""
 
 import asyncio
-import json
-import re
 from typing import Optional
 
 
@@ -13,6 +11,59 @@ class TelegramHandler:
         self.webhook_url = webhook_url
         self.api_url = "https://api.telegram.org/bot"
 
+    def build_prompt_guide_message(self, backend_url: str | None = None) -> str:
+        """Build a Telegram message explaining the expected prompt format."""
+        lines = [
+            "AI Software Factory is listening in this chat.",
+            "",
+            "You can send free-form software requests in normal language.",
+            "",
+            "Example:",
+            "Build an internal inventory portal for our warehouse team.",
+            "It should support role-based login, stock dashboards, and purchase orders.",
+            "Prefer FastAPI, PostgreSQL, and a simple web UI.",
+            "",
+            "The backend will interpret the request and turn it into a structured project plan.",
+        ]
+        if backend_url:
+            lines.extend(["", f"Backend target: {backend_url}"])
+        return "\n".join(lines)
+
+    async def send_message(self, bot_token: str, chat_id: str | int, text: str) -> dict:
+        """Send a direct Telegram message using the configured bot."""
+        if not bot_token:
+            return {"status": "error", "message": "Telegram bot token is not configured"}
+        if chat_id in (None, ""):
+            return {"status": "error", "message": "Telegram chat id is not configured"}
+
+        api_endpoint = f"{self.api_url}{bot_token}/sendMessage"
+
+        try:
+            import aiohttp
+            async with aiohttp.ClientSession() as session:
+                async with session.post(
+                    api_endpoint,
+                    json={
+                        "chat_id": str(chat_id),
+                        "text": text,
+                    },
+                ) as resp:
+                    payload = await resp.json()
+                    if 200 <= resp.status < 300 and payload.get("ok"):
+                        return {
+                            "status": "success",
+                            "message": "Telegram prompt guide sent successfully",
+                            "payload": payload,
+                        }
+                    description = payload.get("description") or payload.get("message") or str(payload)
+                    return {
+                        "status": "error",
+                        "message": f"Telegram API returned {resp.status}: {description}",
+                        "payload": payload,
+                    }
+        except Exception as exc:
+            return {"status": "error", "message": str(exc)}
+    
     async def handle_message(self, message_data: dict) -> dict:
         """Handle incoming Telegram message."""
         text = message_data.get("text", "")

ai_software_factory/dashboard_ui.py

@@ -3,19 +3,22 @@
 from __future__ import annotations
 
 from contextlib import closing
+from html import escape
 
-from nicegui import ui
+from nicegui import app, ui
 
 try:
     from .agents.database_manager import DatabaseManager
     from .agents.n8n_setup import N8NSetupAgent
+    from .agents.telegram import TelegramHandler
     from .config import settings
-    from .database import get_db_sync, init_db
+    from .database import get_database_runtime_summary, get_db_sync, init_db
 except ImportError:
     from agents.database_manager import DatabaseManager
     from agents.n8n_setup import N8NSetupAgent
+    from agents.telegram import TelegramHandler
     from config import settings
-    from database import get_db_sync, init_db
+    from database import get_database_runtime_summary, get_db_sync, init_db
 
 
 def _resolve_n8n_api_url() -> str:
@@ -65,8 +68,32 @@ def _load_dashboard_snapshot() -> dict:
             return {'error': f'Database error: {exc}'}
 
 
-def create_dashboard():
-    """Create the main NiceGUI dashboard."""
+def _load_n8n_health_snapshot() -> dict:
+    """Load an n8n health snapshot for UI rendering."""
+    api_url = _resolve_n8n_api_url()
+    if not api_url:
+        return {
+            'status': 'error',
+            'message': 'N8N_API_URL or N8N_WEBHOOK_URL is not configured.',
+            'api_url': 'Not configured',
+            'auth_configured': bool(settings.n8n_api_key),
+            'checks': [],
+            'suggestion': 'Set N8N_API_URL to the base n8n address before provisioning workflows.',
+        }
+    try:
+        return N8NSetupAgent(api_url=api_url, webhook_token=settings.n8n_api_key).health_check_sync()
+    except Exception as exc:
+        return {
+            'status': 'error',
+            'message': f'Unable to run n8n health checks: {exc}',
+            'api_url': api_url,
+            'auth_configured': bool(settings.n8n_api_key),
+            'checks': [],
+        }
+
+
+def _add_dashboard_styles() -> None:
+    """Register shared dashboard styles."""
     ui.add_head_html(
         """
         <style>
@@ -81,6 +108,115 @@ def create_dashboard():
         """
     )
 
+
+def _render_n8n_error_dialog(result: dict) -> None:
+    """Render a detailed n8n failure dialog."""
+    health = result.get('health', {}) if isinstance(result.get('health'), dict) else {}
+    checks = result.get('checks') or health.get('checks') or []
+    details = result.get('details') if isinstance(result.get('details'), dict) else {}
+
+    with ui.dialog() as dialog, ui.card().classes('factory-panel q-pa-lg').style('max-width: 840px; width: min(92vw, 840px);'):
+        ui.label('n8n provisioning failed').style('font-size: 1.35rem; font-weight: 800; color: #5c2d1f;')
+        ui.label(result.get('message', 'No error message returned.')).classes('factory-muted')
+        if result.get('suggestion') or health.get('suggestion'):
+            ui.label(result.get('suggestion') or health.get('suggestion')).classes('factory-chip q-mt-sm')
+        if checks:
+            ui.label('Health checks').style('font-size: 1rem; font-weight: 700; color: #3a281a; margin-top: 12px;')
+            for check in checks:
+                status = 'OK' if check.get('ok') else 'FAIL'
+                message = check.get('message') or 'No detail available'
+                ui.markdown(
+                    f"- **{escape(check.get('name', 'check'))}** · {status} · {escape(str(check.get('status_code') or 'n/a'))} · {escape(check.get('url') or 'unknown url')}"
+                )
+                ui.label(message).classes('factory-muted')
+        if details:
+            ui.label('API response').style('font-size: 1rem; font-weight: 700; color: #3a281a; margin-top: 12px;')
+            ui.label(str(details)).classes('factory-code')
+        with ui.row().classes('justify-end w-full q-mt-md'):
+            ui.button('Close', on_click=dialog.close).props('unelevated color=dark')
+    dialog.open()
+
+
+def _render_health_panels() -> None:
+    """Render application and n8n health panels."""
+    runtime = get_database_runtime_summary()
+    n8n_health = _load_n8n_health_snapshot()
+
+    with ui.grid(columns=2).classes('w-full gap-4'):
+        with ui.card().classes('factory-panel q-pa-lg'):
+            ui.label('Application Health').style('font-size: 1.25rem; font-weight: 700; color: #3a281a;')
+            rows = [
+                ('Status', 'healthy'),
+                ('Database Backend', runtime['backend']),
+                ('Database Target', runtime['target']),
+                ('Database Name', runtime['database']),
+                ('Backend URL', settings.backend_public_url),
+                ('Projects Root', str(settings.projects_root)),
+            ]
+            for label, value in rows:
+                with ui.row().classes('justify-between w-full q-mt-sm'):
+                    ui.label(label).classes('factory-muted')
+                    ui.label(str(value)).style('font-weight: 600; color: #3a281a;')
+
+        with ui.card().classes('factory-panel q-pa-lg'):
+            ui.label('n8n Connection Status').style('font-size: 1.25rem; font-weight: 700; color: #3a281a;')
+            status_label = n8n_health.get('status', 'unknown').upper()
+            ui.label(status_label).classes('factory-chip')
+            ui.label(n8n_health.get('message', 'No n8n status available.')).classes('factory-muted q-mt-sm')
+            rows = [
+                ('API URL', n8n_health.get('api_url') or 'Not configured'),
+                ('Auth Configured', 'yes' if n8n_health.get('auth_configured') else 'no'),
+                ('Checked Via', n8n_health.get('checked_via') or 'none'),
+                ('Telegram Chat ID', settings.telegram_chat_id or 'Not configured'),
+            ]
+            if n8n_health.get('workflow_count') is not None:
+                rows.append(('Workflow Count', str(n8n_health['workflow_count'])))
+            for label, value in rows:
+                with ui.row().classes('justify-between w-full q-mt-sm'):
+                    ui.label(label).classes('factory-muted')
+                    ui.label(str(value)).style('font-weight: 600; color: #3a281a;')
+            if n8n_health.get('suggestion'):
+                ui.label(n8n_health['suggestion']).classes('factory-chip q-mt-md')
+            checks = n8n_health.get('checks', [])
+            if checks:
+                ui.label('Checks').style('font-size: 1rem; font-weight: 700; color: #3a281a; margin-top: 12px;')
+                for check in checks:
+                    status = 'OK' if check.get('ok') else 'FAIL'
+                    ui.markdown(
+                        f"- **{escape(check.get('name', 'check'))}** · {status} · {escape(str(check.get('status_code') or 'n/a'))} · {escape(check.get('url') or 'unknown url')}"
+                    )
+                    if check.get('message'):
+                        ui.label(check['message']).classes('factory-muted')
+
+
+def create_health_page() -> None:
+    """Create a dedicated health page for runtime diagnostics."""
+    _add_dashboard_styles()
+    with ui.column().classes('factory-shell w-full gap-4 q-pa-lg'):
+        with ui.card().classes('factory-panel w-full q-pa-lg'):
+            with ui.row().classes('items-center justify-between w-full'):
+                with ui.column().classes('gap-1'):
+                    ui.label('Factory Health').style('font-size: 2rem; font-weight: 800; color: #302116;')
+                    ui.label('Current application and n8n connectivity diagnostics.').classes('factory-muted')
+                with ui.row().classes('items-center gap-2'):
+                    ui.link('Back to Dashboard', '/')
+                    ui.link('Refresh Health', '/health-ui')
+        _render_health_panels()
+
+
+def create_dashboard():
+    """Create the main NiceGUI dashboard."""
+    _add_dashboard_styles()
+    active_tab_key = 'dashboard.active_tab'
+
+    def _selected_tab_name() -> str:
+        """Return the persisted active dashboard tab."""
+        return app.storage.user.get(active_tab_key, 'overview')
+
+    def _store_selected_tab(event) -> None:
+        """Persist the active dashboard tab across refreshes."""
+        app.storage.user[active_tab_key] = event.value or 'overview'
+
     async def setup_n8n_workflow_action() -> None:
         api_url = _resolve_n8n_api_url()
         if not api_url:
@@ -90,7 +226,7 @@ def create_dashboard():
         agent = N8NSetupAgent(api_url=api_url, webhook_token=settings.n8n_api_key)
         result = await agent.setup(
             webhook_path='telegram',
-            backend_url=f'{settings.backend_public_url}/generate',
+            backend_url=f'{settings.backend_public_url}/generate/text',
             force_update=True,
         )
 
