Hua/nanobot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: guard validate_params against non-dict input

Browse Source 
When the LLM returns malformed tool arguments (e.g. a list or string
instead of a dict), validate_params would crash with AttributeError
in _validate() when calling val.items(). Now returns a clear
validation error instead of crashing.
This commit is contained in:
Kiplangatkorir
2026-03-04 10:53:30 +03:00
parent 1303cc6669
commit df8d09f2b6
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
nanobot/agent/tools/base.py
View File

@@ -54,6 +54,8 @@ class Tool(ABC):
def validate_params(self, params: dict[str, Any]) -> list[str]: def validate_params(self, params: dict[str, Any]) -> list[str]:
"""Validate tool parameters against JSON schema. Returns error list (empty if valid).""" """Validate tool parameters against JSON schema. Returns error list (empty if valid)."""
if not isinstance(params, dict):
return [f"parameters must be an object, got {type(params).__name__}"]
schema = self.parameters or {} schema = self.parameters or {}
if schema.get("type", "object") != "object": if schema.get("type", "object") != "object":
raise ValueError(f"Schema must be object type, got {schema.get('type')!r}") raise ValueError(f"Schema must be object type, got {schema.get('type')!r}")