merge: SP25 + SP26 SFTP polling + secret-file lookup into Version-1.0.0

Bring the SP25 SFTP Polling Enablement (PATCH /api/clearhouse,
scheduler hot-reload, env-var-first secret lookup) and SP26
SFTP Password File Companion (Docker secret _FILE tier) onto
the v1.0.0 release branch so the production stack can actually
flip the Gainwell MFT poll from stub → real.

Conflict resolved in docker-compose.yml: kept both the SP26
CYCLONE_SFTP_PASSWORD_FILE env var and the new 'Always bind
to 0.0.0.0' comment.
This commit is contained in:
tyler
2026-06-24 18:09:32 -06:00
16 changed files with 3189 additions and 14 deletions
+66
View File
@@ -2604,6 +2604,72 @@ def get_clearhouse():
return json.loads(ch.model_dump_json())
@app.patch("/api/clearhouse", dependencies=[Depends(matrix_gate)])
async def patch_clearhouse(body: dict) -> Any:
"""Replace the singleton clearhouse row (SP25).
The full ``Clearhouse`` model is required — we don't accept partial
updates because the operator-facing use case is "I'm switching the
loop to real MFT" or "I'm pointing at a different MFT server",
not "I'm tweaking one field at a time." Validation errors are
returned as 422 (Pydantic default).
After a successful write, the running scheduler is hot-reloaded
via ``scheduler.reconfigure_scheduler()`` so the next tick uses
the new SftpBlock without a process restart.
"""
from cyclone import scheduler as _scheduler_mod
from cyclone.providers import Clearhouse as _Clearhouse, SftpBlock as _SftpBlock
# Strict-validate the sftp_block sub-dict FIRST. Pydantic v2's
# default mode coerces strings to bools (e.g. ``"stub": "yes"``
# silently becomes True), which would hide a real operator
# mistake. The Clearhouse model itself stays in loose mode so
# ISO-string ``updated_at`` (the JSON round-trip shape) keeps
# parsing.
raw_sb = body.get("sftp_block", {})
try:
_SftpBlock.model_validate(raw_sb, strict=True)
except Exception as exc:
raise HTTPException(
status_code=422, detail=f"invalid sftp_block: {exc}",
) from exc
# Now validate the full body in loose mode.
try:
parsed = _Clearhouse.model_validate(body)
except Exception as exc:
raise HTTPException(status_code=422, detail=str(exc)) from exc
# SP25: when sftp_block.stub=false, the block must carry an auth
# account name and a non-empty host. The Pydantic model catches
# some of these; this catches the "empty password_keychain_account"
# case (which Pydantic allows because it's a free-form dict).
sb = parsed.sftp_block
if not sb.stub:
if not sb.host:
raise HTTPException(
status_code=422,
detail="sftp_block.host is required when stub=false",
)
auth = sb.auth or {}
if not auth.get("password_keychain_account") and not auth.get("key_file"):
raise HTTPException(
status_code=422,
detail=(
"sftp_block.auth must contain either "
"'password_keychain_account' or 'key_file' when stub=false"
),
)
updated = store.update_clearhouse(parsed)
await _scheduler_mod.reconfigure_scheduler(
updated.sftp_block,
sftp_block_name=updated.name or "default",
)
return json.loads(updated.model_dump_json())
@app.post("/api/clearhouse/submit", dependencies=[Depends(matrix_gate)])
def submit_to_clearhouse(request: Request, body: dict):
"""Submit a batch of claims to the clearhouse (SFTP). SP9: stub.
+59 -1
View File
@@ -69,6 +69,11 @@ STATUS_SKIPPED = "skipped"
STATUS_PENDING = "pending"
# How long reconfigure_scheduler waits for the in-flight tick to
# drain before cancelling the old task. Matches Scheduler.stop().
_DRAIN_TIMEOUT_SECONDS = 30
# File types we know how to route. The HCPF set is broader (270/271/
# 276/277/278/820/834/ENCR) but Cyclone's parser only covers the
# four below. Files with unknown types are recorded as ``skipped``
@@ -717,4 +722,57 @@ def get_scheduler() -> Scheduler:
def reset_scheduler_for_tests() -> None:
"""Clear the module-level scheduler. Test-only."""
global _scheduler
_scheduler = None
_scheduler = None
async def reconfigure_scheduler(
sftp_block: SftpBlock,
*,
poll_interval_seconds: int = 60,
sftp_block_name: str = "default",
) -> Scheduler:
"""Replace the singleton scheduler; restart if it was running. SP25.
