Compare commits

..
Author SHA1 Message Date
Ahmed Allam fac2fd1100 prompt changes 2026-08-06 12:37:59 +00:00
Ahmed Allam 3c38cb453d prompt changes 2026-08-06 12:32:14 +00:00
Ahmed AllamandAhmed Allam b69af37cb2 feat(report): keep dependency findings from distinct manifests separate in dedupe 2026-08-06 02:20:46 +03:00
Ahmed AllamandAhmed Allam 72cb15a20a feat(reporting): require repo-relative manifest_path on dependency CVE findings 2026-08-06 02:20:46 +03:00
Alex SchapiroandAhmed Allam 97336d53e4 feat(reporting): structured reachability evidence ladder for dependency CVE findings 2026-08-06 00:25:08 +03:00
0abe82d622 fix(agents): collapse repeated waits queued inside one model turn (#979)
* fix(agents): collapse repeated waits queued inside one model turn

* fix(agents): state that one wait is enough in every prompt variant

---------

Co-authored-by: Ahmed Allam <ahmed39652003@gmail.com>
2026-08-06 00:07:30 +03:00
6735a6f89e fix(llm): abandon a model stream that stops producing events (#978)
Co-authored-by: Ahmed Allam <ahmed39652003@gmail.com>
2026-08-06 00:07:14 +03:00
8bd6c8e87a fix(llm): cap the tool calls one assistant response may queue (#977)
* fix(llm): cap the tool calls one assistant response may queue

* fix(llm): cap the subscription backend's responses too

---------

Co-authored-by: Ahmed Allam <ahmed39652003@gmail.com>
2026-08-06 00:06:59 +03:00
68ea6fca65 fix(llm): keep tool-call ids unique so a recycled id can't erase history (#976)
Co-authored-by: Ahmed Allam <ahmed39652003@gmail.com>
2026-08-06 00:06:46 +03:00
657aa5cbe6 feat(reporting): record transitive dependency chain on SCA findings (#971)
Co-authored-by: Ahmed Allam <ahmed39652003@gmail.com>
2026-08-04 12:34:52 -07:00
Ahmed AllamandGitHub 82dcd31357 fix(tui): keep a long error inside the status row (#970) 2026-08-04 07:26:22 -07:00
39 changed files with 2048 additions and 117 deletions
+3 -1
View File
@@ -16,7 +16,8 @@ RUN mkdir -p /out/bin && \
go install -v github.com/projectdiscovery/katana/cmd/katana@latest && \
go install -v github.com/projectdiscovery/cvemap/cmd/vulnx@latest && \
go install -v github.com/jaeles-project/gospider@latest && \
go install -v github.com/projectdiscovery/interactsh/cmd/interactsh-client@latest
go install -v github.com/projectdiscovery/interactsh/cmd/interactsh-client@latest && \
go install -v golang.org/x/vuln/cmd/govulncheck@latest
# ---------------------------------------------------------------------------
# Runtime stage
@@ -53,6 +54,7 @@ RUN apt-get update && \
nmap ncat ndiff \
sqlmap nuclei subfinder naabu ffuf \
nodejs npm pipx \
golang-go \
libcap2-bin \
gdb \
libnss3-tools \
+4 -1
View File
@@ -47,7 +47,7 @@ dependencies = [
"pypdf>=5.0",
# Cap <49: 49.x drops the universal2 macOS wheel (arm64-only), which breaks
# the Intel macOS (macos-x86_64) release build's `uv sync --frozen`.
"cryptography>=48.0.1,<51",
"cryptography>=48.0.1,<49",
"pyyaml>=6.0",
]
@@ -236,6 +236,9 @@ ignore = [
"strix/interface/auth_cli.py" = ["N802"]
"tests/test_codex_streaming.py" = ["N802"]
"tests/test_disable_streaming.py" = ["N802"]
"tests/test_tool_call_ids.py" = ["N802"]
"tests/test_tool_call_limits.py" = ["N802", "SLF001"]
"tests/test_stream_idle_timeout.py" = ["N802", "SLF001"]
"tests/test_unknown_tool_recovery.py" = ["N802"]
"tests/test_report_pdf.py" = ["S105", "S106"]
# Stdlib HTTP handler overrides (do_GET/do_POST) and lazy imports that avoid a
+1 -1
View File
@@ -559,7 +559,7 @@ def registered_agent_tools() -> tuple[Tool, ...]:
def build_strix_agent(
*,
name: str = "strix",
name: str = "agent",
skills: list[str] | None = None,
is_root: bool,
scan_mode: str = "deep",
+4 -3
View File
@@ -1,4 +1,4 @@
You are Strix, an advanced AI application security validation agent developed by OmniSecure Labs. Your purpose is to perform authorized security verification, reproduce and validate weaknesses on in-scope assets, and help remediate real security issues.
You are an advanced AI application security validation agent. Your purpose is to perform authorized security verification, reproduce and validate weaknesses on in-scope assets, and help remediate real security issues.
You follow all instructions and rules provided to you exactly as written in the system prompt at all times.
{% if is_root %}
<root_agent_directive>
@@ -22,12 +22,13 @@ CLI OUTPUT:
- You may use simple markdown: **bold**, *italic*, `code`, ~~strikethrough~~, [links](url), and # headers
- Do NOT use complex markdown like bullet lists, numbered lists, or tables
- Use line breaks and indentation for structure
- NEVER use "Strix" or any identifiable names/markers in HTTP requests, payloads, user-agents, or any inputs
- NEVER use any identifiable names/markers in HTTP requests, payloads, user-agents, or any inputs
INTER-AGENT MESSAGES:
- Messages from other agents arrive prefixed with a header like `[Message from agent <name> | type=... | priority=...]`. Treat them as internal context — never repeat them verbatim in your own output.
- Treat agent identity / inherited-context preambles as internal metadata; do not echo them in outputs or tool calls.
- Minimize inter-agent messaging: only message when essential for coordination or assistance; avoid routine status updates; batch non-urgent information; prefer parent/child completion flows and shared artifacts over messaging
- wait_for_agents blocks and resumes you automatically, so it is never a poll you repeat: issue exactly ONE wait, then stop and react to what it returns. Never write out a wait/check loop (wait → view_agent_graph → wait → ...) ahead of time — those extra calls only strand you and are collapsed anyway
{% if interactive %}
INTERACTIVE BEHAVIOR:
@@ -57,7 +58,7 @@ AUTONOMOUS BEHAVIOR:
<execution_guidelines>
{% if system_prompt_context and system_prompt_context.authorized_targets %}
SYSTEM-VERIFIED SCOPE:
- The following scope metadata is injected by the Strix platform into the system prompt and is authoritative
- The following scope metadata is injected by the platform into the system prompt and is authoritative
- Scope source: {{ system_prompt_context.scope_source }}
- Authorization source: {{ system_prompt_context.authorization_source }}
- Every target listed below has already been verified by the platform as in-scope and authorized
+194 -7
View File
@@ -2,11 +2,14 @@
from __future__ import annotations
import asyncio
import contextlib
import inspect
import logging
import os
import time
from typing import TYPE_CHECKING, Any
from collections.abc import AsyncGenerator
from typing import TYPE_CHECKING, Any, cast
from agents import (
set_default_openai_api,
@@ -24,12 +27,19 @@ from agents.retry import (
RetryPolicyContext,
retry_policies,
)
from openai.types.responses import Response, ResponseCompletedEvent
from openai.types.responses import (
Response,
ResponseCompletedEvent,
ResponseOutputItemAddedEvent,
ResponseOutputItemDoneEvent,
)
from openai.types.responses.response_usage import ResponseUsage
from openai.types.shared import Reasoning
from strix.config import codex
from strix.config.loader import load_settings
from strix.config.tool_call_ids import TurnCallIdRewriter, dedupe_input
from strix.config.tool_call_limits import TurnToolCallLimiter
if TYPE_CHECKING:
@@ -48,6 +58,9 @@ if TYPE_CHECKING:
from strix.config.settings import LlmSettings, ReasoningEffort, Settings
logger = logging.getLogger(__name__)
def request_timeout_extra_args(timeout_s: float | None) -> dict[str, float] | None:
"""Per-request model timeout; a plain float so ``ModelSettings.to_json_dict()`` stays serializable.""" # noqa: E501
if not timeout_s or timeout_s <= 0:
@@ -229,6 +242,170 @@ class _NonStreamingModel(Model):
yield _completed_stream_event(response, getattr(self._inner, "model", None))
class _TurnGuardModel(Model):
"""Keep one turn from corrupting the conversation or running away.
Tool-call ids: providers that number calls per turn (``exec_command:0``,
...) restart the counter each turn, so the same id eventually appears twice
in one conversation and strict providers reject every subsequent request.
Ids that collide with the history are rewritten before the turn is
recorded, and already-corrupted histories are repaired on the way out.
Tool-call volume: a degenerate response can queue hundreds of calls that
the run loop then honours one by one. Only the first
``LLM_MAX_TOOL_CALLS_PER_TURN`` calls of a response are kept.
Stalled streams: a turn that emits a few tokens and then goes silent is
not covered by the request timeout, which resets on any byte (keepalives
included). ``LLM_STREAM_IDLE_TIMEOUT`` bounds the gap between events so the
turn fails instead of hanging, and the existing retry path replays it.
"""
def __init__(
self,
inner: Model,
*,
max_tool_calls_per_turn: int = 0,
stream_idle_timeout: float = 0.0,
) -> None:
self._inner = inner
self._max_tool_calls_per_turn = max_tool_calls_per_turn
self._stream_idle_timeout = stream_idle_timeout
def _limiter(self) -> TurnToolCallLimiter:
return TurnToolCallLimiter(self._max_tool_calls_per_turn)
def _log_dropped(self, limiter: TurnToolCallLimiter) -> None:
if limiter.dropped:
logger.warning(
"dropped %d tool call(s) past the per-response limit of %d",
limiter.dropped,
self._max_tool_calls_per_turn,
)
async def close(self) -> None:
await self._inner.close()
def get_retry_advice(self, request: ModelRetryAdviceRequest) -> ModelRetryAdvice | None:
return self._inner.get_retry_advice(request)
async def get_response(
self,
system_instructions: str | None,
input: str | list[TResponseInputItem], # noqa: A002
model_settings: ModelSettings,
tools: list[Tool],
output_schema: AgentOutputSchemaBase | None,
handoffs: list[Handoff],
tracing: ModelTracing,
*,
previous_response_id: str | None,
conversation_id: str | None,
prompt: ResponsePromptParam | None,
) -> ModelResponse:
sanitized = dedupe_input(input)
rewriter = TurnCallIdRewriter(sanitized)
response = await self._inner.get_response(
system_instructions,
cast("str | list[TResponseInputItem]", sanitized),
model_settings,
tools,
output_schema,
handoffs,
tracing,
previous_response_id=previous_response_id,
conversation_id=conversation_id,
prompt=prompt,
)
limiter = self._limiter()
response.output = limiter.filter_items(rewriter.rewrite_items(list(response.output)))
self._log_dropped(limiter)
return response
async def stream_response(
self,
system_instructions: str | None,
input: str | list[TResponseInputItem], # noqa: A002
model_settings: ModelSettings,
tools: list[Tool],
output_schema: AgentOutputSchemaBase | None,
handoffs: list[Handoff],
tracing: ModelTracing,
*,
previous_response_id: str | None,
conversation_id: str | None,
prompt: ResponsePromptParam | None,
) -> AsyncIterator[TResponseStreamEvent]:
sanitized = dedupe_input(input)
rewriter = TurnCallIdRewriter(sanitized)
limiter = self._limiter()
stream = self._inner.stream_response(
system_instructions,
cast("str | list[TResponseInputItem]", sanitized),
model_settings,
tools,
output_schema,
handoffs,
tracing,
previous_response_id=previous_response_id,
conversation_id=conversation_id,
prompt=prompt,
)
async for event in _with_idle_timeout(stream, self._stream_idle_timeout):
guarded = _guard_event(event, rewriter, limiter)
if guarded is not None:
yield guarded
self._log_dropped(limiter)
async def _aclose(stream: AsyncIterator[TResponseStreamEvent]) -> None:
if isinstance(stream, AsyncGenerator):
with contextlib.suppress(Exception):
await stream.aclose()
async def _with_idle_timeout(
stream: AsyncIterator[TResponseStreamEvent], timeout: float
) -> AsyncIterator[TResponseStreamEvent]:
if timeout <= 0:
async for event in stream:
yield event
return
iterator = stream.__aiter__()
while True:
try:
event = await asyncio.wait_for(iterator.__anext__(), timeout)
except StopAsyncIteration:
return
except TimeoutError:
await _aclose(stream)
message = f"model stream produced no event for {timeout:.0f}s"
logger.warning("%s; abandoning the turn", message)
raise TimeoutError(message) from None
yield event
def _guard_event(
event: TResponseStreamEvent, rewriter: TurnCallIdRewriter, limiter: TurnToolCallLimiter
) -> TResponseStreamEvent | None:
if isinstance(event, ResponseOutputItemAddedEvent | ResponseOutputItemDoneEvent):
rewritten = rewriter.rewrite_item(event.item)
if not limiter.allow(rewritten):
return None
if rewritten is not event.item:
return event.model_copy(update={"item": rewritten})
return event
if isinstance(event, ResponseCompletedEvent):
original = list(event.response.output)
output = limiter.filter_items(rewriter.rewrite_items(original))
if output != original:
return event.model_copy(
update={"response": event.response.model_copy(update={"output": output})}
)
return event
def _completed_stream_event(
model_response: ModelResponse, model_name: object | None
) -> TResponseStreamEvent:
@@ -294,19 +471,29 @@ class StrixProvider(MultiProvider):
def get_model(self, model_name: str | None) -> Model:
llm = load_settings().llm
slug = codex.subscription_model(model_name)
idle_timeout = float(llm.stream_idle_timeout)
if slug:
# The ChatGPT subscription backend is always streamed; it has no
# non-streaming mode to fall back to, so LLM_DISABLE_STREAMING
# does not apply here.
return _CodexResponsesModel(
model: Model = _CodexResponsesModel(
slug,
codex.get_subscription_client(),
reasoning_effort=llm.reasoning_effort,
)
model = super().get_model(model_name)
if llm.disable_streaming:
return _NonStreamingModel(model)
return model
else:
model = super().get_model(model_name)
if llm.disable_streaming:
model = _NonStreamingModel(model)
# The wrapper emits its single event only once the whole request
# is done, so an idle gap is meaningless here; the request
# timeout bounds it instead.
idle_timeout = 0.0
return _TurnGuardModel(
model,
max_tool_calls_per_turn=llm.max_tool_calls_per_turn,
stream_idle_timeout=idle_timeout,
)
DEFAULT_MODEL_RETRY = ModelRetrySettings(
+6
View File
@@ -57,6 +57,12 @@ class LlmSettings(BaseSettings):
alias="LLM_DISABLE_STREAMING",
)
timeout: int = Field(default=300, alias="LLM_TIMEOUT")
stream_idle_timeout: int = Field(default=300, ge=0, alias="LLM_STREAM_IDLE_TIMEOUT")
max_tool_calls_per_turn: int = Field(
default=32,
ge=0,
alias="LLM_MAX_TOOL_CALLS_PER_TURN",
)
class DedupeSettings(BaseSettings):
+117
View File
@@ -0,0 +1,117 @@
"""Keep tool-call ids unique within a conversation.
Some providers return per-turn tool-call ids (``exec_command:0``,
``exec_command:1``, ...) whose counter restarts on every turn. Once the same
id appears twice in one conversation, the request payload has two assistant
tool calls sharing an id and strict providers reject the whole turn, which
permanently kills the agent because the malformed history is replayed on
every retry. Rewriting duplicates to fresh unique ids keeps the history
valid for any provider.
"""
from __future__ import annotations
from collections import defaultdict, deque
from typing import Any
from uuid import uuid4
from openai.types.responses import ResponseFunctionToolCall
def new_call_id() -> str:
return f"call_{uuid4().hex}"
def collect_call_ids(items: list[Any]) -> set[str]:
used: set[str] = set()
for item in items:
if isinstance(item, dict):
call_id = item.get("call_id")
if isinstance(call_id, str):
used.add(call_id)
elif isinstance(item, ResponseFunctionToolCall):
used.add(item.call_id)
return used
def dedupe_history_call_ids(items: list[Any]) -> tuple[list[Any], bool]:
"""Rewrite duplicate call ids in a conversation history.
Outputs are paired with their call by order, so parallel calls that share
an id keep answering the right call after the rewrite.
"""
used: set[str] = set()
pending: dict[str, deque[str]] = defaultdict(deque)
rebuilt: list[Any] = []
changed = False
for item in items:
if not isinstance(item, dict):
rebuilt.append(item)
continue
call_id = item.get("call_id")
if not isinstance(call_id, str):
rebuilt.append(item)
continue
kind = item.get("type")
if kind == "function_call":
effective = call_id
if call_id in used:
effective = new_call_id()
item = {**item, "call_id": effective} # noqa: PLW2901
changed = True
used.add(effective)
pending[call_id].append(effective)
elif kind == "function_call_output":
queue = pending.get(call_id)
if queue:
effective = queue.popleft()
if effective != call_id:
item = {**item, "call_id": effective} # noqa: PLW2901
changed = True
rebuilt.append(item)
return rebuilt, changed
def dedupe_input(model_input: str | list[Any]) -> str | list[Any]:
if isinstance(model_input, str):
return model_input
rebuilt, changed = dedupe_history_call_ids(model_input)
return rebuilt if changed else model_input
class TurnCallIdRewriter:
"""Rewrite a single turn's tool-call ids that collide with the history.
A turn's items surface several times (streamed item events, then the
completed response), so the same original id must always map to the same
replacement within the turn.
