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.

Merge pull request #224 from gglucass/codex/compact-stats-history-default

Tejas Choprada54d4a80aea
diff --cc headroom/proxy/server.py
index fa2a0e65a,2146d8059..596893e66
--- a/headroom/proxy/server.py
+++ b/headroom/proxy/server.py
@@@ -1678,41 -1662,8 +1679,41 @@@ def create_app(config: ProxyConfig | No
headers={"Content-Disposition": f'attachment; filename="{filename}"'},
)
- return proxy.metrics.savings_tracker.history_response()
+ return proxy.metrics.savings_tracker.history_response(history_mode=history_mode)
+ @app.get("/transformations/feed")
+ async def transformations_feed(limit: int = 20):
+ """Get recent message transformations for the live feed.
+
+ Returns empty list if log_full_messages is disabled (messages are not stored).
+ """
+ if limit > 100:
+ limit = 100
+
+ transformations = []
+ log_full_messages = proxy.config.log_full_messages if proxy else False
+
+ if proxy and proxy.logger:
+ logs = proxy.logger.get_recent_with_messages(limit)
+ for log in logs:
+ transformations.append(
+ {
+ "request_id": log.get("request_id"),
+ "timestamp": log.get("timestamp"),
+ "provider": log.get("provider"),
+ "model": log.get("model"),
+ "input_tokens_original": log.get("input_tokens_original"),
+ "input_tokens_optimized": log.get("input_tokens_optimized"),
+ "tokens_saved": log.get("tokens_saved"),
+ "savings_percent": log.get("savings_percent"),
+ "transforms_applied": log.get("transforms_applied", []),
+ "request_messages": log.get("request_messages"),
+ "response_content": log.get("response_content"),
+ }
+ )
+
+ return {"transformations": transformations, "log_full_messages": log_full_messages}
+
@app.get("/subscription-window")
async def subscription_window():
"""Current Anthropic subscription window utilisation and Headroom contribution."""