fix: thread safety for concurrent subagent delegation (#1672)

* fix: thread safety for concurrent subagent delegation

Four thread-safety fixes that prevent crashes and data races when
running multiple subagents concurrently via delegate_task:

1. Remove redirect_stdout/stderr from delegate_tool — mutating global
   sys.stdout races with the spinner thread when multiple children start
   concurrently, causing segfaults. Children already run with
   quiet_mode=True so the redirect was redundant.

2. Split _run_single_child into _build_child_agent (main thread) +
   _run_single_child (worker thread). AIAgent construction creates
   httpx/SSL clients which are not thread-safe to initialize
   concurrently.

3. Add threading.Lock to SessionDB — subagents share the parent's
   SessionDB and call create_session/append_message from worker threads
   with no synchronization.

4. Add _active_children_lock to AIAgent — interrupt() iterates
   _active_children while worker threads append/remove children.

5. Add _client_cache_lock to auxiliary_client — multiple subagent
   threads may resolve clients concurrently via call_llm().

Based on PR #1471 by peteromallet.

* feat: Honcho base_url override via config.yaml + quick command alias type

Two features salvaged from PR #1576:

1. Honcho base_url override: allows pointing Hermes at a remote
   self-hosted Honcho deployment via config.yaml:

     honcho:
       base_url: "http://192.168.x.x:8000"

   When set, this overrides the Honcho SDK's environment mapping
   (production/local), enabling LAN/VPN Honcho deployments without
   requiring the server to live on localhost. Uses config.yaml instead
   of env var (HONCHO_URL) per project convention.

2. Quick command alias type: adds a new 'alias' quick command type
   that rewrites to another slash command before normal dispatch:

     quick_commands:
       sc:
         type: alias
         target: /context

   Supports both CLI and gateway. Arguments are forwarded to the
   target command.

Based on PR #1576 by redhelix.

---------

Co-authored-by: peteromallet <peteromallet@users.noreply.github.com>
Co-authored-by: redhelix <redhelix@users.noreply.github.com>
This commit is contained in:
Teknium 2026-03-17 02:53:33 -07:00 committed by GitHub
parent fd61ae13e5
commit 1d5a39e002
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
14 changed files with 397 additions and 272 deletions

View file

@ -55,6 +55,7 @@ class TestRealSubagentInterrupt(unittest.TestCase):
parent._interrupt_requested = False
parent._interrupt_message = None
parent._active_children = []
parent._active_children_lock = threading.Lock()
parent.quiet_mode = True
parent.model = "test/model"
parent.base_url = "http://localhost:1"
@ -103,19 +104,28 @@ class TestRealSubagentInterrupt(unittest.TestCase):
return original_run(self_agent, *args, **kwargs)
with patch.object(AIAgent, 'run_conversation', patched_run):
# Build a real child agent (AIAgent is NOT patched here,
# only run_conversation and _build_system_prompt are)
child = AIAgent(
base_url="http://localhost:1",
api_key="test-key",
model="test/model",
provider="test",
api_mode="chat_completions",
max_iterations=5,
enabled_toolsets=["terminal"],
quiet_mode=True,
skip_context_files=True,
skip_memory=True,
platform="cli",
)
child._delegate_depth = 1
parent._active_children.append(child)
result = _run_single_child(
task_index=0,
goal="Test task",
context=None,
toolsets=["terminal"],
model="test/model",
max_iterations=5,
child=child,
parent_agent=parent,
task_count=1,
override_provider="test",
override_base_url="http://localhost:1",
override_api_key="test",
override_api_mode="chat_completions",
)
result_holder[0] = result
except Exception as e: