release: version 0.9.12 🚀

Containerfile

@@ -12,7 +12,10 @@ WORKDIR /app
 
 # Install system dependencies
 RUN apt-get update && apt-get install -y --no-install-recommends \
+    ca-certificates \
     curl \
+    git \
+    && update-ca-certificates \
     && rm -rf /var/lib/apt/lists/*
 
 # Install dependencies

HISTORY.md

@@ -5,10 +5,77 @@ Changelog
 (unreleased)
 ------------
 
+Fix
+~~~
+- Remove heuristic decision making fallbacks, refs NOISSUE. [Simon
+  Diesenreiter]
+
+
+0.9.11 (2026-04-11)
+-------------------
+
+Fix
+~~~
+- Project association improvements, refs NOISSUE. [Simon Diesenreiter]
+
+Other
+~~~~~
+
+
+0.9.10 (2026-04-11)
+-------------------
+
+Fix
+~~~
+- More git integration fixes, refs NOISSUE. [Simon Diesenreiter]
+
+Other
+~~~~~
+
+
+0.9.9 (2026-04-11)
+------------------
+
+Fix
+~~~
+- Add missing git binary, refs NOISSUE. [Simon Diesenreiter]
+
+Other
+~~~~~
+
+
+0.9.8 (2026-04-11)
+------------------
+
+Fix
+~~~
+- More file change fixes, refs NOISSUE. [Simon Diesenreiter]
+
+Other
+~~~~~
+
+
+0.9.7 (2026-04-11)
+------------------
+
+Fix
+~~~
+- More file generation improvements, refs NOISSUE. [Simon Diesenreiter]
+
+Other
+~~~~~
+
+
+0.9.6 (2026-04-11)
+------------------
+
 Fix
 ~~~
 - Repo onboarding fix, refs NOISSUE. [Simon Diesenreiter]
 
+Other
+~~~~~
+
 
 0.9.5 (2026-04-11)
 ------------------

ai_software_factory/VERSION

@@ -1 +1 @@
-0.9.6
+0.9.12

ai_software_factory/agents/database_manager.py

@@ -2272,6 +2272,7 @@ class DatabaseManager:
                 "timeline": [],
                 "issues": [],
                 "issue_work": [],
+                "ui_data": {},
             }
         
         # Get logs
@@ -2296,6 +2297,7 @@ class DatabaseManager:
         llm_traces = self.get_llm_traces(project_id=project_id)
         correlations = self.get_prompt_change_correlations(project_id=project_id)
         code_changes, local_only_code_changes, orphan_code_changes = self._partition_code_changes(raw_code_changes, commits)
+        ui_data = self._get_latest_ui_snapshot_data(history.id)
         repository = self._get_project_repository(history)
         timeline = self.get_project_timeline(project_id=project_id)
         repository_sync = self.get_repository_sync_status(project_id=project_id)
@@ -2306,6 +2308,10 @@ class DatabaseManager:
             if commit.get('remote_status') == 'pushed' or commit.get('imported_from_remote') or commit.get('commit_url')
         ]
         has_pull_request = any(pr.get('pr_state') == 'open' and not pr.get('merged') for pr in pull_requests)
+        published_non_main_commits = [
+            commit for commit in published_commits
+            if (commit.get('branch') or '').strip() not in {'', 'main', 'master'}
+        ]
         if orphan_code_changes:
             delivery_status = 'uncommitted'
             delivery_message = (
@@ -2318,12 +2324,15 @@ class DatabaseManager:
                 f"{len(local_only_code_changes)} generated file change(s) were committed only in the local workspace. "
                 "No remote repo push was recorded for this prompt yet."
             )
-        elif published_commits and repository and repository.get('mode') == 'project' and not has_pull_request:
+        elif published_non_main_commits and repository and repository.get('mode') == 'project' and not has_pull_request:
             delivery_status = 'pushed_no_pr'
             delivery_message = 'Changes were pushed to the remote repository, but no pull request is currently tracked for review.'
         elif published_commits:
             delivery_status = 'delivered'
+            if has_pull_request:
                 delivery_message = 'Generated changes were published to the tracked repository and are reviewable through the recorded pull request.'
+            else:
+                delivery_message = 'Generated changes were published directly to the tracked repository default branch.'
         else:
             delivery_status = 'pending'
             delivery_message = 'No git commit has been recorded for this project yet.'
@@ -2395,6 +2404,7 @@ class DatabaseManager:
             "repository_sync": repository_sync,
             "issues": issues,
             "issue_work": issue_work,
+            "ui_data": ui_data,
         }
 
     def get_prompt_events(self, project_id: str | None = None, limit: int = 100) -> list[dict]:

ai_software_factory/agents/gitea.py

@@ -58,6 +58,18 @@ class GiteaAPI:
         """Build a Gitea API URL from a relative path."""
         return f"{self.base_url}/api/v1/{path.lstrip('/')}"
 
+    def _normalize_pull_request_head(self, head: str | None, owner: str | None = None) -> str | None:
+        """Return a Gitea-compatible head ref for pull request creation."""
+        normalized = (head or '').strip()
+        if not normalized:
+            return None
+        if ':' in normalized:
+            return normalized
+        effective_owner = (owner or self.owner or '').strip()
+        if not effective_owner:
+            return normalized
+        return f"{effective_owner}:{normalized}"
+
     def build_repo_git_url(self, owner: str | None = None, repo: str | None = None) -> str | None:
         """Build the clone URL for a repository."""
         _owner = owner or self.owner
@@ -222,11 +234,12 @@ class GiteaAPI:
         """Create a pull request."""
         _owner = owner or self.owner
         _repo = repo or self.repo
+        normalized_head = self._normalize_pull_request_head(head, _owner)
         payload = {
             "title": title,
             "body": body,
             "base": base,
-            "head": head or f"{_owner}-{_repo}-ai-gen-{hash(title) % 10000}",
+            "head": normalized_head or f"{_owner}:{_owner}-{_repo}-ai-gen-{hash(title) % 10000}",
         }
         return await self._request("POST", f"repos/{_owner}/{_repo}/pulls", payload)
 
@@ -242,11 +255,12 @@ class GiteaAPI:
         """Synchronously create a pull request."""
