Merge pull request #20 from FuzzingLabs/dev

Release: v0.7.1 - Worker fixes, monitor consolidation, and findings improvements

backend/src/api/runs.py

@@ -55,9 +55,12 @@ async def get_run_status(
         is_failed = workflow_status == "FAILED"
         is_running = workflow_status == "RUNNING"
 
+        # Extract workflow name from run_id (format: workflow_name-unique_id)
+        workflow_name = run_id.rsplit('-', 1)[0] if '-' in run_id else "unknown"
+
         return WorkflowStatus(
             run_id=run_id,
-            workflow="unknown",  # Temporal doesn't track workflow name in status
+            workflow=workflow_name,
             status=workflow_status,
             is_completed=is_completed,
             is_failed=is_failed,
@@ -123,6 +126,9 @@ async def get_run_findings(
         else:
             sarif = {}
 
+        # Extract workflow name from run_id (format: workflow_name-unique_id)
+        workflow_name = run_id.rsplit('-', 1)[0] if '-' in run_id else "unknown"
+
         # Metadata
         metadata = {
             "completion_time": status.get("close_time"),
@@ -130,7 +136,7 @@ async def get_run_findings(
         }
 
         return WorkflowFindings(
-            workflow="unknown",
+            workflow=workflow_name,
             run_id=run_id,
             sarif=sarif,
             metadata=metadata

backend/src/api/workflows.py

@@ -566,7 +566,6 @@ async def get_workflow_worker_info(
     return {
         "workflow": workflow_name,
         "vertical": vertical,
-        "worker_container": f"fuzzforge-worker-{vertical}",
         "worker_service": f"worker-{vertical}",
         "task_queue": f"{vertical}-queue",
         "required": True

cli/src/fuzzforge_cli/commands/findings.py

@@ -140,11 +140,145 @@ def get_findings(
         else:  # table format
             display_findings_table(findings.sarif)
 
+            # Suggest export command and show command
+            console.print(f"\n💡 View full details of a finding: [bold cyan]ff finding show {run_id} --rule <rule-id>[/bold cyan]")
+            console.print(f"💡 Export these findings: [bold cyan]ff findings export {run_id} --format sarif[/bold cyan]")
+            console.print("   Supported formats: [cyan]sarif[/cyan] (standard), [cyan]json[/cyan], [cyan]csv[/cyan], [cyan]html[/cyan]")
+
     except Exception as e:
         console.print(f"❌ Failed to get findings: {e}", style="red")
         raise typer.Exit(1)
 
