From b653183bb0f76b0f3e157506e9906398efe7c311 Mon Sep 17 00:00:00 2001
From: Re-bin <xubinrencs@gmail.com>
Date: Sun, 22 Feb 2026 18:26:42 +0000
Subject: [PATCH] refactor(providers): move empty content sanitization to base
 class

---
 nanobot/providers/base.py             | 40 ++++++++++++++++++++++++
 nanobot/providers/custom_provider.py  | 45 +--------------------------
 nanobot/providers/litellm_provider.py |  2 +-
 3 files changed, 42 insertions(+), 45 deletions(-)

diff --git a/nanobot/providers/base.py b/nanobot/providers/base.py
index c69c38b..eb1599a 100644
--- a/nanobot/providers/base.py
+++ b/nanobot/providers/base.py
@@ -39,6 +39,46 @@ class LLMProvider(ABC):
     def __init__(self, api_key: str | None = None, api_base: str | None = None):
         self.api_key = api_key
         self.api_base = api_base
+
+    @staticmethod
+    def _sanitize_empty_content(messages: list[dict[str, Any]]) -> list[dict[str, Any]]:
+        """Replace empty text content that causes provider 400 errors.
+
+        Empty content can appear when MCP tools return nothing. Most providers
+        reject empty-string content or empty text blocks in list content.
+        """
+        result: list[dict[str, Any]] = []
+        for msg in messages:
+            content = msg.get("content")
+
+            if isinstance(content, str) and not content:
+                clean = dict(msg)
+                clean["content"] = None if (msg.get("role") == "assistant" and msg.get("tool_calls")) else "(empty)"
+                result.append(clean)
+                continue
+
+            if isinstance(content, list):
+                filtered = [
+                    item for item in content
+                    if not (
+                        isinstance(item, dict)
+                        and item.get("type") in ("text", "input_text", "output_text")
+                        and not item.get("text")
+                    )
+                ]
+                if len(filtered) != len(content):
+                    clean = dict(msg)
+                    if filtered:
+                        clean["content"] = filtered
+                    elif msg.get("role") == "assistant" and msg.get("tool_calls"):
+                        clean["content"] = None
+                    else:
+                        clean["content"] = "(empty)"
+                    result.append(clean)
+                    continue
+
+            result.append(msg)
+        return result
     
     @abstractmethod
     async def chat(
diff --git a/nanobot/providers/custom_provider.py b/nanobot/providers/custom_provider.py
index 9a0901c..a578d14 100644
--- a/nanobot/providers/custom_provider.py
+++ b/nanobot/providers/custom_provider.py
@@ -21,7 +21,7 @@ class CustomProvider(LLMProvider):
                    model: str | None = None, max_tokens: int = 4096, temperature: float = 0.7) -> LLMResponse:
         kwargs: dict[str, Any] = {
             "model": model or self.default_model,
-            "messages": self._prevent_empty_text_blocks(messages),
+            "messages": self._sanitize_empty_content(messages),
             "max_tokens": max(1, max_tokens),
             "temperature": temperature,
         }
@@ -50,46 +50,3 @@ class CustomProvider(LLMProvider):
     def get_default_model(self) -> str:
         return self.default_model
 
-    @staticmethod
-    def _prevent_empty_text_blocks(messages: list[dict[str, Any]]) -> list[dict[str, Any]]:
-        """Filter empty text content blocks that cause provider 400 errors.
-
-        When MCP tools return empty content, messages may contain empty-string
-        text blocks. Most providers (OpenAI-compatible) reject these with 400.
-        This method filters them out before sending to the API.
-        """
-        patched: list[dict[str, Any]] = []
-        for msg in messages:
-            content = msg.get("content")
-
-            # Empty string content
-            if isinstance(content, str) and content == "":
-                clean = dict(msg)
-                if msg.get("role") == "assistant" and msg.get("tool_calls"):
-                    clean["content"] = None
-                else:
-                    clean["content"] = "(empty)"
-                patched.append(clean)
-                continue
-
-            # List content — filter out empty text items
-            if isinstance(content, list):
-                filtered = [
-                    item for item in content
-                    if not (isinstance(item, dict)
-                            and item.get("type") in {"text", "input_text", "output_text"}
-                            and item.get("text") == "")
-                ]
-                if filtered != content:
-                    clean = dict(msg)
-                    if filtered:
-                        clean["content"] = filtered
-                    elif msg.get("role") == "assistant" and msg.get("tool_calls"):
-                        clean["content"] = None
-                    else:
-                        clean["content"] = "(empty)"
-                    patched.append(clean)
-                    continue
-
-            patched.append(msg)
-        return patched
diff --git a/nanobot/providers/litellm_provider.py b/nanobot/providers/litellm_provider.py
index 784f02c..7402a2b 100644
--- a/nanobot/providers/litellm_provider.py
+++ b/nanobot/providers/litellm_provider.py
@@ -196,7 +196,7 @@ class LiteLLMProvider(LLMProvider):
         
         kwargs: dict[str, Any] = {
             "model": model,
-            "messages": self._sanitize_messages(messages),
+            "messages": self._sanitize_messages(self._sanitize_empty_content(messages)),
             "max_tokens": max_tokens,
             "temperature": temperature,
         }