fix(blocks): validate non-empty input in AIConversationBlock before LLM call (#12545)

### Why / What / How

**Why:** When `AIConversationBlock` receives an empty messages list and
an empty prompt, the block blindly forwards the empty array to the
downstream LLM API, which returns a cryptic `400 Bad Request` error:
`"Invalid 'messages': empty array. Expected an array with minimum length
1."` This is confusing for users who don't understand why their agent
failed.

**What:** Add early input validation in `AIConversationBlock.run()` that
raises a clear `ValueError` when both `messages` and `prompt` are empty.
Also add three unit tests covering the validation logic.

**How:** A simple guard clause at the top of the `run` method checks `if
not input_data.messages and not input_data.prompt` before the LLM call
is made. If both are empty, a descriptive `ValueError` is raised. If
either one has content, the block proceeds normally.

### Changes

- `autogpt_platform/backend/backend/blocks/llm.py`: Add validation guard
in `AIConversationBlock.run()` to reject empty messages + empty prompt
before calling the LLM
- `autogpt_platform/backend/backend/blocks/test/test_llm.py`: Add
`TestAIConversationBlockValidation` with three tests:
- `test_empty_messages_and_empty_prompt_raises_error` — validates the
guard clause
- `test_empty_messages_with_prompt_succeeds` — ensures prompt-only usage
still works
- `test_nonempty_messages_with_empty_prompt_succeeds` — ensures
messages-only usage still works

### Checklist

#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
  - [x] Lint passes (`ruff check`)
  - [x] Formatting passes (`ruff format`)
- [x] New unit tests validate the empty-input guard and the happy paths

Closes #11875

---------

Co-authored-by: Zamil Majdy <zamil.majdy@agpt.co>

autogpt_platform/backend/backend/blocks/llm.py

@@ -2016,6 +2016,19 @@ class AIConversationBlock(AIBlockBase):
     async def run(
         self, input_data: Input, *, credentials: APIKeyCredentials, **kwargs
     ) -> BlockOutput:
+        has_messages = any(
+            isinstance(m, dict)
+            and isinstance(m.get("content"), str)
+            and bool(m["content"].strip())
+            for m in (input_data.messages or [])
+        )
+        has_prompt = bool(input_data.prompt and input_data.prompt.strip())
+        if not has_messages and not has_prompt:
+            raise ValueError(
+                "Cannot call LLM with no messages and no prompt. "
+                "Provide at least one message or a non-empty prompt."
+            )
+
         response = await self.llm_call(
             AIStructuredResponseGeneratorBlock.Input(
                 prompt=input_data.prompt,

autogpt_platform/backend/backend/blocks/test/test_llm.py

@@ -488,6 +488,154 @@ class TestLLMStatsTracking:
         assert outputs["response"] == {"result": "test"}
 
 
+class TestAIConversationBlockValidation:
+    """Test that AIConversationBlock validates inputs before calling the LLM."""
+
+    @pytest.mark.asyncio
+    async def test_empty_messages_and_empty_prompt_raises_error(self):
+        """Empty messages with no prompt should raise ValueError, not a cryptic API error."""
+        block = llm.AIConversationBlock()
+
+        input_data = llm.AIConversationBlock.Input(
+            messages=[],
+            prompt="",
+            model=llm.DEFAULT_LLM_MODEL,
+            credentials=_TEST_AI_CREDENTIALS,
+        )
+
+        with pytest.raises(ValueError, match="no messages and no prompt"):
+            async for _ in block.run(input_data, credentials=llm.TEST_CREDENTIALS):
+                pass
+
+    @pytest.mark.asyncio
+    async def test_empty_messages_with_prompt_succeeds(self):
+        """Empty messages but a non-empty prompt should proceed without error."""
+        block = llm.AIConversationBlock()
+
+        async def mock_llm_call(input_data, credentials):
+            return {"response": "OK"}
+
+        with patch.object(block, "llm_call", new=AsyncMock(side_effect=mock_llm_call)):
+            input_data = llm.AIConversationBlock.Input(
+                messages=[],
+                prompt="Hello, how are you?",
+                model=llm.DEFAULT_LLM_MODEL,
+                credentials=_TEST_AI_CREDENTIALS,
+            )
+
+            outputs = {}
+            async for name, data in block.run(
+                input_data, credentials=llm.TEST_CREDENTIALS
+            ):
+                outputs[name] = data
+
+        assert outputs["response"] == "OK"
+
+    @pytest.mark.asyncio
+    async def test_nonempty_messages_with_empty_prompt_succeeds(self):
+        """Non-empty messages with no prompt should proceed without error."""
+        block = llm.AIConversationBlock()
+
+        async def mock_llm_call(input_data, credentials):
+            return {"response": "response from conversation"}
+
+        with patch.object(block, "llm_call", new=AsyncMock(side_effect=mock_llm_call)):
+            input_data = llm.AIConversationBlock.Input(
+                messages=[{"role": "user", "content": "Hello"}],
+                prompt="",
+                model=llm.DEFAULT_LLM_MODEL,
+                credentials=_TEST_AI_CREDENTIALS,
+            )
+
+            outputs = {}
+            async for name, data in block.run(
+                input_data, credentials=llm.TEST_CREDENTIALS
+            ):
+                outputs[name] = data
+
+        assert outputs["response"] == "response from conversation"
+
+    @pytest.mark.asyncio
+    async def test_messages_with_empty_content_raises_error(self):
+        """Messages with empty content strings should be treated as no messages."""
+        block = llm.AIConversationBlock()
+
+        input_data = llm.AIConversationBlock.Input(
+            messages=[{"role": "user", "content": ""}],
+            prompt="",
+            model=llm.DEFAULT_LLM_MODEL,
+            credentials=_TEST_AI_CREDENTIALS,
+        )
+
+        with pytest.raises(ValueError, match="no messages and no prompt"):
+            async for _ in block.run(input_data, credentials=llm.TEST_CREDENTIALS):
+                pass
+
+    @pytest.mark.asyncio
+    async def test_messages_with_whitespace_content_raises_error(self):
+        """Messages with whitespace-only content should be treated as no messages."""
+        block = llm.AIConversationBlock()
+
+        input_data = llm.AIConversationBlock.Input(
+            messages=[{"role": "user", "content": "   "}],
+            prompt="",
+            model=llm.DEFAULT_LLM_MODEL,
+            credentials=_TEST_AI_CREDENTIALS,
+        )
+
+        with pytest.raises(ValueError, match="no messages and no prompt"):
+            async for _ in block.run(input_data, credentials=llm.TEST_CREDENTIALS):
+                pass
+
+    @pytest.mark.asyncio
+    async def test_messages_with_none_entry_raises_error(self):
+        """Messages list containing None should be treated as no messages."""
+        block = llm.AIConversationBlock()
+
+        input_data = llm.AIConversationBlock.Input(
+            messages=[None],
+            prompt="",
+            model=llm.DEFAULT_LLM_MODEL,
+            credentials=_TEST_AI_CREDENTIALS,
+        )
+
+        with pytest.raises(ValueError, match="no messages and no prompt"):
+            async for _ in block.run(input_data, credentials=llm.TEST_CREDENTIALS):
+                pass
+
+    @pytest.mark.asyncio
+    async def test_messages_with_empty_dict_raises_error(self):
+        """Messages list containing empty dict should be treated as no messages."""
+        block = llm.AIConversationBlock()
+
+        input_data = llm.AIConversationBlock.Input(
+            messages=[{}],
+            prompt="",
+            model=llm.DEFAULT_LLM_MODEL,
+            credentials=_TEST_AI_CREDENTIALS,
+        )
+
+        with pytest.raises(ValueError, match="no messages and no prompt"):
+            async for _ in block.run(input_data, credentials=llm.TEST_CREDENTIALS):
+                pass
+
+    @pytest.mark.asyncio
+    async def test_messages_with_none_content_raises_error(self):
+        """Messages with content=None should not crash with AttributeError."""
+        block = llm.AIConversationBlock()
+
+        input_data = llm.AIConversationBlock.Input(
+            messages=[{"role": "user", "content": None}],
+            prompt="",
+            model=llm.DEFAULT_LLM_MODEL,
+            credentials=_TEST_AI_CREDENTIALS,
+        )
+
+        with pytest.raises(ValueError, match="no messages and no prompt"):
+            async for _ in block.run(input_data, credentials=llm.TEST_CREDENTIALS):
+                pass
+
+
 class TestAITextSummarizerValidation:
     """Test that AITextSummarizerBlock validates LLM responses are strings."""