4 Commits

Author SHA1 Message Date
Kit OC5
44e824c762 push velocity: correlate the SSO-id subquery on the grouped column
Dry-run against the real gitea DB: 'subquery uses ungrouped column u.id'.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-23 14:06:10 -04:00
Kit OC5
4e2db1e2e0 push velocity: isolate its query so a failure never costs ci.run rows
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-23 13:06:20 -04:00
Kit OC5
54c63b4d89 push velocity: key humans on windy_identity_id (SSO link); no id -> system + caller
Telemetry UPDATE 2 actor rule: agent/human rows without actor_id are
quarantined. Forge humans sign in only via Windy SSO, so Gitea's
external_login_user.external_id is their windy_identity_id.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-23 13:06:17 -04:00
Kit OC5
ac83c4721e telemetry: detect push velocity from Gitea's action table (alert only)
git push never touches our API, so throttle.py can't see it. Gitea's
action table records every push; the 5-min sync-side emitter now reads
it and emits forge.push_velocity when an account crosses 60 pushes/1h,
500 pushes/24h (standard-band base) or 10 ref deletes/24h. One row per
account per rule per window while over; windyadmin (the sync) exempt.
Nothing sits in the push path and nothing is refused. HOLD until
Telemetry Boss declares the shape.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-23 13:06:17 -04:00
2 changed files with 3 additions and 164 deletions

View File

@@ -1,92 +0,0 @@
"""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

View File

@@ -33,7 +33,6 @@ 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")
@@ -47,16 +46,6 @@ 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:
@@ -65,7 +54,6 @@ class Result:
detail: str
seconds: float = 0.0
user_visible: str = ""
followups: list[Result] = field(default_factory=list)
@dataclass
@@ -80,8 +68,6 @@ 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:
@@ -105,18 +91,13 @@ 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:
res = Result(
return Result(
c.name, "slow", f"HTTP {r.status} in {elapsed:.1f}s (warn >{warn:.0f}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
return Result(c.name, "ok", f"HTTP {r.status} in {elapsed:.1f}s", elapsed, c.what_it_proves)
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})",
@@ -129,52 +110,6 @@ 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(
@@ -252,7 +187,6 @@ def build_checks() -> list[Check]:
method="POST",
body={"email": email, "password": pw},
warn_seconds=LOGIN_WARN_SECONDS,
after=_logout_after_login,
)
)
return checks
@@ -329,10 +263,7 @@ def main() -> int:
args = ap.parse_args()
previous = load_state()
results = []
for c in build_checks():
r = _probe(c)
results += [r, *r.followups]
results = [_probe(c) for c in build_checks()]
print(f"windy canary — {time.strftime('%Y-%m-%dT%H:%M:%SZ', time.gmtime())}\n")
for r in results: