feat: add explicit workflow steps and guardrail prompts, refs NOISSUE

ai_software_factory/main.py

@@ -30,6 +30,7 @@ try:
     from .agents.change_summary import ChangeSummaryGenerator
     from .agents.database_manager import DatabaseManager
     from .agents.request_interpreter import RequestInterpreter
+    from .agents.llm_service import LLMServiceClient
     from .agents.orchestrator import AgentOrchestrator
     from .agents.n8n_setup import N8NSetupAgent
     from .agents.prompt_workflow import PromptWorkflowManager
@@ -41,6 +42,7 @@ except ImportError:
     from agents.change_summary import ChangeSummaryGenerator
     from agents.database_manager import DatabaseManager
     from agents.request_interpreter import RequestInterpreter
+    from agents.llm_service import LLMServiceClient
     from agents.orchestrator import AgentOrchestrator
     from agents.n8n_setup import N8NSetupAgent
     from agents.prompt_workflow import PromptWorkflowManager
@@ -109,6 +111,75 @@ def _build_project_id(name: str) -> str:
     return f"{slug}-{uuid4().hex[:8]}"
 
 
+def _build_project_slug(name: str) -> str:
+    """Normalize a project name into a kebab-case identifier slug."""
+    return PROJECT_ID_PATTERN.sub("-", name.strip().lower()).strip("-") or "project"
+
+
+def _ensure_unique_identifier(base_slug: str, reserved_ids: set[str]) -> str:
+    """Return a unique identifier using deterministic numeric suffixes when needed."""
+    normalized = _build_project_slug(base_slug)
+    if normalized not in reserved_ids:
+        return normalized
+    suffix = 2
+    while f"{normalized}-{suffix}" in reserved_ids:
+        suffix += 1
+    return f"{normalized}-{suffix}"
+
+
+def _build_project_identity_context(manager: DatabaseManager) -> list[dict]:
+    """Build a compact project catalog for naming stages."""
+    projects = []
+    for history in manager.get_all_projects(include_archived=True):
+        repository = manager._get_project_repository(history) or {}
+        projects.append(
+            {
+                'project_id': history.project_id,
+                'name': history.project_name,
+                'description': history.description,
+                'repository': {
+                    'owner': repository.get('owner'),
+                    'name': repository.get('name'),
+                },
+            }
+        )
+    return projects
+
+
+async def _derive_project_id_for_request(
+    request: SoftwareRequest,
+    *,
+    prompt_text: str,
+    prompt_routing: dict | None,
+    existing_projects: list[dict],
+) -> tuple[str, dict | None]:
+    """Derive a stable project id for a newly created project."""
+    reserved_ids = {str(project.get('project_id')).strip() for project in existing_projects if project.get('project_id')}
+    fallback_id = _ensure_unique_identifier((prompt_routing or {}).get('project_name') or request.name, reserved_ids)
+    user_prompt = (
+        f"Original user prompt:\n{prompt_text}\n\n"
+        f"Structured request:\n{json.dumps({'name': request.name, 'description': request.description, 'features': request.features, 'tech_stack': request.tech_stack}, indent=2)}\n\n"
+        f"Naming context:\n{json.dumps(prompt_routing or {}, indent=2)}\n\n"
+        f"Reserved project ids:\n{json.dumps(sorted(reserved_ids))}\n\n"
+        "Suggest the best stable project id for this new project."
+    )
+    content, trace = await LLMServiceClient().chat_with_trace(
+        stage='project_id_naming',
+        system_prompt=database_module.settings.llm_project_id_system_prompt,
+        user_prompt=user_prompt,
+        tool_context_input={'projects': existing_projects},
+        expect_json=True,
+    )
+    if content:
+        try:
+            parsed = json.loads(content)
+            candidate = parsed.get('project_id') or parsed.get('slug') or request.name
+            return _ensure_unique_identifier(str(candidate), reserved_ids), trace
+        except Exception:
+            pass
+    return fallback_id, trace
+
+
 def _serialize_project(history: ProjectHistory) -> dict:
     """Serialize a project history row for API responses."""
     return {
@@ -176,13 +247,15 @@ async def _run_generation(
     prompt_source_context: dict | None = None,
     prompt_routing: dict | None = None,
     preferred_project_id: str | None = None,
+    repo_name_override: str | None = None,
     related_issue: dict | None = None,
 ) -> dict:
     """Run the shared generation pipeline for a structured request."""
     database_module.init_db()
 
     manager = DatabaseManager(db)
-    reusable_history = manager.get_project_by_id(preferred_project_id, include_archived=False) if preferred_project_id else manager.get_latest_project_by_name(request.name)
+    is_explicit_new_project = (prompt_routing or {}).get('intent') == 'new_project'
+    reusable_history = manager.get_project_by_id(preferred_project_id, include_archived=False) if preferred_project_id else (None if is_explicit_new_project else manager.get_latest_project_by_name(request.name))
     if reusable_history and database_module.settings.gitea_url and database_module.settings.gitea_token:
         try:
             from .agents.gitea import GiteaAPI
@@ -197,14 +270,23 @@ async def _run_generation(
             ),
             project_id=reusable_history.project_id,
         )
+    project_id_trace = None
+    resolved_prompt_text = prompt_text or _compose_prompt_text(request)
     if preferred_project_id and reusable_history is not None:
         project_id = reusable_history.project_id
-    elif reusable_history and manager.get_open_pull_request(project_id=reusable_history.project_id):
+    elif reusable_history and not is_explicit_new_project and manager.get_open_pull_request(project_id=reusable_history.project_id):
         project_id = reusable_history.project_id
     else:
-        project_id = _build_project_id(request.name)
+        if is_explicit_new_project or prompt_text:
+            project_id, project_id_trace = await _derive_project_id_for_request(
+                request,
+                prompt_text=resolved_prompt_text,
+                prompt_routing=prompt_routing,
+                existing_projects=_build_project_identity_context(manager),
+            )
+        else:
+            project_id = _build_project_id(request.name)
         reusable_history = None
-    resolved_prompt_text = prompt_text or _compose_prompt_text(request)
     orchestrator = AgentOrchestrator(
         project_id=project_id,
         project_name=request.name,
@@ -217,6 +299,7 @@ async def _run_generation(
         existing_history=reusable_history,
         prompt_source_context=prompt_source_context,
         prompt_routing=prompt_routing,
+        repo_name_override=repo_name_override,
         related_issue_hint=related_issue,
     )
     result = await orchestrator.run()
@@ -240,6 +323,20 @@ async def _run_generation(
     response_data['repository'] = result.get('repository')
     response_data['related_issue'] = result.get('related_issue') or (result.get('ui_data') or {}).get('related_issue')
     response_data['pull_request'] = result.get('pull_request') or manager.get_open_pull_request(project_id=project_id)
+    if project_id_trace:
+        manager.log_llm_trace(
+            project_id=project_id,
+            history_id=history.id if history else None,
+            prompt_id=orchestrator.prompt_audit.id if orchestrator.prompt_audit else None,
+            stage=project_id_trace['stage'],
+            provider=project_id_trace['provider'],
+            model=project_id_trace['model'],
+            system_prompt=project_id_trace['system_prompt'],
+            user_prompt=project_id_trace['user_prompt'],
+            assistant_response=project_id_trace['assistant_response'],
+            raw_response=project_id_trace.get('raw_response'),
+            fallback_used=project_id_trace.get('fallback_used', False),
+        )
     summary_context = {
         'name': response_data['name'],
         'description': response_data['description'],
@@ -322,6 +419,7 @@ def read_api_info():
             '/',
             '/api',
             '/health',
+            '/llm/runtime',
             '/generate',
             '/generate/text',
             '/projects',
@@ -363,6 +461,12 @@ def health_check():
     }
 
 
+@app.get('/llm/runtime')
+def get_llm_runtime():
+    """Return the active external LLM runtime, guardrail, and tool configuration."""
+    return LLMServiceClient().get_runtime_configuration()
+
+
 @app.post('/generate')
 async def generate_software(request: SoftwareRequest, db: DbSession):
     """Create and record a software-generation request."""
@@ -411,6 +515,7 @@ async def generate_software_from_text(request: FreeformSoftwareRequest, db: DbSe
         },
         prompt_routing=routing,
         preferred_project_id=routing.get('project_id') if routing.get('intent') != 'new_project' else None,
+        repo_name_override=routing.get('repo_name') if routing.get('intent') == 'new_project' else None,
         related_issue={'number': routing.get('issue_number')} if routing.get('issue_number') is not None else None,
     )
     project_data = response.get('data', {})
@@ -431,6 +536,21 @@ async def generate_software_from_text(request: FreeformSoftwareRequest, db: DbSe
             raw_response=interpretation_trace.get('raw_response'),
             fallback_used=interpretation_trace.get('fallback_used', False),
         )
+        naming_trace = interpretation_trace.get('project_naming')
+        if naming_trace:
+            manager.log_llm_trace(
+                project_id=project_data.get('project_id'),
+                history_id=project_data.get('history_id'),
+                prompt_id=prompt_id,
+                stage=naming_trace['stage'],
+                provider=naming_trace['provider'],
+                model=naming_trace['model'],
+                system_prompt=naming_trace['system_prompt'],
+                user_prompt=naming_trace['user_prompt'],
+                assistant_response=naming_trace['assistant_response'],
+                raw_response=naming_trace.get('raw_response'),
+                fallback_used=naming_trace.get('fallback_used', False),
+            )
     response['interpreted_request'] = interpreted
     response['routing'] = routing
     response['llm_trace'] = interpretation_trace