@@ -103,9 +239,39 @@ def create_dashboard():
                     message=result.get('message', str(result)),
                 )
 
+        if result.get('status') == 'error':
+            _render_n8n_error_dialog(result)
         ui.notify(result.get('message', 'n8n setup finished'), color='positive' if result.get('status') == 'success' else 'negative')
         dashboard_body.refresh()
 
+    async def send_telegram_prompt_guide_action() -> None:
+        if not settings.telegram_bot_token:
+            ui.notify('Configure TELEGRAM_BOT_TOKEN first', color='negative')
+            return
+        if not settings.telegram_chat_id:
+            ui.notify('Configure TELEGRAM_CHAT_ID to message the prompt channel', color='negative')
+            return
+
+        handler = TelegramHandler(settings.n8n_webhook_url or _resolve_n8n_api_url())
+        message = handler.build_prompt_guide_message(settings.backend_public_url)
+        result = await handler.send_message(
+            bot_token=settings.telegram_bot_token,
+            chat_id=settings.telegram_chat_id,
+            text=message,
+        )
+
+        db = get_db_sync()
+        if db is not None:
+            with closing(db):
+                DatabaseManager(db).log_system_event(
+                    component='telegram',
+                    level='INFO' if result.get('status') == 'success' else 'ERROR',
+                    message=result.get('message', str(result)),
+                )
+
+        ui.notify(result.get('message', 'Telegram message sent'), color='positive' if result.get('status') == 'success' else 'negative')
+        dashboard_body.refresh()
+
     def init_db_action() -> None:
         result = init_db()
         ui.notify(result.get('message', 'Database initialized'), color='positive' if result.get('status') == 'success' else 'negative')
@@ -144,6 +310,7 @@ def create_dashboard():
                         ui.button('Refresh', on_click=dashboard_body.refresh).props('outline')
                         ui.button('Initialize DB', on_click=init_db_action).props('unelevated color=dark')
                         ui.button('Provision n8n Workflow', on_click=setup_n8n_workflow_action).props('unelevated color=accent')
+                        ui.button('Message Prompt Channel', on_click=send_telegram_prompt_guide_action).props('outline color=secondary')
 
             with ui.grid(columns=4).classes('w-full gap-4'):
                 metrics = [
@@ -158,14 +325,16 @@ def create_dashboard():
                         ui.label(str(value)).style('font-size: 2.1rem; font-weight: 800; margin-top: 6px;')
                         ui.label(subtitle).style('font-size: 0.9rem; opacity: 0.78; margin-top: 8px;')
 
