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(proxy): log unknown model ids as one bounded token; skip unparseable PERF lines (#4374)
HetCreepc014bd631174
diff --git a/headroom/perf/analyzer.py b/headroom/perf/analyzer.pyindex 55c880902..c40e62f20 100644--- a/headroom/perf/analyzer.py+++ b/headroom/perf/analyzer.py@@ -224,6 +224,7 @@ class PerfReport:oldest_kept_ts: str | None = Nonenewest_kept_ts: str | None = Nonerecords_filtered_out: int = 0+ records_malformed: int = 0# True when no time cutoff was applied (--hours 0, or a value so large it# overflows datetime arithmetic). The header says "all data" instead of a# misleading "last 0h".@@ -386,9 +387,8 @@ def parse_log_files(last_n_hours: float = 168.0) -> PerfReport:if not _within_window(ts):report.records_filtered_out += 1continue- _track_window(ts)- report.perf_records.append(- PerfRecord(+ try:+ record = PerfRecord(timestamp=ts,request_id=m.group("rid"),model=kv.get("model", ""),@@ -411,7 +411,13 @@ def parse_log_files(last_n_hours: float = 168.0) -> PerfReport:from_response_cache=kv.get("cached", "0") == "1",stages=stages_by_rid.get(m.group("rid"), {}),)- )+ except ValueError:+ # A non-numeric field is not a PERF line Headroom wrote+ # (e.g. text a client put into a logged model id).+ report.records_malformed += 1+ continue+ _track_window(ts)+ report.perf_records.append(record)continue# content_router summary lines@@ -544,6 +550,11 @@ def format_report(report: PerfReport) -> str:f"Records outside window: {report.records_filtered_out:,} ""(filtered out — increase --hours to include them)")+ if report.records_malformed > 0:+ lines.append(+ f"Malformed PERF lines: {report.records_malformed:,} "+ "(skipped — a numeric field did not parse)"+ )lines.append("")records = report.perf_records@@ -1400,6 +1411,7 @@ def build_perf_summary(report: PerfReport) -> dict:"newest": report.newest_kept_ts,},"records_filtered_out": report.records_filtered_out,+ "records_malformed": report.records_malformed,"total_requests": len(records),"total_tokens_before": total_before,"total_tokens_after": total_after,diff --git a/headroom/providers/openai.py b/headroom/providers/openai.pyindex 006018c60..139583fd4 100644--- a/headroom/providers/openai.py+++ b/headroom/providers/openai.py@@ -646,7 +646,7 @@ class OpenAIProvider(Provider):if model not in _UNKNOWN_MODEL_WARNINGS:_UNKNOWN_MODEL_WARNINGS.add(model)logger.warning(- f"Unknown OpenAI model '{model}': {reason} ({limit:,} tokens). "+ f"Unknown OpenAI model {safe_id(model)}: {reason} ({limit:,} tokens). "f"To configure explicitly, set HEADROOM_MODEL_LIMITS env var or "f"add to ~/.headroom/models.json")diff --git a/tests/test_perf_per_port_logs.py b/tests/test_perf_per_port_logs.pyindex fd8c449f3..aaf9b9a4b 100644--- a/tests/test_perf_per_port_logs.py+++ b/tests/test_perf_per_port_logs.py@@ -401,3 +401,22 @@ def test_router_content_dump_needs_the_content_opt_in(router_logger.setLevel(previous)assert ("secret-tool-output" in stream.getvalue()) is logged+++def test_parse_log_files_skips_a_perf_line_with_non_numeric_fields(workspace: Path) -> None:+ """A PERF-shaped line with a non-numeric count is skipped, not fatal."""+ log_dir = workspace / "logs"+ ts = "2026-08-22 10:00:00,000"+ bad = _perf_line(ts, "hr_bad", "model-BAD").replace("msgs=3", "msgs=lots")+ good = _perf_line(ts, "hr_good", "model-GOOD")+ (log_dir / "proxy.log").write_text(bad + "\n" + good + "\n")++ report = analyzer.parse_log_files(last_n_hours=0.0)++ assert {r.model for r in report.perf_records} == {"model-GOOD"}+ assert report.records_malformed == 1+ assert report.records_filtered_out == 0 # nothing was outside the window+ text = analyzer.format_report(report)+ assert "Malformed PERF lines:" in text+ assert "Records outside window" not in text+ assert analyzer.build_perf_summary(report)["records_malformed"] == 1diff --git a/tests/test_providers_openai_unknown_model_log.py b/tests/test_providers_openai_unknown_model_log.pynew file mode 100644index 000000000..ca1c302e6--- /dev/null+++ b/tests/test_providers_openai_unknown_model_log.py@@ -0,0 +1,17 @@+"""The unknown-model warning must log the client-supplied model id as one bounded token."""++from __future__ import annotations++import logging++from headroom.providers import openai as openai_provider+++def test_unknown_model_warning_is_one_line(caplog) -> None:+ provider = openai_provider.OpenAIProvider()+ openai_provider._UNKNOWN_MODEL_WARNINGS.discard("odd\nmodel")+ with caplog.at_level(logging.WARNING, logger=openai_provider.logger.name):+ provider._warn_unknown_model("odd\nmodel", 128000, "pattern match")+ messages = [r.getMessage() for r in caplog.records if "Unknown OpenAI model" in r.getMessage()]+ assert messages+ assert all("\n" not in m for m in messages)