 
+def show_finding(
+    run_id: str = typer.Argument(..., help="Run ID to get finding from"),
+    rule_id: str = typer.Option(..., "--rule", "-r", help="Rule ID of the specific finding to show")
+):
+    """
+    🔍 Show detailed information about a specific finding
+
+    This function is registered as a command in main.py under the finding (singular) command group.
+    """
+    try:
+        require_project()
+        validate_run_id(run_id)
+
+        # Try to get from database first, fallback to API
+        db = get_project_db()
+        findings_data = None
+        if db:
+            findings_data = db.get_findings(run_id)
+
+        if not findings_data:
+            with get_client() as client:
+                console.print(f"🔍 Fetching findings for run: {run_id}")
+                findings = client.get_run_findings(run_id)
+                sarif_data = findings.sarif
+        else:
+            sarif_data = findings_data.sarif_data
+
+        # Find the specific finding by rule_id
+        runs = sarif_data.get("runs", [])
+        if not runs:
+            console.print("❌ No findings data available", style="red")
+            raise typer.Exit(1)
+
+        run_data = runs[0]
+        results = run_data.get("results", [])
+        tool = run_data.get("tool", {}).get("driver", {})
+
+        # Search for matching finding
+        matching_finding = None
+        for result in results:
+            if result.get("ruleId") == rule_id:
+                matching_finding = result
+                break
+
+        if not matching_finding:
+            console.print(f"❌ No finding found with rule ID: {rule_id}", style="red")
+            console.print(f"💡 Use [bold cyan]ff findings get {run_id}[/bold cyan] to see all findings", style="dim")
+            raise typer.Exit(1)
+
+        # Display detailed finding
+        display_finding_detail(matching_finding, tool, run_id)
+
+    except Exception as e:
+        console.print(f"❌ Failed to get finding: {e}", style="red")
+        raise typer.Exit(1)
+
+
+def display_finding_detail(finding: Dict[str, Any], tool: Dict[str, Any], run_id: str):
+    """Display detailed information about a single finding"""
+    rule_id = finding.get("ruleId", "unknown")
+    level = finding.get("level", "note")
+    message = finding.get("message", {})
+    message_text = message.get("text", "No summary available")
+    message_markdown = message.get("markdown", message_text)
+
+    # Get location
+    locations = finding.get("locations", [])
+    location_str = "Unknown location"
+    code_snippet = None
+
+    if locations:
+        physical_location = locations[0].get("physicalLocation", {})
+        artifact_location = physical_location.get("artifactLocation", {})
+        region = physical_location.get("region", {})
+
+        file_path = artifact_location.get("uri", "")
+        if file_path:
+            location_str = file_path
+            if region.get("startLine"):
+                location_str += f":{region['startLine']}"
+                if region.get("startColumn"):
+                    location_str += f":{region['startColumn']}"
+
+        # Get code snippet if available
+        if region.get("snippet", {}).get("text"):
+            code_snippet = region["snippet"]["text"].strip()
+
+    # Get severity style
+    severity_color = {
+        "error": "red",
+        "warning": "yellow",
+        "note": "blue",
+        "info": "cyan"
+    }.get(level.lower(), "white")
+
+    # Build detailed content
+    content_lines = []
+    content_lines.append(f"[bold]Rule ID:[/bold] {rule_id}")
+    content_lines.append(f"[bold]Severity:[/bold] [{severity_color}]{level.upper()}[/{severity_color}]")
+    content_lines.append(f"[bold]Location:[/bold] {location_str}")
+    content_lines.append(f"[bold]Tool:[/bold] {tool.get('name', 'Unknown')} v{tool.get('version', 'unknown')}")
+    content_lines.append(f"[bold]Run ID:[/bold] {run_id}")
+    content_lines.append("")
+    content_lines.append(f"[bold]Summary:[/bold]")
+    content_lines.append(message_text)
+    content_lines.append("")
+    content_lines.append(f"[bold]Description:[/bold]")
+    content_lines.append(message_markdown)
+
+    if code_snippet:
+        content_lines.append("")
+        content_lines.append(f"[bold]Code Snippet:[/bold]")
+        content_lines.append(f"[dim]{code_snippet}[/dim]")
+
+    content = "\n".join(content_lines)
+
+    # Display in panel
+    console.print()
+    console.print(Panel(
+        content,
+        title=f"🔍 Finding Detail",
+        border_style=severity_color,
+        box=box.ROUNDED,
+        padding=(1, 2)
+    ))
+    console.print()
+    console.print(f"💡 Export this run: [bold cyan]ff findings export {run_id} --format sarif[/bold cyan]")
+
+
 def display_findings_table(sarif_data: Dict[str, Any]):
     """Display SARIF findings in a rich table format"""
     runs = sarif_data.get("runs", [])
@@ -195,8 +329,8 @@ def display_findings_table(sarif_data: Dict[str, Any]):
     # Detailed results - Rich Text-based table with proper emoji alignment
     results_table = Table(box=box.ROUNDED)
     results_table.add_column("Severity", width=12, justify="left", no_wrap=True)
-    results_table.add_column("Rule", width=25, justify="left", style="bold cyan", no_wrap=True)
-    results_table.add_column("Message", width=55, justify="left", no_wrap=True)
+    results_table.add_column("Rule", justify="left", style="bold cyan", no_wrap=True)
+    results_table.add_column("Message", width=45, justify="left", no_wrap=True)
     results_table.add_column("Location", width=20, justify="left", style="dim", no_wrap=True)
 
     for result in results[:50]:  # Limit to first 50 results
@@ -224,18 +358,16 @@ def display_findings_table(sarif_data: Dict[str, Any]):
         severity_text = Text(level.upper(), style=severity_style(level))
         severity_text.truncate(12, overflow="ellipsis")
 
