fix(proxy/gemini): tolerate malformed parts on the compression path (#2486)

## Description

Three helpers on the Gemini compression path read a content entry's
`parts` and iterate it without type guards:

```python
# _has_non_text_parts
parts = content.get("parts", [])
for part in parts: ...
# _rebuild_gemini_contents
had_text = any("text" in p for p in content.get("parts", []))
# _gemini_contents_to_messages
parts = content.get("parts", [])
text_parts = [p.get("text", "") for p in parts if "text" in p]
```

`parts` is request-controlled and `.get("parts", [])` only falls back
when the key is absent, so:

- a present-but-null `parts` returns `None`, and `for part in None` /
`any(... for p in None)` raises `TypeError`;
- a list carrying a bare string (a client that treats `parts` as a
string array) makes `p.get("text", "")` raise `AttributeError`, while
`"text" in p` silently does substring matching first;
- a null element in the list crashes the same way.

Any of these 500s the request on the compression path, on data that
parsed as valid JSON.

## Fix

Route all three helpers through a shared `_dict_parts(content)` that
returns the dict entries of `parts`, coercing a non-dict content or a
non-list `parts` to an empty list and dropping non-dict elements.
`_gemini_contents_to_messages` also reads `role` defensively for a
non-dict content entry. Conversion now degrades gracefully (the
malformed part contributes nothing) instead of raising. Well-formed
requests are unchanged.

## Type of Change

- [x] Bug fix (non-breaking change that fixes an issue)
- [ ] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Performance improvement
- [ ] Code refactoring (no functional changes)

## Changes Made

- `headroom/proxy/handlers/gemini.py`: add `_dict_parts`; use it in
`_has_non_text_parts`, `_rebuild_gemini_contents`, and
`_gemini_contents_to_messages`; read `role` defensively for a non-dict
content entry.
- `tests/test_gemini_function_response_waste.py`: regressions for null
`parts`, bare-string part elements, a null part element,
`_has_non_text_parts` on malformed parts, and a non-dict content entry.

## Testing

- [x] Unit tests pass (`pytest`)
- [x] Linting passes (`ruff check .`)
- [x] Type checking passes (`mypy headroom`)
- [x] New tests added for new functionality
- [ ] Manual testing performed

### Test Output

```text
$ python -m pytest tests/test_gemini_function_response_waste.py -q
16 passed

# with the fix reverted, the new malformed-parts tests fail with
# TypeError: 'NoneType' object is not iterable  (and AttributeError on string parts)

$ uvx ruff@0.15.17 check headroom/proxy/handlers/gemini.py tests/test_gemini_function_response_waste.py
All checks passed!
$ uvx mypy@1.20.2 --ignore-missing-imports headroom/proxy/handlers/gemini.py
Success: no issues found in 1 source file
```

## Real Behavior Proof

- Environment: Windows 11, Python 3.12, project venv (`uv sync --extra
proxy`), `uvx ruff@0.15.17` / `uvx mypy@1.20.2`, pytest in the venv.
- Exact command / steps: built a real `HeadroomProxy` and called
`_gemini_contents_to_messages` / `_has_non_text_parts` with contents
carrying `parts: null`, `parts: ["bare string", {text}]`, `parts: [null,
{text}]`, and a non-dict content entry; then reverted `gemini.py` and
re-ran.
- Observed result: with the fix each malformed shape converts without
raising and the valid text part is still emitted (`[{"role": "user",
"content": "kept"}]`); with the fix reverted the null-`parts` and
null-element cases raise `TypeError: 'NoneType' object is not iterable`
and the string-element case raises `AttributeError: 'str' object has no
attribute 'get'`. Ran against the actual module via
`tests/test_gemini_function_response_waste.py`.
- Not tested: a live Gemini request with malformed `parts` routed
through the full proxy compression pipeline end to end.

## Review Readiness

- [x] I have performed a self-review
- [x] This PR is ready for human review

## Checklist

- [x] My code follows the project's style guidelines
- [x] I have performed a self-review of my code
- [x] I have commented my code, particularly in hard-to-understand areas
- [ ] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [ ] I have updated the CHANGELOG.md if applicable
This commit is contained in:
Abhay Singh 2026-07-22 18:37:15 +05:30 committed by GitHub
parent f0975b8de0
commit 07cf547607
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 63 additions and 7 deletions

