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
Switch telemetry to proxy_telemetry_v2 table, bump to 0.5.12
chopratejasc6d6c6a96ca8
diff --git a/headroom/__init__.py b/headroom/__init__.pyindex cfd774d6c..fedca9f29 100644--- a/headroom/__init__.py+++ b/headroom/__init__.py@@ -153,7 +153,7 @@ from .transforms import (TransformPipeline,)-__version__ = "0.5.11"+__version__ = "0.5.12"__all__ = [# Main clientdiff --git a/headroom/telemetry/beacon.py b/headroom/telemetry/beacon.pyindex b093e3c71..e47ce902e 100644--- a/headroom/telemetry/beacon.py+++ b/headroom/telemetry/beacon.py@@ -32,7 +32,7 @@ _SUPABASE_KEY = ".".join("h_C6dLQKa8BVc3upgEvulR4E0K4eiEViyddRMIylKjU",])-_TABLE = "proxy_telemetry"+_TABLE = "proxy_telemetry_v2"_ENDPOINT = f"{_SUPABASE_URL}/rest/v1/{_TABLE}"# Report every 5 minutesdiff --git a/pyproject.toml b/pyproject.tomlindex b514c70cf..f5bd3caf2 100644--- a/pyproject.toml+++ b/pyproject.toml@@ -4,7 +4,7 @@ build-backend = "hatchling.build"[project]name = "headroom-ai"-version = "0.5.11"+version = "0.5.12"description = "The Context Optimization Layer for LLM Applications - Cut costs by 50-90%"readme = "README.md"license = "Apache-2.0"diff --git a/sql/create_proxy_telemetry_v2.sql b/sql/create_proxy_telemetry_v2.sqlnew file mode 100644index 000000000..18efdcbbb--- /dev/null+++ b/sql/create_proxy_telemetry_v2.sql@@ -0,0 +1,70 @@+-- Supabase SQL: Create proxy_telemetry_v2 table+-- Run this in the Supabase SQL Editor (https://supabase.com/dashboard → SQL Editor)+-- This table matches every field the beacon code writes in headroom/telemetry/beacon.py++CREATE TABLE IF NOT EXISTS proxy_telemetry_v2 (+ id uuid DEFAULT gen_random_uuid() PRIMARY KEY,+ created_at timestamptz DEFAULT now() NOT NULL,++ -- Core identity (always present)+ session_id text NOT NULL,+ instance_id text,+ headroom_version text,+ python_version text,+ os text,+ sdk text,+ backend text,+ session_minutes integer,++ -- Effectiveness metrics+ tokens_saved bigint,+ requests integer,+ compression_percent real,+ cache_hit_rate real,+ cost_saved_usd real,+ cache_saved_usd real,+ models_used jsonb,++ -- Performance overhead+ overhead_avg_ms real,+ overhead_max_ms real,++ -- TTFB+ ttfb_avg_ms real,++ -- Pipeline timing (JSONB: {transform_name: avg_ms})+ pipeline_timing jsonb,++ -- Request patterns+ avg_tokens_before integer,+ avg_tokens_after integer,++ -- Compression cache+ compression_cache jsonb,++ -- CCR usage+ ccr jsonb,++ -- Waste signals+ waste_signals jsonb+);++-- Index for querying by session and time+CREATE INDEX IF NOT EXISTS idx_ptv2_session_id ON proxy_telemetry_v2(session_id);+CREATE INDEX IF NOT EXISTS idx_ptv2_created_at ON proxy_telemetry_v2(created_at DESC);+CREATE INDEX IF NOT EXISTS idx_ptv2_version ON proxy_telemetry_v2(headroom_version);++-- Enable Row Level Security+ALTER TABLE proxy_telemetry_v2 ENABLE ROW LEVEL SECURITY;++-- RLS policies: anon can INSERT (telemetry beacon) and SELECT (for debugging)+CREATE POLICY "anon_insert" ON proxy_telemetry_v2+ FOR INSERT TO anon+ WITH CHECK (true);++CREATE POLICY "anon_select" ON proxy_telemetry_v2+ FOR SELECT TO anon+ USING (true);++-- Grant permissions to anon role+GRANT INSERT, SELECT ON proxy_telemetry_v2 TO anon;