perf(cli): ~10x faster startup via lazy imports (#920)

* perf(cli): fast startup — lazy heavy imports + onedir standalone build

* perf(cli): drop legacy single-file compat from install/self-update

* perf(cli): simplify — drop constants module and extra lazy-import refactors

* refactor(update): strix --update just re-runs the install script

* perf(cli): drop packaging/install/update changes; deepen lazy imports instead

Reverts the onedir build, install.sh, and self-update changes so release
mechanics stay untouched. Startup cost is addressed purely by deferring
heavy imports (agents/openai, config.models, report state/writer, docker)
until a scan actually runs; DEFAULT_MAX_TURNS moves to strix.config.settings
so argparse no longer pulls the agents SDK.

---------

Co-authored-by: Ahmed Allam <ahmed39652003@gmail.com>

strix/config/settings.py

@@ -10,6 +10,8 @@ from pydantic_settings import BaseSettings, SettingsConfigDict
 
 ReasoningEffort = Literal["none", "minimal", "low", "medium", "high", "xhigh", "max"]
 
+DEFAULT_MAX_TURNS = 500
+
 _BASE_CONFIG = SettingsConfigDict(
     case_sensitive=False,
     populate_by_name=True,

strix/core/inputs.py

@@ -24,9 +24,6 @@ if TYPE_CHECKING:
     from strix.config.settings import ReasoningEffort
 
 
-DEFAULT_MAX_TURNS = 500
-
-
 def _accepts_required_tool_choice(model_name: str | None) -> bool:
     name = (model_name or "").strip().lower()
     for prefix in ("litellm/", "any-llm/"):

strix/core/runner.py

@@ -23,6 +23,7 @@ from strix.config.models import (
     configure_sdk_model_defaults,
     uses_chat_completions_tool_schema,
 )
+from strix.config.settings import DEFAULT_MAX_TURNS
 from strix.core.agents import AgentCoordinator
 from strix.core.execution import (
     respawn_subagents,
@@ -33,7 +34,6 @@ from strix.core.execution import (
 )
 from strix.core.hooks import BudgetExceededError, ReportUsageHooks, recomputed_budget_flags
 from strix.core.inputs import (
-    DEFAULT_MAX_TURNS,
     build_root_task,
     build_scope_context,
     make_model_settings,

strix/interface/cli.py

@@ -13,7 +13,7 @@ from rich.panel import Panel
 from rich.text import Text
 
 from strix.config import load_settings
-from strix.core.inputs import DEFAULT_MAX_TURNS
+from strix.config.settings import DEFAULT_MAX_TURNS
 from strix.core.runner import run_strix_scan
 from strix.report.state import ReportState, set_global_report_state
 from strix.runtime import session_manager

strix/interface/main.py

@@ -11,9 +11,6 @@ import sys
 from datetime import UTC, datetime
 from pathlib import Path
 
-from agents.model_settings import ModelSettings
-from agents.models.interface import ModelTracing
-from docker.errors import DockerException
 from rich.console import Console
 from rich.panel import Panel
 from rich.text import Text
@@ -24,17 +21,8 @@ from strix.config import (
     load_settings,
     persist_current,
 )
-from strix.config.models import (
-    RECOMMENDED_MODEL_NAMES,
-    StrixProvider,
-    configure_sdk_model_defaults,
-    is_known_openai_bare_model,
-    is_recommended_or_frontier_model,
-)
-from strix.core.inputs import DEFAULT_MAX_TURNS, make_model_settings
+from strix.config.settings import DEFAULT_MAX_TURNS
 from strix.core.paths import run_dir_for, runtime_state_dir
-from strix.interface.cli import run_cli
-from strix.interface.tui import run_tui
 from strix.interface.update_check import (
     is_binary_install,
     notify_update,
@@ -61,8 +49,6 @@ from strix.interface.utils import (
     rewrite_localhost_targets,
     validate_config_file,
 )
-from strix.report.state import get_global_report_state
-from strix.report.writer import read_run_record, write_run_record
 from strix.telemetry import posthog, scarf
 from strix.telemetry.logging import configure_dependency_logging
 
