common/hermes
2
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

fix(gateway): resume sessions after crash/restart instead of blanket suspend

Browse Source 
suspend_recently_active() was unconditionally setting suspended=True on
startup, causing get_or_create_session() to wipe conversation history on
every restart. Change to set resume_pending=True instead, so sessions
auto-resume while still allowing stuck-loop escalation after 3 failures.
This commit is contained in:
millerc79
2026-05-02 19:19:24 -05:00
committed by kshitij
parent 0a97ce6bff
commit f1e0292517
2 changed files with 18 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
gateway/run.py
View File

@@ -2755,7 +2755,7 @@ class GatewayRunner:
try:
suspended = self.session_store.suspend_recently_active()
if suspended:
logger.info("Suspended %d in-flight session(s) from previous run", suspended)
logger.info("Marked %d in-flight session(s) as resumable from previous run", suspended)
except Exception as e:
logger.warning("Session suspension on startup failed: %s", e)

29
gateway/session.py
View File

@@ -1086,19 +1086,22 @@ class SessionStore:
return len(removed_keys)
def suspend_recently_active(self, max_age_seconds: int = 120) -> int:
"""Mark recently-active sessions as suspended.
"""Mark recently-active sessions as resumable after an unexpected exit.
Called on gateway startup to prevent sessions that were likely
in-flight when the gateway last exited from being blindly resumed
(#7536). Only suspends sessions updated within *max_age_seconds*
to avoid resetting long-idle sessions that are harmless to resume.
Returns the number of sessions that were suspended.
Called on gateway startup after a crash or fast restart to preserve
in-flight sessions instead of destroying their conversation history
(#7536). Only marks sessions updated within *max_age_seconds* to
avoid touching long-idle sessions. Sets ``resume_pending=True`` so
the next incoming message on the same session_key auto-resumes from
the existing transcript.
Entries flagged ``resume_pending=True`` are skipped — those were
marked intentionally by the drain-timeout path as recoverable.
Terminal escalation for genuinely stuck ``resume_pending`` sessions
is handled by the existing ``.restart_failure_counts`` stuck-loop
counter, which runs after this method on startup.
Entries already flagged ``resume_pending=True`` are skipped. Entries
explicitly ``suspended=True`` (from /stop or stuck-loop escalation)
are also skipped. Terminal escalation for genuinely stuck sessions
is still handled by the existing ``.restart_failure_counts`` counter
(threshold 3), which runs after this method and sets ``suspended=True``.
Returns the number of sessions marked resumable.
"""
from datetime import timedelta
@@ -1110,7 +1113,9 @@ class SessionStore:
if entry.resume_pending:
continue
if not entry.suspended and entry.updated_at >= cutoff:
entry.suspended = True
entry.resume_pending = True
entry.resume_reason = "restart_interrupted"
entry.last_resume_marked_at = _now()
count += 1
if count:
self._save()