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: --disable-kompress should not override fallback_strategy to PASSTHROUGH (#1046)

AKT99!64ca95361a78
diff --git a/headroom/proxy/server.py b/headroom/proxy/server.py
index 728ab9a7a..5aa80b8b6 100644
--- a/headroom/proxy/server.py
+++ b/headroom/proxy/server.py
@@ -167,7 +167,6 @@ from headroom.transforms import (
CacheAligner,
CodeAwareCompressor,
CodeCompressorConfig,
- CompressionStrategy,
ContentRouter,
ContentRouterConfig,
TransformPipeline,
@@ -618,7 +617,6 @@ class HeadroomProxy(
)
if config.disable_kompress:
router_config.enable_kompress = False
- router_config.fallback_strategy = CompressionStrategy.PASSTHROUGH
# A non-None exclude_tools replaces DEFAULT_EXCLUDE_TOOLS in
# ContentRouter, so merge rather than assign.
if config.exclude_tools:
diff --git a/tests/test_proxy_disable_kompress.py b/tests/test_proxy_disable_kompress.py
index a45b590f1..d608b0fbc 100644
--- a/tests/test_proxy_disable_kompress.py
+++ b/tests/test_proxy_disable_kompress.py
@@ -33,7 +33,7 @@ def test_disable_kompress_config_keeps_optimization_but_disables_ml_fallback() -
)
assert router.config.enable_kompress is False
- assert router.config.fallback_strategy == CompressionStrategy.PASSTHROUGH
+ assert router.config.fallback_strategy == CompressionStrategy.KOMPRESS
def test_disable_kompress_defaults_to_existing_kompress_behavior() -> None: