ci: mount windy-pro's read-only build inputs into dind; allow exactly that path for jobs

Non-secret inputs git-ignored in windy-pro (models, linux-x64 portable
bundle, enter-monitor build) that build-desktop needs. Mounted :ro into
dind; valid_volumes allows only /ci-inputs/windy-pro; refresh-ci-inputs.sh
copies them from the frozen release clone (read-only on the source).
Invariant I-5 narrowed, not dropped: exactly that one path, read-only in
dind, no other service mounts it, still no docker socket (proven to fail
on :rw). Orchestrator-approved (option a). Applied in an idle window.

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

api/tests/test_canary_cleanup.py

@@ -0,0 +1,92 @@
+"""The canary's login probe must end the session it opens (journey cleanup rule)."""
+
+from __future__ import annotations
+
+import importlib.util
+import io
+import sys
+import urllib.error
+from pathlib import Path
+
+ROOT = Path(__file__).resolve().parents[2]
+_spec = importlib.util.spec_from_file_location("canary", ROOT / "scripts" / "canary.py")
+canary = importlib.util.module_from_spec(_spec)
+sys.modules["canary"] = canary  # dataclasses resolve their module by name
+_spec.loader.exec_module(canary)
+
+
+class _Resp:
+    def __init__(self, status=200, body=b"{}"):
+        self.status, self._body = status, body
+
+    def read(self):
+        return self._body
+
+    def __enter__(self):
+        return self
+
+    def __exit__(self, *a):
+        return False
+
+
+def _err(code):
+    return urllib.error.HTTPError(canary.LOGOUT_URL, code, "x", {}, io.BytesIO(b""))
+
+
+def _script(monkeypatch, outcomes):
+    calls = []
+
+    def fake(req, timeout=None):
+        calls.append((req.get_method(), req.full_url, req.get_header("Authorization")))
+        o = outcomes.pop(0)
+        if isinstance(o, Exception):
+            raise o
+        return o
+
+    monkeypatch.setattr(canary.urllib.request, "urlopen", fake)
+    return calls
+
+
+def test_logout_ends_the_session(monkeypatch):
+    calls = _script(monkeypatch, [_Resp(200)])
+    r = canary.logout("tok", sleep=lambda s: None)
+    assert r.status == "ok"
+    assert calls == [("POST", canary.LOGOUT_URL, "Bearer tok")]
+
+
+def test_5xx_and_no_response_are_retried_then_succeed(monkeypatch):
+    calls = _script(monkeypatch, [_err(502), OSError("reset"), _Resp(200)])
+    assert canary.logout("tok", sleep=lambda s: None).status == "ok"
+    assert len(calls) == 3
+
+
+def test_already_over_counts_as_done(monkeypatch):
+    _script(monkeypatch, [_err(401)])
+    assert canary.logout("tok", sleep=lambda s: None).status == "ok"
+
+
+def test_other_4xx_fails_fast_and_honestly(monkeypatch):
+    calls = _script(monkeypatch, [_err(400)])
+    r = canary.logout("tok", sleep=lambda s: None)
+    assert r.status == "down" and r.detail.startswith("CLEANUP FAILED") and len(calls) == 1
+
+
+def test_retries_are_bounded_and_reported(monkeypatch):
+    calls = _script(monkeypatch, [_err(503)] * 8)
+    r = canary.logout("tok", attempts=8, sleep=lambda s: None)
+    assert r.status == "down" and "CLEANUP FAILED after 8 tries" in r.detail and len(calls) == 8
+
+
+def test_login_probe_logs_out_with_the_token_it_got(monkeypatch):
+    calls = _script(monkeypatch, [_Resp(200, b'{"token": "abc"}'), _Resp(200)])
+    c = canary.Check("identity.login", "https://account.windyword.ai/api/v1/auth/login", "x",
+                     method="POST", body={"email": "e", "password": "p"},
+                     after=canary._logout_after_login)
+    r = canary._probe(c)
+    assert r.status == "ok" and [f.status for f in r.followups] == ["ok"]
+    assert calls[1] == ("POST", canary.LOGOUT_URL, "Bearer abc")
+
+
+def test_login_without_token_is_a_cleanup_failure_not_a_pass():
+    [f] = canary._logout_after_login(b"{}")
+    assert f.status == "down" and "CLEANUP FAILED" in f.detail

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_invariants.py

@@ -425,9 +425,28 @@ def test_i05_jobs_get_a_network_per_job_not_a_shared_bridge():
 
 
 def test_i05_jobs_cannot_bind_mount_from_the_daemon_host():
-    cfg = (ROOT / "deploy" / "runner" / "config.yaml").read_text()
-    assert "valid_volumes: []" in cfg
-    assert 'docker_host: "-"' in cfg
+    """Narrowed 2026-09-23 (orchestrator-approved): a job may bind-mount EXACTLY
+    one daemon path, windy-pro's non-secret build inputs, and only because dind
+    itself has that path READ-ONLY. Anything more (a second path, a writable
+    one, a glob) reopens the host to CI code. Still no docker socket for jobs."""
+    import re
+
+    import yaml
+
+    rd = ROOT / "deploy" / "runner"
+    cfg = yaml.safe_load((rd / "config.yaml").read_text())
+    allowed = cfg["container"]["valid_volumes"]
+    assert allowed in ([], ["/ci-inputs/windy-pro"]), f"I-5: jobs may mount nothing else: {allowed}"
+    assert cfg["container"]["docker_host"] == "-"
+    if allowed:
+        compose = yaml.safe_load((rd / "docker-compose.yml").read_text())
+        binds = [v for v in compose["services"]["dind"]["volumes"] if v.startswith("/")]
+        assert binds == ["/home/user1-gpu/ci-inputs/windy-pro:/ci-inputs/windy-pro:ro"], (
+            f"I-5: dind's only host bind must be the ci-inputs path, READ-ONLY: {binds}")
+        for name, svc in compose["services"].items():
+            if name != "dind":
+                for v in svc.get("volumes") or []:
+                    assert not re.match(r"^/home/user1-gpu/ci-inputs", v), f"I-5: {name} mounts ci-inputs"
 
 
 def test_i05_no_ci_container_can_reach_the_forge_network():

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
@@ -79,10 +80,11 @@ class Fake:
 
 @pytest.fixture
 def fake(monkeypatch):
-    def make(**kw):
+    def make(queued=(), **kw):
         f = Fake(**kw)
         monkeypatch.setattr(bridge, "gitea", f.gitea)
         monkeypatch.setattr(bridge, "github", f.github)
+        monkeypatch.setattr(bridge, "queued_jobs", lambda repo, sha: list(queued))
         return f
 
     return make
@@ -272,3 +274,111 @@ def test_gitea_dir_wins_over_github_dir(fake):
 )
 def test_workflow_problem(text, problem):
     assert bridge.workflow_problem(text) == problem
+
+
+def _q(n, wf, job):
+    return {"run_number": n, "workflow_id": wf, "name": job}
+
+
+def test_queued_job_shows_pending_instead_of_nothing(fake):
+    f = fake(queued=[_q(5, "ci.yml", "test")])
+    bridge.post_statuses("windy-chat", SHA)
+    assert [(p["context"], p["state"]) for p in f.posted] == [("windy-git/ci/test", "pending")]
+    assert f.posted[0]["target_url"].endswith("/actions/runs/5")
+
+
+def test_queued_rerun_supersedes_the_stale_failure(fake):
+    f = fake(runs=[_run(1, "ci.yml", "test", "failure", n=4)], queued=[_q(7, "ci.yml", "test")])
+    bridge.post_statuses("windy-chat", SHA)
+    assert [(p["context"], p["state"]) for p in f.posted] == [("windy-git/ci/test", "pending")]
+
+
+def test_older_queued_job_never_overrides_a_newer_verdict(fake):
+    f = fake(runs=[_run(1, "ci.yml", "test", "success", n=9)], queued=[_q(3, "ci.yml", "test")])
+    bridge.post_statuses("windy-chat", SHA)
+    assert [(p["context"], p["state"]) for p in f.posted] == [("windy-git/ci/test", "success")]
+
+
+def test_queued_docker_and_non_blocking_jobs_stay_unposted(fake):
+    f = fake(queued=[_q(2, "ci.yml", "docker-build"), _q(2, "ci.yml", "build-desktop")])
+    bridge.post_statuses("windy-pro", SHA)
+    assert f.posted == []
+
+
+def test_queued_lookup_refuses_unsafe_input():
+    assert bridge.queued_jobs("x'; drop table t;--", SHA) == []
+    assert bridge.queued_jobs("windy-chat", "not-a-sha") == []
+
+
+def _db(monkeypatch, jobs, labels):
+    import json as _json
+    import subprocess as _sp
+
+    payload = _json.dumps({"jobs": jobs, "labels": [_json.dumps(x) for x in labels]})
+    monkeypatch.setattr(
+        bridge.subprocess, "run",
+        lambda *a, **k: _sp.CompletedProcess(a, 0, stdout=payload, stderr=""),
+    )
+
+
+RUNNER = ["veron-1", "linux-x64", "self-hosted", "linux", "x64"]
+
+
+def test_only_jobs_a_runner_can_take_are_pending(monkeypatch):
+    # macos-latest is cancelled unpicked by the janitor: pending would never resolve.
+    _db(monkeypatch, [
+        {"run_number": 3, "workflow_id": "ci.yml", "name": "test", "runs_on": '["self-hosted","linux","x64"]'},
+        {"run_number": 3, "workflow_id": "ci.yml", "name": "mac", "runs_on": '["macos-latest"]'},
+    ], [RUNNER])
+    assert [j["name"] for j in bridge.queued_jobs("windy-chat", SHA)] == ["test"]
+
+
+def test_lookup_failure_is_non_fatal(monkeypatch):
+    import subprocess as _sp
+
+    def boom(*a, **k):
+        raise _sp.TimeoutExpired("docker", 30)
+
+    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 == []

ci/compute-guard-allow.yml

@@ -0,0 +1,40 @@
+# Compute guard allow-list: code that MAY talk to an AI provider directly.
+# Windy Mind is the ONLY door to AI compute (Grant, 2026-09-23). Every entry
+# here is an exception to that rule and MUST say why. Paths are fnmatch globs
+# relative to the repo root. Owner of this file: Windy Git lane (13); changes
+# go through the orchestrator. Source of the first entries: COMPUTE_BYPASS_AUDIT.md.
+allow:
+  - repo: windy-mind
+    paths: ["*"]
+    reason: "Windy Mind IS the door: provider clients belong here by definition."
+
+  - repo: windy-agent
+    paths: ["*"]
+    reason: >-
+      User BYOK: self-hosted agents call providers on the USER's own keys.
+      Mind stays opt-in there, or every self-hosted user's inference lands on
+      Grant's bill (no-cloud-cost-liability rule; audit #7).
+
+  - repo: windy-code
+    paths: ["extensions/windy-ai/*"]
+    reason: "User BYOK AI extension: the user's own provider keys; Mind is one opt-in provider (audit #8)."
+
+  - repo: windy-connect
+    paths: ["*writers/*"]
+    reason: "Writes client configs that NAME the user's own provider env vars; makes no provider calls (audit #11)."
+
+  - repo: windy-pro
+    paths: ["src/client/desktop/*"]
+    reason: >-
+      User BYOK desktop client: cloud STT/translate keys come from what the USER
+      enters (renderer localStorage -> electron-store; env var only for dev), and
+      the CSP line allows exactly those user-keyed hosts (audit #10). The
+      account-server is NOT covered: server-side calls go through Mind.
+
+  - repo: windy-pro
+    paths: ["src/client/web/src/pages/panels/MindPanel.jsx"]
+    reason: "Validates the USER's own OpenRouter key for BYOK (audit #10); spends no house money."
+
+  - repo: windy-git
+    paths: ["scripts/compute_guard.py", "ci/compute-guard-allow.yml"]
+    reason: "The guard's own pattern list and this file."

