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.
Python agentaianthropicclaude-codecompressioncontext-engineeringcontext-windowcursorfastapilangchainllmmcpopenaiprompt-engineeringproxypythonragtoken-optimizationtokenstypescript
Format OpenAI Responses tests
Tejas Chopraead07cc1b058
diff --git a/tests/test_openai_responses_compression_units.py b/tests/test_openai_responses_compression_units.pyindex 0f3700545..80b06d3d8 100644--- a/tests/test_openai_responses_compression_units.py+++ b/tests/test_openai_responses_compression_units.py@@ -105,9 +105,7 @@ def test_openai_responses_adapter_compresses_custom_tool_call_output():assert modified is Trueassert saved > 0assert new_payload["input"][0]["output"] == "custom output summary"- assert (- "router:openai:responses:custom_tool_call_output:kompress" in transforms- )+ assert "router:openai:responses:custom_tool_call_output:kompress" in transformsassert units_by_category == {"applied": 1}assert strategy_chain == []diff --git a/tests/test_openai_responses_context_compaction.py b/tests/test_openai_responses_context_compaction.pyindex 793be1cf8..f501f642a 100644--- a/tests/test_openai_responses_context_compaction.py+++ b/tests/test_openai_responses_context_compaction.py@@ -287,10 +287,7 @@ def test_compression_pass_debug_logs_are_suppressed(caplog) -> None:payload_a, model="gpt-5.5", request_id="hr_shared_request")- assert not any(- "event=codex_compression_" in record.getMessage()- for record in caplog.records- )+ assert not any("event=codex_compression_" in record.getMessage() for record in caplog.records)return# Collect pass_ids in call order — payload bodies are no longer