release: version 0.9.7 🚀

HISTORY.md

@@ -5,10 +5,32 @@ Changelog
 (unreleased)
 ------------
 
+Fix
+~~~
+- More file generation improvements, refs NOISSUE. [Simon Diesenreiter]
+
+
+0.9.6 (2026-04-11)
+------------------
+
+Fix
+~~~
+- Repo onboarding fix, refs NOISSUE. [Simon Diesenreiter]
+
+Other
+~~~~~
+
+
+0.9.5 (2026-04-11)
+------------------
+
 Fix
 ~~~
 - Better code generation, refs NOISSUE. [Simon Diesenreiter]
 
+Other
+~~~~~
+
 
 0.9.4 (2026-04-11)
 ------------------

ai_software_factory/VERSION

@@ -1 +1 @@
-0.9.5
+0.9.7

ai_software_factory/agents/orchestrator.py

@@ -7,6 +7,7 @@ import json
 import py_compile
 import re
 import subprocess
+from pathlib import PurePosixPath
 from typing import Optional
 from datetime import datetime
 
@@ -29,6 +30,13 @@ except ImportError:
 class AgentOrchestrator:
     """Orchestrates the software generation process with full audit trail."""
 
+    REMOTE_READY_REPOSITORY_MODES = {'project', 'onboarded'}
+    REMOTE_READY_REPOSITORY_STATUSES = {'created', 'exists', 'ready', 'onboarded'}
+    GENERATED_TEXT_FILE_SUFFIXES = {'.py', '.md', '.txt', '.toml', '.yaml', '.yml', '.json', '.ini', '.cfg', '.sh', '.html', '.css', '.js', '.ts'}
+    GENERATED_TEXT_FILE_NAMES = {'README', 'README.md', '.gitignore', 'requirements.txt', 'pyproject.toml', 'Dockerfile', 'Containerfile', 'Makefile'}
+    MAX_WORKSPACE_CONTEXT_FILES = 20
+    MAX_WORKSPACE_CONTEXT_CHARS = 24000
+
     def __init__(
         self,
         project_id: str,
@@ -80,6 +88,7 @@ class AgentOrchestrator:
         self.branch_name = self._build_pr_branch_name(project_id)
         self.active_pull_request = None
         self._gitea_username: str | None = None
+        existing_repository: dict | None = None
         hinted_issue_number = (related_issue_hint or {}).get('number') if related_issue_hint else None
         self.related_issue_number = hinted_issue_number if hinted_issue_number is not None else self._extract_issue_number(prompt_text)
         self.related_issue: dict | None = DatabaseManager._normalize_issue(related_issue_hint)
@@ -110,9 +119,12 @@ class AgentOrchestrator:
                 latest_ui = self.db_manager._get_latest_ui_snapshot_data(self.history.id)
                 repository = latest_ui.get('repository') if isinstance(latest_ui, dict) else None
                 if isinstance(repository, dict) and repository:
+                    existing_repository = dict(repository)
                     self.repo_owner = repository.get('owner') or self.repo_owner
                     self.repo_name = repository.get('name') or self.repo_name
                     self.repo_url = repository.get('url') or self.repo_url
+                    git_state = latest_ui.get('git') if isinstance(latest_ui.get('git'), dict) else {}
+                    self.branch_name = git_state.get('active_branch') or self.branch_name
             if self.prompt_text:
                 self.prompt_audit = self.db_manager.log_prompt_submission(
                     history_id=self.history.id,
@@ -129,18 +141,26 @@ class AgentOrchestrator:
         self.ui_manager.ui_data["project_root"] = str(self.project_root)
         self.ui_manager.ui_data["features"] = list(self.features)
         self.ui_manager.ui_data["tech_stack"] = list(self.tech_stack)
-        self.ui_manager.ui_data["repository"] = {
+        repository_ui = {
             "owner": self.repo_owner,
             "name": self.repo_name,
             "mode": "project" if settings.use_project_repositories else "shared",
             "status": "pending" if settings.use_project_repositories else "shared",
             "provider": "gitea",
         }
+        if existing_repository:
+            repository_ui.update(existing_repository)
+        self.ui_manager.ui_data["repository"] = repository_ui
         if self.related_issue:
             self.ui_manager.ui_data["related_issue"] = self.related_issue
         if self.active_pull_request:
             self.ui_manager.ui_data["pull_request"] = self.active_pull_request
 
+    def _repository_supports_remote_delivery(self, repository: dict | None = None) -> bool:
+        """Return whether repository metadata supports git push and PR delivery."""
