Files
hermes-agent/tests/run_agent/test_interactive_interrupt.py
Teknium 2a95791992 simplify(compat): run_agent/model_tools/toolsets/acp/providers — drop 42 re-exports/aliases, repoint 15 callers + 99 test files
run_agent.py: delete the `# noqa: F401` re-export block (agent.process_bootstrap
OpenAI/_SafeWriter/_get_proxy_*, model_tools get_tool_definitions/
handle_function_call/check_toolset_requirements, FailoverReason,
_qwen_portal_headers/_routermint_headers, session_persistence names,
estimate_request_tokens_rough, ContextCompressor + friends, jittered_backoff,
prompt_builder names, message_sanitization names, tool_dispatch_helpers
names) — 41 names run_agent never used itself — and the `_STREAM_DIAG_HEADERS`
back-compat class alias (no in-tree reader). run_agent now imports only what
it uses (get_toolset_for_tool, is_local_endpoint, coalesce/uniquify tool-call
ids, cleanup_vm/get_active_env from terminal_tool_lifecycle).

agent/*: `_ra().X` late-binds that only reached a re-export now import the
defining module directly (agent_runtime_helpers -> process_bootstrap.OpenAI,
model_tools.handle_function_call, session_persistence._safe_session_filename_component;
agent_init -> model_tools.get_tool_definitions/check_toolset_requirements,
_lazy_headers("agent.client_lifecycle", ...) for qwen/routermint;
system_prompt -> agent.prompt_builder / model_tools directly, dropping its
own _ra() shim and the `_r` parameter threading). `_ra()` stays for
run_agent-resident names (logger, AIAgent, _hermes_home, _set_interrupt, ...).

toolsets.py: remove resolve_multiple_toolsets (shim-only, restored by
34abf954bd); tests/test_toolsets.py pins the same union behavior via
resolve_toolset over each name.

providers/__init__.py: drop the OMIT_TEMPERATURE re-export (no callers via the
package); ProviderProfile stays because __init__ uses it for annotations —
2 tests repointed to providers.base.

agent/iteration_budget.py: drop the "run_agent re-exports the class"
docstring pointer; 4 tests import IterationBudget from its home.

model_tools.py (arg_coercion names), agent/tool_executor.py, and
hermes_cli/cli_session_mixin.py repoints landed via a sibling commit on this
shared worktree.

Callers repointed: gateway/run.py, hermes_cli/cli_chat_turn_mixin.py,
hermes_cli/cli_tui_mixin.py, tui_gateway/session_workdir.py,
agent/transports/codex.py (one-line imports) + comment pointers in
tools/file_state.py, tools/schema_sanitizer.py, scripts/tool_search_livetest.py.
Tests: patch("run_agent.X") / monkeypatch.setattr(run_agent, "X") /
`from run_agent import X` -> defining module across 99 test files.
2026-09-03 13:28:22 -07:00

