Skip to content

Agent Zero AI framework

Solidify LiteLLM global kwargs handling

Alessandro3d4c30218560
diff --git a/AGENTS.md b/AGENTS.md
index 47736dbb4..a3738d8ee 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -100,7 +100,7 @@ Key Files:
- helpers/plugins.py: Plugin discovery and configuration logic.
- webui/js/AlpineStore.js: Store factory for reactive frontend state.
- helpers/api.py: Base class for all API endpoints.
-- models.py: LLM provider configuration and LiteLLM wrappers; framework LiteLLM defaults such as `drop_params=True` are merged with `litellm_global_kwargs`, configured values override framework defaults, and the merged kwargs are applied at LiteLLM module and per-call boundaries.
+- models.py: LLM provider configuration and LiteLLM wrappers; framework LiteLLM defaults such as `drop_params=True` are merged with `litellm_global_kwargs`, configured values override framework defaults, documented module-level switches such as `drop_params` are applied to LiteLLM, and merged kwargs are passed per call.
- scripts/openrouter_release_notes_system_prompt.md: Editable system prompt used to generate GitHub release notes during Docker publishing.
- knowledge/main/about/: Agent self-knowledge files, indexed into the vector DB for runtime recall. Not user-facing docs - written for the agent's internal reference.
- webui/components/AGENTS.md: DOX contract for Alpine component architecture.
diff --git a/models.py b/models.py
index b81333a0a..811fa31e0 100644
--- a/models.py
+++ b/models.py
@@ -49,6 +49,11 @@ DEFAULT_LITELLM_GLOBAL_KWARGS: dict[str, Any] = {
"drop_params": True,
}
+# LiteLLM documents drop_params as both a module-level switch and per-call kwarg.
+# Other entries in litellm_global_kwargs, such as timeout or additional_drop_params,
+# are kept as per-call kwargs instead of becoming arbitrary module attributes.
+LITELLM_MODULE_GLOBAL_KEYS = frozenset({"drop_params"})
+
def _normalize_litellm_kwargs(values: dict[str, Any]) -> dict[str, Any]:
# Normalize .env/UI-style scalar strings into native types for LiteLLM.
@@ -100,6 +105,8 @@ def turn_off_logging():
def set_litellm_params():
global_kwargs = get_litellm_global_kwargs()
for key, value in global_kwargs.items():
+ if key not in LITELLM_MODULE_GLOBAL_KEYS:
+ continue
setattr(litellm, key, value)
return global_kwargs
@@ -959,12 +966,6 @@ def _merge_provider_defaults(
if key and key not in ("None", "NA"):
kwargs["api_key"] = key
- # Merge LiteLLM global kwargs. Framework defaults are merged first, then
- # configured global kwargs override those defaults; explicit provider/model
- # kwargs still keep priority via setdefault.
- for k, v in get_litellm_global_kwargs().items():
- kwargs.setdefault(k, v)
-
return provider_name, kwargs
diff --git a/tests/test_stream_tool_early_stop.py b/tests/test_stream_tool_early_stop.py
index 8aa7de661..a1d0ac63e 100644
--- a/tests/test_stream_tool_early_stop.py
+++ b/tests/test_stream_tool_early_stop.py
@@ -94,30 +94,83 @@ def test_litellm_global_kwargs_merge_defaults_and_config(monkeypatch):
monkeypatch.setattr(
models.settings,
"get_settings",
- lambda: {"litellm_global_kwargs": {"drop_params": "false", "timeout": "30"}},
+ lambda: {
+ "litellm_global_kwargs": {
+ "drop_params": "false",
+ "timeout": "30",
+ "additional_drop_params": ["response_format"],
+ }
+ },
)
assert models._merge_litellm_call_kwargs({}) == {
"drop_params": False,
"timeout": 30,
+ "additional_drop_params": ["response_format"],
}
original_drop_params = getattr(models.litellm, "drop_params", None)
had_timeout = hasattr(models.litellm, "timeout")
original_timeout = getattr(models.litellm, "timeout", None)
+ had_additional_drop_params = hasattr(models.litellm, "additional_drop_params")
+ original_additional_drop_params = getattr(
+ models.litellm, "additional_drop_params", None
+ )
try:
assert models.set_litellm_params() == {
"drop_params": False,
"timeout": 30,
+ "additional_drop_params": ["response_format"],
}
assert models.litellm.drop_params is False
- assert models.litellm.timeout == 30
+ if had_timeout:
+ assert models.litellm.timeout == original_timeout
+ else:
+ assert not hasattr(models.litellm, "timeout")
+ if had_additional_drop_params:
+ assert (
+ models.litellm.additional_drop_params
+ == original_additional_drop_params
+ )
+ else:
+ assert not hasattr(models.litellm, "additional_drop_params")
finally:
setattr(models.litellm, "drop_params", original_drop_params)
if had_timeout:
setattr(models.litellm, "timeout", original_timeout)
elif hasattr(models.litellm, "timeout"):
delattr(models.litellm, "timeout")
+ if had_additional_drop_params:
+ setattr(
+ models.litellm,
+ "additional_drop_params",
+ original_additional_drop_params,
+ )
+ elif hasattr(models.litellm, "additional_drop_params"):
+ delattr(models.litellm, "additional_drop_params")
+
+
+def test_provider_defaults_do_not_freeze_litellm_global_kwargs(monkeypatch):
+ monkeypatch.setattr(models, "get_provider_config", lambda *args, **kwargs: None)
+ monkeypatch.setattr(models, "get_api_key", lambda *_args, **_kwargs: None)
+ monkeypatch.setattr(
+ models.settings,
+ "get_settings",
+ lambda: {"litellm_global_kwargs": {"drop_params": "true"}},
+ )
+
+ _, provider_kwargs = models._merge_provider_defaults("chat", "openai", {})
+
+ assert "drop_params" not in provider_kwargs
+ assert models._merge_litellm_call_kwargs(provider_kwargs)["drop_params"] is True
+
+ monkeypatch.setattr(
+ models.settings,
+ "get_settings",
+ lambda: {"litellm_global_kwargs": {"drop_params": "false"}},
+ )
+
+ assert models._merge_litellm_call_kwargs(provider_kwargs)["drop_params"] is False
@pytest.mark.asyncio