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
fix: restore Authorization header in telemetry beacon
chopratejas27e026d58b75
diff --git a/headroom/telemetry/beacon.py b/headroom/telemetry/beacon.pyindex e3789789c..fb13ecfdf 100644--- a/headroom/telemetry/beacon.py+++ b/headroom/telemetry/beacon.py@@ -252,8 +252,7 @@ class TelemetryBeacon:json=payload,headers={"apikey": _SUPABASE_KEY,- # sb_publishable_ keys are not JWTs — don't send as Bearer token- # (Supabase migrated from JWT anon keys to publishable keys in 2025)+ "Authorization": f"Bearer {_SUPABASE_KEY}","Content-Type": "application/json",# Upsert: on conflict with session_id, merge (overwrite) the row"Prefer": "resolution=merge-duplicates,return=minimal",