fix: normalize tool-call arguments for strict providers

Ensure assistant tool-call function.arguments is always emitted as valid JSON text so strict OpenAI-compatible backends (including Alibaba code models) do not reject requests. Add regressions for dict and malformed-string argument payloads in message sanitization.

Made-with: Cursor
This commit is contained in:
Michael-lhh
2026-04-15 01:37:41 +08:00
committed by Xubin Ren
parent 1f33df1ea6
commit f293ff7f18
2 changed files with 77 additions and 0 deletions
@@ -3,6 +3,7 @@
from __future__ import annotations
import asyncio
import json
import hashlib
import importlib.util
import os
@@ -222,6 +223,24 @@ class OpenAICompatProvider(LLMProvider):
return tool_call_id
return hashlib.sha1(tool_call_id.encode()).hexdigest()[:9]
@staticmethod
def _normalize_tool_call_arguments(arguments: Any) -> str:
"""Force function.arguments into a valid JSON object string."""
if isinstance(arguments, str):
stripped = arguments.strip()
if not stripped:
return "{}"
try:
parsed = json_repair.loads(stripped)
except Exception:
return "{}"
if isinstance(parsed, dict):
return json.dumps(parsed, ensure_ascii=False)
return "{}"
if isinstance(arguments, dict):
return json.dumps(arguments, ensure_ascii=False)
return "{}"
def _sanitize_messages(self, messages: list[dict[str, Any]]) -> list[dict[str, Any]]:
"""Strip non-standard keys, normalize tool_call IDs."""
sanitized = LLMProvider._sanitize_request_messages(messages, _ALLOWED_MSG_KEYS)
@@ -241,6 +260,16 @@ class OpenAICompatProvider(LLMProvider):
continue
tc_clean = dict(tc)
tc_clean["id"] = map_id(tc_clean.get("id"))
function = tc_clean.get("function")
if isinstance(function, dict):
function_clean = dict(function)
if "arguments" in function_clean:
function_clean["arguments"] = self._normalize_tool_call_arguments(
function_clean.get("arguments")
)
else:
function_clean["arguments"] = "{}"
tc_clean["function"] = function_clean
normalized.append(tc_clean)
clean["tool_calls"] = normalized
if clean.get("role") == "assistant":
+48
View File
@@ -584,6 +584,54 @@ def test_openai_compat_keeps_tool_calls_after_consecutive_assistant_messages() -
assert sanitized[2]["tool_call_id"] == "3ec83c30d"
def test_openai_compat_stringifies_dict_tool_arguments() -> None:
with patch("nanobot.providers.openai_compat_provider.AsyncOpenAI"):
provider = OpenAICompatProvider()
sanitized = provider._sanitize_messages([
{"role": "user", "content": "hi"},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_1",
"type": "function",
"function": {"name": "exec", "arguments": {"cmd": "ls -la"}},
}
],
},
{"role": "tool", "tool_call_id": "call_1", "name": "exec", "content": "ok"},
{"role": "user", "content": "done"},
])
assert sanitized[1]["tool_calls"][0]["function"]["arguments"] == '{"cmd": "ls -la"}'
def test_openai_compat_repairs_non_json_tool_arguments_string() -> None:
with patch("nanobot.providers.openai_compat_provider.AsyncOpenAI"):
provider = OpenAICompatProvider()
sanitized = provider._sanitize_messages([
{"role": "user", "content": "hi"},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_1",
"type": "function",
"function": {"name": "exec", "arguments": "{'cmd': 'pwd'}"},
}
],
},
{"role": "tool", "tool_call_id": "call_1", "name": "exec", "content": "ok"},
{"role": "user", "content": "done"},
])
assert sanitized[1]["tool_calls"][0]["function"]["arguments"] == '{"cmd": "pwd"}'
@pytest.mark.asyncio
async def test_openai_compat_stream_watchdog_returns_error_on_stall(monkeypatch) -> None:
monkeypatch.setenv("NANOBOT_STREAM_IDLE_TIMEOUT_S", "0")