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(kompress): skip the local model download when a remote endpoint is set (#4234)
Tejas Chopraff3693165344
diff --git a/headroom/proxy/server.py b/headroom/proxy/server.pyindex 231deefcd..0edd8e1c5 100644--- a/headroom/proxy/server.py+++ b/headroom/proxy/server.py@@ -2229,7 +2229,10 @@ class HeadroomProxy(# Log component statusif self._kompress_status == "enabled":- logger.info("Kompress: ENABLED (ModernBERT token compressor)")+ if eager_status.get("kompress_backend") == "remote":+ logger.info("Kompress: ENABLED (remote endpoint; no local model)")+ else:+ logger.info("Kompress: ENABLED (ModernBERT token compressor)")elif self._kompress_status == "deferred":if self._start_kompress_background_warmup():logger.info("Kompress: DEFERRED (warming in the background after startup)")diff --git a/headroom/proxy/warmup.py b/headroom/proxy/warmup.pyindex 9c66ab36a..895b6fdfd 100644--- a/headroom/proxy/warmup.py+++ b/headroom/proxy/warmup.py@@ -111,21 +111,27 @@ class WarmupRegistry:``error`` statuses must be set explicitly by the caller."""- def _apply(slot: WarmupSlot, value: str | None) -> None:+ def _apply(slot: WarmupSlot, value: str | None, **info: Any) -> None:if value is None:returnv = value.strip().lower()if v in {"enabled", "ready"} or v.startswith("loaded"):# Preserve whatever handle/info was set already.if slot.status != "loaded":- slot.mark_loaded(handle=slot.handle, source_status=value)+ slot.mark_loaded(handle=slot.handle, source_status=value, **info)else:slot.info.setdefault("source_status", value)else:if slot.status != "loaded":slot.info["source_status"] = value- _apply(self.kompress, status.get("kompress"))+ # A remote endpoint is ready at startup; /readyz reports its backend.+ kompress_backend = status.get("kompress_backend")+ _apply(+ self.kompress,+ status.get("kompress"),+ **({"backend": kompress_backend} if kompress_backend == "remote" else {}),+ )_apply(self.magika, status.get("magika"))_apply(self.code_aware, status.get("code_aware"))_apply(self.tree_sitter, status.get("tree_sitter"))diff --git a/headroom/transforms/content_router.py b/headroom/transforms/content_router.pyindex 0ff77f423..9d56c87f6 100644--- a/headroom/transforms/content_router.py+++ b/headroom/transforms/content_router.py@@ -5198,7 +5198,12 @@ class ContentRouter(Transform):if self.config.enable_kompress:compressor = self._get_kompress()if compressor:- if not hasattr(compressor, "preload"):+ if compressor is self._get_remote_kompress():+ # HEADROOM_KOMPRESS_ENDPOINT runs the model; there is no+ # local model to download or warm.+ status["kompress"] = "enabled"+ status["kompress_backend"] = "remote"+ elif not hasattr(compressor, "preload"):status["kompress"] = "enabled"status["kompress_backend"] = "unknown"else:diff --git a/tests/test_proxy_health.py b/tests/test_proxy_health.pyindex b45cb42ad..d931eeb28 100644--- a/tests/test_proxy_health.py+++ b/tests/test_proxy_health.py@@ -323,3 +323,29 @@ def test_readyz_kompress_state_matrix(monkeypatch, slot_status, compressor, disapayload = TestClient(app).get("/readyz").json()["checks"]["kompress"]assert payload == expected+++def test_remote_kompress_endpoint_skips_local_model_at_startup(monkeypatch):+ """With HEADROOM_KOMPRESS_ENDPOINT set, startup neither fetches nor warms the+ local model, and /readyz still names the remote backend."""+ import threading++ monkeypatch.setenv("HEADROOM_SKIP_UPSTREAM_CHECK", "1")+ monkeypatch.setenv("HEADROOM_KOMPRESS_ENDPOINT", "https://kompress.example.test")+ monkeypatch.setenv("HEADROOM_KOMPRESS_WARMUP", "1")+ monkeypatch.setenv("HEADROOM_KOMPRESS_WARMUP_DELAY_SECONDS", "3600")+ prefetched: list[str] = []+ monkeypatch.setattr(+ kompress_compressor,+ "ensure_background_prefetch",+ lambda model_id: (prefetched.append(model_id), True)[1],+ )+ app = create_app(ProxyConfig(optimize=True, cache_enabled=False, rate_limit_enabled=False))++ with TestClient(app) as client:+ app.state.proxy.http_client = object()+ payload = client.get("/readyz").json()++ assert prefetched == []+ assert not any(t.name == "kompress-warmup" for t in threading.enumerate())+ assert payload["checks"]["kompress"]["backend"] == "remote"