mirror of
https://github.com/headroomlabs-ai/headroom.git
synced 2026-08-27 14:17:10 -04:00
## Description Anthropic tool sorting was rewriting `tools` lists even when canonical order was already present, which forced a mutation path that bypassed byte-faithful forwarding and reduced prefix-cache hit stability on repeated `/v1/messages` turns. Closes #1042 ## 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 - changed Anthropic tool canonicalization so already-canonical tool arrays are not rewritten in both single-request and batch paths - preserved byte-faithful forwarding for no-op single-request canonical tool-order requests by avoiding unnecessary `body["tools"]` reassignment - kept canonicalization behavior intact for out-of-order tool arrays - added one true regression proof for the PRE_SEND empty-tools path, plus forward-coverage tests for canonical no-op and real-sort-mutation request bodies in `test_proxy_byte_faithful_forwarding.py` - updated `CHANGELOG.md` to document the prefix-cache fix ## Testing - [x] Unit tests pass (`uv run pytest tests/test_proxy_handler_helpers.py tests/test_proxy_byte_faithful_forwarding.py -x -v`) - [x] Linting passes (`uv run ruff check headroom/proxy/handlers/anthropic.py tests/test_proxy_handler_helpers.py tests/test_proxy_byte_faithful_forwarding.py`) - [ ] Type checking passes (`uv run mypy headroom`) or explain N/A truthfully - [x] New tests added for new functionality when applicable - [ ] Manual testing performed ### Test Output ```text uv run pytest tests/test_proxy_handler_helpers.py tests/test_proxy_byte_faithful_forwarding.py -x -v 56 passed in 12.42s uv run ruff check headroom/proxy/handlers/anthropic.py tests/test_proxy_handler_helpers.py tests/test_proxy_byte_faithful_forwarding.py All checks passed! uv run ruff format headroom/proxy/handlers/anthropic.py tests/test_proxy_handler_helpers.py tests/test_proxy_byte_faithful_forwarding.py --check 3 files already formatted ``` ## Real Behavior Proof - Environment: Windows, local proxy test environment, Anthropic request-forwarding path - Exact command / steps: post `/v1/messages` requests with canonical tool order and then intentionally unsorted tool order through the `TestClient` path with the no-optimize app variant - Observed result: the PRE_SEND empty-tools runtime path now keeps `body_mutated` false where base would mark the request mutated, canonical-order tool payloads still preserve exact inbound bytes end-to-end, and unsorted tool-order payloads are still canonicalized as expected. - Batch coverage: no dedicated runtime batch regression test was added; batch no-op/mutation correctness is addressed through the same compare-and-assign pattern on both batch canonical-sort call sites. - Not tested: full-suite behavior outside the touched Anthropic forwarding regression surface ## 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 - [x] 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 - [ ] New and existing unit tests pass locally with my changes - [x] I have updated the CHANGELOG.md if applicable ## Screenshots (if applicable) Not applicable. ## Additional Notes The important boundary is not whether tool arrays can be sorted. The real contract is whether a no-op canonicalization should count as a mutation. This change keeps canonicalization for real reorder cases and restores byte-faithful forwarding for already-canonical requests.
166 lines
6.9 KiB
Python
166 lines
6.9 KiB
Python
"""Issue #728: proxy must not inject ``tools: []`` when the client omitted the tools field.
|
|
|
|
vLLM-based providers (Venice.ai, etc.) reject requests containing an empty ``tools``
|
|
array. The bug: ``apply_session_sticky_ccr_tool`` / ``apply_session_sticky_memory_tools``
|
|
always return a list (empty when no tools exist and none were injected), and the
|
|
old handler guard ``if tools is not None`` evaluated True for ``[]``, causing
|
|
``body["tools"] = []`` to be sent upstream unconditionally.
|
|
|
|
Fix: the guard was changed to ``if tools or _original_tools is not None`` in both
|
|
the OpenAI and Anthropic handlers so that an empty result list only reaches the
|
|
outgoing body when the original request already carried a ``tools`` field.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import pytest
|
|
|
|
from headroom.ccr.tool_injection import CCR_TOOL_NAME
|
|
from headroom.proxy.handlers.anthropic import AnthropicHandlerMixin
|
|
from headroom.proxy.helpers import (
|
|
_reset_session_ccr_tracker_for_test,
|
|
apply_session_sticky_ccr_tool,
|
|
)
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def _reset_tracker():
|
|
_reset_session_ccr_tracker_for_test()
|
|
yield
|
|
_reset_session_ccr_tracker_for_test()
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Guard-condition logic (the actual fix)
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
def _should_set_body_tools(tools: list | None, original_tools: list | None) -> bool:
|
|
"""Mirror the fixed handler condition: ``if tools or _original_tools is not None``."""
|
|
return bool(tools or original_tools is not None)
|
|
|
|
|
|
def _sort_tools(tools: list | None) -> list | None:
|
|
return AnthropicHandlerMixin._sort_tools_deterministically(tools)
|
|
|
|
|
|
def _should_set_body_tools_after_sort(tools: list | None, original_tools: list | None) -> bool:
|
|
"""Mirror fixed logic when candidate tools may already be sorted."""
|
|
if not _should_set_body_tools(tools, original_tools):
|
|
return False
|
|
sorted_tools = _sort_tools(tools)
|
|
if sorted_tools != tools:
|
|
tools = sorted_tools
|
|
return tools != original_tools
|
|
|
|
|
|
def _legacy_should_set_body_tools_after_sort(
|
|
tools: list | None, original_tools: list | None
|
|
) -> bool:
|
|
"""Older comparator that only wrote when sorting reordered."""
|
|
if not _should_set_body_tools(tools, original_tools):
|
|
return False
|
|
return _sort_tools(tools) != tools
|
|
|
|
|
|
class TestHandlerGuardCondition:
|
|
"""Verify the guard condition that decides whether to write body['tools']."""
|
|
|
|
def test_no_tools_no_injection_does_not_inject(self):
|
|
"""Client sent no tools and nothing was injected → body must stay tools-free."""
|
|
original_tools = None # client did not send tools
|
|
tools_after_helpers = [] # helpers return [] when existing_tools=None and no inject
|
|
|
|
assert not _should_set_body_tools(tools_after_helpers, original_tools), (
|
|
"Empty tools from helpers + no original tools must NOT write body['tools']"
|
|
)
|
|
|
|
def test_client_sent_empty_tools_is_preserved(self):
|
|
"""Client explicitly sent ``tools: []`` → preserve that field (their choice)."""
|
|
original_tools = [] # client explicitly sent an empty array
|
|
tools_after_helpers = [] # nothing injected
|
|
|
|
assert _should_set_body_tools(tools_after_helpers, original_tools), (
|
|
"Client's explicit tools:[] should be preserved in body"
|
|
)
|
|
|
|
def test_ccr_injection_sets_body_tools(self):
|
|
"""When CCR injects a tool into an originally tool-free request → set body."""
|
|
original_tools = None
|
|
from headroom.ccr.tool_injection import create_ccr_tool_definition
|
|
|
|
tools_after_helpers = [create_ccr_tool_definition("openai")]
|
|
|
|
assert _should_set_body_tools(tools_after_helpers, original_tools), (
|
|
"Injected CCR tool must reach body['tools']"
|
|
)
|
|
|
|
def test_client_tools_always_set(self):
|
|
"""Client provided real tools → always write body['tools']."""
|
|
original_tools = [{"type": "function", "function": {"name": "my_tool"}}]
|
|
tools_after_helpers = original_tools[:]
|
|
|
|
assert _should_set_body_tools(tools_after_helpers, original_tools)
|
|
|
|
def test_sorted_replacement_reaches_body(self):
|
|
"""A sorted replacement that differs from payload still needs to be written."""
|
|
original_tools = [{"name": "zeta"}, {"name": "alpha"}]
|
|
tools_after_helpers = [{"name": "alpha"}, {"name": "zeta"}]
|
|
|
|
assert not _legacy_should_set_body_tools_after_sort(tools_after_helpers, original_tools)
|
|
assert _should_set_body_tools_after_sort(tools_after_helpers, original_tools)
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# apply_session_sticky_ccr_tool behaviour with no existing tools
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
class TestCCRHelperNoToolsNoCompression:
|
|
"""Verify what the helper returns when there are no tools and no CCR happened."""
|
|
|
|
def test_returns_empty_list_and_false_when_no_session_ccr(self):
|
|
"""No session CCR history + no compression this turn → ([], False)."""
|
|
tools_out, was_injected = apply_session_sticky_ccr_tool(
|
|
provider="openai",
|
|
session_id="fresh-session-728",
|
|
request_id="req-1",
|
|
existing_tools=None,
|
|
has_compressed_content_this_turn=False,
|
|
)
|
|
assert was_injected is False
|
|
# Helper still returns [] — the guard in the handler is what prevents injection.
|
|
assert tools_out == []
|
|
|
|
def test_returns_tool_list_when_compression_occurred(self):
|
|
"""First turn with CCR → helper returns the CCR tool definition."""
|
|
tools_out, was_injected = apply_session_sticky_ccr_tool(
|
|
provider="openai",
|
|
session_id="ccr-session-728",
|
|
request_id="req-1",
|
|
existing_tools=None,
|
|
has_compressed_content_this_turn=True,
|
|
)
|
|
assert was_injected is True
|
|
tool_names = [t.get("function", {}).get("name") or t.get("name") for t in tools_out]
|
|
assert CCR_TOOL_NAME in tool_names
|
|
|
|
def test_no_double_injection_when_client_pre_registered_ccr_tool(self):
|
|
"""If the client already included the CCR tool, the helper must not duplicate it."""
|
|
from headroom.ccr.tool_injection import create_ccr_tool_definition
|
|
|
|
existing = [create_ccr_tool_definition("openai")]
|
|
tools_out, was_injected = apply_session_sticky_ccr_tool(
|
|
provider="openai",
|
|
session_id="pre-reg-session-728",
|
|
request_id="req-1",
|
|
existing_tools=existing,
|
|
has_compressed_content_this_turn=True,
|
|
)
|
|
assert was_injected is False
|
|
ccr_count = sum(
|
|
1
|
|
for t in tools_out
|
|
if (t.get("function", {}).get("name") or t.get("name")) == CCR_TOOL_NAME
|
|
)
|
|
assert ccr_count == 1, "CCR tool should appear exactly once"
|