Merge remote-tracking branch 'origin/master' into feature/blocked-for-human-input

# Conflicts:
#	server/services/process_manager.py

parallel_orchestrator.py

@@ -194,6 +194,7 @@ class ParallelOrchestrator:
         # Legacy alias for backward compatibility
         self.running_agents = self.running_coding_agents
         self.abort_events: dict[int, threading.Event] = {}
+        self._testing_session_counter = 0
         self.is_running = False
 
         # Track feature failures to prevent infinite retry loops
@@ -212,6 +213,9 @@ class ParallelOrchestrator:
         # Signal handlers only set this flag; cleanup happens in the main loop
         self._shutdown_requested = False
 
+        # Graceful pause (drain mode) flag
+        self._drain_requested = False
+
         # Session tracking for logging/debugging
         self.session_start_time: datetime | None = None
 
@@ -852,7 +856,7 @@ class ParallelOrchestrator:
                 "encoding": "utf-8",
                 "errors": "replace",
                 "cwd": str(self.project_dir),  # Run from project dir so CLI creates .claude/ in project
-                "env": {**os.environ, "PYTHONUNBUFFERED": "1"},
+                "env": {**os.environ, "PYTHONUNBUFFERED": "1", "NODE_COMPILE_CACHE": "", "PLAYWRIGHT_CLI_SESSION": f"coding-{feature_id}"},
             }
             if sys.platform == "win32":
                 popen_kwargs["creationflags"] = subprocess.CREATE_NO_WINDOW
@@ -915,7 +919,7 @@ class ParallelOrchestrator:
                 "encoding": "utf-8",
                 "errors": "replace",
                 "cwd": str(self.project_dir),  # Run from project dir so CLI creates .claude/ in project
-                "env": {**os.environ, "PYTHONUNBUFFERED": "1"},
+                "env": {**os.environ, "PYTHONUNBUFFERED": "1", "NODE_COMPILE_CACHE": "", "PLAYWRIGHT_CLI_SESSION": f"coding-{primary_id}"},
             }
             if sys.platform == "win32":
                 popen_kwargs["creationflags"] = subprocess.CREATE_NO_WINDOW
@@ -1019,8 +1023,9 @@ class ParallelOrchestrator:
                     "encoding": "utf-8",
                     "errors": "replace",
                     "cwd": str(self.project_dir),  # Run from project dir so CLI creates .claude/ in project
-                    "env": {**os.environ, "PYTHONUNBUFFERED": "1"},
+                    "env": {**os.environ, "PYTHONUNBUFFERED": "1", "NODE_COMPILE_CACHE": "", "PLAYWRIGHT_CLI_SESSION": f"testing-{self._testing_session_counter}"},
                 }
+                self._testing_session_counter += 1
                 if sys.platform == "win32":
                     popen_kwargs["creationflags"] = subprocess.CREATE_NO_WINDOW
 
@@ -1080,7 +1085,7 @@ class ParallelOrchestrator:
             "encoding": "utf-8",
             "errors": "replace",
             "cwd": str(AUTOFORGE_ROOT),
-            "env": {**os.environ, "PYTHONUNBUFFERED": "1"},
+            "env": {**os.environ, "PYTHONUNBUFFERED": "1", "NODE_COMPILE_CACHE": ""},
         }
         if sys.platform == "win32":
             popen_kwargs["creationflags"] = subprocess.CREATE_NO_WINDOW
@@ -1166,6 +1171,19 @@ class ParallelOrchestrator:
                 debug_log.log("CLEANUP", f"Error killing process tree for {agent_type} agent", error=str(e))
             self._on_agent_complete(feature_id, proc.returncode, agent_type, proc)
 
+    def _run_inter_session_cleanup(self):
+        """Run lightweight cleanup between agent sessions.
+
+        Removes stale temp files and project screenshots to prevent
+        disk space accumulation during long overnight runs.
+        """
+        try:
+            from temp_cleanup import cleanup_project_screenshots, cleanup_stale_temp
+            cleanup_stale_temp()
+            cleanup_project_screenshots(self.project_dir)
+        except Exception as e:
+            debug_log.log("CLEANUP", f"Inter-session cleanup failed (non-fatal): {e}")
+
     def _signal_agent_completed(self):
         """Signal that an agent has completed, waking the main loop.
 
@@ -1241,6 +1259,8 @@ class ParallelOrchestrator:
                 pid=proc.pid,
                 feature_id=feature_id,
                 status=status)
+            # Run lightweight cleanup between sessions
+            self._run_inter_session_cleanup()
             # Signal main loop that an agent slot is available
             self._signal_agent_completed()
             return
@@ -1307,6 +1327,8 @@ class ParallelOrchestrator:
         else:
             print(f"Feature #{feature_id} {status}", flush=True)
 
+        # Run lightweight cleanup between sessions
+        self._run_inter_session_cleanup()
         # Signal main loop that an agent slot is available
         self._signal_agent_completed()
 
@@ -1374,6 +1396,9 @@ class ParallelOrchestrator:
         # Must happen before any debug_log.log() calls
         debug_log.start_session()
 
+        # Clear any stale drain signal from a previous session
+        self._clear_drain_signal()
+
         # Log startup to debug file
         debug_log.section("ORCHESTRATOR STARTUP")
         debug_log.log("STARTUP", "Orchestrator run_loop starting",
@@ -1495,6 +1520,34 @@ class ParallelOrchestrator:
                     print("\nAll features complete!", flush=True)
                     break
 
+                # --- Graceful pause (drain mode) ---
+                if not self._drain_requested and self._check_drain_signal():
+                    self._drain_requested = True
+                    print("Graceful pause requested - draining running agents...", flush=True)
+                    debug_log.log("DRAIN", "Graceful pause requested, draining running agents")
+
+                if self._drain_requested:
+                    with self._lock:
+                        coding_count = len(self.running_coding_agents)
+                        testing_count = len(self.running_testing_agents)
+
+                    if coding_count == 0 and testing_count == 0:
+                        print("All agents drained - paused.", flush=True)
+                        debug_log.log("DRAIN", "All agents drained, entering paused state")
+                        # Wait until signal file is removed (resume) or shutdown
+                        while self._check_drain_signal() and self.is_running and not self._shutdown_requested:
+                            await asyncio.sleep(1)
+                        if not self.is_running or self._shutdown_requested:
+                            break
+                        self._drain_requested = False
+                        print("Resuming from graceful pause...", flush=True)
+                        debug_log.log("DRAIN", "Resuming from graceful pause")
+                        continue
+                    else:
+                        debug_log.log("DRAIN", f"Waiting for agents to finish: coding={coding_count}, testing={testing_count}")
+                        await self._wait_for_agent_completion()
+                        continue
+
                 # Maintain testing agents independently (runs every iteration)
                 self._maintain_testing_agents(feature_dicts)
 
@@ -1619,6 +1672,17 @@ class ParallelOrchestrator:
                 "yolo_mode": self.yolo_mode,
             }
 
+    def _check_drain_signal(self) -> bool:
+        """Check if the graceful pause (drain) signal file exists."""
+        from autoforge_paths import get_pause_drain_path
+        return get_pause_drain_path(self.project_dir).exists()
+
+    def _clear_drain_signal(self) -> None:
+        """Delete the drain signal file and reset the flag."""
+        from autoforge_paths import get_pause_drain_path
+        get_pause_drain_path(self.project_dir).unlink(missing_ok=True)
+        self._drain_requested = False
+
     def cleanup(self) -> None:
         """Clean up database resources. Safe to call multiple times.