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(tests): pin proxy_ccr + text_compressors tests to lossy+CCR path

chopratejas3ad69650b434
diff --git a/tests/test_proxy_ccr.py b/tests/test_proxy_ccr.py
index beeb85723..123f994a6 100644
--- a/tests/test_proxy_ccr.py
+++ b/tests/test_proxy_ccr.py
@@ -441,7 +441,11 @@ class TestEndToEndTOINIntegration:
},
]
- # Create pipeline with SmartCrusher (same as proxy does)
+ # Create pipeline with SmartCrusher (same as proxy does).
+ # Use with_compaction=False so we exercise the lossy + CCR
+ # caching path that this test asserts. The PR4 lossless
+ # default substitutes a CSV+schema string and skips CCR
+ # caching (nothing dropped → no cache entry).
pipeline = TransformPipeline(
transforms=[
SmartCrusher(
@@ -455,6 +459,7 @@ class TestEndToEndTOINIntegration:
inject_retrieval_marker=True,
min_items_to_cache=10,
),
+ with_compaction=False,
),
],
provider=AnthropicProvider(),
diff --git a/tests/test_text_compressors.py b/tests/test_text_compressors.py
index 98ebfdfcc..1b76ea554 100644
--- a/tests/test_text_compressors.py
+++ b/tests/test_text_compressors.py
@@ -390,7 +390,14 @@ class TestSmartCrusherTextIntegration:
assert result.compression_ratio < 1.0 # Some compression occurred
def test_smart_crusher_json_still_works(self):
- """SmartCrusher still handles JSON correctly."""
+ """SmartCrusher still handles JSON correctly.
+
+ Asserts the legacy lossy + JSON-shape behavior: output is a
+ JSON-parseable array. The PR4 lossless default substitutes a
+ CSV+schema STRING for tabular arrays, which doesn't round-trip
+ as a JSON array — that's tested separately in
+ `test_smart_crusher_lossless_default.py`.
+ """
import json
import re
@@ -413,8 +420,11 @@ class TestSmartCrusherTextIntegration:
{"role": "tool", "content": json_content},
]
+ # Use without_compaction to exercise the legacy lossy + JSON-shape
+ # path. Lossless default would substitute a non-JSON string.
crusher = SmartCrusher(
- config=SmartCrusherConfig(min_tokens_to_crush=10, min_items_to_analyze=5)
+ config=SmartCrusherConfig(min_tokens_to_crush=10, min_items_to_analyze=5),
+ with_compaction=False,
)
tokenizer = self._get_tokenizer()