strix/strix/interface/main.py

#!/usr/bin/env python3
"""
Strix Agent Interface
"""

import argparse
import asyncio
import shutil
import sys
from pathlib import Path
from typing import Any

import litellm
from docker.errors import DockerException
from rich.console import Console
from rich.panel import Panel
from rich.text import Text

from strix.config import apply_config_override, load_settings, persist_current
from strix.interface.cli import run_cli
from strix.interface.tui import run_tui
from strix.interface.utils import (
    assign_workspace_subdirs,
    build_final_stats_text,
    check_docker_connection,
    clone_repository,
    collect_local_sources,
    generate_run_name,
    image_exists,
    infer_target_type,
    is_whitebox_scan,
    process_pull_line,
    resolve_diff_scope_context,
    rewrite_localhost_targets,
    validate_config_file,
    validate_llm_response,
)
from strix.telemetry import posthog
from strix.telemetry.tracer import get_global_tracer


HOST_GATEWAY_HOSTNAME = "host.docker.internal"


import logging  # noqa: E402


# Per-scan logging is set up by ``setup_scan_logging`` from inside
# ``orchestration.scan.run_strix_scan`` once the scan ``run_dir`` is
# known — that's where ``strix.*`` levels and handlers are owned. Pre-scan
# work (``main()``, env validation, image pull) emits via the module
# logger; once setup_scan_logging runs, those records start landing in
# the file too.

logger = logging.getLogger(__name__)


def validate_environment() -> None:
    logger.info("Validating environment")
    console = Console()
    missing_required_vars = []
    missing_optional_vars = []

    settings = load_settings()

    if not settings.llm.model:
        missing_required_vars.append("STRIX_LLM")

    if not settings.llm.api_key:
        missing_optional_vars.append("LLM_API_KEY")

    if not settings.llm.api_base:
        missing_optional_vars.append("LLM_API_BASE")

    if not settings.integrations.perplexity_api_key:
        missing_optional_vars.append("PERPLEXITY_API_KEY")

    if missing_required_vars:
        error_text = Text()
        error_text.append("MISSING REQUIRED ENVIRONMENT VARIABLES", style="bold red")
        error_text.append("\n\n", style="white")

        for var in missing_required_vars:
            error_text.append(f"• {var}", style="bold yellow")
            error_text.append(" is not set\n", style="white")

        if missing_optional_vars:
            error_text.append("\nOptional environment variables:\n", style="dim white")
            for var in missing_optional_vars:
                error_text.append(f"• {var}", style="dim yellow")
                error_text.append(" is not set\n", style="dim white")

        error_text.append("\nRequired environment variables:\n", style="white")
        for var in missing_required_vars:
            if var == "STRIX_LLM":
                error_text.append("• ", style="white")
                error_text.append("STRIX_LLM", style="bold cyan")
                error_text.append(
                    " - Model name to use with litellm (e.g., 'openai/gpt-5.4')\n",
                    style="white",
                )

        if missing_optional_vars:
            error_text.append("\nOptional environment variables:\n", style="white")
            for var in missing_optional_vars:
                if var == "LLM_API_KEY":
                    error_text.append("• ", style="white")
                    error_text.append("LLM_API_KEY", style="bold cyan")
                    error_text.append(
                        " - API key for the LLM provider "
                        "(not needed for local models, Vertex AI, AWS, etc.)\n",
                        style="white",
                    )
                elif var == "LLM_API_BASE":
                    error_text.append("• ", style="white")
                    error_text.append("LLM_API_BASE", style="bold cyan")
                    error_text.append(
                        " - Custom API base URL if using local models (e.g., Ollama, LMStudio)\n",
                        style="white",
                    )
                elif var == "PERPLEXITY_API_KEY":
                    error_text.append("• ", style="white")
                    error_text.append("PERPLEXITY_API_KEY", style="bold cyan")
                    error_text.append(
                        " - API key for Perplexity AI web search (enables real-time research)\n",
                        style="white",
                    )
                elif var == "STRIX_REASONING_EFFORT":
                    error_text.append("• ", style="white")
                    error_text.append("STRIX_REASONING_EFFORT", style="bold cyan")
                    error_text.append(
                        " - Reasoning effort level: none, minimal, low, medium, high, xhigh "
                        "(default: high)\n",
                        style="white",
                    )

        error_text.append("\nExample setup:\n", style="white")
        error_text.append("export STRIX_LLM='openai/gpt-5.4'\n", style="dim white")