         _owner = owner or self.owner
         _repo = repo or self.repo
+        normalized_head = self._normalize_pull_request_head(head, _owner)
         payload = {
             "title": title,
             "body": body,
             "base": base,
-            "head": head or f"{_owner}-{_repo}-ai-gen-{hash(title) % 10000}",
+            "head": normalized_head or f"{_owner}:{_owner}-{_repo}-ai-gen-{hash(title) % 10000}",
         }
         return self._request_sync("POST", f"repos/{_owner}/{_repo}/pulls", payload)
 

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
 
@@ -31,6 +32,10 @@ class AgentOrchestrator:
 
     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,
@@ -119,7 +124,9 @@ class AgentOrchestrator:
                     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
+                    persisted_active_branch = git_state.get('active_branch')
+                    if persisted_active_branch and persisted_active_branch not in {'main', 'master'}:
+                        self.branch_name = persisted_active_branch
             if self.prompt_text:
                 self.prompt_audit = self.db_manager.log_prompt_submission(
                     history_id=self.history.id,
@@ -128,6 +135,7 @@ class AgentOrchestrator:
                     features=self.features,
                     tech_stack=self.tech_stack,
                     actor_name=self.prompt_actor,
+                    source=self.prompt_actor,
                     related_issue={'number': self.related_issue_number} if self.related_issue_number is not None else None,
                     source_context=self.prompt_source_context,
                     routing=self.prompt_routing,
@@ -162,38 +170,18 @@ class AgentOrchestrator:
             ".gitignore": "__pycache__/\n*.pyc\n.venv/\n.pytest_cache/\n.mypy_cache/\n",
         }
 
-    def _fallback_generated_files(self) -> dict[str, str]:
-        """Deterministic fallback files when LLM generation is unavailable."""
-        feature_section = "\n".join(f"- {feature}" for feature in self.features) or "- None specified"
-        tech_section = "\n".join(f"- {tech}" for tech in self.tech_stack) or "- Python"
-        return {
-            "README.md": (
-                f"# {self.project_name}\n\n"
-                f"{self.description}\n\n"
-                "## Features\n"
-                f"{feature_section}\n\n"
-                "## Tech Stack\n"
-                f"{tech_section}\n"
-            ),
-            "requirements.txt": "fastapi\nuvicorn\npytest\n",
-            "main.py": (
-                "from fastapi import FastAPI\n\n"
-                "app = FastAPI(title=\"Generated App\")\n\n"
-                "@app.get('/')\n"
-                "def read_root():\n"
-                f"    return {{'name': '{self.project_name}', 'status': 'generated', 'features': {self.features!r}}}\n"
-            ),
-            "tests/test_app.py": (
-                "from main import read_root\n\n"
-                "def test_read_root():\n"
-                f"    assert read_root()['name'] == '{self.project_name}'\n"
-            ),
-        }
-
     def _build_pr_branch_name(self, project_id: str) -> str:
         """Build a stable branch name used until the PR is merged."""
         return f"ai/{project_id}"
 
+    def _should_use_pull_request_flow(self) -> bool:
+        """Return whether this run should deliver changes through a PR branch."""
+        return self.existing_history is not None or self.active_pull_request is not None
+
+    def _delivery_branch_name(self) -> str:
+        """Return the git branch used for the current delivery."""
+        return self.branch_name if self._should_use_pull_request_flow() else 'main'
+
     def _extract_issue_number(self, prompt_text: str | None) -> int | None:
         """Extract an issue reference from prompt text."""
         if not prompt_text:
@@ -210,7 +198,7 @@ class AgentOrchestrator:
         """Persist the current generation plan as an inspectable trace."""
         if not self.db_manager or not self.history or not self.prompt_audit:
             return
-        planned_files = list(self._static_files().keys()) + list(self._fallback_generated_files().keys())
+        planned_files = list(self._static_files().keys()) + ['README.md', 'requirements.txt', 'main.py', 'tests/test_app.py']
         self.db_manager.log_llm_trace(
             project_id=self.project_id,
             history_id=self.history.id,
@@ -222,7 +210,7 @@ class AgentOrchestrator:
             user_prompt=self.prompt_text or self.description,
             assistant_response=(
                 f"Planned files: {', '.join(planned_files)}. "
-                f"Target branch: {self.branch_name}. "
+                f"Target branch: {self._delivery_branch_name()}. "
                 f"Repository mode: {self.ui_manager.ui_data.get('repository', {}).get('mode', 'unknown')}."
                 + (
                     f" Linked issue: #{self.related_issue.get('number')} {self.related_issue.get('title')}."
@@ -233,13 +221,66 @@ class AgentOrchestrator:
                 'planned_files': planned_files,
                 'features': list(self.features),
                 'tech_stack': list(self.tech_stack),
-                'branch': self.branch_name,
+                'branch': self._delivery_branch_name(),
                 'repository': self.ui_manager.ui_data.get('repository', {}),
                 'related_issue': self.related_issue,
             },
             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:
@@ -248,7 +289,6 @@ 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']:
@@ -256,17 +296,49 @@ 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():
+                normalized_path = str(path).strip()
-                    generated[str(path)] = file_content.rstrip() + "\n"
+                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()
+        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. '
@@ -282,7 +354,8 @@ class AgentOrchestrator:
                 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\": \"...\"}, ...]}."
+                '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',
@@ -293,12 +366,41 @@ 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,
         )
+        raw_generated_paths = self._extract_raw_generated_paths(content)
         generated_files = self._parse_generated_files(content)
-        merged_files = {**fallback_files, **generated_files}
+        accepted_paths = list(generated_files.keys())
-        return merged_files, trace
+        rejected_paths = [path for path in raw_generated_paths if path not in accepted_paths]
+        generation_debug = {
+            'raw_paths': raw_generated_paths,
+            'accepted_paths': accepted_paths,
+            'rejected_paths': rejected_paths,
+            'existing_workspace': has_existing_files,
+        }
+        self.ui_manager.ui_data['generation_debug'] = generation_debug
+        self._append_log(
+            'LLM returned file candidates: '
+            f"raw={raw_generated_paths or []}; accepted={accepted_paths or []}; rejected={rejected_paths or []}."
