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.

fix(grok): preserve business-seat auth while routing only inference (#2514)

Rod Boeve4076bbe99d5
diff --git a/README.md b/README.md
index f52f481c0..f46e40640 100644
--- a/README.md
+++ b/README.md
@@ -227,7 +227,7 @@ shows an **Output Tokens Saved** card next to input compression, labelled
|--------------|:---------------:|----------------------------------|
| Claude Code | ✅ | `--memory` · `--code-graph` · `--1m` · `--tool-search` |
| Codex | ✅ | shares memory with Claude |
-| Grok CLI | ✅ | routes via `GROK_CLI_CHAT_PROXY_BASE_URL` |
+| Grok CLI | ✅ | routes via `GROK_MODELS_BASE_URL` |
| Cursor | Manual setup | starts proxy and prints base URLs for Cursor settings |
| Aider | ✅ | starts proxy + launches |
| Copilot CLI | ✅ | starts proxy + launches |
diff --git a/headroom/cli/wrap.py b/headroom/cli/wrap.py
index 29b706744..5c5f37a79 100644
--- a/headroom/cli/wrap.py
+++ b/headroom/cli/wrap.py
@@ -6381,9 +6381,10 @@ def grok(
"""Launch Grok CLI through Headroom proxy.
\b
- Sets ``GROK_CLI_CHAT_PROXY_BASE_URL`` so Grok routes inference traffic
- through Headroom. Registers the headroom MCP server in ``~/.grok/config.toml``
- so Grok can call ``headroom_retrieve`` on compression markers.
+ Sets ``GROK_MODELS_BASE_URL`` so Grok routes inference traffic through
+ Headroom while preserving native settings and authentication routing.
+ Registers the headroom MCP server in ``~/.grok/config.toml`` so Grok can
+ call ``headroom_retrieve`` on compression markers.
\b
Examples:
@@ -8210,10 +8211,11 @@ def unwrap_omp(port: int, no_stop_proxy: bool) -> None:
def unwrap_grok(port: int, no_stop_proxy: bool) -> None:
"""Undo durable ``headroom wrap grok`` MCP and guidance edits.
- Grok API routing is session-scoped via ``GROK_CLI_CHAT_PROXY_BASE_URL`` and
- does not require config restoration. This command removes Headroom MCP
- servers from ``~/.grok/config.toml`` and strips injected RTK guidance from
- the project ``AGENTS.md``.
+ Grok inference routing is session-scoped via ``GROK_MODELS_BASE_URL`` and
+ does not require config restoration. Native settings and authentication
+ routing stay unchanged. This command removes Headroom MCP servers from
+ ``~/.grok/config.toml`` and strips injected RTK guidance from the project
+ ``AGENTS.md``.
"""
click.echo()
click.echo(" ╔═══════════════════════════════════════════════╗")
diff --git a/headroom/providers/grok/runtime.py b/headroom/providers/grok/runtime.py
index eb9480312..2f4e150fb 100644
--- a/headroom/providers/grok/runtime.py
+++ b/headroom/providers/grok/runtime.py
@@ -8,7 +8,7 @@ from collections.abc import Mapping
from headroom.proxy.project_context import with_project_prefix
DEFAULT_API_URL = "https://api.x.ai"
-PROXY_ENV_KEY = "GROK_CLI_CHAT_PROXY_BASE_URL"
+PROXY_ENV_KEY = "GROK_MODELS_BASE_URL"
def proxy_base_url(port: int) -> str:
@@ -23,9 +23,9 @@ def build_launch_env(
) -> tuple[dict[str, str], list[str]]:
"""Build environment variables for Grok CLI through the local proxy.
- Grok routes inference traffic through ``GROK_CLI_CHAT_PROXY_BASE_URL``
- when set (see Grok CLI auth/custom-models docs). The proxy forwards
- OpenAI-compatible chat requests upstream to xAI.
+ Grok routes inference traffic through ``GROK_MODELS_BASE_URL`` when set.
+ The proxy forwards OpenAI-compatible chat requests upstream to xAI while
+ Grok keeps its native settings and authentication routing.
``project`` (the wrap launch directory) is encoded as a ``/p/<name>``
base-URL prefix because Grok cannot send custom attribution headers;
diff --git a/tests/test_cli/test_wrap_grok.py b/tests/test_cli/test_wrap_grok.py
index 1cd278809..03053be81 100644
--- a/tests/test_cli/test_wrap_grok.py
+++ b/tests/test_cli/test_wrap_grok.py
@@ -44,6 +44,7 @@ def test_wrap_grok_sets_proxy_env(
env = captured["env"]
assert isinstance(env, dict)
assert env[PROXY_ENV_KEY] == f"http://127.0.0.1:8787{_expected_project_prefix()}/v1"
+ assert "GROK_CLI_CHAT_PROXY_BASE_URL" not in env
assert captured["tool_label"] == "GROK"
assert captured["agent_type"] == "grok"
assert captured["args"] == ("-p", "hello")
diff --git a/tests/test_provider_grok.py b/tests/test_provider_grok.py
index 08793332d..3af357ccd 100644
--- a/tests/test_provider_grok.py
+++ b/tests/test_provider_grok.py
@@ -8,10 +8,11 @@ def test_grok_proxy_base_url_uses_local_headroom_proxy() -> None:
assert proxy_base_url(8787) == "http://127.0.0.1:8787/v1"
-def test_grok_build_launch_env_sets_chat_proxy_base_url() -> None:
+def test_grok_build_launch_env_sets_models_base_url() -> None:
env, display = build_launch_env(9999, environ={})
assert env[PROXY_ENV_KEY] == "http://127.0.0.1:9999/v1"
+ assert "GROK_CLI_CHAT_PROXY_BASE_URL" not in env
assert display == [f"{PROXY_ENV_KEY}=http://127.0.0.1:9999/v1"]
@@ -19,6 +20,7 @@ def test_grok_build_launch_env_applies_project_prefix() -> None:
env, _display = build_launch_env(8787, environ={}, project="frontend")
assert env[PROXY_ENV_KEY] == "http://127.0.0.1:8787/p/frontend/v1"
+ assert "GROK_CLI_CHAT_PROXY_BASE_URL" not in env
def test_grok_build_install_env_returns_proxy_url() -> None: