strix/strix/entry.py
0xallam 1e641e56ce refactor(config): pydantic-settings revamp + drop `is_whitebox` plumbing
Replaces 200+ lines of bespoke env-loader / persist / change-detection
machinery with ``pydantic_settings.BaseSettings`` (already a transitive
of ``openai-agents → mcp``, no new direct dep).

What was wrong with ``Config``:

- 14 knobs flat in one namespace, weak grouping by comment-block.
- ``Config._applied_from_default`` and ``Config._config_file_override``
  were externally mutated from ``interface/main.py:532-534``. Private
  members were part of the public contract.
- Stringly-typed values: every caller had to coerce
  (``int(Config.get("llm_timeout") or "300")``,
  ``... not in {"0", "false", "no", "off"}``).
- Dead knob: ``strix_llm_max_retries`` declared, persisted, listed in
  ``_LLM_CANONICAL_NAMES`` — zero readers (``DEFAULT_RETRY``
  hardcodes ``max_retries=5``). Dropped.
- ``_LLM_CANONICAL_NAMES`` tuple maintained alongside class vars —
  duplicate source of truth.
- ``_tracked_names()`` introspected ``vars(cls).items()`` filtered on
  ``(v is None or isinstance(v, str))`` — fragile.
- Awkward path: ``strix/config/config.py`` inside ``strix/config/``
  with ``__init__.py`` just re-exporting.
- Dual access for the same fact: ``web_search`` read
  ``os.getenv("PERPLEXITY_API_KEY")`` while ``main.py`` read
  ``Config.get("perplexity_api_key")``.

New shape:

- ``strix/config/settings.py`` — typed dataclass tree:
  ``Settings.{llm,runtime,telemetry,integrations}``. Each sub-model is
  its own ``BaseSettings`` so it reads env independently. Field-level
  ``alias=`` and ``validation_alias=AliasChoices(...)`` mirror the
  existing flat env-var names — user-facing env contract is unchanged.
  Bool fields auto-parse ``"0"``/``"false"``/``"no"``/``"off"``;
  int fields auto-coerce.
- ``strix/config/loader.py`` — thin ``load_settings()``,
  ``apply_config_override(path)``, ``persist_current()`` with module
  cache. JSON file reader walks aliases to populate sub-models, dropping
  entries already covered by env (so env still wins).
- 13 callsites migrated from ``Config.get("...")`` to
  ``load_settings().<group>.<field>``.
- ``posthog._is_enabled()`` collapses to one line.
- ``--config <path>`` flow simplified: one
  ``apply_config_override(...)`` call replaces three lines of
  class-private mutation.

Drive-by — drop ``is_whitebox`` from ``scan_config`` dict:

- It was being derived as ``bool(args.local_sources)`` in three places
  (``cli.py``, ``tui.py``, ``main.py``) and stuffed into the dict for
  ``entry.py`` to read back. The fact is fully derivable from
  ``scan_config["targets"]`` — any target with ``type == "local_code"``.
- New helper ``is_whitebox_scan(targets)`` in ``interface/utils.py``
  alongside the other target-classification utilities.
- ``entry.py`` computes once; ``main.py``'s posthog start uses the same
  helper. Triplicate derivation gone.

Verified: ruff at baseline (3), mypy at baseline (69). Six smoke tests
pass — defaults / JSON-only / env-wins-over-JSON / alias-chain
fallback / bool parsing / ``is_whitebox_scan``.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-25 16:05:40 -07:00

