From 6fd7b9bbba0dc31f887228e9f56b41ec9394918f Mon Sep 17 00:00:00 2001
From: jenkins <jenkins@bstein.dev>
Date: Sat, 15 Aug 2026 14:20:12 -0300
Subject: [PATCH] hermes: close stale API worker sessions

---
 .../scripts/migrate_api_session_lineage.py    | 23 +++++++++++
 testing/tests/test_hermes_chat_quality.py     | 40 +++++++++++++++++++
 2 files changed, 63 insertions(+)

diff --git a/services/hermes/scripts/migrate_api_session_lineage.py b/services/hermes/scripts/migrate_api_session_lineage.py
index 1e921add..bdb0fb9a 100644
--- a/services/hermes/scripts/migrate_api_session_lineage.py
+++ b/services/hermes/scripts/migrate_api_session_lineage.py
@@ -37,6 +37,28 @@ TRIAGE_MESSAGE_PREFIXES = (
 )
 
 
+def close_stale_api_workers(connection: sqlite3.Connection) -> int:
+    """Close parent-linked API runs that survived a prior gateway lifetime."""
+    columns = {
+        str(row[1])
+        for row in connection.execute("PRAGMA table_info(sessions)").fetchall()
+    }
+    if not {"ended_at", "end_reason"}.issubset(columns):
+        return 0
+    cursor = connection.execute(
+        """
+        UPDATE sessions
+           SET ended_at = ?,
+               end_reason = 'api_run_recovered_stale'
+         WHERE source = 'api_server'
+           AND parent_session_id IS NOT NULL
+           AND ended_at IS NULL
+        """,
+        (time.time(),),
+    )
+    return cursor.rowcount
+
+
 def _triage_title(message: str, session_id: str) -> str:
     """Create a concise label from Ariadne's stable incident contract."""
     match = re.search(r"(?:for|Analyze) incident ([^\s.]+)(?:\.|\s)", message)
@@ -98,6 +120,7 @@ def migrate(path: Path = STATE_DB, *, group_triage: bool = False) -> int:
         return 0
     changed = 0
     with sqlite3.connect(path) as connection:
+        changed += close_stale_api_workers(connection)
         parent = connection.execute(
             "SELECT id FROM sessions WHERE id = ?", (LEGACY_CASSANDRA_PARENT,)
         ).fetchone()
diff --git a/testing/tests/test_hermes_chat_quality.py b/testing/tests/test_hermes_chat_quality.py
index 0d96d9c8..16537a1d 100644
--- a/testing/tests/test_hermes_chat_quality.py
+++ b/testing/tests/test_hermes_chat_quality.py
@@ -1186,6 +1186,46 @@ def test_automated_triage_sessions_are_grouped_without_touching_interactive_runs
     )
 
 
+def test_stale_parent_linked_api_workers_close_on_startup(tmp_path: Path):
+    """A previous gateway lifetime cannot leave phantom active workers."""
+    module_path = HERMES / "scripts" / "migrate_api_session_lineage.py"
+    spec = importlib.util.spec_from_file_location("close_stale_api_workers", module_path)
+    assert spec and spec.loader
+    module = importlib.util.module_from_spec(spec)
+    spec.loader.exec_module(module)
+    database = tmp_path / "state.db"
+    with sqlite3.connect(database) as connection:
+        connection.execute(
+            "CREATE TABLE sessions (id TEXT PRIMARY KEY, source TEXT, "
+            "parent_session_id TEXT, title TEXT, started_at REAL, ended_at REAL, "
+            "end_reason TEXT, archived INTEGER DEFAULT 0)"
+        )
+        connection.executemany(
+            "INSERT INTO sessions "
+            "(id, source, parent_session_id, started_at, ended_at, end_reason) "
+            "VALUES (?, ?, ?, 1, ?, ?)",
+            (
+                ("stale", "api_server", "parent", None, None),
+                ("root", "api_server", None, None, None),
+                ("finished", "api_server", "parent", 2.0, "api_run_completed"),
+                ("interactive", "tui", "parent", None, None),
+            ),
+        )
+
+    assert module.migrate(database) == 1
+    assert module.migrate(database) == 0
+    with sqlite3.connect(database) as connection:
+        rows = connection.execute(
+            "SELECT id, ended_at, end_reason FROM sessions ORDER BY id"
+        ).fetchall()
+    by_id = {row[0]: row[1:] for row in rows}
+    assert by_id["stale"][0] is not None
+    assert by_id["stale"][1] == "api_run_recovered_stale"
+    assert by_id["root"] == (None, None)
+    assert by_id["finished"] == (2.0, "api_run_completed")
+    assert by_id["interactive"] == (None, None)
+
+
 def test_switchyard_brokers_and_native_claude_lane_use_the_right_images():
     """Thin brokers stay small while native Claude runs beside owner auth."""
     dockerfile = (ROOT / "dockerfiles" / "Dockerfile.hermes-switchyard-brokers").read_text()