+        )
+        self._log_system_debug(
+            'generation',
+            'LLM file candidates '
+            f"raw={raw_generated_paths or []}; accepted={accepted_paths or []}; rejected={rejected_paths or []}; "
+            f"existing_workspace={has_existing_files}",
+        )
+        if not content:
+            raise RuntimeError('LLM code generation did not return a usable response.')
+        if not generated_files:
+            raise RuntimeError('LLM code generation did not return any writable files.')
+        if not has_existing_files:
+            required_files = {'README.md', 'requirements.txt', 'main.py', 'tests/test_app.py'}
+            missing_files = sorted(required_files - set(generated_files))
+            if missing_files:
+                raise RuntimeError(f"LLM code generation omitted required starter files: {', '.join(missing_files)}")
+        return generated_files, trace, has_existing_files
 
     async def _sync_issue_context(self) -> None:
         """Sync repository issues and resolve a linked issue from the prompt when present."""
@@ -458,11 +560,15 @@ class AgentOrchestrator:
                 self.ui_manager.ui_data.setdefault('git', {})['remote_error'] = str(exc)
                 self._append_log(f'Initial main push skipped: {exc}')
 
+        delivery_branch = self._delivery_branch_name()
+        if self._should_use_pull_request_flow():
             if self.git_manager.branch_exists(self.branch_name):
                 self.git_manager.checkout_branch(self.branch_name)
             else:
                 self.git_manager.checkout_branch(self.branch_name, create=True, start_point='main')
-        self.ui_manager.ui_data.setdefault('git', {})['active_branch'] = self.branch_name
+        else:
+            self.git_manager.checkout_branch('main')
+        self.ui_manager.ui_data.setdefault('git', {})['active_branch'] = delivery_branch
 
     async def _ensure_pull_request(self) -> dict | None:
         """Create the project pull request on first delivery and reuse it later."""
@@ -479,6 +585,16 @@ class AgentOrchestrator:
             f"Prompt: {self.prompt_text or self.description}\n\n"
             f"Branch: {self.branch_name}"
         )
+        pull_request_debug = self.ui_manager.ui_data.setdefault('git', {}).setdefault('pull_request_debug', {})
+        pull_request_request = {
+            'owner': self.repo_owner,
+            'repo': self.repo_name,
+            'title': title,
+            'body': body,
+            'base': 'main',
+            'head': self.gitea_api._normalize_pull_request_head(self.branch_name, self.repo_owner) or self.branch_name,
+        }
+        pull_request_debug['request'] = pull_request_request
         result = await self.gitea_api.create_pull_request(
             title=title,
             body=body,
@@ -487,7 +603,9 @@ class AgentOrchestrator:
             base='main',
             head=self.branch_name,
         )
+        pull_request_debug['response'] = result
         if result.get('error'):
+            pull_request_debug['status'] = 'error'
             raise RuntimeError(f"Unable to create pull request: {result.get('error')}")
 
         pr_number = result.get('number') or result.get('id') or 0
@@ -502,6 +620,8 @@ class AgentOrchestrator:
             'merged': bool(result.get('merged')),
             'pr_state': result.get('state', 'open'),
         }
+        pull_request_debug['status'] = 'created'
+        pull_request_debug['resolved'] = pr_data
         if self.db_manager and self.history:
             self.db_manager.save_pr_data(self.history.id, pr_data)
         self.active_pull_request = self.db_manager.get_open_pull_request(project_id=self.project_id) if self.db_manager else pr_data
@@ -513,16 +633,17 @@ class AgentOrchestrator:
         repository = self.ui_manager.ui_data.get("repository") or {}
         if not self._repository_supports_remote_delivery(repository):
             return None
-        push_result = await self._push_branch(self.branch_name)
+        delivery_branch = self._delivery_branch_name()
+        push_result = await self._push_branch(delivery_branch)
         if push_result is None:
             return None
-        pull_request = await self._ensure_pull_request()
+        pull_request = await self._ensure_pull_request() if self._should_use_pull_request_flow() else None
         commit_url = self.gitea_api.build_commit_url(commit_hash, owner=self.repo_owner, repo=self.repo_name)
         compare_url = self.gitea_api.build_compare_url(base_commit, commit_hash, owner=self.repo_owner, repo=self.repo_name) if base_commit else None
         remote_record = {
             "status": "pushed",
             "remote": push_result.get('remote'),
-            "branch": self.branch_name,
+            "branch": delivery_branch,
             "commit_url": commit_url,
             "compare_url": compare_url,
             "changed_files": changed_files,
@@ -532,7 +653,10 @@ class AgentOrchestrator:
         repository["last_commit_url"] = commit_url
         if compare_url:
             repository["last_compare_url"] = compare_url
-        self._append_log(f"Pushed generated commit to {self.repo_owner}/{self.repo_name}.")
+        if pull_request:
+            self._append_log(f"Pushed generated commit to {self.repo_owner}/{self.repo_name} and updated the delivery pull request.")
+        else:
+            self._append_log(f"Pushed generated commit directly to {self.repo_owner}/{self.repo_name} on {delivery_branch}.")
         return remote_record
 
     def _build_diff_text(self, relative_path: str, previous_content: str, new_content: str) -> str:
@@ -553,6 +677,35 @@ class AgentOrchestrator:
         if self.db_manager and self.history:
             self.db_manager._log_action(self.history.id, "INFO", message)
 
+    def _log_system_debug(self, component: str, message: str, level: str = 'INFO') -> None:
+        """Persist a system-level debug breadcrumb for generation and git decisions."""
+        if not self.db_manager:
+            return
+        self.db_manager.log_system_event(component=component, level=level, message=f"{self.project_id}: {message}")
+
+    def _extract_raw_generated_paths(self, content: str | None) -> list[str]:
+        """Return all file paths proposed by the LLM response before safety filtering."""
