compute guard: flag direct AI-provider use (Windy Mind is the only door), warn-only

Grant's rule (09-23): every model call goes through Windy Mind. The bridge
now posts windy-git/compute-guard on every PR head (lines the PR ADDS vs its
merge-base) and default-branch head (whole tree): provider hosts, provider
SDK imports/deps and raw provider key names. Warn-only: success + "⚠ WARN"
and a link to the first hit; COMPUTE_GUARD_MODE=block turns it red later.

Exceptions live in ci/compute-guard-allow.yml, each with a reason (Mind
itself, user-BYOK windy-agent / windy-code extension / windy-pro desktop +
MindPanel, windy-connect config writers). Tests, docs, comments, lockfiles,
vendored code and CI config are never scanned. Reads the sync's bare clones
(no docker exec); cached per (repo, sha, rules). Non-fatal; never a fake OK.

First cases = COMPUTE_BYPASS_AUDIT.md. Today on default branches: 38
findings in 3 repos (windy-chat audit #2, windy-pro account-server #3/#4,
windytalk reference/), 0 elsewhere.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

api/tests/test_compute_guard.py

@@ -0,0 +1,184 @@
+"""Compute guard: Windy Mind is the only door to AI compute (warn-only today)."""
+
+from __future__ import annotations
+
+import importlib.util
+import subprocess
+import sys
+from pathlib import Path
+
+import pytest
+
+ROOT = Path(__file__).resolve().parents[2]
+_spec = importlib.util.spec_from_file_location("compute_guard", ROOT / "scripts" / "compute_guard.py")
+cg = importlib.util.module_from_spec(_spec)
+sys.modules["compute_guard"] = cg
+_spec.loader.exec_module(cg)
+
+ALLOW = cg.load_allow(ROOT / "ci" / "compute-guard-allow.yml")
+
+
+@pytest.mark.parametrize(
+    "path, text, kind",
+    [
+        # audit #1 (windy-search, closed) and #2 (windy-chat, live): the shapes they had
+        ("service/app/anthropic_client.py", 'URL = "https://api.anthropic.com/v1/messages"', "provider host"),
+        ("service/app/config.py", 'token = os.environ["ANTHROPIC_OAUTH_TOKEN"]', "provider key"),
+        ("services/agent-roster/lib/llm.js", "const url = 'https://api.groq.com/openai/v1/chat/completions'", "provider host"),
+        ("docker-compose.yml", "      GROQ_API_KEY: ${GROQ_API_KEY}", "provider key"),
+        # audit #3/#4 (windy-pro account-server)
+        ("account-server/src/routes/transcription.ts", "const r = await fetch('https://api.openai.com/v1/audio/transcriptions'", "provider host"),
+        ("account-server/src/config.ts", "openaiKey: process.env.OPENAI_API_KEY,", "provider key"),
+        # SDKs and deps
+        ("app/llm.py", "from anthropic import Anthropic", "provider SDK"),
+        ("app/llm.py", "import openai", "provider SDK"),
+        ("app/llm.py", "import google.generativeai as genai", "provider SDK"),
+        ("src/ai.ts", 'import Anthropic from "@anthropic-ai/sdk";', "provider SDK"),
+        ("src/ai.js", "const Groq = require('groq-sdk')", "provider SDK"),
+        ("package.json", '    "openai": "^4.52.0",', "provider SDK dep"),
+        ("requirements.txt", "anthropic>=0.40", "provider SDK dep"),
+        ("pyproject.toml", '  "google-generativeai>=0.8",', "provider SDK dep"),
+    ],
+)
+def test_audit_shapes_are_flagged(path, text, kind):
+    assert kind in [k for k, _ in cg.scan_line(path, text)]
+
+
+@pytest.mark.parametrize(
+    "path, text",
+    [
+        ("app/mind.py", 'MIND = "https://mind.windyword.ai/v1/chat/completions"'),  # the door itself
+        ("app/models.py", "openai_compatible = True  # Mind speaks the OpenAI wire format"),
+        ("app/x.py", "from app.openai_shim import x"),  # a local module, not the SDK
+        ("package.json", '    "openai-types-lite": "1.0.0",'),  # a different package
+        ("README.txt", "set OPENAI_API_KEY"),  # scanned-by-rule, excluded by SKIP separately
+    ],
+)
+def test_near_misses_are_not_flagged(path, text):
+    if cg.SKIP.search(path):
+        return
+    assert cg.scan_line(path, text) == []
+
+
+@pytest.mark.parametrize(
+    "path",
+    ["tests/test_llm.py", "api/tests/x.py", "src/ai.test.ts", "web/foo.spec.js", "docs/setup.md",
+     "README.md", "package-lock.json", "uv.lock", "node_modules/openai/index.js", ".github/workflows/ci.yml",
+     "conftest.py", "app/llm_test.py"],
+)
+def test_tests_docs_lockfiles_vendored_ci_are_never_scanned(path):