-            tabs = ui.tabs().classes('w-full')
-            overview_tab = ui.tab('Overview')
-            projects_tab = ui.tab('Projects')
-            trace_tab = ui.tab('Prompt Trace')
-            system_tab = ui.tab('System')
+            selected_tab = _selected_tab_name()
+            with ui.tabs(value=selected_tab, on_change=_store_selected_tab).classes('w-full') as tabs:
+                ui.tab('Overview').props('name=overview')
+                ui.tab('Projects').props('name=projects')
+                ui.tab('Prompt Trace').props('name=trace')
+                ui.tab('System').props('name=system')
+                ui.tab('Health').props('name=health')
 
-            with ui.tab_panels(tabs, value=overview_tab).classes('w-full'):
-                with ui.tab_panel(overview_tab):
+            with ui.tab_panels(tabs, value=selected_tab).classes('w-full'):
+                with ui.tab_panel('overview'):
                     with ui.grid(columns=2).classes('w-full gap-4'):
                         with ui.card().classes('factory-panel q-pa-lg'):
                             ui.label('Project Pipeline').style('font-size: 1.25rem; font-weight: 700; color: #3a281a;')
@@ -195,7 +364,7 @@ def create_dashboard():
                                     ui.label(label).classes('factory-muted')
                                     ui.label(value).style('font-weight: 600; color: #3a281a;')
 
-                with ui.tab_panel(projects_tab):
+                with ui.tab_panel('projects'):
                     if not projects:
                         with ui.card().classes('factory-panel q-pa-lg'):
                             ui.label('No project data available yet.').classes('factory-muted')
@@ -249,7 +418,7 @@ def create_dashboard():
                                     else:
                                         ui.label('No audit events yet.').classes('factory-muted')
 
-                with ui.tab_panel(trace_tab):
+                with ui.tab_panel('trace'):
                     with ui.card().classes('factory-panel q-pa-lg'):
                         ui.label('Prompt to Code Correlation').style('font-size: 1.25rem; font-weight: 700; color: #3a281a;')
                         ui.label('Each prompt entry is linked to the generated files recorded after that prompt for the same project.').classes('factory-muted')
@@ -270,7 +439,7 @@ def create_dashboard():
                         else:
                             ui.label('No prompt traces recorded yet.').classes('factory-muted')
 
-                with ui.tab_panel(system_tab):
+                with ui.tab_panel('system'):
                     with ui.grid(columns=2).classes('w-full gap-4'):
                         with ui.card().classes('factory-panel q-pa-lg'):
                             ui.label('System Logs').style('font-size: 1.25rem; font-weight: 700; color: #3a281a;')
@@ -296,6 +465,21 @@ def create_dashboard():
                             for endpoint in endpoints:
                                 ui.label(endpoint).classes('factory-code q-mt-sm')
 
+                with ui.tab_panel('health'):
+                    with ui.card().classes('factory-panel q-pa-lg q-mb-md'):
+                        ui.label('Health and Diagnostics').style('font-size: 1.25rem; font-weight: 700; color: #3a281a;')
+                        ui.label('Use this page to verify runtime configuration, n8n API connectivity, and likely causes of provisioning failures.').classes('factory-muted')
+                        ui.link('Open dedicated health page', '/health-ui')
+                    with ui.card().classes('factory-panel q-pa-lg q-mb-md'):
+                        ui.label('Telegram Prompt Channel').style('font-size: 1.25rem; font-weight: 700; color: #3a281a;')
+                        ui.label('Send a guide message into the same Telegram chat/channel where the bot is expected to receive prompts.').classes('factory-muted')
+                        with ui.row().classes('justify-between w-full q-mt-sm'):
+                            ui.label('Configured Chat ID').classes('factory-muted')
+                            ui.label(settings.telegram_chat_id or 'Not configured').style('font-weight: 600; color: #3a281a;')
+                        with ui.row().classes('items-center gap-2 q-mt-md'):
+                            ui.button('Send Prompt Guide', on_click=send_telegram_prompt_guide_action).props('unelevated color=secondary')
+                    _render_health_panels()
+
     dashboard_body()
     ui.timer(10.0, dashboard_body.refresh)
 

