Skip to content

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

fix(anthropic): stop the spurious compaction warning and drop dead handler code (#3678)

trs-806e712672cb5c
diff --git a/headroom/proxy/handlers/anthropic.py b/headroom/proxy/handlers/anthropic.py
index 7aeb457dd..b1f0a8869 100644
--- a/headroom/proxy/handlers/anthropic.py
+++ b/headroom/proxy/handlers/anthropic.py
@@ -1032,7 +1032,6 @@ class AnthropicHandlerMixin:
# Check request body size
content_length = request.headers.get("content-length")
if content_length and int(content_length) > MAX_REQUEST_BODY_SIZE:
- await _finalize_pre_upstream()
return JSONResponse(
status_code=413,
content={
@@ -1055,7 +1054,6 @@ class AnthropicHandlerMixin:
async with stage_timer.measure("read_request_json"):
body, original_body_bytes = await read_request_json_with_bytes(request)
except (json.JSONDecodeError, ValueError) as e:
- await _finalize_pre_upstream()
return JSONResponse(
status_code=400,
content={
@@ -1132,7 +1130,6 @@ class AnthropicHandlerMixin:
# Validate message array size
if len(messages) > MAX_MESSAGE_ARRAY_LENGTH:
- await _finalize_pre_upstream()
return JSONResponse(
status_code=400,
content={
@@ -1424,9 +1421,6 @@ class AnthropicHandlerMixin:
f"hits={cached.hit_count}"
)
- # Unit 4: release the pre-upstream semaphore on cache
- # hit — no upstream call will happen.
- await _finalize_pre_upstream()
return Response(
content=cached.response_body,
headers=response_headers,
@@ -1455,9 +1449,6 @@ class AnthropicHandlerMixin:
if hasattr(e, "reason"):
from fastapi.responses import JSONResponse as _JSONResp
- # Unit 4: release the pre-upstream semaphore on
- # security block — no upstream call will happen.
- await _finalize_pre_upstream()
return _JSONResp(
status_code=403,
content={
@@ -2969,15 +2960,15 @@ class AnthropicHandlerMixin:
model=model,
request_id=request_id,
)
- if _sys_modified:
- transforms_applied.append("anthropic:system_prompt_compaction")
- logger.debug(
- "[%s] system prompt compaction: %d -> %d bytes (%.0f%% saved)",
- request_id,
- _sys_before,
- _sys_after,
- (1 - _sys_after / max(_sys_before, 1)) * 100,
- )
+ if _sys_modified:
+ transforms_applied.append("anthropic:system_prompt_compaction")
+ logger.debug(
+ "[%s] system prompt compaction: %d -> %d bytes (%.0f%% saved)",
+ request_id,
+ _sys_before,
+ _sys_after,
+ (1 - _sys_after / max(_sys_before, 1)) * 100,
+ )
except Exception as _sys_compaction_exc:
_sys_modified = False
logger.warning(
@@ -3683,8 +3674,6 @@ class AnthropicHandlerMixin:
)
except Exception as e:
logger.error(f"[{request_id}] Bedrock backend error: {e}")
- # Unit 4: release the pre-upstream semaphore on error.
- await _finalize_pre_upstream()
return JSONResponse(
status_code=500,
content={
@@ -5036,12 +5025,6 @@ class AnthropicHandlerMixin:
# Log full error details internally for debugging
logger.error(f"[{request_id}] Request failed: {type(e).__name__}: {e}")
- # Try fallback if enabled
- if self.config.fallback_enabled and self.config.fallback_provider == "openai":
- logger.info(f"[{request_id}] Attempting fallback to OpenAI")
- # Convert to OpenAI format and retry
- # (simplified - would need message format conversion)
-
# Return sanitized error message to client (don't expose internal details)
return JSONResponse(
status_code=502,
diff --git a/headroom/proxy/models.py b/headroom/proxy/models.py
index 4aa7163c1..5957f5773 100644
--- a/headroom/proxy/models.py
+++ b/headroom/proxy/models.py
@@ -371,10 +371,6 @@ class ProxyConfig:
