Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
84353d3343 | ||
|
|
14b03fc893 | ||
|
|
04100a1aae | ||
|
|
e13f601cff | ||
|
|
1e7d1969cd | ||
|
|
d2a3814a2f | ||
|
|
c444622279 |
@@ -11,3 +11,7 @@ runtime/tmp/
|
||||
runtime/cache/
|
||||
logs/
|
||||
config/test_write_perms
|
||||
/data/webops.sqlite3
|
||||
/data/webops.sqlite3-wal
|
||||
/data/webops.sqlite3-shm
|
||||
/data/webops.sqlite3-journal
|
||||
|
||||
@@ -0,0 +1,89 @@
|
||||
"""Append-only audit chain for AIOS V2R1."""
|
||||
from __future__ import annotations
|
||||
|
||||
import hashlib
|
||||
import json
|
||||
from pathlib import Path
|
||||
import sqlite3
|
||||
from typing import Any
|
||||
|
||||
from .tenant_context import canonical_json, isoformat, require_ident
|
||||
|
||||
|
||||
class AuditLog:
|
||||
def __init__(self, database: str | Path) -> None:
|
||||
self.database = str(database)
|
||||
with sqlite3.connect(self.database) as db:
|
||||
db.execute("PRAGMA journal_mode=WAL")
|
||||
db.execute(
|
||||
"""
|
||||
CREATE TABLE IF NOT EXISTS audit_events (
|
||||
seq INTEGER PRIMARY KEY AUTOINCREMENT,
|
||||
tenant_id TEXT NOT NULL,
|
||||
trace_id TEXT NOT NULL,
|
||||
event_type TEXT NOT NULL,
|
||||
payload TEXT NOT NULL,
|
||||
previous_hash TEXT NOT NULL,
|
||||
event_hash TEXT NOT NULL UNIQUE,
|
||||
created_at TEXT NOT NULL
|
||||
)
|
||||
"""
|
||||
)
|
||||
|
||||
def append(self, *, tenant_id: str, trace_id: str, event_type: str, payload: dict[str, Any]) -> str:
|
||||
tenant_id = require_ident("tenant_id", tenant_id, tenant=True)
|
||||
trace_id = require_ident("trace_id", trace_id)
|
||||
event_type = require_ident("event_type", event_type)
|
||||
with sqlite3.connect(self.database) as db:
|
||||
previous = db.execute(
|
||||
"SELECT event_hash FROM audit_events ORDER BY seq DESC LIMIT 1"
|
||||
).fetchone()
|
||||
previous_hash = previous[0] if previous else "GENESIS"
|
||||
body = {
|
||||
"tenant_id": tenant_id,
|
||||
"trace_id": trace_id,
|
||||
"event_type": event_type,
|
||||
"payload": payload,
|
||||
"previous_hash": previous_hash,
|
||||
"created_at": isoformat(),
|
||||
}
|
||||
digest = hashlib.sha256(
|
||||
canonical_json(body)
|
||||
).hexdigest()
|
||||
db.execute(
|
||||
"INSERT INTO audit_events VALUES(NULL,?,?,?,?,?,?,?)",
|
||||
(
|
||||
tenant_id,
|
||||
trace_id,
|
||||
event_type,
|
||||
json.dumps(payload, ensure_ascii=False),
|
||||
previous_hash,
|
||||
digest,
|
||||
body["created_at"],
|
||||
),
|
||||
)
|
||||
return digest
|
||||
|
||||
def verify(self) -> bool:
|
||||
previous = "GENESIS"
|
||||
with sqlite3.connect(self.database) as db:
|
||||
rows = db.execute(
|
||||
"SELECT tenant_id,trace_id,event_type,payload,previous_hash,event_hash,created_at "
|
||||
"FROM audit_events ORDER BY seq"
|
||||
)
|
||||
for row in rows:
|
||||
body = {
|
||||
"tenant_id": row[0],
|
||||
"trace_id": row[1],
|
||||
"event_type": row[2],
|
||||
"payload": json.loads(row[3]),
|
||||
"previous_hash": row[4],
|
||||
"created_at": row[6],
|
||||
}
|
||||
if row[4] != previous:
|
||||
return False
|
||||
digest = hashlib.sha256(canonical_json(body)).hexdigest()
|
||||
if digest != row[5]:
|
||||
return False
|
||||
previous = digest
|
||||
return True
|
||||
@@ -0,0 +1,73 @@
|
||||
"""AIOS V2R1 Tenant Cell lifecycle CLI primitives."""
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
from datetime import datetime, timezone
|
||||
import json
|
||||
from pathlib import Path
|
||||
|
||||
from .tenant_context import ValidationError, require_ident
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class CellRecord:
|
||||
tenant_id: str
|
||||
cell_id: str
|
||||
version: str
|
||||
state: str
|
||||
config_digest: str
|
||||
created_at: str
|
||||
|
||||
|
||||
class CellManager:
|
||||
def __init__(self, registry: str | Path) -> None:
|
||||
self.registry = Path(registry)
|
||||
self.registry.parent.mkdir(parents=True, exist_ok=True)
|
||||
if not self.registry.exists():
|
||||
self.registry.write_text("{\"cells\":{}}\n", encoding="utf-8")
|
||||
|
||||
def _load(self) -> dict:
|
||||
return json.loads(self.registry.read_text(encoding="utf-8"))
|
||||
|
||||
def _save(self, value: dict) -> None:
|
||||
self.registry.write_text(
|
||||
json.dumps(value, ensure_ascii=False, indent=2) + "\n",
|
||||
encoding="utf-8",
|
||||
)
|
||||
|
||||
def create(self, tenant_id: str, cell_id: str, version: str, digest: str) -> CellRecord:
|
||||
tenant_id = require_ident("tenant_id", tenant_id, tenant=True)
|
||||
cell_id = require_ident("cell_id", cell_id)
|
||||
data = self._load()
|
||||
if tenant_id in data["cells"]:
|
||||
raise ValidationError("tenant already has a cell")
|
||||
record = CellRecord(
|
||||
tenant_id,
|
||||
cell_id,
|
||||
version,
|
||||
"created",
|
||||
digest,
|
||||
datetime.now(timezone.utc).isoformat(),
|
||||
)
|
||||
data["cells"][tenant_id] = record.__dict__
|
||||
self._save(data)
|
||||
return record
|
||||
|
||||
def status(self, tenant_id: str) -> CellRecord:
|
||||
data = self._load()
|
||||
item = data["cells"].get(tenant_id)
|
||||
if not item:
|
||||
raise ValidationError("unknown tenant")
|
||||
return CellRecord(**item)
|
||||
|
||||
def transition(self, tenant_id: str, state: str) -> CellRecord:
|
||||
allowed = {"created", "starting", "healthy", "upgrading", "rollback", "failed"}
|
||||
if state not in allowed:
|
||||
raise ValidationError("invalid cell state")
|
||||
data = self._load()
|
||||
item = data["cells"].get(tenant_id)
|
||||
if not item:
|
||||
raise ValidationError("unknown tenant")
|
||||
item["state"] = state
|
||||
self._save(data)
|
||||
return CellRecord(**item)
|
||||
@@ -0,0 +1,64 @@
|
||||
"""The only V2R1 ingress adapter: verified context to routed ledger record."""
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
from datetime import datetime
|
||||
from threading import RLock
|
||||
from typing import Callable, Mapping, Any
|
||||
|
||||
from .message_ledger import LedgerRecord, MessageLedger
|
||||
from .router import Route, TenantRouter
|
||||
from .session_pool import SessionLease, SessionPool
|
||||
from .tenant_context import CanonicalMessage, TenantContext, utc_now
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class IngressResult:
|
||||
record: LedgerRecord
|
||||
route: Route
|
||||
session: SessionLease
|
||||
|
||||
|
||||
class ChannelAdapter:
|
||||
"""Fail-closed runtime ingress composition.
|
||||
|
||||
The adapter intentionally accepts no tenant or Cell authority outside the
|
||||
signed context and TenantRouter. A process lock keeps rollback handling
|
||||
deterministic for a single runtime while SQLite protects cross-process
|
||||
ledger writes.
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
*,
|
||||
router: TenantRouter,
|
||||
ledger: MessageLedger,
|
||||
session_pool: SessionPool,
|
||||
signing_key: bytes,
|
||||
clock: Callable[[], datetime] = utc_now,
|
||||
) -> None:
|
||||
self._router = router
|
||||
self._ledger = ledger
|
||||
self._session_pool = session_pool
|
||||
self._signing_key = signing_key
|
||||
self._clock = clock
|
||||
self._lock = RLock()
|
||||
|
||||
def ingest(self, *, token: str, message: Mapping[str, Any]) -> IngressResult:
|
||||
with self._lock:
|
||||
context = TenantContext.verify(token, self._signing_key, now=self._clock())
|
||||
canonical = CanonicalMessage.from_mapping(message)
|
||||
canonical.assert_context(context)
|
||||
route = self._router.assert_context_route(context)
|
||||
self._router.assert_message_route(canonical)
|
||||
self._session_pool.assert_available(context, route)
|
||||
|
||||
existed = self._ledger.matches(canonical)
|
||||
record = self._ledger.append(canonical)
|
||||
try:
|
||||
lease = self._session_pool.acquire(context, route)
|
||||
except Exception:
|
||||
if not existed:
|
||||
self._ledger.remove(record)
|
||||
raise
|
||||
return IngressResult(record=record, route=route, session=lease)
|
||||
@@ -0,0 +1,48 @@
|
||||
"""aios-cell command implementation for V2R1 Cell lifecycle."""
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import sys
|
||||
|
||||
from .cell_manager import CellManager
|
||||
|
||||
|
||||
def build_parser() -> argparse.ArgumentParser:
|
||||
parser = argparse.ArgumentParser(prog="aios-cell")
|
||||
parser.add_argument("registry")
|
||||
sub = parser.add_subparsers(dest="command", required=True)
|
||||
|
||||
create = sub.add_parser("create")
|
||||
create.add_argument("tenant_id")
|
||||
create.add_argument("cell_id")
|
||||
create.add_argument("version")
|
||||
create.add_argument("digest")
|
||||
|
||||
status = sub.add_parser("status")
|
||||
status.add_argument("tenant_id")
|
||||
|
||||
transition = sub.add_parser("transition")
|
||||
transition.add_argument("tenant_id")
|
||||
transition.add_argument("state")
|
||||
|
||||
return parser
|
||||
|
||||
|
||||
def main(argv: list[str] | None = None) -> int:
|
||||
args = build_parser().parse_args(argv)
|
||||
manager = CellManager(args.registry)
|
||||
if args.command == "create":
|
||||
result = manager.create(args.tenant_id, args.cell_id, args.version, args.digest)
|
||||
elif args.command == "status":
|
||||
result = manager.status(args.tenant_id)
|
||||
elif args.command == "transition":
|
||||
result = manager.transition(args.tenant_id, args.state)
|
||||
else:
|
||||
return 2
|
||||
print(json.dumps(result.__dict__, ensure_ascii=False, sort_keys=True))
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
@@ -0,0 +1,106 @@
|
||||
"""OpenClaw Cell lifecycle adapter for AIOS V2R1."""
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import asdict, dataclass, field
|
||||
import json
|
||||
from pathlib import Path
|
||||
import subprocess
|
||||
from typing import Any, Mapping
|
||||
|
||||
from .tenant_context import ValidationError, V2R1Error, require_ident
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class CellSpec:
|
||||
tenant_id: str
|
||||
image: str
|
||||
runtime: str = "docker"
|
||||
port: int | None = None
|
||||
memory: str = "2g"
|
||||
cpus: str = "2"
|
||||
pids_limit: int = 512
|
||||
network: str = "bridge"
|
||||
env: tuple[str, ...] = field(default_factory=tuple)
|
||||
|
||||
def __post_init__(self) -> None:
|
||||
require_ident("tenant_id", self.tenant_id, tenant=True)
|
||||
if self.runtime not in {"docker", "podman"}:
|
||||
raise ValidationError("unsupported runtime")
|
||||
if not self.image:
|
||||
raise ValidationError("image required")
|
||||
|
||||
|
||||
class OpenClawFleet:
|
||||
def __init__(self, binary: str = "openclaw") -> None:
|
||||
self.binary = binary
|
||||
|
||||
def _run(self, args: list[str]) -> dict[str, Any]:
|
||||
proc = subprocess.run(
|
||||
[self.binary, *args],
|
||||
check=False,
|
||||
text=True,
|
||||
stdout=subprocess.PIPE,
|
||||
stderr=subprocess.PIPE,
|
||||
)
|
||||
if proc.returncode:
|
||||
raise V2R1Error(proc.stderr.strip() or "openclaw command failed")
|
||||
data = json.loads(proc.stdout or "{}")
|
||||
if isinstance(data, dict):
|
||||
return data
|
||||
return {"result": data}
|
||||
|
||||
def create(self, spec: CellSpec) -> dict[str, Any]:
|
||||
return self._run([
|
||||
"fleet", "create", spec.tenant_id,
|
||||
"--image", spec.image,
|
||||
"--runtime", spec.runtime,
|
||||
"--json",
|
||||
])
|
||||
|
||||
def status(self, tenant_id: str) -> dict[str, Any]:
|
||||
require_ident("tenant_id", tenant_id, tenant=True)
|
||||
return self._run(["fleet", "status", tenant_id, "--json"])
|
||||
|
||||
def doctor(self, tenant_id: str | None = None) -> dict[str, Any]:
|
||||
args = ["fleet", "doctor"]
|
||||
if tenant_id:
|
||||
require_ident("tenant_id", tenant_id, tenant=True)
|
||||
args.append(tenant_id)
|
||||
args.append("--json")
|
||||
return self._run(args)
|
||||
|
||||
def backup(self, tenant_id: str, output: str | Path) -> dict[str, Any]:
|
||||
return self._run(["fleet", "backup", tenant_id, "--out", str(output), "--json"])
|
||||
|
||||
def restore(self, tenant_id: str, archive: str | Path) -> dict[str, Any]:
|
||||
return self._run(["fleet", "restore", tenant_id, "--from", str(archive), "--json"])
|
||||
|
||||
def upgrade(self, tenant_id: str, image: str) -> dict[str, Any]:
|
||||
return self._run(["fleet", "upgrade", tenant_id, "--image", image, "--json"])
|
||||
|
||||
|
||||
def load_inventory(path: str | Path) -> list[CellSpec]:
|
||||
raw = json.loads(Path(path).read_text(encoding="utf-8"))
|
||||
if raw.get("schema_version") != "aios.cells.v1":
|
||||
raise ValidationError("invalid inventory schema")
|
||||
result: list[CellSpec] = []
|
||||
seen: set[str] = set()
|
||||
for item in raw.get("cells", []):
|
||||
spec = CellSpec(
|
||||
tenant_id=item["tenant_id"],
|
||||
image=item["image"],
|
||||
runtime=item.get("runtime", "docker"),
|
||||
port=item.get("port"),
|
||||
env=tuple(item.get("env", [])),
|
||||
)
|
||||
if spec.tenant_id in seen:
|
||||
raise ValidationError("duplicate tenant")
|
||||
seen.add(spec.tenant_id)
|
||||
result.append(spec)
|
||||
if not result:
|
||||
raise ValidationError("no cells")
|
||||
return result
|
||||
|
||||
|
||||
def inventory_as_dict(items: list[CellSpec]) -> dict[str, Any]:
|
||||
return {"schema_version": "aios.cells.v1", "cells": [asdict(x) for x in items]}
|
||||
@@ -0,0 +1,143 @@
|
||||
"""Tenant-partitioned Hermes shared agent fabric primitives."""
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
from datetime import datetime, timezone
|
||||
from contextlib import closing
|
||||
from pathlib import Path
|
||||
import sqlite3
|
||||
from typing import Any
|
||||
|
||||
from .tenant_context import (
|
||||
CanonicalMessage,
|
||||
ConflictError,
|
||||
ScopeError,
|
||||
ValidationError,
|
||||
isoformat,
|
||||
require_ident,
|
||||
)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class FabricJob:
|
||||
job_id: str
|
||||
tenant_id: str
|
||||
cell_id: str
|
||||
profile_id: str
|
||||
session_id: str
|
||||
event_id: str
|
||||
status: str = "queued"
|
||||
|
||||
def __post_init__(self) -> None:
|
||||
for name in (
|
||||
"job_id", "cell_id", "profile_id", "session_id", "event_id"
|
||||
):
|
||||
require_ident(name, getattr(self, name))
|
||||
require_ident("tenant_id", self.tenant_id, tenant=True)
|
||||
if self.status not in {"queued", "running", "completed", "failed", "cancelled"}:
|
||||
raise ValidationError("invalid job status")
|
||||
|
||||
|
||||
class HermesFabric:
|
||||
"""Shared scheduler storage with mandatory tenant partition keys."""
|
||||
|
||||
def __init__(self, database: str | Path) -> None:
|
||||
self.database = str(database)
|
||||
with closing(sqlite3.connect(self.database)) as connection, connection as db:
|
||||
db.execute("PRAGMA journal_mode=WAL")
|
||||
db.execute("PRAGMA synchronous=FULL")
|
||||
db.execute(
|
||||
"""
|
||||
CREATE TABLE IF NOT EXISTS fabric_jobs (
|
||||
job_id TEXT PRIMARY KEY,
|
||||
tenant_id TEXT NOT NULL,
|
||||
cell_id TEXT NOT NULL,
|
||||
profile_id TEXT NOT NULL,
|
||||
session_id TEXT NOT NULL,
|
||||
event_id TEXT NOT NULL UNIQUE,
|
||||
status TEXT NOT NULL,
|
||||
created_at TEXT NOT NULL,
|
||||
updated_at TEXT NOT NULL
|
||||
)
|
||||
"""
|
||||
)
|
||||
db.execute(
|
||||
"CREATE INDEX IF NOT EXISTS idx_fabric_tenant_queue "
|
||||
"ON fabric_jobs(tenant_id, cell_id, status)"
|
||||
)
|
||||
|
||||
def enqueue(
|
||||
self,
|
||||
*,
|
||||
message: CanonicalMessage,
|
||||
profile_id: str,
|
||||
) -> FabricJob:
|
||||
profile_id = require_ident("profile_id", profile_id)
|
||||
if not message.command_capable:
|
||||
raise ScopeError("non-command events cannot create execution jobs")
|
||||
if not message.is_authenticated_human_command:
|
||||
raise ScopeError("only authenticated human commands can create jobs")
|
||||
job = FabricJob(
|
||||
job_id=f"job-{message.event_id}",
|
||||
tenant_id=message.tenant_id,
|
||||
cell_id=message.cell_id,
|
||||
profile_id=profile_id,
|
||||
session_id=message.session_id,
|
||||
event_id=message.event_id,
|
||||
)
|
||||
now = isoformat()
|
||||
conflict: ConflictError | None = None
|
||||
try:
|
||||
with closing(sqlite3.connect(self.database)) as connection, connection as db:
|
||||
db.execute("PRAGMA journal_mode=WAL")
|
||||
db.execute(
|
||||
"INSERT INTO fabric_jobs VALUES(?,?,?,?,?,?,?,?,?)",
|
||||
(
|
||||
job.job_id,
|
||||
job.tenant_id,
|
||||
job.cell_id,
|
||||
job.profile_id,
|
||||
job.session_id,
|
||||
job.event_id,
|
||||
job.status,
|
||||
now,
|
||||
now,
|
||||
),
|
||||
)
|
||||
except sqlite3.IntegrityError:
|
||||
conflict = ConflictError(
|
||||
"fabric event already exists or violates queue uniqueness"
|
||||
)
|
||||
if conflict is not None:
|
||||
raise conflict
|
||||
return job
|
||||
|
||||
def claim(self, tenant_id: str, cell_id: str, profile_id: str) -> FabricJob | None:
|
||||
require_ident("tenant_id", tenant_id, tenant=True)
|
||||
require_ident("cell_id", cell_id)
|
||||
require_ident("profile_id", profile_id)
|
||||
with closing(sqlite3.connect(self.database)) as connection, connection as db:
|
||||
db.execute("BEGIN IMMEDIATE")
|
||||
row = db.execute(
|
||||
"SELECT * FROM fabric_jobs WHERE tenant_id=? AND cell_id=? "
|
||||
"AND profile_id=? AND status='queued' ORDER BY created_at LIMIT 1",
|
||||
(tenant_id, cell_id, profile_id),
|
||||
).fetchone()
|
||||
if not row:
|
||||
db.commit()
|
||||
return None
|
||||
db.execute(
|
||||
"UPDATE fabric_jobs SET status='running', updated_at=? WHERE job_id=?",
|
||||
(isoformat(), row[0]),
|
||||
)
|
||||
db.commit()
|
||||
return FabricJob(*row[:7])
|
||||
|
||||
def health(self) -> dict[str, Any]:
|
||||
with closing(sqlite3.connect(self.database)) as connection, connection as db:
|
||||
count = db.execute("SELECT count(*) FROM fabric_jobs").fetchone()[0]
|
||||
return {
|
||||
"component": "hermes_fabric",
|
||||
"jobs": count,
|
||||
"checked_at": datetime.now(timezone.utc).isoformat(),
|
||||
}
|
||||
@@ -0,0 +1,47 @@
|
||||
"""Hermes shared fabric profile isolation primitives."""