        if missing_optional_vars:
            for var in missing_optional_vars:
                if var == "LLM_API_KEY":
                    error_text.append(
                        "export LLM_API_KEY='your-api-key-here'  "
                        "# not needed for local models, Vertex AI, AWS, etc.\n",
                        style="dim white",
                    )
                elif var == "LLM_API_BASE":
                    error_text.append(
                        "export LLM_API_BASE='http://localhost:11434'  "
                        "# needed for local models only\n",
                        style="dim white",
                    )
                elif var == "PERPLEXITY_API_KEY":
                    error_text.append(
                        "export PERPLEXITY_API_KEY='your-perplexity-key-here'\n", style="dim white"
                    )
                elif var == "STRIX_REASONING_EFFORT":
                    error_text.append(
                        "export STRIX_REASONING_EFFORT='high'\n",
                        style="dim white",
                    )

        panel = Panel(
            error_text,
            title="[bold white]STRIX",
            title_align="left",
            border_style="red",
            padding=(1, 2),
        )

        logger.error("Missing required env vars: %s", missing_required_vars)
        console.print("\n")
        console.print(panel)
        console.print()
        sys.exit(1)
    logger.info(
        "Environment OK (optional missing: %s)",
        missing_optional_vars or "none",
    )


def check_docker_installed() -> None:
    if shutil.which("docker") is None:
        logger.error("Docker CLI not found in PATH")
        console = Console()
        error_text = Text()
        error_text.append("DOCKER NOT INSTALLED", style="bold red")
        error_text.append("\n\n", style="white")
        error_text.append("The 'docker' CLI was not found in your PATH.\n", style="white")
        error_text.append(
            "Please install Docker and ensure the 'docker' command is available.\n\n", style="white"
        )

        panel = Panel(
            error_text,
            title="[bold white]STRIX",
            title_align="left",
            border_style="red",
            padding=(1, 2),
        )
        console.print("\n", panel, "\n")
        sys.exit(1)
    logger.debug("Docker CLI present")


async def warm_up_llm() -> None:
    console = Console()
    logger.info("Warming up LLM connection")

    try:
        llm = load_settings().llm

        test_messages = [
            {"role": "system", "content": "You are a helpful assistant."},
            {"role": "user", "content": "Reply with just 'OK'."},
        ]

        completion_kwargs: dict[str, Any] = {
            "model": llm.model,
            "messages": test_messages,
            "timeout": llm.timeout,
        }
        if llm.api_key:
            completion_kwargs["api_key"] = llm.api_key
        if llm.api_base:
            completion_kwargs["api_base"] = llm.api_base

        response = litellm.completion(**completion_kwargs)

        validate_llm_response(response)
        logger.info("LLM warm-up succeeded for model %s", llm.model)

    except Exception as e:
        logger.exception("LLM warm-up failed")
        error_text = Text()
        error_text.append("LLM CONNECTION FAILED", style="bold red")
        error_text.append("\n\n", style="white")
        error_text.append("Could not establish connection to the language model.\n", style="white")
        error_text.append("Please check your configuration and try again.\n", style="white")
        error_text.append(f"\nError: {e}", style="dim white")

        panel = Panel(
            error_text,
            title="[bold white]STRIX",
            title_align="left",
            border_style="red",
            padding=(1, 2),
        )

        console.print("\n")
        console.print(panel)
        console.print()
        sys.exit(1)


def get_version() -> str:
    try:
        from importlib.metadata import version

        return version("strix-agent")
    except Exception:
        return "unknown"


def parse_arguments() -> argparse.Namespace:
    parser = argparse.ArgumentParser(
        description="Strix Multi-Agent Cybersecurity Penetration Testing Tool",
        formatter_class=argparse.RawDescriptionHelpFormatter,
        epilog="""
Examples:
  # Web application penetration test
  strix --target https://example.com

  # GitHub repository analysis
  strix --target https://github.com/user/repo
  strix --target git@github.com:user/repo.git

  # Local code analysis
  strix --target ./my-project

  # Domain penetration test
  strix --target example.com

  # IP address penetration test
  strix --target 192.168.1.42

  # Multiple targets (e.g., white-box testing with source and deployed app)
  strix --target https://github.com/user/repo --target https://example.com
  strix --target ./my-project --target https://staging.example.com --target https://prod.example.com

  # Custom instructions (inline)
  strix --target example.com --instruction "Focus on authentication vulnerabilities"

  # Custom instructions (from file)
  strix --target example.com --instruction-file ./instructions.txt
  strix --target https://app.com --instruction-file /path/to/detailed_instructions.md
        """,
    )

    parser.add_argument(
        "-v",
        "--version",
        action="version",
        version=f"strix {get_version()}",
    )

    parser.add_argument(
        "-t",
        "--target",
        type=str,
        required=True,
        action="append",
        help="Target to test (URL, repository, local directory path, domain name, or IP address). "
        "Can be specified multiple times for multi-target scans.",
    )
    parser.add_argument(
        "--instruction",
        type=str,
        help="Custom instructions for the penetration test. This can be "
        "specific vulnerability types to focus on (e.g., 'Focus on IDOR and XSS'), "
        "testing approaches (e.g., 'Perform thorough authentication testing'), "
        "test credentials (e.g., 'Use the following credentials to access the app: "
        "admin:password123'), "
        "or areas of interest (e.g., 'Check login API endpoint for security issues').",
    )

    parser.add_argument(
        "--instruction-file",
        type=str,
        help="Path to a file containing detailed custom instructions for the penetration test. "
        "Use this option when you have lengthy or complex instructions saved in a file "
        "(e.g., '--instruction-file ./detailed_instructions.txt').",
    )

    parser.add_argument(
        "-n",
        "--non-interactive",
        action="store_true",
        help=(
            "Run in non-interactive mode (no TUI, exits on completion). "
            "Default is interactive mode with TUI."
        ),
    )

    parser.add_argument(
        "-m",
        "--scan-mode",
        type=str,
        choices=["quick", "standard", "deep"],
        default="deep",
        help=(
            "Scan mode: "
            "'quick' for fast CI/CD checks, "
            "'standard' for routine testing, "
            "'deep' for thorough security reviews (default). "
            "Default: deep."
        ),
    )

    parser.add_argument(
        "--scope-mode",
        type=str,
        choices=["auto", "diff", "full"],
        default="auto",
        help=(
            "Scope mode for code targets: "
            "'auto' enables PR diff-scope in CI/headless runs, "
            "'diff' forces changed-files scope, "
            "'full' disables diff-scope."
        ),
    )

    parser.add_argument(
        "--diff-base",
        type=str,
        help=(
            "Target branch or commit to compare against (e.g., origin/main). "
            "Defaults to the repository's default branch."
        ),
    )

    parser.add_argument(
        "--config",
        type=str,
        help="Path to a custom config file (JSON) to use instead of ~/.strix/cli-config.json",
    )

    args = parser.parse_args()

    if args.instruction and args.instruction_file:
        parser.error(
            "Cannot specify both --instruction and --instruction-file. Use one or the other."
        )

    if args.instruction_file:
        instruction_path = Path(args.instruction_file)
        try:
            with instruction_path.open(encoding="utf-8") as f:
                args.instruction = f.read().strip()
                if not args.instruction:
                    parser.error(f"Instruction file '{instruction_path}' is empty")
        except Exception as e:
            parser.error(f"Failed to read instruction file '{instruction_path}': {e}")

    args.targets_info = []
    for target in args.target:
        try:
            target_type, target_dict = infer_target_type(target)

            if target_type == "local_code":
                display_target = target_dict.get("target_path", target)
            else:
                display_target = target

            args.targets_info.append(
                {"type": target_type, "details": target_dict, "original": display_target}
            )
        except ValueError:
            parser.error(f"Invalid target '{target}'")

    assign_workspace_subdirs(args.targets_info)
    rewrite_localhost_targets(args.targets_info, HOST_GATEWAY_HOSTNAME)

    return args


def display_completion_message(args: argparse.Namespace, results_path: Path) -> None:
    console = Console()
    tracer = get_global_tracer()

    scan_completed = False
    if tracer and tracer.scan_results:
        scan_completed = tracer.scan_results.get("scan_completed", False)

    completion_text = Text()
    if scan_completed:
        completion_text.append("Penetration test completed", style="bold #22c55e")
    else:
        completion_text.append("SESSION ENDED", style="bold #eab308")

    target_text = Text()
    target_text.append("Target", style="dim")
    target_text.append("  ")
    if len(args.targets_info) == 1:
        target_text.append(args.targets_info[0]["original"], style="bold white")
    else:
        target_text.append(f"{len(args.targets_info)} targets", style="bold white")
        for target_info in args.targets_info:
            target_text.append("\n        ")
            target_text.append(target_info["original"], style="white")

    stats_text = build_final_stats_text(tracer)

    panel_parts: list[Text | str] = [completion_text, "\n\n", target_text]

    if stats_text.plain:
        panel_parts.extend(["\n", stats_text])

    results_text = Text()
    results_text.append("\n")
    results_text.append("Output", style="dim")
    results_text.append("  ")
    results_text.append(str(results_path), style="#60a5fa")
    panel_parts.extend(["\n", results_text])

    if not scan_completed:
        resume_text = Text()
        resume_text.append("\n")
        resume_text.append("Resume", style="dim")
        resume_text.append("  ")
        resume_text.append(f"strix --run-name {args.run_name}", style="#22c55e")
        panel_parts.extend(["\n", resume_text])

    panel_content = Text.assemble(*panel_parts)

    border_style = "#22c55e" if scan_completed else "#eab308"

    panel = Panel(
        panel_content,
        title="[bold white]STRIX",
        title_align="left",
        border_style=border_style,
        padding=(1, 2),
    )

    console.print("\n")
    console.print(panel)
    console.print()
    console.print("[#60a5fa]strix.ai[/]  [dim]·[/]  [#60a5fa]discord.gg/strix-ai[/]")
    console.print()


def pull_docker_image() -> None:
    console = Console()
    client = check_docker_connection()

    image = load_settings().runtime.image

    if image_exists(client, image):
        logger.debug("Docker image already present locally: %s", image)
        return

    logger.info("Pulling docker image: %s", image)
    console.print()
    console.print(f"[dim]Pulling image[/] {image}")
    console.print("[dim yellow]This only happens on first run and may take a few minutes...[/]")
    console.print()

    with console.status("[bold cyan]Downloading image layers...", spinner="dots") as status:
        try:
            layers_info: dict[str, str] = {}
            last_update = ""

            for line in client.api.pull(image, stream=True, decode=True):
                last_update = process_pull_line(line, layers_info, status, last_update)

        except DockerException as e:
            logger.exception("Failed to pull docker image %s", image)
            console.print()
            error_text = Text()
            error_text.append("FAILED TO PULL IMAGE", style="bold red")
            error_text.append("\n\n", style="white")
            error_text.append(f"Could not download: {image}\n", style="white")
            error_text.append(str(e), style="dim red")

            panel = Panel(
                error_text,
                title="[bold white]STRIX",
                title_align="left",
                border_style="red",
                padding=(1, 2),
            )
            console.print(panel, "\n")
            sys.exit(1)

    logger.info("Docker image %s ready", image)
    success_text = Text()
    success_text.append("Docker image ready", style="#22c55e")
    console.print(success_text)
    console.print()


def main() -> None:
    if sys.platform == "win32":
        asyncio.set_event_loop_policy(asyncio.WindowsSelectorEventLoopPolicy())

    args = parse_arguments()

    if args.config:
        apply_config_override(validate_config_file(args.config))

    check_docker_installed()
    pull_docker_image()

    validate_environment()
    asyncio.run(warm_up_llm())

    persist_current()

    args.run_name = generate_run_name(args.targets_info)

    for target_info in args.targets_info:
        if target_info["type"] == "repository":
            repo_url = target_info["details"]["target_repo"]
            dest_name = target_info["details"].get("workspace_subdir")
            cloned_path = clone_repository(repo_url, args.run_name, dest_name)
            target_info["details"]["cloned_repo_path"] = cloned_path

    args.local_sources = collect_local_sources(args.targets_info)
    try:
        diff_scope = resolve_diff_scope_context(
            local_sources=args.local_sources,
            scope_mode=args.scope_mode,
            diff_base=args.diff_base,
            non_interactive=args.non_interactive,
        )
    except ValueError as e:
        console = Console()
        error_text = Text()
        error_text.append("DIFF SCOPE RESOLUTION FAILED", style="bold red")
        error_text.append("\n\n", style="white")
        error_text.append(str(e), style="white")

        panel = Panel(
            error_text,
            title="[bold white]STRIX",
            title_align="left",
            border_style="red",
            padding=(1, 2),
        )
        console.print("\n")
        console.print(panel)
        console.print()
        sys.exit(1)

    args.diff_scope = diff_scope.metadata
    if diff_scope.instruction_block:
        if args.instruction:
            args.instruction = f"{diff_scope.instruction_block}\n\n{args.instruction}"
        else:
            args.instruction = diff_scope.instruction_block

    posthog.start(
        model=load_settings().llm.model,
        scan_mode=args.scan_mode,
        is_whitebox=is_whitebox_scan(args.targets_info),
        interactive=not args.non_interactive,
        has_instructions=bool(args.instruction),
    )

    exit_reason = "user_exit"
    try:
        if args.non_interactive:
            asyncio.run(run_cli(args))
        else:
            asyncio.run(run_tui(args))
    except KeyboardInterrupt:
        exit_reason = "interrupted"
    except Exception as e:
        exit_reason = "error"
        posthog.error("unhandled_exception", str(e))
        raise
    finally:
        tracer = get_global_tracer()
        if tracer:
            posthog.end(tracer, exit_reason=exit_reason)

    results_path = Path("strix_runs") / args.run_name
    display_completion_message(args, results_path)

    if args.non_interactive:
        tracer = get_global_tracer()
        if tracer and tracer.vulnerability_reports:
            sys.exit(2)


if __name__ == "__main__":
    main()