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(install/apply): add --no-rate-limit flag, persist in proxy_args (#1350) (#1365)
Peter Lodri31d03449910f
diff --git a/headroom/cli/install.py b/headroom/cli/install.pyindex e8bd77bb8..f5a7141c3 100644--- a/headroom/cli/install.py+++ b/headroom/cli/install.py@@ -437,6 +437,7 @@ def _build_deployment_manifest(extra_env: dict[str, str] | None = None,supervisor_kind: str | None = None,extra_base_env: dict[str, str] | None = None,+ no_rate_limit: bool = False,) -> DeploymentManifest:manifest = build_manifest(profile=profile,@@ -452,6 +453,7 @@ def _build_deployment_manifest(proxy_mode=proxy_mode,memory_enabled=memory,telemetry_enabled=telemetry and not no_telemetry,+ no_rate_limit=no_rate_limit,image=image,no_http2=no_http2,code_aware=code_aware,@@ -620,6 +622,18 @@ def _echo_installed(manifest: DeploymentManifest, *, prefix: str = "Installed peis_flag=True,help="Force anonymous telemetry off in the runtime (already the default).",)+ "--no-rate-limit",+ "no_rate_limit",+ is_flag=True,+ default=False,+ help=(+ "Disable the proxy's built-in rate limiter (default: 60 req/min). "+ "Recommended for always-on agentic targets (Claude Code, Codex) that "+ "burst above the default threshold. The flag is persisted in the "+ "deployment manifest so reinstalls don't silently reintroduce throttling."+ ),+)@click.option("--image",default="ghcr.io/headroomlabs-ai/headroom:latest",@@ -691,6 +705,7 @@ def install_apply(memory: bool,telemetry: bool,no_telemetry: bool,+ no_rate_limit: bool,image: str,no_http2: bool,code_aware: bool | None,@@ -737,6 +752,7 @@ def install_apply(memory=memory,telemetry=telemetry,no_telemetry=no_telemetry,+ no_rate_limit=no_rate_limit,image=image,no_http2=no_http2,code_aware=code_aware,diff --git a/headroom/install/planner.py b/headroom/install/planner.pyindex a545ffd01..6bdd3700b 100644--- a/headroom/install/planner.py+++ b/headroom/install/planner.py@@ -133,6 +133,7 @@ def build_manifest(memory_enabled: bool,telemetry_enabled: bool,image: str,+ no_rate_limit: bool = False,no_http2: bool = False,code_aware: bool | None = None,intercept_tool_results: bool = False,@@ -231,6 +232,11 @@ def build_manifest(backend,]proxy_args.append("--telemetry" if telemetry_enabled else "--no-telemetry")+ # Agentic CLI targets (Claude Code, Codex) burst well above 60 req/min.+ # Persist the flag so reinstalls don't silently reintroduce throttling.+ # (see: https://github.com/headroomlabs-ai/headroom/issues/1350)+ if no_rate_limit:+ proxy_args.append("--no-rate-limit")if memory_enabled:proxy_args.append("--memory")# `_paths.memory_db_path()` resolves against the HOST home. A containerdiff --git a/tests/test_install_apply_no_rate_limit.py b/tests/test_install_apply_no_rate_limit.pynew file mode 100644index 000000000..799681813--- /dev/null+++ b/tests/test_install_apply_no_rate_limit.py@@ -0,0 +1,102 @@+"""Tests that --no-rate-limit is wired through install apply to proxy_args.++Regression for https://github.com/headroomlabs-ai/headroom/issues/1350:+agentic CLI targets (Claude Code, Codex) burst above the 60 req/min default,+causing the proxy to self-throttle instead of forwarding to Anthropic.+--no-rate-limit on `headroom proxy` existed, but `headroom install apply`+had no flag to persist it — reinstalls silently reintroduced throttling.+"""++from __future__ import annotations++import pytest++from headroom.install.planner import build_manifest++_BASE_KWARGS = {+ "profile": "default",+ "preset": "persistent-service",+ "runtime_kind": "python",+ "scope": "user",+ "provider_mode": "auto",+ "targets": [],+ "port": 8787,+ "backend": "anthropic",+ "anyllm_provider": None,+ "region": None,+ "proxy_mode": "token",+ "memory_enabled": False,+ "telemetry_enabled": False,+ "image": "ghcr.io/chopratejas/headroom:latest",+}+++def test_no_rate_limit_false_by_default() -> None:+ """Default manifest must NOT include --no-rate-limit in proxy_args."""+ manifest = build_manifest(**_BASE_KWARGS)+ assert "--no-rate-limit" not in manifest.proxy_args+++def test_no_rate_limit_true_appends_flag() -> None:+ """no_rate_limit=True must append --no-rate-limit to proxy_args."""+ manifest = build_manifest(**_BASE_KWARGS, no_rate_limit=True)+ assert "--no-rate-limit" in manifest.proxy_args+++def test_no_rate_limit_flag_position() -> None:+ """--no-rate-limit must appear after --no-telemetry in proxy_args+ so the manifest is deterministic and diffable."""+ manifest = build_manifest(**_BASE_KWARGS, no_rate_limit=True)+ args = manifest.proxy_args+ assert "--no-telemetry" in args+ assert args.index("--no-rate-limit") > args.index("--no-telemetry")+++def test_no_rate_limit_idempotent_on_reinstall() -> None:+ """Rebuilding the manifest with the same flag must not duplicate it."""+ manifest1 = build_manifest(**_BASE_KWARGS, no_rate_limit=True)+ manifest2 = build_manifest(**_BASE_KWARGS, no_rate_limit=True)+ assert manifest1.proxy_args.count("--no-rate-limit") == 1+ assert manifest2.proxy_args.count("--no-rate-limit") == 1+++def test_cli_flag_wired_through_install_apply() -> None:+ """headroom install apply --no-rate-limit must produce a manifest+ with --no-rate-limit in proxy_args (integration: CLI → planner)."""+ from unittest.mock import patch++ pytest.importorskip("fastapi")+ from click.testing import CliRunner++ from headroom.cli.install import install_apply++ runner = CliRunner()+ # --dry-run or equivalent: we just check the manifest is built correctly.+ # Since install_apply does real side-effects, we patch the heavy parts.++ built_manifests = []++ def capture_manifest(**kwargs):+ m = build_manifest(**kwargs)+ built_manifests.append(m)+ return m++ with (+ patch("headroom.cli.install.build_manifest", side_effect=capture_manifest),+ patch("headroom.cli.install.load_manifest", return_value=None),+ patch("headroom.cli.install.apply_mutations", return_value=[]),+ patch("headroom.cli.install.install_supervisor", return_value=[]),+ patch("headroom.cli.install.save_manifest"),+ patch("headroom.cli.install._start_deployment"),+ patch("headroom.cli.install.click.echo"),+ ):+ runner.invoke(+ install_apply,+ ["--no-rate-limit", "--scope", "user"],+ catch_exceptions=False,+ )++ assert built_manifests, "build_manifest was never called"+ assert "--no-rate-limit" in built_manifests[0].proxy_args, (+ f"--no-rate-limit not in proxy_args: {built_manifests[0].proxy_args}"+ )