+    assert cg.SKIP.search(path)
+
+
+def test_allow_list_needs_a_reason_per_entry(tmp_path):
+    bad = tmp_path / "a.yml"
+    bad.write_text("allow:\n  - repo: x\n    paths: ['*']\n")
+    with pytest.raises(ValueError):
+        cg.load_allow(bad)
+
+
+@pytest.mark.parametrize(
+    "repo, path, ok",
+    [
+        ("windy-mind", "app/providers/anthropic.py", True),
+        ("windy-agent", "agent/providers.py", True),
+        ("windy-code", "extensions/windy-ai/src/aiProvider.ts", True),
+        ("windy-code", "web/server/llm.ts", False),  # BYOK is the extension only
+        ("windy-connect", "backend/src/writers/claude_code.py", True),
+        ("windy-chat", "services/agent-roster/lib/llm.js", False),  # audit #2: must be flagged
+        ("windy-pro", "account-server/src/routes/translations.ts", False),
+    ],
+)
+def test_allow_list_entries(repo, path, ok):
+    assert cg.allowed(repo, path, ALLOW) is ok
+
+
+DIFF = """diff --git a/app/llm.py b/app/llm.py
+--- a/app/llm.py
++++ b/app/llm.py
+@@ -10,0 +11,2 @@
++import anthropic
++client = anthropic.Anthropic()
+diff --git a/tests/test_llm.py b/tests/test_llm.py
+--- /dev/null
++++ b/tests/test_llm.py
+@@ -0,0 +1 @@
++import anthropic
+@@ -40 +42 @@
+-x = 1
++x = 2
+"""
+
+
+def test_only_added_non_test_lines_are_findings():
+    fs = cg.parse_added("windy-chat", DIFF, ALLOW)
+    assert [(f.path, f.line, f.kind) for f in fs] == [("app/llm.py", 11, "provider SDK")]
+
+
+def _repo(tmp_path, files: dict[str, str]) -> tuple[Path, str]:
+    work = tmp_path / "w"
+    work.mkdir()
+    run = lambda *a: subprocess.run(["git", *a], cwd=work, check=True, capture_output=True)  # noqa: E731
+    run("init", "-q", "-b", "main")
+    for p, text in files.items():
+        (work / p).parent.mkdir(parents=True, exist_ok=True)
+        (work / p).write_text(text)
+    run("add", "-A")
+    run("-c", "user.email=t@t", "-c", "user.name=t", "commit", "-qm", "x")
+    bare = tmp_path / "r.git"
+    subprocess.run(["git", "clone", "-q", "--bare", str(work), str(bare)], check=True)
+    sha = subprocess.run(["git", "--git-dir", str(bare), "rev-parse", "main"],
+                         capture_output=True, text=True, check=True).stdout.strip()
+    return bare, sha
+
+
+def test_tree_scan_on_a_real_git_repo(tmp_path):
+    bare, sha = _repo(tmp_path, {
+        "app/llm.py": "import os\nKEY = os.environ['OPENAI_API_KEY']\n",
+        "app/ok.py": "MIND = 'https://mind.windyword.ai'\n",
+        "tests/test_llm.py": "import anthropic\n",
+        "docs/x.md": "api.anthropic.com\n",
+    })
+    fs = cg.scan_tree("windy-chat", bare, sha, ALLOW)
+    assert [(f.path, f.line, f.kind) for f in fs] == [("app/llm.py", 2, "provider key")]
+
+
+def test_warn_mode_never_turns_red(monkeypatch):
+    monkeypatch.setattr(cg, "MODE", "warn")
+    state, desc, f = cg.status_for([cg.Finding("a.py", 3, "provider host", "api.openai.com")], whole_tree=False)
+    assert state == "success" and desc.startswith("⚠ WARN (not blocking): 1 direct AI-provider use added")
+    assert "a.py:3" in desc and f.path == "a.py"
+
+
+def test_block_mode_fails(monkeypatch):
+    monkeypatch.setattr(cg, "MODE", "block")
+    state, desc, _ = cg.status_for([cg.Finding("a.py", 3, "provider host", "x")], whole_tree=True)
+    assert state == "failure" and desc.startswith("BLOCKED")
+
+
+def test_clean_is_ok():
+    assert cg.status_for([], whole_tree=True)[:2] == (
+        "success", "OK: no direct AI-provider use in tree (Windy Mind is the only door)")
+
+
+@pytest.mark.parametrize(
+    "text",
+    [
+        "    # The ANTHROPIC_OAUTH_TOKEN setting was removed on 2026-09-23 ON PURPOSE",  # windy-search
+        "# ANTHROPIC_API_KEY=",
+        "  // fallback used to call https://api.groq.com directly",
+        " * @see https://api.openai.com/v1/audio",
+        "<!-- api.anthropic.com -->",
+    ],
+)
+def test_comments_are_not_calls(text):
+    assert cg.scan_line("service/app/config.py", text) == []
+
+
+def test_code_with_a_trailing_comment_still_counts():
+    assert cg.scan_line("a.js", "fetch('https://api.openai.com/v1') // TODO move to Mind")
+
+
+def test_windy_pro_desktop_is_byok_but_the_account_server_is_not():
+    assert cg.allowed("windy-pro", "src/client/desktop/main.js", ALLOW)
+    assert not cg.allowed("windy-pro", "account-server/src/routes/translations.ts", ALLOW)

api/tests/test_pr_status_bridge.py

@@ -10,6 +10,7 @@ from __future__ import annotations
 
 import base64
 import importlib.util
+import sys
 from pathlib import Path
 
 import pytest
@@ -340,3 +341,44 @@ def test_lookup_failure_is_non_fatal(monkeypatch):
 
     monkeypatch.setattr(bridge.subprocess, "run", boom)
     assert bridge.queued_jobs("windy-chat", SHA) == []
+
+
+class _Guard:
+    def __init__(self, findings):
+        self.findings = findings
+
+    def check(self, repo, sha, default_branch, is_default_head):
+        return self.findings
+
+    @staticmethod
+    def status_for(findings, whole_tree):
+        if not findings:
+            return "success", "OK: clean", None
+        return "success", f"WARN {len(findings)}", findings[0]
+
+
+class _F:
+    path, line = "app/llm.py", 7
+
+
+def test_guard_posts_warn_with_a_link_to_the_first_finding(fake, monkeypatch):
+    f = fake()
+    monkeypatch.setitem(sys.modules, "compute_guard", _Guard([_F()]))
+    bridge.post_compute_guard("windy-chat", SHA, "main", False)
+    assert [(p["context"], p["state"], p["description"]) for p in f.posted] == [
+        ("windy-git/compute-guard", "success", "WARN 1")]
+    assert f.posted[0]["target_url"].endswith(f"/src/commit/{SHA}/app/llm.py#L7")
+
+
+def test_guard_same_status_is_not_reposted(fake, monkeypatch):
+    f = fake(statuses=[{"context": "windy-git/compute-guard", "state": "success", "description": "WARN 1"}])
+    monkeypatch.setitem(sys.modules, "compute_guard", _Guard([_F()]))
+    bridge.post_compute_guard("windy-chat", SHA, "main", False)
+    assert f.posted == []
+
+
+def test_guard_that_cannot_run_posts_nothing(fake, monkeypatch):
+    f = fake()
+    monkeypatch.setitem(sys.modules, "compute_guard", _Guard(None))
+    bridge.post_compute_guard("windy-chat", SHA, "main", True)
+    assert f.posted == []