ed
72f8f466fe
Three real fixes for the sim test + the live_gui coordination layer:
1. /api/project_switch_status endpoint in src/app_controller.py.
The wait helper had been calling this endpoint but it did not exist;
the helper always received a 404, fell back to {in_progress: False},
and returned immediately even when a switch was in flight. Added the
endpoint that reads _project_switch_in_progress, active_project_path,
and _project_switch_error from the controller.
2. simulation/sim_base.py: replace time.sleep(2.0)/time.sleep(1.5) in
the setup() with wait_io_pool_idle and wait_for_project_switch so
the test does not click btn_md_only while a project switch is in
flight. Also added the wait calls to sim_context.py for the same
reason.
3. src/app_controller.py _handle_md_only: removed the is_project_stale()
early-return. The stale state is a transient window during which the
previous code dropped the click on the floor with a misleading
'stale ui' status. The MD generation worker is safe to run from any
project state; the action handler now always proceeds.
4. tests/test_extended_sims.py: set current_model to 'gemini-cli' so
_do_generate does not raise KeyError('model') when the test
overrides provider to gemini_cli.
KNOWN ISSUE: test_context_sim_live still fails with status
'switching to: temp_livecontextsim' after a 60s wait. The click
appears to be re-triggering a project switch via the GUI's render
loop. Root cause investigation deferred; the sim is async and the
test path is fragile.
105 lines
5.9 KiB
Python
105 lines
5.9 KiB
Python
import os
|
|
import time
|
|
from simulation.sim_base import BaseSimulation, run_sim
|
|
|
|
class ContextSimulation(BaseSimulation):
|
|
def run(self) -> None:
|
|
"""
|
|
[C: tests/conftest.py:kill_process_tree, tests/conftest.py:live_gui, tests/test_conductor_abort_event.py:test_conductor_abort_event_populated, tests/test_conductor_engine_v2.py:test_conductor_engine_dynamic_parsing_and_execution, tests/test_conductor_engine_v2.py:test_conductor_engine_run_executes_tickets_in_order, tests/test_extended_sims.py:test_ai_settings_sim_live, tests/test_extended_sims.py:test_context_sim_live, tests/test_extended_sims.py:test_execution_sim_live, tests/test_extended_sims.py:test_tools_sim_live, tests/test_external_editor_gui.py:get_vscode_processes, tests/test_external_editor_gui.py:test_vscode_launches_with_diff_view, tests/test_gui_custom_window.py:test_app_window_is_borderless, tests/test_headless_simulation.py:module, tests/test_headless_verification.py:test_headless_verification_error_and_qa_interceptor, tests/test_headless_verification.py:test_headless_verification_full_run, tests/test_mock_gemini_cli.py:run_mock, tests/test_orchestration_logic.py:test_conductor_engine_run, tests/test_parallel_execution.py:test_conductor_engine_pool_integration, tests/test_sim_ai_settings.py:test_ai_settings_simulation_run, tests/test_sim_context.py:test_context_simulation_run, tests/test_sim_execution.py:test_execution_simulation_run, tests/test_sim_tools.py:test_tools_simulation_run]
|
|
"""
|
|
print("\n--- Running Context & Chat Simulation ---")
|
|
# Wait for any in-flight async work (e.g., prior setup_new_project switch) to finish.
|
|
self.client.wait_io_pool_idle(timeout=10.0)
|
|
print("\n--- Running Context & Chat Simulation ---")
|
|
# Wait for the sim_base.setup() project switch to fully complete.
|
|
self.client.wait_io_pool_idle(timeout=10.0)
|
|
self.client.wait_for_project_switch(timeout=15.0)
|
|
# 1. Skip Discussion Creation, use 'main'
|
|
print("[Sim] Using existing 'main' discussion")
|
|
self.sim.switch_discussion("main")
|
|
# Discussion switch is a local state update (not async), but give the GUI
|
|
# a moment to render the new discussion tab.
|
|
self.client.wait_io_pool_idle(timeout=5.0)
|
|
# Verify it's in the list
|
|
session = self.client.get_session()
|
|
# The session structure usually has discussions listed somewhere, or we can check the listbox
|
|
# For now, we'll trust the click and check the session update
|
|
# 2. Test File Aggregation & Context Refresh
|
|
print("[Sim] Testing context refresh and token budget...")
|
|
proj = self.client.get_project()
|
|
# Add many files to ensure we cross the 1% threshold (~9000 tokens)
|
|
import glob
|
|
all_py = [os.path.basename(f) for f in glob.glob("*.py")]
|
|
for f in all_py:
|
|
if f not in proj['project']['files']['paths']:
|
|
proj['project']['files']['paths'].append(f)
|
|
# Update project via hook
|
|
self.client.post_project(proj['project'])
|
|
self.client.wait_io_pool_idle(timeout=10.0)
|
|
proj = self.client.get_project()
|
|
# Add many files to ensure we cross the 1% threshold (~9000 tokens)
|
|
import glob
|
|
all_py = [os.path.basename(f) for f in glob.glob("*.py")]
|
|
for f in all_py:
|
|
if f not in proj['project']['files']['paths']:
|
|
proj['project']['files']['paths'].append(f)
|
|
# Update project via hook
|
|
self.client.post_project(proj['project'])
|
|
self.client.wait_io_pool_idle(timeout=10.0)
|
|
# Trigger MD Only to refresh context and token budget
|
|
# Trigger MD Only to refresh context and token budget
|
|
print("[Sim] Clicking MD Only...")
|
|
self.client.click("btn_md_only")
|
|
# Poll for "md written" specifically. The status will go through transient
|
|
# states ("switching", "sending", etc.); we want the terminal state.
|
|
start = time.time()
|
|
status = ""
|
|
while time.time() - start < 60.0:
|
|
status = self.client.get_value("ai_status") or ""
|
|
s = str(status).lower()
|
|
if "md written" in s:
|
|
break
|
|
if "error" in s and "md written" not in s:
|
|
# Terminal error state. Print the status and break so the assertion
|
|
# below shows a clear message rather than a 60s timeout.
|
|
print(f"[Sim] Terminal error: {status}")
|
|
break
|
|
time.sleep(0.5)
|
|
print(f"[Sim] Status: {status}")
|
|
assert "md written" in status, f"Expected 'md written' in status, got {status}"
|
|
pct = self.client.get_value("token_budget_pct")
|
|
current = self.client.get_value("token_budget_current")
|
|
print(f"[Sim] Token budget pct: {pct}, current={current}")
|
|
# We'll just warn if it's 0 but the MD was written, as it might be a small context
|
|
if pct == 0:
|
|
print("[Sim] WARNING: token_budget_pct is 0. This might be due to small context or estimation failure.")
|
|
# 3. Test Chat Turn
|
|
msg = "What is the current date and time? Answer in one sentence."
|
|
print(f"[Sim] Sending message: {msg}")
|
|
self.sim.run_discussion_turn(msg)
|
|
# 4. Verify History
|
|
print("[Sim] Verifying history...")
|
|
session = self.client.get_session()
|
|
entries = session.get('session', {}).get('entries', [])
|
|
if not entries:
|
|
print("[Sim] !!! WARNING: entries list is EMPTY. Waiting another 2 seconds for eventual consistency...")
|
|
time.sleep(2)
|
|
session = self.client.get_session()
|
|
entries = session.get('session', {}).get('entries', [])
|
|
# We expect at least 2 entries (User and AI)
|
|
assert len(entries) >= 2, f"Expected at least 2 entries, found {len(entries)}"
|
|
assert entries[-2]['role'] == 'User', "Expected second to last entry to be User"
|
|
assert entries[-1]['role'] == 'AI', "Expected last entry to be AI"
|
|
print(f"[Sim] AI responded: {entries[-1]['content'][:50]}...")
|
|
# 5. Test History Truncation
|
|
print("[Sim] Testing history truncation...")
|
|
self.sim.truncate_history(1)
|
|
time.sleep(1)
|
|
session = self.client.get_session()
|
|
entries = session.get('session', {}).get('entries', [])
|
|
print(f"[DEBUG] Entries after truncation: {entries}")
|
|
chat_entries = [e for e in entries if e.get('role') in ('User', 'AI')]
|
|
assert len(chat_entries) == 2, f"Expected exactly 2 chat entries after truncation, found {len(chat_entries)}"
|
|
|
|
if __name__ == "__main__":
|
|
run_sim(ContextSimulation) |