mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-06-21 10:22:18 +00:00
75ed07ace8
When a tool call itself restarts the gateway (docker restart, systemctl restart, and similar), the process is terminated mid-call — before the tool result is persisted and before the orderly drain rewind can run. The transcript tail is left as an assistant(tool_calls) with no matching tool answer. On resume the model re-issues the unanswered call, taking the gateway down again — an infinite loop (#49201). Source fix: _build_gateway_agent_history now strips a trailing assistant(tool_calls) block that has no tool answers (_strip_dangling_tool_call_tail), so there is nothing for the model to re-execute. This complements _strip_interrupted_tool_tails, which only handles the case where a tool result row exists with an interrupt marker. Cognitive backstop: the resume-pending system note now states that any restart command in the history already ran and must not be re-executed or verified, and the empty-message auto-resume startup turn reports recovery and asks for instructions instead of the nonsensical "address the user's NEW message" (there is no new message on that turn). Reimplements the intent of #49243 by @JoaoMarcos44 at the replay layer. Fixes #49201 |
||
|---|---|---|
| .. | ||
| assets | ||
| builtin_hooks | ||
| platforms | ||
| relay | ||
| __init__.py | ||
| authz_mixin.py | ||
| channel_directory.py | ||
| config.py | ||
| delivery.py | ||
| display_config.py | ||
| hooks.py | ||
| kanban_watchers.py | ||
| memory_monitor.py | ||
| message_timestamps.py | ||
| mirror.py | ||
| pairing.py | ||
| platform_registry.py | ||
| response_filters.py | ||
| restart.py | ||
| rich_sent_store.py | ||
| run.py | ||
| runtime_footer.py | ||
| session.py | ||
| session_context.py | ||
| shutdown_forensics.py | ||
| slash_access.py | ||
| slash_commands.py | ||
| status.py | ||
| sticker_cache.py | ||
| stream_consumer.py | ||
| stream_dispatch.py | ||
| stream_events.py | ||
| whatsapp_identity.py | ||