ai_software_factory/frontend.py

@@ -10,9 +10,9 @@ from fastapi.responses import RedirectResponse
 from nicegui import app, ui
 
 try:
-    from .dashboard_ui import create_dashboard
+    from .dashboard_ui import create_dashboard, create_health_page
 except ImportError:
-    from dashboard_ui import create_dashboard
+    from dashboard_ui import create_dashboard, create_health_page
 
 
 def init(fastapi_app: FastAPI, storage_secret: str = 'Secr2t!') -> None:
@@ -38,6 +38,10 @@ def init(fastapi_app: FastAPI, storage_secret: str = 'Secr2t!') -> None:
     def show() -> None:
         render_dashboard_page()
 
+    @ui.page('/health-ui')
+    def health_ui() -> None:
+        create_health_page()
+
     @fastapi_app.get('/dashboard', include_in_schema=False)
     def dashboard_redirect() -> RedirectResponse:
         return RedirectResponse(url='/', status_code=307)

ai_software_factory/hello_world.sh

@@ -1,3 +0,0 @@
-#!/bin/bash
-
-echo "Hello world"

ai_software_factory/main.py

@@ -28,6 +28,7 @@ try:
     from . import __version__, frontend
     from . import database as database_module
     from .agents.database_manager import DatabaseManager
+    from .agents.request_interpreter import RequestInterpreter
     from .agents.orchestrator import AgentOrchestrator
     from .agents.n8n_setup import N8NSetupAgent
     from .agents.ui_manager import UIManager
@@ -36,6 +37,7 @@ except ImportError:
     import frontend
     import database as database_module
     from agents.database_manager import DatabaseManager
+    from agents.request_interpreter import RequestInterpreter
     from agents.orchestrator import AgentOrchestrator
     from agents.n8n_setup import N8NSetupAgent
     from agents.ui_manager import UIManager
@@ -79,6 +81,15 @@ class N8NSetupRequest(BaseModel):
     force_update: bool = False
 
 
+class FreeformSoftwareRequest(BaseModel):
+    """Request body for free-form software generation."""
+
+    prompt_text: str = Field(min_length=1)
+    source: str = 'telegram'
+    chat_id: str | None = None
+    chat_type: str | None = None
+
+
 def _build_project_id(name: str) -> str:
     """Create a stable project id from the requested name."""
     slug = PROJECT_ID_PATTERN.sub("-", name.strip().lower()).strip("-") or "project"
@@ -144,6 +155,49 @@ def _compose_prompt_text(request: SoftwareRequest) -> str:
     )
 
 
+async def _run_generation(
+    request: SoftwareRequest,
+    db: Session,
+    prompt_text: str | None = None,
+    prompt_actor: str = 'api',
+) -> dict:
+    """Run the shared generation pipeline for a structured request."""
+    database_module.init_db()
+
+    project_id = _build_project_id(request.name)
+    resolved_prompt_text = prompt_text or _compose_prompt_text(request)
+    orchestrator = AgentOrchestrator(
+        project_id=project_id,
+        project_name=request.name,
+        description=request.description,
+        features=request.features,
+        tech_stack=request.tech_stack,
+        db=db,
+        prompt_text=resolved_prompt_text,
+        prompt_actor=prompt_actor,
+    )
+    result = await orchestrator.run()
+
+    manager = DatabaseManager(db)
+    manager.log_system_event(
+        component='api',
+        level='INFO' if result['status'] == 'completed' else 'ERROR',
+        message=f"Generated project {project_id} with {len(result.get('changed_files', []))} artifact(s)",
+    )
+
+    history = manager.get_project_by_id(project_id)
+    project_logs = manager.get_project_logs(history.id)
+    response_data = _serialize_project(history)
+    response_data['logs'] = [_serialize_project_log(log) for log in project_logs]
+    response_data['ui_data'] = result.get('ui_data')
+    response_data['features'] = request.features
+    response_data['tech_stack'] = request.tech_stack
+    response_data['project_root'] = result.get('project_root', str(_project_root(project_id)))
+    response_data['changed_files'] = result.get('changed_files', [])
+    response_data['repository'] = result.get('repository')
+    return {'status': result['status'], 'data': response_data}
+
+
 def _project_root(project_id: str) -> Path:
     """Resolve the filesystem location for a generated project."""
     return database_module.settings.projects_root / project_id
@@ -172,6 +226,7 @@ def read_api_info():
             '/api',
             '/health',
             '/generate',
+            '/generate/text',
             '/projects',
             '/status/{project_id}',
             '/audit/projects',
@@ -202,40 +257,43 @@ def health_check():
 @app.post('/generate')
 async def generate_software(request: SoftwareRequest, db: DbSession):
     """Create and record a software-generation request."""
-    database_module.init_db()
+    return await _run_generation(request, db)
 