+        repo = repository or self.ui_manager.ui_data.get('repository') or {}
+        return repo.get('mode') in self.REMOTE_READY_REPOSITORY_MODES and repo.get('status') in self.REMOTE_READY_REPOSITORY_STATUSES
+
     def _static_files(self) -> dict[str, str]:
         """Files that do not need prompt-specific generation."""
         return {
@@ -225,6 +245,59 @@ class AgentOrchestrator:
             fallback_used=False,
         )
 
+    def _is_safe_relative_path(self, path: str) -> bool:
+        """Return whether a generated file path is safe to write under the project root."""
+        normalized = str(PurePosixPath((path or '').strip()))
+        if not normalized or normalized in {'.', '..'}:
+            return False
+        if normalized.startswith('/') or normalized.startswith('../') or '/../' in normalized:
+            return False
+        if normalized.startswith('.git/'):
+            return False
+        return True
+
+    def _is_supported_generated_text_file(self, path: str) -> bool:
+        """Return whether the generated path is a supported text artifact."""
+        normalized = PurePosixPath(path)
+        if normalized.name in self.GENERATED_TEXT_FILE_NAMES:
+            return True
+        return normalized.suffix.lower() in self.GENERATED_TEXT_FILE_SUFFIXES
+
+    def _collect_workspace_context(self) -> dict:
+        """Collect a compact, text-only snapshot of the current project workspace."""
+        if not self.project_root.exists():
+            return {'has_existing_files': False, 'files': []}
+
+        files: list[dict] = []
+        total_chars = 0
+        for path in sorted(self.project_root.rglob('*')):
+            if not path.is_file():
+                continue
+            relative_path = path.relative_to(self.project_root).as_posix()
+            if relative_path == '.gitignore':
+                continue
+            if not self._is_safe_relative_path(relative_path) or not self._is_supported_generated_text_file(relative_path):
+                continue
+            try:
+                content = path.read_text(encoding='utf-8')
+            except (UnicodeDecodeError, OSError):
+                continue
+            remaining_chars = self.MAX_WORKSPACE_CONTEXT_CHARS - total_chars
+            if remaining_chars <= 0:
+                break
+            snippet = content[:remaining_chars]
+            files.append(
+                {
+                    'path': relative_path,
+                    'content': snippet,
+                    'truncated': len(snippet) < len(content),
+                }
+            )
+            total_chars += len(snippet)
+            if len(files) >= self.MAX_WORKSPACE_CONTEXT_FILES:
+                break
+        return {'has_existing_files': bool(files), 'files': files}
+
     def _parse_generated_files(self, content: str | None) -> dict[str, str]:
         """Parse an LLM file bundle response into relative-path/content pairs."""
         if not content:
@@ -233,7 +306,6 @@ class AgentOrchestrator:
             parsed = json.loads(content)
         except Exception:
             return {}
-        allowed_paths = set(self._fallback_generated_files().keys())
         generated: dict[str, str] = {}
         if isinstance(parsed, dict) and isinstance(parsed.get('files'), list):
             for item in parsed['files']:
@@ -241,34 +313,68 @@ class AgentOrchestrator:
                     continue
                 path = str(item.get('path') or '').strip()
                 file_content = item.get('content')
-                if path in allowed_paths and isinstance(file_content, str) and file_content.strip():
+                if (
+                    self._is_safe_relative_path(path)
+                    and self._is_supported_generated_text_file(path)
+                    and isinstance(file_content, str)
+                    and file_content.strip()
+                ):
                     generated[path] = file_content.rstrip() + "\n"
         elif isinstance(parsed, dict):
             for path, file_content in parsed.items():
-                if path in allowed_paths and isinstance(file_content, str) and file_content.strip():
-                    generated[str(path)] = file_content.rstrip() + "\n"
+                normalized_path = str(path).strip()
+                if (
+                    self._is_safe_relative_path(normalized_path)
+                    and self._is_supported_generated_text_file(normalized_path)
+                    and isinstance(file_content, str)
+                    and file_content.strip()
+                ):
+                    generated[normalized_path] = file_content.rstrip() + "\n"
         return generated
 
-    async def _generate_prompt_driven_files(self) -> tuple[dict[str, str], dict | None]:
+    async def _generate_prompt_driven_files(self) -> tuple[dict[str, str], dict | None, bool]:
         """Use the configured LLM to generate prompt-specific project files."""
         fallback_files = self._fallback_generated_files()
-        system_prompt = (
-            'You generate small but concrete starter projects. '
-            'Return only JSON. Provide production-like but compact code that directly reflects the user request. '
-            'Include the files README.md, requirements.txt, main.py, and tests/test_app.py. '
-            'Use FastAPI for Python web requests unless the prompt clearly demands something else. '
-            'The test must verify a real behavior from main.py. '
-            'Do not wrap the JSON in markdown fences.'