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
import os
|
||||
|
||||
from .tenant_context import ValidationError, require_ident
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class HermesProfile:
|
||||
tenant_id: str
|
||||
cell_id: str
|
||||
profile_id: str
|
||||
hermes_home: Path
|
||||
workspace: Path
|
||||
|
||||
def __post_init__(self) -> None:
|
||||
require_ident("tenant_id", self.tenant_id, tenant=True)
|
||||
for name in ("cell_id", "profile_id"):
|
||||
require_ident(name, getattr(self, name))
|
||||
if not self.hermes_home.is_absolute() or not self.workspace.is_absolute():
|
||||
raise ValidationError("profile paths must be absolute")
|
||||
|
||||
@property
|
||||
def environment(self) -> dict[str, str]:
|
||||
return {
|
||||
"HERMES_HOME": str(self.hermes_home),
|
||||
"HOME": str(self.hermes_home),
|
||||
"AIOS_TENANT_ID": self.tenant_id,
|
||||
"AIOS_CELL_ID": self.cell_id,
|
||||
"AIOS_PROFILE_ID": self.profile_id,
|
||||
}
|
||||
|
||||
def prepare(self) -> None:
|
||||
self.hermes_home.mkdir(parents=True, exist_ok=True)
|
||||
self.workspace.mkdir(parents=True, exist_ok=True)
|
||||
os.chmod(self.hermes_home, 0o700)
|
||||
os.chmod(self.workspace, 0o700)
|
||||
|
||||
def assert_path_allowed(self, path: str | Path) -> None:
|
||||
target = Path(path).resolve()
|
||||
for root in (self.hermes_home.resolve(), self.workspace.resolve()):
|
||||
if target == root or root in target.parents:
|
||||
return
|
||||
raise ValidationError("path escapes profile isolation boundary")
|
||||
@@ -0,0 +1,158 @@
|
||||
"""Fail-closed identity binding for authenticated external ingress.
|
||||
|
||||
External payload claims are not authority. An HMAC-authenticated envelope is
|
||||
the sole factory for :class:`AuthenticatedPrincipal`; the resolver then checks
|
||||
every claim against the authoritative ``TenantRouter`` before the runtime signs
|
||||
an internal ``TenantContext``.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
import hashlib
|
||||
import hmac
|
||||
import re
|
||||
from typing import Any, Mapping
|
||||
|
||||
from .router import Route, TenantRouter
|
||||
from .tenant_context import ScopeError, ValidationError, canonical_json, require_ident
|
||||
|
||||
|
||||
_PROVENANCE = object()
|
||||
_SIGNATURE_RE = re.compile(r"^[0-9a-f]{64}$")
|
||||
_SCOPE_FIELDS = (
|
||||
"principal_id", "tenant_id", "cell_id", "channel",
|
||||
"channel_account_id", "session_id", "message",
|
||||
)
|
||||
|
||||
|
||||
class AuthenticationError(ValidationError):
|
||||
"""Authentication or identity resolution failed without disclosing scope."""
|
||||
|
||||
|
||||
@dataclass(frozen=True, init=False)
|
||||
class AuthenticatedPrincipal:
|
||||
"""A principal which only the verified envelope factory can create."""
|
||||
|
||||
principal_id: str
|
||||
|
||||
def __init__(self, principal_id: str, *, _provenance: object) -> None:
|
||||
if _provenance is not _PROVENANCE:
|
||||
raise TypeError("AuthenticatedPrincipal is created by authenticated ingress only")
|
||||
object.__setattr__(self, "principal_id", require_ident("principal_id", principal_id))
|
||||
|
||||
@classmethod
|
||||
def _verified(cls, principal_id: str) -> "AuthenticatedPrincipal":
|
||||
return cls(principal_id, _provenance=_PROVENANCE)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class IdentityClaims:
|
||||
tenant_id: str
|
||||
cell_id: str
|
||||
channel: str
|
||||
channel_account_id: str
|
||||
session_id: str
|
||||
|
||||
def __post_init__(self) -> None:
|
||||
require_ident("tenant_id", self.tenant_id, tenant=True)
|
||||
for field in ("cell_id", "channel", "channel_account_id", "session_id"):
|
||||
require_ident(field, getattr(self, field))
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class AuthenticatedIngress:
|
||||
principal: AuthenticatedPrincipal
|
||||
claims: IdentityClaims
|
||||
message: Mapping[str, Any]
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class RuntimeIdentity:
|
||||
tenant_id: str
|
||||
cell_id: str
|
||||
principal_id: str
|
||||
channel: str
|
||||
channel_account_id: str
|
||||
session_id: str
|
||||
|
||||
|
||||
class IngressAuthenticator:
|
||||
"""Verify a canonical HMAC envelope before any identity lookup occurs."""
|
||||
|
||||
def __init__(self, hmac_key: bytes) -> None:
|
||||
if not isinstance(hmac_key, bytes) or len(hmac_key) < 32:
|
||||
raise ValidationError("ingress HMAC key must be at least 32 bytes")
|
||||
self._hmac_key = hmac_key
|
||||
|
||||
@staticmethod
|
||||
def _signed_payload(request: Mapping[str, Any]) -> dict[str, Any]:
|
||||
if not isinstance(request, Mapping):
|
||||
raise ValidationError("ingress request must be an object")
|
||||
if set(request) != {*_SCOPE_FIELDS, "signature"}:
|
||||
raise ValidationError("ingress request fields are invalid")
|
||||
values = {field: request[field] for field in _SCOPE_FIELDS}
|
||||
if not isinstance(values["message"], Mapping):
|
||||
raise ValidationError("ingress message must be an object")
|
||||
return values
|
||||
|
||||
def authenticate(self, request: Mapping[str, Any]) -> AuthenticatedIngress:
|
||||
values = self._signed_payload(request)
|
||||
signature = request["signature"]
|
||||
if not isinstance(signature, str) or not _SIGNATURE_RE.fullmatch(signature):
|
||||
raise AuthenticationError("invalid ingress signature")
|
||||
expected = hmac.new(
|
||||
self._hmac_key, canonical_json(values), hashlib.sha256
|
||||
).hexdigest()
|
||||
if not hmac.compare_digest(expected, signature):
|
||||
raise AuthenticationError("invalid ingress signature")
|
||||
return AuthenticatedIngress(
|
||||
principal=AuthenticatedPrincipal._verified(values["principal_id"]),
|
||||
claims=IdentityClaims(
|
||||
tenant_id=values["tenant_id"],
|
||||
cell_id=values["cell_id"],
|
||||
channel=values["channel"],
|
||||
channel_account_id=values["channel_account_id"],
|
||||
session_id=values["session_id"],
|
||||
),
|
||||
message=dict(values["message"]),
|
||||
)
|
||||
|
||||
|
||||
class RuntimeIdentityResolver:
|
||||
"""Resolve authenticated ingress identity through ``TenantRouter`` only."""
|
||||
|
||||
def __init__(self, router: TenantRouter) -> None:
|
||||
self._router = router
|
||||
|
||||
def resolve(
|
||||
self, principal: AuthenticatedPrincipal, claims: IdentityClaims
|
||||
) -> RuntimeIdentity:
|
||||
if not isinstance(principal, AuthenticatedPrincipal):
|
||||
raise AuthenticationError("untrusted principal type")
|
||||
try:
|
||||
route: Route = self._router.resolve(
|
||||
channel=claims.channel,
|
||||
channel_account_id=claims.channel_account_id,
|
||||
principal_id=principal.principal_id,
|
||||
session_id=claims.session_id,
|
||||
)
|
||||
except (ScopeError, ValidationError) as exc:
|
||||
raise AuthenticationError("identity is not registered") from None
|
||||
expected = (
|
||||
claims.tenant_id, claims.cell_id, claims.channel,
|
||||
claims.channel_account_id, principal.principal_id, claims.session_id,
|
||||
)
|
||||
actual = (
|
||||
route.tenant_id, route.cell_id, route.channel,
|
||||
route.channel_account_id, route.principal_id, route.session_id,
|
||||
)
|
||||
if actual != expected:
|
||||
raise AuthenticationError("identity claims do not match authoritative route")
|
||||
return RuntimeIdentity(
|
||||
tenant_id=route.tenant_id,
|
||||
cell_id=route.cell_id,
|
||||
principal_id=route.principal_id,
|
||||
channel=route.channel,
|
||||
channel_account_id=route.channel_account_id,
|
||||
session_id=route.session_id or "",
|
||||
)
|
||||
@@ -0,0 +1,60 @@
|
||||
"""Tenant-scoped memory namespace and access policy for AIOS V2R1."""
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
from pathlib import PurePosixPath
|
||||
from typing import Literal
|
||||
|
||||
from .tenant_context import ScopeError, ValidationError, require_ident
|
||||
|
||||
|
||||
MemoryKind = Literal["session", "profile", "cell", "tenant", "shared_artifact"]
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class MemoryScope:
|
||||
tenant_id: str
|
||||
cell_id: str
|
||||
profile_id: str
|
||||
session_id: str | None
|
||||
kind: MemoryKind
|
||||
|
||||
def __post_init__(self) -> None:
|
||||
require_ident("tenant_id", self.tenant_id, tenant=True)
|
||||
for name in ("cell_id", "profile_id"):
|
||||
require_ident(name, getattr(self, name))
|
||||
if self.session_id is not None:
|
||||
require_ident("session_id", self.session_id)
|
||||
if self.kind not in {"session", "profile", "cell", "tenant", "shared_artifact"}:
|
||||
raise ValidationError("invalid memory kind")
|
||||
if self.kind == "session" and self.session_id is None:
|
||||
raise ValidationError("session memory requires session_id")
|
||||
|
||||
@property
|
||||
def namespace(self) -> str:
|
||||
parts = ["tenant", self.tenant_id, "cell", self.cell_id]
|
||||
if self.kind in {"profile", "session"}:
|
||||
parts.extend(["profile", self.profile_id])
|
||||
if self.kind == "session":
|
||||
parts.extend(["session", str(self.session_id)])
|
||||
parts.extend(["memory", self.kind])
|
||||
return str(PurePosixPath(*parts))
|
||||
|
||||
def assert_access(self, requested: "MemoryScope", *, write: bool = False) -> None:
|
||||
if self.tenant_id != requested.tenant_id:
|
||||
raise ScopeError("cross-tenant memory access denied")
|
||||
if self.cell_id != requested.cell_id:
|
||||
raise ScopeError("cross-cell memory access denied")
|
||||
if requested.kind == "shared_artifact":
|
||||
if write:
|
||||
raise ScopeError("shared artifacts are immutable")
|
||||
return
|
||||
if self.profile_id != requested.profile_id and requested.kind in {"profile", "session"}:
|
||||
raise ScopeError("cross-profile memory access denied")
|
||||
if requested.kind == "session" and self.session_id != requested.session_id:
|
||||
raise ScopeError("cross-session memory access denied")
|
||||
|
||||
|
||||
def qualify_memory_key(scope: MemoryScope, key: str) -> str:
|
||||
key = require_ident("memory_key", key)
|
||||
return f"{scope.namespace}/{key}"
|
||||
@@ -0,0 +1,224 @@
|
||||
"""Tenant-scoped append-only message ledger and exact quote resolver."""
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
from datetime import timedelta
|
||||
from contextlib import closing
|
||||
import os
|
||||
from pathlib import Path
|
||||
import sqlite3
|
||||
from typing import Iterable
|
||||
|
||||
from .tenant_context import (
|
||||
CanonicalMessage,
|
||||
ConflictError,
|
||||
ScopeError,
|
||||
ValidationError,
|
||||
isoformat,
|
||||
normalize_message_id,
|
||||
parse_time,
|
||||
utc_now,
|
||||
)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class LedgerRecord:
|
||||
tenant_id: str
|
||||
cell_id: str
|
||||
channel: str
|
||||
channel_account_id: str
|
||||
peer_id: str
|
||||
direction: str
|
||||
message_id: str
|
||||
event_id: str
|
||||
body: str
|
||||
occurred_at: str
|
||||
expires_at: str
|
||||
|
||||
|
||||
class MessageLedger:
|
||||
"""Exact-ID ledger.
|
||||
|
||||
The resolver never uses time windows, prefixes, similarity, or nearest-message
|
||||
fallbacks. Ambiguity and absence fail closed.
|
||||
"""
|
||||
|
||||
def __init__(self, database: str | Path, *, ttl_days: int = 7) -> None:
|
||||
if not 1 <= ttl_days <= 365:
|
||||
raise ValidationError("ttl_days must be between 1 and 365")
|
||||
self.database = Path(database)
|
||||
self.ttl_days = ttl_days
|
||||
self.database.parent.mkdir(parents=True, exist_ok=True)
|
||||
self._initialize()
|
||||
try:
|
||||
os.chmod(self.database, 0o600)
|
||||
except OSError:
|
||||
pass
|
||||
|
||||
def _connect(self) -> sqlite3.Connection:
|
||||
db = sqlite3.connect(str(self.database), timeout=30)
|
||||
db.row_factory = sqlite3.Row
|
||||
db.execute("PRAGMA journal_mode=WAL")
|
||||
db.execute("PRAGMA synchronous=FULL")
|
||||
db.execute("PRAGMA busy_timeout=30000")
|
||||
return db
|
||||
|
||||
def _initialize(self) -> None:
|
||||
with closing(self._connect()) as connection, connection as db:
|
||||
db.executescript(
|
||||
"""
|
||||
CREATE TABLE IF NOT EXISTS message_ledger (
|
||||
tenant_id TEXT NOT NULL,
|
||||
cell_id TEXT NOT NULL,
|
||||
channel TEXT NOT NULL,
|
||||
channel_account_id TEXT NOT NULL,
|
||||
peer_id TEXT NOT NULL,
|
||||
direction TEXT NOT NULL CHECK(direction IN ('inbound','outbound','internal')),
|
||||
message_id TEXT NOT NULL,
|
||||
event_id TEXT NOT NULL,
|
||||
body TEXT NOT NULL,
|
||||
occurred_at TEXT NOT NULL,
|
||||
expires_at TEXT NOT NULL,
|
||||
created_at TEXT NOT NULL,
|
||||
PRIMARY KEY(
|
||||
tenant_id, cell_id, channel, channel_account_id,
|
||||
peer_id, direction, message_id
|
||||
),
|
||||
UNIQUE(tenant_id, cell_id, event_id)
|
||||
);
|
||||
CREATE INDEX IF NOT EXISTS idx_message_reply_lookup ON message_ledger(
|
||||
tenant_id, cell_id, channel, channel_account_id,
|
||||
peer_id, message_id, expires_at
|
||||
);
|
||||
"""
|
||||
)
|
||||
|
||||
def append(self, message: CanonicalMessage) -> LedgerRecord:
|
||||
"""Append one exact message through the runtime write path.
|
||||
|
||||
This is intentionally the owner of validation, idempotency, and the
|
||||
immediate SQLite transaction. Runtime callers must not depend on the
|
||||
legacy ``remember`` compatibility name.
|
||||
"""
|
||||
message_id = normalize_message_id(message.message_id)
|
||||
now = utc_now()
|
||||
expires = isoformat(now + timedelta(days=self.ttl_days))
|
||||
key = (
|
||||
message.tenant_id,
|
||||
message.cell_id,
|
||||
message.channel,
|
||||
message.channel_account_id,
|
||||
message.peer_id,
|
||||
message.direction,
|
||||
message_id,
|
||||
)
|
||||
storage_error: ConflictError | None = None
|
||||
try:
|
||||
with closing(self._connect()) as connection, connection as db:
|
||||
db.execute("BEGIN IMMEDIATE")
|
||||
existing = db.execute(
|
||||
"SELECT event_id, body, occurred_at, expires_at FROM message_ledger "
|
||||
"WHERE tenant_id=? AND cell_id=? AND channel=? AND channel_account_id=? "
|
||||
"AND peer_id=? AND direction=? AND message_id=?",
|
||||
key,
|
||||
).fetchone()
|
||||
if existing:
|
||||
if existing["body"] != message.body:
|
||||
db.rollback()
|
||||
raise ConflictError("message ID collision with different content")
|
||||
db.commit()
|
||||
return LedgerRecord(
|
||||
*key, existing["event_id"], existing["body"],
|
||||
existing["occurred_at"], existing["expires_at"],
|
||||
)
|
||||
db.execute(
|
||||
"INSERT INTO message_ledger VALUES(?,?,?,?,?,?,?,?,?,?,?,?)",
|
||||
(*key, message.event_id, message.body, message.occurred_at, expires, isoformat(now)),
|
||||
)
|
||||
db.commit()
|
||||
except sqlite3.Error:
|
||||
storage_error = ConflictError("ledger storage unavailable")
|
||||
if storage_error is not None:
|
||||
# Raise outside the sqlite exception handler so callers cannot inspect
|
||||
# a driver exception through __cause__ or __context__.
|
||||
raise storage_error
|
||||
return LedgerRecord(*key, message.event_id, message.body, message.occurred_at, expires)
|
||||
|
||||
def remember(self, message: CanonicalMessage) -> LedgerRecord:
|
||||
"""Backward-compatible API wrapper for callers outside the runtime path."""
|
||||
return self.append(message)
|
||||
|
||||
def matches(self, message: CanonicalMessage) -> bool:
|
||||
"""Whether this exact message is already durably represented."""
|
||||
message_id = normalize_message_id(message.message_id)
|
||||
with closing(self._connect()) as connection, connection as db:
|
||||
row = db.execute(
|
||||
"SELECT event_id, body FROM message_ledger WHERE tenant_id=? AND "
|
||||
"cell_id=? AND channel=? AND channel_account_id=? AND peer_id=? "
|
||||
"AND direction=? AND message_id=?",
|
||||
(
|
||||
message.tenant_id, message.cell_id, message.channel,
|
||||
message.channel_account_id, message.peer_id, message.direction,
|
||||
message_id,
|
||||
),
|
||||
).fetchone()
|
||||
return bool(row and row["event_id"] == message.event_id and row["body"] == message.body)
|
||||
|
||||
def remove(self, record: LedgerRecord) -> None:
|
||||
"""Compensate a newly appended record if a later ingress step fails."""
|
||||
with closing(self._connect()) as connection, connection as db:
|
||||
db.execute(
|
||||
"DELETE FROM message_ledger WHERE tenant_id=? AND cell_id=? AND "
|
||||
"channel=? AND channel_account_id=? AND peer_id=? AND direction=? "
|
||||
"AND message_id=? AND event_id=?",
|
||||
(
|
||||
record.tenant_id, record.cell_id, record.channel,
|
||||
record.channel_account_id, record.peer_id, record.direction,
|
||||
record.message_id, record.event_id,
|
||||
),
|
||||
)
|
||||
|
||||
def resolve_quote(self, message: CanonicalMessage) -> str:
|
||||
if message.quoted_body is not None:
|
||||
return message.quoted_body
|
||||
if message.reply_to_message_id is None:
|
||||
raise ScopeError("quoted_text_unavailable")
|
||||
reply_id = normalize_message_id(
|
||||
message.reply_to_message_id,
|
||||
field_name="reply_to_message_id",
|
||||
)
|
||||
with closing(self._connect()) as connection, connection as db:
|
||||
rows = db.execute(
|
||||
"SELECT direction, body, event_id FROM message_ledger "
|
||||
"WHERE tenant_id=? AND cell_id=? AND channel=? AND channel_account_id=? "
|
||||
"AND peer_id=? AND message_id=? AND expires_at>?",
|
||||
(
|
||||
message.tenant_id,
|
||||
message.cell_id,
|
||||
message.channel,
|
||||
message.channel_account_id,
|
||||
message.peer_id,
|
||||
reply_id,
|
||||
isoformat(),
|
||||
),
|
||||
).fetchall()
|
||||
if len(rows) == 1:
|
||||
return str(rows[0]["body"])
|
||||
if len(rows) > 1:
|
||||
raise ConflictError("ambiguous reply ID across message directions")
|
||||
raise ScopeError("quoted_text_unavailable")
|
||||
|
||||
def purge_expired(self) -> int:
|
||||
with closing(self._connect()) as connection, connection as db:
|
||||
cursor = db.execute(
|
||||
"DELETE FROM message_ledger WHERE expires_at<=?", (isoformat(),)
|
||||
)
|
||||
return cursor.rowcount
|
||||
|
||||
def integrity_check(self) -> str:
|
||||
with closing(self._connect()) as connection, connection as db:
|
||||
return str(db.execute("PRAGMA integrity_check").fetchone()[0])
|
||||
|
||||
def count(self) -> int:
|
||||
with closing(self._connect()) as connection, connection as db:
|
||||
return int(db.execute("SELECT count(*) FROM message_ledger").fetchone()[0])
|
||||
@@ -0,0 +1,336 @@
|
||||
"""Authoritative tenant registry and fail-closed message router."""
|
||||
from __future__ import annotations
|
||||
|
||||
from contextlib import contextmanager
|
||||
from contextlib import closing
|
||||
from dataclasses import dataclass
|
||||
from datetime import datetime, timedelta
|
||||
import sqlite3
|
||||
from pathlib import Path
|
||||
from typing import Callable, Iterator
|
||||
|
||||
from .tenant_context import (
|
||||
CanonicalMessage,
|
||||
ConflictError,
|
||||
ScopeError,
|
||||
TenantContext,
|
||||
ValidationError,
|
||||
isoformat,
|
||||
parse_time,
|
||||
require_ident,
|
||||
utc_now,
|
||||
)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class Route:
|
||||
tenant_id: str
|
||||
cell_id: str
|
||||
channel: str
|
||||
channel_account_id: str
|
||||
principal_id: str
|
||||
session_id: str | None
|
||||
|
||||
|
||||
class TenantRouter:
|
||||
"""SQLite-backed routing registry.
|
||||
|
||||
Channel accounts are authoritative tenant ownership boundaries. Principal and
|
||||
session bindings may narrow a route, but can never move traffic to another
|
||||
tenant or Cell.