Called from ``PATCH /api/clearhouse`` so the next scheduler tick
uses the new SftpBlock without a process restart.
Lifecycle:
* If the previous scheduler is running, ``stop()`` it (waits
up to ``_DRAIN_TIMEOUT_SECONDS`` for the current tick to
finish — matches the existing ``Scheduler.stop()`` timeout).
* Replace the module-level ``_scheduler`` singleton with a
fresh ``Scheduler`` against the new block.
* If the previous one was running, ``start()`` the new one.
Threading: same constraint as ``configure_scheduler`` — must be
called from the FastAPI event loop, not a worker thread.
"""
global _scheduler
was_running = False
if _scheduler is not None:
was_running = _scheduler.is_running()
if was_running:
# Drain the in-flight tick. Scheduler.stop() already
# applies the _DRAIN_TIMEOUT_SECONDS timeout internally;
# we just await it.
await _scheduler.stop()
poll = int(
os.environ.get("CYCLONE_SCHEDULER_POLL_SECONDS", poll_interval_seconds),
)
_scheduler = Scheduler(
sftp_block,
poll_interval_seconds=poll,
sftp_block_name=sftp_block_name,
)
if was_running:
await _scheduler.start()
log.info(
"Scheduler reconfigured",
extra={
"was_running": was_running,
"sftp_block": sftp_block_name,
"host": sftp_block.host,
"stub": sftp_block.stub,
},
)
return _scheduler
+91 -12
View File
@@ -14,11 +14,36 @@ Setup (one-time, by the operator):
Verification:
security find-generic-password -s cyclone -a sftp.gainwell.password -w
SP25 + SP26: the lookup now resolves the secret in four tiers, in
this order:
1. ``<env_name>_FILE`` env var set — highest priority. Reads the
file at that path, strips whitespace, returns the contents.
This is the standard Docker-secrets pattern: mount a file at
``/run/secrets/<name>`` and point the env var at it. An
operator who explicitly sets ``_FILE`` is making a positive
statement about where the secret lives, so a missing file
surfaces as a ``RuntimeError`` rather than silently falling
through. Empty string is treated as unset.
2. Plain env var named exactly ``<env_name>`` — second priority.
Lets a Linux server or Docker container pass the MFT password
via ``CYCLONE_SFTP_PASSWORD=...`` without touching the Keychain
or a file mount. Trailing/leading whitespace (including the
``\\n`` that .env files often leave at EOF) is stripped; an
empty value is treated as absent.
3. macOS Keychain via ``keyring`` — third priority. Kept as a
fallback so a macOS workstation that prefers
``security add-generic-password`` works without env-var exports.
4. ``None`` — caller decides what to do (``SftpClient._connect``
raises a precise ``RuntimeError`` on real-mode auth).
"""
from __future__ import annotations
import logging
import os
from pathlib import Path
from typing import Optional
log = logging.getLogger(__name__)
@@ -36,24 +61,68 @@ except ImportError:
_HAS_KEYRING = False
def _env_var_for(name: str) -> str:
"""Resolve the operator-facing env-var name for a secret.
Returns the entry from ``_ENV_NAME_FOR`` if present, otherwise
returns ``name`` verbatim.
"""
return _ENV_NAME_FOR.get(name, name)
def get_secret(name: str) -> Optional[str]:
"""Fetch a secret from macOS Keychain by name.
"""Fetch a secret by name. Four-tier lookup: _FILE, env var, Keychain, None.
Args:
name: The Keychain account (e.g. "sftp.gainwell.password").
name: The secret name. Matches the Keychain account name
(e.g. ``"sftp.gainwell.password"``). The operator-facing
env-var form is mapped via the ``_ENV_NAME_FOR`` table at
the bottom of this module.
Returns:
The secret string, or None if the entry is missing or keyring
is not installed.
The secret string (stripped), or ``None`` if no tier produced
a value.