-        )
-        user_prompt = (
-            f"Project name: {self.project_name}\n"
-            f"Description: {self.description}\n"
-            f"Original prompt: {self.prompt_text or self.description}\n"
-            f"Requested features: {json.dumps(self.features)}\n"
-            f"Preferred tech stack: {json.dumps(self.tech_stack)}\n"
-            f"Related issue: {json.dumps(self.related_issue) if self.related_issue else 'null'}\n\n"
-            "Return JSON shaped as {\"files\": [{\"path\": \"README.md\", \"content\": \"...\"}, ...]}."
-        )
+        workspace_context = self._collect_workspace_context()
+        has_existing_files = bool(workspace_context.get('has_existing_files'))
+        if has_existing_files:
+            system_prompt = (
+                'You modify an existing software repository. '
+                'Return only JSON. Update the smallest necessary set of files to satisfy the new prompt. '
+                'Prefer editing existing files over inventing a new starter app. '
+                'Only return files that should be written. Omit unchanged files. '
+                'Use repository-relative paths and do not wrap the JSON in markdown fences.'
+            )
+            user_prompt = (
+                f"Project name: {self.project_name}\n"
+                f"Description: {self.description}\n"
+                f"Original prompt: {self.prompt_text or self.description}\n"
+                f"Requested features: {json.dumps(self.features)}\n"
+                f"Preferred tech stack: {json.dumps(self.tech_stack)}\n"
+                f"Related issue: {json.dumps(self.related_issue) if self.related_issue else 'null'}\n\n"
+                f"Current workspace snapshot:\n{json.dumps(workspace_context['files'], indent=2)}\n\n"
+                'Return JSON shaped as {"files": [{"path": "relative/path.py", "content": "..."}, ...]}. '
+                'Each file path must be relative to the repository root.'
+            )
+        else:
+            system_prompt = (
+                'You generate small but concrete starter projects. '
+                'Return only JSON. Provide production-like but compact code that directly reflects the user request. '
+                'Include the files README.md, requirements.txt, main.py, and tests/test_app.py. '
+                'Use FastAPI for Python web requests unless the prompt clearly demands something else. '
+                'The test must verify a real behavior from main.py. '
+                'Do not wrap the JSON in markdown fences.'
+            )
+            user_prompt = (
+                f"Project name: {self.project_name}\n"
+                f"Description: {self.description}\n"
+                f"Original prompt: {self.prompt_text or self.description}\n"
+                f"Requested features: {json.dumps(self.features)}\n"
+                f"Preferred tech stack: {json.dumps(self.tech_stack)}\n"
+                f"Related issue: {json.dumps(self.related_issue) if self.related_issue else 'null'}\n\n"
+                'Return JSON shaped as {"files": [{"path": "README.md", "content": "..."}, ...]}. '
+                'At minimum include README.md, requirements.txt, main.py, and tests/test_app.py.'
+            )
         content, trace = await LLMServiceClient().chat_with_trace(
             stage='generation_plan',
             system_prompt=system_prompt,
@@ -278,12 +384,15 @@ class AgentOrchestrator:
                 'project_name': self.project_name,
                 'repository': self.ui_manager.ui_data.get('repository'),
                 'related_issue': self.related_issue,
+                'workspace_files': workspace_context.get('files', []),
             },
             expect_json=True,
         )
         generated_files = self._parse_generated_files(content)
+        if has_existing_files:
+            return generated_files, trace, True
         merged_files = {**fallback_files, **generated_files}
-        return merged_files, trace
+        return merged_files, trace, False
 
     async def _sync_issue_context(self) -> None:
         """Sync repository issues and resolve a linked issue from the prompt when present."""