deploy/runner/config.yaml

@@ -54,6 +54,9 @@ container:
   privileged: false
   options:
   workdir_parent: /workspace
-  valid_volumes: []      # a job cannot bind-mount anything from the daemon host
+  # A job may bind-mount exactly ONE daemon path: the read-only windy-pro build
+  # inputs (mounted :ro into dind itself). Per-runner, not per-repo (act_runner
+  # limit): any windyadmin repo could mount it; it is non-secret and read-only.
+  valid_volumes: ["/ci-inputs/windy-pro"]
   docker_host: "-"       # do NOT expose the runner's own docker socket to jobs
   force_pull: false

deploy/runner/docker-compose.privileged.yml

@@ -0,0 +1,15 @@
+# ROLLBACK ONLY: the pre-Sysbox dind (privileged: true), kept one command away.
+# Use it if CI breaks under Sysbox:
+#
+#   cd /srv/windygit/src/deploy/runner
+#   sudo docker compose -f docker-compose.yml -f docker-compose.privileged.yml up -d dind
+#
+# (then restart the runners while idle). Compose merges `volumes` by container
+# path, so this puts back the old `dind-storage` volume with its image cache.
+# Going forward again: the same command without the second -f.
+services:
+  dind:
+    runtime: runc
+    privileged: true
+    volumes:
+      - dind-storage:/var/lib/docker

deploy/runner/docker-compose.yml

@@ -26,8 +26,12 @@
 #   * `dind` and every job container it spawns are UNTRUSTED. They are on a
 #     private network with no access to the forge, its database, or its .env.
 #
-# dind itself is privileged — that is the cost, and it is the reason a job
-# escape lands in a disposable daemon rather than on Grant's workstation.
+# dind is NOT privileged (2026-09-23): it runs under the Sysbox runtime
+# (sysbox-ce on Veron, `runtime: sysbox-runc`), a user-namespaced system
+# container whose root is an unprivileged host uid. A job that escapes its own
+# container lands in dind as a nobody on the host, not as root on Grant's
+# workstation. Before Sysbox, dind was `privileged: true`; that config is kept
+# as docker-compose.privileged.yml (ROLLBACK ONLY, one command, see that file).
 #
 # ⚠️ Do NOT "simplify" this by mounting the host docker socket.
 
@@ -36,13 +40,20 @@ name: windy-git-runner
 services:
   dind:
     image: docker.io/library/docker:27-dind
-    privileged: true
+    runtime: sysbox-runc   # NOT privileged: see the I-5 note above
     environment:
       DOCKER_TLS_CERTDIR: ""   # plain TCP on an isolated network, no host route
     command: ["dockerd", "--host=tcp://0.0.0.0:2375", "--tls=false"]
     networks: [jobs]
     volumes:
-      - dind-storage:/var/lib/docker
+      # A fresh volume: Sysbox shifts ownership to its own uid range. The old
+      # `dind-storage` is kept untouched for the privileged rollback.
+      - dind-storage-sysbox:/var/lib/docker
+      # READ-ONLY, non-secret build inputs for windy-pro's desktop jobs (models,
+      # linux-x64 portable bundle, enter-monitor build), copied from the frozen
+      # release clone by deploy/runner/refresh-ci-inputs.sh. Jobs may mount ONLY
+      # this path (config.yaml valid_volumes). Orchestrator-approved 09-23.
+      - /home/user1-gpu/ci-inputs/windy-pro:/ci-inputs/windy-pro:ro
     # G1.5 — bounded so a fork-bomb workflow cannot starve Grant's interactive
     # session. Veron 1 is his workstation, not a dedicated build box.
     cpus: 12.0            # 12 of 24 cores
@@ -159,6 +170,7 @@ networks:
 
 volumes:
   dind-storage:
+  dind-storage-sysbox:
   runner-data:
   runner-data-2:
   runner-data-3:

deploy/runner/refresh-ci-inputs.sh

@@ -0,0 +1,21 @@
+#!/usr/bin/env bash
+# Refresh the READ-ONLY CI input cache for windy-pro desktop jobs from the FROZEN
+# release clone on Veron. Reads ~/windy-pro-release only; never writes to it.
+# Run when the release lane says engines / wheels / the portable bundle changed.
+# Linux inputs only: 3 models + requirements-bundle.txt, bundled-portable/linux-x64,
+# native/enter-monitor/build. Result is chmod a-w and mounted :ro into dind.
+set -euo pipefail
+SRC=/home/user1-gpu/windy-pro-release
+DST=/home/user1-gpu/ci-inputs/windy-pro
+models=$(ls "$SRC/extraResources/model" | grep -E '^windy-(nano|lite|core)-ct2$')
+[ "$(wc -w <<<"$models")" = 3 ] || { echo "expected 3 models, got: $models"; exit 1; }
+mkdir -p "$DST/extraResources/model" "$DST/bundled-portable" "$DST/native-enter-monitor-build"
+chmod -R u+w "$DST"
+R="ionice -c3 nice -n 19 rsync -a --delete"
+for m in $models; do $R "$SRC/extraResources/model/$m/" "$DST/extraResources/model/$m/"; done
+$R "$SRC/extraResources/requirements-bundle.txt" "$DST/extraResources/requirements-bundle.txt"
+$R "$SRC/bundled-portable/linux-x64/" "$DST/bundled-portable/linux-x64/"
+$R "$SRC/native/enter-monitor/build/" "$DST/native-enter-monitor-build/"
+date -u +%FT%TZ > "$DST/.refreshed-from-windy-pro-release"
+chmod -R a-w "$DST"
+du -sh --apparent-size "$DST"

docs/RUNBOOK-VERON.md

@@ -152,3 +152,16 @@ disqualifying the moment a stranger depends on it. **The trigger is not a date
 it is the first external push.** Move the control plane to a dedicated VPS (not
 Kit 0), keep Veron 1 as the runner. It is an rsync, a Postgres dump and three
 DNS record edits.
+
+## Re-run a PR's CI (Gitea 1.24 has no rerun API)
+
+```bash
+ssh wg-veron
+cd /srv/windygit/src && bash scripts/rerun_ci.sh <repo> <branch> <github-head-sha-prefix>
+```
+Moves the Windy Git branch back one commit; the next sync force-pushes the
+GitHub head again and Gitea re-fires every workflow for that event on the same
+commit. Guarded: refuses unless the branch is at the given sha, waits for a
+sync that starts AFTER the rewind, restores the branch itself on timeout.
+Don't use the web "Re-run" button: it needs a hub-SSO session as windyadmin,
+which is Grant's identity.

scripts/canary.py

@@ -33,6 +33,7 @@ import sys
 import time
 import urllib.error
 import urllib.request
+from collections.abc import Callable
 from dataclasses import dataclass, field
 
 STATE_PATH = os.environ.get("CANARY_STATE", "canary-state.json")
@@ -46,6 +47,16 @@ ALERT_FROM = os.environ.get("CANARY_ALERT_FROM", "office@thewindstorm.uk")
 LOGIN_WARN_SECONDS = float(os.environ.get("CANARY_LOGIN_WARN_S", "35"))
 TIMEOUT = float(os.environ.get("CANARY_TIMEOUT_S", "60"))
 