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self, database: str | Path, *, clock: Callable[[], datetime] = utc_now
|
||||
) -> None:
|
||||
self.database = str(database)
|
||||
self._clock = clock
|
||||
self._initialize()
|
||||
|
||||
def _connect(self) -> sqlite3.Connection:
|
||||
connection = sqlite3.connect(self.database, timeout=30, isolation_level=None)
|
||||
connection.row_factory = sqlite3.Row
|
||||
connection.execute("PRAGMA foreign_keys=ON")
|
||||
connection.execute("PRAGMA journal_mode=WAL")
|
||||
connection.execute("PRAGMA synchronous=FULL")
|
||||
connection.execute("PRAGMA busy_timeout=30000")
|
||||
return connection
|
||||
|
||||
@contextmanager
|
||||
def _transaction(self) -> Iterator[sqlite3.Connection]:
|
||||
connection = self._connect()
|
||||
try:
|
||||
connection.execute("BEGIN IMMEDIATE")
|
||||
yield connection
|
||||
connection.execute("COMMIT")
|
||||
except Exception:
|
||||
connection.execute("ROLLBACK")
|
||||
raise
|
||||
finally:
|
||||
connection.close()
|
||||
|
||||
def _initialize(self) -> None:
|
||||
with closing(self._connect()) as connection, connection as db:
|
||||
db.executescript(
|
||||
"""
|
||||
CREATE TABLE IF NOT EXISTS tenants (
|
||||
tenant_id TEXT PRIMARY KEY,
|
||||
cell_id TEXT NOT NULL UNIQUE,
|
||||
status TEXT NOT NULL CHECK(status IN ('active','suspended','retired')),
|
||||
created_at TEXT NOT NULL,
|
||||
updated_at TEXT NOT NULL
|
||||
);
|
||||
CREATE TABLE IF NOT EXISTS channel_routes (
|
||||
channel TEXT NOT NULL,
|
||||
channel_account_id TEXT NOT NULL,
|
||||
tenant_id TEXT NOT NULL,
|
||||
cell_id TEXT NOT NULL,
|
||||
created_at TEXT NOT NULL,
|
||||
PRIMARY KEY(channel, channel_account_id),
|
||||
FOREIGN KEY(tenant_id) REFERENCES tenants(tenant_id)
|
||||
);
|
||||
CREATE TABLE IF NOT EXISTS principal_routes (
|
||||
channel TEXT NOT NULL,
|
||||
channel_account_id TEXT NOT NULL,
|
||||
principal_id TEXT NOT NULL,
|
||||
tenant_id TEXT NOT NULL,
|
||||
cell_id TEXT NOT NULL,
|
||||
created_at TEXT NOT NULL,
|
||||
PRIMARY KEY(channel, channel_account_id, principal_id),
|
||||
FOREIGN KEY(channel, channel_account_id)
|
||||
REFERENCES channel_routes(channel, channel_account_id)
|
||||
);
|
||||
CREATE TABLE IF NOT EXISTS session_bindings (
|
||||
tenant_id TEXT NOT NULL,
|
||||
session_id TEXT NOT NULL,
|
||||
cell_id TEXT NOT NULL,
|
||||
principal_id TEXT NOT NULL,
|
||||
expires_at TEXT NOT NULL,
|
||||
created_at TEXT NOT NULL,
|
||||
PRIMARY KEY(tenant_id, session_id),
|
||||
FOREIGN KEY(tenant_id) REFERENCES tenants(tenant_id)
|
||||
);
|
||||
CREATE INDEX IF NOT EXISTS idx_session_expiry
|
||||
ON session_bindings(expires_at);
|
||||
"""
|
||||
)
|
||||
|
||||
def register_tenant(self, tenant_id: str, cell_id: str) -> None:
|
||||
tenant_id = require_ident("tenant_id", tenant_id, tenant=True)
|
||||
cell_id = require_ident("cell_id", cell_id)
|
||||
now = isoformat(self._clock())
|
||||
with self._transaction() as db:
|
||||
row = db.execute(
|
||||
"SELECT cell_id, status FROM tenants WHERE tenant_id=?", (tenant_id,)
|
||||
).fetchone()
|
||||
if row:
|
||||
if row["cell_id"] != cell_id:
|
||||
raise ConflictError("tenant already bound to another cell")
|
||||
db.execute(
|
||||
"UPDATE tenants SET status='active', updated_at=? WHERE tenant_id=?",
|
||||
(now, tenant_id),
|
||||
)
|
||||
return
|
||||
conflict = db.execute(
|
||||
"SELECT tenant_id FROM tenants WHERE cell_id=?", (cell_id,)
|
||||
).fetchone()
|
||||
if conflict:
|
||||
raise ConflictError("cell already belongs to another tenant")
|
||||
db.execute(
|
||||
"INSERT INTO tenants VALUES(?,?,?,?,?)",
|
||||
(tenant_id, cell_id, "active", now, now),
|
||||
)
|
||||
|
||||
def set_tenant_status(self, tenant_id: str, status: str) -> None:
|
||||
tenant_id = require_ident("tenant_id", tenant_id, tenant=True)
|
||||
if status not in {"active", "suspended", "retired"}:
|
||||
raise ValidationError("invalid tenant status")
|
||||
with self._transaction() as db:
|
||||
cursor = db.execute(
|
||||
"UPDATE tenants SET status=?, updated_at=? WHERE tenant_id=?",
|
||||
(status, isoformat(self._clock()), tenant_id),
|
||||
)
|
||||
if cursor.rowcount != 1:
|
||||
raise ValidationError("unknown tenant")
|
||||
|
||||
def bind_channel(
|
||||
self,
|
||||
*,
|
||||
tenant_id: str,
|
||||
channel: str,
|
||||
channel_account_id: str,
|
||||
) -> None:
|
||||
tenant_id = require_ident("tenant_id", tenant_id, tenant=True)
|
||||
channel = require_ident("channel", channel)
|
||||
channel_account_id = require_ident("channel_account_id", channel_account_id)
|
||||
with self._transaction() as db:
|
||||
tenant = db.execute(
|
||||
"SELECT cell_id, status FROM tenants WHERE tenant_id=?", (tenant_id,)
|
||||
).fetchone()
|
||||
if not tenant or tenant["status"] != "active":
|
||||
raise ValidationError("tenant is not active")
|
||||
existing = db.execute(
|
||||
"SELECT tenant_id, cell_id FROM channel_routes "
|
||||
"WHERE channel=? AND channel_account_id=?",
|
||||
(channel, channel_account_id),
|
||||
).fetchone()
|
||||
if existing:
|
||||
if existing["tenant_id"] != tenant_id or existing["cell_id"] != tenant["cell_id"]:
|
||||
raise ConflictError("channel account already belongs to another tenant")
|
||||
return
|
||||
db.execute(
|
||||
"INSERT INTO channel_routes VALUES(?,?,?,?,?)",
|
||||
(channel, channel_account_id, tenant_id, tenant["cell_id"], isoformat(self._clock())),
|
||||
)
|
||||
|
||||
def bind_principal(
|
||||
self,
|
||||
*,
|
||||
tenant_id: str,
|
||||
channel: str,
|
||||
channel_account_id: str,
|
||||
principal_id: str,
|
||||
) -> None:
|
||||
principal_id = require_ident("principal_id", principal_id)
|
||||
route = self.resolve_channel(channel, channel_account_id)
|
||||
if route.tenant_id != tenant_id:
|
||||
raise ScopeError("principal cannot cross tenant boundary")
|
||||
with self._transaction() as db:
|
||||
existing = db.execute(
|
||||
"SELECT tenant_id, cell_id FROM principal_routes WHERE "
|
||||
"channel=? AND channel_account_id=? AND principal_id=?",
|
||||
(channel, channel_account_id, principal_id),
|
||||
).fetchone()
|
||||
if existing:
|
||||
if existing["tenant_id"] != tenant_id or existing["cell_id"] != route.cell_id:
|
||||
raise ConflictError("principal route conflict")
|
||||
return
|
||||
db.execute(
|
||||
"INSERT INTO principal_routes VALUES(?,?,?,?,?,?)",
|
||||
(
|
||||
channel,
|
||||
channel_account_id,
|
||||
principal_id,
|
||||
tenant_id,
|
||||
route.cell_id,
|
||||
isoformat(self._clock()),
|
||||
),
|
||||
)
|
||||
|
||||
def bind_session(
|
||||
self,
|
||||
*,
|
||||
tenant_id: str,
|
||||
session_id: str,
|
||||
cell_id: str,
|
||||
principal_id: str,
|
||||
ttl_seconds: int = 86400,
|
||||
) -> None:
|
||||
tenant_id = require_ident("tenant_id", tenant_id, tenant=True)
|
||||
session_id = require_ident("session_id", session_id)
|
||||
cell_id = require_ident("cell_id", cell_id)
|
||||
principal_id = require_ident("principal_id", principal_id)
|
||||
if not 60 <= ttl_seconds <= 31 * 86400:
|
||||
raise ValidationError("invalid session TTL")
|
||||
now = self._clock()
|
||||
expires = isoformat(now + timedelta(seconds=ttl_seconds))
|
||||
with self._transaction() as db:
|
||||
tenant = db.execute(
|
||||
"SELECT cell_id, status FROM tenants WHERE tenant_id=?", (tenant_id,)
|
||||
).fetchone()
|
||||
if not tenant or tenant["status"] != "active" or tenant["cell_id"] != cell_id:
|
||||
raise ScopeError("session cell does not match tenant")
|
||||
existing = db.execute(
|
||||
"SELECT cell_id, principal_id FROM session_bindings "
|
||||
"WHERE tenant_id=? AND session_id=?",
|
||||
(tenant_id, session_id),
|
||||
).fetchone()
|
||||
if existing and (
|
||||
existing["cell_id"] != cell_id or existing["principal_id"] != principal_id
|
||||
):
|
||||
raise ConflictError("session is already bound to another principal or cell")
|
||||
db.execute(
|
||||
"INSERT INTO session_bindings VALUES(?,?,?,?,?,?) "
|
||||
"ON CONFLICT(tenant_id,session_id) DO UPDATE SET expires_at=excluded.expires_at",
|
||||
(tenant_id, session_id, cell_id, principal_id, expires, isoformat(now)),
|
||||
)
|
||||
|
||||
def resolve_channel(self, channel: str, channel_account_id: str) -> Route:
|
||||
channel = require_ident("channel", channel)
|
||||
channel_account_id = require_ident("channel_account_id", channel_account_id)
|
||||
with closing(self._connect()) as connection, connection as db:
|
||||
row = db.execute(
|
||||
"SELECT r.tenant_id, r.cell_id, t.status FROM channel_routes r "
|
||||
"JOIN tenants t ON t.tenant_id=r.tenant_id "
|
||||
"WHERE r.channel=? AND r.channel_account_id=?",
|
||||
(channel, channel_account_id),
|
||||
).fetchone()
|
||||
if not row:
|
||||
raise ScopeError("unknown channel account")
|
||||
if row["status"] != "active":
|
||||
raise ScopeError("tenant is not active")
|
||||
return Route(row["tenant_id"], row["cell_id"], channel, channel_account_id, "", None)
|
||||
|
||||
def resolve(
|
||||
self,
|
||||
*,
|
||||
channel: str,
|
||||
channel_account_id: str,
|
||||
principal_id: str,
|
||||
session_id: str | None = None,
|
||||
) -> Route:
|
||||
principal_id = require_ident("principal_id", principal_id)
|
||||
base = self.resolve_channel(channel, channel_account_id)
|
||||
with closing(self._connect()) as connection, connection as db:
|
||||
principal = db.execute(
|
||||
"SELECT tenant_id, cell_id FROM principal_routes WHERE "
|
||||
"channel=? AND channel_account_id=? AND principal_id=?",
|
||||
(channel, channel_account_id, principal_id),
|
||||
).fetchone()
|
||||
if principal and (
|
||||
principal["tenant_id"] != base.tenant_id or principal["cell_id"] != base.cell_id
|
||||
):
|
||||
raise ScopeError("principal route violates channel ownership")
|
||||
if session_id is not None:
|
||||
session_id = require_ident("session_id", session_id)
|
||||
session = db.execute(
|
||||
"SELECT cell_id, principal_id, expires_at FROM session_bindings "
|
||||
"WHERE tenant_id=? AND session_id=?",
|
||||
(base.tenant_id, session_id),
|
||||
).fetchone()
|
||||
if not session:
|
||||
raise ScopeError("unknown session")
|
||||
if parse_time(session["expires_at"]) <= self._clock():
|
||||
raise ScopeError("session expired")
|
||||
if session["cell_id"] != base.cell_id or session["principal_id"] != principal_id:
|
||||
raise ScopeError("session scope mismatch")
|
||||
return Route(
|
||||
base.tenant_id,
|
||||
base.cell_id,
|
||||
channel,
|
||||
channel_account_id,
|
||||
principal_id,
|
||||
session_id,
|
||||
)
|
||||
|
||||
def assert_message_route(self, message: CanonicalMessage) -> Route:
|
||||
route = self.resolve(
|
||||
channel=message.channel,
|
||||
channel_account_id=message.channel_account_id,
|
||||
principal_id=message.principal_id,
|
||||
session_id=message.session_id,
|
||||
)
|
||||
if message.tenant_id != route.tenant_id or message.cell_id != route.cell_id:
|
||||
raise ScopeError("message claims do not match authoritative route")
|
||||
return route
|
||||
|
||||
def assert_context_route(self, context: TenantContext) -> Route:
|
||||
route = self.resolve(
|
||||
channel=context.channel,
|
||||
channel_account_id=context.channel_account_id,
|
||||
principal_id=context.principal_id,
|
||||
session_id=context.session_id,
|
||||
)
|
||||
if context.tenant_id != route.tenant_id or context.cell_id != route.cell_id:
|
||||
raise ScopeError("context claims do not match authoritative route")
|
||||
return route
|
||||
@@ -0,0 +1,136 @@
|
||||
"""V2R1 runtime composition root for authenticated channel ingress."""
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
from typing import Any, Callable, Mapping
|
||||
|
||||
from .channel_adapter import ChannelAdapter, IngressResult
|
||||
from .identity import (
|
||||
AuthenticationError,
|
||||
IngressAuthenticator,
|
||||
RuntimeIdentity,
|
||||
RuntimeIdentityResolver,
|
||||
)
|
||||
from .message_ledger import MessageLedger
|
||||
from .router import TenantRouter
|
||||
from .session_pool import SessionPool
|
||||
from .tenant_context import ConflictError, ScopeError, TenantContext, ValidationError, utc_now
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class RuntimeIngressResponse:
|
||||
"""Sanitised boundary response; no exception text crosses external ingress."""
|
||||
|
||||
status: str
|
||||
result: IngressResult | None = None
|
||||
|
||||
|
||||
class RuntimeWiring:
|
||||
"""Own the only external-to-runtime identity binding and message path.
|
||||
|
||||
The request accepted by :meth:`ingest` is an HMAC-authenticated envelope;
|
||||
tenant, cell, channel, account, session, principal, and message claims are
|
||||
signed together. The envelope is then resolved against ``TenantRouter``.
|
||||
Only that resolved identity can mint the short-lived internal context passed
|
||||
to ``ChannelAdapter``.
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
*,
|
||||
router: TenantRouter,
|
||||
ledger: MessageLedger,
|
||||
session_pool: SessionPool,
|
||||
channel_adapter: ChannelAdapter,
|
||||
identity_resolver: RuntimeIdentityResolver,
|
||||
ingress_authenticator: IngressAuthenticator,
|
||||
internal_signing_key: bytes,
|
||||
clock: Callable[[], datetime],
|
||||
) -> None:
|
||||
self.router = router
|
||||
self.ledger = ledger
|
||||
self.session_pool = session_pool
|
||||
self.channel_adapter = channel_adapter
|
||||
self.identity_resolver = identity_resolver
|
||||
self._ingress_authenticator = ingress_authenticator
|
||||
self._internal_signing_key = internal_signing_key
|
||||
self._clock = clock
|
||||
|
||||
@classmethod
|
||||
def create(
|
||||
cls,
|
||||
root: str | Path,
|
||||
*,
|
||||
signing_key: bytes,
|
||||
ingress_hmac_key: bytes | None = None,
|
||||
clock: Callable[[], datetime] = utc_now,
|
||||
) -> "RuntimeWiring":
|
||||
if not isinstance(signing_key, bytes) or len(signing_key) < 32:
|
||||
raise ValidationError("internal signing key must be at least 32 bytes")
|
||||
# Kept optional for one controlled migration release; the external
|
||||
# request path still cannot supply a TenantContext token.
|
||||
hmac_key = ingress_hmac_key if ingress_hmac_key is not None else signing_key
|
||||
root_path = Path(root)
|
||||
root_path.mkdir(parents=True, exist_ok=True)
|
||||
router = TenantRouter(root_path / "router.sqlite3", clock=clock)
|
||||
ledger = MessageLedger(root_path / "message_ledger.sqlite3")
|
||||
session_pool = SessionPool(router)
|
||||
adapter = ChannelAdapter(
|
||||
router=router,
|
||||
ledger=ledger,
|
||||
session_pool=session_pool,
|
||||
signing_key=signing_key,
|
||||
clock=clock,
|
||||
)
|
||||
return cls(
|
||||
router=router,
|
||||
ledger=ledger,
|
||||
session_pool=session_pool,
|
||||
channel_adapter=adapter,
|
||||
identity_resolver=RuntimeIdentityResolver(router),
|
||||
ingress_authenticator=IngressAuthenticator(hmac_key),
|
||||
internal_signing_key=signing_key,
|
||||
clock=clock,
|
||||
)
|
||||
|
||||
def _issue_internal_context(self, identity: RuntimeIdentity) -> TenantContext:
|
||||
"""Mint internal scope only after all claims matched the router route."""
|
||||
return TenantContext.issue(
|
||||
lifetime_seconds=300,
|
||||
now=self._clock(),
|
||||
tenant_id=identity.tenant_id,
|
||||
cell_id=identity.cell_id,
|
||||
principal_id=identity.principal_id,
|
||||
principal_type="authenticated_user",
|
||||
session_id=identity.session_id,
|
||||
task_id=None,
|
||||
channel=identity.channel,
|
||||
channel_account_id=identity.channel_account_id,
|
||||
)
|
||||
|
||||
def ingest(self, *, request: Mapping[str, Any]) -> RuntimeIngressResponse:
|
||||
"""Authenticate, resolve, issue internal context, then append and lease.
|
||||
|
||||
The only successful route is ``IngressAuthenticator`` ->
|
||||
``RuntimeIdentityResolver`` -> ``ChannelAdapter`` ->
|
||||
``MessageLedger.append`` + ``SessionPool``. The legacy caller-supplied
|
||||
TenantContext token interface is intentionally not accepted.
|
||||
"""
|
||||
try:
|
||||
ingress = self._ingress_authenticator.authenticate(request)
|
||||
identity = self.identity_resolver.resolve(ingress.principal, ingress.claims)
|
||||
context = self._issue_internal_context(identity)
|
||||
result = self.channel_adapter.ingest(
|
||||
token=context.sign(self._internal_signing_key), message=ingress.message
|
||||
)
|
||||
return RuntimeIngressResponse(status="ACCEPTED", result=result)
|
||||
except (AuthenticationError, ScopeError):
|
||||
return RuntimeIngressResponse(status="AUTH_FAILED")
|
||||
except ValidationError:
|
||||
return RuntimeIngressResponse(status="VALIDATION_FAILED")
|
||||
except ConflictError:
|
||||
return RuntimeIngressResponse(status="CONFLICT")
|
||||
except Exception:
|
||||
return RuntimeIngressResponse(status="INTERNAL_ERROR")
|
||||
@@ -0,0 +1,33 @@
|
||||
"""Tenant and Cell scoped secret reference model.
|
||||
|
||||
This module never stores secret values. It stores ownership and retrieval scope
|
||||
metadata for integration with a real secret broker.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
from typing import Literal
|
||||
|
||||
from .tenant_context import ValidationError, require_ident
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class SecretRef:
|
||||
secret_id: str
|
||||
tenant_id: str
|
||||
cell_id: str
|
||||
kind: Literal["channel", "model", "tool", "runtime"]
|
||||
version: str
|
||||
broker_path: str
|
||||
|
||||
def __post_init__(self) -> None:
|
||||
for name in ("secret_id", "cell_id", "version"):
|
||||
require_ident(name, getattr(self, name))
|
||||
require_ident("tenant_id", self.tenant_id, tenant=True)
|
||||
if self.kind not in {"channel", "model", "tool", "runtime"}:
|
||||
raise ValidationError("invalid secret kind")
|
||||
if not self.broker_path.startswith("secret://"):
|
||||
raise ValidationError("secret broker path required")
|
||||
|
||||
def can_be_used_by(self, *, tenant_id: str, cell_id: str) -> bool:
|
||||
return self.tenant_id == tenant_id and self.cell_id == cell_id
|
||||
@@ -0,0 +1,59 @@
|
||||
"""Process-local session lease pool backed by TenantRouter authority."""
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
from threading import RLock
|
||||
|
||||
from .router import Route, TenantRouter
|
||||
from .tenant_context import ScopeError, TenantContext
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class SessionLease:
|
||||
tenant_id: str
|
||||
cell_id: str
|
||||
principal_id: str
|
||||
session_id: str
|
||||
|
||||
|
||||
class SessionPool:
|
||||
"""Tracks active leases without creating a second session authority store."""
|
||||
|
||||
def __init__(self, router: TenantRouter) -> None:
|
||||
self._router = router
|
||||
self._leases: dict[tuple[str, str], SessionLease] = {}
|
||||
self._lock = RLock()
|
||||
|
||||
@staticmethod
|
||||
def _assert_route(context: TenantContext, route: Route) -> None:
|
||||
if (
|
||||
route.tenant_id != context.tenant_id
|
||||
or route.cell_id != context.cell_id
|
||||
or route.principal_id != context.principal_id
|
||||
or route.session_id != context.session_id
|
||||
):
|
||||
raise ScopeError("session lease does not match authoritative route")
|
||||
|
||||
def assert_available(self, context: TenantContext, route: Route) -> None:
|
||||
"""Re-resolve the context from the router before a ledger mutation."""
|
||||
self._assert_route(context, route)
|
||||
self._assert_route(context, self._router.assert_context_route(context))
|
||||
|
||||
def acquire(self, context: TenantContext, route: Route) -> SessionLease:
|
||||
self._assert_route(context, route)
|
||||
lease = SessionLease(
|
||||
tenant_id=context.tenant_id,
|
||||
cell_id=context.cell_id,
|
||||
principal_id=context.principal_id,
|
||||
session_id=context.session_id,
|
||||
)
|
||||
with self._lock:
|
||||
return self._leases.setdefault((lease.tenant_id, lease.session_id), lease)
|
||||
|
||||
def release(self, lease: SessionLease) -> None:
|
||||
with self._lock:
|
||||
self._leases.pop((lease.tenant_id, lease.session_id), None)
|
||||
|
||||
def active_count(self) -> int:
|
||||
with self._lock:
|
||||
return len(self._leases)
|
||||
@@ -0,0 +1,316 @@
|
||||
"""Signed tenant context and canonical message contract for AIOS V2R1."""
|
||||
from __future__ import annotations
|
||||
|
||||
import base64
|
||||
from dataclasses import asdict, dataclass
|
||||
from datetime import datetime, timedelta, timezone
|
||||
import hashlib
|
||||
import hmac
|
||||
import json
|
||||
import re
|
||||
import secrets
|
||||
from typing import Any, Mapping
|
||||
|
||||
VERSION = "V2R1C0"
|
||||
MAX_SAFE_INTEGER = 9_007_199_254_740_991
|
||||
TENANT_RE = re.compile(r"^[a-z0-9](?:[a-z0-9-]{0,38}[a-z0-9])?$")
|
||||
IDENT_RE = re.compile(r"^[A-Za-z0-9](?:[A-Za-z0-9._:@-]{0,126}[A-Za-z0-9])?$")
|
||||
|
||||
|
||||
class V2R1Error(RuntimeError):
|
||||
pass
|
||||
|
||||
|
||||
class ValidationError(V2R1Error):
|
||||
pass
|
||||
|
||||
|
||||
class ScopeError(V2R1Error):
|
||||
pass
|
||||
|
||||
|
||||
class ConflictError(V2R1Error):
|
||||
pass
|
||||
|
||||
|
||||
def utc_now() -> datetime:
|
||||
return datetime.now(timezone.utc)
|
||||
|
||||
|
||||
def isoformat(value: datetime | None = None) -> str:
|
||||
return (value or utc_now()).astimezone(timezone.utc).isoformat()
|
||||
|
||||
|
||||
def parse_time(value: str) -> datetime:
|
||||
if not isinstance(value, str) or not value.strip():
|
||||
raise ValidationError("timestamp must be a non-empty string")
|
||||
text = value.strip()
|
||||
if text.endswith("Z"):
|
||||
text = text[:-1] + "+00:00"
|
||||
try:
|
||||
parsed = datetime.fromisoformat(text)
|
||||
except ValueError as exc:
|
||||
raise ValidationError(f"invalid timestamp: {value!r}") from exc
|
||||
if parsed.tzinfo is None:
|
||||
raise ValidationError("timestamp must include timezone")
|
||||
return parsed.astimezone(timezone.utc)
|
||||
|
||||
|
||||
def require_ident(name: str, value: Any, *, tenant: bool = False) -> str:
|
||||
if not isinstance(value, str):
|
||||
raise ValidationError(f"{name} must be a string")
|
||||
value = value.strip()
|
||||
pattern = TENANT_RE if tenant else IDENT_RE
|
||||
if not pattern.fullmatch(value):
|
||||
raise ValidationError(f"invalid {name}: {value!r}")
|
||||
return value
|
||||
|
||||
|
||||
def normalize_message_id(value: Any, *, field_name: str = "message_id") -> str:
|
||||
if isinstance(value, bool):
|
||||
raise ValidationError(f"{field_name} cannot be boolean")
|
||||
if isinstance(value, str):
|
||||
value = value.strip()
|
||||
if not value or len(value) > 256 or any(ord(ch) < 32 for ch in value):
|
||||
raise ValidationError(f"invalid {field_name}")
|
||||
return value
|
||||
if isinstance(value, int):
|
||||
if abs(value) > MAX_SAFE_INTEGER:
|
||||
raise ValidationError(f"{field_name} is an unsafe numeric ID")
|
||||
return str(value)
|
||||
raise ValidationError(f"{field_name} must be a lossless string or safe integer")
|
||||
|
||||
|
||||
def canonical_json(value: Any) -> bytes:
|
||||
return json.dumps(
|
||||
value, ensure_ascii=False, separators=(",", ":"), sort_keys=True
|
||||
).encode("utf-8")
|
||||
|
||||
|
||||
def _b64(data: bytes) -> str:
|
||||
return base64.urlsafe_b64encode(data).rstrip(b"=").decode("ascii")
|
||||
|
||||
|
||||
def _unb64(value: str) -> bytes:
|
||||
return base64.urlsafe_b64decode(value + "=" * (-len(value) % 4))
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class TenantContext:
|
||||
tenant_id: str
|
||||
cell_id: str
|
||||
principal_id: str
|
||||
principal_type: str
|
||||
session_id: str
|
||||
task_id: str | None
|
||||
channel: str
|
||||
channel_account_id: str
|
||||
issued_at: str
|
||||
expires_at: str
|
||||
nonce: str
|
||||
|
||||
def __post_init__(self) -> None:
|
||||
require_ident("tenant_id", self.tenant_id, tenant=True)
|
||||
for name in (
|
||||
"cell_id", "principal_id", "principal_type", "session_id",
|
||||
"channel", "channel_account_id", "nonce",
|
||||
):
|
||||
require_ident(name, getattr(self, name))
|
||||
if self.task_id is not None:
|
||||
require_ident("task_id", self.task_id)
|
||||
issued = parse_time(self.issued_at)
|
||||
expires = parse_time(self.expires_at)
|
||||
if expires <= issued or expires - issued > timedelta(hours=1):
|
||||
raise ValidationError("invalid tenant context lifetime")
|
||||
|
||||
@classmethod
|
||||
def issue(cls, *, lifetime_seconds: int = 300, now: datetime | None = None, **scope: Any) -> "TenantContext":
|
||||
if not 1 <= lifetime_seconds <= 3600:
|
||||
raise ValidationError("lifetime_seconds must be between 1 and 3600")
|
||||
current = (now or utc_now()).astimezone(timezone.utc)
|
||||
return cls(
|
||||
**scope,
|
||||
issued_at=isoformat(current),
|
||||
expires_at=isoformat(current + timedelta(seconds=lifetime_seconds)),
|
||||
nonce=secrets.token_hex(16),
|
||||
)
|
||||
|
||||
def sign(self, key: bytes) -> str:
|
||||
if len(key) < 32:
|
||||
raise ValidationError("signing key must be at least 32 bytes")
|
||||
payload = _b64(canonical_json(asdict(self)))
|
||||
signature = _b64(hmac.new(key, payload.encode("ascii"), hashlib.sha256).digest())
|
||||
return f"{payload}.{signature}"
|
||||
|
||||
@classmethod
|
||||
def verify(
|
||||
cls,
|
||||
token: str,
|
||||
key: bytes,
|
||||
*,
|
||||
now: datetime | None = None,
|
||||
expected_tenant_id: str | None = None,
|
||||
expected_cell_id: str | None = None,
|
||||
) -> "TenantContext":
|
||||
if len(key) < 32:
|
||||
raise ValidationError("signing key must be at least 32 bytes")
|
||||
try:
|
||||
payload, encoded_signature = token.split(".", 1)
|
||||
actual = _unb64(encoded_signature)
|
||||
if encoded_signature != _b64(actual):
|
||||
raise ValidationError("non-canonical tenant context signature")
|
||||
data = json.loads(_unb64(payload))
|
||||
except Exception as exc:
|
||||
raise ValidationError("malformed tenant context token") from exc
|
||||
expected = hmac.new(key, payload.encode("ascii"), hashlib.sha256).digest()
|
||||
if not hmac.compare_digest(actual, expected):
|
||||
raise ValidationError("tenant context signature mismatch")
|
||||
context = cls(**data)
|
||||
current = (now or utc_now()).astimezone(timezone.utc)
|
||||
if current < parse_time(context.issued_at) - timedelta(seconds=60):
|
||||
raise ValidationError("tenant context issued in future")
|
||||
if current >= parse_time(context.expires_at):
|
||||
raise ValidationError("tenant context expired")
|
||||
if expected_tenant_id and context.tenant_id != expected_tenant_id:
|
||||
raise ScopeError("tenant mismatch")
|
||||
if expected_cell_id and context.cell_id != expected_cell_id:
|
||||
raise ScopeError("cell mismatch")
|
||||
return context
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class CanonicalMessage:
|
||||
tenant_id: str
|
||||
cell_id: str
|
||||
principal_id: str
|
||||
principal_type: str
|
||||
origin_type: str
|
||||
channel: str
|
||||
channel_account_id: str
|
||||
peer_id: str
|
||||
conversation_id: str
|
||||
session_id: str
|
||||
task_id: str | None
|
||||
event_id: str
|
||||
message_id: str
|
||||
reply_to_message_id: str | None
|
||||
direction: str
|
||||
command_capable: bool
|
||||
occurred_at: str
|
||||
received_at: str
|
||||
body: str
|
||||
quoted_body: str | None
|
||||
adapter_name: str
|
||||
adapter_version: str
|
||||
schema_version: str = "aios.message.v1"
|
||||
|
||||
def __post_init__(self) -> None:
|
||||
if self.schema_version != "aios.message.v1":
|
||||
raise ValidationError("unsupported message schema version")
|
||||
require_ident("tenant_id", self.tenant_id, tenant=True)
|
||||
for name in (
|
||||
"cell_id", "principal_id", "principal_type", "origin_type", "channel",
|
||||
"channel_account_id", "peer_id", "conversation_id", "session_id",
|
||||
"event_id", "adapter_name", "adapter_version",
|
||||
):
|
||||
require_ident(name, getattr(self, name))
|
||||
if self.task_id is not None:
|
||||
require_ident("task_id", self.task_id)
|
||||
normalize_message_id(self.message_id)
|
||||
if self.reply_to_message_id is not None:
|
||||
normalize_message_id(self.reply_to_message_id, field_name="reply_to_message_id")
|
||||
if self.direction not in {"inbound", "outbound", "internal"}:
|
||||
raise ValidationError("invalid direction")
|
||||
if not isinstance(self.command_capable, bool):
|
||||
raise ValidationError("command_capable must be boolean")
|
||||
parse_time(self.occurred_at)
|
||||
parse_time(self.received_at)
|
||||
if not isinstance(self.body, str):
|
||||
raise ValidationError("body must be a string")
|
||||
if self.quoted_body is not None and not isinstance(self.quoted_body, str):
|
||||
raise ValidationError("quoted_body must be a string or null")
|
||||
|
||||
@classmethod
|
||||
def from_mapping(cls, data: Mapping[str, Any]) -> "CanonicalMessage":
|
||||
content = data.get("content") or {}
|
||||
adapter = data.get("adapter") or {}
|
||||
if not isinstance(content, Mapping) or not isinstance(adapter, Mapping):
|
||||
raise ValidationError("content and adapter must be objects")
|
||||
values = dict(data)
|
||||
return cls(
|
||||
schema_version=values.get("schema_version", "aios.message.v1"),
|
||||
tenant_id=values["tenant_id"],
|
||||
cell_id=values["cell_id"],
|
||||
principal_id=values["principal_id"],
|
||||
principal_type=values["principal_type"],
|
||||
origin_type=values["origin_type"],
|
||||
channel=values["channel"],
|
||||
channel_account_id=values["channel_account_id"],
|
||||
peer_id=values["peer_id"],
|
||||
conversation_id=values["conversation_id"],
|
||||
session_id=values["session_id"],
|
||||
task_id=values.get("task_id"),
|
||||
event_id=values["event_id"],
|
||||
message_id=normalize_message_id(values["message_id"]),
|
||||
reply_to_message_id=(
|
||||
normalize_message_id(values["reply_to_message_id"], field_name="reply_to_message_id")
|
||||
if values.get("reply_to_message_id") is not None else None
|
||||
),
|
||||
direction=values["direction"],
|
||||
command_capable=values["command_capable"],
|
||||
occurred_at=values["occurred_at"],
|
||||
received_at=values["received_at"],
|
||||
body=content.get("body", ""),
|
||||
quoted_body=content.get("quoted_body"),
|
||||
adapter_name=adapter["name"],
|
||||
adapter_version=adapter["version"],
|
||||
)
|
||||
|
||||
def assert_context(self, context: TenantContext) -> None:
|
||||
fields = (
|
||||
"tenant_id", "cell_id", "principal_id", "session_id", "task_id",
|
||||
"channel", "channel_account_id",
|
||||
)
|
||||
mismatches = [name for name in fields if getattr(self, name) != getattr(context, name)]
|
||||
if mismatches:
|
||||
raise ScopeError("message/context mismatch: " + ", ".join(mismatches))
|
||||
|
||||
@property
|
||||
def is_authenticated_human_command(self) -> bool:
|
||||
return (
|
||||
self.direction == "inbound"
|
||||
and self.command_capable
|
||||
and self.principal_type == "authenticated_user"
|
||||
and self.origin_type == "channel_user"
|
||||
)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class PolicyDecision:
|
||||
allowed: bool
|
||||
approval_required: bool
|
||||
code: str
|
||||
reason: str
|
||||
|
||||
|
||||
READ_ONLY_TOOLS = frozenset({
|
||||
"read", "grep", "glob", "find", "ls", "web_search", "web_fetch",
|
||||
"memory_search", "sessions_list", "sessions_history", "session_status",
|
||||
})
|
||||
|
||||
|
||||
def evaluate_tool_call(tool_name: str, message: CanonicalMessage) -> PolicyDecision:
|
||||
normalized = tool_name.strip().lower() if isinstance(tool_name, str) else ""
|
||||
if not normalized:
|
||||
return PolicyDecision(False, False, "invalid_tool", "tool name missing")
|
||||
if normalized in READ_ONLY_TOOLS:
|
||||
return PolicyDecision(True, False, "read_only", "read-only operation")
|
||||
if not message.is_authenticated_human_command:
|
||||
return PolicyDecision(
|
||||
False, False, "origin_denied",
|
||||
"side effects require an authenticated current human command",
|
||||
)
|
||||
return PolicyDecision(
|
||||
True, True, "approval_required",
|
||||
"authenticated human side effect requires explicit approval",
|
||||
)
|
||||
+18
-29
@@ -1,8 +1,7 @@
|
||||
<<<<<<< HEAD
|
||||
# AIOS Agent Command Plane Registry
|
||||
# Git is the single source of truth for all agent commands.
|
||||
version: 1.0.0
|
||||
created_at: 2026-07-08T15:20:00+08:00
|
||||
created_at: "2026-07-08T15:20:00+08:00"
|
||||
baseline: V1R3C1
|
||||
|
||||
commands:
|
||||
@@ -12,6 +11,22 @@ commands:
|
||||
completed_path: "agents/commands/completed/"
|
||||
failed_path: "agents/commands/failed/"
|
||||
|
||||
directories:
|
||||
commands/active: "New commands pending execution — Git is the only entry point"
|
||||
commands/running: "Commands currently being executed by an agent"
|
||||
commands/completed: "Commands that finished successfully — moved here on success"
|
||||
commands/failed: "Commands that finished with errors — moved here on failure"
|
||||
|
||||
lifecycle:
|
||||
new: active/
|
||||
running: running/
|
||||
success: completed/
|
||||
failure: failed/
|
||||
|
||||
# Command lifecycle state machine:
|
||||
# active/ → locked & moved to running/ → execute → success → completed/
|
||||
# → failure → failed/
|
||||
|
||||
policies:
|
||||
path: "agents/policies/"
|
||||
source: "git"
|
||||
@@ -38,30 +53,4 @@ audit:
|
||||
agent_runs: "audit/agent-runs/"
|
||||
version_history: "audit/version-history/"
|
||||
command_history: "audit/command-history/"
|
||||
=======
|
||||
# AIOS Agent Command Registry
|
||||
# Git is the single source of truth for all agent commands.
|
||||
|
||||
registry_version: 1.0.0
|
||||
created_at: "2026-07-08T15:44:00+08:00"
|
||||
baseline: V1R3C1
|
||||
|
||||
directories:
|
||||
commands/active: "New commands pending execution — Git is the only entry point"
|
||||
commands/running: "Commands currently being executed by an agent"
|
||||
commands/completed: "Commands that finished successfully — moved here on success"
|
||||
commands/failed: "Commands that finished with errors — moved here on failure"
|
||||
|
||||
state: agents/state/
|
||||
policies: agents/policies/
|
||||
|
||||
lifecycle:
|
||||
new: active/
|
||||
running: running/
|
||||
success: completed/
|
||||
failure: failed/
|
||||
|
||||
# Command lifecycle state machine:
|
||||
# active/ → locked & moved to running/ → execute → success → completed/
|
||||
# → failure → failed/
|
||||
>>>>>>> 4d18ee0 (feat(cmd): enable Agent Command Plane, audit plane, and Web UI dashboard)
|
||||
interaction_history: "audit/interaction-history/"
|
||||
|
||||
Binary file not shown.
@@ -0,0 +1,20 @@
|
||||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
|
||||
printf 'AIOS V2R1C0 RC1 health check\n'
|
||||
|
||||
python3 - <<'PY'
|
||||
from pathlib import Path
|
||||
required = [
|
||||
'active-runtime/app/aios_v2r1/tenant_context.py',
|
||||
'active-runtime/app/aios_v2r1/router.py',
|
||||
'active-runtime/app/aios_v2r1/hermes_fabric.py',
|
||||
'openclaw/plugins/aios-tenant-boundary/openclaw.plugin.json',
|
||||
]
|
||||
missing=[p for p in required if not Path(p).exists()]
|
||||
if missing:
|
||||
raise SystemExit('missing: '+','.join(missing))
|
||||
print('artifact presence PASS')
|
||||
PY
|
||||
|
||||
echo 'runtime health requires OpenClaw environment probe'
|
||||
@@ -0,0 +1,29 @@
|
||||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
|
||||
ROOT=$(cd "$(dirname "$0")/../.." && pwd)
|
||||
EXPECTED_BRANCH="release/v2r1c0-tenant-cell-fabric-20260712"
|
||||
|
||||
if [[ "$(git -C "$ROOT" branch --show-current)" != "$EXPECTED_BRANCH" ]]; then
|
||||
echo "wrong release branch"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
COMMIT=$(git -C "$ROOT" rev-parse HEAD)
|
||||
echo "Installing AIOS V2R1C0 RC1 commit=$COMMIT"
|
||||
|
||||
python3 - <<'PY'
|
||||
import compileall
|
||||
if not compileall.compile_dir('active-runtime/app/aios_v2r1', quiet=1):
|
||||
raise SystemExit(1)
|
||||
print('python compile PASS')
|
||||
PY
|
||||
|
||||
if [[ -f openclaw/plugins/aios-tenant-boundary/package.json ]]; then
|
||||
echo "plugin package PASS"
|
||||
else
|
||||
echo "plugin package missing"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "Installation preflight PASS"
|
||||
@@ -0,0 +1,27 @@
|
||||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
|
||||
MODE=${1:---check}
|
||||
|
||||
case "$MODE" in
|
||||
--check)
|
||||
echo "V2R1C0 RC1 validation mode"
|
||||
;;
|
||||
--install)
|
||||
echo "Install requires approved OpenClaw Cell target"
|
||||
;;
|
||||
--rollback)
|
||||
echo "Rollback requires recorded Cell backup"
|
||||
;;
|
||||
*)
|
||||
echo "Usage: $0 [--check|--install|--rollback]"
|
||||
exit 2
|
||||
;;
|
||||
esac
|
||||
|
||||
python3 - <<'PY'
|
||||
import compileall
|
||||
raise SystemExit(0 if compileall.compile_dir('active-runtime/app/aios_v2r1', quiet=1) else 1)
|
||||
PY
|
||||
|
||||
echo "python runtime syntax: PASS"
|
||||
@@ -1,4 +1,3 @@
|
||||
<<<<<<< HEAD
|
||||
# AIOS Agent Audit Plane Architecture
|
||||
|
||||
## Overview
|
||||
@@ -25,9 +24,10 @@ Agent Command Plane (agents/commands/)
|
||||
+---> Audit
|
||||
| |
|
||||
| v
|
||||
| audit/agent-runs/ (per-agent log)
|
||||
| audit/command-history/ (per-command log)
|
||||
| audit/version-history/ (per-baseline log)
|
||||
| audit/agent-runs/ (per-agent log)
|
||||
| audit/command-history/ (per-command log)
|
||||
| audit/version-history/ (per-baseline log)
|
||||
| audit/interaction-history/ (agent conversation traces)
|
||||
|
|
||||
+---> Git Commit
|
||||
|
|
||||
@@ -45,8 +45,39 @@ Agent Command Plane (agents/commands/)
|
||||
5. Git commit locks the audit record
|
||||
6. Web UI displays timeline from git history
|
||||
|
||||
## Directory Structure
|
||||
|
||||
```
|
||||
audit/
|
||||
├── agent-runs/ # Per-execution records (JSON)
|
||||
├── command-history/ # Command lifecycle history
|
||||
├── version-history/ # Version/baseline change log
|
||||
└── interaction-history/ # Agent conversation traces
|
||||
```
|
||||
|
||||
## Audit Record Schema
|
||||
|
||||
Current agent-run records use the following fields:
|
||||
|
||||
| Field | Description |
|
||||
|-------|-------------|
|
||||
| agent_run_id | Unique execution ID |
|
||||
| command | Command file name |
|
||||
| agent | Executing agent name |
|
||||
| version | Baseline version at execution time |
|
||||
| objective | Human-readable goal |
|
||||
| start_time | ISO-8601 start timestamp |
|
||||
| end_time | ISO-8601 completion timestamp |
|
||||
| interaction_count | Agent-owner interaction turns |
|
||||
| tool_call_count | Tool invocations during execution |
|
||||
| changed_files | Files modified in this run |
|
||||
| commit_sha | Git commit hash |
|
||||
| test_result | Test verification outcome |
|
||||
| final_result | SUCCESS / FAILED / PARTIAL |
|
||||
| evidence_path | Link to evidence directory |
|
||||
|
||||
Legacy records remain valid and may use the following compatibility shape:
|
||||
|
||||
```json
|
||||
{
|
||||
"id": "",
|
||||
@@ -72,51 +103,6 @@ Agent Command Plane (agents/commands/)
|
||||
- Every code change must be traceable to who/what agent created it
|
||||
- No agent-created changes without audit trail
|
||||
|
||||
## Related
|
||||
|
||||
- [Agent Command Plane](../agents/README.md)
|
||||
- [Baseline System](baseline-system.md)
|
||||
=======
|
||||
# AIOS Agent Audit Plane
|
||||
|
||||
## Purpose
|
||||
|
||||
Every agent action is recorded. All code changes are traceable to:
|
||||
- Who made the change
|
||||
- Why the change was made
|
||||
- When it was made
|
||||
- Which version introduced it
|
||||
- What test results showed
|
||||
|
||||
## Directory Structure
|
||||
|
||||
```
|
||||
audit/
|
||||
├── agent-runs/ # Per-execution records (JSON)
|
||||
├── command-history/ # Command lifecycle history
|
||||
├── version-history/ # Version/baseline change log
|
||||
└── interaction-history/ # Agent conversation traces
|
||||
```
|
||||
|
||||
## Agent Run Record
|
||||
|
||||
| Field | Description |
|
||||
|-------|-------------|
|
||||
| agent_run_id | Unique execution ID |
|
||||
| command | Command file name |
|
||||
| agent | Executing agent name |
|
||||
| version | Baseline version at execution time |
|
||||
| objective | Human-readable goal |
|
||||
| start_time | ISO-8601 start timestamp |
|
||||
| end_time | ISO-8601 completion timestamp |
|
||||
| interaction_count | Agent-owner interaction turns |
|
||||
| tool_call_count | Tool invocations during execution |
|
||||
| changed_files | Files modified in this run |
|
||||
| commit_sha | Git commit hash |
|
||||
| test_result | Test verification outcome |
|
||||
| final_result | SUCCESS / FAILED / PARTIAL |
|
||||
| evidence_path | Link to evidence directory |
|
||||
|
||||
## Version History
|
||||
|
||||
Records baseline promotions, rollbacks, and version changes.
|
||||
@@ -127,6 +113,9 @@ Conversation logs between agent and owner for each command execution.
|
||||
|
||||
## Audit Trail Requirement
|
||||
|
||||
All changes tracked via Git with signed commits where possible.
|
||||
Every commit message references the originating Command ID.
|
||||
>>>>>>> 4d18ee0 (feat(cmd): enable Agent Command Plane, audit plane, and Web UI dashboard)
|
||||
All changes are tracked via Git with signed commits where possible. Every commit references the originating Command ID.
|
||||
|
||||
## Related
|
||||
|
||||
- [Agent Command Plane](../agents/README.md)
|
||||
- [Baseline System](baseline-system.md)
|
||||
|
||||
@@ -0,0 +1,26 @@
|
||||
# AIOS V1R5 to V2R1 Migration Plan
|
||||
|
||||
## Goal
|
||||
|
||||
Move from shared Gateway assumptions to Tenant Cell isolation.
|
||||
|
||||
## Order
|
||||
|
||||
1. Establish Tenant Registry and signed Tenant Context.
|
||||
2. Implement Tenant Router.
|
||||
3. Implement OpenClaw Cell lifecycle management.
|
||||
4. Introduce canonical message envelope.
|
||||
5. Add provenance and execution policy enforcement.
|
||||
6. Migrate Hermes into shared fabric with isolated profiles.
|
||||
7. Migrate memory, secrets and audit storage.
|
||||
|
||||
## Do Not
|
||||
|
||||
- Do not modify Hermes first.
|
||||
- Do not share production credentials across tenants.
|
||||
- Do not treat workspace separation as a sandbox.
|
||||
- Do not allow unknown message origins to execute tools.
|
||||
|
||||
## Acceptance
|
||||
|
||||
Each migration stage requires automated tests and runtime evidence before promotion.
|
||||
+49
@@ -0,0 +1,49 @@
|
||||
# AIOS V2R1 OpenClaw Tenant Cell + Hermes Shared Agent Fabric Architecture
|
||||
|
||||
## Status
|
||||
|
||||
Release train: V2R1C0
|
||||
|
||||
Purpose: replace shared runtime trust assumptions with tenant-isolated Cell architecture.
|
||||
|
||||
## Principles
|
||||
|
||||
1. OpenClaw Gateway is a trust boundary.
|
||||
2. Each production tenant receives an isolated Cell.
|
||||
3. Hermes provides shared scheduling/fabric capability but not shared tenant state.
|
||||
4. Tenant identity, origin, session and task scope are mandatory in every event.
|
||||
5. Unknown provenance fails closed.
|
||||
|
||||
## Target Components
|
||||
|
||||
- Tenant Router
|
||||
- OpenClaw Cell Manager
|
||||
- Canonical Message Envelope
|
||||
- Tenant Inbox/Outbox Ledger
|
||||
- Secret Scope Manager
|
||||
- Memory Namespace Manager
|
||||
- Hermes Profile Worker Fabric
|
||||
- Sandbox Execution Layer
|
||||
- Audit Event Pipeline
|
||||
|
||||
## Migration Order
|
||||
|
||||
Phase 1: Tenant Router + Cell Manager
|
||||
|
||||
Phase 2: Canonical Message and Policy Layer
|
||||
|
||||
Phase 3: Hermes Shared Agent Fabric
|
||||
|
||||
Phase 4: Memory, Secret and Audit isolation
|
||||
|
||||
Phase 5: Production tenant migration
|
||||
|
||||
## Release Gate
|
||||
|
||||
A V2R1 production release requires:
|
||||
|
||||
- tenant isolation tests passed
|
||||
- message provenance tests passed
|
||||
- runtime commit matches release commit
|
||||
- OpenClaw plugin runtime inspection passed
|
||||
- rollback verified
|
||||
@@ -0,0 +1,601 @@
|
||||
# V2R1 Authenticated Runtime Release Implementation Plan
|
||||
|
||||
> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
|
||||
|
||||
**Goal:** Close exactly five reviewed blockers between the replayed V2R1 tree and an evidence-backed, authenticated, digest-bound release candidate.
|
||||
|
||||
**Architecture:** Use one canonical `aios_v2r1` Python package; authenticate a Node-to-Python loopback envelope before server-side Weixin projection and authority resolution; make `ACCEPTED` terminal; dispatch through a durable outbox and the verified Hermes HTTP router; stage an isolated OpenClaw candidate with three services; promote only byte-identical artifacts after live reconciliation evidence.
|
||||
|
||||
**Tech Stack:** Python 3.11 and pytest, SQLite, Node.js, OpenClaw 2026.6.11, loopback HTTP, systemd credentials and units, SHA-256 manifests.
|
||||
|
||||
## Global gates and dynamic blocker ledger
|
||||
|
||||
- B1 and B2 may proceed only after review accepts the corrected design and plan.
|
||||
- B3, B4, and B5 are evidence-gated. Unresolved evidence stops that task before implementation, commit, or ledger append.
|
||||
- Current outbound evidence is `EVIDENCE_REQUIRED`; B4 and B5 remain stopped until a verified provider echo exactly binds `client_id -> message_id`.
|
||||
- Keep exactly five blocker commits, one each for B1 through B5. The docs-correction commit is the reviewed starting point, not a blocker.
|
||||
- Do not create a tag, edit `VERSION` or `baseline/current.json`, push `main`, deploy/restart a live service, modify active OpenClaw configuration, or invoke Fleet.
|
||||
- All OpenClaw loader work uses an isolated temporary or candidate config/state directory.
|
||||
- `ACCEPTED` is terminal. Legacy handling is reachable only when bridge mode is explicitly `disabled`.
|
||||
- Never claim exactly-once Hermes delivery or use time/approximation as message authority.
|
||||
|
||||
After docs review, initialize the stable per-worktree ledger from the then-current tip rather than a hardcoded SHA:
|
||||
|
||||
```bash
|
||||
test -z "$(git status --porcelain)"
|
||||
test "$(git branch --show-current)" = "integration/v2r1-runtime-20260714"
|
||||
start_sha="$(git rev-parse HEAD)"
|
||||
start_parent="$(git rev-parse HEAD^)"
|
||||
start_tree="$(git rev-parse HEAD^{tree})"
|
||||
ledger="$(git rev-parse --git-path v2r1-blocker-ledger.tsv)"
|
||||
umask 077
|
||||
test ! -e "$ledger"
|
||||
printf 'START\t%s\t%s\t%s\n' "$start_sha" "$start_parent" "$start_tree" >"$ledger"
|
||||
```
|
||||
|
||||
Expected: the clean reviewed docs-correction tip is `START`. At the beginning of every blocker, rehydrate and verify the latest ledger row before work:
|
||||
|
||||
```bash
|
||||
ledger="$(git rev-parse --git-path v2r1-blocker-ledger.tsv)"
|
||||
test -s "$ledger"
|
||||
IFS=$'\t' read -r last_label last_sha last_parent last_tree < <(tail -n 1 "$ledger")
|
||||
test "$(git rev-parse HEAD)" = "$last_sha"
|
||||
test "$(git rev-parse HEAD^)" = "$last_parent"
|
||||
test "$(git rev-parse HEAD^{tree})" = "$last_tree"
|
||||
```
|
||||
|
||||
Each blocker appends `label, SHA, parent, tree` only after its review passes. The ledger stays in the worktree Git directory and is never staged.
|
||||
|
||||
---
|
||||
|
||||
## Task B1: Prove the real OpenClaw plugin loader and permission contract
|
||||
|
||||
**Files:**
|
||||
|
||||
- Modify: `openclaw/plugins/aios-tenant-boundary/package.json`
|
||||
- Modify: `openclaw/plugins/aios-tenant-boundary/openclaw.plugin.json`
|
||||
- Modify only on demonstrated hook failure: `openclaw/plugins/aios-tenant-boundary/dist/index.js`
|
||||
- Modify only on demonstrated policy failure: `openclaw/plugins/aios-tenant-boundary/dist/policy.js`
|
||||
- Create: `openclaw/plugins/aios-tenant-boundary/test/compat.test.js`
|
||||
- Create: `openclaw/plugins/aios-tenant-boundary/test/policy.test.js`
|
||||
- Create: `openclaw/plugins/aios-tenant-boundary/test/loader.test.mjs`
|
||||
|
||||
**Exact contract:** package/manifest versions `2.1.0-rc.1`; `blockUnknownAgentRuns` boolean default `false`; `approvalTimeoutMs` integer min `1000`, max `300000`, default `60000`; every runtime-read property declared. Default permission proves only `before_tool_call` is usable. `before_agent_run` and `agent_end` require `plugins.entries.aios-tenant-boundary.hooks.allowConversationAccess=true`. Fake API tests are supplemental; real runtime inspection is mandatory.
|
||||
|
||||
- [ ] Add Node tests for missing/blocked/allowlisted senders, automation, read-only tools, absent provenance, approval, exact timeout bounds, cleanup, age pruning, versions, and schema.
|
||||
- [ ] Add `loader.test.mjs` to parse real inspect JSON and assert linked path, version, diagnostics, hooks, and permission state.
|
||||
- [ ] Run initial RED:
|
||||
|
||||
```bash
|
||||
cd openclaw/plugins/aios-tenant-boundary
|
||||
npm test
|
||||
```
|
||||
|
||||
Expected RED: current package has no tracked tests; version and missing-schema assertions fail.
|
||||
|
||||
- [ ] Normalize versions/schema; change runtime only when an executable test proves incompatibility. Capture TAP and prove at least one test executed:
|
||||
|
||||
```bash
|
||||
tmp="$(mktemp -d)"
|
||||
set -o pipefail
|
||||
npm test -- --test-reporter=tap | tee "$tmp/plugin.tap"
|
||||
test "$(grep -c '^ok [0-9]' "$tmp/plugin.tap")" -gt 0
|
||||
test -z "$(grep '^not ok ' "$tmp/plugin.tap" || true)"
|
||||
```
|
||||
|
||||
Expected GREEN: npm exits 0, TAP contains one or more `ok` test records, and contains no `not ok` record.
|
||||
- [ ] Run the real loader twice in isolated state:
|
||||
|
||||
```bash
|
||||
repo="$(git rev-parse --show-toplevel)"
|
||||
tmp="$(mktemp -d)"
|
||||
export OPENCLAW_STATE_DIR="$tmp/state"
|
||||
export OPENCLAW_CONFIG_PATH="$tmp/state/openclaw.json"
|
||||
mkdir -p "$OPENCLAW_STATE_DIR"
|
||||
openclaw plugins install --link "$repo/openclaw/plugins/aios-tenant-boundary"
|
||||
openclaw plugins inspect aios-tenant-boundary --runtime --json >"$tmp/default-inspect.json"
|
||||
node "$repo/openclaw/plugins/aios-tenant-boundary/test/loader.test.mjs" default "$tmp/default-inspect.json"
|
||||
openclaw config set plugins.entries.aios-tenant-boundary.hooks.allowConversationAccess true --strict-json
|
||||
openclaw config validate
|
||||
set +e
|
||||
openclaw doctor --lint --json >"$tmp/doctor-lint.json"
|
||||
doctor_rc=$?
|
||||
set -e
|
||||
test "$doctor_rc" = 0 || test "$doctor_rc" = 1
|
||||
python3 - "$tmp/doctor-lint.json" <<'PY'
|
||||
import json, sys
|
||||
data = json.load(open(sys.argv[1]))
|
||||
def walk(value):
|
||||
if isinstance(value, dict):
|
||||
yield value
|
||||
for child in value.values(): yield from walk(child)
|
||||
elif isinstance(value, list):
|
||||
for child in value: yield from walk(child)
|
||||
bad = [item for item in walk(data) if str(item.get("severity", "")).lower() in {"error", "fatal"} and "plugin" in json.dumps(item).lower()]
|
||||
assert not bad, bad
|
||||
PY
|
||||
openclaw doctor --post-upgrade --json >"$tmp/doctor-plugin.json"
|
||||
openclaw plugins inspect aios-tenant-boundary --runtime --json >"$tmp/opt-in-inspect.json"
|
||||
node "$repo/openclaw/plugins/aios-tenant-boundary/test/loader.test.mjs" opt-in "$tmp/opt-in-inspect.json"
|
||||
```
|
||||
|
||||
Expected GREEN: config validation and post-upgrade doctor exit 0; lint doctor may exit 0 or 1, warnings are allowed, parsed JSON contains zero error/fatal plugin findings; default inspection proves only `before_tool_call`; opt-in proves `before_agent_run`, `before_tool_call`, `agent_end`.
|
||||
|
||||
- [ ] Run carried-forward tests:
|
||||
|
||||
```bash
|
||||
PYTHONDONTWRITEBYTECODE=1 PYTEST_ADDOPTS='-p no:cacheprovider' PYTHONPATH=active-runtime/app python3 -m pytest tests/v2r1 tests/integration -q
|
||||
```
|
||||
|
||||
Expected GREEN: `32 passed`.
|
||||
|
||||
- [ ] Commit and append ledger:
|
||||
|
||||
```bash
|
||||
git add openclaw/plugins/aios-tenant-boundary/package.json openclaw/plugins/aios-tenant-boundary/openclaw.plugin.json \
|
||||
openclaw/plugins/aios-tenant-boundary/dist/index.js openclaw/plugins/aios-tenant-boundary/dist/policy.js \
|
||||
openclaw/plugins/aios-tenant-boundary/test/compat.test.js openclaw/plugins/aios-tenant-boundary/test/policy.test.js \
|
||||
openclaw/plugins/aios-tenant-boundary/test/loader.test.mjs
|
||||
git commit -m "fix(v2r1): prove OpenClaw plugin compatibility"
|
||||
```
|
||||
|
||||
### Review B1
|
||||
|
||||
- [ ] `git diff --check HEAD^ HEAD` has no output; commit contains only named B1 paths and unchanged optional `dist` files do not appear.
|
||||
- [ ] Re-run Node tests, both real loader permission modes, validation/doctor, and 32 Python tests.
|
||||
- [ ] Prove B1 parent equals ledger `START` and, before the final append step, the ledger still contains only `START`.
|
||||
- [ ] Stop if real inspection does not prove default-only `before_tool_call` and explicit conversation-access hooks.
|
||||
- [ ] After every prior B1 review check passes, append B1 and verify the recorded commit identity:
|
||||
|
||||
```bash
|
||||
ledger="$(git rev-parse --git-path v2r1-blocker-ledger.tsv)"
|
||||
printf 'B1\t%s\t%s\t%s\n' "$(git rev-parse HEAD)" "$(git rev-parse HEAD^)" "$(git rev-parse HEAD^{tree})" >>"$ledger"
|
||||
IFS=$'\t' read -r label sha parent tree < <(tail -n 1 "$ledger")
|
||||
test "$label" = B1
|
||||
test "$sha" = "$(git rev-parse HEAD)"
|
||||
test "$parent" = "$(git rev-parse HEAD^)"
|
||||
test "$tree" = "$(git rev-parse HEAD^{tree})"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Task B2: Package only `aios_v2r1` and repair the exact legacy import set
|
||||
|
||||
**Files:**
|
||||
|
||||
- Create: `active-runtime/pyproject.toml`
|
||||
- Create: `active-runtime/app/aios_v2r1/__init__.py`
|
||||
- Create: `active-runtime/app/aios_v2r1/ingress_service.py`
|
||||
- Modify: `active-runtime/app/aios_v2r1/cli.py`
|
||||
- Create: `tests/v2r1/test_ingress_service.py`
|
||||
- Create: `tests/test_v2r1_package_identity.py`
|
||||
- Modify: the exact 23 Appendix A test files, and no unlisted legacy import file
|
||||
|
||||
**Exact contract:** V2R1 imports only as `aios_v2r1`; no `active_runtime` shim/alias/namespace extension/copied tree. Wheel includes `aios_v2r1`, excludes `active_runtime` and legacy `app`. Legacy repository tests change `active_runtime.app.*` to `app.*` and run with `PYTHONPATH='active-runtime:active-runtime/app'`. Mutation routes return bounded `SERVICE_NOT_CONFIGURED` until B3/B4 processors exist. Existing cell CLI stays compatible and `serve` is separate.
|
||||
|
||||
- [ ] Rehydrate the stable blocker ledger using the global snippet and require its latest label is `B1`.
|
||||
- [ ] Rehydrate the exact explorer manifest path and compare sorted actual/expected lists between exact marker lines. The marker names are assembled from split literals so this command cannot match itself:
|
||||
|
||||
```bash
|
||||
actual="$(git rev-parse --git-path v2r1-active-runtime-imports.actual)"
|
||||
expected="$(git rev-parse --git-path v2r1-active-runtime-imports.expected)"
|
||||
plan=docs/superpowers/plans/2026-07-14-v2r1-runtime-release-plan.md
|
||||
begin="$(printf '%s' 'APPENDIX_A_''BEGIN')"
|
||||
end="$(printf '%s' 'APPENDIX_A_''END')"
|
||||
tick="$(printf '\140')"
|
||||
git grep -l -E '^(from|import) active_runtime\.app' -- tests | sort >"$actual"
|
||||
awk -v begin="${tick}${begin}${tick}" -v end="${tick}${end}${tick}" '
|
||||
$0 == begin {inside=1; next}
|
||||
$0 == end {inside=0; next}
|
||||
inside && /^- tests\// {sub(/^- /, ""); print}
|
||||
' "$plan" | sort >"$expected"
|
||||
test "$(wc -l < "$actual" | tr -d ' ')" = 23
|
||||
test "$(wc -l < "$expected" | tr -d ' ')" = 23
|
||||
cmp -s "$actual" "$expected"
|
||||
```
|
||||
|
||||
Expected: exact match to 23 paths. Drift requires another docs review.
|
||||
|
||||
- [ ] Add package/service/CLI tests; run initial RED:
|
||||
|
||||
```bash
|
||||
PYTHONDONTWRITEBYTECODE=1 PYTEST_ADDOPTS='-p no:cacheprovider' PYTHONPATH='active-runtime:active-runtime/app' \
|
||||
python3 -m pytest tests/v2r1/test_ingress_service.py tests/test_v2r1_package_identity.py -q
|
||||
```
|
||||
|
||||
Expected RED: package metadata, ingress service, and identity tests do not exist.
|
||||
|
||||
- [ ] Implement package/disabled processor boundary and replace imports in exactly Appendix A. Prove no shim/old import:
|
||||
|
||||
```bash
|
||||
test ! -e active_runtime
|
||||
test -z "$(git grep -l -E '^(from|import) active_runtime\.app' -- tests || true)"
|
||||
```
|
||||
|
||||
- [ ] Run full collect and full suite:
|
||||
|
||||
```bash
|
||||
PYTHONDONTWRITEBYTECODE=1 PYTEST_ADDOPTS='-p no:cacheprovider' PYTHONPATH='active-runtime:active-runtime/app' python3 -m pytest --collect-only -q
|
||||
PYTHONDONTWRITEBYTECODE=1 PYTEST_ADDOPTS='-p no:cacheprovider' PYTHONPATH='active-runtime:active-runtime/app' python3 -m pytest -q
|
||||
```
|
||||
|
||||
Expected GREEN: zero collection/import errors and complete suite passes; pre-existing failures still block B2.
|
||||
|
||||
- [ ] Build and inspect isolated wheel:
|
||||
|
||||
```bash
|
||||
tmp="$(mktemp -d)"
|
||||
python3 -m pip wheel --no-deps --no-build-isolation active-runtime -w "$tmp/wheels"
|
||||
wheel="$(find "$tmp/wheels" -name '*.whl' -print -quit)"
|
||||
python3 -m venv "$tmp/venv"
|
||||
"$tmp/venv/bin/python" -m pip install --no-deps "$wheel"
|
||||
"$tmp/venv/bin/python" - "$wheel" <<'PY'
|
||||
import sys, zipfile
|
||||
names = zipfile.ZipFile(sys.argv[1]).namelist()
|
||||
assert any(n.endswith("aios_v2r1/ingress_service.py") for n in names)
|
||||
assert not any(n.startswith("active_runtime/") or n.startswith("app/") for n in names)
|
||||
import aios_v2r1
|
||||
assert aios_v2r1.__name__ == "aios_v2r1"
|
||||
PY
|
||||
```
|
||||
|
||||
Expected GREEN: one wheel, one V2R1 namespace, installed identity `aios_v2r1`.
|
||||
|
||||
- [ ] Stage six named paths plus exact explorer list, commit, append ledger:
|
||||
|
||||
```bash
|
||||
actual="$(git rev-parse --git-path v2r1-active-runtime-imports.actual)"
|
||||
git add active-runtime/pyproject.toml active-runtime/app/aios_v2r1/__init__.py \
|
||||
active-runtime/app/aios_v2r1/ingress_service.py active-runtime/app/aios_v2r1/cli.py \
|
||||
tests/v2r1/test_ingress_service.py tests/test_v2r1_package_identity.py
|
||||
while IFS= read -r path; do git add -- "$path"; done <"$actual"
|
||||
git commit -m "feat(v2r1): package canonical authenticated ingress"
|
||||
```
|
||||
|
||||
### Review B2
|
||||
|
||||
- [ ] Require `git diff --check`, exactly 29 paths (six named plus Appendix A), exact-list/no-shim checks, full collect/full pytest, and wheel identity.
|
||||
- [ ] Require B2 parent equals B1 in ledger.
|
||||
- [ ] Prove mutation routes remain fail-closed until authenticated processors are installed.
|
||||
- [ ] After all prior B2 review checks pass, append B2 and verify the recorded commit identity:
|
||||
|
||||
```bash
|
||||
ledger="$(git rev-parse --git-path v2r1-blocker-ledger.tsv)"
|
||||
printf 'B2\t%s\t%s\t%s\n' "$(git rev-parse HEAD)" "$(git rev-parse HEAD^)" "$(git rev-parse HEAD^{tree})" >>"$ledger"
|
||||
IFS=$'\t' read -r label sha parent tree < <(tail -n 1 "$ledger")
|
||||
test "$label" = B2
|
||||
test "$sha" = "$(git rev-parse HEAD)"
|
||||
test "$parent" = "$(git rev-parse HEAD^)"
|
||||
test "$tree" = "$(git rev-parse HEAD^{tree})"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Task B3: Implement authenticated Node transport and server-side Weixin authority
|
||||
|
||||
**Evidence gate before code:** create `release/v2r1c0-rc1/weixin-bridge-evidence.json` only after recording installed TS/JS paths and SHA-256, exact inbound bigint/raw fields, authenticated account/sender/conversation sources, authority-map owner/mode/schema, candidate credential contract, and `disabled|enforced` mode owner. Stop if any source is inferred, Node would need the authority map, or patch targets are not byte-idempotent.
|
||||
|
||||
**Files after evidence acceptance:**
|
||||
|
||||
- Modify: `active-runtime/app/aios_v2r1/identity.py`
|
||||
- Modify: `active-runtime/app/aios_v2r1/tenant_context.py`
|
||||
- Modify: `active-runtime/app/aios_v2r1/ingress_service.py`
|
||||
- Create: `active-runtime/app/aios_v2r1/bridge_auth.py`
|
||||
- Create: `active-runtime/app/aios_v2r1/weixin_projection.py`
|
||||
- Create: `fixes/patch_openclaw_weixin_v2r1_ingress.py`
|
||||
- Create: `tests/v2r1/test_bridge_auth.py`
|
||||
- Create: `tests/v2r1/test_weixin_projection.py`
|
||||
- Create: `tests/integration/test_v2r1_bridge_transport.py`
|
||||
- Create: `tests/test_weixin_v2r1_ingress_bridge.py`
|
||||
- Create: four `tests/fixtures/weixin_v2r1/*.json` files named in the commit command
|
||||
- Create: `release/v2r1c0-rc1/weixin-bridge-evidence.json`
|
||||
|
||||
**Exact contract:** Every authenticated POST has wire shape `{"unsigned_body":{"schema_version":"aios.signed-request.v1","key_id":"bridge-current","issued_at_ms":1784000000000,"nonce":"base64url-16-byte-value","route_payload":{}},"signature":"lowercase-64-hex"}`. `unsigned_body` has exactly those five fields; `route_payload` holds only route-specific content. The signing object is exactly `{"method":"POST","path":"<exact route>","body":unsigned_body}`. Canonical JSON is UTF-8 with recursive Unicode-codepoint-sorted object keys, no whitespace, no ASCII escaping, no floats, and string IDs; the outer `signature` is the lowercase 64-hex HMAC-SHA256 of those bytes. There is no authorization header, nested signature, or alternate route form. Python verifies before projection. Skew 30 seconds; replay five minutes; active+previous rotation; fresh nonce retry. Node reads bridge-ingress and the separate receipt-read keyring through distinct `$CREDENTIALS_DIRECTORY` files. Python owns projection/authority/internal signing. `POST /v1/receipts/status` accepts `account_id` plus exactly one of `event_id|receipt_id`, resolves only same-account/event scope, and uses receipt-read. Response max 4096 bytes. `REPLAY_REJECTED` is transport/service-only, never `RuntimeIngressResponse`. Accepted is terminal; legacy disabled-only. `Date.now()` and every local `_ms` timestamp are telemetry only.
|
||||
|
||||
- [ ] Rehydrate the stable ledger with the global snippet and require latest label `B2` before evidence collection.
|
||||
- [ ] Add RED tests for the one exact wire/signing contract on `/v1/ingress` and `/v1/receipts/status`, including rejection of extra/missing fields, signature-inside-body, authorization-header variants, nonce lengths, skew boundaries, replay, key rotation, fresh retry, roles, bounded routes, terminal accepted, disabled legacy, bigint, and exact quote/attachment.
|
||||
- [ ] Run initial RED:
|
||||
|
||||
```bash
|
||||
PYTHONDONTWRITEBYTECODE=1 PYTEST_ADDOPTS='-p no:cacheprovider' PYTHONPATH='active-runtime:active-runtime/app' \
|
||||
python3 -m pytest tests/v2r1/test_bridge_auth.py tests/v2r1/test_weixin_projection.py \
|
||||
tests/integration/test_v2r1_bridge_transport.py tests/test_weixin_v2r1_ingress_bridge.py -q
|
||||
```
|
||||
|
||||
Expected RED: authenticator, server projection, processor, patcher absent.
|
||||
|
||||
- [ ] Implement authenticated transport/server projection and byte-idempotent TS/JS patch. Never embed authority or internal key in Node.
|
||||
- [ ] Run focused, existing Weixin, full collect, and full pytest. Expected GREEN: all pass.
|
||||
- [ ] Commit exactly 15 paths and append ledger:
|
||||
|
||||
```bash
|
||||
git add active-runtime/app/aios_v2r1/identity.py active-runtime/app/aios_v2r1/tenant_context.py \
|
||||
active-runtime/app/aios_v2r1/ingress_service.py active-runtime/app/aios_v2r1/bridge_auth.py \
|
||||
active-runtime/app/aios_v2r1/weixin_projection.py fixes/patch_openclaw_weixin_v2r1_ingress.py \
|
||||
tests/v2r1/test_bridge_auth.py tests/v2r1/test_weixin_projection.py \
|
||||
tests/integration/test_v2r1_bridge_transport.py tests/test_weixin_v2r1_ingress_bridge.py \
|
||||
tests/fixtures/weixin_v2r1/text.json tests/fixtures/weixin_v2r1/quoted-text.json \
|
||||
tests/fixtures/weixin_v2r1/image-with-text.json tests/fixtures/weixin_v2r1/unresolved-reference.json \
|
||||
release/v2r1c0-rc1/weixin-bridge-evidence.json
|
||||
git commit -m "feat(v2r1): bridge authenticated Weixin authority"
|
||||
```
|
||||
|
||||
### Review B3
|
||||
|
||||
- [ ] Require exactly 15 named paths, `git diff --check`, focused/full tests, and a second patcher pass with empty diff.
|
||||
- [ ] Prove Node transports evidence only; Python owns projection/authority; RuntimeWiring re-resolves.
|
||||
- [ ] Prove fresh nonce on retry, terminal accepted, and legacy unreachable in `enforced`.
|
||||
- [ ] Require B3 parent equals B2. Stop without commit/ledger append when evidence is unresolved.
|
||||
- [ ] After all prior B3 review checks pass, append B3 and verify the recorded commit identity:
|
||||
|
||||
```bash
|
||||
ledger="$(git rev-parse --git-path v2r1-blocker-ledger.tsv)"
|
||||
printf 'B3\t%s\t%s\t%s\n' "$(git rev-parse HEAD)" "$(git rev-parse HEAD^)" "$(git rev-parse HEAD^{tree})" >>"$ledger"
|
||||
IFS=$'\t' read -r label sha parent tree < <(tail -n 1 "$ledger")
|
||||
test "$label" = B3
|
||||
test "$sha" = "$(git rev-parse HEAD)"
|
||||
test "$parent" = "$(git rev-parse HEAD^)"
|
||||
test "$tree" = "$(git rev-parse HEAD^{tree})"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Task B4: Connect the durable outbox to the verified Hermes HTTP router
|
||||
|
||||
**Evidence gate before code:** create `release/v2r1c0-rc1/hermes-http-contract-evidence.json` from live listener/unit/source/schema inspection and `release/v2r1c0-rc1/weixin-outbound-binding-evidence.json` from raw protocol evidence. Hermes evidence resolves schemas, `aios-hermes-router.service`, source digest, exact 140-second timeout, tenant/user ownership, and repeated-`route_id` behavior as idempotent/non-idempotent. Outbound evidence must prove exact provider echo `client_id -> message_id`. Current ACK `ret/errmsg` plus reference `ref_msg.message_item.msg_id/ref_msg.message_item.create_time_ms` is `EVIDENCE_REQUIRED` and hard-stops B4; timestamp cannot unlock it.
|
||||
|
||||
**Files only after both gates pass:**
|
||||
|
||||
- Create: `active-runtime/app/aios_v2r1/outbox.py`
|
||||
- Create: `active-runtime/app/aios_v2r1/hermes_http.py`
|
||||
- Create: `active-runtime/app/aios_v2r1/hermes_worker.py`
|
||||
- Create: `active-runtime/app/aios_v2r1/outbound_receipt.py`
|
||||
- Modify: `active-runtime/app/aios_v2r1/ingress_service.py`
|
||||
- Modify: `active-runtime/app/aios_v2r1/message_ledger.py`
|
||||
- Create: `tests/v2r1/test_outbox.py`
|
||||
- Create: `tests/v2r1/test_hermes_http.py`
|
||||
- Create: `tests/v2r1/test_outbound_receipt.py`
|
||||
- Create: `tests/integration/test_v2r1_delivery_flow.py`
|
||||
- Modify: `fixes/patch_openclaw_weixin_outbound_quotes.py`
|
||||
- Create: `fixes/patch_openclaw_weixin_outbound_receipts.py`
|
||||
- Create: `openclaw/plugins/aios-tenant-boundary/dist/receipt-client.js`
|
||||
- Create: `openclaw/plugins/aios-tenant-boundary/dist/outbound-receipt-journal.js`
|
||||
- Create: `openclaw/plugins/aios-tenant-boundary/test/receipt-client.test.js`
|
||||
- Modify: `tests/test_weixin_outbound_quote_timestamp.py`
|
||||
- Create: `tests/test_weixin_outbound_receipt_boundary.py`
|
||||
- Create: both evidence JSON files named above
|
||||
|
||||
**Exact contract:** readiness `GET http://127.0.0.1:18791/health/ready`; dispatch `POST http://127.0.0.1:18791/internal/hermes/route`; downstream 140 seconds; worker deadline 150 seconds; 120-second direct timeout forbidden. States `pending|leased|delivered|delivery_unknown|dead`. No exactly-once. Unknown idempotency stops; known false prevents ambiguous retry; known true retries same `route_id`/digest. After B4 evidence, the actual Node Weixin sender receives a separate `outbound-receipt-write` `LoadCredential=` and uses the same one POST signing contract for `/v1/outbound-receipts`: exact five-field `unsigned_body`, exact `{method,path,body}` signing object, canonical JSON, and outer lowercase 64-hex HMAC-SHA256 signature.
|
||||
|
||||
Node alone owns its callback journal at `$STATE_DIRECTORY/outbound-receipts`. The gateway unit supplies a gateway-specific `StateDirectory=` with `StateDirectoryMode=0700`; the directory and its mode-`0600` files are owned and readable only by that gateway's service user. The send-boundary patch persists one sanitized per-client-ID JSON entry using a safe fixed-width digest filename: same-directory temporary file, file `fsync`, atomic rename to `.pending`, then directory `fsync`. Records contain only bounded IDs, send-success, attempt count, and next-attempt metadata—no bodies, quotes, attachments, signatures, credentials, key material, or provider payloads. Startup recovery and a background worker perform bounded authenticated callback retries without invoking Weixin send again. A pending record is deleted and the directory `fsync`ed only after an authenticated application ACK. Python owns receipt/outbox/worker storage and has no second send journal. Missing exact binding records `EVIDENCE_REQUIRED`, null provider ID, hard stop; `Date.now()` and local `_ms` fields remain telemetry only.
|
||||
|
||||
- [ ] Rehydrate the stable ledger and require latest label `B3` before evidence collection.
|
||||
- [ ] Execute evidence collectors first. Current expected result is `EVIDENCE_REQUIRED`; stop with no runtime edit, B4 commit, or ledger append.
|
||||
- [ ] After future exact binding acceptance, add RED tests for replay/collision/lease/unknown/dead, HTTP schema, 140/150 budgets, idempotency branches, the exact receipt signing role, exact provider mapping, ledger quote, `$STATE_DIRECTORY/outbound-receipts` resolution, directory/file ownership and `0700`/`0600` modes, file/directory `fsync`, atomic `.pending` rename, startup/background bounded retry, no-body/no-secret persistence, no content resend, and authenticated-ACK-only delete plus directory `fsync`.
|
||||
- [ ] Run initial RED:
|
||||
|
||||
```bash
|
||||
PYTHONDONTWRITEBYTECODE=1 PYTEST_ADDOPTS='-p no:cacheprovider' PYTHONPATH='active-runtime:active-runtime/app' \
|
||||
python3 -m pytest tests/v2r1/test_outbox.py tests/v2r1/test_hermes_http.py \
|
||||
tests/v2r1/test_outbound_receipt.py tests/integration/test_v2r1_delivery_flow.py \
|
||||
tests/test_weixin_outbound_quote_timestamp.py tests/test_weixin_outbound_receipt_boundary.py -q
|
||||
node --test openclaw/plugins/aios-tenant-boundary/test/receipt-client.test.js
|
||||
```
|
||||
|
||||
Expected RED after evidence acceptance: modules absent.
|
||||
|
||||
- [ ] Implement outbox, bounded HTTP adapter/worker, authenticated callback client, Node-owned durable callback journal, actual Weixin send-boundary patch, role-authenticated receipt route, exact Python receipt store, and outbound ledger append only after exact binding. Run Python, Node, both patchers twice for byte-idempotence, actual send-boundary, full, and loader tests; expected GREEN, with callback failure journaled without resend, timeout ambiguity `delivery_unknown`, and no exactly-once assertion.
|
||||
- [ ] Commit exactly 19 paths:
|
||||
|
||||
```bash
|
||||
git add active-runtime/app/aios_v2r1/outbox.py active-runtime/app/aios_v2r1/hermes_http.py \
|
||||
active-runtime/app/aios_v2r1/hermes_worker.py active-runtime/app/aios_v2r1/outbound_receipt.py \
|
||||
active-runtime/app/aios_v2r1/ingress_service.py active-runtime/app/aios_v2r1/message_ledger.py \
|
||||
tests/v2r1/test_outbox.py tests/v2r1/test_hermes_http.py tests/v2r1/test_outbound_receipt.py \
|
||||
tests/integration/test_v2r1_delivery_flow.py fixes/patch_openclaw_weixin_outbound_quotes.py \
|
||||
fixes/patch_openclaw_weixin_outbound_receipts.py openclaw/plugins/aios-tenant-boundary/dist/receipt-client.js \
|
||||
openclaw/plugins/aios-tenant-boundary/dist/outbound-receipt-journal.js \
|
||||
openclaw/plugins/aios-tenant-boundary/test/receipt-client.test.js tests/test_weixin_outbound_quote_timestamp.py \
|
||||
tests/test_weixin_outbound_receipt_boundary.py release/v2r1c0-rc1/hermes-http-contract-evidence.json \
|
||||
release/v2r1c0-rc1/weixin-outbound-binding-evidence.json
|
||||
git commit -m "feat(v2r1): dispatch through evidenced Hermes outbox"
|
||||
```
|
||||
|
||||
### Review B4
|
||||
|
||||
- [ ] Require exactly 19 paths, accepted evidence digests, `git diff --check`, Python/Node/patcher/send-boundary/full/loader tests.
|
||||
- [ ] Prove 150 exceeds exact 140 and no 120-second production deadline remains.
|
||||
- [ ] Search changed files for exactly-once claims and timestamp/approximate binding; require none.
|
||||
- [ ] Require B4 parent equals B3. If either evidence remains unresolved, correct result is STOP with no commit.
|
||||
- [ ] After all prior B4 review checks pass, append B4 and verify the recorded commit identity:
|
||||
|
||||
```bash
|
||||
ledger="$(git rev-parse --git-path v2r1-blocker-ledger.tsv)"
|
||||
printf 'B4\t%s\t%s\t%s\n' "$(git rev-parse HEAD)" "$(git rev-parse HEAD^)" "$(git rev-parse HEAD^{tree})" >>"$ledger"
|
||||
IFS=$'\t' read -r label sha parent tree < <(tail -n 1 "$ledger")
|
||||
test "$label" = B4
|
||||
test "$sha" = "$(git rev-parse HEAD)"
|
||||
test "$parent" = "$(git rev-parse HEAD^)"
|
||||
test "$tree" = "$(git rev-parse HEAD^{tree})"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Task B5: Build digest-bound isolated candidate staging and rollback
|
||||
|
||||
**Evidence gate before code:** accepted B3/B4 ledger entries. `capture_live_preflight.py` creates one evidence file containing a reconciled Gitea branch-consistency sentinel (`status=healthy`, `drift_count=0`, refs matching candidate) and the V1R4C6 live snapshot (host identity, capture time, Git SHA, units, commands, listeners, OpenClaw version, config/plugin digests, credential metadata, state/database paths, mounts, active artifact, rollback target). `release_ctl.py --preflight-file` validates the schema, exact current host, sentinel, all required fields, and freshness no older than 300 seconds. Stop if either record is missing, stale, host-mismatched, malformed, or inconsistent before staging or promotion.
|
||||
|
||||
**Files:**
|
||||
|
||||
- Create: `deploy/v2r1/release_ctl.py`
|
||||
- Create: `deploy/v2r1/capture_live_preflight.py`
|
||||
- Modify: `deploy/v2r1/install.sh`, `deploy/v2r1/validate.sh`, `deploy/v2r1/healthcheck.sh`
|
||||
- Create: `deploy/v2r1/rollback.sh`
|
||||
- Create: `deploy/v2r1/aios-v2r1-candidate-gateway.service`
|
||||
- Create: `deploy/v2r1/aios-v2r1-production-gateway.service`
|
||||
- Create: `deploy/v2r1/aios-v2r1-ingress.service`
|
||||
- Create: `deploy/v2r1/aios-v2r1-hermes-worker.service`
|
||||
- Create: `deploy/v2r1/openclaw-candidate.json5`
|
||||
- Create: `release/v2r1c0-rc1/FLEET_UNSUPPORTED`
|
||||
- Create: `tests/deploy/test_v2r1_release_contract.py`
|
||||
- Modify: `release/v2r1c0-rc1/RELEASE.md`
|
||||
|
||||
**Exact contract:** `python3 deploy/v2r1/release_ctl.py` exposes only `build`, `stage`, `verify-stage`, `promote`, `status`, and `rollback`. Forward states are exactly `BUILT -> STAGED -> STAGE_VERIFIED -> PRODUCTION`; rollback states are `ROLLBACK_STARTED -> ROLLED_BACK|ROLLBACK_FAILED`. Forward commands accept `--preflight-file`; callers supply no artifact, reconciled-sentinel, or runtime-snapshot digest strings. The controller validates the evidence and computes/persists all three digests internally. `verify-stage` and `promote` each recapture live evidence with the collector, revalidate it, recompute the triplet, and reject any drift from the recorded candidate state. Deterministic same bytes stage/prod; isolated users/state/config/ports/credentials; `LoadCredential=` least-role delivery; linked candidate plugin with runtime inspect, `allowConversationAccess=true`, config validate, doctor, inspect; `NOOP_DIGEST_MATCH` zero mutation/controller calls. Candidate and production gateway units use distinct dedicated users and distinct `StateDirectory=` values (`aios-v2r1-candidate-gateway` versus `aios-v2r1-production-gateway`), both set `StateDirectoryMode=0700`, and resolve journals only below their own `$STATE_DIRECTORY/outbound-receipts`; sharing, symlinking, or bind-mounting journal state is forbidden. The current root-run production gateway remains root-owned only until its audited migration; candidate staging never reads it, and migrated mode-`0600` records become readable only by the production gateway user. STOP blocks forward actions but permits only `rollback --rollback-only --to-previous-recorded --reason-file "$reason_file"`; exact prior digest/snapshot, no forward migration, cannot remove STOP, audited.
|
||||
|
||||
- [ ] Rehydrate the stable ledger and require latest label `B4` before live evidence capture.
|
||||
- [ ] Add RED release tests for deterministic builds, dirty/secret rejection, rejection of caller digest arguments, preflight schema/required fields/exact-host/sentinel/freshness-at-300-seconds, tamper and recapture drift, isolated config, loader sequence, unit credentials, candidate/production service-user ownership, exact distinct `StateDirectory=` names and paths, `StateDirectoryMode=0700`, journal file mode `0600`, no shared/symlink/bind-mounted journal state, root-production transition only during audited migration, no-op, STOP forward block, constrained rollback, readiness timeout, and prior integrity.
|
||||
- [ ] Run initial RED:
|
||||
|
||||
```bash
|
||||
PYTHONDONTWRITEBYTECODE=1 PYTEST_ADDOPTS='-p no:cacheprovider' python3 -m pytest tests/deploy/test_v2r1_release_contract.py -q
|
||||
```
|
||||
|
||||
Expected RED: driver, collector, units/config, rollback wrapper, lifecycle absent.
|
||||
|
||||
- [ ] Implement deterministic artifact and the executable state machine; wrappers never switch branches/create tags/edit baseline/version/suppress errors. Exercise exact commands:
|
||||
|
||||
```bash
|
||||
preflight_file="$(mktemp)"
|
||||
python3 deploy/v2r1/capture_live_preflight.py --output "$preflight_file"
|
||||
python3 deploy/v2r1/release_ctl.py build --source "$source_sha" --output "$build_dir" --preflight-file "$preflight_file"
|
||||
python3 deploy/v2r1/release_ctl.py stage --artifact "$artifact" --preflight-file "$preflight_file" --root "$release_root"
|
||||
python3 deploy/v2r1/release_ctl.py verify-stage --preflight-file "$preflight_file" --root "$release_root"
|
||||
python3 deploy/v2r1/release_ctl.py promote --preflight-file "$preflight_file" --root "$release_root"
|
||||
python3 deploy/v2r1/release_ctl.py status --root "$release_root"
|
||||
python3 deploy/v2r1/release_ctl.py rollback --root "$release_root" --rollback-only --to-previous-recorded --reason-file "$reason_file"
|
||||
```
|
||||
|
||||
Expected GREEN: the collector creates the evidence file; the controller accepts no caller digest strings, validates it, and computes the artifact/sentinel/runtime triplet internally. State records advance only through `BUILT,STAGED,STAGE_VERIFIED,PRODUCTION`; `verify-stage` and `promote` recapture current live state and require the same triplet; rollback records `ROLLBACK_STARTED` then `ROLLED_BACK` or `ROLLBACK_FAILED`.
|
||||
- [ ] Execute candidate loader in isolated environment:
|
||||
|
||||
```bash
|
||||
tmp="$(mktemp -d)"
|
||||
candidate_release="$tmp/release/current"
|
||||
export OPENCLAW_STATE_DIR="$tmp/openclaw-state"
|
||||
export OPENCLAW_CONFIG_PATH="$tmp/openclaw-state/openclaw.json"
|
||||
mkdir -p "$OPENCLAW_STATE_DIR"
|
||||
openclaw plugins install --link "$candidate_release/openclaw/plugins/aios-tenant-boundary"
|
||||
openclaw plugins inspect aios-tenant-boundary --runtime --json >"$tmp/plugin-before.json"
|
||||
openclaw config set plugins.entries.aios-tenant-boundary.hooks.allowConversationAccess true --strict-json
|
||||
openclaw config validate
|
||||
set +e
|
||||
openclaw doctor --lint --json >"$tmp/doctor-lint.json"
|
||||
doctor_rc=$?
|
||||
set -e
|
||||
test "$doctor_rc" = 0 || test "$doctor_rc" = 1
|
||||
python3 - "$tmp/doctor-lint.json" <<'PY'
|
||||
import json, sys
|
||||
data = json.load(open(sys.argv[1]))
|
||||
def walk(value):
|
||||
if isinstance(value, dict):
|
||||
yield value
|
||||
for child in value.values(): yield from walk(child)
|
||||
elif isinstance(value, list):
|
||||
for child in value: yield from walk(child)
|
||||
bad = [item for item in walk(data) if str(item.get("severity", "")).lower() in {"error", "fatal"} and "plugin" in json.dumps(item).lower()]
|
||||
assert not bad, bad
|
||||
PY
|
||||
openclaw doctor --post-upgrade --json >"$tmp/doctor-plugin.json"
|
||||
openclaw plugins inspect aios-tenant-boundary --runtime --json >"$tmp/plugin-after.json"
|
||||
```
|
||||
|
||||
Expected GREEN: plugin path inside candidate; config validation and post-upgrade doctor exit 0; lint doctor exits 0 or 1, warnings are allowed, and parsed JSON has zero error/fatal plugin findings; final inspect proves three hooks/permission; active V1R4C6 paths are absent.
|
||||
|
||||
- [ ] Run release/full Python/Node/loader tests, two byte-identical builds, and refreshed sentinel/snapshot comparisons. Expected GREEN: all pass.
|
||||
- [ ] Commit exactly 14 paths and append ledger:
|
||||
|
||||
```bash
|
||||
git add deploy/v2r1/release_ctl.py deploy/v2r1/capture_live_preflight.py deploy/v2r1/install.sh \
|
||||
deploy/v2r1/validate.sh deploy/v2r1/healthcheck.sh deploy/v2r1/rollback.sh \
|
||||
deploy/v2r1/aios-v2r1-candidate-gateway.service deploy/v2r1/aios-v2r1-production-gateway.service \
|
||||
deploy/v2r1/aios-v2r1-ingress.service \
|
||||
deploy/v2r1/aios-v2r1-hermes-worker.service deploy/v2r1/openclaw-candidate.json5 \
|
||||
release/v2r1c0-rc1/FLEET_UNSUPPORTED tests/deploy/test_v2r1_release_contract.py release/v2r1c0-rc1/RELEASE.md
|
||||
git commit -m "deploy(v2r1): bind candidate release to live evidence"
|
||||
```
|
||||
|
||||
### Review B5
|
||||
|
||||
- [ ] Require exactly 14 paths, no live secret/snapshot payload in Git, `git diff --check`, complete tests, two identical builds.