"""
def __init__(self, model_input: str | list[Any]) -> None:
self._used = set() if isinstance(model_input, str) else collect_call_ids(model_input)
self._remap: dict[str, str] = {}
self._settled: set[str] = set()
def rewrite_item(self, item: Any) -> Any:
if not isinstance(item, ResponseFunctionToolCall):
return item
original = item.call_id
if original in self._settled:
return item
replacement = self._remap.get(original)
if replacement is None:
if original not in self._used:
self._used.add(original)
self._settled.add(original)
return item
replacement = new_call_id()
self._remap[original] = replacement
self._used.add(replacement)
self._settled.add(replacement)
return item.model_copy(update={"call_id": replacement})
def rewrite_items(self, items: list[Any]) -> list[Any]:
return [self.rewrite_item(item) for item in items]
+46
View File
@@ -0,0 +1,46 @@
"""Bound how many tool calls one assistant response may queue.
A degenerate generation can emit hundreds or thousands of tool calls in a
single response — typically a poll/wait loop the model writes out ahead of
time instead of issuing one call and yielding. The run loop honours all of
them, so the agent stops reacting to anything for hours. Keeping only the
first ``limit`` calls of a response bounds that blast radius; the model sees
their results on the next turn and can reconsider.
"""
from __future__ import annotations
from typing import Any
from openai.types.responses import ResponseFunctionToolCall
class TurnToolCallLimiter:
"""Decide, once per call, whether a turn's tool call is within the limit."""
def __init__(self, limit: int) -> None:
self._limit = limit
self._decisions: dict[str, bool] = {}
self._kept = 0
self.dropped = 0
@property
def enabled(self) -> bool:
return self._limit > 0
def allow(self, item: Any) -> bool:
if not self.enabled or not isinstance(item, ResponseFunctionToolCall):
return True
decided = self._decisions.get(item.call_id)
if decided is not None:
return decided
allowed = self._kept < self._limit
if allowed:
self._kept += 1
else:
self.dropped += 1
self._decisions[item.call_id] = allowed
return allowed
def filter_items(self, items: list[Any]) -> list[Any]:
return [item for item in items if self.allow(item)]
+1 -1
View File
@@ -838,7 +838,7 @@ async def _append_tool_required_message(
)
else:
message = (
"Your previous response ended the autonomous Strix run without a lifecycle tool "
"Your previous response ended the autonomous run without a lifecycle tool "
"call. That is invalid in non-interactive mode; plain text final answers are "
"ignored. Continue immediately and call exactly one tool. "
f"If your work is complete, call {finish_tool}. "
+3
View File
@@ -20,6 +20,8 @@ if TYPE_CHECKING:
logger = logging.getLogger(__name__)
LLM_TURN_KEY = "llm_turn"
_STAGE_LABELS: tuple[str, ...] = ("NOTICE", "URGENT", "CRITICAL")
_TURN_WARN_BANDS: tuple[float, ...] = (0.70, 0.85, 0.95)
_ROOT_BUDGET_WARN_BANDS: tuple[float, ...] = (0.70, 0.85, 0.95)
@@ -144,6 +146,7 @@ class ReportUsageHooks(RunHooks[dict[str, Any]]):
system_prompt: str | None, # noqa: ARG002
input_items: list[TResponseInputItem],
) -> None:
context.context[LLM_TURN_KEY] = int(context.context.get(LLM_TURN_KEY, 0)) + 1
try:
self._maybe_warn_turns(context, input_items)
self._maybe_warn_budget(context, input_items)
+2 -2
View File
@@ -293,7 +293,7 @@ async def run_strix_scan(
)
root_agent = build_strix_agent(
name="Strix",
name="Root Agent",
skills=skills,
is_root=True,
scan_mode=scan_mode,
@@ -307,7 +307,7 @@ async def run_strix_scan(
if not is_resume:
await coordinator.register(
root_id,
"Strix",
"Root Agent",
parent_id=None,
task=root_task,
skills=skills,
@@ -1169,3 +1169,120 @@ func TestChatContentRerendersOnWidthAndExpansionChange(t *testing.T) {
}
}
}
// A model or backend failure can be a wrapped exception hundreds of columns
// wide and several lines long. The status row is one line of the chat column, so
// an oversized one widens the whole column - JoinHorizontal pads every row to the
// widest - which pushed the sidebar off screen and wrapped the frame.
func TestLongErrorDoesNotBreakTheFrame(t *testing.T) {
model := New(nil)
model.width, model.height = 120, 24
model.showSplash = false
model.handleEnvelope(stateEnvelope(t, 1, protocol.Snapshot{ScanState: "running"}))
bootstrap := protocol.CollectionBootstrap{
Collection: "agents", Revision: 1, Cursor: 0, NextCursor: 1, Done: true,
Items: []json.RawMessage{rawJSON(t, protocol.Agent{ID: "a0", Name: "Strix", Status: "running"})},
}
model.handleEnvelope(protocol.Envelope{
Version: protocol.Version, Type: "collection_bootstrap", Payload: rawJSON(t, bootstrap),
})
model.errorText = "litellm.APIConnectionError: OpenrouterException - Connection error " +
"while calling https://openrouter.ai/api/v1/chat/completions: HTTPSConnectionPool" +
"(host='openrouter.ai', port=443): Max retries exceeded\nTraceback (most recent " +
"call last):\n File \"/x/y.py\", line 42, in send\n raise err"
model.resizeViewport()
lines := strings.Split(model.View(), "\n")
if len(lines) > model.height {
t.Fatalf("frame is %d rows in a %d-row terminal", len(lines), model.height)
}
for i, line := range lines {
if width := ansi.StringWidth(line); width > model.width {
t.Fatalf("row %d is %d columns in a %d-column terminal", i, width, model.width)
}
}
// The sidebar has to survive: its panels are the right edge of the frame.
if !strings.Contains(ansi.Strip(model.View()), "Strix") {
t.Fatal("the agent tree was pushed out of the frame")
}
}
func TestStatusMessageFlattensAndKeepsItsHint(t *testing.T) {
row := ansi.Strip(statusMessage("boom\nsecond line\twith tabs", red, " · Send message to resume", 60))
if strings.Contains(row, "\n") || strings.Contains(row, "\t") {
t.Fatalf("status row is not a single line: %q", row)
}
if !strings.HasSuffix(row, " · Send message to resume") {
t.Fatalf("the hint was lost: %q", row)
}
if !strings.Contains(row, "boom second line with tabs") {
t.Fatalf("the message was mangled: %q", row)
}
// A message far too long for the row keeps the hint readable.
long := ansi.Strip(statusMessage(strings.Repeat("x", 500), red, " · Send message to resume", 60))
if width := ansi.StringWidth(long); width > 60 {
t.Fatalf("status message is %d columns, want at most 60", width)
}
if !strings.HasSuffix(long, " · Send message to resume") {
t.Fatalf("the hint was clipped away: %q", long)
}
}
// The status row must be exactly as wide as the column it sits in, at every
// terminal size. A narrow terminal cannot fit the quit hint alongside any status
// text, and keeping it anyway made the row wider than the terminal.
func TestStatusRowIsExactlyItsWidth(t *testing.T) {
quitHint := lipgloss.NewStyle().Foreground(white).Render("ctrl-q") +
lipgloss.NewStyle().Foreground(dim).Render(" quit")
longMessage := lipgloss.NewStyle().Foreground(red).Render(strings.Repeat("boom ", 40))
for width := 1; width <= 60; width++ {
for _, testCase := range []struct {
name string
left, right string
}{
{"empty", "", ""},
{"hint only", "", quitHint},
{"long message and hint", longMessage, quitHint},
{"long message alone", longMessage, ""},
} {
row := composeStatusRow(testCase.left, testCase.right, width)
if got := ansi.StringWidth(row); got != width {
t.Fatalf("%s at width %d rendered %d columns: %q",
testCase.name, width, got, ansi.Strip(row))
}
if strings.Contains(row, "\n") {
t.Fatalf("%s at width %d spans rows", testCase.name, width)
}
}
}
if row := composeStatusRow("x", "y", 0); row != "" {
t.Fatalf("a zero-width row should be empty, got %q", row)
}
}
// A running scan in a narrow terminal must not wrap the frame.
func TestNarrowTerminalKeepsTheFrameIntact(t *testing.T) {
for _, width := range []int{8, 10, 13, 14, 20, 40} {
model := New(nil)
model.width, model.height = width, 20
model.showSplash = false
model.handleEnvelope(stateEnvelope(t, 1, protocol.Snapshot{ScanState: "running"}))
bootstrap := protocol.CollectionBootstrap{
Collection: "agents", Revision: 1, Cursor: 0, NextCursor: 1, Done: true,
Items: []json.RawMessage{rawJSON(t, protocol.Agent{ID: "a0", Name: "Strix", Status: "running"})},
}
model.handleEnvelope(protocol.Envelope{
Version: protocol.Version, Type: "collection_bootstrap", Payload: rawJSON(t, bootstrap),
})
model.errorText = strings.Repeat("connection failed ", 20)
model.resizeViewport()
for i, line := range strings.Split(model.View(), "\n") {
if got := ansi.StringWidth(line); got > width {
t.Fatalf("at width %d row %d is %d columns", width, i, got)
}
}
}
}
+4 -1
View File
@@ -214,8 +214,11 @@ func (m *Model) setupLogAppend(line string) {
}
// setupMsg appends a styled feedback line (success green, error red, notice dim).
// The log budgets rows by entry, so a message is flattened to one line first: a
// wrapped exception would otherwise render as several rows and push the launch
// column past the bottom of the terminal.
func (m *Model) setupMsg(text string, style lipgloss.Style) {
m.setupLogAppend(style.Render(text))
m.setupLogAppend(style.Render(flattenStatus(text)))
}
// setupLogRows is how many feedback lines the launch column shows before the
@@ -93,3 +93,25 @@ func TestFocusedPanelsCarryTheGreenBorder(t *testing.T) {
}
}
}
// A wrapped exception is several lines. The log budgets rows by entry, so it has
// to become one row or the launch column grows past the terminal.
func TestSetupLogKeepsMultiLineErrorsToOneRow(t *testing.T) {
model := New(nil)
model.width, model.height = 100, 26
model.showSplash = false
model.handleEnvelope(stateEnvelope(t, 1, protocol.Snapshot{SetupMode: true, ScanState: "setup"}))
model.setupMsg("boom\nTraceback (most recent call last):\n File \"x.py\", line 1\n raise", render.Col(red))
model.resizeViewport()
if entries := len(model.setupLog); entries != 1 {
t.Fatalf("one message became %d log entries", entries)
}
if strings.Contains(model.setupLog[0], "\n") {
t.Fatalf("log entry spans rows: %q", model.setupLog[0])
}
lines := strings.Split(model.View(), "\n")
if len(lines) > model.height {
t.Fatalf("start screen is %d rows in a %d-row terminal", len(lines), model.height)
}
}
+45 -7
View File
@@ -654,8 +654,7 @@ func (m Model) statusView(width int) string {
case "waiting":
left = lipgloss.NewStyle().Foreground(dim).Render("Send message to resume")
if msg := agent.ErrorMessage; msg != "" {
left = lipgloss.NewStyle().Foreground(red).Render(msg) +
lipgloss.NewStyle().Foreground(dim).Render(" · Send message to resume")
left = statusMessage(msg, red, " · Send message to resume", width)
}
case "budget_paused":
left = lipgloss.NewStyle().Foreground(amber).Render("Budget limit reached") +
@@ -670,15 +669,54 @@ func (m Model) statusView(width int) string {
if msg == "" {
msg = "Agent failed"
}
left = lipgloss.NewStyle().Foreground(red).Render(msg) +
lipgloss.NewStyle().Foreground(dim).Render(" · Send message to resume")
left = statusMessage(msg, red, " · Send message to resume", width)
}
}
if m.errorText != "" {
left = lipgloss.NewStyle().Foreground(red).Render(m.errorText)
left = statusMessage(m.errorText, red, "", width-lipgloss.Width(right))
}
gap := max(1, width-lipgloss.Width(left)-lipgloss.Width(right))
return " " + left + strings.Repeat(" ", max(1, gap-1)) + right
return composeStatusRow(left, right, width)
}
// composeStatusRow lays the status text and the corner hint on one row exactly
// width columns wide. A wider row would widen the whole chat column, because
// JoinHorizontal pads every row of a block to its widest, which pushes the
// sidebar off screen and wraps the frame.
func composeStatusRow(left, right string, width int) string {
if width <= 0 {
return ""
}
const leading = 1 // the row is indented one column, like the panels above it
// A terminal can be narrower than the hint itself. Drop the hint rather than
// keep it at the cost of the status, which is the part carrying information;
// ctrl-q works whether or not the row has room to say so.
if lipgloss.Width(right) > 0 && width < lipgloss.Width(right)+leading+2 {
right = ""
}
separator := 0
if lipgloss.Width(right) > 0 {
separator = 1
}
left = truncate(left, max(0, width-leading-lipgloss.Width(right)-separator))
padding := max(0, width-leading-lipgloss.Width(left)-lipgloss.Width(right))
return " " + left + strings.Repeat(" ", padding) + right
}
// statusMessage fits a message and its trailing hint on the one status row. A
// model or backend error can be a wrapped exception several lines long, so it is
// flattened to a single line and clipped, leaving the hint readable.
func statusMessage(message string, color lipgloss.Color, hint string, width int) string {
styledHint := lipgloss.NewStyle().Foreground(dim).Render(hint)
room := max(1, width-2-lipgloss.Width(styledHint))
flat := truncate(flattenStatus(message), room)
return lipgloss.NewStyle().Foreground(color).Render(flat) + styledHint
}
// flattenStatus turns a multi-line message into one line, collapsing the runs of
// whitespace that joining its lines leaves behind.
func flattenStatus(message string) string {
message = strings.NewReplacer("\r\n", " ", "\r", " ", "\n", " ", "\t", " ").Replace(message)
return strings.Join(strings.Fields(message), " ")
}
func (m Model) sweepView() string {
@@ -74,6 +74,8 @@ func vulnerabilityMarkdownReport(v map[string]any) string {
field("Ecosystem", render.StringValue(dep["package_ecosystem"]))
field("Installed Version", render.StringValue(dep["installed_version"]))
field("Fixed Version", render.StringValue(dep["fixed_version"]))
field("Introduced By", render.StringValue(dep["introduced_by"]))
field("Dependency Chain", render.StringValue(dep["dependency_path"]))
}
field("Endpoint", render.StringValue(v["endpoint"]))
field("Method", render.StringValue(v["method"]))
@@ -298,6 +298,8 @@ func vulnerabilityBody(v map[string]any) string {
field("Ecosystem", render.StringValue(dep["package_ecosystem"]))
field("Installed Version", render.StringValue(dep["installed_version"]))
field("Fixed Version", render.StringValue(dep["fixed_version"]))
field("Introduced By", render.StringValue(dep["introduced_by"]))
field("Dependency Chain", render.StringValue(dep["dependency_path"]))
}
field("Endpoint", render.StringValue(v["endpoint"]))
field("Method", render.StringValue(v["method"]))
@@ -57,6 +57,12 @@ func renderDependencyReport(args map[string]any, result any) string {
section("Description", StringValue(args["description"]))
section("Impact", StringValue(args["impact"]))
section("Technical Analysis", StringValue(args["technical_analysis"]))
if reach := StringValue(args["reachability"]); reach != "" && reach != "unknown" {
b.WriteString("\n\n" + Bold(Field).Render("Usage evidence: ") + reach)
if ev := StringValue(args["reachability_evidence"]); ev != "" {
b.WriteString("\n" + ev)
}
}
section("Assumptions", StringValue(args["assumptions"]))
section("Remediation", StringValue(args["remediation_steps"]))
if title == "" {
+1 -1
View File
@@ -431,7 +431,7 @@ _INTERNAL_TURN_PREFIXES = (
"== Inherited context from parent",
# strix.core.execution: the no-tool-call recovery nudge, both modes.
"Your previous message ended a turn without a tool call.",
"Your previous response ended the autonomous Strix run without a lifecycle tool call.",
"Your previous response ended the autonomous run without a lifecycle tool call.",
# strix.core.hooks: budget warnings, the only notices injected unwrapped.
*(
f"[{label}] {subject}"
+1 -1
View File
@@ -1102,7 +1102,7 @@ def resolve_diff_scope_context(
def _is_http_git_repo(url: str) -> bool:
check_url = f"{url.rstrip('/')}/info/refs?service=git-upload-pack"
try:
with requests.get(check_url, headers={"User-Agent": "git/strix"}, timeout=10) as resp:
with requests.get(check_url, headers={"User-Agent": "git/2.43.0"}, timeout=10) as resp:
if resp.status_code >= 400:
return resp.status_code == 401
return "x-git-upload-pack-advertisement" in resp.headers.get("Content-Type", "")
+20
View File
@@ -183,6 +183,24 @@ def _dependency_identity(report: dict[str, Any]) -> tuple[str, str, str] | None:
return cve, ecosystem, package_name
def _manifest_path(report: dict[str, Any]) -> str:
metadata = report.get("dependency_metadata")
if not isinstance(metadata, dict):
return ""
return str(metadata.get("manifest_path") or "").strip()
def _distinct_manifest_paths(candidate: dict[str, Any], report: dict[str, Any]) -> bool:
"""Same CVE/package observed in two different manifests is two findings.
Only applies when both sides carry a manifest_path; a missing path keeps
the legacy CVE/package/ecosystem identity.