+        if not content:
+            return []
+        try:
+            parsed = json.loads(content)
+        except Exception:
+            return []
+        raw_paths: list[str] = []
+        if isinstance(parsed, dict) and isinstance(parsed.get('files'), list):
+            for item in parsed['files']:
+                if not isinstance(item, dict):
+                    continue
+                path = str(item.get('path') or '').strip()
+                if path:
+                    raw_paths.append(path)
+        elif isinstance(parsed, dict):
+            for path in parsed.keys():
+                normalized_path = str(path).strip()
+                if normalized_path:
+                    raw_paths.append(normalized_path)
+        return raw_paths
+
     def _update_progress(self, progress: int, step: str, message: str) -> None:
         self.progress = progress
         self.current_step = step
@@ -571,6 +724,8 @@ 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)
@@ -679,10 +834,13 @@ 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)
-        fallback_used = bool(trace and trace.get('fallback_used')) or trace is None
+        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'))
         if self.db_manager and self.history and self.prompt_audit and trace:
             self.db_manager.log_llm_trace(
                 project_id=self.project_id,
@@ -697,9 +855,6 @@ class AgentOrchestrator:
                 raw_response=trace.get('raw_response'),
                 fallback_used=fallback_used,
             )
-        if fallback_used:
-            self._append_log('LLM code generation was unavailable; used deterministic scaffolding fallback.')
-        else:
         self._append_log('Application files generated from the prompt with the configured LLM.')
 
     async def _run_tests(self) -> None:
@@ -711,11 +866,25 @@ class AgentOrchestrator:
     async def _commit_to_git(self) -> None:
         """Commit changes to git."""
         unique_files = list(dict.fromkeys(self.changed_files))
+        git_debug = self.ui_manager.ui_data.setdefault('git', {})
         if not unique_files:
+            git_debug.update({
+                'commit_status': 'skipped',
+                'early_exit_reason': 'changed_files_empty',
+                'candidate_files': [],
+            })
+            self._append_log('Git commit skipped: no generated files were marked as changed.')
+            self._log_system_debug('git', 'Commit exited early because changed_files was empty.')
             return
         if not self.git_manager.is_git_available():
-            self.ui_manager.ui_data.setdefault('git', {})['error'] = 'git executable is not available in PATH'
+            git_debug.update({
+                'commit_status': 'error',
+                'early_exit_reason': 'git_unavailable',
+                'candidate_files': unique_files,
+                'error': 'git executable is not available in PATH',
+            })
             self._append_log('Git commit skipped: git executable is not available in PATH')
+            self._log_system_debug('git', 'Commit exited early because git is unavailable.', level='ERROR')
             return
 
         try:
@@ -723,7 +892,23 @@ class AgentOrchestrator:
                 self.git_manager.init_repo()
             base_commit = self.git_manager.current_head_or_none()
             self.git_manager.add_files(unique_files)
-            if not self.git_manager.get_status():
+            status_after_add = self.git_manager.get_status()
+            if not status_after_add:
+                git_debug.update({
+                    'commit_status': 'skipped',
+                    'early_exit_reason': 'clean_after_staging',
+                    'candidate_files': unique_files,
+                    'status_after_add': '',
+                })
+                self._append_log(
+                    'Git commit skipped: working tree was clean after staging candidate files '
+                    f'{unique_files}. No repository diff was created.'
+                )
+                self._log_system_debug(
+                    'git',
+                    'Commit exited early because git status was clean after staging '
+                    f'files={unique_files}',
+                )
                 return
 
             commit_message = f"AI generation for prompt: {self.project_name}"
@@ -734,13 +919,19 @@ class AgentOrchestrator:
                 "files": unique_files,
                 "timestamp": datetime.utcnow().isoformat(),
                 "scope": "local",
-                "branch": self.branch_name,
+                "branch": self._delivery_branch_name(),
             }
+            git_debug.update({
+                'commit_status': 'committed',
+                'early_exit_reason': None,
+                'candidate_files': unique_files,
+                'status_after_add': status_after_add,
+            })
             remote_record = None
             try:
                 remote_record = await self._push_remote_commit(commit_hash, commit_message, unique_files, base_commit)
             except (RuntimeError, subprocess.CalledProcessError, FileNotFoundError) as remote_exc:
-                self.ui_manager.ui_data.setdefault("git", {})["remote_error"] = str(remote_exc)
+                git_debug["remote_error"] = str(remote_exc)
                 self._append_log(f"Remote git push skipped: {remote_exc}")
 
             if remote_record:
@@ -750,8 +941,8 @@ class AgentOrchestrator:
                 if remote_record.get('pull_request'):
                     commit_record['pull_request'] = remote_record['pull_request']
                     self.ui_manager.ui_data['pull_request'] = remote_record['pull_request']
-            self.ui_manager.ui_data.setdefault("git", {})["latest_commit"] = commit_record
+            git_debug["latest_commit"] = commit_record
-            self.ui_manager.ui_data.setdefault("git", {})["commits"] = [commit_record]
+            git_debug["commits"] = [commit_record]
             self._append_log(f"Recorded git commit {commit_hash[:12]} for generated files.")
             if self.db_manager:
                 self.db_manager.log_commit(
@@ -797,7 +988,12 @@ class AgentOrchestrator:
                         commit_url=remote_record.get('commit_url') if remote_record else None,
                     )
         except (RuntimeError, subprocess.CalledProcessError, FileNotFoundError) as exc:
-            self.ui_manager.ui_data.setdefault("git", {})["error"] = str(exc)
+            git_debug.update({
+                'commit_status': 'error',
+                'early_exit_reason': 'commit_exception',
+                'candidate_files': unique_files,
+                'error': str(exc),
+            })
             self._append_log(f"Git commit skipped: {exc}")
 
     async def _create_pr(self) -> None:

ai_software_factory/agents/request_interpreter.py

@@ -28,9 +28,6 @@ class RequestInterpreter:
     GENERIC_PROJECT_NAME_WORDS = {
         'app', 'application', 'harness', 'platform', 'project', 'purpose', 'service', 'solution', 'suite', 'system', 'test', 'tool',
     }
-    PLACEHOLDER_PROJECT_NAME_WORDS = {
-        'generated project', 'new project', 'project', 'temporary name', 'temp name', 'placeholder', 'untitled project',
-    }
 
     def __init__(self, ollama_url: str | None = None, model: str | None = None):
         self.ollama_url = (ollama_url or settings.ollama_url).rstrip('/')
@@ -91,11 +88,18 @@ class RequestInterpreter:
             },
             expect_json=True,
         )
-        if content:
+        if not content:
+            raise RuntimeError('LLM request interpretation did not return a usable response.')