|
||||
- [ ] Inspect both gateway units and acceptance-test distinct service users, distinct `StateDirectory=` names/absolute paths, `StateDirectoryMode=0700`, mode-`0600` journal files, and no shared, symlinked, or bind-mounted receipt journal.
|
||||
- [ ] Prove candidate paths never resolve active V1R4C6; STOP blocks forward while rollback selects only recorded previous state and cannot remove STOP.
|
||||
- [ ] Prove staging validates the collector-created file and `verify-stage`/`promote` each recapture current live sentinel/runtime state, compute digests internally, and compare the same triplet; prove no caller-supplied digest option exists.
|
||||
- [ ] Require B5 parent equals B4.
|
||||
- [ ] After all prior B5 review checks pass, append B5 and verify the recorded commit identity:
|
||||
|
||||
```bash
|
||||
ledger="$(git rev-parse --git-path v2r1-blocker-ledger.tsv)"
|
||||
printf 'B5\t%s\t%s\t%s\n' "$(git rev-parse HEAD)" "$(git rev-parse HEAD^)" "$(git rev-parse HEAD^{tree})" >>"$ledger"
|
||||
IFS=$'\t' read -r label sha parent tree < <(tail -n 1 "$ledger")
|
||||
test "$label" = B5
|
||||
test "$sha" = "$(git rev-parse HEAD)"
|
||||
test "$parent" = "$(git rev-parse HEAD^)"
|
||||
test "$tree" = "$(git rev-parse HEAD^{tree})"
|
||||
```
|
||||
|
||||
## Final five-commit verification
|
||||
|
||||
Run only after all evidence/task reviews pass:
|
||||
|
||||
```bash
|
||||
ledger="$(git rev-parse --git-path v2r1-blocker-ledger.tsv)"
|
||||
python3 - "$ledger" <<'PY'
|
||||
from pathlib import Path
|
||||
import subprocess, sys
|
||||
rows = [line.split("\t") for line in Path(sys.argv[1]).read_text().splitlines()]
|
||||
assert [row[0] for row in rows] == ["START", "B1", "B2", "B3", "B4", "B5"]
|
||||
for i in range(1, len(rows)):
|
||||
label, sha, recorded_parent, recorded_tree = rows[i]
|
||||
parent = subprocess.check_output(["git", "rev-parse", sha + "^"], text=True).strip()
|
||||
tree = subprocess.check_output(["git", "rev-parse", sha + "^{tree}"], text=True).strip()
|
||||
assert parent == rows[i - 1][1]
|
||||
assert parent == recorded_parent and tree == recorded_tree, label
|
||||
start, head = rows[0][1], rows[-1][1]
|
||||
assert subprocess.check_output(["git", "rev-parse", "HEAD"], text=True).strip() == head
|
||||
assert subprocess.check_output(["git", "rev-list", "--count", f"{start}..{head}"], text=True).strip() == "5"
|
||||
assert not subprocess.check_output(["git", "rev-list", "--merges", f"{start}..{head}"], text=True).strip()
|
||||
PY
|
||||
test -z "$(git status --porcelain)"
|
||||
PYTHONDONTWRITEBYTECODE=1 PYTEST_ADDOPTS='-p no:cacheprovider' PYTHONPATH='active-runtime:active-runtime/app' python3 -m pytest --collect-only -q
|
||||
PYTHONDONTWRITEBYTECODE=1 PYTEST_ADDOPTS='-p no:cacheprovider' PYTHONPATH='active-runtime:active-runtime/app' python3 -m pytest -q
|
||||
(cd openclaw/plugins/aios-tenant-boundary && npm test)
|
||||
```
|
||||
|
||||
Expected: labels exactly `START,B1,B2,B3,B4,B5`; current HEAD/parent/tree match recorded values; `START..HEAD` has exactly five commits and no merge; clean tree; full collect/full Python/Node/loader/release tests pass.
|
||||
|
||||
Review authority roles, status spelling, timeout units, routes, response bounds, terminal semantics, evidence states, types, and sentinel behavior. Scan unresolved markers with split literals:
|
||||
|
||||
```bash
|
||||
marker_pattern="$(printf '%s' 'TO''DO|T''BD|FIX''ME|CHANGE''_ME|INSERT''_')"
|
||||
git grep -nE "$marker_pattern" -- active-runtime deploy/v2r1 openclaw/plugins/aios-tenant-boundary release/v2r1c0-rc1 tests
|
||||
```
|
||||
|
||||
Expected: no matches. Any contradiction, type mismatch, unresolved evidence, extra blocker commit, or missing review stops release preparation.
|
||||
|
||||
## Appendix A: Exact legacy `active_runtime.app` import files
|
||||
|
||||
`APPENDIX_A_BEGIN`
|
||||
- tests/test_agent_event_bus.py
|
||||
- tests/test_agent_observability_loop.py
|
||||
- tests/test_architect_governance.py
|
||||
- tests/test_architect_research_timeline.py
|
||||
- tests/test_architecture_change_classifier.py
|
||||
- tests/test_architecture_owner_gate.py
|
||||
- tests/test_architect_weekly_research.py
|
||||
- tests/test_change_governance.py
|
||||
- tests/test_governance_event_bridge.py
|
||||
- tests/test_governance_timeline.py
|
||||
- tests/test_search_agent_adapter.py
|
||||
- tests/test_search_architect_integration.py
|
||||
- tests/test_search_gateway_dashboard.py
|
||||
- tests/test_search_gateway_general_capability.py
|
||||
- tests/test_search_gateway_orchestrator.py
|
||||
- tests/test_search_gateway.py
|
||||
- tests/test_search_provider_registry.py
|
||||
- tests/test_task_center.py
|
||||
- tests/test_task_dashboard_view.py
|
||||
- tests/test_task_event_and_statistics.py
|
||||
- tests/test_task_lifecycle.py
|
||||
- tests/test_task_orchestrator.py
|
||||
- tests/test_v1r4c1_risk_fixes.py
|
||||
`APPENDIX_A_END`
|
||||
@@ -0,0 +1,287 @@
|
||||
# V2R1 Authenticated Runtime Bridge Design
|
||||
|
||||
**Date:** 2026-07-14
|
||||
**Status:** Preflight design — B3/B4/B5 evidence-gated
|
||||
**Release target:** V2R1C0 RC1
|
||||
**Scope:** Executable OpenClaw policy compatibility, canonical Python packaging, authenticated Weixin loopback ingress, exact message authority, real Hermes HTTP dispatch, and digest-bound release operations.
|
||||
|
||||
## Decision and execution gates
|
||||
|
||||
Three alternatives were evaluated:
|
||||
|
||||
- **Alternative A — preserve the verified replay and stop at documentation.** Lowest immediate risk, but every runtime release blocker remains open.
|
||||
- **Alternative B — patch only the Weixin path.** Demonstrates a message path but cannot prove plugin loading, transport authority, durable dispatch, artifact identity, or rollback.
|
||||
- **Alternative C — close five independently reviewed blockers.** Prove the plugin, package one Python namespace, build the authenticated bridge, connect a durable outbox to the real Hermes HTTP router, then rehearse a digest-bound release.
|
||||
|
||||
Alternative C remains the selected architecture because active full-execution authorization covers implementation preparation. That authorization does not waive the following gates:
|
||||
|
||||
- B1 and B2 may start only after this corrected design and plan are reviewed.
|
||||
- B3 stops unless the installed Weixin payload shape, patch target hashes, authority-map ownership, and transport signing boundary are evidenced.
|
||||
- B4 stops unless Hermes request/response schema, router ownership, downstream timeout, idempotency behavior, and exact outbound message binding are evidenced.
|
||||
- B5 stops unless B3 and B4 are accepted and the reconciled sentinel plus the V1R4C6 live-runtime snapshot are current for the candidate digest.
|
||||
|
||||
The present outbound evidence is insufficient, so B4 and B5 are currently stopped. This document defines the fail-closed path; it does not claim the missing evidence exists.
|
||||
|
||||
## Verified preflight observations
|
||||
|
||||
Read-only inspection on 2026-07-14 established these facts:
|
||||
|
||||
- OpenClaw is `2026.6.11` and exposes `plugins install --link`, `plugins inspect --runtime --json`, `config set`, `config validate`, and `doctor`.
|
||||
- The OpenClaw schema requires a non-bundled plugin to opt into conversation-bearing hooks with `plugins.entries.aios-tenant-boundary.hooks.allowConversationAccess=true`.
|
||||
- Without that opt-in, the tenant-boundary plugin's currently usable policy hook is `before_tool_call`; `before_agent_run` and `agent_end` cannot be treated as delivered authority.
|
||||
- `aios-hermes-router.service` owns `/opt/aios-v23/shared/hermes_route_memory/hermes_router_service.py` and listens on `127.0.0.1:18791`.
|
||||
- `GET http://127.0.0.1:18791/health/ready` returns router readiness and identifies the executor health URL.
|
||||
- `POST http://127.0.0.1:18791/internal/hermes/route` is the router submission endpoint.
|
||||
- The router forwards to the executor with an exact 140-second timeout. The existing direct Weixin helper uses 120 seconds, so it is incompatible and cannot be reused as the worker deadline.
|
||||
- Router ownership and schema are inspectable, but replay/idempotency behavior for repeated `route_id` is not proved.
|
||||
- A Weixin reference event exposes `ref_msg.message_item.msg_id` and `ref_msg.message_item.create_time_ms`, but not the original outbound `client_id`. The send acknowledgement exposes only `ret` and `errmsg`. No exact `client_id -> message_id` binding currently exists.
|
||||
|
||||
## Execution modes and terminal semantics
|
||||
|
||||
The gateway has exactly two modes:
|
||||
|
||||
- `disabled`: the V2R1 bridge performs no submission and the legacy message path may run.
|
||||
- `enforced`: every eligible Weixin event is handled by the V2R1 bridge. The legacy path is prohibited.
|
||||
|
||||
There is no shadow, dual-send, or fall-through mode. In `enforced` mode:
|
||||
|
||||
- `ACCEPTED` is terminal. The Node caller must not invoke the legacy handler, Hermes directly, or a second transport path.
|
||||
- A duplicate with the same canonical event and payload returns the same accepted receipt and is also terminal.
|
||||
- `AUTH_FAILED`, `VALIDATION_FAILED`, `CONFLICT`, and `INTERNAL_ERROR` are terminal runtime results for that attempt. They never authorize legacy fallback. `REPLAY_REJECTED` belongs only to the authenticated HTTP transport/service boundary and is never a `RuntimeIngressResponse.status`.
|
||||
- A transport timeout requires a receipt-status query. A retry is allowed only when the status is absent and must use a fresh nonce while retaining the same exact event identity.
|
||||
|
||||
Legacy handling is therefore reachable only when configuration explicitly says `disabled`, never as error recovery.
|
||||
|
||||
## Architecture and data flow
|
||||
|
||||
```text
|
||||
Authenticated Weixin event in isolated OpenClaw candidate gateway
|
||||
-> Node bridge client reads bridge credential from CREDENTIALS_DIRECTORY
|
||||
-> Node signs the exact method/path/unsigned_body object and POSTs the outer wrapper to 127.0.0.1
|
||||
-> Python ingress service authenticates freshness, nonce, key role, and replay
|
||||
-> server-side WeixinProjection parses exact protocol evidence
|
||||
-> server-side root-owned authority map supplies tenant/cell/principal/session
|
||||
-> Python signs an internal RuntimeWiring request with a separate key role
|
||||
-> RuntimeWiring.ingest -> TenantRouter -> MessageLedger -> SessionPool
|
||||
-> ingress receipt reaches terminal ACCEPTED
|
||||
-> HermesOutbox -> dedicated Hermes worker
|
||||
-> HermesHttpAdapter -> 127.0.0.1:18791/internal/hermes/route
|
||||
-> Weixin send boundary -> outbound receipt evidence
|
||||
```
|
||||
|
||||
Node never constructs `CanonicalMessage`, never opens the authority map, and never supplies tenant or cell authority. Python never trusts route claims from the raw Weixin object. The root-owned authority map is keyed by authenticated account, sender, and conversation evidence; its result is still re-resolved through `TenantRouter` before mutation.
|
||||
|
||||
## One POST signing contract
|
||||
|
||||
Every authenticated POST route uses exactly one wire shape; there is no `auth`, authorization header, nested signature, or route-specific signing variant:
|
||||
|
||||
```json
|
||||
{"unsigned_body":{"schema_version":"aios.signed-request.v1","key_id":"bridge-current","issued_at_ms":1784000000000,"nonce":"base64url-16-byte-value","route_payload":{}},"signature":"lowercase-64-hex"}
|
||||
```
|
||||
|
||||
`unsigned_body` contains exactly `schema_version`, `key_id`, `issued_at_ms`, `nonce`, and `route_payload`. `route_payload` is the route-specific content: ingress account/sender/conversation/raw event, receipt-status account plus one identifier, or outbound receipt. The signer constructs exactly:
|
||||
|
||||
```json
|
||||
{"method":"POST","path":"<exact route>","body":{"schema_version":"aios.signed-request.v1","key_id":"bridge-current","issued_at_ms":1784000000000,"nonce":"base64url-16-byte-value","route_payload":{}}}
|
||||
```
|
||||
|
||||
The signing input is canonical JSON encoded as UTF-8, with object keys recursively sorted by Unicode code point, `,` and `:` separators, no insignificant whitespace, no ASCII escaping of Unicode, no floats, and protocol IDs represented as strings. `signature` is lowercase 64-hex HMAC-SHA256 of those bytes. It is outside `unsigned_body` and outside the signing input. Verification reconstructs the same object using literal method `POST` and the exact request path; no normalized, decoded, prefix-matched, or caller-declared path is accepted.
|
||||
|
||||
Transport authentication is fail-closed:
|
||||
|
||||
- accepted clock skew is at most 30 seconds in either direction;
|
||||
- `(key_id, nonce)` is retained in a durable replay cache for five minutes;
|
||||
- a nonce decoding to any length other than 16 bytes is rejected;
|
||||
- a repeated nonce is `REPLAY_REJECTED`, even when payload and signature are identical;
|
||||
- every retry creates a cryptographically fresh nonce and `issued_at_ms` while preserving the exact event/message identity used for idempotency;
|
||||
- the keyring contains one active key and at most one previous key; `key_id` selects the key and unknown IDs fail;
|
||||
- rotation first installs the new verifier key, then switches the Node signer, then removes the old key only after the five-minute replay window and maximum request lifetime have elapsed.
|
||||
|
||||
The Node candidate gateway receives the bridge-ingress and receipt-read keyrings through separate systemd `LoadCredential=` entries below `$CREDENTIALS_DIRECTORY`. It never receives the Python internal signing key or authority map. Only after B4 evidence is accepted, the Node Weixin sender receives a third, separate `outbound-receipt-write` credential for authenticated callbacks.
|
||||
|
||||
## Service routes and bounded responses
|
||||
|
||||
The Python service binds loopback only and exposes exactly:
|
||||
|
||||
- `GET /health/live`
|
||||
- `GET /health/ready`
|
||||
- `POST /v1/ingress`
|
||||
- `POST /v1/receipts/status`
|
||||
- `POST /v1/outbound-receipts`
|
||||
|
||||
`POST /v1/ingress` requires the `bridge-ingress` HMAC role. `POST /v1/receipts/status` requires `receipt-read`; its `route_payload` contains `account_id` plus exactly one of `event_id` or `receipt_id`. Both or neither is `VALIDATION_FAILED`. Resolution is restricted to the same account and event scope, and unknown/cross-account identifiers return the same bounded result. `POST /v1/outbound-receipts` requires `outbound-receipt-write`; no receipt role can submit ingress. Every route uses the one POST signing contract above and the same nonce, skew, replay, rotation, and fresh-retry rules.
|
||||
|
||||
Request bodies are at most 1 MiB. Any JSON response is at most 4096 bytes and contains only stable codes and bounded identifiers. The ingress response fields are `status`, `event_id`, `message_id`, and `receipt_id`. The receipt-status response fields are `status`, `receipt_id`, `event_id`, `updated_at`, `outbox_status`, `outbound_status`, and `evidence_state`. No response contains message bodies, quote text, attachments, route objects, paths, signatures, keys, provider payloads, or exception text.
|
||||
|
||||
Runtime-to-HTTP status mapping is exact:
|
||||
|
||||
| Stable status | HTTP | Retry rule |
|
||||
|---|---:|---|
|
||||
| `ACCEPTED` | 202 | Terminal; query receipt after transport uncertainty |
|
||||
| `AUTH_FAILED` | 401 | No retry until credential or authority changes |
|
||||
| `REPLAY_REJECTED` | 409 | Transport/service only; retry same event with a fresh nonce |
|
||||
| `VALIDATION_FAILED` | 400 | No retry |
|
||||
| `CONFLICT` | 409 | Operator review |
|
||||
| `INTERNAL_ERROR` | 503 | Query receipt first; identical event may retry with fresh nonce |
|
||||
|
||||
## Canonical Python package
|
||||
|
||||
The release package has one V2R1 import identity: `aios_v2r1`. There is no `active_runtime` compatibility shim, alias package, `sys.modules` alias, or copied source tree.
|
||||
|
||||
`active-runtime/pyproject.toml` packages `aios_v2r1` from `active-runtime/app`. Repository tests use `PYTHONPATH='active-runtime:active-runtime/app'`: legacy modules import as `app.*`, while V2R1 imports as `aios_v2r1.*`. The implementation plan enumerates all 23 known `active_runtime.app` test imports and replaces them explicitly. Full collection, full pytest, and wheel inspection must prove the wheel contains one V2R1 namespace and that source and installed imports resolve to `aios_v2r1` only.
|
||||
|
||||
## Exact projection, quote, and attachment authority
|
||||
|
||||
`WeixinProjection` runs in Python after transport authentication. It preserves numeric Weixin IDs from the JSON token as decimal strings and rejects a value that has already passed through unsafe JavaScript-number conversion.
|
||||
|
||||
- `event_id` is deterministic from authenticated account, sender, conversation, direction, and exact protocol event ID.
|
||||
- `message_id` is an exact provider/server message ID when supplied.
|
||||
- `reply_to_message_id` comes only from an explicit reference ID.
|
||||
- `quoted_body` comes only from explicit referenced text or from `MessageLedger.resolve_quote()` using the fully scoped exact message ID.
|
||||
- Timestamp, nearest-message order, recent-message cache, numeric approximation, prefix, similarity, and local client ID are never quote authority.
|
||||
|
||||
`CanonicalAttachment` contains `attachment_id`, `kind`, `media_type`, `sha256`, and `size_bytes`. Attachment bytes are accepted only when exact protocol identity and digest/size verification both pass. A reference without exact media evidence cannot fall back to the latest image.
|
||||
|
||||
`Date.now()` is local send telemetry only. It may populate a local observation timestamp but cannot populate a provider timestamp, resolve a quote, correlate a client ID, or select a message.
|
||||
|
||||
## Outbound evidence and hard stop
|
||||
|
||||
The current Weixin protocol evidence cannot bind an outbound client ID to a later reference:
|
||||
|
||||
- send acknowledgement: `ret` and `errmsg` only;
|
||||
- later reference: `ref_msg.message_item.msg_id` and `ref_msg.message_item.create_time_ms`;
|
||||
- absent evidence: the original outbound `client_id` echoed beside the provider `message_id`.
|
||||
|
||||
Therefore outbound quote authority is unavailable. A successful send may be recorded as transport success, but `OutboundReceipt.evidence_state` must be `EVIDENCE_REQUIRED`, and the release gate must hard STOP. `sent` does not mean `confirmed`, and neither timestamp equality nor proximity may upgrade it.
|
||||
|
||||
The only acceptable future unlock is verified provider/reference evidence that echoes or otherwise exactly binds `client_id -> message_id`. That evidence must include the raw protocol fields, parser test, collision test, and a durable mapping scoped by tenant, cell, account, peer, direction, and exact IDs. Until then no outbound record becomes quote authority.
|
||||
|
||||
`OutboundReceipt` has stable fields:
|
||||
|
||||
```text
|
||||
receipt_id, outbox_id, tenant_id, cell_id, channel, channel_account_id,
|
||||
peer_id, client_message_id, provider_message_id, payload_sha256,
|
||||
status = sent | confirmed | failed,
|
||||
evidence_state = EXACT | EVIDENCE_REQUIRED
|
||||
```
|
||||
|
||||
`provider_message_id` is null while evidence is unavailable. `POST /v1/outbound-receipts` rejects any attempt to synthesize it from `Date.now()`, `ref_msg.message_item.create_time_ms`, message order, or approximate matching. Every local timestamp field is explicitly suffixed `_ms` and remains telemetry.
|
||||
|
||||
After B4 evidence is accepted, the actual Node Weixin sender owns its outbound callback retry journal at `$STATE_DIRECTORY/outbound-receipts`. Its systemd unit declares a gateway-specific `StateDirectory=` and `StateDirectoryMode=0700`; systemd owns that directory to the unit's `User=`/`Group=`, and no other gateway service user may read it. The sender receives its separate `outbound-receipt-write` `LoadCredential=` entry only at that gate. Each journal entry is one sanitized JSON record per client ID, named by a safe fixed-width digest of that ID. It contains only bounded identifiers, send-success state, callback-attempt count, and next-attempt metadata—never message bodies, quote text, attachments, signatures, key material, credentials, or provider payloads.
|
||||
|
||||
Persistence is exact: create a same-directory temporary file with mode `0600`, owned and readable only by that gateway's service user, write the sanitized record, `fsync` the file, atomically rename it to its final `.pending` name, then `fsync` the directory. Startup recovery and a background worker retry authenticated callbacks with bounded attempts and backoff; they never call the Weixin send operation again. A pending record is deleted, followed by directory `fsync`, only after the Python callback returns an authenticated application ACK. Transport uncertainty, non-ACK responses, and callback authentication failures retain the record for bounded retry.
|
||||
|
||||
Ownership is deliberately split. Node owns this send-success/callback-retry journal. Python owns the authenticated receipt endpoint, receipt store, outbox, and Hermes worker state. Python does not create or own a second send journal, so there is only one durable resend boundary.
|
||||
|
||||
## Real Hermes HTTP adapter and outbox semantics
|
||||
|
||||
The runtime does not claim that the local `HermesFabric` SQLite primitive is the production Hermes transport. Production dispatch uses:
|
||||
|
||||
- readiness: `GET http://127.0.0.1:18791/health/ready`;
|
||||
- submission: `POST http://127.0.0.1:18791/internal/hermes/route`;
|
||||
- owner: `aios-hermes-router.service`;
|
||||
- downstream executor budget: exactly 140 seconds;
|
||||
- worker HTTP deadline: 150 seconds, so the known 120-second direct-bridge mismatch is removed.