202 lines
7.5 KiB
Python

#!/usr/bin/env python3
"""Interactive interrupt test that mimics the exact CLI flow.
Starts an agent in a thread with a mock delegate_task that takes a while,
then simulates the user typing a message via _interrupt_queue.
Logs every step to stderr (which isn't affected by redirect_stdout)
so we can see exactly where the interrupt gets lost.
"""
import logging
import queue
import sys
import threading
import time
import os
# Force stderr logging so redirect_stdout doesn't swallow it
logging.basicConfig(level=logging.DEBUG, stream=sys.stderr,
format="%(asctime)s [%(threadName)s] %(message)s")
log = logging.getLogger("interrupt_test")
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
from unittest.mock import MagicMock, patch
from agent.iteration_budget import IterationBudget
from run_agent import AIAgent
from tools.interrupt import set_interrupt
def make_slow_response(delay=2.0):
"""API response that takes a while."""
def create(**kwargs):
log.info(f" 🌐 Mock API call starting (will take {delay}s)...")
time.sleep(delay)
log.info(" 🌐 Mock API call completed")
resp = MagicMock()
resp.choices = [MagicMock()]
resp.choices[0].message.content = "Done with the task"
resp.choices[0].message.tool_calls = None
resp.choices[0].message.refusal = None
resp.choices[0].finish_reason = "stop"
resp.usage.prompt_tokens = 100
resp.usage.completion_tokens = 10
resp.usage.total_tokens = 110
resp.usage.prompt_tokens_details = None
return resp
return create
def main() -> int:
set_interrupt(False)
# ─── Create parent agent ───
parent = AIAgent.__new__(AIAgent)
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"
parent.api_key = "test"
parent.provider = "test"
parent.api_mode = "chat_completions"
parent.platform = "cli"
parent.enabled_toolsets = ["terminal", "file"]
parent.providers_allowed = None
parent.providers_ignored = None
parent.providers_order = None
parent.provider_sort = None
parent.max_tokens = None
parent.reasoning_config = None
parent.prefill_messages = None
parent._session_db = None
parent._delegate_depth = 0
parent._delegate_spinner = None
parent.tool_progress_callback = None
parent.iteration_budget = IterationBudget(max_total=100)
parent._client_kwargs = {"api_key": "test", "base_url": "http://localhost:1"}
# Monkey-patch parent.interrupt to log
_original_interrupt = AIAgent.interrupt
def logged_interrupt(self, message=None):
log.info(f"🔴 parent.interrupt() called with: {message!r}")
log.info(f" _active_children count: {len(self._active_children)}")
_original_interrupt(self, message)
log.info(f" After interrupt: _interrupt_requested={self._interrupt_requested}")
for i, child in enumerate(self._active_children):
log.info(f" Child {i}._interrupt_requested={child._interrupt_requested}")
parent.interrupt = lambda msg=None: logged_interrupt(parent, msg)
# ─── Simulate the exact CLI flow ───
interrupt_queue = queue.Queue()
child_running = threading.Event()
agent_result = [None]
def agent_thread_func():
"""Simulates the agent_thread in cli.py's chat() method."""
log.info("🟢 agent_thread starting")
with patch("agent.process_bootstrap.OpenAI") as MockOpenAI:
mock_client = MagicMock()
mock_client.chat.completions.create = make_slow_response(delay=3.0)
mock_client.close = MagicMock()
MockOpenAI.return_value = mock_client
from tools.delegate_tool import _run_single_child
# Signal that child is about to start
original_init = AIAgent.__init__
def patched_init(self_agent, *a, **kw):
log.info("🟡 Child AIAgent.__init__ called")
original_init(self_agent, *a, **kw)
child_running.set()
log.info(
f"🟡 Child started, parent._active_children = {len(parent._active_children)}"
)
with patch.object(AIAgent, "__init__", patched_init):
result = _run_single_child(
task_index=0,
goal="Do a slow thing",
context=None,
toolsets=["terminal"],
model="test/model",
max_iterations=3,
parent_agent=parent,
task_count=1,
override_provider="test",
override_base_url="http://localhost:1",
override_api_key="test",
override_api_mode="chat_completions",
)
agent_result[0] = result
log.info(f"🟢 agent_thread finished. Result status: {result.get('status')}")
# ─── Start agent thread (like chat() does) ───
agent_thread = threading.Thread(target=agent_thread_func, name="agent_thread", daemon=True)
agent_thread.start()
# ─── Wait for child to start ───
if not child_running.wait(timeout=10):
print("FAIL: Child never started", file=sys.stderr)
set_interrupt(False)
return 1
# Give child time to enter its main loop and start API call
time.sleep(1.0)
# ─── Simulate user typing a message (like handle_enter does) ───
log.info("📝 Simulating user typing 'Hey stop that'")
interrupt_queue.put("Hey stop that")
# ─── Simulate chat() polling loop (like the real chat() method) ───
log.info("📡 Starting interrupt queue polling (like chat())")
interrupt_msg = None
poll_count = 0
while agent_thread.is_alive():
try:
interrupt_msg = interrupt_queue.get(timeout=0.1)
if interrupt_msg:
log.info(f"📨 Got interrupt message from queue: {interrupt_msg!r}")
log.info(" Calling parent.interrupt()...")
parent.interrupt(interrupt_msg)
log.info(" parent.interrupt() returned. Breaking poll loop.")
break
except queue.Empty:
poll_count += 1
if poll_count % 20 == 0: # Log every 2s
log.info(f" Still polling ({poll_count} iterations)...")
# ─── Wait for agent to finish ───
log.info("⏳ Waiting for agent_thread to join...")
t0 = time.monotonic()
agent_thread.join(timeout=10)
elapsed = time.monotonic() - t0
log.info(f"✅ agent_thread joined after {elapsed:.2f}s")
# ─── Check results ───
result = agent_result[0]
if result:
log.info(f"Result status: {result['status']}")
log.info(f"Result duration: {result['duration_seconds']}s")
if result["status"] == "interrupted" and elapsed < 2.0:
print("✅ PASS: Interrupt worked correctly!", file=sys.stderr)
set_interrupt(False)
return 0
print(f"❌ FAIL: status={result['status']}, elapsed={elapsed:.2f}s", file=sys.stderr)
set_interrupt(False)
return 1
print("❌ FAIL: No result returned", file=sys.stderr)
set_interrupt(False)
return 1
if __name__ == "__main__":
sys.exit(main())