From 37134b8c1859a95cddecbfa81ccb81b240849106 Mon Sep 17 00:00:00 2001
From: Alex Blank <noreply@runfusion.ai>
Date: Tue, 2 Jun 2026 15:23:16 +0200
Subject: [PATCH] fix: terminal EOF detection and dead session cleanup

When a tool container stops, the docker exec PTY reaches EOF. Previously,
the event-driven reader silently returned on EOF, leaving websockets
attached to a dead session. Input writes then failed silently.

Changes:
- _on_fd_readable: detect EOF (empty read) and call _handle_eof()
- _handle_eof: stop reading, mark process dead, close all websockets
  with code 4001 to force frontend reconnection
- write_input: detect write errors and trigger EOF cleanup

Quality gates: pytest (19 passed, 1 skipped)
---
 apps/api/src/services/terminal_session.py | 37 +++++++++++++++++++++--
 1 file changed, 34 insertions(+), 3 deletions(-)

diff --git a/apps/api/src/services/terminal_session.py b/apps/api/src/services/terminal_session.py
index e2609c0..a824407 100644
--- a/apps/api/src/services/terminal_session.py
+++ b/apps/api/src/services/terminal_session.py
@@ -186,10 +186,17 @@ class TerminalSession:
 
         try:
             data = os.read(self._master_fd, 4096)
-        except (OSError, IOError):
+        except (OSError, IOError) as exc:
+            logger.debug(
+                "PTY read error for session %s: %s", self.session_id, exc
+            )
+            self._handle_eof()
             return
 
         if not data:
+            # EOF: docker exec process exited
+            logger.debug("PTY EOF for session %s", self.session_id)
+            self._handle_eof()
             return
 
         self._add_to_buffer(data)
@@ -297,6 +304,27 @@ class TerminalSession:
         """Get buffered output for replay."""
         return b"".join(self._output_buffer)
 
+    def _handle_eof(self) -> None:
+        """Handle PTY EOF: process died, close websockets to force reconnect."""
+        self._stop_reading()
+        # Mark process as done so is_alive() returns False
+        if self.process is not None and self.process.returncode is None:
+            # Force returncode to a non-None value since the process is dead
+            # but asyncio.subprocess may not have set it yet
+            try:
+                self.process._transport.close()  # type: ignore[attr-defined]
+            except Exception:
+                pass
+        # Close all websockets to force frontend reconnection
+        dead_sockets = set(self._websockets)
+        self._websockets.clear()
+        for ws in dead_sockets:
+            try:
+                asyncio.create_task(ws.close(code=4001, reason="Session process exited"))
+            except Exception:
+                pass
+        logger.info("Session %s EOF handled, websockets closed", self.session_id)
+
     async def write_input(self, data: bytes) -> None:
         """Write input to the PTY master."""
         if self._master_fd is None or self._closed:
@@ -304,8 +332,11 @@ class TerminalSession:
         try:
             os.write(self._master_fd, data)
             self.last_activity = time.time()
-        except (OSError, IOError):
-            pass
+        except (OSError, IOError) as exc:
+            logger.debug(
+                "PTY write error for session %s: %s", self.session_id, exc
+            )
+            self._handle_eof()
 
     def _set_terminal_size(self, cols: int, rows: int) -> None:
         """Set the terminal size using TIOCSWINSZ."""