-        rule_text = Text(rule_id)
-        rule_text.truncate(25, overflow="ellipsis")
-
+        # Show full rule ID without truncation
         message_text = Text(message)
-        message_text.truncate(55, overflow="ellipsis")
+        message_text.truncate(45, overflow="ellipsis")
 
         location_text = Text(location_str)
         location_text.truncate(20, overflow="ellipsis")
 
         results_table.add_row(
             severity_text,
-            rule_text,
+            rule_id,  # Pass string directly to show full UUID
             message_text,
             location_text
         )
@@ -307,16 +439,20 @@ def findings_history(
 def export_findings(
     run_id: str = typer.Argument(..., help="Run ID to export findings for"),
     format: str = typer.Option(
-        "json", "--format", "-f",
-        help="Export format: json, csv, html, sarif"
+        "sarif", "--format", "-f",
+        help="Export format: sarif (standard), json, csv, html"
     ),
     output: Optional[str] = typer.Option(
         None, "--output", "-o",
-        help="Output file path (defaults to findings-<run-id>.<format>)"
+        help="Output file path (defaults to findings-<run-id>-<timestamp>.<format>)"
     )
 ):
     """
     📤 Export security findings in various formats
+
+    SARIF is the standard format for security findings and is recommended
+    for interoperability with other security tools. Filenames are automatically
+    made unique with timestamps to prevent overwriting previous exports.
     """
     db = get_project_db()
     if not db:
@@ -334,9 +470,10 @@ def export_findings(
         else:
             sarif_data = findings_data.sarif_data
 
-        # Generate output filename
+        # Generate output filename with timestamp for uniqueness
         if not output:
-            output = f"findings-{run_id[:8]}.{format}"
+            timestamp = datetime.now().strftime("%Y%m%d-%H%M%S")
+            output = f"findings-{run_id[:8]}-{timestamp}.{format}"
 
         output_path = Path(output)
 

cli/src/fuzzforge_cli/commands/monitor.py

@@ -59,66 +59,6 @@ def format_number(num: int) -> str:
         return str(num)
 
 
-@app.command("stats")
-def fuzzing_stats(
-    run_id: str = typer.Argument(..., help="Run ID to get statistics for"),
-    refresh: int = typer.Option(
-        5, "--refresh", "-r",
-        help="Refresh interval in seconds"
-    ),
-    once: bool = typer.Option(
-        False, "--once",
-        help="Show stats once and exit"
-    )
-):
-    """
-    📊 Show current fuzzing statistics for a run
-    """
-    try:
-        with get_client() as client:
-            if once:
-                # Show stats once
-                stats = client.get_fuzzing_stats(run_id)
-                display_stats_table(stats)
-            else:
-                # Live updating stats
-                console.print(f"📊 [bold]Live Fuzzing Statistics[/bold] (Run: {run_id[:12]}...)")
-                console.print(f"Refreshing every {refresh}s. Press Ctrl+C to stop.\n")
-
-                with Live(auto_refresh=False, console=console) as live:
-                    while True:
-                        try:
-                            # Check workflow status
-                            run_status = client.get_run_status(run_id)
-                            stats = client.get_fuzzing_stats(run_id)
-                            table = create_stats_table(stats)
-                            live.update(table, refresh=True)
-
-                            # Exit if workflow completed or failed
-                            if getattr(run_status, 'is_completed', False) or getattr(run_status, 'is_failed', False):
-                                final_status = getattr(run_status, 'status', 'Unknown')
-                                if getattr(run_status, 'is_completed', False):
-                                    console.print("\n✅ [bold green]Workflow completed[/bold green]", style="green")
-                                else:
-                                    console.print(f"\n⚠️ [bold yellow]Workflow ended[/bold yellow] | Status: {final_status}", style="yellow")
-                                break
-
-                            time.sleep(refresh)
-                        except KeyboardInterrupt:
-                            console.print("\n📊 Monitoring stopped", style="yellow")
-                            break
-
-    except Exception as e:
-        console.print(f"❌ Failed to get fuzzing stats: {e}", style="red")
-        raise typer.Exit(1)
-
-
-def display_stats_table(stats):
-    """Display stats in a simple table"""
-    table = create_stats_table(stats)
-    console.print(table)
-
-
 def create_stats_table(stats) -> Panel:
     """Create a rich table for fuzzing statistics"""
     # Create main stats table
@@ -266,8 +206,8 @@ def crash_reports(
         raise typer.Exit(1)
 
