mirror of
https://github.com/headroomlabs-ai/headroom.git
synced 2026-08-27 14:17:10 -04:00
ce8ce8313f
## Description Fixes #2509. CCR marker resolution today depends entirely on the model calling `headroom_retrieve` back a tool-call round-trip. Callers with no such round-trip (e.g. Headroom running as a LiteLLM guardrail/proxy hop, per the issue's repro) never get an offered path to redeem a marker, so raw `<<ccr:HASH,type,size>>` text leaks straight to the agent. This adds an explicit, opt-in fallback: `--ccr-inline-resolve` / `HEADROOM_CCR_INLINE_RESOLVE`. When set, the proxy resolves markers directly from the compression store on the response path instead of waiting for a tool call. Off by default, guessing "this caller can't use tools" is fragile, so operators opt in explicitly for guardrail/proxy deployments. ## Type of Change - [x] Bug fix (non-breaking change which fixes an issue) - [ ] New feature (non-breaking change which adds functionality) - [ ] Breaking change - [ ] Documentation update ## Changes Made - `headroom/ccr/marker_resolution.py` (new): `resolve_markers_in_text` / `resolve_markers_in_response` regex-match `<<ccr:HASH,...>>`, look up the hash in `CompressionStore`, splice the original content back in. A miss (expired/evicted hash) leaves the marker in place with the miss reason appended, since there's no tool-call round-trip to report it back to the model. - `headroom/proxy/models.py`: `ProxyConfig.ccr_resolve_markers_inline: bool = False`. - `headroom/cli/proxy.py`: `--ccr-inline-resolve` flag / `HEADROOM_CCR_INLINE_RESOLVE` env, wired into `ProxyConfig`. - `headroom/proxy/handlers/anthropic.py`, `headroom/proxy/handlers/openai.py`: call `resolve_markers_in_response` on the finalized response JSON, right after existing CCR tool-call handling, at all three non-streaming response sites (Anthropic Messages, OpenAI Chat Completions backend path, OpenAI Responses API). Streaming responses are out of scope for this PR, tracked as follow-up, noted in the module docstring's scope. ## Testing - [x] Added new tests - [x] All tests pass locally ``` $ python -m pytest tests/test_ccr_marker_resolution.py -q ============================= test session starts ============================= collected 6 items tests\test_ccr_marker_resolution.py ...... [100%] ============================== 6 passed in 0.45s ============================== $ python -m pytest tests/test_ccr.py tests/test_ccr_response_handler.py tests/test_ccr_response_handler_extra.py tests/test_ccr_response_handler_openai_responses.py tests/test_proxy/test_openai_responses_ccr.py tests/test_proxy/test_anthropic_ccr_raise.py -q ======================= 83 passed, 1 warning in 34.50s ======================== ``` ## Real Behavior Proof - Environment: Windows 11, Python 3.13.11, local headroom repo (`G:\Programmi Aggiuntivi\headroom`) - Exact command / steps: `python -m pytest tests/test_ccr_marker_resolution.py tests/test_ccr.py tests/test_ccr_response_handler.py tests/test_ccr_response_handler_extra.py tests/test_ccr_response_handler_openai_responses.py tests/test_proxy/test_openai_responses_ccr.py tests/test_proxy/test_anthropic_ccr_raise.py -q` - Observed result: 89 passed, 0 failed (6 new + 83 existing CCR tests, no regressions). `ruff check`, `ruff format --check`, and `mypy --ignore-missing-imports` all clean on every changed/new file. - Not tested: the actual Docker Compose / LiteLLM guardrail deployment from the issue's repro steps (no such environment available here); streaming response paths (out of scope, see Changes Made). ## Review Readiness - [x] I have performed a self-review - [x] This PR is ready for human review --------- Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
99 lines
2.7 KiB
Python
99 lines
2.7 KiB
Python
"""Tests for inline <<ccr:...>> marker resolution (issue #2509)."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
|
|
import pytest
|
|
|
|
from headroom.cache.compression_store import get_compression_store, reset_compression_store
|
|
from headroom.ccr.marker_resolution import (
|
|
resolve_markers_in_response,
|
|
resolve_markers_in_text,
|
|
)
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def reset_store():
|
|
reset_compression_store()
|
|
yield
|
|
reset_compression_store()
|
|
|
|
|
|
def _store_entry(original: str) -> str:
|
|
store = get_compression_store()
|
|
return store.store(
|
|
original=original,
|
|
compressed="[]",
|
|
original_item_count=1,
|
|
compressed_item_count=0,
|
|
)
|
|
|
|
|
|
def test_resolve_markers_in_text_no_marker_is_noop():
|
|
assert resolve_markers_in_text("plain text, no markers here") == "plain text, no markers here"
|
|
|
|
|
|
def test_resolve_markers_in_text_replaces_hit():
|
|
hash_key = _store_entry("the original uncompressed content")
|
|
text = f"before <<ccr:{hash_key},string,23.6KB>> after"
|
|
|
|
resolved = resolve_markers_in_text(text)
|
|
|
|
assert resolved == "before the original uncompressed content after"
|
|
|
|
|
|
def test_resolve_markers_in_text_replaces_multiple_hits():
|
|
hash_a = _store_entry("AAA")
|
|
hash_b = _store_entry("BBB")
|
|
text = f"<<ccr:{hash_a},string,1KB>> and <<ccr:{hash_b},string,1KB>>"
|
|
|
|
resolved = resolve_markers_in_text(text)
|
|
|
|
assert resolved == "AAA and BBB"
|
|
|
|
|
|
def test_resolve_markers_in_text_json_array_original_content():
|
|
store = get_compression_store()
|
|
hash_key = store.store(
|
|
original=json.dumps([1, 2, 3]),
|
|
compressed="[]",
|
|
original_item_count=3,
|
|
compressed_item_count=0,
|
|
)
|
|
text = f"<<ccr:{hash_key},array,3>>"
|
|
|
|
resolved = resolve_markers_in_text(text)
|
|
|
|
assert json.loads(resolved) == [1, 2, 3]
|
|
|
|
|
|
def test_resolve_markers_in_text_miss_leaves_marker_with_reason():
|
|
text = "<<ccr:deadbeefdeadbeef,string,1KB>>"
|
|
|
|
resolved = resolve_markers_in_text(text)
|
|
|
|
assert text in resolved
|
|
assert "[unresolved:" in resolved
|
|
|
|
|
|
def test_resolve_markers_in_response_walks_nested_structure():
|
|
hash_key = _store_entry("full tool output")
|
|
response = {
|
|
"choices": [
|
|
{
|
|
"message": {
|
|
"role": "assistant",
|
|
"content": f"here it is: <<ccr:{hash_key},string,1KB>>",
|
|
}
|
|
}
|
|
],
|
|
"unrelated": 42,
|
|
"nested": {"list": ["a", f"<<ccr:{hash_key},string,1KB>>", "c"]},
|
|
}
|
|
|
|
resolved = resolve_markers_in_response(response)
|
|
|
|
assert resolved["choices"][0]["message"]["content"] == "here it is: full tool output"
|
|
assert resolved["nested"]["list"] == ["a", "full tool output", "c"]
|
|
assert resolved["unrelated"] == 42
|