+
         try:
             parsed = json.loads(content)
-                interpreted = self._normalize_interpreted_request(parsed, normalized)
+        except Exception as exc:
+            raise RuntimeError('LLM request interpretation did not return valid JSON.') from exc
+
+        interpreted = self._normalize_interpreted_request(parsed)
         routing = self._normalize_routing(parsed.get('routing'), interpreted, compact_context)
+        if routing.get('intent') == 'continue_project' and routing.get('project_name'):
+            interpreted['name'] = routing['project_name']
         naming_trace = None
         if routing.get('intent') == 'new_project':
             interpreted, routing, naming_trace = await self._refine_new_project_identity(
@@ -109,27 +113,6 @@ class RequestInterpreter:
         if naming_trace is not None:
             trace['project_naming'] = naming_trace
         return interpreted, trace
-            except Exception:
-                pass
-
-        interpreted, routing = self._heuristic_fallback(normalized, compact_context)
-        if routing.get('intent') == 'new_project':
-            constraints = await self._collect_project_identity_constraints(compact_context)
-            routing['repo_name'] = self._ensure_unique_repo_name(routing.get('repo_name') or interpreted.get('name') or 'project', constraints['repo_names'])
-        return interpreted, {
-            'stage': 'request_interpretation',
-            'provider': 'heuristic',
-            'model': self.model,
-            'system_prompt': system_prompt,
-            'user_prompt': user_prompt,
-            'assistant_response': json.dumps({'request': interpreted, 'routing': routing}),
-            'raw_response': {'fallback': 'heuristic', 'llm_trace': trace.get('raw_response') if isinstance(trace, dict) else None},
-            'routing': routing,
-            'context_excerpt': compact_context,
-            'guardrails': trace.get('guardrails') if isinstance(trace, dict) else [],
-            'tool_context': trace.get('tool_context') if isinstance(trace, dict) else [],
-            'fallback_used': True,
-        }
 
     async def _refine_new_project_identity(
         self,
@@ -157,26 +140,20 @@ class RequestInterpreter:
             },
             expect_json=True,
         )
-        if content:
+        if not content:
+            raise RuntimeError('LLM project naming did not return a usable response.')
+
         try:
-                fallback_name = self._preferred_project_name_fallback(prompt_text, interpreted.get('name'))
             parsed = json.loads(content)
-                project_name, repo_name = self._normalize_project_identity(
+        except Exception as exc:
-                    parsed,
+            raise RuntimeError('LLM project naming did not return valid JSON.') from exc
-                    fallback_name=fallback_name,
+
-                )
+        project_name, repo_name = self._normalize_project_identity(parsed)
         repo_name = self._ensure_unique_repo_name(repo_name, constraints['repo_names'])
         interpreted['name'] = project_name
         routing['project_name'] = project_name
         routing['repo_name'] = repo_name
         return interpreted, routing, trace
-            except Exception:
-                pass
-
-        fallback_name = self._preferred_project_name_fallback(prompt_text, interpreted.get('name'))
-        routing['project_name'] = fallback_name
-        routing['repo_name'] = self._ensure_unique_repo_name(self._derive_repo_name(fallback_name), constraints['repo_names'])
-        return interpreted, routing, trace
 
     async def _collect_project_identity_constraints(self, context: dict) -> dict[str, set[str]]:
         """Collect reserved project names and repository slugs from tracked state and Gitea."""
@@ -205,17 +182,19 @@ class RequestInterpreter:
             return set()
         return {str(repo.get('name')).strip() for repo in repos if repo.get('name')}
 
-    def _normalize_interpreted_request(self, interpreted: dict, original_prompt: str) -> dict:
+    def _normalize_interpreted_request(self, interpreted: dict) -> dict:
         """Normalize LLM output into the required request shape."""
         request_payload = interpreted.get('request') if isinstance(interpreted.get('request'), dict) else interpreted
-        name = str(interpreted.get('name') or '').strip() or self._derive_name(original_prompt)
+        if not isinstance(request_payload, dict):
-        if isinstance(request_payload, dict):
+            raise RuntimeError('LLM request interpretation did not include a request object.')
-            name = str(request_payload.get('name') or '').strip() or self._derive_name(original_prompt)
+        name = str(request_payload.get('name') or '').strip()
-        description = str((request_payload or {}).get('description') or '').strip() or original_prompt[:255]
+        description = str(request_payload.get('description') or '').strip()
-        features = self._normalize_list((request_payload or {}).get('features'))
+        if not name:
-        tech_stack = self._normalize_list((request_payload or {}).get('tech_stack'))
+            raise RuntimeError('LLM request interpretation did not provide a project name.')
-        if not features:
+        if not description:
-            features = ['core workflow based on free-form request']
+            raise RuntimeError('LLM request interpretation did not provide a project description.')
+        features = self._normalize_list(request_payload.get('features'))
+        tech_stack = self._normalize_list(request_payload.get('tech_stack'))
         return {
             'name': name[:255],
             'description': description[:255],
@@ -249,6 +228,9 @@ class RequestInterpreter:
     def _normalize_routing(self, routing: dict | None, interpreted: dict, context: dict) -> dict:
         """Normalize routing metadata returned by the LLM."""
         routing = routing or {}
+        intent = str(routing.get('intent') or '').strip()
+        if intent not in {'new_project', 'continue_project'}:
+            raise RuntimeError('LLM request interpretation did not provide a valid routing intent.')
         project_id = routing.get('project_id')
         project_name = routing.get('project_name')
         issue_number = routing.get('issue_number')
@@ -257,6 +239,7 @@ class RequestInterpreter:
         elif isinstance(issue_number, str) and issue_number.isdigit():
             issue_number = int(issue_number)
         matched_project = None
+        if intent == 'continue_project':
             for project in context.get('projects', []):
                 if project_id and project.get('project_id') == project_id:
                     matched_project = project
@@ -264,18 +247,24 @@ class RequestInterpreter:
                 if project_name and project.get('name') == project_name:
                     matched_project = project
                     break
-        intent = str(routing.get('intent') or '').strip() or ('continue_project' if matched_project else 'new_project')
+        elif project_id:
+            matched_project = next(
+                (project for project in context.get('projects', []) if project.get('project_id') == project_id),
+                None,
+            )
+        if intent == 'continue_project' and matched_project is None:
+            raise RuntimeError('LLM selected continue_project without identifying a tracked project from prompt history.')
