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.

Pin litellm to v1.82.3 and bump version to 0.5.3

chopratejascb215896761d
diff --git a/pyproject.toml b/pyproject.toml
index 38ef929d3..efb715400 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
[project]
name = "headroom-ai"
-version = "0.5.2"
+version = "0.5.3"
description = "The Context Optimization Layer for LLM Applications - Cut costs by 50-90%"
readme = "README.md"
license = "Apache-2.0"
@@ -47,7 +47,7 @@ dependencies = [
# Core: lightweight compression (SmartCrusher, ContentRouter, CCR, TOIN)
"tiktoken>=0.5.0", # Tokenizer for all compressors
"pydantic>=2.0.0", # Config and data models
- "litellm>=1.0.0", # Model registry, pricing, and provider support
+ "litellm==1.82.3", # Model registry, pricing, and provider support
"click>=8.1.0", # CLI framework
"rich>=13.0.0", # Rich terminal output
]
@@ -162,7 +162,7 @@ dev = [
"pre-commit>=3.0.0",
"openai>=1.0.0",
"anthropic>=0.18.0",
- "litellm>=1.0.0",
+ "litellm==1.82.3",
"fastapi>=0.100.0",
"uvicorn>=0.23.0",
"httpx[http2]>=0.24.0",