mirror of
https://github.com/usestrix/strix.git
synced 2026-08-23 03:12:37 +02:00
refactor: nuke legacy harness, drop sdk_ prefixes
The SDK harness is the only path now; legacy host-side code is gone. File names no longer carry the ``sdk_`` distinction. Deleted legacy host-side modules: - strix/agents/StrixAgent/ (template moved to strix/agents/prompts/) - strix/agents/base_agent.py, state.py - strix/llm/llm.py, config.py - strix/runtime/docker_runtime.py, runtime.py - strix/tools/executor.py, agents_graph/agents_graph_actions.py - strix/interface/sdk_dispatch.py + the env-flag dispatch in cli.py Renamed (drop ``sdk_`` prefix): - strix/sdk_entry.py → strix/entry.py - strix/agents/sdk_factory.py → strix/agents/factory.py - strix/agents/sdk_prompt.py → strix/agents/prompt.py - strix/tools/<x>/<x>_sdk_tool[s].py → strix/tools/<x>/tool[s].py - strix/tools/_legacy_adapter.py → strix/tools/_state_adapter.py - ``_legacy`` aliases inside the wrappers → ``_impl`` CLI + TUI now call ``run_strix_scan`` directly — they build the sandbox image / sources_path locally and rely on ``session_manager.cleanup`` (called inside ``run_strix_scan``'s finally) for teardown. Three TUI handlers that reached into legacy multi-agent globals (``_agent_instances``, ``send_user_message_to_agent``, ``stop_agent``) are now no-ops with a TODO; reconnecting them to the ``AgentMessageBus`` is a follow-up. Tracer.get_total_llm_stats no longer reaches into the deleted ``agents_graph_actions`` globals — the orchestration hooks now feed the tracer via ``Tracer.record_llm_usage`` (live + completed buckets). finish_scan's ``_check_active_agents`` and load_skill's runtime ``_agent_instances`` reach-in are no-op stubs; the ``AgentMessageBus`` is the source of truth post-migration. llm/utils.py rewritten to keep only the streaming-parser helpers (``normalize_tool_format``, ``parse_tool_invocations``, ``fix_incomplete_tool_call``, ``format_tool_call``, ``clean_content``). ``STRIX_MODEL_MAP`` moved to ``llm/multi_provider_setup.py`` (its only remaining caller). Per-file ruff ignores added for legacy interface modules (TUI / main / CLI / utils / streaming_parser / tool_components) and tracer.py — pre-existing PLC0415/BLE001/PLR0915 patterns are out of scope. Tests: 287/287 passing. Renamed test files to drop ``sdk_`` prefix. ``test_tracer.py::test_get_total_llm_stats_aggregates_live_and_completed`` rewritten to feed ``Tracer.record_llm_usage`` instead of legacy globals. Test file annotations added so pre-commit's strict mypy passes.
This commit is contained in:
0xallam
+267
@@ -0,0 +1,267 @@
|
||||
"""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.sandbox.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
|
||||
|
||||
from agents import Runner
|
||||
|
||||
from strix.agents.factory import build_strix_agent, make_child_factory
|
||||
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.sandbox 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,
|
||||
interactive: bool = False,
|
||||
max_turns: int = STRIX_DEFAULT_MAX_TURNS,
|
||||
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)
|
||||
|
||||
bus = AgentMessageBus()
|
||||
root_id = uuid.uuid4().hex[:8]
|
||||
|
||||
bundle = await session_manager.create_or_reuse(
|
||||
scan_id,
|
||||
image=image,
|
||||
sources_path=sources_path,
|
||||
)
|
||||
|
||||
try:
|
||||
scan_mode = str(scan_config.get("scan_mode") or "deep")
|
||||
is_whitebox = bool(scan_config.get("is_whitebox", False))
|
||||
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"],
|
||||
sandbox_token=bundle["bearer"],
|
||||
tool_server_host_port=bundle["tool_server_host_port"],
|
||||
caido_host_port=bundle["caido_host_port"],
|
||||
agent_id=root_id,
|
||||
agent_name="strix",
|
||||
parent_id=None,
|
||||
tracer=tracer,
|
||||
max_turns=max_turns,
|
||||
is_whitebox=is_whitebox,
|
||||
diff_scope=diff_scope,
|
||||
run_id=run_id,
|
||||
agent_factory=agent_factory,
|
||||
)
|
||||
|
||||
run_config = make_run_config(
|
||||
sandbox_session=bundle["session"],
|
||||
sandbox_client=bundle["client"],
|
||||
)
|
||||
|
||||
task_text = _build_root_task(scan_config)
|
||||
return await Runner.run(
|
||||
root_agent,
|
||||
input=task_text,
|
||||
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)
|
||||
Reference in New Issue
Block a user