293 lines
10 KiB
Python

"""Top-level scan entry point.
1. Build the per-scan ``AgentMessageBus``.
2. Bring up (or reuse) a sandbox session for ``scan_id`` via the
:mod:`strix.runtime.session_manager`.
3. Build the root ``Agent`` via :func:`build_strix_agent` and a
matching child factory via :func:`make_child_factory`.
4. Build the root context dict (bus + sandbox bundle + agent_factory).
5. Register the root in the bus.
6. Build the ``RunConfig`` via the factory.
7. Call ``Runner.run(...)`` and surface the result.
8. ``finally`` cleanup the sandbox session — even on cancel, the bus
propagates ``cancel_descendants`` to every spawned child task.
"""
from __future__ import annotations
import logging
import uuid
from pathlib import Path
from typing import TYPE_CHECKING, Any, Literal
from agents import Runner
from agents.memory import SQLiteSession
from strix.agents.factory import build_strix_agent, make_child_factory
from strix.config import load_settings
from strix.orchestration.bus import AgentMessageBus
from strix.orchestration.hooks import StrixOrchestrationHooks
from strix.run_config_factory import (
STRIX_DEFAULT_MAX_TURNS,
make_agent_context,
make_run_config,
)
from strix.runtime import session_manager
if TYPE_CHECKING:
from agents.result import RunResult
logger = logging.getLogger(__name__)
def _build_root_task(scan_config: dict[str, Any]) -> str:
"""Format the user-facing task for the root agent.
Collects each target type into a labelled section, appends
diff-scope context if active, and tacks on user_instructions. The
structured section headers are referenced by the system prompt
template, so the shape matters for prompt parity.
"""
targets = scan_config.get("targets", []) or []
diff_scope = scan_config.get("diff_scope") or {}
user_instructions = scan_config.get("user_instructions", "") or ""
repos: list[str] = []
locals_: list[str] = []
urls: list[str] = []
ips: list[str] = []
for target in targets:
ttype = target.get("type")
details = target.get("details") or {}
workspace_subdir = details.get("workspace_subdir")
workspace_path = f"/workspace/{workspace_subdir}" if workspace_subdir else "/workspace"
if ttype == "repository":
url = details.get("target_repo", "")
cloned = details.get("cloned_repo_path")
repos.append(
f"- {url} (available at: {workspace_path})" if cloned else f"- {url}",
)
elif ttype == "local_code":
path = details.get("target_path", "unknown")
locals_.append(f"- {path} (available at: {workspace_path})")
elif ttype == "web_application":
urls.append(f"- {details.get('target_url', '')}")
elif ttype == "ip_address":
ips.append(f"- {details.get('target_ip', '')}")
parts: list[str] = []
if repos:
parts.append("\n\nRepositories:")
parts.extend(repos)
if locals_:
parts.append("\n\nLocal Codebases:")
parts.extend(locals_)
if urls:
parts.append("\n\nURLs:")
parts.extend(urls)
if ips:
parts.append("\n\nIP Addresses:")
parts.extend(ips)
if diff_scope.get("active"):
parts.append("\n\nScope Constraints:")
parts.append(
"- Pull request diff-scope mode is active. Prioritize changed files "
"and use other files only for context.",
)
for repo_scope in diff_scope.get("repos", []) or []:
label = (
repo_scope.get("workspace_subdir") or repo_scope.get("source_path") or "repository"
)
changed = repo_scope.get("analyzable_files_count", 0)
deleted = repo_scope.get("deleted_files_count", 0)
parts.append(f"- {label}: {changed} changed file(s) in primary scope")
if deleted:
parts.append(f"- {label}: {deleted} deleted file(s) are context-only")
task = " ".join(parts)
if user_instructions:
task = f"{task}\n\nSpecial instructions: {user_instructions}"
return task
def _build_scope_context(scan_config: dict[str, Any]) -> dict[str, Any]:
"""Produce the system_prompt_context block used by the prompt template.
The prompt template's ``system_prompt_context.authorized_targets``
lookups expect this exact shape.
"""
authorized: list[dict[str, str]] = []
for target in scan_config.get("targets", []) or []:
ttype = target.get("type", "unknown")
details = target.get("details") or {}
if ttype == "repository":
value = details.get("target_repo", "")
elif ttype == "local_code":
value = details.get("target_path", "")
elif ttype == "web_application":
value = details.get("target_url", "")
elif ttype == "ip_address":
value = details.get("target_ip", "")
else:
value = target.get("original", "")
workspace_subdir = details.get("workspace_subdir")
workspace_path = f"/workspace/{workspace_subdir}" if workspace_subdir else ""