@@ -310,6 +296,18 @@ def _subscription_error_hint(exc: BaseException) -> str | None:
 
 
 async def warm_up_llm(show_model_warning: bool = True) -> None:
+    from agents.model_settings import ModelSettings
+    from agents.models.interface import ModelTracing
+
+    from strix.config.models import (
+        RECOMMENDED_MODEL_NAMES,
+        StrixProvider,
+        configure_sdk_model_defaults,
+        is_known_openai_bare_model,
+        is_recommended_or_frontier_model,
+    )
+    from strix.core.inputs import make_model_settings
+
     console = Console()
     logger.info("Warming up LLM connection")
 
@@ -794,6 +792,8 @@ Examples:
 
 
 def _persist_run_record(args: argparse.Namespace) -> None:
+    from strix.report.writer import write_run_record
+
     run_dir = run_dir_for(args.run_name)
     run_dir.mkdir(parents=True, exist_ok=True)
     run_record = {
@@ -817,6 +817,8 @@ def _persist_run_record(args: argparse.Namespace) -> None:
 
 def _load_resume_state(args: argparse.Namespace, parser: argparse.ArgumentParser) -> None:
     """Populate ``args.targets_info`` and friends from a prior run's run.json."""
+    from strix.report.writer import read_run_record
+
     run_dir = run_dir_for(args.resume)
     state_path = run_dir / "run.json"
     if not state_path.exists():
@@ -861,6 +863,8 @@ def _load_resume_state(args: argparse.Namespace, parser: argparse.ArgumentParser
 
 
 def display_completion_message(args: argparse.Namespace, results_path: Path) -> None:
+    from strix.report.state import get_global_report_state
+
     console = Console()
     report_state = get_global_report_state()
 
@@ -940,6 +944,8 @@ def display_completion_message(args: argparse.Namespace, results_path: Path) ->
 
 
 def pull_docker_image() -> None:
+    from docker.errors import DockerException
+
     console = Console()
     client = check_docker_connection()
 
@@ -1086,11 +1092,17 @@ def main() -> None:
     posthog.start(**_telemetry_start_kwargs)
     scarf.start(**_telemetry_start_kwargs)
 
+    from strix.report.state import get_global_report_state
+
     exit_reason = "user_exit"
     try:
         if args.non_interactive:
+            from strix.interface.cli import run_cli
+
             asyncio.run(run_cli(args))
         else:
+            from strix.interface.tui import run_tui
+
             asyncio.run(run_tui(args))
     except KeyboardInterrupt:
         exit_reason = "interrupted"

strix/interface/tui/app.py

@@ -34,8 +34,8 @@ from textual.widgets.tree import TreeNode
 
 from strix.config import load_settings
 from strix.config.models import is_recommended_or_frontier_model
+from strix.config.settings import DEFAULT_MAX_TURNS
 from strix.core.hooks import BudgetExceededError
-from strix.core.inputs import DEFAULT_MAX_TURNS
 from strix.core.runner import run_strix_scan
 from strix.interface.tui.live_view import TuiLiveView
 from strix.interface.tui.messages import send_user_message_to_agent

strix/telemetry/logging.py

@@ -5,6 +5,7 @@ from __future__ import annotations
 import contextlib
 import logging
 import os
+import sys
 import warnings
 from contextvars import ContextVar
 from pathlib import Path  # noqa: TC003  used at runtime by ``setup_scan_logging``
@@ -78,11 +79,10 @@ class _StdoutQuietFilter(logging.Filter):
 
 def configure_dependency_logging() -> None:
     """Quiet dependency logging/warnings that obscure Strix scan logs."""
-    with contextlib.suppress(Exception):
-        import litellm
-
-        litellm_logging = litellm._logging
-        litellm_logging._disable_debugging()  # type: ignore[no-untyped-call]
+    litellm = sys.modules.get("litellm")
+    if litellm is not None:
+        with contextlib.suppress(Exception):
+            litellm._logging._disable_debugging()
 
     logging.getLogger("asyncio").setLevel(logging.CRITICAL)
     logging.getLogger("asyncio").propagate = False