### What problem does this PR solve?
Fixes#10933
This PR fixes a `TypeError` in the Gemini model provider where the
`total_token_count_from_response()` function could receive a `None`
response object, causing the error:
TypeError: argument of type 'NoneType' is not iterable
**Root Cause:**
The function attempted to use the `in` operator to check dictionary keys
(lines 48, 54, 60) without first validating that `resp` was not `None`.
When Gemini's `chat_streamly()` method returns `None`, this triggers the
error.
**Solution:**
1. Added a null check at the beginning of the function to return `0` if
`resp is None`
2. Added `isinstance(resp, dict)` checks before all `in` operations to
ensure type safety
3. This defensive programming approach prevents the TypeError while
maintaining backward compatibility
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### Changes Made
**File:** `rag/utils/__init__.py`
- Line 36-38: Added `if resp is None: return 0` check
- Line 52: Added `isinstance(resp, dict)` before `'usage' in resp`
- Line 58: Added `isinstance(resp, dict)` before `'usage' in resp`
- Line 64: Added `isinstance(resp, dict)` before `'meta' in resp`
### Testing
- [x] Code compiles without errors
- [x] Follows existing code style and conventions
- [x] Change is minimal and focused on the specific issue
### Additional Notes
This fix ensures robust handling of various response types from LLM
providers, particularly Gemini, w
---------
Signed-off-by: Zhang Zhefang <zhangzhefang@example.com>
