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
test(agno): follow the metrics dataclass move in agno 3.0.0 (#3260)
gglucassc2fbb4eed0c4
diff --git a/tests/test_integrations/agno/test_model.py b/tests/test_integrations/agno/test_model.pyindex 26545996c..5a0bf990e 100644--- a/tests/test_integrations/agno/test_model.py+++ b/tests/test_integrations/agno/test_model.py@@ -19,6 +19,11 @@ try:AGNO_AVAILABLE = Trueexcept ImportError:AGNO_AVAILABLE = False+else:+ try: # agno < 3: the per-message usage dataclass lived at agno.models.metrics+ from agno.models.metrics import Metrics+ except ImportError: # agno >= 3 moved it to agno.metrics, renamed MessageMetrics+ from agno.metrics import MessageMetrics as Metricsfrom headroom import HeadroomConfig, HeadroomMode@@ -50,8 +55,6 @@ def mock_agno_model():# Mock invoke method (returns ModelResponse for Agno's response() loop)def mock_invoke(messages, **kwargs):- from agno.models.metrics import Metrics-# Create a proper ModelResponse that Agno's response() can processreturn ModelResponse(role="assistant",@@ -73,8 +76,6 @@ def mock_agno_model():# Mock invoke_stream for streamingdef mock_invoke_stream(messages, **kwargs):- from agno.models.metrics import Metrics-yield ModelResponse(role="assistant",content="Streaming...",