# (repeatable); env: HEADROOM_COMPRESSORS.
compressors: set[str] | None = None
- # Fallback
- fallback_enabled: bool = False
- fallback_provider: str | None = None
-
# Timeouts
request_timeout_seconds: int = 300
connect_timeout_seconds: int = 10
diff --git a/tests/test_anthropic_pre_upstream_backpressure.py b/tests/test_anthropic_pre_upstream_backpressure.py
index 6524c4af9..6447e65c2 100644
--- a/tests/test_anthropic_pre_upstream_backpressure.py
+++ b/tests/test_anthropic_pre_upstream_backpressure.py
@@ -39,6 +39,7 @@ from fastapi.testclient import TestClient
from headroom.cli.proxy import proxy as proxy_cli
from headroom.proxy.handlers.anthropic import AnthropicHandlerMixin
+from headroom.proxy.helpers import MAX_MESSAGE_ARRAY_LENGTH, MAX_REQUEST_BODY_SIZE
from headroom.proxy.models import CacheEntry, ProxyConfig
from headroom.proxy.server import HeadroomProxy, create_app
@@ -136,8 +137,6 @@ class _DummyAnthropicHandler(AnthropicHandlerMixin):
mode="token",
cache_enabled=False,
rate_limit_enabled=False,
- fallback_enabled=False,
- fallback_provider=None,
prefix_freeze_enabled=False,
memory_enabled=False,
)
@@ -291,8 +290,8 @@ class _DummyAnthropicHandler(AnthropicHandlerMixin):
)
-def _build_request(body: dict, headers: dict[str, str]) -> Request:
- payload = json.dumps(body).encode("utf-8")
+def _build_request(body: dict | bytes, headers: dict[str, str]) -> Request:
+ payload = body if isinstance(body, bytes) else json.dumps(body).encode("utf-8")
async def receive():
return {"type": "http.request", "body": payload, "more_body": False}
@@ -723,8 +722,6 @@ def test_compression_is_not_bypassed_when_gated(stage_log_capture):
mode="token",
cache_enabled=False,
rate_limit_enabled=False,
- fallback_enabled=False,
- fallback_provider=None,
prefix_freeze_enabled=False,
memory_enabled=False,
anthropic_pre_upstream_concurrency=2,
@@ -848,11 +845,12 @@ def test_auto_computed_default_on_this_machine():
# --------------------------------------------------------------------------- #
# Semaphore released on HTTPException / early-exit paths even with an #
-# already-held permit. Explicitly covers the 4 pre-upstream early exits: #
+# already-held permit. Explicitly covers the pre-upstream early exits: #
# - rate_limiter deny (429) #
# - cost_tracker block (429) #
# - security scan block (403) #
# - cache hit (200) #
+# - oversized body (413), invalid JSON (400), too many messages (400) #
# Each test holds 1 permit of a Semaphore(2) with a concurrent request, #
# then verifies the handler restores ``_value`` to the original after #
# the early return. #
@@ -910,7 +908,15 @@ class _CacheHit:
@pytest.mark.parametrize(
"scenario",
- ["rate_limiter", "cost_tracker", "security", "cache"],
+ [
+ "rate_limiter",
+ "cost_tracker",
+ "security",
+ "cache",
+ "oversized_body",
+ "invalid_json",
+ "too_many_messages",
+ ],
)
def test_early_exit_paths_release_semaphore_under_contention(scenario):
"""Hold one permit of a Semaphore(1) with a concurrent request, trigger
@@ -931,13 +937,19 @@ def test_early_exit_paths_release_semaphore_under_contention(scenario):
elif scenario == "cache":
handler.cache = _CacheHit()
- req = _build_request(
- {
- "model": "claude-3-5-sonnet-latest",
- "messages": [{"role": "user", "content": "hello"}],
- },
- {"authorization": "Bearer sk-ant-api-test"},
- )
+ body: dict | bytes = {
+ "model": "claude-3-5-sonnet-latest",
+ "messages": [{"role": "user", "content": "hello"}],
+ }
+ headers = {"authorization": "Bearer sk-ant-api-test"}
+ if scenario == "oversized_body":
+ headers["content-length"] = str(MAX_REQUEST_BODY_SIZE + 1)
+ elif scenario == "invalid_json":
+ body = b"{not json"
+ elif scenario == "too_many_messages":
+ body["messages"] = [{"role": "user", "content": "hi"}] * (MAX_MESSAGE_ARRAY_LENGTH + 1)
+ req = _build_request(body, headers)
+ expected_status = {"oversized_body": 413, "invalid_json": 400, "too_many_messages": 400}
# Drive several iterations to confirm each early-exit call fully
# releases the semaphore rather than leaking a permit AND that the
@@ -968,6 +980,8 @@ def test_early_exit_paths_release_semaphore_under_contention(scenario):