authorized.append(
{"type": ttype, "value": value, "workspace_path": workspace_path},
)
return {
"scope_source": "system_scan_config",
"authorization_source": "strix_platform_verified_targets",
"authorized_targets": authorized,
"user_instructions_do_not_expand_scope": True,
}
async def run_strix_scan(
*,
scan_config: dict[str, Any],
scan_id: str | None = None,
image: str,
sources_path: Path,
tracer: Any | None = None,
bus: AgentMessageBus | None = None,
interactive: bool = False,
max_turns: int = STRIX_DEFAULT_MAX_TURNS,
model: str = "anthropic/claude-sonnet-4-6",
cleanup_on_exit: bool = True,
) -> RunResult:
"""Run one Strix scan end-to-end against a freshly-prepared sandbox.
Args:
scan_config: Per-scan configuration — ``targets``,
``user_instructions``, ``diff_scope``, ``scan_mode``,
``is_whitebox``, ``skills``.
scan_id: Used to key the sandbox session cache. Auto-generated
if omitted — callers that want resume-after-crash semantics
should pass a stable id.
image: Docker image tag for the sandbox (e.g.
``"strix-sandbox:0.1.13"``).
sources_path: Host directory mounted into ``/workspace/sources``.
tracer: Optional Strix tracer. Stored in context for the
telemetry hook chain. Pass ``None`` for unit tests.
interactive: Renders the interactive-mode prompt block on the
root agent.
max_turns: Cap on root-agent LLM turns (default 300).
cleanup_on_exit: When True (default), tears down the sandbox
session in a ``finally``. Set to False for resume scenarios
where the caller wants to preserve the container.
Returns the SDK ``RunResult`` from ``Runner.run``. Raises if the
sandbox bring-up fails or the run itself raises.
"""
if scan_id is None:
scan_id = f"scan-{uuid.uuid4().hex[:8]}"
logger.info("Starting Strix scan %s", scan_id)
# Caller may pre-create the bus so it can hold a handle (e.g., the
# TUI uses it to route stop / chat-input commands). Otherwise we
# own the bus internally for the scan's lifetime.
if bus is None:
bus = AgentMessageBus()
root_id = uuid.uuid4().hex[:8]
bundle = await session_manager.create_or_reuse(
scan_id,
image=image,
sources_path=sources_path,
)
try:
# Lazy: ``strix.interface`` pulls cli→tui→entry which would cycle.
from strix.interface.utils import is_whitebox_scan
scan_mode = str(scan_config.get("scan_mode") or "deep")
is_whitebox = is_whitebox_scan(scan_config.get("targets") or [])
skills = list(scan_config.get("skills") or [])
diff_scope = scan_config.get("diff_scope") or None
run_id = scan_config.get("run_id") or scan_id
scope_context = _build_scope_context(scan_config)
root_agent = build_strix_agent(
name="strix",
skills=skills,
is_root=True,
scan_mode=scan_mode,
is_whitebox=is_whitebox,
interactive=interactive,
system_prompt_context=scope_context,
)
await bus.register(root_id, "strix", parent_id=None)
agent_factory = make_child_factory(
scan_mode=scan_mode,
is_whitebox=is_whitebox,
interactive=interactive,
system_prompt_context=scope_context,
)
context = make_agent_context(
bus=bus,
sandbox_session=bundle["session"],
sandbox_client=bundle["client"],
caido_client=bundle["caido_client"],
agent_id=root_id,
parent_id=None,
tracer=tracer,
model=model,
max_turns=max_turns,
is_whitebox=is_whitebox,
diff_scope=diff_scope,
run_id=run_id,
agent_factory=agent_factory,
)
reasoning_effort: Literal["low", "medium", "high"] | None = (
load_settings().llm.reasoning_effort
)
run_config = make_run_config(
sandbox_session=bundle["session"],
sandbox_client=bundle["client"],
model=model,
reasoning_effort=reasoning_effort,
)
# Native SDK session: persists conversation history to
# ``strix_runs/<scan_id>/session.db`` so a second invocation
# with the same ``scan_id`` resumes from where we left off.
session_db = (
(tracer.get_run_dir() / "session.db")
if tracer is not None and hasattr(tracer, "get_run_dir")
else Path.cwd() / "strix_runs" / scan_id / "session.db"
)
session_db.parent.mkdir(parents=True, exist_ok=True)
session = SQLiteSession(session_id=scan_id, db_path=session_db)
task_text = _build_root_task(scan_config)
return await Runner.run(
root_agent,
input=task_text,
session=session,
run_config=run_config,
context=context,
hooks=StrixOrchestrationHooks(),
max_turns=max_turns,
)
except BaseException:
# Cancel any descendant tasks the root spawned before unwinding.
# cancel_descendants is idempotent and handles the empty-tree case.
await bus.cancel_descendants(root_id)
raise
finally:
if cleanup_on_exit:
await session_manager.cleanup(scan_id)