+# Journey cleanup rule (orchestrator, 2026-09-23). The login probe creates a hub
+# session (access + refresh token) every run, so it must end it. The hub's
+# /auth/logout revokes the token AND every refresh token of the account
+# (verified live: access 401, refresh 401 after it). So the next successful
+# logout also heals anything a failed run left behind; no ledger needed.
+LOGOUT_URL = "https://account.windyword.ai/api/v1/auth/logout"
+LOGOUT_ATTEMPTS = 8       # retried on 5xx / no response only
+LOGOUT_GAP_S = 15.0
+LOGOUT_GONE = (401, 404, 410)  # the session is already over = done
+
 
 @dataclass
 class Result:
@@ -54,6 +65,7 @@ class Result:
     detail: str
     seconds: float = 0.0
     user_visible: str = ""
+    followups: list[Result] = field(default_factory=list)
 
 
 @dataclass
@@ -68,6 +80,8 @@ class Check:
     # When True this check INVERTS: a 2xx is a critical failure (a security
     # control opened) and a 401/403/503 is the healthy, expected outcome.
     must_refuse: bool = False
+    # Runs on a 2xx with the response body; returns follow-up results (cleanup).
+    after: Callable[[bytes], list[Result]] | None = None
 
 
 def _probe(c: Check) -> Result:
@@ -91,13 +105,18 @@ def _probe(c: Check) -> Result:
                               elapsed, c.what_it_proves)
             if r.status >= 400:
                 return Result(c.name, "down", f"HTTP {r.status}", elapsed, c.what_it_proves)
+            raw = r.read()
             warn = c.warn_seconds
             if warn and elapsed > warn:
-                return Result(
+                res = Result(
                     c.name, "slow", f"HTTP {r.status} in {elapsed:.1f}s (warn >{warn:.0f}s)",
                     elapsed, c.what_it_proves,
                 )
-            return Result(c.name, "ok", f"HTTP {r.status} in {elapsed:.1f}s", elapsed, c.what_it_proves)
+            else:
+                res = Result(c.name, "ok", f"HTTP {r.status} in {elapsed:.1f}s", elapsed, c.what_it_proves)
+            if c.after:
+                res.followups = c.after(raw)
+            return res
     except urllib.error.HTTPError as e:
         if c.must_refuse and e.code in (401, 403, 503):
             return Result(c.name, "ok", f"correctly refused (HTTP {e.code})",
@@ -110,6 +129,52 @@ def _probe(c: Check) -> Result:
         )
 
 
+def logout(token: str, *, attempts: int = LOGOUT_ATTEMPTS, gap: float = LOGOUT_GAP_S,
+           sleep: Callable[[float], None] = time.sleep) -> Result:
+    """End the session the login probe opened. Honest: never ok unless proven."""
+    what = "the canary leaves no live session behind (journey cleanup rule)"
+    headers = {
+        "User-Agent": "windy-git-canary/1.0",
+        "X-Windy-Synthetic": "1",
+        "Authorization": f"Bearer {token}",
+    }
+    start = time.monotonic()
+    last = "no attempt"
+    for i in range(attempts):
+        if i:
+            sleep(gap)
+        req = urllib.request.Request(LOGOUT_URL, data=b"", method="POST", headers=headers)
+        try:
+            with urllib.request.urlopen(req, timeout=TIMEOUT) as r:
+                return Result("identity.logout", "ok", f"session ended (HTTP {r.status})",
+                              time.monotonic() - start, what)
+        except urllib.error.HTTPError as e:
+            if e.code in LOGOUT_GONE:
+                return Result("identity.logout", "ok", f"session already over (HTTP {e.code})",
+                              time.monotonic() - start, what)
+            if e.code < 500:  # a 4xx won't change on retry: fail fast
+                return Result("identity.logout", "down", f"CLEANUP FAILED: HTTP {e.code}",
+                              time.monotonic() - start, what)
+            last = f"HTTP {e.code}"
+        except Exception as e:  # noqa: BLE001 — no response / timeout: retry
+            last = f"{type(e).__name__}"
+    return Result("identity.logout", "down",
+                  f"CLEANUP FAILED after {attempts} tries: {last} (next run's logout heals it)",
+                  time.monotonic() - start, what)
+
+
+def _logout_after_login(raw: bytes) -> list[Result]:
+    try:
+        token = (json.loads(raw or b"{}") or {}).get("token")
+    except ValueError:
+        token = None
+    if not token:
+        return [Result("identity.logout", "down",
+                       "CLEANUP FAILED: login returned no token to log out with",
+                       0.0, "the canary leaves no live session behind (journey cleanup rule)")]
+    return [logout(token)]
+
+
 def build_checks() -> list[Check]:
     checks = [
         Check(
@@ -187,6 +252,7 @@ def build_checks() -> list[Check]:
                 method="POST",
                 body={"email": email, "password": pw},
                 warn_seconds=LOGIN_WARN_SECONDS,
+                after=_logout_after_login,
             )
         )
     return checks
@@ -263,7 +329,10 @@ def main() -> int:
     args = ap.parse_args()
 
     previous = load_state()
-    results = [_probe(c) for c in build_checks()]
+    results = []
+    for c in build_checks():
+        r = _probe(c)
+        results += [r, *r.followups]
 
     print(f"windy canary — {time.strftime('%Y-%m-%dT%H:%M:%SZ', time.gmtime())}\n")
     for r in results:

scripts/compute_guard.py

@@ -0,0 +1,270 @@
+#!/usr/bin/env python3
+"""Compute guard: Windy Mind is the ONLY door to AI compute (Grant, 2026-09-23).
+
+Flags code that talks to an AI provider directly instead of through Windy Mind:
+a provider API host, a provider SDK import or dependency, or a raw provider key
+name. Direct calls skip Mind's metering, caps and live-model routing, and they
+spend whichever key happens to be lying around (the audit found Grant's personal
+Max OAuth token inside a platform container).
+
+WARN-ONLY for now: the bridge posts `windy-git/compute-guard` as success with a
+"⚠ WARN" description, so nothing turns red. `COMPUTE_GUARD_MODE=block` flips
+findings to failure once the repos are clean (orchestrator's call).
+
+- PR heads: only lines the PR ADDS (vs its merge-base with the default branch).
+- Default-branch head: the whole tree (the baseline, and what `report` prints).
+
+Exceptions live in ONE file, ci/compute-guard-allow.yml, each with a reason.
+Tests, docs, lockfiles, vendored code and CI config are never scanned.
+Reads the sync's bare GitHub clones on Veron (no docker exec: IO-stall lesson).
+
+  python3 scripts/compute_guard.py report [repo ...]   # whole-tree findings on each default branch
+"""
+
+from __future__ import annotations
+
+import fnmatch
+import hashlib
+import json
+import os
+import re
+import subprocess
+import sys
+from dataclasses import dataclass
+from pathlib import Path
+
+import yaml
+
+ROOT = Path(__file__).resolve().parents[1]
+ALLOW_FILE = Path(os.environ.get("COMPUTE_GUARD_ALLOW", ROOT / "ci" / "compute-guard-allow.yml"))
+WORK = Path(os.environ.get("SYNC_WORK", "/srv/windygit/sync"))
+CACHE = Path(os.environ.get("COMPUTE_GUARD_CACHE", "/var/lib/windy-git/compute-guard-cache.json"))
+MODE = os.environ.get("COMPUTE_GUARD_MODE", "warn")  # warn | block
+
+HOSTS = [
+    "api.anthropic.com", "api.openai.com", "api.groq.com",
+    "generativelanguage.googleapis.com", "api.mistral.ai", "api.perplexity.ai",
+    "openrouter.ai", "api.together.xyz", "api.together.ai", "api.cerebras.ai",
+    "api.sambanova.ai", "api.deepseek.com", "api.x.ai", "api.cohere.ai",
+    "api.cohere.com", "api.fireworks.ai", "api.replicate.com",
+    "api-inference.huggingface.co",
+]
+KEYS = [
+    "ANTHROPIC_API_KEY", "ANTHROPIC_OAUTH_TOKEN", "ANTHROPIC_AUTH_TOKEN",
+    "OPENAI_API_KEY", "GROQ_API_KEY", "GEMINI_API_KEY", "GOOGLE_GENERATIVE_AI_API_KEY",
+    "GOOGLE_AI_API_KEY", "MISTRAL_API_KEY", "PERPLEXITY_API_KEY", "PPLX_API_KEY",
+    "OPENROUTER_API_KEY", "TOGETHER_API_KEY", "CEREBRAS_API_KEY", "SAMBANOVA_API_KEY",
+    "DEEPSEEK_API_KEY", "XAI_API_KEY", "COHERE_API_KEY", "FIREWORKS_API_KEY",
+    "REPLICATE_API_TOKEN",
+]
+PY_SDKS = r"anthropic|openai|groq|mistralai|cohere|google\.generativeai|google\.genai|together|cerebras|litellm"
+JS_SDKS = (r"@anthropic-ai/sdk|openai|groq-sdk|@google/generative-ai|@google/genai|@mistralai/mistralai"
+           r"|cohere-ai|together-ai|@ai-sdk/(?:anthropic|openai|groq|google|mistral)")
+
+RULES: list[tuple[str, re.Pattern]] = [
+    ("provider host", re.compile("|".join(re.escape(h) for h in HOSTS))),
+    ("provider key", re.compile(r"\b(?:" + "|".join(KEYS) + r")\b")),
+    ("provider SDK", re.compile(rf"^\s*(?:from|import)\s+(?:{PY_SDKS})(?:\s|\.|$|,)")),
+    ("provider SDK", re.compile(rf"""(?:from\s+|require\(\s*|import\(\s*)['"](?:{JS_SDKS})(?:/[^'"]*)?['"]""")),
+    # dependency manifests: package.json keys, requirements / pyproject lines
+    ("provider SDK dep", re.compile(rf'''^\s*"(?:{JS_SDKS})"\s*:''')),
+    ("provider SDK dep", re.compile(rf'''^\s*["']?(?:{PY_SDKS.replace(chr(92) + ".", "-")})(?:\[[^\]]*\])?\s*(?:[<>=~!]=?|["',]|$)''')),
+]
+DEP_FILES = re.compile(r"(^|/)(package\.json|requirements[^/]*\.txt|pyproject\.toml|setup\.cfg|Pipfile)$")
+
+# Never scanned: tests, docs, lockfiles, vendored/built code, CI config.
+SKIP = re.compile(
+    r"(^|/)(tests?|__tests__|spec|docs?|node_modules|vendor|dist|build|\.github|\.gitea)/"
+    r"|(^|/)(test_[^/]*|[^/]*_test\.py|conftest\.py|[^/]*\.(test|spec)\.[cm]?[jt]sx?)$"
+    r"|\.(md|mdx|rst|txt|lock|snap|svg|png|jpg|pdf)$"
+    r"|(^|/)(package-lock\.json|pnpm-lock\.yaml|yarn\.lock|uv\.lock|poetry\.lock|Cargo\.lock)$"
+)
+
+
+@dataclass(frozen=True)
+class Finding:
+    path: str
+    line: int
+    kind: str
+    match: str
+
+
+def load_allow(path: Path = ALLOW_FILE) -> list[dict]:
+    data = yaml.safe_load(path.read_text()) or {}
+    entries = data.get("allow") or []
+    for e in entries:  # a reason per entry is the whole point of the file
+        if not (e.get("repo") and e.get("paths") and str(e.get("reason", "")).strip()):
+            raise ValueError(f"allow entry needs repo, paths and a reason: {e}")
+    return entries
+
+
+def allowed(repo: str, path: str, allow: list[dict]) -> bool:
+    for e in allow:
+        if e["repo"] == repo and any(fnmatch.fnmatch(path, g) for g in e["paths"]):
+            return True
+    return False
+
+
+COMMENT = re.compile(r"^\s*(?:#|//|/\*|\*|<!--)")
+
+
+def scan_line(path: str, text: str) -> list[tuple[str, str]]:
+    # A comment is not a call: "the ANTHROPIC_OAUTH_TOKEN setting was removed"
+    # (windy-search) must not count, nor a commented-out `# OPENAI_API_KEY=`.
+    if COMMENT.match(text):
+        return []
+    hits = []
+    for kind, rx in RULES:
+        if kind == "provider SDK dep" and not DEP_FILES.search(path):
+            continue
+        m = rx.search(text)
+        if m:
+            hits.append((kind, m.group(0).strip()[:60]))
+    return hits
+
+
+def _git(bare: Path, *args: str) -> str:
+    return subprocess.run(