-    project_id = _build_project_id(request.name)
-    prompt_text = _compose_prompt_text(request)
-    orchestrator = AgentOrchestrator(
-        project_id=project_id,
-        project_name=request.name,
-        description=request.description,
-        features=request.features,
-        tech_stack=request.tech_stack,
-        db=db,
-        prompt_text=prompt_text,
+
+@app.post('/generate/text')
+async def generate_software_from_text(request: FreeformSoftwareRequest, db: DbSession):
+    """Interpret a free-form request and run generation."""
+    if (
+        request.source == 'telegram'
+        and database_module.settings.telegram_chat_id
+        and request.chat_id
+        and str(request.chat_id) != str(database_module.settings.telegram_chat_id)
+    ):
+        return {
+            'status': 'ignored',
+            'message': f"Ignoring Telegram message from chat {request.chat_id}",
+            'source': {
+                'type': request.source,
+                'chat_id': request.chat_id,
+                'chat_type': request.chat_type,
+            },
+        }
+
+    interpreted = await RequestInterpreter().interpret(request.prompt_text)
+    structured_request = SoftwareRequest(**interpreted)
+    response = await _run_generation(
+        structured_request,
+        db,
+        prompt_text=request.prompt_text,
+        prompt_actor=request.source,
     )
-    result = await orchestrator.run()
-
-    manager = DatabaseManager(db)
-    manager.log_system_event(
-        component='api',
-        level='INFO' if result['status'] == 'completed' else 'ERROR',
-        message=f"Generated project {project_id} with {len(result.get('changed_files', []))} artifact(s)",
-    )
-
-    history = manager.get_project_by_id(project_id)
-    project_logs = manager.get_project_logs(history.id)
-    response_data = _serialize_project(history)
-    response_data['logs'] = [_serialize_project_log(log) for log in project_logs]
-    response_data['ui_data'] = result.get('ui_data')
-    response_data['features'] = request.features
-    response_data['tech_stack'] = request.tech_stack
-    response_data['project_root'] = result.get('project_root', str(_project_root(project_id)))
-    response_data['changed_files'] = result.get('changed_files', [])
-    response_data['repository'] = result.get('repository')
-
-    return {'status': result['status'], 'data': response_data}
+    response['interpreted_request'] = interpreted
+    response['source'] = {
+        'type': request.source,
+        'chat_id': request.chat_id,
+        'chat_type': request.chat_type,
+    }
+    return response
 
 
 @app.get('/projects')
@@ -323,10 +381,16 @@ async def get_n8n_health():
     """Check whether the configured n8n instance is reachable."""
     api_url = _resolve_n8n_api_url()
     if not api_url:
-        return {'status': 'error', 'message': 'N8N_API_URL or N8N_WEBHOOK_URL is not configured'}
+        return {
+            'status': 'error',
+            'message': 'N8N_API_URL or N8N_WEBHOOK_URL is not configured.',
+            'api_url': '',
+            'auth_configured': bool(database_module.settings.n8n_api_key),
+            'checks': [],
+            'suggestion': 'Set N8N_API_URL to the base n8n address before provisioning workflows.',
+        }
     agent = N8NSetupAgent(api_url=api_url, webhook_token=database_module.settings.n8n_api_key)
-    result = await agent.health_check()
-    return {'status': 'ok' if not result.get('error') else 'error', 'data': result}
+    return await agent.health_check()
 
 
 @app.post('/n8n/setup')
@@ -342,7 +406,7 @@ async def setup_n8n_workflow(request: N8NSetupRequest, db: DbSession):
     )
     result = await agent.setup(
         webhook_path=request.webhook_path,
-        backend_url=request.backend_url or f"{database_module.settings.backend_public_url}/generate",
+        backend_url=request.backend_url or f"{database_module.settings.backend_public_url}/generate/text",
         force_update=request.force_update,
         telegram_bot_token=database_module.settings.telegram_bot_token,
         telegram_credential_name=database_module.settings.n8n_telegram_credential_name,