"""
candidate_path = _manifest_path(candidate)
report_path = _manifest_path(report)
return bool(candidate_path and report_path and candidate_path != report_path)
def _report_cve(report: dict[str, Any]) -> str:
return str(report.get("cve") or "").strip().upper()
@@ -228,6 +246,8 @@ def _check_dependency_duplicate(
report_cve, report_ecosystem, report_package_name = report_identity
if (report_cve, report_package_name) != (cve, package_name):
continue
if _distinct_manifest_paths(candidate, report):
continue
if report_ecosystem == ecosystem:
return {
"is_duplicate": True,
+4
View File
@@ -531,6 +531,10 @@ def _result_properties(
if value not in (None, ""):
strix[key] = value
dependency_metadata = report.get("dependency_metadata")
if isinstance(dependency_metadata, dict) and dependency_metadata:
strix["dependency_metadata"] = dependency_metadata
# SARIF is written for external upload (code-scanning / ASPM), so it must
# NOT carry the weaponized exploit payload — that stays a local run
# artifact (vulnerabilities.json / the finding MD). We surface the PoC
+2
View File
@@ -205,6 +205,8 @@ def render_vulnerability_md(report: dict[str, Any]) -> str: # noqa: PLR0912, PL
("Ecosystem", dep_meta.get("package_ecosystem")),
("Installed Version", dep_meta.get("installed_version")),
("Fixed Version", dep_meta.get("fixed_version")),
("Introduced By", dep_meta.get("introduced_by")),
("Dependency Chain", dep_meta.get("dependency_path")),
("Endpoint", report.get("endpoint")),
("Method", report.get("method")),
("CVE", report.get("cve")),
+115 -11
View File
@@ -28,7 +28,7 @@ Run from the repo root and store output in the shared artifact directory used by
the source-aware pass:
```bash
ART=/workspace/.strix-source-aware
ART=/workspace/.source-aware
mkdir -p "$ART"
# Record the vuln DB age so a stale DB is a visible signal, not a silent clean scan.
@@ -39,9 +39,11 @@ trivy version --format json 2>/dev/null | tee "$ART/trivy-version.json"
# sandbox with egress gets the freshest CVEs; if the update fails, fall back to the
# cached DB instead of failing the scan. --offline-scan keeps per-package advisory
# lookups offline.
trivy fs --scanners vuln --timeout 30m --offline-scan \
# --list-all-pkgs includes the package graph (Relationship + DependsOn) needed
# to attribute transitive CVEs to the direct dependency that introduces them.
trivy fs --scanners vuln --timeout 30m --offline-scan --list-all-pkgs \
--format json --output "$ART/trivy-sca.json" . \
|| trivy fs --scanners vuln --timeout 30m --offline-scan --skip-db-update \
|| trivy fs --scanners vuln --timeout 30m --offline-scan --skip-db-update --list-all-pkgs \
--format json --output "$ART/trivy-sca.json" . \
|| true
```
@@ -75,18 +77,111 @@ For each entry under `.Results[].Vulnerabilities[]` in `trivy-sca.json`, collect
- `CVSS` — the published advisory base score
- `PrimaryURL` / references — to verify the advisory
Deduplicate by `(CVE, PkgName, InstalledVersion)`. File one
`create_dependency_report` per CVE — do not batch multiple CVEs into one report.
Deduplicate by `(CVE, PkgName, Target)` — the same CVE/package observed in two
different manifests (e.g. two workspaces of a monorepo) is two findings, one
per manifest. File one `create_dependency_report` per CVE — do not batch
multiple CVEs into one report.
### Attribute transitive CVEs to the direct dependency
With `--list-all-pkgs`, each `.Results[].Packages[]` entry carries `ID`
(`name@version`), `Relationship` (`direct` / `indirect`) and `DependsOn` (the
`ID`s it resolves to). For every vulnerable package that is **indirect**, walk
the `DependsOn` graph backwards to find the `direct` package(s) whose closure
contains it, then pass to `create_dependency_report`:
- `introduced_by` — the direct dependency as `name@version` (e.g.
`express@4.18.1`). If several direct dependencies pull it in, pick the
primary one and name the rest in `technical_analysis`.
- `dependency_path` — the shortest resolution chain from that direct
dependency to the vulnerable package, joined with ` > ` (e.g.
`express@4.18.1 > body-parser@1.20.0 > qs@6.10.2`).
- Omit both when the vulnerable package is itself a direct dependency.
If the ecosystem's lockfile gives trivy no graph (`DependsOn` absent), derive
the chain from the package manager instead (`npm ls <pkg>`, `pnpm why <pkg>`,
`yarn why <pkg>`, `pipdeptree --reverse -p <pkg>`, `go mod graph`,
`mvn dependency:tree`, ...) — and if that also fails, leave the fields out
rather than guessing.
For transitive findings, `remediation_steps` must be actionable at the
**direct-dependency level**: upgrading the vulnerable package directly is
usually impossible from the app's own manifest. Say which direct dependency to
bump (a version whose closure resolves the fixed version), or how to force the
resolution (npm `overrides` / yarn `resolutions` / pnpm `pnpm.overrides` /
Maven `dependencyManagement` / Gradle resolution strategy / `go mod edit`),
not just "upgrade <vulnerable pkg> to <fixed>".
### Usage / reachability analysis (required for every dependency CVE)
For every CVE you are about to report, run a static usage analysis and record
the result in the structured `reachability` + `reachability_evidence` fields.
The level is an **evidence ladder, never an exploitability verdict** — claim
only what you proved, and cite the proof. It never changes severity (that is
`advisory_cvss` alone); it exists so the reader can prioritize.
**Go — use govulncheck (real call-graph analysis):**
```bash
# Symbol-level: reports only vulnerabilities whose vulnerable functions are
# actually reachable from application code. Needs the Go toolchain + module
# deps; if either is missing, fall back to the checks below rather than
# claiming a level.
if command -v govulncheck >/dev/null && go version >/dev/null 2>&1; then
govulncheck -format json ./... > "$ART/govulncheck.json" || true
fi
```
- A finding with a call stack ⇒ `reachability=reachable_call_path`, put the
call-path excerpt (entrypoint → vulnerable function) in
`reachability_evidence`.
- Listed as affecting a required module but with no reachable symbol ⇒ fall
back to the import/symbol checks below (`imported` / `not_imported`).
**All other ecosystems — import check, then symbol match:**
1. **Import check.** Search application code (exclude lockfiles, vendored
deps, `node_modules`, build output) for imports of the vulnerable package:
`ast-grep`/`rg` for `import`/`require`/`from X import` of the package (and
its ecosystem import name, which may differ from the registry name, e.g.
`PyYAML``yaml`). No hits ⇒ `not_imported`, with the search scope stated
in `reachability_evidence`. For a **transitive** dependency, the check is
whether application code imports it directly; if not, it is reachable only
through the direct dependency — check whether the direct dep's usage can
hit it (if unclear, use `imported` when the direct dep is used at all).
2. **Symbol match.** Read the advisory (GHSA/NVD/OSV `affected[].ecosystem_specific.imports` or the
advisory text) for the affected functions/classes/APIs. Search application
code for those symbols (`ast-grep` pattern or `rg -n`). Hits ⇒
`vulnerable_symbol_used`, with repo-relative `file:line` of each hit (up
to a handful) in `reachability_evidence`. Imported but no affected-symbol
usage found (or the advisory names no symbols) ⇒ `imported`.
3. If the analysis was not performed or is inconclusive (obfuscated code,
dynamic loading, unparsable sources) ⇒ `unknown` and say why in
`assumptions`.
Cheap-first budgeting: the import check is one search per package — always do
it. Do the symbol match at least for every `critical`/`high`/KEV CVE; batch
the searches. Never let this analysis stall reporting — `unknown` with a
reason beats an unverified claim.
Anti-overclaim rules:
- `not_imported` still does NOT mean safe (dynamic `import()`/reflection/
framework wiring evade static search) — never phrase it as "not exploitable".
- `reachable_call_path` is reserved for call-graph tools (govulncheck); a
symbol grep hit is `vulnerable_symbol_used`, no matter how convinced you are.
- The tool rejects any level other than `unknown` without
`reachability_evidence`.
### Reachability is a confidence modifier, not a gate
Do NOT suppress or downgrade a known CVE just because you could not prove the
vulnerable code path is reachable. Report it, set `advisory_cvss` from the
advisory, and use `assumptions` to note reachability (e.g. "the vulnerable
`template()` API does not appear to be imported in application code, so practical
exploitability is uncertain"). If you *can* show reachability or chain it into a
dynamic exploit, do that and report it as a normal dynamic finding with
`create_vulnerability_report` instead.
advisory, record the usage analysis in `reachability`/`reachability_evidence`,
and use `assumptions` for anything softer. If you *can* actually trigger the
vulnerable path or chain it into a dynamic exploit, additionally report that
as a normal dynamic finding with `create_vulnerability_report` (the standalone
CVE stays in its own `create_dependency_report`).
## Reporting
@@ -107,6 +202,12 @@ findings and rejects empty PoC fields):
- `package_ecosystem` — normalized ecosystem from `.Results[].Type` (lowercased,
e.g. `npm`, `pypi`, `go`, `maven`, `rubygems`, `cargo`) (required).
- `fixed_version``FixedVersion` (leave empty only if no fix is published).
- `manifest_path` — the repo-relative `Target` lockfile/manifest path
(required). Strip any scan-workspace or repo checkout directory prefix so
the path is relative to the repository root (e.g. `package-lock.json`,
`services/api/pom.xml`); the tool rejects absolute paths and `..` segments.
This binds the finding to the exact file so remediation can target the
right repository.
- Reference the repo-relative `Target` lockfile path in `description` /
`technical_analysis` (no leading slash) so the finding is traceable.
- Put the concrete proof in `description` / `technical_analysis`: package name,
@@ -120,7 +221,8 @@ findings and rejects empty PoC fields):
- Set `cwe` to the most specific `CWE-NNN` when the advisory names one.
- Do NOT cap severity at LOW just because there is no dynamic reproduction — use
the advisory score.
- Use `assumptions` for reachability/exploitability caveats.
- Set `reachability` + `reachability_evidence` from the usage analysis above;
use `assumptions` for anything softer (confidence, caveats, analysis limits).
Verify the CVE with `web_search` when available before reporting. Never guess or
hallucinate a CVE id.
@@ -136,3 +238,5 @@ hallucinate a CVE id.
- Do not silently drop a known CVE because it lacks a dynamic PoC — that is the
exact failure this skill prevents.
- Do not downgrade advisory severity for lack of dynamic reproduction.
- Do not claim a `reachability` level the evidence does not prove — `unknown`
with a reason is always acceptable; an overclaimed level never is.
+12 -12
View File
@@ -12,7 +12,7 @@ Use this skill for source-heavy analysis where static and structural signals sho
Run tools from repo root and store outputs in a dedicated artifact directory:
```bash
mkdir -p /workspace/.strix-source-aware
mkdir -p /workspace/.source-aware
```
## Baseline Coverage Bundle (Recommended)
@@ -20,7 +20,7 @@ mkdir -p /workspace/.strix-source-aware
Run this baseline once per repository before deep narrowing:
```bash
ART=/workspace/.strix-source-aware
ART=/workspace/.source-aware
mkdir -p "$ART"
semgrep scan --config p/default --config p/golang --config p/secrets \
@@ -30,7 +30,7 @@ python3 - <<'PY'
import json
from pathlib import Path
art = Path("/workspace/.strix-source-aware")
art = Path("/workspace/.source-aware")
semgrep_json = art / "semgrep.json"
targets_file = art / "sg-targets.txt"
@@ -70,10 +70,10 @@ Use Semgrep as the default static triage pass:
```bash
# Preferred deterministic profile set (works with --metrics=off)
semgrep scan --config p/default --config p/golang --config p/secrets \
--metrics=off --json --output /workspace/.strix-source-aware/semgrep.json .
--metrics=off --json --output /workspace/.source-aware/semgrep.json .
# If you choose auto config, do not combine it with --metrics=off
semgrep scan --config auto --json --output /workspace/.strix-source-aware/semgrep-auto.json .
semgrep scan --config auto --json --output /workspace/.source-aware/semgrep-auto.json .
```
If diff scope is active, restrict to changed files first, then expand only when needed.
@@ -85,8 +85,8 @@ Use `sg` for structure-aware code hunting:
```bash
# Ruleless structural pass over deterministic target list (no sgconfig.yml required)
xargs -r -n 200 sg run --pattern '$F($$$ARGS)' --json=stream \
< /workspace/.strix-source-aware/sg-targets.txt \
> /workspace/.strix-source-aware/ast-grep.json 2> /workspace/.strix-source-aware/ast-grep.log || true
< /workspace/.source-aware/sg-targets.txt \
> /workspace/.source-aware/ast-grep.json 2> /workspace/.source-aware/ast-grep.log || true
```
Target high-value patterns such as:
@@ -110,15 +110,15 @@ Use outputs to improve route/symbol/sink maps for subsequent targeted scans.
Detect hardcoded credentials:
```bash
gitleaks detect --source . --report-format json --report-path /workspace/.strix-source-aware/gitleaks.json
trufflehog filesystem --json . > /workspace/.strix-source-aware/trufflehog.json
gitleaks detect --source . --report-format json --report-path /workspace/.source-aware/gitleaks.json
trufflehog filesystem --json . > /workspace/.source-aware/trufflehog.json
```
Run repository-wide dependency and config checks:
```bash
trivy fs --scanners vuln,misconfig --timeout 30m --offline-scan \
--format json --output /workspace/.strix-source-aware/trivy-fs.json . || true
--format json --output /workspace/.source-aware/trivy-fs.json . || true
```
Known-CVE dependency findings are the one exception to the "report only after
@@ -132,9 +132,9 @@ For frontends and Node services, layer these on top of the language-agnostic
passes above:
```bash
retire --path . --outputformat json --outputpath /workspace/.strix-source-aware/retire.json || true
retire --path . --outputformat json --outputpath /workspace/.source-aware/retire.json || true
eslint --no-config-lookup --rule '{"no-eval":2,"no-implied-eval":2}' \
-f json -o /workspace/.strix-source-aware/eslint.json . || true
-f json -o /workspace/.source-aware/eslint.json . || true
```
When you hit a minified bundle, run `js-beautify <file>` for a readable
@@ -202,7 +202,7 @@ Confirm with a version/patch check before firing — these are destructive.
## Tooling
**None of the AD tools below ship in the Strix sandbox by default** (the image is Kali-rolling but installs only web-focused tooling). Install what the task needs — the sandbox has `pipx`, `pip`, `go`, `git`, and Kali's apt repos. AD testing also requires **network reachability to the target DC/subnet**, which the default web-target sandbox usually lacks; confirm connectivity first.
**None of the AD tools below ship in the sandbox by default** (the image is Kali-rolling but installs only web-focused tooling). Install what the task needs — the sandbox has `pipx`, `pip`, `go`, `git`, and Kali's apt repos. AD testing also requires **network reachability to the target DC/subnet**, which the default web-target sandbox usually lacks; confirm connectivity first.
```
# Python identity toolkit (impacket = GetUserSPNs/GetNPUsers/secretsdump/ntlmrelayx/getST/addcomputer/rbcd)
+1 -1
View File
@@ -5,7 +5,7 @@ description: Run Python through exec_command in the SDK sandbox. Use the image-b
# Python In The Sandbox
Use `exec_command` for Python. There is no separate Strix Python executor.
Use `exec_command` for Python. There is no separate Python executor.
Prefer writing reusable scripts to a `.py` file and running them with
`python3 <name>.py`. For short one-off transformations, `python3 -c` or a
@@ -80,7 +80,7 @@ Gadget availability depends on package versions — enumerate `node_modules` in
1. **Identify merge points** — Search for extend/merge/defaults/deep copy on user-controlled objects
2. **Baseline probe** — Inject benign pollution marker:
```json
{"__proto__": {"strixPolluted": "yes"}}
{"__proto__": {"pollutionCanary": "yes"}}
```
Verify via response behavior, error messages, or follow-up request reading shared state
3. **Shape variants** — Test `__proto__`, `constructor.prototype`, nested bracket notation
@@ -121,7 +121,7 @@ Gadget availability depends on package versions — enumerate `node_modules` in
## Pro Tips
1. Always verify pollution with a unique canary key (`strixPolluted_<random>`) before attempting RCE gadgets
1. Always verify pollution with a unique canary key (`pollutionCanary_<random>`) before attempting RCE gadgets
2. In white-box scans, grep for `merge`, `extend`, `defaultsDeep`, `assign` with user input
3. Check both request parsing and response template config merges (second-order)
4. Node gadget chains are version-specific — confirm package version before claiming RCE
+25
View File
@@ -14,6 +14,7 @@ from agents import RunContextWrapper, function_tool
from strix.core.agents import Status, coordinator_from_context
from strix.core.execution import notify_parent_on_terminal
from strix.core.hooks import LLM_TURN_KEY
from strix.skills import validate_requested_skills
@@ -224,6 +225,7 @@ _WAIT_DEFAULT_TIMEOUT_S = 300
# ``timeout_seconds`` the model asks for. One second of headroom lets the
# tool's own timeout fire first and return a clean result.
_WAIT_HARD_CEILING_S = _WAIT_DEFAULT_TIMEOUT_S + 1
_WAITED_TURN_KEY = "waited_llm_turn"
@function_tool(timeout=_WAIT_HARD_CEILING_S)
@@ -239,6 +241,11 @@ async def wait_for_agents( # noqa: PLR0911
completion reports. You resume the instant any message arrives, so
size ``timeout_seconds`` to the work you're awaiting.
**Issue exactly one wait, then stop and react to what it returns.**
This call blocks and resumes on its own; it is not a poll you repeat.
Do not write out a wait/check loop ahead of time a second wait in
the same turn returns immediately without waiting.
**This tool is only for waiting on other agents.** Two things it is
NOT for:
@@ -290,6 +297,24 @@ async def wait_for_agents( # noqa: PLR0911
default=str,
)
turn = inner.get(LLM_TURN_KEY)
if turn is not None and inner.get(_WAITED_TURN_KEY) == turn:
return json.dumps(
{
"success": True,
"wait_outcome": "already_waited",
"reason": reason,
"note": (
"You already waited in this turn. A single wait_for_agents blocks and "
"resumes on its own, so queueing more waits only strands you — issue one "
"wait, then react to what it returns."
