Skip to content

armgit / strix

Public Imported from GitHub
0

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

fix(llm): avoid auth during ChatGPT lookup

chunguscodes76e97e6a59fb
diff --git a/strix/llm/context_budget.py b/strix/llm/context_budget.py
index 3f153d91..b7589a9e 100644
--- a/strix/llm/context_budget.py
+++ b/strix/llm/context_budget.py
@@ -17,7 +17,14 @@ logger = logging.getLogger(__name__)
# LiteLLM keys models without the routing prefix users type (``openai/``,
# ``litellm/``, ``ollama/`` ...). Strip a leading provider segment on lookup.
-_STRIPPABLE_PREFIXES = ("openai/", "litellm/", "any-llm/", "ollama/", "ollama_chat/")
+_STRIPPABLE_PREFIXES = (
+ "openai/",
+ "chatgpt/",
+ "litellm/",
+ "any-llm/",
+ "ollama/",
+ "ollama_chat/",
+)
_DEFAULT_OUTPUT_TOKENS = 8_192
@@ -38,7 +45,11 @@ def _safe_get_model_info(model: str) -> dict[str, Any] | None:
@lru_cache(maxsize=128)
def _model_info(model: str) -> dict[str, int]:
- for candidate in (model, _lookup_key(model)):
+ lookup_key = _lookup_key(model)
+ # Provider-qualified ChatGPT lookups may start a synchronous device-login
+ # poll. LiteLLM keys the metadata by the underlying model slug.
+ candidates = (lookup_key,) if model.startswith("chatgpt/") else (model, lookup_key)
+ for candidate in candidates:
info = _safe_get_model_info(candidate)
if info is not None:
return {
diff --git a/tests/test_context_budget.py b/tests/test_context_budget.py
index 8b34b483..a9a48e0c 100644
--- a/tests/test_context_budget.py
+++ b/tests/test_context_budget.py
@@ -21,6 +21,24 @@ def test_context_window_strips_provider_prefix() -> None:
assert context_budget.context_window("openai/gpt-4o") == 128_000
+def test_context_window_chatgpt_prefix_skips_provider_auth(
+ monkeypatch: pytest.MonkeyPatch,
+) -> None:
+ context_budget._model_info.cache_clear()
+ calls: list[str] = []
+
+ def _model_info(model: str) -> dict[str, int]:
+ calls.append(model)
+ return {"max_input_tokens": 1_050_000, "max_output_tokens": 128_000}
+
+ monkeypatch.setattr("strix.llm.context_budget.litellm.get_model_info", _model_info)
+ try:
+ assert context_budget.context_window("chatgpt/gpt-5.6-luna") == 1_050_000
+ assert calls == ["gpt-5.6-luna"]
+ finally:
+ context_budget._model_info.cache_clear()
+
+
def test_context_window_unmapped_uses_fallback(monkeypatch: pytest.MonkeyPatch) -> None:
context_budget._model_info.cache_clear()