+        ["git", "--git-dir", str(bare), *args],
+        capture_output=True, text=True, check=True, timeout=120,
+    ).stdout
+
+
+def scan_tree(repo: str, bare: Path, sha: str, allow: list[dict]) -> list[Finding]:
+    """Every line in the tree at `sha` (default branch: the baseline)."""
+    # A cheap prefilter by git, then the real rules in Python.
+    pre = "|".join([re.escape(h) for h in HOSTS] + KEYS + ["anthropic", "openai", "groq", "mistral",
+                   "generativeai", "genai", "cohere", "together", "cerebras", "litellm"])
+    try:
+        out = _git(bare, "grep", "-nIE", "-e", pre, sha, "--", ".")
+    except subprocess.CalledProcessError as e:
+        if e.returncode == 1:  # no matches
+            return []
+        raise
+    found = []
+    for raw in out.splitlines():
+        # <sha>:<path>:<line>:<text>
+        try:
+            _, path, line, text = raw.split(":", 3)
+        except ValueError:
+            continue
+        if SKIP.search(path) or allowed(repo, path, allow):
+            continue
+        for kind, match in scan_line(path, text):
+            found.append(Finding(path, int(line), kind, match))
+    return found
+
+
+def scan_added(repo: str, bare: Path, base_ref: str, sha: str, allow: list[dict]) -> list[Finding]:
+    """Only the lines a PR adds, vs its merge-base with the default branch."""
+    mb = _git(bare, "merge-base", base_ref, sha).strip()
+    diff = _git(bare, "diff", "-U0", "--no-color", "--no-ext-diff", mb, sha)
+    return parse_added(repo, diff, allow)
+
+
+HUNK = re.compile(r"^@@ -\d+(?:,\d+)? \+(\d+)(?:,\d+)? @@")
+
+
+def parse_added(repo: str, diff: str, allow: list[dict]) -> list[Finding]:
+    found, path, line = [], None, 0
+    for raw in diff.splitlines():
+        if raw.startswith("+++ "):
+            p = raw[4:]
+            path = None if p == "/dev/null" else p[2:] if p.startswith("b/") else p
+            continue
+        m = HUNK.match(raw)
+        if m:
+            line = int(m.group(1))
+            continue
+        if path is None or raw.startswith("--- "):
+            continue
+        if raw.startswith("+"):
+            if not (SKIP.search(path) or allowed(repo, path, allow)):
+                for kind, match in scan_line(path, raw[1:]):
+                    found.append(Finding(path, line, kind, match))
+            line += 1
+    return found
+
+
+# ---- cache: a tree scan runs once per (repo, sha, rules+allow) --------------
+def _fingerprint(allow: list[dict]) -> str:
+    return hashlib.sha256(
+        json.dumps([HOSTS, KEYS, PY_SDKS, JS_SDKS, SKIP.pattern, allow], sort_keys=True).encode()
+    ).hexdigest()[:16]
+
+
+def cached_scan(key: str, fn) -> list[Finding]:
+    try:
+        cache = json.loads(CACHE.read_text())
+    except (OSError, ValueError):
+        cache = {}
+    if key in cache:
+        return [Finding(**f) for f in cache[key]]
+    result = fn()
+    cache[key] = [f.__dict__ for f in result]
+    if len(cache) > 2000:  # keep it small: newest entries win
+        cache = dict(list(cache.items())[-1000:])
+    try:
+        CACHE.parent.mkdir(parents=True, exist_ok=True)
+        tmp = CACHE.with_suffix(".tmp")
+        tmp.write_text(json.dumps(cache))
+        tmp.replace(CACHE)
+    except OSError:
+        pass
+    return result
+
+
+def check(repo: str, sha: str, default_branch: str, is_default_head: bool) -> list[Finding] | None:
+    """Findings for one commit, or None when the guard can't run (never a fake OK)."""
+    bare = WORK / f"{repo}.git"
+    if not bare.is_dir():
+        return None
+    allow = load_allow()
+    fp = _fingerprint(allow)
+    if is_default_head:
+        return cached_scan(f"tree:{repo}:{sha}:{fp}", lambda: scan_tree(repo, bare, sha, allow))
+    return cached_scan(
+        f"pr:{repo}:{sha}:{fp}",
+        lambda: scan_added(repo, bare, f"refs/heads/{default_branch}", sha, allow),
+    )
+
+
+def status_for(findings: list[Finding], whole_tree: bool) -> tuple[str, str, Finding | None]:
+    """(state, description, first finding) for the GitHub commit status."""
+    scope = "in tree" if whole_tree else "added"
+    if not findings:
+        what = "no direct AI-provider use in tree" if whole_tree else "no direct AI-provider use added"
+        return "success", f"OK: {what} (Windy Mind is the only door)", None
+    f = findings[0]
+    n = len(findings)
+    state = "failure" if MODE == "block" else "success"
+    lead = "BLOCKED" if MODE == "block" else "⚠ WARN (not blocking)"
+    desc = f"{lead}: {n} direct AI-provider use{'s' if n > 1 else ''} {scope}, e.g. {f.path}:{f.line} {f.match}"
+    return state, desc[:140], f
+
+
+def report(repos: list[str]) -> int:
+    allow = load_allow()
+    total = 0
+    for repo in repos:
+        bare = WORK / f"{repo}.git"
+        if not bare.is_dir():
+            print(f"## {repo}: no sync clone, skipped")
+            continue
+        head = _git(bare, "symbolic-ref", "--short", "HEAD").strip()
+        sha = _git(bare, "rev-parse", head).strip()
+        fs = scan_tree(repo, bare, sha, allow)
+        total += len(fs)
+        print(f"## {repo} ({head} {sha[:7]}): {len(fs)} finding(s)")
+        for f in fs:
+            print(f"  {f.path}:{f.line}  [{f.kind}]  {f.match}")
+    print(f"TOTAL {total}")
+    return 0
+
+
+if __name__ == "__main__":
+    if len(sys.argv) >= 2 and sys.argv[1] == "report":
+        default = os.environ.get("BRIDGE_REPOS", "").split() or sorted(
+            p.name.removesuffix(".git") for p in WORK.glob("*.git"))
+        sys.exit(report(sys.argv[2:] or default))
+    sys.exit(__doc__)

scripts/pr_status_bridge.py

@@ -32,6 +32,7 @@ import base64
 import json
 import os
 import re
+import subprocess
 import sys
 import time
 import urllib.error
@@ -222,6 +223,54 @@ def sync_prs(repo: str) -> list[str]:
     return heads
 
 
+SAFE_NAME = re.compile(r"^[A-Za-z0-9._-]+$")
+SAFE_SHA = re.compile(r"^[0-9a-f]{40}$")
+
+
+def queued_jobs(repo: str, sha: str) -> list[dict]:
+    """Jobs at `sha` that are waiting for a runner and that a runner CAN take.
+
+    Gitea 1.24's API lists only PICKED-UP jobs (/actions/tasks), so a queued PR
+    showed nothing on GitHub and people asked whether the push was lost. The
+    truth is in the gitea DB. Bounded + non-fatal: during the 09-23 IO stall
+    `docker exec` hung for an hour and must never wedge the bridge again.
+
+    Only status 5 (waiting) with labels some live runner has. A `pending` we
+    post must end in a verdict we will also see, or it sits yellow forever:
+    blocked jobs (7) often end SKIPPED, and jobs for labels no runner has
+    (macos-/windows-/ubuntu-latest) are cancelled by the janitor unpicked;
+    neither ever appears in /actions/tasks.
+    """
+    if not (SAFE_NAME.match(repo) and SAFE_NAME.match(WG_OWNER) and SAFE_SHA.match(sha)):
+        return []
+    query = (
+        "select json_build_object("
+        " 'jobs', (select coalesce(json_agg(t), '[]'::json) from ("
+        "  select ar.index as run_number, ar.workflow_id, j.name, j.runs_on"
+        "  from action_run_job j join action_run ar on ar.id = j.run_id"
+        "  join repository r on r.id = j.repo_id join \"user\" o on o.id = r.owner_id"
+        f"  where o.lower_name = '{WG_OWNER.lower()}' and r.lower_name = '{repo.lower()}'"
+        f"  and ar.commit_sha = '{sha}' and j.status = 5) t),"
+        " 'labels', (select coalesce(json_agg(agent_labels), '[]'::json)"
+        "  from action_runner where coalesce(deleted, 0) = 0));"
+    )
+    try:
+        out = subprocess.run(
+            ["docker", "exec", "-i", "windy-git-db-1", "sh", "-c",
+             'psql -U "$POSTGRES_USER" -d gitea -At -v ON_ERROR_STOP=1'],
+            input=query, capture_output=True, text=True, check=True, timeout=30,
+        ).stdout.strip()
+        got = json.loads(out or "{}")
+        runners = [set(json.loads(x or "[]")) for x in got.get("labels") or []]
+        return [
+            j for j in got.get("jobs") or []
+            if any(set(json.loads(j.get("runs_on") or "[]")) <= r for r in runners)
+        ]
+    except (subprocess.SubprocessError, OSError, ValueError) as e:
+        print(f"  {repo}: queued-job lookup skipped ({type(e).__name__})")
+        return []
+
+
 def post_statuses(repo: str, sha: str) -> None:
     # Gitea caps a page at 50 (MAX_RESPONSE_ITEMS) whatever `limit` says, and a
     # daily scheduled workflow can push a quiet main's runs off page 1.
@@ -242,6 +291,17 @@ def post_statuses(repo: str, sha: str) -> None:
         ctx = f"windy-git/{r['workflow_id'].removesuffix('.yml')}/{r['name']}"
         if ctx not in latest or r["id"] > latest[ctx]["id"]:
             latest[ctx] = r
+    # Queued jobs: `pending` where nothing newer has been picked up. A re-run
+    # queued behind an old failure must read pending, not the stale red.
+    for q in queued_jobs(repo, sha):
+        if NO_DAEMON_JOB.search(q["name"]):
+            continue
+        wf = q["workflow_id"].removesuffix(".yml")
+        if f"{wf}/{q['name']}" in NON_BLOCKING.get(repo, ()):
+            continue
+        ctx = f"windy-git/{wf}/{q['name']}"
+        if ctx not in latest or q["run_number"] > latest[ctx]["run_number"]:
+            latest[ctx] = {"id": 0, "status": "waiting", "run_number": q["run_number"]}
     bad = invalid_workflows(repo, sha)
     if not (latest or bad):
         return
@@ -283,6 +343,37 @@ def post_statuses(repo: str, sha: str) -> None:
         print(f"  {repo}@{sha[:7]} {ctx} = {state} -> {st}")
 
 
+GUARD_CTX = "windy-git/compute-guard"
+
+
+def post_compute_guard(repo: str, sha: str, default_branch: str, is_default_head: bool) -> None:
+    """Windy Mind is the only door to AI compute: flag direct provider use (warn-only).
+
+    Non-fatal and never a fake OK: if the guard can't run, nothing is posted.
+    """
+    try:
+        import compute_guard as cg  # same directory; loaded lazily so the bridge never depends on it
+
+        findings = cg.check(repo, sha, default_branch, is_default_head)
+    except Exception as e:  # noqa: BLE001 — the guard must never break CI signals
+        print(f"  {repo}@{sha[:7]} compute-guard skipped ({type(e).__name__}: {str(e)[:80]})")
+        return
+    if findings is None:
+        return
+    state, desc, first = cg.status_for(findings, whole_tree=is_default_head)
+    st, existing = github("GET", f"/repos/{GH_OWNER}/{repo}/commits/{sha}/statuses?per_page=100")
+    for s in existing or []:  # newest first: compare the latest guard status only
+        if s["context"] == GUARD_CTX:
+            if (s["state"], s.get("description")) == (state, desc):
+                return
+            break
+    url = (f"{PUBLIC}/{WG_OWNER}/{repo}/src/commit/{sha}/{first.path}#L{first.line}"
+           if first else f"{PUBLIC}/{WG_OWNER}/{repo}/src/commit/{sha}")
+    st, _ = github("POST", f"/repos/{GH_OWNER}/{repo}/statuses/{sha}",
+                   {"state": state, "context": GUARD_CTX, "description": desc, "target_url": url})
+    print(f"  {repo}@{sha[:7]} {GUARD_CTX} = {state} ({len(findings)} finding(s)) -> {st}")
+
+
 def main() -> int:
     if not (GITEA_TOKEN and GITHUB_TOKEN):
         sys.exit("GITEA_ADMIN_TOKEN and GITHUB_TOKEN are required")
@@ -290,13 +381,17 @@ def main() -> int:
     for repo in REPOS:
         try:
             shas = sync_prs(repo)
+            default_branch, default_head = "main", None
             st, br = github("GET", f"/repos/{GH_OWNER}/{repo}")
             if st == 200:
-                st, b = github("GET", f"/repos/{GH_OWNER}/{repo}/branches/{br['default_branch']}")
+                default_branch = br["default_branch"]
+                st, b = github("GET", f"/repos/{GH_OWNER}/{repo}/branches/{default_branch}")
                 if st == 200:
-                    shas.append(b["commit"]["sha"])
+                    default_head = b["commit"]["sha"]
+                    shas.append(default_head)
             for sha in dict.fromkeys(shas):
                 post_statuses(repo, sha)
+                post_compute_guard(repo, sha, default_branch, sha == default_head)
         except Exception as e:  # one repo's failure must not hide the others'
             print(f"  FAILED {repo}: {e}")
             failed = 1