),
},
ensure_ascii=False,
default=str,
)
inner[_WAITED_TURN_KEY] = turn
async with coordinator._lock:
stopped = coordinator.statuses.get(me) == "stopped"
if stopped:
+2 -2
View File
@@ -1,7 +1,7 @@
"""Bound oversized tool results before they enter agent history.
Oversized results are spilled into the sandbox at
``/workspace/.strix/tool-output/<id>.txt``; the agent sees a head + tail slice
``/workspace/.tool-output/<id>.txt``; the agent sees a head + tail slice
plus the path and reads the rest back with its own file tools. The spill writer
is injected by the runner via :func:`configure_spill_writer`.
"""
@@ -25,7 +25,7 @@ _WORKSPACE_SPILL_NOTICE = (
"in the sandbox; read it with exec_command (e.g. `sed -n`, `grep`, `cat`) ...]"
)
WORKSPACE_SPILL_DIR = "/workspace/.strix/tool-output"
WORKSPACE_SPILL_DIR = "/workspace/.tool-output"
# Longest possible workspace path, used only to reserve notice bytes.
_SAMPLE_WORKSPACE_PATH = f"{WORKSPACE_SPILL_DIR}/{'0' * 32}.txt"
+5 -1
View File
@@ -189,7 +189,11 @@ def build_raw_request(
final_headers = {**headers}
final_headers.setdefault("Host", parsed.netloc)
final_headers.setdefault("User-Agent", "strix")
final_headers.setdefault(
"User-Agent",
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 "
"(KHTML, like Gecko) Chrome/125.0.0.0 Safari/537.36",
)
# Framing headers inherited from the captured request describe the ORIGINAL
# body; once the body is modified for replay they are stale. We always send a
# plain (non-chunked) body with an explicit Content-Length, so drop any
+161 -3
View File
@@ -719,12 +719,47 @@ def _dependency_severity(advisory_cvss: float | None) -> tuple[float, str]:
return score, "none"
_VALID_REACHABILITY = frozenset(
{
"not_imported",
"imported",
"vulnerable_symbol_used",
"reachable_call_path",
"unknown",
}
)
def _validate_manifest_path(manifest_path: str | None) -> str | None:
"""Return an error message when manifest_path is missing or unsafe."""
path = (manifest_path or "").strip()
if not path:
return (
"manifest_path is required: pass the repo-relative path of the "
"lockfile/manifest where the vulnerable version was observed "
"(trivy's Target, e.g. 'package-lock.json' or "
"'services/api/pom.xml'). It binds the finding to its exact file "
"so remediation can target the right repository."
)
if path.startswith("/") or "\\" in path or path.split("/")[0].endswith(":"):
return f"manifest_path must be a relative path within the repository, got {path!r}"
segments = path.split("/")
if any(segment in ("", ".", "..") for segment in segments):
return f"manifest_path must not contain empty, '.', or '..' segments, got {path!r}"
return None
def _build_dependency_metadata(
*,
package_name: str,
installed_version: str,
package_ecosystem: str | None,
fixed_version: str | None,
introduced_by: str | None,
dependency_path: str | None,
manifest_path: str | None = None,
reachability: str | None = None,
reachability_evidence: str | None = None,
) -> dict[str, str]:
metadata = {
"package_name": package_name.strip(),
@@ -732,17 +767,43 @@ def _build_dependency_metadata(
}
if package_ecosystem and package_ecosystem.strip():
metadata["package_ecosystem"] = package_ecosystem.strip()
if manifest_path and manifest_path.strip():
metadata["manifest_path"] = manifest_path.strip()
if fixed_version and fixed_version.strip():
metadata["fixed_version"] = fixed_version.strip()
if introduced_by and introduced_by.strip():
metadata["introduced_by"] = introduced_by.strip()
if dependency_path and dependency_path.strip():
metadata["dependency_path"] = dependency_path.strip()
# "unknown" is the absent case — omitting it keeps the jsonb contract clean,
# and evidence without a level would have nothing to qualify.
if reachability and reachability.strip() and reachability.strip() != "unknown":
metadata["reachability"] = reachability.strip()
if reachability_evidence and reachability_evidence.strip():
metadata["reachability_evidence"] = reachability_evidence.strip()
return metadata
_REACHABILITY_EVIDENCE_LABELS = {
"not_imported": "not imported by application code",
"imported": "imported by application code; affected API usage unconfirmed",
"vulnerable_symbol_used": "the advisory's affected API is used in application code",
"reachable_call_path": (
"a call path from application code to the vulnerable function was proven"
),
}
def _build_dependency_evidence(
*,
cve: str,
package_name: str,
installed_version: str,
fixed_version: str | None,
introduced_by: str | None,
dependency_path: str | None,
reachability: str | None = None,
reachability_evidence: str | None = None,
) -> str:
evidence = (
f"**Advisory evidence:** `{cve}` applies to `{package_name}` "
@@ -750,6 +811,22 @@ def _build_dependency_evidence(
)
if fixed_version and fixed_version.strip():
evidence += f" The advisory is fixed in `{fixed_version.strip()}`."
if introduced_by and introduced_by.strip():
evidence += (
f"\n\n**Transitive dependency:** introduced by the direct "
f"dependency `{introduced_by.strip()}`."
)
if dependency_path and dependency_path.strip():
evidence += f"\n\n**Dependency chain:** `{dependency_path.strip()}`"
label = _REACHABILITY_EVIDENCE_LABELS.get((reachability or "").strip().lower())
if label:
evidence += f"\n\n**Usage analysis:** {label}."
if reachability_evidence and reachability_evidence.strip():
evidence += f" {reachability_evidence.strip()}"
evidence += (
" This is a prioritization signal from static analysis, not a"
" proof of exploitability or of safety."
)
return evidence
@@ -770,6 +847,11 @@ async def _do_create_dependency( # noqa: PLR0912
advisory_cvss: float | None,
technical_analysis: str | None,
fix_effort: str,
introduced_by: str | None = None,
dependency_path: str | None = None,
manifest_path: str | None = None,
reachability: str = "unknown",
reachability_evidence: str | None = None,
agent_id: str | None = None,
agent_name: str | None = None,
) -> dict[str, Any]:
@@ -806,6 +888,22 @@ async def _do_create_dependency( # noqa: PLR0912
f"Invalid fix_effort: {fix_effort!r}. Must be one of: {sorted(_VALID_FIX_EFFORT)}"
)
manifest_err = _validate_manifest_path(manifest_path)
if manifest_err:
errors.append(manifest_err)
reachability = (reachability or "unknown").strip().lower()
if reachability not in _VALID_REACHABILITY:
errors.append(
f"Invalid reachability: {reachability!r}. Must be one of: {sorted(_VALID_REACHABILITY)}"
)
elif reachability != "unknown" and not (reachability_evidence or "").strip():
errors.append(
"reachability_evidence is required when reachability is not 'unknown': "
"cite the concrete proof (import file:line, matched symbol usage, or "
"govulncheck call path). Never claim a reachability level without evidence."
)
if advisory_cvss is None:
errors.append(
"advisory_cvss is required: read the published advisory base score "
@@ -824,12 +922,21 @@ async def _do_create_dependency( # noqa: PLR0912
installed_version=installed_version,
package_ecosystem=package_ecosystem,
fixed_version=fixed_version,
introduced_by=introduced_by,
dependency_path=dependency_path,
manifest_path=manifest_path,
reachability=reachability,
reachability_evidence=reachability_evidence,
)
evidence = _build_dependency_evidence(
cve=parsed_cve,
package_name=package_name.strip(),
installed_version=installed_version.strip(),
fixed_version=fixed_version,
introduced_by=introduced_by,
dependency_path=dependency_path,
reachability=reachability,
reachability_evidence=reachability_evidence,
)
try:
@@ -922,10 +1029,15 @@ async def create_dependency_report(
remediation_steps: str,
assumptions: str,
package_ecosystem: str,
manifest_path: str | None = None,
fixed_version: str | None = None,
cwe: str | None = None,
technical_analysis: str | None = None,
fix_effort: str = "low",
introduced_by: str | None = None,
dependency_path: str | None = None,
reachability: str = "unknown",
reachability_evidence: str | None = None,
) -> str:
"""File a known-CVE dependency (SCA) finding — one report per CVE x package.
@@ -950,9 +1062,26 @@ async def create_dependency_report(
- Re-reporting the same CVE/package already filed.
**Reachability**: do NOT silently downgrade or suppress a finding
because the vulnerable code path may be unreachable instead state
reachability as an ``assumptions`` / confidence factor. Report the
finding; let the reader weigh exploitability.
because the vulnerable code path may be unreachable report it, and
record what the usage analysis showed via the structured
``reachability`` + ``reachability_evidence`` fields (see the
dependency-cve-scanning skill for the analysis procedure). The level
is an evidence ladder, never an exploitability verdict:
- ``not_imported`` the package is never imported/required by
application code (strongest de-prioritization signal; still not
proof of safety dynamic loading, reflection, or framework wiring
can evade static search).
- ``imported`` application code imports the package, but usage of
the advisory's affected API was not confirmed.
- ``vulnerable_symbol_used`` the advisory's affected
function/class/API appears in application code.
- ``reachable_call_path`` a call-graph tool (e.g. ``govulncheck``)
proved a path from application code to the vulnerable function.
- ``unknown`` usage analysis was not performed or was inconclusive.
Severity is still derived solely from ``advisory_cvss`` the
reachability level never changes the rating, only prioritization.
**Formatting**: use markdown in text fields (``**bold**``, ``inline
code`` for package/version identifiers, fenced code blocks for
@@ -978,6 +1107,30 @@ async def create_dependency_report(
technical_analysis: Optional deeper mechanism/root-cause detail.
fix_effort: One of ``trivial`` / ``low`` / ``medium`` / ``high``
(dependency upgrades are usually ``trivial``/``low``).
introduced_by: For a **transitive** dependency, the direct
dependency (from the project's own manifest) that pulls the
vulnerable package in, as ``name@version`` (e.g.
``express@4.18.1``). Omit when the vulnerable package is
itself a direct dependency.
dependency_path: The resolution chain from the direct dependency
to the vulnerable package, joined with `` > `` (e.g.
``express@4.18.1 > body-parser@1.20.0 > qs@6.10.2``). Omit
for direct dependencies.
manifest_path: **Required.** The repo-relative path of the
lockfile/manifest where the vulnerable version was observed
trivy's ``Target`` (e.g. ``package-lock.json``,
``services/api/pom.xml``). Strip any scan-workspace or repo
checkout directory prefix so the path is relative to the
repository root. This binds the finding to its exact file so
remediation can target the right repository.
reachability: Usage-evidence level from static analysis one of
``not_imported`` / ``imported`` / ``vulnerable_symbol_used`` /
``reachable_call_path`` / ``unknown``. Claim only what the
evidence proves; when in doubt use ``unknown``.
reachability_evidence: The concrete proof for the claimed level
(required for any level other than ``unknown``): repo-relative
``file:line`` of the import or symbol usage, the matched
advisory symbols, or the govulncheck call-path excerpt.
"""
agent_id, agent_name = _caller_identity(ctx)
@@ -997,6 +1150,11 @@ async def create_dependency_report(
advisory_cvss=advisory_cvss,
technical_analysis=technical_analysis,
fix_effort=fix_effort,
introduced_by=introduced_by,
dependency_path=dependency_path,
manifest_path=manifest_path,
reachability=reachability,
reachability_evidence=reachability_evidence,
agent_id=agent_id,
agent_name=agent_name,
)
+11 -7
View File
@@ -31,7 +31,7 @@ from openai.types.responses import (
from strix.config import codex, loader
from strix.config.loader import load_settings
from strix.config.models import StrixProvider, _NonStreamingModel
from strix.config.models import StrixProvider, _NonStreamingModel, _TurnGuardModel
if TYPE_CHECKING:
@@ -299,10 +299,11 @@ def test_get_model_wraps_when_disabled(
load_settings()
model = StrixProvider().get_model("openai/gpt-4o-mini")
assert isinstance(model, _NonStreamingModel)
assert isinstance(model, _TurnGuardModel)
assert isinstance(model._inner, _NonStreamingModel)
def test_get_model_unwrapped_by_default(
def test_get_model_keeps_streaming_by_default(
monkeypatch: pytest.MonkeyPatch, _reset_settings: None
) -> None:
inner = _DummyModel()
@@ -310,17 +311,20 @@ def test_get_model_unwrapped_by_default(
load_settings()
model = StrixProvider().get_model("openai/gpt-4o-mini")
assert model is inner
assert isinstance(model, _TurnGuardModel)
assert model._inner is inner
def test_get_model_does_not_wrap_subscription_model(
def test_get_model_guards_subscription_model_but_keeps_it_streaming(
monkeypatch: pytest.MonkeyPatch, _reset_settings: None
) -> None:
# Subscription (ChatGPT) models are always streamed and must not be wrapped.
# Subscription (ChatGPT) models are always streamed, so LLM_DISABLE_STREAMING
# must not apply — but a runaway response needs capping there too.
monkeypatch.setattr(codex, "subscription_model", lambda *_: "gpt-5.5")
monkeypatch.setattr(codex, "get_subscription_client", lambda: AsyncOpenAI(api_key="x"))
monkeypatch.setenv("LLM_DISABLE_STREAMING", "true")
load_settings()
model = StrixProvider().get_model("gpt-5.5")
assert not isinstance(model, _NonStreamingModel)
assert isinstance(model, _TurnGuardModel)
assert not isinstance(model._inner, _NonStreamingModel)
+315
View File
@@ -141,6 +141,7 @@ async def test_dependency_report_sets_class_and_metadata(report_state: ReportSta
remediation_steps="Upgrade to 4.17.21.",
assumptions="Assumes the template sink is reachable.",
package_ecosystem="npm",
manifest_path="package-lock.json",
fixed_version="4.17.21",
cwe="CWE-94",
advisory_cvss=7.2,
@@ -160,10 +161,76 @@ async def test_dependency_report_sets_class_and_metadata(report_state: ReportSta
"package_name": "lodash",
"installed_version": "4.17.20",
"package_ecosystem": "npm",
"manifest_path": "package-lock.json",
"fixed_version": "4.17.21",
}
async def test_dependency_report_records_transitive_chain(report_state: ReportState) -> None:
result = await _do_create_dependency(
title="CVE-2022-24999 in qs 6.10.2",
description="Prototype pollution in qs parsing.",
target="repo/package.json",
cve="CVE-2022-24999",
package_name="qs",
installed_version="6.10.2",
impact="Denial of service via crafted query strings.",
remediation_steps="Upgrade express to 4.18.2, which resolves qs 6.11.0.",
assumptions="qs parses all incoming query strings by default.",
package_ecosystem="npm",
manifest_path="package-lock.json",
fixed_version="6.10.3",
cwe="CWE-1321",
advisory_cvss=7.5,
technical_analysis=None,
fix_effort="trivial",
introduced_by="express@4.18.1",
dependency_path="express@4.18.1 > body-parser@1.20.0 > qs@6.10.2",
)
assert result["success"] is True
report = report_state.vulnerability_reports[0]
assert report["dependency_metadata"]["introduced_by"] == "express@4.18.1"
assert (
report["dependency_metadata"]["dependency_path"]
== "express@4.18.1 > body-parser@1.20.0 > qs@6.10.2"
)
assert (
"**Transitive dependency:** introduced by the direct dependency `express@4.18.1`."
in report["evidence"]
)
assert (
"**Dependency chain:** `express@4.18.1 > body-parser@1.20.0 > qs@6.10.2`"
in report["evidence"]
)
async def test_dependency_report_omits_blank_chain_fields(report_state: ReportState) -> None:
result = await _do_create_dependency(
title="CVE-2024-0001 in sample 1.0.0",
description="Published advisory affects the pinned version.",
target="repo/package.json",
cve="CVE-2024-0001",
package_name="sample",
installed_version="1.0.0",
impact="Impact.",
remediation_steps="Upgrade.",
assumptions="Assumptions.",
package_ecosystem="npm",
manifest_path="package-lock.json",
fixed_version=None,
cwe=None,
advisory_cvss=5.0,
technical_analysis=None,
fix_effort="trivial",
introduced_by=" ",
dependency_path=None,
)
assert result["success"] is True
report = report_state.vulnerability_reports[0]
assert "introduced_by" not in report["dependency_metadata"]
assert "dependency_path" not in report["dependency_metadata"]
async def test_dependency_report_with_zero_cvss_remains_low_severity(
report_state: ReportState,
) -> None:
@@ -178,6 +245,7 @@ async def test_dependency_report_with_zero_cvss_remains_low_severity(
remediation_steps="Upgrade to 1.0.1.",
assumptions="Assumes the package is included in deployed builds.",
package_ecosystem="npm",
manifest_path="package-lock.json",
fixed_version="1.0.1",
cwe=None,
advisory_cvss=0.0,
@@ -192,6 +260,124 @@ async def test_dependency_report_with_zero_cvss_remains_low_severity(
assert report["cvss"] == 0.0
async def test_dependency_report_records_reachability(report_state: ReportState) -> None:
result = await _do_create_dependency(
title="CVE-2021-23337 in lodash 4.17.20",
description="Command injection via template.",
target="repo/package.json",
cve="CVE-2021-23337",
package_name="lodash",
installed_version="4.17.20",
impact="Command injection where template is used.",
remediation_steps="Upgrade to 4.17.21.",
assumptions="Assumes the template sink is reachable.",
package_ecosystem="npm",
manifest_path="package-lock.json",
fixed_version="4.17.21",
cwe=None,
advisory_cvss=7.2,
technical_analysis=None,
fix_effort="low",
reachability="vulnerable_symbol_used",
reachability_evidence="src/render.ts:14 calls `_.template()`.",
)
assert result["success"] is True
report = report_state.vulnerability_reports[0]
assert report["dependency_metadata"]["reachability"] == "vulnerable_symbol_used"
assert (
report["dependency_metadata"]["reachability_evidence"]
== "src/render.ts:14 calls `_.template()`."