+        if intent == 'new_project' and matched_project is not None:
+            raise RuntimeError('LLM selected new_project while also pointing at an existing tracked project.')
         normalized = {
             'intent': intent,
             'project_id': matched_project.get('project_id') if matched_project else project_id,
             'project_name': matched_project.get('name') if matched_project else (project_name or interpreted.get('name')),
-            'repo_name': routing.get('repo_name') if intent == 'new_project' else None,
+            'repo_name': str(routing.get('repo_name') or '').strip() or None if intent == 'new_project' else None,
             'issue_number': issue_number,
-            'confidence': routing.get('confidence') or ('medium' if matched_project else 'low'),
+            'confidence': routing.get('confidence') or 'medium',
-            'reasoning_summary': routing.get('reasoning_summary') or ('Matched prior project context' if matched_project else 'No strong prior project match found'),
+            'reasoning_summary': routing.get('reasoning_summary') or '',
         }
-        if normalized['intent'] == 'new_project' and not normalized['repo_name']:
-            normalized['repo_name'] = self._derive_repo_name(normalized['project_name'] or interpreted.get('name') or 'Generated Project')
         return normalized
 
     def _normalize_list(self, value) -> list[str]:
@@ -285,42 +274,6 @@ class RequestInterpreter:
             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()
-        quoted = re.search(r'["\']([^"\']{3,80})["\']', first_line)
-        if quoted:
-            return self._humanize_name(quoted.group(1))
-
-        noun_phrase = re.search(
-            r'(?:build|create|start|make|develop|generate|design|need|want)\s+'
-            r'(?:me\s+|us\s+|an?\s+|the\s+|new\s+|internal\s+|simple\s+|lightweight\s+|modern\s+|web\s+|mobile\s+)*'
-            r'([a-z0-9][a-z0-9\s-]{2,80}?(?:portal|dashboard|app|application|service|tool|system|platform|api|bot|assistant|website|site|workspace|tracker|manager|harness|runner|framework|suite|pipeline|lab))\b',
-            first_line,
-            flags=re.IGNORECASE,
-        )
-        if noun_phrase:
-            return self._humanize_name(noun_phrase.group(1))
-
-        focused_phrase = re.search(
-            r'(?:purpose\s+is\s+to\s+create\s+(?:an?\s+)?)'
-            r'([a-z0-9][a-z0-9\s-]{2,80}?(?:portal|dashboard|app|application|service|tool|system|platform|api|bot|assistant|website|site|workspace|tracker|manager|harness|runner|framework|suite|pipeline|lab))\b',
-            first_line,
-            flags=re.IGNORECASE,
-        )
-        if focused_phrase:
-            return self._humanize_name(focused_phrase.group(1))
-
-        cleaned = re.sub(r'[^A-Za-z0-9 ]+', ' ', first_line)
-        stopwords = {
-            'build', 'create', 'start', 'make', 'develop', 'generate', 'design', 'need', 'want', 'please', 'for', 'our', 'with', 'that', 'this',
-            'new', 'internal', 'simple', 'modern', 'web', 'mobile', 'app', 'application', 'tool', 'system',
-        }
-        tokens = [word for word in cleaned.split() if word and word.lower() not in stopwords]
-        if tokens:
-            return self._humanize_name(' '.join(tokens[:4]))
-        return 'Generated Project'
-
     def _humanize_name(self, raw_name: str) -> str:
         """Normalize a candidate project name into a readable title."""
         cleaned = re.sub(r'[^A-Za-z0-9\s-]+', ' ', raw_name).strip(' -')
@@ -397,15 +350,6 @@ class RequestInterpreter:
                 return False
         return True
 
-    def _preferred_project_name_fallback(self, prompt_text: str, interpreted_name: str | None) -> str:
-        """Pick the best fallback title when the earlier interpretation produced a placeholder."""
-        interpreted_clean = self._humanize_name(str(interpreted_name or '').strip()) if interpreted_name else ''
-        normalized_interpreted = interpreted_clean.lower()
-        if normalized_interpreted and normalized_interpreted not in self.PLACEHOLDER_PROJECT_NAME_WORDS:
-            if not (len(normalized_interpreted.split()) == 1 and normalized_interpreted in self.GENERIC_PROJECT_NAME_WORDS):
-                return interpreted_clean
-        return self._derive_name(prompt_text)
-
     def _ensure_unique_repo_name(self, repo_name: str, reserved_names: set[str]) -> str:
         """Choose a repository slug that does not collide with tracked or remote repositories."""
         base_name = self._derive_repo_name(repo_name)
@@ -416,76 +360,19 @@ class RequestInterpreter:
             suffix += 1
         return f'{base_name}-{suffix}'
 
-    def _normalize_project_identity(self, payload: dict, fallback_name: str) -> tuple[str, str]:
+    def _normalize_project_identity(self, payload: dict) -> tuple[str, str]:
-        """Normalize model-proposed project and repository naming."""
+        """Validate model-proposed project and repository naming."""
-        fallback_project_name = self._humanize_name(str(fallback_name or 'Generated Project'))
         project_candidate = str(payload.get('project_name') or payload.get('name') or '').strip()
-        project_name = fallback_project_name
-        if project_candidate and self._should_use_project_name_candidate(project_candidate, fallback_project_name):
-            project_name = self._humanize_name(project_candidate)
         repo_candidate = str(payload.get('repo_name') or '').strip()
-        repo_name = self._derive_repo_name(project_name)
+        if not project_candidate:
-        if repo_candidate and self._should_use_repo_name_candidate(repo_candidate, project_name):
+            raise RuntimeError('LLM project naming did not provide a project name.')
-            repo_name = self._derive_repo_name(repo_candidate)
+        if not repo_candidate:
-        return project_name, repo_name
+            raise RuntimeError('LLM project naming did not provide a repository slug.')
-
+        if not self._should_use_project_name_candidate(project_candidate, project_candidate):
-    def _heuristic_fallback(self, prompt_text: str, context: dict | None = None) -> tuple[dict, dict]:
+            raise RuntimeError('LLM project naming returned an unusable project name.')
-        """Fallback request extraction when Ollama is unavailable."""
+        if not self._should_use_repo_name_candidate(repo_candidate, project_candidate):
-        lowered = prompt_text.lower()
+            raise RuntimeError('LLM project naming returned an unusable repository slug.')
-        tech_candidates = [
+        return self._humanize_name(project_candidate), self._derive_repo_name(repo_candidate)
-            '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']
-        interpreted = {
-            'name': self._derive_name(prompt_text),
-            'description': sentences[0][:255] if sentences else prompt_text[:255],
-            'features': features,
-            'tech_stack': tech_stack,
-        }
-        routing = self._heuristic_routing(prompt_text, context or {})
-        if routing.get('project_name'):
-            interpreted['name'] = routing['project_name']
-        return interpreted, routing
-
-    def _heuristic_routing(self, prompt_text: str, context: dict) -> dict:
-        """Best-effort routing when the LLM is unavailable."""
-        lowered = prompt_text.lower()
-        explicit_new = any(token in lowered for token in ['new project', 'start a new project', 'create a new project', 'build a new app'])
-        referenced_issue = self._extract_issue_number(prompt_text)
-        recent_history = context.get('recent_chat_history', [])
-        projects = context.get('projects', [])
-        last_project_id = recent_history[0].get('project_id') if recent_history else None
-        last_issue = ((recent_history[0].get('related_issue') or {}).get('number') if recent_history else None)
-
-        matched_project = None
-        for project in projects:
-            name = (project.get('name') or '').lower()
-            repo = ((project.get('repository') or {}).get('name') or '').lower()
-            if name and name in lowered:
-                matched_project = project
-                break
-            if repo and repo in lowered:
-                matched_project = project
-                break
-        if matched_project is None and not explicit_new:
-            follow_up_tokens = ['also', 'continue', 'for this project', 'for that project', 'work on this', 'work on that', 'fix that', 'add this']
-            if any(token in lowered for token in follow_up_tokens) and last_project_id:
-                matched_project = next((project for project in projects if project.get('project_id') == last_project_id), None)
-        issue_number = referenced_issue
-        if issue_number is None and any(token in lowered for token in ['that issue', 'this issue', 'the issue']) and last_issue is not None:
-            issue_number = last_issue
-        intent = 'new_project' if explicit_new or matched_project is None else 'continue_project'
-        return {
-            'intent': intent,
-            'project_id': matched_project.get('project_id') if matched_project else None,
-            'project_name': matched_project.get('name') if matched_project else self._derive_name(prompt_text),
-            'repo_name': None if matched_project else self._derive_repo_name(self._derive_name(prompt_text)),
-            'issue_number': issue_number,
-            'confidence': 'medium' if matched_project or explicit_new else 'low',
-            'reasoning_summary': 'Heuristic routing from chat history and project names.',
-        }
 
     def _extract_issue_number(self, prompt_text: str) -> int | None:
         match = re.search(r'(?:#|issue\s+)(\d+)', prompt_text, flags=re.IGNORECASE)

ai_software_factory/dashboard_ui.py

@@ -214,6 +214,70 @@ def _render_commit_list(commits: list[dict]) -> None:
                     ui.link('Open compare view', compare_url, new_tab=True)
 
 
+def _render_generation_diagnostics(ui_data: dict | None) -> None:
+    """Render generation and git diagnostics from the latest UI snapshot."""
+    snapshot = ui_data if isinstance(ui_data, dict) else {}
+    generation_debug = snapshot.get('generation_debug') if isinstance(snapshot.get('generation_debug'), dict) else {}
+    git_debug = snapshot.get('git') if isinstance(snapshot.get('git'), dict) else {}
+
+    if not generation_debug and not git_debug:
+        ui.label('No generation diagnostics captured yet.').classes('factory-muted')
+        return
+
+    def _render_path_row(label: str, values: list[str]) -> None:
+        text = ', '.join(values) if values else 'none'
+        ui.label(f'{label}: {text}').classes('factory-muted' if values else 'factory-code')
+
+    with ui.column().classes('gap-3 w-full'):
+        if generation_debug:
+            with ui.column().classes('gap-1'):
+                ui.label('Generation filtering').style('font-weight: 700; color: #2f241d;')
+                ui.label(
+                    'Existing workspace: '
+                    + ('yes' if generation_debug.get('existing_workspace') else 'no')
+                ).classes('factory-muted')
+                _render_path_row('Raw paths', generation_debug.get('raw_paths') or [])
+                _render_path_row('Accepted paths', generation_debug.get('accepted_paths') or [])
+                _render_path_row('Rejected paths', generation_debug.get('rejected_paths') or [])
+        if git_debug:
+            with ui.column().classes('gap-1'):
+                ui.label('Git outcome').style('font-weight: 700; color: #2f241d;')
+                if git_debug.get('commit_status'):
+                    with ui.row().classes('items-center gap-2'):
+                        ui.label(git_debug['commit_status']).classes('factory-chip')
+                        if git_debug.get('early_exit_reason'):
+                            ui.label(git_debug['early_exit_reason']).classes('factory-chip')
+                if git_debug.get('candidate_files') is not None:
+                    _render_path_row('Candidate files', git_debug.get('candidate_files') or [])
+                latest_commit = git_debug.get('latest_commit') if isinstance(git_debug.get('latest_commit'), dict) else {}
+                if latest_commit:
+                    ui.label(
