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
"""Pricing-lookup warnings for an unresolvable model must fire once, not per request.
#2504: a custom / OpenAI-compatible model LiteLLM can't price (e.g. glm-5.2)
logged an identical WARNING on every single request, flooding proxy.log.
"""
from __future__ import annotations
import logging
import pytest
from headroom.log_safety import WarnOnce
@pytest.fixture
def cost_tracker(monkeypatch: pytest.MonkeyPatch):
import headroom.proxy.cost as cost_mod
# A fresh dedup guard so tests are order-independent.
monkeypatch.setattr(cost_mod, "_pricing_warnings", WarnOnce(1024, "unpriceable models"))
class _FakeLiteLLM:
@staticmethod
def cost_per_token(**_kwargs):
raise RuntimeError("LLM Provider NOT provided.")
monkeypatch.setattr(cost_mod, "_get_litellm_module", lambda: _FakeLiteLLM())
return cost_mod.CostTracker()
def test_pricing_failure_warns_once_per_model(cost_tracker, caplog):
with caplog.at_level(logging.WARNING, logger="headroom.proxy"):
for _ in range(5):
assert cost_tracker.estimate_cost("glm-5.2", 100, 50) is None
warnings = [
r for r in caplog.records if "Failed to get pricing for model 'glm-5.2'" in r.getMessage()
]
assert len(warnings) == 1
def test_distinct_models_each_warn_once(cost_tracker, caplog):
with caplog.at_level(logging.WARNING, logger="headroom.proxy"):
cost_tracker.estimate_cost("glm-5.2", 10, 5)
cost_tracker.estimate_cost("glm-5.2", 10, 5)
cost_tracker.estimate_cost("mystery-model", 10, 5)
cost_tracker.estimate_cost("mystery-model", 10, 5)
msgs = [r.getMessage() for r in caplog.records if "Failed to get pricing" in r.getMessage()]
assert sum("for model 'glm-5.2':" in m for m in msgs) == 1
assert sum("for model 'mystery-model':" in m for m in msgs) == 1
def test_litellm_unavailable_warns_once_per_model(monkeypatch, caplog):
import headroom.proxy.cost as cost_mod
monkeypatch.setattr(cost_mod, "_pricing_warnings", WarnOnce(1024, "unpriceable models"))
monkeypatch.setattr(cost_mod, "_get_litellm_module", lambda: None)
tracker = cost_mod.CostTracker()
with caplog.at_level(logging.WARNING, logger="headroom.proxy"):
for _ in range(3):
assert tracker.estimate_cost("glm-5.2", 10, 5) is None
unavailable = [r for r in caplog.records if "LiteLLM not available" in r.getMessage()]
assert len(unavailable) == 1
def test_passthrough_model_skips_pricing_without_warning(monkeypatch, caplog):
import headroom.proxy.cost as cost_mod
class _FakeLiteLLM:
@staticmethod
def cost_per_token(**_kwargs):
raise AssertionError("cost_per_token must not be called")
monkeypatch.setattr(cost_mod, "_get_litellm_module", lambda: _FakeLiteLLM())
tracker = cost_mod.CostTracker()
with caplog.at_level(logging.WARNING, logger="headroom.proxy"):
assert tracker.estimate_cost("passthrough:count_tokens", 100, 50) is None
assert not caplog.records
def test_stats_omit_passthrough_models(cost_tracker):
cost_tracker.record_tokens("passthrough:count_tokens", 10, 90)
cost_tracker.record_tokens("glm-5.2", 20, 80)
stats = cost_tracker.stats()
assert set(stats["per_model"]) == {"glm-5.2"}
assert stats["total_tokens_saved"] == 20
assert stats["total_input_tokens"] == 80