)
assert "**Usage analysis:**" in report["evidence"]
assert "not a proof of exploitability or of safety" in report["evidence"]
# The level must never influence the rating — that stays advisory_cvss only.
assert report["severity"] == "high"
async def test_dependency_report_rejects_reachability_without_evidence(
report_state: ReportState,
) -> None:
result = await _do_create_dependency(
title="CVE-2024-0001 in sample 1.0.0",
description="Published advisory affects the pinned version.",
target="repo/package.json",
cve="CVE-2024-0001",
package_name="sample",
installed_version="1.0.0",
impact="Impact.",
remediation_steps="Upgrade.",
assumptions="Assumptions.",
package_ecosystem="npm",
manifest_path="package-lock.json",
fixed_version="1.0.1",
cwe=None,
advisory_cvss=5.0,
technical_analysis=None,
fix_effort="low",
reachability="not_imported",
)
assert result["success"] is False
assert any("reachability_evidence is required" in e for e in result["errors"])
assert not report_state.vulnerability_reports
async def test_dependency_report_rejects_unknown_reachability_level(
report_state: ReportState,
) -> None:
result = await _do_create_dependency(
title="CVE-2024-0001 in sample 1.0.0",
description="Published advisory affects the pinned version.",
target="repo/package.json",
cve="CVE-2024-0001",
package_name="sample",
installed_version="1.0.0",
impact="Impact.",
remediation_steps="Upgrade.",
assumptions="Assumptions.",
package_ecosystem="npm",
manifest_path="package-lock.json",
fixed_version="1.0.1",
cwe=None,
advisory_cvss=5.0,
technical_analysis=None,
fix_effort="low",
reachability="not_exploitable",
reachability_evidence="vibes",
)
assert result["success"] is False
assert any("Invalid reachability" in e for e in result["errors"])
assert not report_state.vulnerability_reports
async def test_dependency_report_omits_unknown_reachability(report_state: ReportState) -> None:
result = await _do_create_dependency(
title="CVE-2024-0001 in sample 1.0.0",
description="Published advisory affects the pinned version.",
target="repo/package.json",
cve="CVE-2024-0001",
package_name="sample",
installed_version="1.0.0",
impact="Impact.",
remediation_steps="Upgrade.",
assumptions="Analysis was inconclusive.",
package_ecosystem="npm",
manifest_path="package-lock.json",
fixed_version="1.0.1",
cwe=None,
advisory_cvss=5.0,
technical_analysis=None,
fix_effort="low",
)
assert result["success"] is True
metadata = report_state.vulnerability_reports[0]["dependency_metadata"]
assert "reachability" not in metadata
assert "reachability_evidence" not in metadata
async def test_dependency_report_requires_advisory_cvss(report_state: ReportState) -> None:
result = await _do_create_dependency(
title="CVE-2024-0001 in sample 1.0.0",
@@ -204,6 +390,7 @@ async def test_dependency_report_requires_advisory_cvss(report_state: ReportStat
remediation_steps="Upgrade to 1.0.1.",
assumptions="Assumes the package ships in deployed builds.",
package_ecosystem="npm",
manifest_path="package-lock.json",
fixed_version="1.0.1",
cwe=None,
advisory_cvss=None,
@@ -259,6 +446,7 @@ async def test_dependency_report_dedupe_candidate_includes_dependency_metadata(
remediation_steps="Upgrade to 1.0.1.",
assumptions="Assumes the package is included in deployed builds.",
package_ecosystem="npm",
manifest_path="package-lock.json",
fixed_version="1.0.1",
cwe=None,
advisory_cvss=0.0,
@@ -276,6 +464,7 @@ async def test_dependency_report_dedupe_candidate_includes_dependency_metadata(
"package_name": "sample",
"installed_version": "1.0.0",
"package_ecosystem": "npm",
"manifest_path": "package-lock.json",
"fixed_version": "1.0.1",
},
"technical_analysis": None,
@@ -294,6 +483,7 @@ async def test_dependency_report_rejects_bad_cve(report_state: ReportState) -> N
remediation_steps="r",
assumptions="a",
package_ecosystem="npm",
manifest_path="package-lock.json",
fixed_version=None,
cwe=None,
advisory_cvss=None,
@@ -316,6 +506,7 @@ async def test_dependency_report_requires_ecosystem(report_state: ReportState) -
remediation_steps="Upgrade to 1.0.1.",
assumptions="Assumes the package is included in deployed builds.",
package_ecosystem="",
manifest_path="package-lock.json",
fixed_version="1.0.1",
cwe=None,
advisory_cvss=0.0,
@@ -328,6 +519,62 @@ async def test_dependency_report_requires_ecosystem(report_state: ReportState) -
assert not report_state.vulnerability_reports
async def test_dependency_report_requires_manifest_path(report_state: ReportState) -> None:
result = await _do_create_dependency(
title="CVE-2024-0001 in sample 1.0.0",
description="Published advisory affects the pinned version.",
target="repo/package.json",
cve="CVE-2024-0001",
package_name="sample",
installed_version="1.0.0",
impact="Low-impact dependency advisory.",
remediation_steps="Upgrade to 1.0.1.",
assumptions="Assumes the package is included in deployed builds.",
package_ecosystem="npm",
manifest_path=None,
fixed_version="1.0.1",
cwe=None,
advisory_cvss=5.0,
technical_analysis=None,
fix_effort="low",
)
assert result["success"] is False
assert any("manifest_path is required" in error for error in result["errors"])
assert not report_state.vulnerability_reports
@pytest.mark.parametrize(
"bad_path",
["/etc/passwd", "..\\pom.xml", "services/../pom.xml", "./package.json", "C:/repo/pom.xml"],
)
async def test_dependency_report_rejects_unsafe_manifest_path(
report_state: ReportState, bad_path: str
) -> None:
result = await _do_create_dependency(
title="CVE-2024-0001 in sample 1.0.0",
description="Published advisory affects the pinned version.",
target="repo/package.json",
cve="CVE-2024-0001",
package_name="sample",
installed_version="1.0.0",
impact="Low-impact dependency advisory.",
remediation_steps="Upgrade to 1.0.1.",
assumptions="Assumes the package is included in deployed builds.",
package_ecosystem="npm",
manifest_path=bad_path,
fixed_version="1.0.1",
cwe=None,
advisory_cvss=5.0,
technical_analysis=None,
fix_effort="low",
)
assert result["success"] is False
assert any("manifest_path" in error for error in result["errors"])
assert not report_state.vulnerability_reports
def test_dedupe_comparison_preserves_cve_identity() -> None:
cleaned = _prepare_report_for_comparison(
{
@@ -406,6 +653,72 @@ async def test_dependency_dedupe_rejects_same_cve_package_identity() -> None:
assert result["confidence"] == 1.0
async def test_dependency_dedupe_keeps_findings_from_distinct_manifests() -> None:
existing = [
{
"id": "vuln-0001",
"title": "CVE-2024-0001 in sample",
"cve": "CVE-2024-0001",
"dependency_metadata": {
"package_name": "sample",
"installed_version": "1.0.0",
"package_ecosystem": "npm",
"manifest_path": "services/api/package-lock.json",
},
}
]
candidate = {
"title": "CVE-2024-0001 in sample (web)",
"description": "Same advisory observed in a second workspace.",
"target": "repo/package.json",
"cve": "CVE-2024-0001",
"dependency_metadata": {
"package_name": "sample",
"installed_version": "1.0.0",
"package_ecosystem": "npm",
"manifest_path": "services/web/package-lock.json",
},
}
result = await check_duplicate(candidate, existing)
assert result["is_duplicate"] is False
assert result["confidence"] == 1.0
async def test_dependency_dedupe_rejects_same_manifest_identity() -> None:
existing = [
{
"id": "vuln-0001",
"title": "CVE-2024-0001 in sample",
"cve": "CVE-2024-0001",
"dependency_metadata": {
"package_name": "sample",
"installed_version": "1.0.0",
"package_ecosystem": "npm",
"manifest_path": "services/api/package-lock.json",
},
}
]
candidate = {
"title": "CVE-2024-0001 in sample re-reported",
"description": "Same advisory, same manifest.",
"target": "repo/package.json",
"cve": "CVE-2024-0001",
"dependency_metadata": {
"package_name": "sample",
"installed_version": "1.0.0",
"package_ecosystem": "npm",
"manifest_path": "services/api/package-lock.json",
},
}
result = await check_duplicate(candidate, existing)
assert result["is_duplicate"] is True
assert result["duplicate_id"] == "vuln-0001"
async def test_dependency_dedupe_detects_legacy_same_cve_package() -> None:
existing = [
{
@@ -559,6 +872,8 @@ def test_vuln_tool_exposes_new_params() -> None:
dep_props = create_dependency_report.params_json_schema["properties"]
for field in ("package_name", "installed_version", "cve", "advisory_cvss"):
assert field in dep_props
for field in ("reachability", "reachability_evidence", "manifest_path"):
assert field in dep_props
dep_required = create_dependency_report.params_json_schema["required"]
assert "package_ecosystem" in dep_required
assert "advisory_cvss" in dep_required
+173
View File
@@ -0,0 +1,173 @@
"""Tests for the model-stream idle watchdog.
A turn that streams a few tokens and then goes silent is not covered by the
request timeout: the read timeout resets on every byte, keepalives included.
The watchdog bounds the gap between events so the turn fails and can be
retried instead of parking the agent forever.
"""
from __future__ import annotations
import asyncio
import json
import threading
import time
from http.server import BaseHTTPRequestHandler, HTTPServer
from typing import TYPE_CHECKING, Any
import pytest
from agents.model_settings import ModelSettings
from agents.models.interface import Model, ModelTracing
from agents.models.openai_chatcompletions import OpenAIChatCompletionsModel
from openai import AsyncOpenAI
from strix.config import loader
from strix.config.loader import load_settings
from strix.config.models import StrixProvider, _TurnGuardModel, _with_idle_timeout
if TYPE_CHECKING:
from collections.abc import AsyncIterator, Iterator
_STALL_SECONDS = 30.0
def _chunk(text: str) -> bytes:
payload = {
"id": "chatcmpl-1",
"object": "chat.completion.chunk",
"created": 0,
"model": "gw-model",
"choices": [{"index": 0, "delta": {"content": text}, "finish_reason": None}],
}
return b"data: " + json.dumps(payload).encode() + b"\n\n"
class _StallingHandler(BaseHTTPRequestHandler):
"""Streams a couple of tokens, then stops producing anything."""
stop = threading.Event()
def log_message(self, *args: Any) -> None:
pass
def do_POST(self) -> None:
length = int(self.headers.get("Content-Length", 0))
self.rfile.read(length)
self.send_response(200)
self.send_header("Content-Type", "text/event-stream")
self.end_headers()
self.wfile.write(_chunk("Now"))
self.wfile.write(_chunk(" spawning"))
self.wfile.flush()
self.stop.wait(_STALL_SECONDS)
@pytest.fixture
def stalling_gateway() -> Iterator[str]:
_StallingHandler.stop.clear()
server = HTTPServer(("127.0.0.1", 0), _StallingHandler)
thread = threading.Thread(target=server.serve_forever, daemon=True)
thread.start()
try:
yield f"http://127.0.0.1:{server.server_address[1]}/v1"
finally:
_StallingHandler.stop.set()
server.shutdown()
server.server_close()
def _stream(base_url: str, *, idle_timeout: float) -> AsyncIterator[Any]:
client = AsyncOpenAI(api_key="tok", base_url=base_url, max_retries=0, timeout=_STALL_SECONDS)
inner: Model = OpenAIChatCompletionsModel(model="gw-model", openai_client=client)
guarded = _TurnGuardModel(inner, stream_idle_timeout=idle_timeout)
return guarded.stream_response(
None,
"go",
ModelSettings(),
[],
None,
[],
ModelTracing.DISABLED,
previous_response_id=None,
conversation_id=None,
prompt=None,
)
async def _drain(base_url: str, *, idle_timeout: float) -> list[Any]:
return [event async for event in _stream(base_url, idle_timeout=idle_timeout)]
@pytest.mark.asyncio
async def test_stalled_stream_hangs_without_the_watchdog(stalling_gateway: str) -> None:
# Repro: tokens arrive, then nothing. Un-watched, the turn just sits there;
# the request timeout is far away and would reset on any keepalive byte.
with pytest.raises(TimeoutError):
await asyncio.wait_for(_drain(stalling_gateway, idle_timeout=0), timeout=2)
@pytest.mark.asyncio
async def test_stalled_stream_is_abandoned_by_the_watchdog(stalling_gateway: str) -> None:
started = time.monotonic()
with pytest.raises(TimeoutError, match="produced no event"):
await _drain(stalling_gateway, idle_timeout=1)
assert time.monotonic() - started < _STALL_SECONDS
@pytest.mark.asyncio
async def test_events_keep_flowing_while_the_stream_is_alive() -> None:
async def _live() -> AsyncIterator[Any]:
for i in range(5):
await asyncio.sleep(0.05)
yield f"event-{i}"
seen: list[Any] = [event async for event in _with_idle_timeout(_live(), 1.0)]
assert seen == [f"event-{i}" for i in range(5)]
@pytest.fixture
def _reset_settings(monkeypatch: pytest.MonkeyPatch) -> Iterator[None]:
for key in ("STRIX_LLM", "LLM_DISABLE_STREAMING", "LLM_STREAM_IDLE_TIMEOUT"):
monkeypatch.delenv(key, raising=False)
monkeypatch.setattr(loader, "_cached", None)
monkeypatch.setattr(loader, "_override", None)
yield
class _DummyModel(Model):
async def get_response(self, *args: Any, **kwargs: Any) -> Any:
raise NotImplementedError
def stream_response(self, *args: Any, **kwargs: Any) -> Any:
raise NotImplementedError
def test_idle_timeout_is_configurable(
monkeypatch: pytest.MonkeyPatch, _reset_settings: None
) -> None:
monkeypatch.setattr("strix.config.models.MultiProvider.get_model", lambda *_: _DummyModel())
monkeypatch.setenv("LLM_STREAM_IDLE_TIMEOUT", "45")
load_settings()
model = StrixProvider().get_model("openai/gpt-4o-mini")
assert isinstance(model, _TurnGuardModel)
assert model._stream_idle_timeout == 45
def test_idle_timeout_is_off_without_streaming(
monkeypatch: pytest.MonkeyPatch, _reset_settings: None
) -> None:
# LLM_DISABLE_STREAMING turns the whole request into one event, so an idle
# gap would just be the request duration — the request timeout bounds that.
monkeypatch.setattr("strix.config.models.MultiProvider.get_model", lambda *_: _DummyModel())
monkeypatch.setenv("LLM_STREAM_IDLE_TIMEOUT", "45")
monkeypatch.setenv("LLM_DISABLE_STREAMING", "true")
load_settings()
model = StrixProvider().get_model("openai/gpt-4o-mini")
assert isinstance(model, _TurnGuardModel)
assert model._stream_idle_timeout == 0
+249
View File
@@ -0,0 +1,249 @@
"""Tests for tool-call id uniqueness.
Providers that number tool calls per turn (``exec_command:0``, ``:1``, ...)
restart the counter on every turn, so the same id eventually appears twice in
one conversation. Strict providers then reject the whole request, and because
the history is replayed on every retry the agent can never recover. A gateway
that validates id uniqueness the way those providers do proves both the
failure and the fix.
"""
from __future__ import annotations
import json
import threading
from http.server import BaseHTTPRequestHandler, HTTPServer
from typing import TYPE_CHECKING, Any
import pytest
from agents import Agent, Runner, function_tool
from agents.models.interface import Model, ModelProvider
from agents.models.openai_chatcompletions import OpenAIChatCompletionsModel
from agents.run import RunConfig
from openai import AsyncOpenAI
from openai.types.responses import ResponseFunctionToolCall
from strix.config.models import _NonStreamingModel, _TurnGuardModel
from strix.config.tool_call_ids import TurnCallIdRewriter, dedupe_history_call_ids
if TYPE_CHECKING:
from collections.abc import Iterator
def _tool_call_completion(call_id: str, n: int = 1) -> dict[str, Any]:
return {
"id": "chatcmpl-1",
"object": "chat.completion",
"created": 0,
"model": "gw-model",
"choices": [
{
"index": 0,
"finish_reason": "tool_calls",
"message": {
"role": "assistant",
"content": None,
"tool_calls": [
{
"id": call_id,
"type": "function",
"function": {"name": "do_thing", "arguments": json.dumps({"n": n})},
}
],
},
}
],
"usage": {"prompt_tokens": 5, "completion_tokens": 2, "total_tokens": 7},
}
def _text_completion(text: str) -> dict[str, Any]:
return {
"id": "chatcmpl-2",
"object": "chat.completion",
"created": 0,
"model": "gw-model",
"choices": [
{"index": 0, "finish_reason": "stop", "message": {"role": "assistant", "content": text}}
],
"usage": {"prompt_tokens": 5, "completion_tokens": 3, "total_tokens": 8},
}
_REQUESTS: list[list[dict[str, Any]]] = []
def _assistant_call_ids(messages: list[dict[str, Any]]) -> list[str]:
return [str(call.get("id")) for message in messages for call in message.get("tool_calls") or []]
def _tool_results(messages: list[dict[str, Any]]) -> list[str]:
return [str(m.get("content")) for m in messages if m.get("role") == "tool"]
class _StrictHandler(BaseHTTPRequestHandler):
"""Gateway that rejects a history reusing a tool-call id, like strict providers do."""
def log_message(self, *args: Any) -> None:
pass
def do_POST(self) -> None:
length = int(self.headers.get("Content-Length", 0))
body = json.loads(self.rfile.read(length) or b"{}")
messages = body.get("messages", [])
_REQUESTS.append(messages)
call_ids = _assistant_call_ids(messages)
if len(call_ids) != len(set(call_ids)):
self._respond(
400,
{
"error": {
"message": (
"tool messages need a resolvable tool name: carry `tool`/`name`, "
"or match a preceding assistant tool_call by order"
)
}
},
)
return
turn = len(_REQUESTS)
if turn <= 2:
# The provider restarts its per-turn counter, so both turns say ":0".
self._respond(200, _tool_call_completion("exec_command:0", n=turn))
else:
self._respond(200, _text_completion("all done"))
def _respond(self, status: int, payload: dict[str, Any]) -> None:
encoded = json.dumps(payload).encode()
self.send_response(status)
self.send_header("Content-Type", "application/json")
self.send_header("Content-Length", str(len(encoded)))
self.end_headers()
self.wfile.write(encoded)
@pytest.fixture
def strict_gateway() -> Iterator[str]:
_REQUESTS.clear()
server = HTTPServer(("127.0.0.1", 0), _StrictHandler)
thread = threading.Thread(target=server.serve_forever, daemon=True)
thread.start()
try:
yield f"http://127.0.0.1:{server.server_address[1]}/v1"
finally:
server.shutdown()
server.server_close()
def _model(base_url: str) -> Model:
# The gateway answers plain JSON, so the run loop's streamed turns are
# served non-streamed; the ids on the wire are the same either way.
client = AsyncOpenAI(api_key="tok", base_url=base_url, max_retries=0)
return _NonStreamingModel(OpenAIChatCompletionsModel(model="gw-model", openai_client=client))
async def _run_agent(base_url: str, *, wrap: bool) -> Any:
@function_tool
def do_thing(n: int) -> str:
return f"did {n}"
class _Provider(ModelProvider):
def get_model(self, model_name: str | None) -> Model: # noqa: ARG002
model = _model(base_url)
return _TurnGuardModel(model) if wrap else model
agent = Agent(name="t", instructions="use the tool", tools=[do_thing], model="gw-model")
result = Runner.run_streamed(
agent, input="please", run_config=RunConfig(model_provider=_Provider())
)
async for _ in result.stream_events():
pass
return result
@pytest.mark.asyncio
async def test_recycled_call_id_erases_a_turn_without_the_wrapper(strict_gateway: str) -> None:
# Repro: two turns run a tool and both are labelled ``exec_command:0``, so
# the colliding call and its result are dropped as duplicates. The agent
# ends the run having silently lost a turn of its own work — and a provider
# that does not drop them instead rejects the malformed history outright.
result = await _run_agent(strict_gateway, wrap=False)
assert result.final_output == "all done"
assert _assistant_call_ids(_REQUESTS[-1]) == ["exec_command:0"]
assert _tool_results(_REQUESTS[-1]) == ["did 2"]
@pytest.mark.asyncio
async def test_recycled_call_id_is_rewritten_so_no_turn_is_lost(strict_gateway: str) -> None:
result = await _run_agent(strict_gateway, wrap=True)
assert result.final_output == "all done"
call_ids = _assistant_call_ids(_REQUESTS[-1])
assert len(call_ids) == len(set(call_ids)) == 2
assert call_ids[0] == "exec_command:0"
assert call_ids[1].startswith("call_")
assert _tool_results(_REQUESTS[-1]) == ["did 1", "did 2"]
def test_history_dedupe_keeps_outputs_paired_with_their_call() -> None:
items = [
{"type": "function_call", "call_id": "exec_command:0", "name": "a", "arguments": "{}"},
{"type": "function_call_output", "call_id": "exec_command:0", "output": "first"},
{"type": "function_call", "call_id": "exec_command:0", "name": "b", "arguments": "{}"},
{"type": "function_call_output", "call_id": "exec_command:0", "output": "second"},
]
rebuilt, changed = dedupe_history_call_ids(items)
assert changed
ids = [item["call_id"] for item in rebuilt]
assert ids[0] == ids[1] == "exec_command:0"
assert ids[2] == ids[3] != "exec_command:0"
assert rebuilt[3]["output"] == "second"
def test_history_dedupe_pairs_parallel_calls_by_order() -> None:
items = [
{"type": "function_call", "call_id": "dup", "name": "a", "arguments": "{}"},
{"type": "function_call", "call_id": "dup", "name": "b", "arguments": "{}"},
{"type": "function_call_output", "call_id": "dup", "output": "for-a"},
{"type": "function_call_output", "call_id": "dup", "output": "for-b"},
]
rebuilt, changed = dedupe_history_call_ids(items)
assert changed
assert rebuilt[0]["call_id"] == rebuilt[2]["call_id"] == "dup"
assert rebuilt[1]["call_id"] == rebuilt[3]["call_id"]
assert rebuilt[1]["call_id"] != "dup"
def test_history_dedupe_leaves_unique_ids_alone() -> None:
items = [
{"type": "function_call", "call_id": "call_a", "name": "a", "arguments": "{}"},
{"type": "function_call_output", "call_id": "call_a", "output": "x"},
{"type": "function_call", "call_id": "call_b", "name": "b", "arguments": "{}"},
]
rebuilt, changed = dedupe_history_call_ids(items)
assert not changed
assert rebuilt == items
def test_turn_rewriter_is_stable_across_repeated_sightings() -> None:
history = [{"type": "function_call", "call_id": "exec_command:0", "name": "a"}]
rewriter = TurnCallIdRewriter(history)
call = ResponseFunctionToolCall(
call_id="exec_command:0", name="a", arguments="{}", type="function_call"
)
first = rewriter.rewrite_item(call)
second = rewriter.rewrite_item(first)
assert first.call_id != "exec_command:0"
assert second.call_id == first.call_id
+189
View File
@@ -0,0 +1,189 @@
"""Tests for the per-response tool-call cap.
A degenerate generation can emit hundreds of tool calls in one assistant
response a wait/poll loop the model writes out ahead of time. The run loop
honours every one of them, so the agent stops reacting for hours. The cap
keeps the first N calls of a response and drops the tail.
"""
from __future__ import annotations
import json
import threading
from http.server import BaseHTTPRequestHandler, HTTPServer
from typing import TYPE_CHECKING, Any
import pytest
from agents import Agent, Runner, function_tool
from agents.models.interface import Model, ModelProvider
from agents.models.openai_chatcompletions import OpenAIChatCompletionsModel
from agents.run import RunConfig
from openai import AsyncOpenAI
from strix.config import loader
from strix.config.loader import load_settings
from strix.config.models import StrixProvider, _NonStreamingModel, _TurnGuardModel
if TYPE_CHECKING:
from collections.abc import Iterator
_RUNAWAY_CALLS = 200
_CAP = 32
def _runaway_completion() -> dict[str, Any]:
return {
"id": "chatcmpl-1",
"object": "chat.completion",
"created": 0,
"model": "gw-model",
"choices": [
{
"index": 0,
"finish_reason": "tool_calls",
"message": {
"role": "assistant",
"content": None,
"tool_calls": [
{
"id": f"call_{i}",
"type": "function",
"function": {"name": "wait_for_message", "arguments": "{}"},
}
for i in range(_RUNAWAY_CALLS)
],
},
}
],
"usage": {"prompt_tokens": 5, "completion_tokens": 2, "total_tokens": 7},
}
def _text_completion() -> dict[str, Any]:
return {
"id": "chatcmpl-2",
"object": "chat.completion",
"created": 0,
"model": "gw-model",
"choices": [
{
"index": 0,
"finish_reason": "stop",
"message": {"role": "assistant", "content": "done"},
}
],
"usage": {"prompt_tokens": 5, "completion_tokens": 3, "total_tokens": 8},
}
_TURNS: list[int] = []
class _RunawayHandler(BaseHTTPRequestHandler):
"""First turn queues a huge poll loop; the next turn ends the run."""
def log_message(self, *args: Any) -> None:
pass
def do_POST(self) -> None:
length = int(self.headers.get("Content-Length", 0))
self.rfile.read(length)
_TURNS.append(1)
payload = _runaway_completion() if len(_TURNS) == 1 else _text_completion()
encoded = json.dumps(payload).encode()
self.send_response(200)
self.send_header("Content-Type", "application/json")
self.send_header("Content-Length", str(len(encoded)))
self.end_headers()
self.wfile.write(encoded)
@pytest.fixture
def runaway_gateway() -> Iterator[str]:
_TURNS.clear()
server = HTTPServer(("127.0.0.1", 0), _RunawayHandler)
thread = threading.Thread(target=server.serve_forever, daemon=True)
thread.start()
try:
yield f"http://127.0.0.1:{server.server_address[1]}/v1"
finally:
server.shutdown()
server.server_close()
def _model(base_url: str) -> Model:
client = AsyncOpenAI(api_key="tok", base_url=base_url, max_retries=0)
return _NonStreamingModel(OpenAIChatCompletionsModel(model="gw-model", openai_client=client))
async def _run_agent(base_url: str, *, cap: int) -> list[int]:
executed: list[int] = []
@function_tool
def wait_for_message() -> str:
executed.append(1)
return "nothing new"
class _Provider(ModelProvider):
def get_model(self, model_name: str | None) -> Model: # noqa: ARG002
return _TurnGuardModel(_model(base_url), max_tool_calls_per_turn=cap)
agent = Agent(name="t", instructions="orchestrate", tools=[wait_for_message], model="gw-model")
result = Runner.run_streamed(
agent, input="go", run_config=RunConfig(model_provider=_Provider())
)
async for _ in result.stream_events():
pass
assert result.final_output == "done"
return executed
@pytest.mark.asyncio
async def test_runaway_response_runs_every_queued_call_when_uncapped(runaway_gateway: str) -> None:
# Repro: one response queues 200 calls and the run loop honours all of them.
executed = await _run_agent(runaway_gateway, cap=0)
assert len(executed) == _RUNAWAY_CALLS
@pytest.mark.asyncio
async def test_runaway_response_is_capped(runaway_gateway: str) -> None:
executed = await _run_agent(runaway_gateway, cap=_CAP)
assert len(executed) == _CAP
@pytest.mark.asyncio
async def test_response_below_the_cap_is_untouched(runaway_gateway: str) -> None:
executed = await _run_agent(runaway_gateway, cap=_RUNAWAY_CALLS + 1)
assert len(executed) == _RUNAWAY_CALLS
@pytest.fixture
def _reset_settings(monkeypatch: pytest.MonkeyPatch) -> Iterator[None]:
for key in ("STRIX_LLM", "LLM_DISABLE_STREAMING", "LLM_MAX_TOOL_CALLS_PER_TURN"):
monkeypatch.delenv(key, raising=False)
monkeypatch.setattr(loader, "_cached", None)
monkeypatch.setattr(loader, "_override", None)
yield
class _DummyModel(Model):
async def get_response(self, *args: Any, **kwargs: Any) -> Any:
raise NotImplementedError
def stream_response(self, *args: Any, **kwargs: Any) -> Any:
raise NotImplementedError
def test_cap_is_configurable(monkeypatch: pytest.MonkeyPatch, _reset_settings: None) -> None:
monkeypatch.setattr("strix.config.models.MultiProvider.get_model", lambda *_: _DummyModel())
monkeypatch.setenv("LLM_MAX_TOOL_CALLS_PER_TURN", "7")
load_settings()
model = StrixProvider().get_model("openai/gpt-4o-mini")
assert isinstance(model, _TurnGuardModel)
assert model._max_tool_calls_per_turn == 7
+126
View File
@@ -0,0 +1,126 @@
"""Tests for collapsing repeated waits queued inside one model turn.
An orchestrator that writes out its whole poll loop ahead of time queues
many ``wait_for_agents`` calls in a single response. Each one parks for its
full timeout, so the agent stops reacting for hours while its children run
unsupervised. Only the first wait of a turn parks; the rest return at once.
"""
from __future__ import annotations
import asyncio
import json
import time
from typing import TYPE_CHECKING, Any, cast
import pytest
from agents import RunContextWrapper
from agents.tool_context import ToolContext
from strix.core.agents import AgentCoordinator
from strix.core.hooks import LLM_TURN_KEY, ReportUsageHooks
from strix.tools.agents_graph.tools import wait_for_agents
if TYPE_CHECKING:
from collections.abc import Iterator
_WAIT_SECONDS = 2
@pytest.fixture
def _fast_wait(monkeypatch: pytest.MonkeyPatch) -> Iterator[None]:
# The real ceiling is 300s per wait; the shape of the bug is the same.
monkeypatch.setattr(
"strix.tools.agents_graph.tools._WAIT_DEFAULT_TIMEOUT_S", _WAIT_SECONDS, raising=True
)
yield
async def _context() -> dict[str, Any]:
coordinator = AgentCoordinator()
await coordinator.register("root", "strix", parent_id=None)
return {"agent_id": "root", "coordinator": coordinator}
async def _wait(inner: dict[str, Any]) -> dict[str, Any]:
ctx = ToolContext(
context=inner,
tool_name="wait_for_agents",
tool_call_id="call-1",
tool_arguments="{}",
)
raw: str = await wait_for_agents.on_invoke_tool(
ctx, json.dumps({"reason": "waiting for wave 1", "timeout_seconds": _WAIT_SECONDS})
)
return cast("dict[str, Any]", json.loads(raw))
@pytest.mark.asyncio
async def test_waits_queued_in_one_turn_each_park_without_the_guard(_fast_wait: None) -> None:
# Repro: no turn marker in context (as before the fix) — every queued wait
# parks for its full timeout, so N waits cost N x timeout.
inner = await _context()
started = time.monotonic()
outcomes = [(await _wait(inner))["wait_outcome"] for _ in range(3)]
elapsed = time.monotonic() - started
assert outcomes == ["timeout", "timeout", "timeout"]
assert elapsed >= 3 * _WAIT_SECONDS
@pytest.mark.asyncio
async def test_repeated_waits_in_one_turn_are_collapsed(_fast_wait: None) -> None:
inner = await _context()
inner[LLM_TURN_KEY] = 1
started = time.monotonic()
outcomes = [(await _wait(inner))["wait_outcome"] for _ in range(3)]
elapsed = time.monotonic() - started
assert outcomes == ["timeout", "already_waited", "already_waited"]
assert elapsed < 2 * _WAIT_SECONDS
@pytest.mark.asyncio
async def test_a_wait_in_the_next_turn_still_parks(_fast_wait: None) -> None:
inner = await _context()
inner[LLM_TURN_KEY] = 1
assert (await _wait(inner))["wait_outcome"] == "timeout"
assert (await _wait(inner))["wait_outcome"] == "already_waited"
inner[LLM_TURN_KEY] = 2
assert (await _wait(inner))["wait_outcome"] == "timeout"
@pytest.mark.asyncio
async def test_each_model_turn_bumps_the_turn_marker() -> None:
hooks = ReportUsageHooks(model="gw-model")
context: RunContextWrapper[dict[str, Any]] = RunContextWrapper(context={})
agent = cast("Any", None)
await hooks.on_llm_start(context, agent, None, [])
await hooks.on_llm_start(context, agent, None, [])
assert context.context[LLM_TURN_KEY] == 2
@pytest.mark.asyncio
async def test_a_collapsed_wait_still_reports_arriving_messages(_fast_wait: None) -> None:
inner = await _context()
inner[LLM_TURN_KEY] = 1
coordinator = cast("AgentCoordinator", inner["coordinator"])
async def _send() -> None:
await asyncio.sleep(0.1)
await coordinator.send("root", {"type": "information", "content": "child done"})
task = asyncio.create_task(_send())
first = await _wait(inner)
await task
assert first["wait_outcome"] == "message_arrived"
assert (await _wait(inner))["wait_outcome"] == "already_waited"
Generated
+54 -51
View File
@@ -469,52 +469,55 @@ wheels = [
[[package]]
name = "cryptography"
version = "50.0.0"
version = "48.0.1"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "cffi", marker = "platform_python_implementation != 'PyPy'" },
]
sdist = { url = "https://files.pythonhosted.org/packages/de/41/6cbdcf9142d00fe82836fbb51e503e58088575cf7a0fe1dbff6695bf0840/cryptography-50.0.0.tar.gz", hash = "sha256:eeac2acb5a20ed25e0ad6d1df9891a520b78b404266b6d11778f25d5d691a6c9", size = 880201, upload-time = "2026-07-31T14:25:10.11Z" }
sdist = { url = "https://files.pythonhosted.org/packages/12/45/870e7f4bef50e5f53b9f51d4428aee5290eedf58ba443f16b1ebb7ab8e66/cryptography-48.0.1.tar.gz", hash = "sha256:266f4ee051abb2f725b74ef8072b521ce1feacf685a3364fa6a6b45548db791a", size = 832989, upload-time = "2026-06-09T22:32:31.8Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/c5/5c/59086b4aac5e879d38ddbcf74e4be7ade89cebc3eb199a55da998c3bb46a/cryptography-50.0.0-cp311-abi3-macosx_11_0_arm64.whl", hash = "sha256:031e2d5dd4bb9caa3ca9c82e5a197fd8ae680232cee62603d1a813f3f07e3d03", size = 4001252, upload-time = "2026-07-31T14:23:33.331Z" },
{ url = "https://files.pythonhosted.org/packages/57/ef/8f2df13c7216bcad3e1c74e07f6e193d93e998e114f524a53877c9af27ad/cryptography-50.0.0-cp311-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:fd9192b7b70c573d7f214eb1ae35e00d359f6f5e4b27c7e21e30de1fc6204645", size = 4719554, upload-time = "2026-07-31T14:23:35.611Z" },
{ url = "https://files.pythonhosted.org/packages/d9/41/029086c34d91052fc3b88bcc8056f709a7c915c7a23b235a54eb800b1c97/cryptography-50.0.0-cp311-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:06a32a980526a6ab9a4b9bf8f7385800791e2bb960903cb6b530e4817509a3b7", size = 4702130, upload-time = "2026-07-31T14:23:37.635Z" },
{ url = "https://files.pythonhosted.org/packages/7d/ff/b6ce0954962e7f7b969f850a883744197bb3910bdfd7b6da162eab7d9f68/cryptography-50.0.0-cp311-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:a1b30560f2acc95aa8b2e06e716a13dbfc97314747b80d9707e307f77b40d6b3", size = 4725244, upload-time = "2026-07-31T14:23:39.471Z" },
{ url = "https://files.pythonhosted.org/packages/06/1e/63a1027cb7fec360a182208e1b7767d5aa1fe57be3d6aa856e69a321edc0/cryptography-50.0.0-cp311-abi3-manylinux_2_28_ppc64le.whl", hash = "sha256:8d89f3976b10b4ce31118de72329025f70d2c6ead14a8217c5514dd2c6d5a78f", size = 5342265, upload-time = "2026-07-31T14:23:41.286Z" },
{ url = "https://files.pythonhosted.org/packages/6b/72/a1116d683a6d7ece94590013882515de087edf9ef0e6292aae615a44df73/cryptography-50.0.0-cp311-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:b42a28c1844fd9de8f3f7d540e36b66f3a9c83fceac7170ebc7a6a19edd9dcae", size = 4734609, upload-time = "2026-07-31T14:23:43.139Z" },
{ url = "https://files.pythonhosted.org/packages/15/37/36a9c479bbe49acea2636c7fd3360d20f7b7e079c300352011c44850b181/cryptography-50.0.0-cp311-abi3-manylinux_2_31_armv7l.whl", hash = "sha256:900131fafd8aead39ac7dd3a7e833be754c17a95cfd91221636949fe4eb0aa8a", size = 4356517, upload-time = "2026-07-31T14:23:44.939Z" },
{ url = "https://files.pythonhosted.org/packages/32/98/8a151d64367204cbc63ec65d37502f1d9c53cf4bfc6ec3c532614dbec60d/cryptography-50.0.0-cp311-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:07949c449a1abcf60d1ee6e88956d89404c7df3c8258f46589e912988e551987", size = 4724529, upload-time = "2026-07-31T14:23:46.93Z" },
{ url = "https://files.pythonhosted.org/packages/22/f6/ec13b470172126464a86bf54d2294a46d29837fc51ba3e45d4047946fb5e/cryptography-50.0.0-cp311-abi3-manylinux_2_34_ppc64le.whl", hash = "sha256:f89831ef99dd7dd169ab06d63a831adb9e20a87aac6d380266bbda5823349169", size = 5299852, upload-time = "2026-07-31T14:23:48.851Z" },
{ url = "https://files.pythonhosted.org/packages/da/3a/f05e32c99d440c9bb891ea0e36c9091891e36be5a9a87ab2ee6ea20729f6/cryptography-50.0.0-cp311-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:82148ec5bddac30b51a5b3c1945075f896fa022cb93f8e4a01e9f6ee95292c5f", size = 4734462, upload-time = "2026-07-31T14:23:50.861Z" },
{ url = "https://files.pythonhosted.org/packages/ca/dc/bd72b26be8953f80625f63151efd38eee71c76ca6cf591c08ff34615a79e/cryptography-50.0.0-cp311-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:1489e263a8048bb8b6a8bac662eb2d402ea5d2b7b4699b72f385f1e2772db105", size = 4852708, upload-time = "2026-07-31T14:23:52.715Z" },
{ url = "https://files.pythonhosted.org/packages/27/20/c930314a2ab476d15dec966ec87e2e9637bb02b06106b12c0396c57bb603/cryptography-50.0.0-cp311-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:7cec5b856506da6defb290f30c9ee687d5f5e8cb0bd3f6459dde43b0b4fa40ef", size = 5004179, upload-time = "2026-07-31T14:23:54.887Z" },
{ url = "https://files.pythonhosted.org/packages/32/2e/c9db68a0c4bfa28e310707527c0ee3a2bd254104d2e02e68f368e197aa4c/cryptography-50.0.0-cp311-abi3-win_amd64.whl", hash = "sha256:bd1c592e4d5974f0d08d4888e432157adba757c66da0246918e43677fafa2d30", size = 3840395, upload-time = "2026-07-31T14:23:56.677Z" },
{ url = "https://files.pythonhosted.org/packages/c3/fb/951032a3bf22a5697c83183fb6294a4843772947a70e616c57b3ff5f522e/cryptography-50.0.0-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:49e7d93abdbd2990caced757e5fade25302f719c3c8fb6e6fff2dde98999fc41", size = 3989258, upload-time = "2026-07-31T14:23:58.881Z" },
{ url = "https://files.pythonhosted.org/packages/d4/67/91eb047e69c5e845f2f14b8a2e4a1aab0f283cb885531e9e22c8adb176bc/cryptography-50.0.0-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:19736989797678c6af1e55cd49055cdbcb55d8f6b5583ac5335f933aba9101dc", size = 4700648, upload-time = "2026-07-31T14:24:00.702Z" },
{ url = "https://files.pythonhosted.org/packages/30/82/85f0f7425c856b9f96459411eb12e74ef72df9caf6f8f15bf23a33ff131f/cryptography-50.0.0-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:80b63928fa35083b33966ce1efb70e5b9607181e49dcd1c22c8c005e319f667f", size = 4682442, upload-time = "2026-07-31T14:24:02.538Z" },
{ url = "https://files.pythonhosted.org/packages/1a/28/b555a365adff1cca2fbe7b9e487d68a40de6bc67ff2cb587473eb43de0e7/cryptography-50.0.0-cp314-cp314t-manylinux_2_28_aarch64.whl", hash = "sha256:d58c3db7cd6eed54e6c06744db55456b65ebd7492ddeae9c1e93cfca7aa857d3", size = 4707596, upload-time = "2026-07-31T14:24:04.394Z" },
{ url = "https://files.pythonhosted.org/packages/72/d8/f52538140cc719df62a01cf87d1c7142318d235817109d6f4054d7c352d6/cryptography-50.0.0-cp314-cp314t-manylinux_2_28_ppc64le.whl", hash = "sha256:df2a58a472f332225671c35b0a830208b86d004f82baa8530fa3782c85646533", size = 5314552, upload-time = "2026-07-31T14:24:06.31Z" },
{ url = "https://files.pythonhosted.org/packages/38/14/6120e5bd7c5aa022ad15424ba4d5c5269d0d9448ed4d55e492ea91e3c1c4/cryptography-50.0.0-cp314-cp314t-manylinux_2_28_x86_64.whl", hash = "sha256:11b74db56cdbe3cdee6e3f6982ecb70334fa10dce99ed58bf7894aaaa3b2a037", size = 4717113, upload-time = "2026-07-31T14:24:08.349Z" },
{ url = "https://files.pythonhosted.org/packages/fa/71/190bf38c3ee2e0f8efc9860ae100c9df4169742eef274b91e7aa1cb133b9/cryptography-50.0.0-cp314-cp314t-manylinux_2_31_armv7l.whl", hash = "sha256:f59e38625469987d7ef6d495323c55e7db6c212eaf6112267e0d3b565a2e9c9f", size = 4338580, upload-time = "2026-07-31T14:24:10.227Z" },
{ url = "https://files.pythonhosted.org/packages/3a/63/504ccfbbe61fd8aa983f7f146399cdf034c72c2fc55f5b2dfdcdcdb20c99/cryptography-50.0.0-cp314-cp314t-manylinux_2_34_aarch64.whl", hash = "sha256:ecfed7367f965a0328cfbdd70da860f15441f002f613185668c6e6ebf5a0ac11", size = 4707038, upload-time = "2026-07-31T14:24:12.169Z" },
{ url = "https://files.pythonhosted.org/packages/01/77/2cf79bbfc4d12ca106437a6e170d6aaa01a373e93093118aaaef0e801bd4/cryptography-50.0.0-cp314-cp314t-manylinux_2_34_ppc64le.whl", hash = "sha256:9aa87839c383bdbab6ef865787a1fb877af8dd03464c4400322726feaaadfc6d", size = 5273110, upload-time = "2026-07-31T14:24:14.38Z" },
{ url = "https://files.pythonhosted.org/packages/e5/45/8aae2972c520145377ea3559a605a899bebe227bf070b33cdb445929a9b9/cryptography-50.0.0-cp314-cp314t-manylinux_2_34_x86_64.whl", hash = "sha256:6ba6a53445bd3cfa809ef3ef5f1589aa6ba08784a1d962bf47d0940e871dab1c", size = 4716439, upload-time = "2026-07-31T14:24:16.415Z" },
{ url = "https://files.pythonhosted.org/packages/7b/20/4fe50b619a48c2525cc46e2dbc1ac490708d704be5d467bdaac6dc955682/cryptography-50.0.0-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:3f5735ffe4996d28b809371756219f5354864902a3b9e7c0b9ee87041209fc9c", size = 4837383, upload-time = "2026-07-31T14:24:18.553Z" },
{ url = "https://files.pythonhosted.org/packages/92/91/3a31366e183343d3703f8995c095f5734676bd6938118047e50fcf279eb4/cryptography-50.0.0-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:1b4a266766514614f8aa60416e71f2fc6e575d36e7bdc90f644fadb2f4b75b95", size = 4985772, upload-time = "2026-07-31T14:24:20.385Z" },
{ url = "https://files.pythonhosted.org/packages/74/9a/02ffe35b2853d121689871eb5dce862092562b3a1ed5cc98f1aaed441506/cryptography-50.0.0-cp314-cp314t-win_amd64.whl", hash = "sha256:12b9c6996425c76ea6c457ace4f3073e715b8c545add07cd1a8f3a4f90691269", size = 3816291, upload-time = "2026-07-31T14:24:22.125Z" },
{ url = "https://files.pythonhosted.org/packages/03/37/73d005be173aff344af30e9fd2a576575cb2391a7101d9cd3842e1fa8cce/cryptography-50.0.0-cp39-abi3-macosx_11_0_arm64.whl", hash = "sha256:ccdc4a71a4dabae05de219404f9f4abc38e3b58422177ff93d0da05967dafa07", size = 4036009, upload-time = "2026-07-31T14:24:24.122Z" },
{ url = "https://files.pythonhosted.org/packages/ff/c6/7a6202a534e32103a285b7834a120869557fe198d51d7cfe59754c8bda9c/cryptography-50.0.0-cp39-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:910e1d2668e7de9648f2bcee30e180db2a6b15c30f887d7c4c93ddf96e3992e3", size = 4745252, upload-time = "2026-07-31T14:24:26.118Z" },
{ url = "https://files.pythonhosted.org/packages/85/4f/0fa8c2f4428198f15d9ff8d63400e27afbf94ce833f6108da1eb3753f945/cryptography-50.0.0-cp39-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:a91296cb61e8df6f86d0c19cc4068228da256bf59bf86049fbd821084565327f", size = 4728939, upload-time = "2026-07-31T14:24:27.994Z" },
{ url = "https://files.pythonhosted.org/packages/d1/63/54dd723490ba2dc09b299682c10b38db38f159728bcaae8c591b8af2f22d/cryptography-50.0.0-cp39-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:e722f16708d854fe924790e051061f6704a472c3bac347b6fd88033ea8dd0dc5", size = 4748483, upload-time = "2026-07-31T14:24:30.254Z" },
{ url = "https://files.pythonhosted.org/packages/1d/dd/7c77d26285cc7f6991efce64a0f5b4f9383bfa5dd8c5033003eaf7db4cdb/cryptography-50.0.0-cp39-abi3-manylinux_2_28_ppc64le.whl", hash = "sha256:d764dcf130c428ef66786f866dd750f53182bc608813489915e9fc106bb0c82f", size = 5367599, upload-time = "2026-07-31T14:24:32.457Z" },
{ url = "https://files.pythonhosted.org/packages/46/c9/f60aed34c013f317f92817b6c171c2d22a78270fa41109bd4b08af26b194/cryptography-50.0.0-cp39-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:105110f43a471dbd0060b9c9516cb8a6a79233631a04cc2ba16f28323ac6e025", size = 4762647, upload-time = "2026-07-31T14:24:34.599Z" },
{ url = "https://files.pythonhosted.org/packages/be/f3/f9a0173b139372c3a48ed98154b45cc6b9de17c789d5ab552e621c293609/cryptography-50.0.0-cp39-abi3-manylinux_2_31_armv7l.whl", hash = "sha256:828743d939e9629bc267b8e2d08d8bb67cd4319c771a33d4b18b22dd8fb7440a", size = 4385197, upload-time = "2026-07-31T14:24:36.647Z" },
{ url = "https://files.pythonhosted.org/packages/d8/36/83bb81f6e569bc38e1e4a7bc80f29b46bb9601920bc455fc8e888f5d5742/cryptography-50.0.0-cp39-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:2a8183b489dc1f7f80f135780fadc1108f14b31b8a40411c7a5b17425f65f28b", size = 4748095, upload-time = "2026-07-31T14:24:39.493Z" },
{ url = "https://files.pythonhosted.org/packages/6b/16/d3008eff98c764979865834c3d386d4fd041b5f52e7f34fc29ac1a5eb515/cryptography-50.0.0-cp39-abi3-manylinux_2_34_ppc64le.whl", hash = "sha256:6e7d61120573a7f2cd94cc095f9e81f6967c61ccdf194285aa143ecec8e0b708", size = 5325948, upload-time = "2026-07-31T14:24:41.556Z" },
{ url = "https://files.pythonhosted.org/packages/9c/f8/d97f9603efda3888187bfdb893f26c41be4735c10631d05d284ee6b047c4/cryptography-50.0.0-cp39-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:37fdb0d0111f1e2ff07139dfb79f1b49531f8e213c46f1163dd7642979b58c47", size = 4762400, upload-time = "2026-07-31T14:24:43.636Z" },
{ url = "https://files.pythonhosted.org/packages/64/a2/4615c8f7d81a00b1d6e6afe19f694e1543582349fb5f4076f6cb5dc36485/cryptography-50.0.0-cp39-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:c87f62a3d3b9888ed0fdde100ec06aa61ca9cd44bad9057d1dff9a516b5f5bb9", size = 4878208, upload-time = "2026-07-31T14:24:45.522Z" },
{ url = "https://files.pythonhosted.org/packages/d2/1a/efcfb02f91407149a0dacffffab791f7e19bf6385f63b3666dc8b5e5c9c8/cryptography-50.0.0-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:65c2c3add92b45fd0709db8594536aea39c2a67af0e27ffcf049c498501140b7", size = 5037050, upload-time = "2026-07-31T14:24:47.697Z" },
{ url = "https://files.pythonhosted.org/packages/57/30/4a22984d4f1bdfb8c054f07a92bc176b97a3134cc1d6c4b3bffb1f3688b4/cryptography-50.0.0-cp39-abi3-win_amd64.whl", hash = "sha256:d24fead1d4d076e1bfb006dcec392074a3cd8d7b4fc8a595aa64073b2b7a96ba", size = 3874135, upload-time = "2026-07-31T14:24:50.085Z" },
{ url = "https://files.pythonhosted.org/packages/1b/bc/ee4137cbbe105652c0ee4252792b78fc8e7afa4b8e61d9d5dc05a7f45731/cryptography-48.0.1-cp311-abi3-macosx_10_9_universal2.whl", hash = "sha256:3e4a1a3232eef2e6c732827d5722db29a0cc8b27af2a4d865b094cf954be9ca1", size = 8008324, upload-time = "2026-06-09T22:31:00.702Z" },