scripts/rerun_ci.sh

@@ -0,0 +1,49 @@
+#!/usr/bin/env bash
+# Re-run a PR's (or branch's) CI on Windy Git. Runs ON Veron 1.
+#
+#   bash scripts/rerun_ci.sh <repo> <branch> <sha-prefix>
+#
+# Gitea 1.24 has NO rerun API; the web button needs a hub-SSO session as
+# windyadmin, which is Grant's identity, so we don't use it. Instead: move the
+# Windy Git branch back one commit, let the next sync force-push the GitHub head
+# again, and Gitea fires an ordinary push / pull_request_sync event on the SAME
+# commit. Every workflow on that event re-runs, not only the failed one.
+#
+# Safety: refuses unless the branch is exactly at <sha-prefix> (GitHub's head),
+# never rewinds while a sync is running (a run already past this repo would
+# not push it back), waits for a sync that STARTS after the rewind, and if the
+# branch is not verifiably back at <sha-prefix> by the deadline, restores it
+# itself, so Windy Git is never left behind GitHub.
+set -euo pipefail
+repo="${1:?repo}"; branch="${2:?branch}"; want="${3:?sha prefix}"
+G="sudo docker exec -u git windy-git-gitea-1 git -C /data/git/repositories/windyadmin/${repo}.git"
+
+head=$($G rev-parse "refs/heads/${branch}")
+[[ "$head" == "$want"* ]] || { echo "refusing: ${branch} is at ${head:0:7}, not ${want}"; exit 1; }
+parent=$($G rev-parse "${head}^")
+
+# NOT `systemctl is-active`: the sync is Type=oneshot, which reads "activating"
+# (exit 3) for its whole run, so is-active says "idle" mid-run.
+busy() { case "$(systemctl show windygit-sync -p ActiveState --value)" in
+  activating|active|deactivating|reloading) return 0;; esac; return 1; }
+while busy; do sleep 5; done
+$G update-ref "refs/heads/${branch}" "$parent" "$head"
+mark=$(awk '{print int($1*1000000)}' /proc/uptime)
+echo "rewound ${repo}:${branch} ${head:0:7} -> ${parent:0:7}"
+
+deadline=$(( $(date +%s) + 900 ))
+until [ "$(systemctl show windygit-sync -p ExecMainStartTimestampMonotonic --value)" -gt "$mark" ] \
+      && [ "$($G rev-parse "refs/heads/${branch}")" = "$head" ]; do
+  if [ "$(date +%s)" -ge "$deadline" ]; then
+    $G update-ref "refs/heads/${branch}" "$head" "$($G rev-parse "refs/heads/${branch}")" || true
+    echo "TIMEOUT: restored ${branch} to ${head:0:7} by hand; NO new run fired"; exit 1
+  fi
+  sleep 10
+done
+echo "restored by sync: ${branch} = ${head:0:7}"
+sleep 5
+~/bin/wg-q <<SQL
+select ar.index, ar.workflow_id, ar.event, ar.status, to_char(to_timestamp(ar.created),'HH24:MI:SS')
+  from action_run ar join repository r on r.id = ar.repo_id
+ where r.name = '${repo}' and ar.commit_sha = '${head}' order by ar.id desc limit 6;
+SQL

scripts/sync_from_github.sh

@@ -82,7 +82,11 @@ done
 
 # Jobs that name labels no runner has (ubuntu/macos/windows-latest) would wait
 # forever and invisibly; cancel them after 30 min. Never fails the sync.
-bash "$(dirname "$0")/cancel_unrunnable.sh" || log "janitor failed (non-fatal)"
+# Both DB steps go through `docker exec`, which hangs outright while the host
+# is in an IO stall (09-23: data2 SMR cliff wedged this sync for 10+ min and
+# stopped mirroring + the bridge for every lane). They are optional; mirroring
+# and the bridge are not. Bound them so a stuck exec costs one step, not the run.
+timeout -k 10 120 bash "$(dirname "$0")/cancel_unrunnable.sh" || log "janitor failed or timed out (non-fatal)"
 
 # Private repos can't run GitHub Actions; mirror their open PRs here so CI
 # fires, and post the verdicts back to GitHub as commit statuses.
@@ -92,7 +96,7 @@ fi
 
 # CI telemetry -> admin.windyword.ai (shapes declared with Windy Telemetry 40).
 # Sends nothing until WINDYGIT_TELEMETRY_TOKEN is set; never fails the sync.
-python3 "$(dirname "$0")/telemetry_emit.py" || log "telemetry emit failed (non-fatal)"
+timeout -k 10 180 python3 "$(dirname "$0")/telemetry_emit.py" || log "telemetry emit failed or timed out (non-fatal)"
 
 [[ "$FAILED" -ne 0 ]] && { log "COMPLETED WITH FAILURES"; exit 1; }
 log "all repos in step with GitHub"

scripts/telemetry_emit.py

@@ -96,7 +96,7 @@ PV_EXEMPT = {"windyadmin"}
 PV_QUERY = """
     select a.act_user_id as uid, u.lower_name as login,
            (select el.external_id from external_login_user el
-             where el.user_id = u.id order by el.external_id limit 1) as wid,
+             where el.user_id = a.act_user_id order by el.external_id limit 1) as wid,
            count(*) filter (where a.op_type in (5, 9) and a.created_unix > {h1}) as p1h,
            count(*) filter (where a.op_type in (5, 9)) as p24h,
            count(*) filter (where a.op_type in (16, 17)) as d24h,
@@ -277,8 +277,14 @@ def main() -> int:
         }
     )
 
-    pv_rows = sql(PV_QUERY.format(h1=int(now) - 3600, h24=int(now) - 86400))
-    pv_events, pv_alerted = push_velocity_events(pv_rows, now, state.get("pv_alerted", {}))
+    # Isolated: a failing push-velocity query must never cost the ci.run rows.
+    pv_alerted = state.get("pv_alerted", {})
+    try:
+        pv_rows = sql(PV_QUERY.format(h1=int(now) - 3600, h24=int(now) - 86400))
+        pv_events, pv_alerted = push_velocity_events(pv_rows, now, pv_alerted)
+    except (subprocess.CalledProcessError, ValueError, KeyError) as e:
+        print(f"[telemetry] push velocity check FAILED (non-fatal): {type(e).__name__}")
+        pv_events = []
     for e in pv_events:
         m = e["metadata"]
         print(f"[telemetry] WARNING push velocity: gitea user {m['gitea_user_id']} "