View file

@ -56,6 +56,24 @@ class GeminiHandlerMixin:
return ANTIGRAVITY_DAILY_API_URL return ANTIGRAVITY_DAILY_API_URL
return getattr(self, "CLOUDCODE_API_URL", DEFAULT_CLOUDCODE_API_URL).rstrip("/") return getattr(self, "CLOUDCODE_API_URL", DEFAULT_CLOUDCODE_API_URL).rstrip("/")
@staticmethod
def _dict_parts(content: Any) -> list[dict]:
"""Return the dict entries of a Gemini content's ``parts``.
``parts`` is request-controlled. ``.get("parts", [])`` only falls back
when the key is absent, so a present-but-null ``parts`` returns ``None``
(crashing ``for part in parts``), and a list carrying a bare string
which a client that treats ``parts`` as a string array can send
crashes ``part.get(...)`` / ``key in part`` semantics downstream.
Coerce to a clean list of dict parts so every caller can iterate safely.
"""
if not isinstance(content, dict):
return []
parts = content.get("parts")
if not isinstance(parts, list):
return []
return [part for part in parts if isinstance(part, dict)]
def _has_non_text_parts(self, content: dict) -> bool: def _has_non_text_parts(self, content: dict) -> bool:
"""Check if a Gemini content entry has non-text parts. """Check if a Gemini content entry has non-text parts.
@ -73,8 +91,7 @@ class GeminiHandlerMixin:
Returns: Returns:
True if any part contains non-text data. True if any part contains non-text data.
""" """
parts = content.get("parts", []) for part in self._dict_parts(content):
for part in parts:
if any( if any(
key in part key in part
for key in ( for key in (
@ -110,7 +127,7 @@ class GeminiHandlerMixin:
opt_iter = iter(optimized_contents) opt_iter = iter(optimized_contents)
result: list[dict] = [] result: list[dict] = []
for idx, content in enumerate(original_contents): for idx, content in enumerate(original_contents):
had_text = any("text" in p for p in content.get("parts", [])) had_text = any("text" in p for p in self._dict_parts(content))
if idx in preserved_indices: if idx in preserved_indices:
result.append(preserved_contents[idx]) result.append(preserved_contents[idx])
if had_text: if had_text:
@ -155,8 +172,8 @@ class GeminiHandlerMixin:
# Add system instruction as system message # Add system instruction as system message
if system_instruction: if system_instruction:
parts = system_instruction.get("parts", []) sys_parts = self._dict_parts(system_instruction)
text_parts = [p.get("text", "") for p in parts if "text" in p] text_parts = [p.get("text", "") for p in sys_parts if "text" in p]
if text_parts: if text_parts:
messages.append({"role": "system", "content": "\n".join(text_parts)}) messages.append({"role": "system", "content": "\n".join(text_parts)})
@ -166,12 +183,12 @@ class GeminiHandlerMixin:
if self._has_non_text_parts(content): if self._has_non_text_parts(content):
preserved_indices.add(idx) preserved_indices.add(idx)
role = content.get("role", "user") role = content.get("role", "user") if isinstance(content, dict) else "user"
# Map Gemini roles to OpenAI roles # Map Gemini roles to OpenAI roles
if role == "model": if role == "model":
role = "assistant" role = "assistant"
parts = content.get("parts", []) parts = self._dict_parts(content)
text_parts = [p.get("text", "") for p in parts if "text" in p] text_parts = [p.get("text", "") for p in parts if "text" in p]
if text_parts: if text_parts:

View file

@ -124,6 +124,45 @@ class TestFunctionResponseConversion:
assert "loop" in text assert "loop" in text
class TestMalformedPartsToleration:
"""A request-controlled `parts` that is null or carries non-dict elements
must not crash the compression-path conversion helpers."""
def test_null_parts_does_not_crash(self, proxy):
contents = [
{"role": "user", "parts": None},
{"role": "user", "parts": [{"text": "real"}]},
]
messages, preserved = proxy._gemini_contents_to_messages(contents)
assert messages == [{"role": "user", "content": "real"}]
assert preserved == set()
def test_string_part_elements_do_not_crash(self, proxy):
# A client that treats `parts` as a string array sends bare strings;
# they carry no `text` key, so they contribute nothing but must not
# crash `.get`.
contents = [{"role": "user", "parts": ["bare string", {"text": "kept"}]}]
messages, _ = proxy._gemini_contents_to_messages(contents)
assert messages == [{"role": "user", "content": "kept"}]
def test_null_part_element_is_skipped(self, proxy):
contents = [{"role": "user", "parts": [None, {"text": "kept"}]}]
messages, _ = proxy._gemini_contents_to_messages(contents)
assert messages == [{"role": "user", "content": "kept"}]
def test_has_non_text_parts_tolerates_null_parts(self, proxy):
assert proxy._has_non_text_parts({"role": "user", "parts": None}) is False
assert proxy._has_non_text_parts({"role": "user", "parts": ["str"]}) is False
assert proxy._has_non_text_parts({"parts": [{"inlineData": {"data": "x"}}]}) is True
def test_non_dict_content_entry_is_tolerated(self, proxy):
# A non-dict entry in contents[] is treated as an empty user turn rather
# than crashing content.get / the parts iteration.
contents = ["not a dict", {"role": "user", "parts": [{"text": "kept"}]}]
messages, _ = proxy._gemini_contents_to_messages(contents)
assert messages == [{"role": "user", "content": "kept"}]
class TestFunctionResponseWasteParsing: class TestFunctionResponseWasteParsing:
def test_function_response_payload_reaches_waste_signals(self, proxy, tokenizer): def test_function_response_payload_reaches_waste_signals(self, proxy, tokenizer):
contents = [ contents = [