@@ -309,6 +418,14 @@ class AgentOrchestrator:
             self.db_manager.attach_issue_to_prompt(self.prompt_audit.id, self.related_issue)
 
     async def _ensure_remote_repository(self) -> None:
+        repository = self.ui_manager.ui_data.get("repository") or {}
+        if self._repository_supports_remote_delivery(repository):
+            repository.setdefault("provider", "gitea")
+            repository.setdefault("status", "ready")
+            if repository.get("url"):
+                self.repo_url = repository.get("url")
+            self.ui_manager.ui_data["repository"] = repository
+            return
         if not settings.use_project_repositories:
             self.ui_manager.ui_data["repository"]["status"] = "shared"
             if settings.gitea_repo:
@@ -400,9 +517,7 @@ class AgentOrchestrator:
     async def _push_branch(self, branch: str) -> dict | None:
         """Push a branch to the configured project repository when available."""
         repository = self.ui_manager.ui_data.get('repository') or {}
-        if repository.get('mode') != 'project':
-            return None
-        if repository.get('status') not in {'created', 'exists', 'ready'}:
+        if not self._repository_supports_remote_delivery(repository):
             return None
         if not settings.gitea_token or not self.repo_owner or not self.repo_name:
             return None
@@ -449,7 +564,7 @@ class AgentOrchestrator:
             self.ui_manager.ui_data['pull_request'] = self.active_pull_request
             return self.active_pull_request
         repository = self.ui_manager.ui_data.get('repository') or {}
-        if repository.get('mode') != 'project' or repository.get('status') not in {'created', 'exists', 'ready'}:
+        if not self._repository_supports_remote_delivery(repository):
             return None
 
         title = f"AI delivery for {self.project_name}"
@@ -490,9 +605,7 @@ class AgentOrchestrator:
     async def _push_remote_commit(self, commit_hash: str, commit_message: str, changed_files: list[str], base_commit: str | None) -> dict | None:
         """Push the local commit to the provisioned Gitea repository and build browser links."""
         repository = self.ui_manager.ui_data.get("repository") or {}
-        if repository.get("mode") != "project":
-            return None
-        if repository.get("status") not in {"created", "exists", "ready"}:
+        if not self._repository_supports_remote_delivery(repository):
             return None
         push_result = await self._push_branch(self.branch_name)
         if push_result is None:
@@ -552,6 +665,8 @@ class AgentOrchestrator:
         target.parent.mkdir(parents=True, exist_ok=True)
         change_type = "UPDATE" if target.exists() else "CREATE"
         previous_content = target.read_text(encoding="utf-8") if target.exists() else ""
+        if previous_content == content:
+            return
         diff_text = self._build_diff_text(relative_path, previous_content, content)
         target.write_text(content, encoding="utf-8")
         self.changed_files.append(relative_path)
@@ -660,9 +775,12 @@ class AgentOrchestrator:
 
     async def _generate_code(self) -> None:
         """Generate code using Ollama."""
-        generated_files, trace = await self._generate_prompt_driven_files()
+        change_count_before = len(self.pending_code_changes)
+        generated_files, trace, editing_existing_workspace = await self._generate_prompt_driven_files()
         for relative_path, content in generated_files.items():
             self._write_file(relative_path, content)
+        if editing_existing_workspace and len(self.pending_code_changes) == change_count_before:
+            raise RuntimeError('The LLM response did not produce any file changes for the existing project.')
         fallback_used = bool(trace and trace.get('fallback_used')) or trace is None
         if self.db_manager and self.history and self.prompt_audit and trace:
             self.db_manager.log_llm_trace(

ai_software_factory/database.py

@@ -6,7 +6,7 @@ from urllib.parse import urlparse
 
 from alembic import command
 from alembic.config import Config
-from sqlalchemy import create_engine, event, text
+from sqlalchemy import create_engine, text
 from sqlalchemy.engine import Engine
 from sqlalchemy.orm import Session, sessionmaker
 
@@ -64,20 +64,6 @@ def get_engine() -> Engine:
             pool_timeout=settings.DB_POOL_TIMEOUT or 30
         )
     
-    # Event listener for connection checkout (PostgreSQL only)
-    if not settings.use_sqlite:
-        @event.listens_for(engine, "checkout")
-        def receive_checkout(dbapi_connection, connection_record, connection_proxy):
-            """Log connection checkout for audit purposes."""
-            if settings.LOG_LEVEL in ("DEBUG", "INFO"):
-                print(f"DB Connection checked out from pool")
-        
-        @event.listens_for(engine, "checkin")
-        def receive_checkin(dbapi_connection, connection_record):
-            """Log connection checkin for audit purposes."""
-            if settings.LOG_LEVEL == "DEBUG":
-                print(f"DB Connection returned to pool")
-    
     return engine