fix: Allow content to be None for role==tool

.github/ISSUE_TEMPLATE/bug_report.md

@@ -11,9 +11,6 @@ assignees: ''
 A clear and concise description of what the bug is.
 
 **Please describe your setup**
-
-- [ ] MemGPT version
-  - What is the output of `memgpt version`? (eg "0.2.4")
 - [ ] How did you install memgpt?
   - `pip install pymemgpt`? `pip install pymemgpt-nightly`? `git clone`?
 - [ ] Describe your setup
@@ -26,6 +23,9 @@ If applicable, add screenshots to help explain your problem.
 **Additional context**
 Add any other context about the problem here.
 
+**MemGPT Config**
+Please attach your `~/.memgpt/config` file or copy past it below.
+
 ---
 
 If you're not using OpenAI, please provide additional information on your local LLM setup:

memgpt/data_types.py

@@ -226,7 +226,7 @@ def to_openai_dict(self):
         # TODO change to pydantic casting, eg `return SystemMessageModel(self)`
 
         if self.role == "system":
-            assert all([v is not None for v in [self.text, self.role]]), vars(self)
+            assert all([v is not None for v in [self.role]]), vars(self)
             openai_message = {
                 "content": self.text,
                 "role": self.role,
@@ -258,13 +258,12 @@ def to_openai_dict(self):
                 openai_message["tool_calls"] = [tool_call.to_dict() for tool_call in self.tool_calls]
 
         elif self.role == "tool":
-            assert all([v is not None for v in [self.text, self.role, self.tool_call_id]]), vars(self)
+            assert all([v is not None for v in [self.role, self.tool_call_id]]), vars(self)
             openai_message = {
                 "content": self.text,
                 "role": self.role,
                 "tool_call_id": self.tool_call_id,
             }
-
         else:
             raise ValueError(self.role)