feat: notify_on_complete for background processes (#5779)

* feat: notify_on_complete for background processes

When terminal(background=true, notify_on_complete=true), the system
auto-triggers a new agent turn when the process exits — no polling needed.

Changes:
- ProcessSession: add notify_on_complete field
- ProcessRegistry: add completion_queue, populate on _move_to_finished()
- Terminal tool: add notify_on_complete parameter to schema + handler
- CLI: drain completion_queue after agent turn AND during idle loop
- Gateway: enhanced _run_process_watcher injects synthetic MessageEvent
  on completion, triggering a full agent turn
- Checkpoint persistence includes notify_on_complete for crash recovery
- code_execution_tool: block notify_on_complete in sandbox scripts
- 15 new tests covering queue mechanics, checkpoint round-trip, schema

* docs: update terminal tool descriptions for notify_on_complete

- background: remove 'ONLY for servers' language, describe both patterns
  (long-lived processes AND long-running tasks with notify_on_complete)
- notify_on_complete: more prescriptive about when to use it
- TERMINAL_TOOL_DESCRIPTION: remove 'Do NOT use background for builds'
  guidance that contradicted the new feature
This commit is contained in:
Teknium
2026-04-07 02:40:16 -07:00
committed by GitHub
parent 1c425f219e
commit e120d2afac
6 changed files with 398 additions and 10 deletions

43
cli.py
View File

@@ -8134,6 +8134,25 @@ class HermesCLI:
# Periodic config watcher — auto-reload MCP on mcp_servers change
if not self._agent_running:
self._check_config_mcp_changes()
# Check for background process completion notifications
# while the agent is idle (user hasn't typed anything yet).
try:
from tools.process_registry import process_registry
if not process_registry.completion_queue.empty():
completion = process_registry.completion_queue.get_nowait()
_exit = completion.get("exit_code", "?")
_cmd = completion.get("command", "unknown")
_sid = completion.get("session_id", "unknown")
_out = completion.get("output", "")
_synth = (
f"[SYSTEM: Background process {_sid} completed "
f"(exit code {_exit}).\n"
f"Command: {_cmd}\n"
f"Output:\n{_out}]"
)
self._pending_input.put(_synth)
except Exception:
pass
continue
if not user_input:
@@ -8247,7 +8266,29 @@ class HermesCLI:
except Exception as e:
_cprint(f"{_DIM}Voice auto-restart failed: {e}{_RST}")
threading.Thread(target=_restart_recording, daemon=True).start()
# Drain process completion notifications — any background
# process that finished with notify_on_complete while the
# agent was running (or before) gets auto-injected as a
# new user message so the agent can react to it.
try:
from tools.process_registry import process_registry
while not process_registry.completion_queue.empty():
completion = process_registry.completion_queue.get_nowait()
_exit = completion.get("exit_code", "?")
_cmd = completion.get("command", "unknown")
_sid = completion.get("session_id", "unknown")
_out = completion.get("output", "")
_synth = (
f"[SYSTEM: Background process {_sid} completed "
f"(exit code {_exit}).\n"
f"Command: {_cmd}\n"
f"Output:\n{_out}]"
)
self._pending_input.put(_synth)
except Exception:
pass # Non-fatal — don't break the main loop
except Exception as e:
print(f"Error: {e}")