Skip to content

armgit / strix

Public Imported from GitHub
0

Open-source AI penetration testing tool to find and fix your app’s vulnerabilities.

Pre-warm-up unknown-model warning + LiteLLM streaming hardening

0xallam143b9e7040d8
diff --git a/strix/config/models.py b/strix/config/models.py
index feedbe72..c6775e28 100644
--- a/strix/config/models.py
+++ b/strix/config/models.py
@@ -95,11 +95,13 @@ def _mirror_api_key_to_provider_env(model_name: str | None, api_key: str) -> Non
def _configure_litellm_compatibility() -> None:
- """Enable LiteLLM's permissive param-handling mode."""
+ """Enable LiteLLM's permissive param handling and disable its callbacks."""
import litellm
litellm.drop_params = True
litellm.modify_params = True
+ litellm.turn_off_message_logging = True
+ litellm.disable_streaming_logging = True
def _configure_litellm_default(name: str, value: str) -> None:
@@ -115,3 +117,13 @@ def uses_chat_completions_tool_schema(model_name: str, settings: Settings) -> bo
if "/" in model and not model.startswith("openai/"):
return True
return bool(settings.llm.api_base)
+
+
+def is_known_openai_bare_model(model_name: str) -> bool:
+ import litellm
+
+ name = model_name.strip().lower()
+ if not name or "/" in name:
+ return False
+ entry = litellm.model_cost.get(name)
+ return bool(entry and entry.get("litellm_provider") == "openai")
diff --git a/strix/core/execution.py b/strix/core/execution.py
index 84fe72f8..1017f70d 100644
--- a/strix/core/execution.py
+++ b/strix/core/execution.py
@@ -349,12 +349,20 @@ async def _run_cycle( # noqa: PLR0912
)
await coordinator.attach_stream(agent_id, stream)
try:
- async for event in stream.stream_events():
- if event_sink is not None:
- try:
- event_sink(agent_id, event)
- except Exception:
- logger.exception("stream event sink failed for %s", agent_id)
+ try:
+ async for event in stream.stream_events():
+ if event_sink is not None:
+ try:
+ event_sink(agent_id, event)
+ except Exception:
+ logger.exception("stream event sink failed for %s", agent_id)
+ except RuntimeError as stream_exc:
+ if "after shutdown" not in str(stream_exc):
+ raise
+ logger.warning(
+ "Ignoring LiteLLM end-of-stream shutdown race for %s",
+ agent_id,
+ )
if stream.run_loop_exception is not None:
raise stream.run_loop_exception
finally:
diff --git a/strix/interface/main.py b/strix/interface/main.py
index ac3a86f1..b5c56ad4 100644
--- a/strix/interface/main.py
+++ b/strix/interface/main.py
@@ -22,7 +22,11 @@ from strix.config import (
load_settings,
persist_current,
)
-from strix.config.models import StrixProvider, configure_sdk_model_defaults
+from strix.config.models import (
+ StrixProvider,
+ configure_sdk_model_defaults,
+ is_known_openai_bare_model,
+)
from strix.core.paths import run_dir_for, runtime_state_dir
from strix.interface.cli import run_cli
from strix.interface.tui import run_tui
@@ -215,7 +219,39 @@ async def warm_up_llm() -> None:
configure_sdk_model_defaults(settings)
llm = settings.llm
- model = StrixProvider().get_model((llm.model or "").strip())
+ raw_model = (llm.model or "").strip()
+ if (
+ raw_model
+ and "/" not in raw_model
+ and not is_known_openai_bare_model(raw_model)
+ and not llm.api_base
+ ):
+ warn_text = Text()
+ warn_text.append("UNKNOWN MODEL NAME", style="bold yellow")
+ warn_text.append("\n\n", style="white")
+ warn_text.append(f"'{raw_model}'", style="bold cyan")
+ warn_text.append(
+ " is not a known OpenAI model. Bare names route to OpenAI by default.\n"
+ "If you meant a non-OpenAI provider, use the '",
+ style="white",
+ )
+ warn_text.append("<provider>/<model>", style="bold cyan")
+ warn_text.append(
+ "' form, e.g. 'anthropic/claude-opus-4-7', 'deepseek/deepseek-v4-pro'.",
+ style="white",
+ )
+ console.print(
+ Panel(
+ warn_text,
+ title="[bold white]STRIX",
+ title_align="left",
+ border_style="yellow",
+ padding=(1, 2),
+ ),
+ )
+ sys.exit(1)
+
+ model = StrixProvider().get_model(raw_model)
await asyncio.wait_for(
model.get_response(
system_instructions="You are a helpful assistant.",