# security returns a JSONResponse; cache returns a Response.
assert raised is None, f"{scenario}: unexpected exception {raised!r}"
assert result is not None
+ if scenario in expected_status:
+ assert result.status_code == expected_status[scenario], result.body
assert sem._value == original_value, (
f"{scenario}: semaphore leak got={sem._value}, want={original_value}"
)
diff --git a/tests/test_anthropic_stage_timings.py b/tests/test_anthropic_stage_timings.py
index db8a2d3a1..58dfe7400 100644
--- a/tests/test_anthropic_stage_timings.py
+++ b/tests/test_anthropic_stage_timings.py
@@ -68,8 +68,6 @@ class _DummyAnthropicHandler(AnthropicHandlerMixin):
mode="token",
cache_enabled=False,
rate_limit_enabled=False,
- fallback_enabled=False,
- fallback_provider=None,
prefix_freeze_enabled=False,
memory_enabled=False,
)
diff --git a/tests/test_cache_mode_cold_start.py b/tests/test_cache_mode_cold_start.py
index 3acc75bcd..4b85c7479 100644
--- a/tests/test_cache_mode_cold_start.py
+++ b/tests/test_cache_mode_cold_start.py
@@ -107,8 +107,6 @@ class _DummyAnthropicHandler(AnthropicHandlerMixin):
mode="cache",
cache_enabled=False,
rate_limit_enabled=False,
- fallback_enabled=False,
- fallback_provider=None,
prefix_freeze_enabled=False,
memory_enabled=False,
)
diff --git a/tests/test_cold_start_fast_pass.py b/tests/test_cold_start_fast_pass.py
index a230facb4..242612cd1 100644
--- a/tests/test_cold_start_fast_pass.py
+++ b/tests/test_cold_start_fast_pass.py
@@ -105,8 +105,6 @@ class _DummyAnthropicHandler(AnthropicHandlerMixin):
mode="token",
cache_enabled=False,
rate_limit_enabled=False,
- fallback_enabled=False,
- fallback_provider=None,
prefix_freeze_enabled=False,
memory_enabled=False,
)
diff --git a/tests/test_system_compaction_handler.py b/tests/test_system_compaction_handler.py
new file mode 100644
index 000000000..724626872
--- /dev/null
+++ b/tests/test_system_compaction_handler.py
@@ -0,0 +1,81 @@
+"""The Anthropic handler's system-prompt compaction must tolerate a pipeline
+with no ContentRouter instead of logging a spurious failure, and must record
+the transform when a router does rewrite the prompt."""
+
+from __future__ import annotations
+
+import logging
+from typing import Any
+
+import pytest
+
+pytest.importorskip("fastapi")
+
+from fastapi.testclient import TestClient # noqa: E402
+
+from headroom.proxy.server import ProxyConfig, create_app # noqa: E402
+
+
+def _post_with_system_compaction(
+ monkeypatch: pytest.MonkeyPatch, caplog: pytest.LogCaptureFixture
+) -> str:
+ """POST one /v1/messages request with HEADROOM_SYSTEM_COMPACT on; return the log."""
+ monkeypatch.setenv("HEADROOM_SYSTEM_COMPACT", "1")
+ app = create_app(
+ ProxyConfig(
+ cache_enabled=False,
+ rate_limit_enabled=False,
+ cost_tracking_enabled=False,
+ anthropic_api_url="http://127.0.0.1:9",
+ )
+ )
+ # The headroom logger does not propagate to root, so capture it directly.
+ proxy_logger = logging.getLogger("headroom.proxy")
+ proxy_logger.addHandler(caplog.handler)
+ caplog.set_level(logging.DEBUG, logger="headroom.proxy")
+ try:
+ with TestClient(app) as client:
+ client.post(
+ "/v1/messages",
+ headers={"x-api-key": "sk-ant-test"},
+ json={
+ "model": "claude-sonnet-4-5",
+ "max_tokens": 8,
+ "system": "You are terse.",
+ "messages": [{"role": "user", "content": "hi"}],
+ },
+ )
+ finally:
+ proxy_logger.removeHandler(caplog.handler)
+ assert "Request failed" in caplog.text # reached the (dead) upstream, so compaction ran
+ return caplog.text
+
+
+def test_system_compaction_without_content_router_is_not_a_failure(
+ monkeypatch: pytest.MonkeyPatch, caplog: pytest.LogCaptureFixture
+) -> None:
+ monkeypatch.setattr(
+ "headroom.transforms.compression_units.find_content_router", lambda _pipeline: None
+ )
+ log = _post_with_system_compaction(monkeypatch, caplog)
+ assert "system prompt compaction FAILED" not in log
+
+
+def test_system_compaction_with_content_router_records_the_transform(
+ monkeypatch: pytest.MonkeyPatch, caplog: pytest.LogCaptureFixture
+) -> None:
+ router = object()
+ monkeypatch.setattr(
+ "headroom.transforms.compression_units.find_content_router", lambda _pipeline: router
+ )
+
+ def fake_compact(
+ payload: dict[str, Any], **kwargs: Any
+ ) -> tuple[dict[str, Any], bool, int, int]:
+ assert kwargs["router"] is router
+ return payload, True, 100, 40
+
+ monkeypatch.setattr("headroom.proxy.system_compaction.compact_system_prompt", fake_compact)
+ log = _post_with_system_compaction(monkeypatch, caplog)
+ assert "system prompt compaction: 100 -> 40 bytes (60% saved)" in log
+ assert "system prompt compaction FAILED" not in log