+                        f"Latest commit: {(latest_commit.get('hash') or 'unknown')[:12]} · {latest_commit.get('scope') or 'local'}"
+                    ).classes('factory-muted')
+                if git_debug.get('status_after_add'):
+                    with ui.expansion('Git status after staging').classes('w-full q-mt-sm'):
+                        ui.label(str(git_debug['status_after_add'])).classes('factory-code')
+                if git_debug.get('remote_error'):
+                    ui.label(f"Remote push error: {git_debug['remote_error']}").classes('factory-code')
+                if git_debug.get('error'):
+                    ui.label(f"Git error: {git_debug['error']}").classes('factory-code')
+                pull_request_debug = git_debug.get('pull_request_debug') if isinstance(git_debug.get('pull_request_debug'), dict) else {}
+                if pull_request_debug:
+                    ui.label('Pull request creation').style('font-weight: 700; color: #2f241d;')
+                    if pull_request_debug.get('status'):
+                        ui.label(str(pull_request_debug['status'])).classes('factory-chip')
+                    if pull_request_debug.get('request'):
+                        with ui.expansion('PR request payload').classes('w-full q-mt-sm'):
+                            ui.label(json.dumps(pull_request_debug['request'], indent=2, sort_keys=True)).classes('factory-code')
+                    if pull_request_debug.get('response'):
+                        with ui.expansion('PR API response').classes('w-full q-mt-sm'):
+                            ui.label(json.dumps(pull_request_debug['response'], indent=2, sort_keys=True)).classes('factory-code')
+                    if pull_request_debug.get('resolved'):
+                        resolved = pull_request_debug['resolved']
+                        if resolved.get('pr_url'):
+                            ui.link('Open pull request', resolved['pr_url'], new_tab=True).classes('factory-code')
+
+
 def _render_timeline(events: list[dict]) -> None:
     """Render a mixed project timeline."""
     if not events:
@@ -1576,6 +1640,9 @@ def create_dashboard():
                             'Sync Repo Activity',
                             on_click=lambda _=None, project_id=project['project_id']: sync_project_repository_action(project_id),
                         ).props('outline color=secondary').classes('q-mt-md')
+                    with ui.card().classes('q-pa-md'):
+                        ui.label('Generation Diagnostics').style('font-weight: 700; color: #3a281a;')
+                        _render_generation_diagnostics(project_bundle.get('ui_data'))
 
     @ui.refreshable
     def render_archived_panel() -> None:
@@ -1642,6 +1709,9 @@ def create_dashboard():
                     with ui.card().classes('q-pa-md'):
                         ui.label('Repository').style('font-weight: 700; color: #3a281a;')
                         _render_repository_block(project_bundle.get('repository') or project.get('repository'))
+                    with ui.card().classes('q-pa-md'):
+                        ui.label('Generation Diagnostics').style('font-weight: 700; color: #3a281a;')
+                        _render_generation_diagnostics(project_bundle.get('ui_data'))
                     with ui.card().classes('q-pa-md'):
                         ui.label('Prompt').style('font-weight: 700; color: #3a281a;')
                         prompts = project_bundle.get('prompts', [])

ai_software_factory/main.py

@@ -187,7 +187,6 @@ async def _derive_project_id_for_request(
 ) -> 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"
@@ -202,14 +201,16 @@ async def _derive_project_id_for_request(
         tool_context_input={'projects': existing_projects},
         expect_json=True,
     )
-    if content:
+    if not content:
+        raise RuntimeError('LLM project id naming did not return a usable response.')
     try:
         parsed = json.loads(content)
-            candidate = parsed.get('project_id') or parsed.get('slug') or request.name
+    except Exception as exc:
-            return _ensure_unique_identifier(str(candidate), reserved_ids), trace
+        raise RuntimeError('LLM project id naming did not return valid JSON.') from exc
-        except Exception:
+    candidate = str(parsed.get('project_id') or parsed.get('slug') or '').strip()
-            pass
+    if not candidate:
-    return fallback_id, trace
+        raise RuntimeError('LLM project id naming did not provide a project id.')
+    return _ensure_unique_identifier(candidate, reserved_ids), trace
 
 
 def _serialize_project(history: ProjectHistory) -> dict:
@@ -241,6 +242,17 @@ def _serialize_project_log(log: ProjectLog) -> dict:
     }
 
 
+def _ensure_summary_mentions_pull_request(summary_message: str, pull_request: dict | None) -> str:
+    """Append the pull request URL to chat summaries when one exists."""
+    if not isinstance(pull_request, dict):
+        return summary_message
+    pr_url = (pull_request.get('pr_url') or '').strip()
+    if not pr_url or pr_url in summary_message:
+        return summary_message
+    separator = '' if summary_message.endswith(('.', '!', '?')) else '.'
+    return f"{summary_message}{separator} Review PR: {pr_url}"
+
+
 def _serialize_system_log(log: SystemLog) -> dict:
     """Serialize a system log row."""
     return {
@@ -306,7 +318,7 @@ async def _run_generation(
     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 not is_explicit_new_project and manager.get_open_pull_request(project_id=reusable_history.project_id):
+    elif reusable_history and not is_explicit_new_project:
         project_id = reusable_history.project_id
     else:
         if is_explicit_new_project or prompt_text:
@@ -348,6 +360,8 @@ async def _run_generation(
     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['generation_debug'] = ((result.get('ui_data') or {}).get('generation_debug'))
+    response_data['git_debug'] = ((result.get('ui_data') or {}).get('git'))
     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)))
@@ -389,6 +403,7 @@ async def _run_generation(
         'logs': [log.get('message', '') for log in response_data.get('logs', []) if isinstance(log, dict)],
     }
     summary_message, summary_trace = await ChangeSummaryGenerator().summarize_with_trace(summary_context)
+    summary_message = _ensure_summary_mentions_pull_request(summary_message, response_data.get('pull_request'))
     if orchestrator.db_manager and orchestrator.history and orchestrator.prompt_audit:
         orchestrator.db_manager.log_llm_trace(
             project_id=project_id,