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
style: apply ruff format to test_proxy_anthropic_cache_stability lambdas
chopratejas521fbbeabddc
diff --git a/tests/test_proxy_anthropic_cache_stability.py b/tests/test_proxy_anthropic_cache_stability.pyindex 705da3817..bd99eb0a5 100644--- a/tests/test_proxy_anthropic_cache_stability.py+++ b/tests/test_proxy_anthropic_cache_stability.py@@ -1445,8 +1445,8 @@ def test_issue_327_streaming_and_non_streaming_compute_same_frozen_count() -> Noproxy = client.app.state.proxyfake_tracker = _FakePrefixTracker(frozen_count=12)- proxy.session_tracker_store.compute_session_id = (- lambda request, model, messages: "stream-parity-A"+ proxy.session_tracker_store.compute_session_id = lambda request, model, messages: (+ "stream-parity-A")proxy.session_tracker_store.get_or_create = lambda s, p: fake_trackerproxy._get_compression_cache = lambda s: fake_cache_a@@ -1502,8 +1502,8 @@ def test_issue_327_streaming_and_non_streaming_compute_same_frozen_count() -> Noproxy = client.app.state.proxyfake_tracker = _FakePrefixTracker(frozen_count=12)- proxy.session_tracker_store.compute_session_id = (- lambda request, model, messages: "stream-parity-B"+ proxy.session_tracker_store.compute_session_id = lambda request, model, messages: (+ "stream-parity-B")proxy.session_tracker_store.get_or_create = lambda s, p: fake_trackerproxy._get_compression_cache = lambda s: fake_cache_b