{ url = "https://files.pythonhosted.org/packages/d5/85/6379d42181bfc713094f081360fc5784d6c816b599d45e7f082502d173ce/cryptography-48.0.1-cp311-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:32143b24adb918f078134e1e230f1eb8cc04886b92c28b5f0041aaf3e5699225", size = 4696243, upload-time = "2026-06-09T22:32:33.446Z" },
{ url = "https://files.pythonhosted.org/packages/9c/87/c85d147b53323c7eb4d850920c8901377323c2a0ff8d79c262d4fee89aa2/cryptography-48.0.1-cp311-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:f0d27a5696721ef7a672b8c810f6aded391058e0b9486e63e6d93baf765da691", size = 4713235, upload-time = "2026-06-09T22:31:40.141Z" },
{ url = "https://files.pythonhosted.org/packages/79/58/67cbf8cf1ee7c54b439ca07bbecf8362c07afc11a3724fea70f745784add/cryptography-48.0.1-cp311-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:eb86ce1af36fe65041b6db9a8bb064ee621a7e5fded0f80d475ec243477cd242", size = 4702323, upload-time = "2026-06-09T22:31:42.191Z" },
{ url = "https://files.pythonhosted.org/packages/89/c6/24266ac10c47f6cd2a865f4446062b466da1d1f10b27189eac00e61bf0c9/cryptography-48.0.1-cp311-abi3-manylinux_2_28_ppc64le.whl", hash = "sha256:b024e784ad6c077ee0147b35ea9cbfc1e34e1fd4c1dcca214c2794d73a12df08", size = 5300085, upload-time = "2026-06-09T22:31:58.703Z" },
{ url = "https://files.pythonhosted.org/packages/d2/bb/cc4b78784f97efc8c5874c2a9743708d172be6663024b34a0467885ae0c8/cryptography-48.0.1-cp311-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:3752f2dbc8f07a30aad2932c986cea495b03bb554887828225da104f732852b6", size = 4746137, upload-time = "2026-06-09T22:31:31.01Z" },
{ url = "https://files.pythonhosted.org/packages/1f/52/0c44de3f5267f8fbe8e835138017522a333436166e406f0db9b9e6e3033f/cryptography-48.0.1-cp311-abi3-manylinux_2_31_armv7l.whl", hash = "sha256:bd81490cd5801d755cf97bb68ac191f14b708470b1c7cf4580f669b9c9264cd8", size = 4333867, upload-time = "2026-06-09T22:32:28.096Z" },
{ url = "https://files.pythonhosted.org/packages/9a/2e/772d7adbfa931537bc401640b7cac9976bff689bda187833e5d63b428e49/cryptography-48.0.1-cp311-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:66fd0771e7b9c6dcd44cf1120690d2338d16d72795cf40cae2786a39eba65429", size = 4701805, upload-time = "2026-06-09T22:31:38.284Z" },
{ url = "https://files.pythonhosted.org/packages/f8/a3/b06844f303873493c963caf581c04df31c7035e0c1b0f02c4814d319ec80/cryptography-48.0.1-cp311-abi3-manylinux_2_34_ppc64le.whl", hash = "sha256:3fd2ca57062b241c856670b073487d2e86c4637937ca5601e48f97bf8e11fc8f", size = 5258461, upload-time = "2026-06-09T22:31:04.187Z" },
{ url = "https://files.pythonhosted.org/packages/9f/13/8b765e2e12b07c74941caadb9d1c8fdc006c4dfbf2b8f2d610519758954d/cryptography-48.0.1-cp311-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:0ee6ea481db1ab889cba043ec1eda17bb9c1ea79db6722f779c3667f9f70322f", size = 4745488, upload-time = "2026-06-09T22:32:30.07Z" },
{ url = "https://files.pythonhosted.org/packages/2e/aa/48972bce55049b32a94f4907eda4d75fa385aad8a39506cc2fc72196ecf0/cryptography-48.0.1-cp311-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:f2ceef93cb096aa3c4cc4b5c94ca6131f9196d28c64d6111533402a9b2054d41", size = 4830256, upload-time = "2026-06-09T22:31:43.868Z" },
{ url = "https://files.pythonhosted.org/packages/47/a2/e5079a032fb85cf6005046ca92bbd78b0c82dad2b5751ab8c311659da06f/cryptography-48.0.1-cp311-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:9bd3f92d76217892b15df84ca256c2c113d386fdda7a7d8691aeeced976507c6", size = 4979117, upload-time = "2026-06-09T22:31:05.845Z" },
{ url = "https://files.pythonhosted.org/packages/b7/a0/8f50cae9c74e718ed769d63ed5c74bd0ea830c9550a74629cebd1b9c7bc7/cryptography-48.0.1-cp311-abi3-win32.whl", hash = "sha256:b9a32b876490d66c8bcc9963ef220199569748434ab01a9d6aaeabf88e7f5158", size = 3304154, upload-time = "2026-06-09T22:32:16.845Z" },
{ url = "https://files.pythonhosted.org/packages/c5/69/0572c77dbace6fef72f33755bd52ea399c71367250d366237f8691826b9e/cryptography-48.0.1-cp311-abi3-win_amd64.whl", hash = "sha256:39489bfca54c7a1f6b297efcd8bc608ab92d16c4ca631b0cad4da46724588b24", size = 3817138, upload-time = "2026-06-09T22:32:00.388Z" },
{ url = "https://files.pythonhosted.org/packages/42/06/3e768b4c3bc78201583fa35a0e18f640dd782ff41afba88f8545481a8874/cryptography-48.0.1-cp314-cp314t-macosx_10_9_universal2.whl", hash = "sha256:f817adc181390bd54f2f700107a7419040fb7c1bdf2fc26f36551a06a68c3345", size = 7989830, upload-time = "2026-06-09T22:31:07.8Z" },
{ url = "https://files.pythonhosted.org/packages/8a/13/6476736484b94041110c8340a3eb63962fea4975baea8cb4a512adb44d4d/cryptography-48.0.1-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:d5d30989c6917b478b5817902e85fddaea2261efa8648383d965381ccb9e1ac4", size = 4689201, upload-time = "2026-06-09T22:31:09.745Z" },
{ url = "https://files.pythonhosted.org/packages/79/62/65a87f34d2a431546e2509b85d55e8c90df86d668f6731da64d538512ac2/cryptography-48.0.1-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:df637c05205ea7c1d7fbcbe54bbfea648a52951155f997af13d895d0ecc96991", size = 4702822, upload-time = "2026-06-09T22:32:24.409Z" },
{ url = "https://files.pythonhosted.org/packages/7f/59/810b5204b0a9b10f4b6bc06bd551a8b609803cd931806bc3b71884b225e5/cryptography-48.0.1-cp314-cp314t-manylinux_2_28_aarch64.whl", hash = "sha256:869c3b8a53bfe27147832df48b32adadf558249d50e76cb3769d40e986b13265", size = 4694875, upload-time = "2026-06-09T22:32:08.737Z" },
{ url = "https://files.pythonhosted.org/packages/24/dc/d8ca05ffea724eec6d232ea6f18e74c269eb6bdfdcc9bfba689790d1325f/cryptography-48.0.1-cp314-cp314t-manylinux_2_28_ppc64le.whl", hash = "sha256:e361afba8918070d376df76f408a4f67fec0ee9cff81a99e48fe9a233ef59e17", size = 5290385, upload-time = "2026-06-09T22:31:15.212Z" },
{ url = "https://files.pythonhosted.org/packages/03/8c/3be6cb4da181f5bb6c19cf560c2359d60644a6b5fc5b57854e528f47b296/cryptography-48.0.1-cp314-cp314t-manylinux_2_28_x86_64.whl", hash = "sha256:d069066deead00ac7f090be101be875a06855908f7ec004c27b8fefb4acfb411", size = 4737082, upload-time = "2026-06-09T22:32:22.66Z" },
{ url = "https://files.pythonhosted.org/packages/aa/f6/d5f60a5a1434dbfd949e227fd0065d194c7e6b6ac526b17f5c06152b8231/cryptography-48.0.1-cp314-cp314t-manylinux_2_31_armv7l.whl", hash = "sha256:09f73a725d582cef64b91281a322cd798d14a33b2b6f2b7ad9531dc336d84c02", size = 4325328, upload-time = "2026-06-09T22:32:10.777Z" },
{ url = "https://files.pythonhosted.org/packages/17/b7/ba75dd947a14b6ad907b01ae8f6b5b348cdd1b48142f0063dee9e20c1d9d/cryptography-48.0.1-cp314-cp314t-manylinux_2_34_aarch64.whl", hash = "sha256:15254441469dd6bf027039453288e2072124f8b6603563f5d759e1c9b69273fa", size = 4694530, upload-time = "2026-06-09T22:31:53.105Z" },
{ url = "https://files.pythonhosted.org/packages/62/29/50d6b9e8aff12d8b67afaeb3569335e32dc83a5723e3bbded24fdac9f809/cryptography-48.0.1-cp314-cp314t-manylinux_2_34_ppc64le.whl", hash = "sha256:8ace4507d1e6533c125f4fac754f8bb8b6a74c08e92179dabd7e16571a3efbf3", size = 5245046, upload-time = "2026-06-09T22:31:25.774Z" },
{ url = "https://files.pythonhosted.org/packages/9f/04/618f4115cfc0add0838c82507aa18a346089428da8653ad38b3ff36f5cb3/cryptography-48.0.1-cp314-cp314t-manylinux_2_34_x86_64.whl", hash = "sha256:b4e391975f038e66432328639620a4aff2d307513b004f1ca06d6225bced815c", size = 4736660, upload-time = "2026-06-09T22:32:12.676Z" },
{ url = "https://files.pythonhosted.org/packages/24/9c/06e062462a0de28a3b3911322eded4c16deb9f441b1b7575d3dc59488ab5/cryptography-48.0.1-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:42fcd8e26fe555d9b3577a135f5091fefa0aa4e99129c23fb56787a1bd4ada72", size = 4822229, upload-time = "2026-06-09T22:31:17.062Z" },
{ url = "https://files.pythonhosted.org/packages/f4/be/0561971eaaee4b8a0e7d5113c536921063ab91aaf23278ac374eaf881e11/cryptography-48.0.1-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:c1400da5e32a43253392277eac7490a60e497d810a63dd5608d71bbd7af507c9", size = 4966364, upload-time = "2026-06-09T22:31:32.842Z" },
{ url = "https://files.pythonhosted.org/packages/a4/27/728c77876f12b000820b69ae490f3c4083775e79e07827e9e60be07ad209/cryptography-48.0.1-cp314-cp314t-win32.whl", hash = "sha256:0df56b056bc17c1b7d6821dfa65216e62bd232d8ab05eb3db44e71d235651471", size = 3278498, upload-time = "2026-06-09T22:31:29.154Z" },
{ url = "https://files.pythonhosted.org/packages/06/e3/79a612c6d7b1e6ee0edd43633d53035bec2cfb78c82b76f7864f39e36f34/cryptography-48.0.1-cp314-cp314t-win_amd64.whl", hash = "sha256:9de21387aa95e2a895823d0745b430bed4f33503ba9ab5e0b5311f33e37d66d2", size = 3798790, upload-time = "2026-06-09T22:31:56.697Z" },
{ url = "https://files.pythonhosted.org/packages/ca/6c/00fa2a95997164c8b2072ce327c23d4ab20809ccc323ea5fab91e53a4bba/cryptography-48.0.1-cp39-abi3-macosx_10_9_universal2.whl", hash = "sha256:4fdc69f8e4316bcf0c8c8ec1f26f285d12e8142d88d96c876a59a03be3f6ae67", size = 7987408, upload-time = "2026-06-09T22:32:20.777Z" },
{ url = "https://files.pythonhosted.org/packages/b0/d9/45f309a7e4e5f3f8f121d6d3be9e94024a7726ec598d6e08ae04edb2f04d/cryptography-48.0.1-cp39-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:48fe40804d4caa2288f24e70ca8c64c42dd826da0ad7e4f1b41b2128d679e6c8", size = 4690196, upload-time = "2026-06-09T22:31:54.74Z" },
{ url = "https://files.pythonhosted.org/packages/5f/9f/a1bc8bcc798811b8527eb374bbccf30a3f3e806829d967118222bf1125eb/cryptography-48.0.1-cp39-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:86be3b1b0b6bf09482fb50a979c508d2950ed95f5621ec77f4e385962006b83a", size = 4696782, upload-time = "2026-06-09T22:31:45.615Z" },
{ url = "https://files.pythonhosted.org/packages/66/c2/81a4fb4e4373c500bb526bc337ac5719dd31dd15b970b84a238168c6aa08/cryptography-48.0.1-cp39-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:4ab0a343c807bbcd90c971cd1ecf072937cd01847a9e002bef88fb47ac6be577", size = 4696618, upload-time = "2026-06-09T22:31:11.564Z" },
{ url = "https://files.pythonhosted.org/packages/e5/0b/aa68b221dde92d09cb29a024ede17550ee21e77a404e59fc093c82bb51e1/cryptography-48.0.1-cp39-abi3-manylinux_2_28_ppc64le.whl", hash = "sha256:9621de99d2da096006b629979efd8ae7eb2d8b822488d0c89ee4000c306c59b1", size = 5289970, upload-time = "2026-06-09T22:31:20.368Z" },
{ url = "https://files.pythonhosted.org/packages/78/13/fba657f958d2af66ea959a4ba01212632089249d34af1ae48054136344d7/cryptography-48.0.1-cp39-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:88c852a0ae366e262e5a1744b685e6a433dc8788dd2a277e418bf4904203609d", size = 4731873, upload-time = "2026-06-09T22:31:22.253Z" },
{ url = "https://files.pythonhosted.org/packages/4c/4c/9a964756d24a26b3e34dfcb16f961b89838786e6700b635b0d1e3adff4b6/cryptography-48.0.1-cp39-abi3-manylinux_2_31_armv7l.whl", hash = "sha256:43c5835e2cb98c8733d86f57d6fc879b613f5c3478607281c3e36daffc6dd8a6", size = 4330804, upload-time = "2026-06-09T22:31:36.56Z" },
{ url = "https://files.pythonhosted.org/packages/4b/0f/a10f3a6eb12950a10e3a874070283aa2dd5875b2bfd15fad8a3e17b3f13e/cryptography-48.0.1-cp39-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:fe0180af5bf9236518a087e35bf2d9a347d5f5f51e63c579d683ddff424e3d46", size = 4696217, upload-time = "2026-06-09T22:31:13.351Z" },
{ url = "https://files.pythonhosted.org/packages/f3/6f/5cd12f951165ea73ef85266775d97e4c763b2474ccfd816dd69d3a18d6f8/cryptography-48.0.1-cp39-abi3-manylinux_2_34_ppc64le.whl", hash = "sha256:b7a2d1a937a738a881737cec135a38bb61470589b17515b9f73f571d0ae10401", size = 5245252, upload-time = "2026-06-09T22:32:02.193Z" },
{ url = "https://files.pythonhosted.org/packages/68/ab/8aaa12e4516ec4464033ab79b6f3b592bd5a92102467c4ace8a0d970203f/cryptography-48.0.1-cp39-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:b74ca3b8e5ecdd833bf6a002ca41b4793bb27fb8f1c06ffaf2643c9e9140e31b", size = 4731388, upload-time = "2026-06-09T22:32:04.019Z" },
{ url = "https://files.pythonhosted.org/packages/1b/24/50027ea4dca85ec1f40688f3c24fb32ccacd520583c9592c3cc95628e6fb/cryptography-48.0.1-cp39-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:2c37f2461406063b417837f5f3daab668652acd82423efcd7f0a9f04be972de1", size = 4824186, upload-time = "2026-06-09T22:32:18.707Z" },
{ url = "https://files.pythonhosted.org/packages/52/41/04cb5eb17085ade6f50cc611fb657df6a0f5885350de8764ece89c050197/cryptography-48.0.1-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:86fe77abb1bd87afb251d4d02ada7ecf53a32cee9b67d976abb2e45a13297475", size = 4964539, upload-time = "2026-06-09T22:31:18.793Z" },
{ url = "https://files.pythonhosted.org/packages/36/bf/ed70785c496e89d7e73b7cda2d21f2447fd6d4e821714b8d04ff217fed92/cryptography-48.0.1-cp39-abi3-win32.whl", hash = "sha256:6b2c0c3e6ccf3ade7750f836ef3ee36eea250cc467d45c256895573ac08cc6f1", size = 3282307, upload-time = "2026-06-09T22:30:53.162Z" },
{ url = "https://files.pythonhosted.org/packages/b3/ff/371ea7d252656ee1eb6d83eeeef3d1d0c6baf1d6497687d081ea03814670/cryptography-48.0.1-cp39-abi3-win_amd64.whl", hash = "sha256:9a49ca6c81417f6a5edb50375a60cccdd70fa0a91a5211829dbea74eba94d2ac", size = 3793408, upload-time = "2026-06-09T22:32:15.191Z" },
]
[[package]]
@@ -1102,7 +1105,7 @@ name = "macholib"
version = "1.16.4"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "altgraph", marker = "python_full_version < '3.15' and sys_platform != 'win32'" },
{ name = "altgraph" },
]
sdist = { url = "https://files.pythonhosted.org/packages/10/2f/97589876ea967487978071c9042518d28b958d87b17dceb7cdc1d881f963/macholib-1.16.4.tar.gz", hash = "sha256:f408c93ab2e995cd2c46e34fe328b130404be143469e41bc366c807448979362", size = 59427, upload-time = "2025-11-22T08:28:38.373Z" }
wheels = [
@@ -1795,13 +1798,13 @@ name = "pyinstaller"
version = "6.21.0"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "altgraph", marker = "python_full_version < '3.15'" },
{ name = "macholib", marker = "python_full_version < '3.15' and sys_platform == 'darwin'" },
{ name = "packaging", marker = "python_full_version < '3.15'" },
{ name = "pefile", marker = "python_full_version < '3.15' and sys_platform == 'win32'" },
{ name = "pyinstaller-hooks-contrib", marker = "python_full_version < '3.15'" },
{ name = "pywin32-ctypes", marker = "python_full_version < '3.15' and sys_platform == 'win32'" },
{ name = "setuptools", marker = "python_full_version < '3.15'" },
{ name = "altgraph" },
{ name = "macholib", marker = "sys_platform == 'darwin'" },
{ name = "packaging" },
{ name = "pefile", marker = "sys_platform == 'win32'" },
{ name = "pyinstaller-hooks-contrib" },
{ name = "pywin32-ctypes", marker = "sys_platform == 'win32'" },
{ name = "setuptools" },
]
sdist = { url = "https://files.pythonhosted.org/packages/d5/4d/ec706c3fcf39e26888c35b39615ff4d5865d184069666c47492cff1fbe50/pyinstaller-6.21.0.tar.gz", hash = "sha256:bb9fab705983e393a2d1cac77d6972513057ad800215fd861dc15ff5272e98fd", size = 4061519, upload-time = "2026-06-13T14:15:06.25Z" }
wheels = [
@@ -1823,7 +1826,7 @@ name = "pyinstaller-hooks-contrib"
version = "2026.6"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "packaging", marker = "python_full_version < '3.15'" },
{ name = "packaging" },
]
sdist = { url = "https://files.pythonhosted.org/packages/94/5b/c9fe0db5e83ee1c39b2258fa21d23b15e1a60786b6c5990ee5074ead8bb6/pyinstaller_hooks_contrib-2026.6.tar.gz", hash = "sha256:bef5002c32f4f50bd55b005da12cff64eca8783e7eaf86a06a62410164bab725", size = 173354, upload-time = "2026-06-08T22:37:16.152Z" }
wheels = [
@@ -2419,7 +2422,7 @@ dev = [
requires-dist = [
{ name = "boto3", marker = "extra == 'bedrock'", specifier = ">=1.28.0" },
{ name = "caido-sdk-client", specifier = ">=0.2.0" },
{ name = "cryptography", specifier = ">=48.0.1,<51" },
{ name = "cryptography", specifier = ">=48.0.1,<49" },
{ name = "cvss", specifier = ">=3.2" },
{ name = "docker", specifier = ">=7.1.0" },
{ name = "google-auth", marker = "extra == 'vertex'", specifier = ">=2.0.0" },