Raises:
RuntimeError: if ``<env_name>_FILE`` is set but the file at
that path is missing or unreadable. The operator made a
positive statement about where the secret lives; silent
fall-through would mask a misconfiguration.
"""
if not _HAS_KEYRING:
log.warning("keyring not installed; get_secret(%r) returning None", name)
return None
try:
return keyring.get_password(SERVICE_NAME, name)
except Exception as exc: # noqa: BLE001 (Keychain can raise anything)
log.warning("Keychain get_secret(%r) failed: %s", name, exc)
return None
env_name = _env_var_for(name)
file_env = env_name + "_FILE"
file_path_raw = os.environ.get(file_env)
if file_path_raw:
# An empty string is treated as unset (matches the SP25 rule
# for plain env vars).
stripped_path = file_path_raw.strip()
if stripped_path:
try:
value = Path(stripped_path).read_text().strip()
except OSError as exc:
raise RuntimeError(
f"failed to read {file_env}={stripped_path}: {exc}"
) from exc
if value:
log.debug("Secret %r resolved from file %r", name, stripped_path)
return value
raw = os.environ.get(env_name)
if raw is not None:
stripped = raw.strip()
if stripped:
log.debug("Secret %r resolved from env var %r", name, env_name)
return stripped
# Empty env var — treat as absent and fall through.
if _HAS_KEYRING:
try:
value = keyring.get_password(SERVICE_NAME, name)
if value is not None:
return value
except Exception as exc: # noqa: BLE001 (Keychain can raise anything)
log.warning("Keychain get_secret(%r) failed: %s", name, exc)
return None
def set_secret(name: str, value: str) -> bool:
@@ -77,3 +146,13 @@ def has_keyring() -> bool:
"""True if the ``keyring`` library is importable (regardless of whether
the Keychain entry actually exists)."""
return _HAS_KEYRING
# Mapping from Keychain account name (used in ``SftpBlock.auth``) to
# the operator-facing env var. Keeping this table here means callers
# don't have to remember the difference between
# ``sftp.gainwell.password`` (Keychain account) and
# ``CYCLONE_SFTP_PASSWORD`` (env var).
_ENV_NAME_FOR: dict[str, str] = {
"sftp.gainwell.password": "CYCLONE_SFTP_PASSWORD",
}
+43
View File
@@ -2302,6 +2302,49 @@ class CycloneStore:
"updated_at": row.updated_at,
})
def update_clearhouse(self, block: Clearhouse) -> Clearhouse:
"""Replace the singleton clearhouse row. SP25.
Used by ``PATCH /api/clearhouse`` to flip ``sftp_block.stub``
and adjust host/port/paths without touching SQLite directly.
Raises ``LookupError`` if the singleton row is missing — the
caller is expected to run the lifespan seed first.
"""
from cyclone.db import ClearhouseORM
with db.SessionLocal()() as s:
row = s.get(ClearhouseORM, 1)
if row is None:
raise LookupError(
"clearhouse singleton row missing; run the lifespan "
"seed (ensure_clearhouse_seeded) before PATCH /api/clearhouse"
)
row.name = block.name
row.tpid = block.tpid
row.submitter_name = block.submitter_name
row.submitter_id_qual = block.submitter_id_qual
row.submitter_contact_name = block.submitter_contact_name
row.submitter_contact_email = block.submitter_contact_email
row.filename_block_json = json.loads(
json.dumps(block.filename_block.model_dump())
)
row.sftp_block_json = json.loads(
json.dumps(block.sftp_block.model_dump())
)
row.updated_at = datetime.now(timezone.utc).isoformat()
s.commit()
return Clearhouse.model_validate({
"id": 1,
"name": row.name,
"tpid": row.tpid,
"submitter_name": row.submitter_name,
"submitter_id_qual": row.submitter_id_qual,
"submitter_contact_name": row.submitter_contact_name,
"submitter_contact_email": row.submitter_contact_email,
"filename_block": dict(row.filename_block_json),
"sftp_block": dict(row.sftp_block_json),
"updated_at": row.updated_at,
})
def ensure_clearhouse_seeded(self) -> None:
"""Insert the default clearhouse singleton + 3 providers + CO_TXIX payer
if they don't exist. Idempotent. Called from the API lifespan."""