 
-def _live_monitor(run_id: str, refresh: int):
-    """Helper for live monitoring with inline real-time display"""
+def _live_monitor(run_id: str, refresh: int, once: bool = False, style: str = "inline"):
+    """Helper for live monitoring with inline real-time display or table display"""
     with get_client() as client:
         start_time = time.time()
 
@@ -319,16 +259,29 @@ def _live_monitor(run_id: str, refresh: int):
                 self.elapsed_time = 0
                 self.last_crash_time = None
 
-        with Live(auto_refresh=False, console=console) as live:
-            # Initial fetch
-            try:
-                run_status = client.get_run_status(run_id)
-                stats = client.get_fuzzing_stats(run_id)
-            except Exception:
-                stats = FallbackStats(run_id)
-                run_status = type("RS", (), {"status":"Unknown","is_completed":False,"is_failed":False})()
+        # Initial fetch
+        try:
+            run_status = client.get_run_status(run_id)
+            stats = client.get_fuzzing_stats(run_id)
+        except Exception:
+            stats = FallbackStats(run_id)
+            run_status = type("RS", (), {"status":"Unknown","is_completed":False,"is_failed":False})()
 
-            live.update(render_inline_stats(run_status, stats), refresh=True)
+        # Handle --once mode: show stats once and exit
+        if once:
+            if style == "table":
+                console.print(create_stats_table(stats))
+            else:
+                console.print(render_inline_stats(run_status, stats))
+            return
+
+        # Live monitoring mode
+        with Live(auto_refresh=False, console=console) as live:
+            # Render based on style
+            if style == "table":
+                live.update(create_stats_table(stats), refresh=True)
+            else:
+                live.update(render_inline_stats(run_status, stats), refresh=True)
 
             # Polling loop
             consecutive_errors = 0
@@ -354,8 +307,11 @@ def _live_monitor(run_id: str, refresh: int):
                     except Exception:
                         stats = FallbackStats(run_id)
 
-                    # Update display
-                    live.update(render_inline_stats(run_status, stats), refresh=True)
+                    # Update display based on style
+                    if style == "table":
+                        live.update(create_stats_table(stats), refresh=True)
+                    else:
+                        live.update(render_inline_stats(run_status, stats), refresh=True)
 
                     # Check if completed
                     if getattr(run_status, 'is_completed', False) or getattr(run_status, 'is_failed', False):
@@ -386,17 +342,36 @@ def live_monitor(
     refresh: int = typer.Option(
         2, "--refresh", "-r",
         help="Refresh interval in seconds"
+    ),
+    once: bool = typer.Option(
+        False, "--once",
+        help="Show stats once and exit"
+    ),
+    style: str = typer.Option(
+        "inline", "--style",
+        help="Display style: 'inline' (default) or 'table'"
     )
 ):
     """
-    📺 Real-time inline monitoring with live statistics updates
+    📺 Real-time monitoring with live statistics updates
+
+    Display styles:
+    - inline: Visual inline display with emojis (default)
+    - table: Clean table-based display
+
+    Use --once to show stats once without continuous monitoring (useful for scripts)
     """
     try:
-        _live_monitor(run_id, refresh)
+        # Validate style
+        if style not in ["inline", "table"]:
+            console.print(f"❌ Invalid style: {style}. Must be 'inline' or 'table'", style="red")
+            raise typer.Exit(1)
+
+        _live_monitor(run_id, refresh, once, style)
     except KeyboardInterrupt:
         console.print("\n\n📊 Monitoring stopped by user.", style="yellow")
     except Exception as e:
-        console.print(f"\n❌ Failed to start live monitoring: {e}", style="red")
+        console.print(f"\n❌ Failed to start monitoring: {e}", style="red")
         raise typer.Exit(1)
 
 
@@ -423,6 +398,5 @@ def monitor_callback(ctx: typer.Context):
     console = Console()
     console.print("📊 [bold cyan]Monitor Command[/bold cyan]")
     console.print("\nAvailable subcommands:")
-    console.print("  • [cyan]ff monitor stats <run-id>[/cyan] - Show execution statistics")
+    console.print("  • [cyan]ff monitor live <run-id>[/cyan] - Monitor with live updates (supports --once, --style)")
     console.print("  • [cyan]ff monitor crashes <run-id>[/cyan] - Show crash reports")
-    console.print("  • [cyan]ff monitor live <run-id>[/cyan] - Real-time inline monitoring")

cli/src/fuzzforge_cli/commands/workflow_exec.py

@@ -365,7 +365,7 @@ def execute_workflow(
     should_auto_start = auto_start if auto_start is not None else config.workers.auto_start_workers
     should_auto_stop = auto_stop if auto_stop is not None else config.workers.auto_stop_workers
 
-    worker_container = None  # Track for cleanup
+    worker_service = None  # Track for cleanup
     worker_mgr = None
     wait_completed = False  # Track if wait completed successfully
 
@@ -384,7 +384,6 @@ def execute_workflow(
                 )
 
                 # Ensure worker is running
-                worker_container = worker_info["worker_container"]
                 worker_service = worker_info.get("worker_service", f"worker-{worker_info['vertical']}")
                 if not worker_mgr.ensure_worker_running(worker_info, auto_start=should_auto_start):
                     console.print(
@@ -434,7 +433,7 @@ def execute_workflow(
                 # Don't fail the whole operation if database save fails
                 console.print(f"⚠️  Failed to save execution to database: {e}", style="yellow")
 
-            console.print(f"\n💡 Monitor progress: [bold cyan]fuzzforge monitor stats {response.run_id}[/bold cyan]")
+            console.print(f"\n💡 Monitor progress: [bold cyan]fuzzforge monitor live {response.run_id}[/bold cyan]")
             console.print(f"💡 Check status: [bold cyan]fuzzforge workflow status {response.run_id}[/bold cyan]")
 
             # Suggest --live for fuzzing workflows
@@ -461,7 +460,7 @@ def execute_workflow(
                     console.print("\n⏹️  Live monitoring stopped (execution continues in background)", style="yellow")
                 except Exception as e:
                     console.print(f"⚠️  Failed to start live monitoring: {e}", style="yellow")
-                    console.print(f"💡 You can still monitor manually: [bold cyan]fuzzforge monitor {response.run_id}[/bold cyan]")
+                    console.print(f"💡 You can still monitor manually: [bold cyan]fuzzforge monitor live {response.run_id}[/bold cyan]")
 
             # Wait for completion if requested
             elif wait:
@@ -527,11 +526,11 @@ def execute_workflow(
         handle_error(e, "executing workflow")
     finally:
         # Stop worker if auto-stop is enabled and wait completed
-        if should_auto_stop and worker_container and worker_mgr and wait_completed:
+        if should_auto_stop and worker_service and worker_mgr and wait_completed:
             try:
                 console.print("\n🛑 Stopping worker (auto-stop enabled)...")
-                if worker_mgr.stop_worker(worker_container):
-                    console.print(f"✅ Worker stopped: {worker_container}")
+                if worker_mgr.stop_worker(worker_service):
+                    console.print(f"✅ Worker stopped: {worker_service}")
             except Exception as e:
                 console.print(
                     f"⚠️  Failed to stop worker: {e}",
@@ -608,7 +607,7 @@ def workflow_status(
 
         # Show next steps
         if status.is_running:
-            console.print(f"\n💡 Monitor live: [bold cyan]fuzzforge monitor {execution_id}[/bold cyan]")
+            console.print(f"\n💡 Monitor live: [bold cyan]fuzzforge monitor live {execution_id}[/bold cyan]")
         elif status.is_completed:
             console.print(f"💡 View findings: [bold cyan]fuzzforge finding {execution_id}[/bold cyan]")
         elif status.is_failed:
@@ -770,7 +769,7 @@ def retry_workflow(
             except Exception as e:
                 console.print(f"⚠️  Failed to save execution to database: {e}", style="yellow")
 
-            console.print(f"\n💡 Monitor progress: [bold cyan]fuzzforge monitor stats {response.run_id}[/bold cyan]")
+            console.print(f"\n💡 Monitor progress: [bold cyan]fuzzforge monitor live {response.run_id}[/bold cyan]")
 
     except Exception as e:
         handle_error(e, "retrying workflow")

cli/src/fuzzforge_cli/main.py

@@ -260,57 +260,17 @@ def workflow_main():
 
 # === Finding commands (singular) ===
 
-@finding_app.command("export")
-def export_finding(
-    execution_id: Optional[str] = typer.Argument(None, help="Execution ID (defaults to latest)"),
-    format: str = typer.Option(
-        "sarif", "--format", "-f",
-        help="Export format: sarif, json, csv"
-    ),
-    output: Optional[str] = typer.Option(
-        None, "--output", "-o",
-        help="Output file (defaults to stdout)"
-    )
+@finding_app.command("show")
+def show_finding_detail(
+    run_id: str = typer.Argument(..., help="Run ID to get finding from"),
+    rule_id: str = typer.Option(..., "--rule", "-r", help="Rule ID of the specific finding to show")
 ):
     """
-    📤 Export findings to file
+    🔍 Show detailed information about a specific finding
     """
-    from .commands.findings import export_findings
-    from .database import get_project_db
-    from .exceptions import require_project
+    from .commands.findings import show_finding
+    show_finding(run_id=run_id, rule_id=rule_id)
 
-    try:
-        require_project()
-
-        # If no ID provided, get the latest
-        if not execution_id:
-            db = get_project_db()
-            if db:
-                recent_runs = db.list_runs(limit=1)
-                if recent_runs:
-                    execution_id = recent_runs[0].run_id
-                    console.print(f"🔍 Using most recent execution: {execution_id}")
-                else:
-                    console.print("⚠️  No findings found in project database", style="yellow")
-                    return
-            else:
-                console.print("❌ No project database found", style="red")
-                return
-
-        export_findings(run_id=execution_id, format=format, output=output)
-    except Exception as e:
-        console.print(f"❌ Failed to export findings: {e}", style="red")
-
-
-@finding_app.command("analyze")
-def analyze_finding(
-    finding_id: Optional[str] = typer.Argument(None, help="Finding ID to analyze")
-):
-    """
-    🤖 AI analysis of a finding
-    """
-    from .commands.ai import analyze_finding as ai_analyze
-    ai_analyze(finding_id)
 
 @finding_app.callback(invoke_without_command=True)
 def finding_main(
@@ -320,9 +280,9 @@ def finding_main(
     View and analyze individual findings
 
     Examples:
-        fuzzforge finding                # Show latest finding
-        fuzzforge finding <id>           # Show specific finding
-        fuzzforge finding export         # Export latest findings
+        fuzzforge finding                            # Show latest finding
+        fuzzforge finding <id>                       # Show specific finding
+        fuzzforge finding show <run-id> --rule <id>  # Show specific finding detail
     """
     # Check if a subcommand is being invoked
     if ctx.invoked_subcommand is not None:
@@ -418,7 +378,7 @@ def main():
 
         # Handle finding command with pattern recognition
         if len(args) >= 2 and args[0] == 'finding':
-            finding_subcommands = ['export', 'analyze']
+            finding_subcommands = ['show']
             # Skip custom dispatching if help flags are present
             if not any(arg in ['--help', '-h', '--version', '-v'] for arg in args):
                 if args[1] not in finding_subcommands:

cli/src/fuzzforge_cli/worker_manager.py

@@ -95,17 +95,30 @@ class WorkerManager:
             check=True
         )
 
-    def is_worker_running(self, container_name: str) -> bool:
+    def _service_to_container_name(self, service_name: str) -> str:
         """
-        Check if a worker container is running.
+        Convert service name to container name based on docker-compose naming convention.
 
         Args:
-            container_name: Name of the Docker container (e.g., "fuzzforge-worker-ossfuzz")
+            service_name: Docker Compose service name (e.g., "worker-python")
+
+        Returns:
+            Container name (e.g., "fuzzforge-worker-python")
+        """
+        return f"fuzzforge-{service_name}"
+
+    def is_worker_running(self, service_name: str) -> bool:
+        """
+        Check if a worker service is running.
+
+        Args:
+            service_name: Name of the Docker Compose service (e.g., "worker-ossfuzz")
 
         Returns:
             True if container is running, False otherwise
         """
         try:
+            container_name = self._service_to_container_name(service_name)
             result = subprocess.run(
                 ["docker", "inspect", "-f", "{{.State.Running}}", container_name],
                 capture_output=True,
@@ -120,46 +133,42 @@ class WorkerManager:
             logger.debug(f"Failed to check worker status: {e}")
             return False
 
-    def start_worker(self, container_name: str) -> bool:
+    def start_worker(self, service_name: str) -> bool:
         """
-        Start a worker container using docker.
+        Start a worker service using docker-compose.
 
         Args:
-            container_name: Name of the Docker container to start
+            service_name: Name of the Docker Compose service to start (e.g., "worker-python")
 
         Returns:
             True if started successfully, False otherwise
         """
         try:
-            console.print(f"🚀 Starting worker: {container_name}")
+            console.print(f"🚀 Starting worker: {service_name}")
 
-            # Use docker start directly (works with container name)
-            subprocess.run(
-                ["docker", "start", container_name],
-                capture_output=True,
-                text=True,
-                check=True
-            )
+            # Use docker-compose up to create and start the service
+            result = self._run_docker_compose("up", "-d", service_name)
 
-            logger.info(f"Worker {container_name} started")
+            logger.info(f"Worker {service_name} started")
             return True
 
         except subprocess.CalledProcessError as e:
-            logger.error(f"Failed to start worker {container_name}: {e.stderr}")
+            logger.error(f"Failed to start worker {service_name}: {e.stderr}")
             console.print(f"❌ Failed to start worker: {e.stderr}", style="red")
+            console.print(f"💡 Start the worker manually: docker compose up -d {service_name}", style="yellow")
             return False
 
         except Exception as e:
-            logger.error(f"Unexpected error starting worker {container_name}: {e}")
+            logger.error(f"Unexpected error starting worker {service_name}: {e}")
             console.print(f"❌ Unexpected error: {e}", style="red")
             return False
 
-    def wait_for_worker_ready(self, container_name: str, timeout: Optional[int] = None) -> bool:
+    def wait_for_worker_ready(self, service_name: str, timeout: Optional[int] = None) -> bool:
         """
         Wait for a worker to be healthy and ready to process tasks.
 
         Args:
-            container_name: Name of the Docker container
+            service_name: Name of the Docker Compose service
             timeout: Maximum seconds to wait (uses instance default if not specified)
 
         Returns:
@@ -170,13 +179,14 @@ class WorkerManager:
         """
         timeout = timeout or self.startup_timeout
         start_time = time.time()
+        container_name = self._service_to_container_name(service_name)
 
         console.print("⏳ Waiting for worker to be ready...")
 
         while time.time() - start_time < timeout:
             # Check if container is running
-            if not self.is_worker_running(container_name):
-                logger.debug(f"Worker {container_name} not running yet")
+            if not self.is_worker_running(service_name):
+                logger.debug(f"Worker {service_name} not running yet")
                 time.sleep(self.health_check_interval)
                 continue
 
@@ -193,16 +203,16 @@ class WorkerManager:
 
                 # If no health check is defined, assume healthy after running
                 if health_status == "<no value>" or health_status == "":
-                    logger.info(f"Worker {container_name} is running (no health check)")
-                    console.print(f"✅ Worker ready: {container_name}")
+                    logger.info(f"Worker {service_name} is running (no health check)")
+                    console.print(f"✅ Worker ready: {service_name}")
                     return True
 
                 if health_status == "healthy":
-                    logger.info(f"Worker {container_name} is healthy")
-                    console.print(f"✅ Worker ready: {container_name}")
+                    logger.info(f"Worker {service_name} is healthy")
+                    console.print(f"✅ Worker ready: {service_name}")
                     return True
 
-                logger.debug(f"Worker {container_name} health: {health_status}")
+                logger.debug(f"Worker {service_name} health: {health_status}")
 
             except Exception as e:
                 logger.debug(f"Failed to check health: {e}")
@@ -210,41 +220,36 @@ class WorkerManager:
             time.sleep(self.health_check_interval)
 
         elapsed = time.time() - start_time
-        logger.warning(f"Worker {container_name} did not become ready within {elapsed:.1f}s")
+        logger.warning(f"Worker {service_name} did not become ready within {elapsed:.1f}s")
         console.print(f"⚠️  Worker startup timeout after {elapsed:.1f}s", style="yellow")
         return False
 
-    def stop_worker(self, container_name: str) -> bool:
+    def stop_worker(self, service_name: str) -> bool:
         """
-        Stop a worker container using docker.
+        Stop a worker service using docker-compose.
 
         Args:
-            container_name: Name of the Docker container to stop
+            service_name: Name of the Docker Compose service to stop
 
         Returns:
             True if stopped successfully, False otherwise
         """
         try:
-            console.print(f"🛑 Stopping worker: {container_name}")
+            console.print(f"🛑 Stopping worker: {service_name}")
 
-            # Use docker stop directly (works with container name)
-            subprocess.run(
-                ["docker", "stop", container_name],
-                capture_output=True,
-                text=True,
-                check=True
-            )
+            # Use docker-compose down to stop and remove the service
+            result = self._run_docker_compose("stop", service_name)
 
-            logger.info(f"Worker {container_name} stopped")
+            logger.info(f"Worker {service_name} stopped")
             return True
 
         except subprocess.CalledProcessError as e:
-            logger.error(f"Failed to stop worker {container_name}: {e.stderr}")
+            logger.error(f"Failed to stop worker {service_name}: {e.stderr}")
             console.print(f"❌ Failed to stop worker: {e.stderr}", style="red")
             return False
 
         except Exception as e:
-            logger.error(f"Unexpected error stopping worker {container_name}: {e}")
+            logger.error(f"Unexpected error stopping worker {service_name}: {e}")
             console.print(f"❌ Unexpected error: {e}", style="red")
             return False
 
@@ -257,17 +262,18 @@ class WorkerManager:
         Ensure a worker is running, starting it if necessary.
 
         Args:
-            worker_info: Worker information dict from API (contains worker_container, etc.)
+            worker_info: Worker information dict from API (contains worker_service, etc.)
             auto_start: Whether to automatically start the worker if not running
 
         Returns:
             True if worker is running, False otherwise
         """
-        container_name = worker_info["worker_container"]
+        # Get worker_service (docker-compose service name)
+        service_name = worker_info.get("worker_service", f"worker-{worker_info['vertical']}")
         vertical = worker_info["vertical"]
 
         # Check if already running
-        if self.is_worker_running(container_name):
+        if self.is_worker_running(service_name):
             console.print(f"✓ Worker already running: {vertical}")
             return True
 
@@ -279,8 +285,8 @@ class WorkerManager:
             return False
 
         # Start the worker
-        if not self.start_worker(container_name):
+        if not self.start_worker(service_name):
             return False
 
         # Wait for it to be ready
-        return self.wait_for_worker_ready(container_name)
+        return self.wait_for_worker_ready(service_name)

cli/uv.lock

@@ -1257,7 +1257,7 @@ wheels = [
 
 [[package]]
 name = "fuzzforge-ai"
-version = "0.6.0"
+version = "0.7.0"
 source = { editable = "../ai" }
 dependencies = [
     { name = "a2a-sdk" },
@@ -1303,7 +1303,7 @@ dev = [
 
 [[package]]
 name = "fuzzforge-cli"
-version = "0.6.0"
+version = "0.7.0"
 source = { editable = "." }
 dependencies = [
     { name = "fuzzforge-ai" },
@@ -1347,7 +1347,7 @@ provides-extras = ["dev"]
 
 [[package]]
 name = "fuzzforge-sdk"
-version = "0.6.0"
+version = "0.7.0"
 source = { editable = "../sdk" }
 dependencies = [
     { name = "httpx" },

docker-compose.yml

@@ -9,8 +9,6 @@
 #   Development: docker-compose -f docker-compose.temporal.yaml up
 #   Production:  docker-compose -f docker-compose.temporal.yaml -f docker-compose.temporal.prod.yaml up
 
-version: '3.8'
-
 services:
   # ============================================================================
   # Temporal Server - Workflow Orchestration