|
||||
|
||||
`HermesHttpAdapter` validates bounded request and response schemas before accepting a result. `HermesOutbox` provides durable intent and leases, but the system makes no exactly-once claim. Exact local states are `pending`, `leased`, `delivered`, `delivery_unknown`, and `dead`.
|
||||
|
||||
Repeated delivery behavior depends on evidence:
|
||||
|
||||
- if the verified router contract proves the same `route_id` and payload digest are idempotent, an expired/failed attempt may retry with that exact pair;
|
||||
- if idempotency is false, the worker never automatically retries an ambiguous submission;
|
||||
- if idempotency is unresolved, B4 stops before implementation and commit;
|
||||
- a client timeout or connection loss after send becomes `delivery_unknown`, never a fabricated failure or success.
|
||||
|
||||
B4 evidence must record the live listener, owning unit, executable/source digest, readiness response schema, route request fields, route response fields, exact 140-second downstream timeout, router tenant/user ownership rules, and repeated-`route_id` behavior. The dedicated `aios-v2r1-hermes-worker.service` is installed only in B5 after this evidence is accepted.
|
||||
|
||||
## OpenClaw plugin compatibility and permissions
|
||||
|
||||
The plugin configuration contract is exact:
|
||||
|
||||
- `blockUnknownAgentRuns`: boolean, default `false`;
|
||||
- `approvalTimeoutMs`: integer, minimum `1000`, maximum `300000`, default `60000`;
|
||||
- package and manifest versions are identical;
|
||||
- every property read by runtime code appears in `configSchema`.
|
||||
|
||||
Unit tests with a fake API remain useful, but they are insufficient. B1 must run the real OpenClaw loader in an isolated state/config directory. It must prove two permission states:
|
||||
|
||||
1. Default hook permissions: runtime inspection shows only `before_tool_call` is usable for this plugin; no test treats `before_agent_run` provenance as present.
|
||||
2. Explicit conversation access: set `plugins.entries.aios-tenant-boundary.hooks.allowConversationAccess=true`, validate config, reload/inspect runtime, and prove `before_agent_run`, `before_tool_call`, and `agent_end` are installed.
|
||||
|
||||
The default remains fail-closed for side effects because absent run provenance cannot authorize them. Candidate production never relies on the default-only state; the isolated staging config explicitly opts in and is validated.
|
||||
|
||||
## Isolated candidate staging and plugin loader sequence
|
||||
|
||||
B5 defines separate staging and production gateway units plus the isolated ingress and worker units. Staging starts the candidate trio; production gateway activation occurs only through the evidence-gated promotion/migration:
|
||||
|
||||
- `aios-v2r1-candidate-gateway.service`
|
||||
- `aios-v2r1-production-gateway.service`
|
||||
- `aios-v2r1-ingress.service`
|
||||
- `aios-v2r1-hermes-worker.service`
|
||||
|
||||
The candidate gateway uses its dedicated service user with `StateDirectory=aios-v2r1-candidate-gateway`; the migrated production gateway uses a different dedicated service user with `StateDirectory=aios-v2r1-production-gateway`. Both units set `StateDirectoryMode=0700`, and both resolve their journal only as `$STATE_DIRECTORY/outbound-receipts`. The names, absolute paths, owners, and journal contents are distinct; staging and production never share, bind-mount, or symlink journal state. The current root-run production gateway retains its own root-owned state only until an explicit audited migration. Candidate staging never reads that state. Migration verifies pending records contain no bodies or secrets, installs them only into the production-specific directory with its service user ownership and mode `0600`, and leaves no root-owned production journal in active use.
|
||||
|
||||
The candidate gateway has its own OpenClaw state directory, config file, port, credentials, and plugin link. It does not edit or restart the active V1R4C6 gateway. The loader sequence against the candidate state is fixed:
|
||||
|
||||
```bash
|
||||
openclaw plugins install --link "$candidate_release/openclaw/plugins/aios-tenant-boundary"
|
||||
openclaw plugins inspect aios-tenant-boundary --runtime --json
|
||||
openclaw config set plugins.entries.aios-tenant-boundary.hooks.allowConversationAccess true --strict-json
|
||||
openclaw config validate
|
||||
openclaw doctor --lint --json
|
||||
openclaw doctor --post-upgrade --json
|
||||
openclaw plugins inspect aios-tenant-boundary --runtime --json
|
||||
```
|
||||
|
||||
The environment supplies the isolated config/state paths. Any command that resolves to the active V1R4C6 config is a hard stop. Inspection output must prove the linked candidate path, version, hooks, and permission state.
|
||||
|
||||
## Artifact, preflight evidence, promotion, and rollback
|
||||
|
||||
One deterministic archive and manifest are built from a clean reviewed commit. Staging and production consume byte-identical artifact digests. `NOOP_DIGEST_MATCH` returns exit 0 and performs no extraction, migration, symlink change, restart, or deployment audit increment.
|
||||
|
||||
The executable controller is `python3 deploy/v2r1/release_ctl.py` with commands `build`, `stage`, `verify-stage`, `promote`, `status`, and `rollback`. Forward state transitions are exactly `BUILT -> STAGED -> STAGE_VERIFIED -> PRODUCTION`; skipping or reversing a forward edge is rejected. `capture_live_preflight.py` creates the evidence file and every mutating controller command accepts it as `--preflight-file`; callers never supply digest strings. The controller validates the evidence schema, exact host identity, reconciled sentinel health and candidate refs, required runtime fields, and capture freshness of at most 300 seconds. It then computes the artifact, reconciled-sentinel, and runtime-snapshot SHA-256 digests internally and persists that triplet in the state record.
|
||||
|
||||
`verify-stage` and `promote` each invoke the live collector again, validate the fresh result by the same rules, recompute the triplet internally, and compare the recaptured live state with the recorded candidate state. Any host, sentinel, candidate-ref, runtime-field, artifact, or digest drift rejects the transition. `status` is read-only. Rollback transitions are `PRODUCTION -> ROLLBACK_STARTED -> ROLLED_BACK`; a failed recovery records `ROLLBACK_FAILED` without claiming the prior state is active. `NOOP_DIGEST_MATCH` leaves the current state and all three digests unchanged.
|
||||
|
||||
Before staging and again before promotion, both pieces of live evidence are mandatory:
|
||||
|
||||
- reconciled Gitea branch-consistency sentinel: `status=healthy`, `drift_count=0`, and recorded refs matching the candidate manifest;
|
||||
- V1R4C6 live-runtime snapshot: active Git SHA, service units, process commands, listener ports, OpenClaw version, config/plugin digests, credential metadata without secrets, state/database paths, mounts, current artifact identity, and rollback target.
|
||||
|
||||
The snapshot is immutable, SHA-256-addressed, and timestamped. Promotion rejects a snapshot older than 300 seconds or any live drift from it. `capture_live_preflight.py` creates these evidence inputs from live inspection; `release_ctl.py` may validate and recapture them but may not invent missing fields or accept caller-asserted digests.
|
||||
|
||||
The host sentinel `/var/lib/aios-v2r1/STOP` blocks forward mutation: install, migration, staging activation, promotion, candidate/production restart, and new artifact selection. It does not block one constrained recovery command:
|
||||
|
||||
```text
|
||||
rollback --rollback-only --to-previous-recorded --reason-file "$reason_file"
|
||||
```
|
||||
|
||||
That escape may only select the exact previous digest and its recorded compatible database snapshot; it cannot install new bytes, run forward migrations, choose an arbitrary digest, remove the sentinel, or start a new candidate. It writes an audit record before and after the attempt. If previous-state evidence is missing or fails digest/integrity checks, rollback also stops.
|
||||
|
||||
The tracked `release/v2r1c0-rc1/FLEET_UNSUPPORTED` capability sentinel remains authoritative. `OpenClawFleet` and `openclaw fleet` are outside this release.
|
||||
|
||||
## Stop conditions
|
||||
|
||||
Preparation or release stops when any of these is true:
|
||||
|
||||
- corrected design/plan review is not accepted;
|
||||
- a B3/B4/B5 evidence gate remains unresolved;
|
||||
- authoritative Git refs differ from reviewed values or the worktree is dirty;
|
||||
- the real plugin loader does not prove the required hook permissions;
|
||||
- transport key role, `key_id`, timestamp, exact nonce length, skew, replay cache, rotation, or fresh-retry behavior fails;
|
||||
- Node attempts projection/authority resolution or Python trusts route claims from the raw event;
|
||||
- `ACCEPTED` can fall through to legacy processing, or legacy runs while bridge mode is `enforced`;
|
||||
- quote or attachment resolution uses timestamp, approximation, recent order, or a local client ID;
|
||||
- outbound evidence remains `EVIDENCE_REQUIRED`;
|
||||
- Hermes schema, ownership, 140-second downstream budget, router identity rules, or repeated-route behavior is unresolved;
|
||||
- any code or document claims exactly-once Hermes delivery;
|
||||
- the candidate gateway is not isolated from V1R4C6;
|
||||
- reconciled sentinel or V1R4C6 live-runtime snapshot is absent, stale, inconsistent, or digest-invalid;
|
||||
- artifact, migration, staging, or production digest differs;
|
||||
- the STOP sentinel blocks a forward action;
|
||||
- constrained rollback cannot prove the exact previous artifact and compatible snapshot;
|
||||
- any main, tag, `VERSION`, baseline, live service, or deployment mutation occurs without the separate release authorization.
|
||||
|
||||
## Acceptance
|
||||
|
||||
The design is review-complete when the plan contains exactly five blocker commits, dynamically anchors their parent chain at B1 start, enumerates all legacy import edits, and has executable RED/GREEN/review gates. Runtime release acceptance additionally requires all B3/B4/B5 evidence gates, the full Python collection and suite, the real Node/OpenClaw loader harness, exact receipt semantics, isolated candidate staging, deterministic artifacts, current live evidence, and rehearsed constrained rollback.
|
||||
+111
@@ -0,0 +1,111 @@
|
||||
import {
|
||||
classifyRun,
|
||||
decideToolCall,
|
||||
resolveSenderId,
|
||||
runKey,
|
||||
} from "./policy.js";
|
||||
|
||||
const MAX_RUN_AGE_MS = 60 * 60 * 1000;
|
||||
|
||||
function prune(activeRuns, now = Date.now()) {
|
||||
for (const [key, value] of activeRuns.entries()) {
|
||||
if (now - value.recordedAt > MAX_RUN_AGE_MS) activeRuns.delete(key);
|
||||
}
|
||||
}
|
||||
|
||||
function approvalTimeout(config) {
|
||||
const value = config.approvalTimeoutMs;
|
||||
return Number.isInteger(value) && value >= 1000 && value <= 300000
|
||||
? value
|
||||
: 60000;
|
||||
}
|
||||
|
||||
export default {
|
||||
id: "aios-tenant-boundary",
|
||||
name: "AIOS Tenant Boundary",
|
||||
description: "Fail-closed user-origin and side-effect policy for Tenant Cells.",
|
||||
|
||||
register(api) {
|
||||
const activeRuns = new Map();
|
||||
|
||||
api.on(
|
||||
"before_agent_run",
|
||||
async (event, ctx) => {
|
||||
prune(activeRuns);
|
||||
const config = event.context?.pluginConfig ?? api.pluginConfig ?? {};
|
||||
const trust = classifyRun(ctx, config);
|
||||
const key = runKey(event, ctx);
|
||||
const existing = key ? activeRuns.get(key) : undefined;
|
||||
if (existing && existing.senderId !== trust.senderId) {
|
||||
return {
|
||||
outcome: "block",
|
||||
reason: "run_scope_sender_conflict",
|
||||
message: "This run scope is already bound to a different authenticated sender.",
|
||||
};
|
||||
}
|
||||
if (key) {
|
||||
activeRuns.set(key, { ...trust, recordedAt: Date.now() });
|
||||
}
|
||||
|
||||
if (
|
||||
config.blockUnknownAgentRuns === true &&
|
||||
trust.trusted !== true &&
|
||||
trust.reason !== "job_id_present"
|
||||
) {
|
||||
return {
|
||||
outcome: "block",
|
||||
reason: trust.reason,
|
||||
message: "This message cannot be verified as coming from the active authenticated user.",
|
||||
};
|
||||
}
|
||||
return { outcome: "pass" };
|
||||
},
|
||||
{ priority: 100 },
|
||||
);
|
||||
|
||||
api.on(
|
||||
"before_tool_call",
|
||||
async (event, ctx) => {
|
||||
prune(activeRuns);
|
||||
const config = event.context?.pluginConfig ?? api.pluginConfig ?? {};
|
||||
const key = runKey(event, ctx);
|
||||
let trust = key ? activeRuns.get(key) : undefined;
|
||||
const senderId = resolveSenderId(ctx);
|
||||
if (trust && senderId && trust.senderId !== senderId) {
|
||||
trust = { trusted: false, reason: "run_scope_sender_conflict" };
|
||||
}
|
||||
const decision = decideToolCall(event.toolName, trust, config);
|
||||
|
||||
if (decision.action === "block") {
|
||||
return {
|
||||
block: true,
|
||||
blockReason: `AIOS V2R1 origin policy denied tool call: ${decision.code}`,
|
||||
};
|
||||
}
|
||||
if (decision.action === "approval") {
|
||||
return {
|
||||
requireApproval: {
|
||||
title: `Approve ${String(event.toolName)}`,
|
||||
description: "Authenticated user requested a side-effecting tool call in this Tenant Cell.",
|
||||
severity: "warning",
|
||||
timeoutMs: approvalTimeout(config),
|
||||
allowedDecisions: ["allow-once", "deny"],
|
||||
pluginId: "aios-tenant-boundary",
|
||||
},
|
||||
};
|
||||
}
|
||||
return undefined;
|
||||
},
|
||||
{ priority: 100 },
|
||||
);
|
||||
|
||||
api.on(
|
||||
"agent_end",
|
||||
async (event, ctx) => {
|
||||
const key = runKey(event, ctx);
|
||||
if (key) activeRuns.delete(key);
|
||||
},
|
||||
{ priority: 100 },
|
||||
);
|
||||
},
|
||||
};
|
||||
@@ -0,0 +1,89 @@
|
||||
const DEFAULT_READ_ONLY_TOOLS = Object.freeze([
|
||||
"read", "grep", "glob", "find", "ls", "web_search", "web_fetch",
|
||||
"memory_search", "sessions_list", "sessions_history", "session_status",
|
||||
]);
|
||||
|
||||
function strings(value) {
|
||||
return Array.isArray(value)
|
||||
? value.filter((item) => typeof item === "string" && item.trim())
|
||||
.map((item) => item.trim())
|
||||
: [];
|
||||
}
|
||||
|
||||
export function resolveSenderId(ctx = {}) {
|
||||
const direct = typeof ctx.senderId === "string" ? ctx.senderId.trim() : "";
|
||||
const nested = typeof ctx.channelContext?.sender?.id === "string"
|
||||
? ctx.channelContext.sender.id.trim()
|
||||
: "";
|
||||
return direct || nested || undefined;
|
||||
}
|
||||
|
||||
export function classifyRun(ctx = {}, config = {}) {
|
||||
const senderId = resolveSenderId(ctx);
|
||||
const trusted = new Set(strings(config.trustedSenderIds));
|
||||
const blocked = new Set(strings(config.blockedSenderIds));
|
||||
|
||||
if (typeof ctx.jobId === "string" && ctx.jobId) {
|
||||
return { trusted: false, origin: "automation", reason: "job_id_present" };
|
||||
}
|
||||
if (!senderId) {
|
||||
return { trusted: false, origin: "system_or_unknown", reason: "sender_id_missing" };
|
||||
}
|
||||
if (blocked.has(senderId)) {
|
||||
return { trusted: false, origin: "blocked_sender", reason: "sender_blocked", senderId };
|
||||
}
|
||||
if (config.requireExplicitTrustedSenders !== false && !trusted.has(senderId)) {
|
||||
return { trusted: false, origin: "untrusted_sender", reason: "sender_not_allowlisted", senderId };
|
||||
}
|
||||
return {
|
||||
trusted: true,
|
||||
origin: "authenticated_channel_user",
|
||||
reason: "sender_verified",
|
||||
senderId,
|
||||
};
|
||||
}
|
||||
|
||||
export function decideToolCall(toolName, runTrust, config = {}) {
|
||||
const name = typeof toolName === "string" ? toolName.trim().toLowerCase() : "";
|
||||
const configured = strings(config.readOnlyTools).map((item) => item.toLowerCase());
|
||||
const readOnly = new Set(configured.length ? configured : DEFAULT_READ_ONLY_TOOLS);
|
||||
if (!name) {
|
||||
return { action: "block", code: "tool_name_missing" };
|
||||
}
|
||||
if (readOnly.has(name)) {
|
||||
return { action: "allow", code: "read_only" };
|
||||
}
|
||||
if (!runTrust || runTrust.trusted !== true) {
|
||||
return {
|
||||
action: "block",
|
||||
code: runTrust?.reason || "run_provenance_missing",
|
||||
};
|
||||
}
|
||||
if (config.requireApprovalForHumanSideEffects === false) {
|
||||
return { action: "allow", code: "trusted_side_effect" };
|
||||
}
|
||||
return { action: "approval", code: "human_side_effect" };
|
||||
}
|
||||
|
||||
export function runKey(event = {}, ctx = {}) {
|
||||
const exact = (...values) => {
|
||||
const normalized = values
|
||||
.filter((value) => typeof value === "string")
|
||||
.map((value) => value.trim())
|
||||
.filter(Boolean);
|
||||
return normalized.length > 0 && new Set(normalized).size === 1
|
||||
? normalized[0]
|
||||
: undefined;
|
||||
};
|
||||
const runId = exact(event.runId, ctx.runId);
|
||||
const agentId = exact(event.agentId, ctx.agentId);
|
||||
const sessionId = exact(
|
||||
event.sessionId,
|
||||
event.sessionKey,
|
||||
ctx.sessionId,
|
||||
ctx.sessionKey,
|
||||
);
|
||||
return runId && agentId && sessionId
|
||||
? JSON.stringify([runId, agentId, sessionId])
|
||||
: undefined;
|
||||
}
|
||||
@@ -0,0 +1,25 @@
|
||||
{
|
||||
"id": "aios-tenant-boundary",
|
||||
"name": "AIOS Tenant Boundary",
|
||||
"description": "Enforces AIOS V2R1 tenant provenance and tool policy boundaries.",
|
||||
"version": "2.1.0-rc.1",
|
||||
"entry": "dist/index.js",
|
||||
"configSchema": {
|
||||
"type": "object",
|
||||
"additionalProperties": false,
|
||||
"properties": {
|
||||
"requireExplicitTrustedSenders": { "type": "boolean", "default": true },
|
||||
"trustedSenderIds": { "type": "array", "items": { "type": "string" }, "default": [] },
|
||||
"blockedSenderIds": { "type": "array", "items": { "type": "string" }, "default": [] },
|
||||
"readOnlyTools": { "type": "array", "items": { "type": "string" } },
|
||||
"requireApprovalForHumanSideEffects": { "type": "boolean", "default": true },
|
||||
"blockUnknownAgentRuns": { "type": "boolean", "default": false },
|
||||
"approvalTimeoutMs": {
|
||||
"type": "integer",
|
||||
"minimum": 1000,
|
||||
"maximum": 300000,
|
||||
"default": 60000
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,18 @@
|
||||
{
|
||||
"name": "@aios/openclaw-tenant-boundary",
|
||||
"version": "2.1.0-rc.1",
|
||||
"type": "module",
|
||||
"description": "AIOS V2R1 Tenant Cell provenance and side-effect policy boundary for OpenClaw.",
|
||||
"files": [
|
||||
"dist",
|
||||
"openclaw.plugin.json"
|
||||
],
|
||||
"scripts": {
|
||||
"test": "node --test test/*.test.js"
|
||||
},
|
||||
"openclaw": {
|
||||
"extensions": [
|
||||
"./dist/index.js"
|
||||
]
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,64 @@
|
||||
import assert from "node:assert/strict";
|
||||
import { readFile } from "node:fs/promises";
|
||||
import test from "node:test";
|
||||
|
||||
import plugin from "../dist/index.js";
|
||||
|
||||
const packageJson = JSON.parse(
|
||||
await readFile(new URL("../package.json", import.meta.url), "utf8"),
|
||||
);
|
||||
const manifest = JSON.parse(
|
||||
await readFile(new URL("../openclaw.plugin.json", import.meta.url), "utf8"),
|
||||
);
|
||||
|
||||
function registrations(config = {}) {
|
||||
const seen = [];
|
||||
plugin.register({
|
||||
pluginConfig: config,
|
||||
on(name, handler, options) {
|
||||
seen.push({ name, handler, options });
|
||||
},
|
||||
});
|
||||
return seen;
|
||||
}
|
||||
|
||||
test("package, manifest, and executable test command are release compatible", () => {
|
||||
assert.equal(packageJson.version, "2.1.0-rc.1");
|
||||
assert.equal(manifest.version, "2.1.0-rc.1");
|
||||
assert.equal(packageJson.scripts.test, "node --test test/*.test.js");
|
||||
});
|
||||
|
||||
test("schema declares every runtime-read property and exact B1 bounds", () => {
|
||||
const properties = manifest.configSchema.properties;
|
||||
const runtimeKeys = [
|
||||
"approvalTimeoutMs",
|
||||
"blockUnknownAgentRuns",
|
||||
"blockedSenderIds",
|
||||
"readOnlyTools",
|
||||
"requireApprovalForHumanSideEffects",
|
||||
"requireExplicitTrustedSenders",
|
||||
"trustedSenderIds",
|
||||
];
|
||||
assert.deepEqual(Object.keys(properties).sort(), runtimeKeys);
|
||||
assert.deepEqual(properties.blockUnknownAgentRuns, {
|
||||
type: "boolean",
|
||||
default: false,
|
||||
});
|
||||
assert.deepEqual(properties.approvalTimeoutMs, {
|
||||
type: "integer",
|
||||
minimum: 1000,
|
||||
maximum: 300000,
|
||||
default: 60000,
|
||||
});
|
||||
});
|
||||
|
||||
test("all three hooks register exactly once at priority 100", () => {
|
||||
const seen = registrations();
|
||||
assert.deepEqual(
|
||||
seen.map(({ name }) => name).sort(),
|
||||
["agent_end", "before_agent_run", "before_tool_call"],
|
||||
);
|
||||
for (const registration of seen) {
|
||||
assert.deepEqual(registration.options, { priority: 100 });
|
||||
}
|
||||
});
|
||||
@@ -0,0 +1,50 @@
|
||||
import assert from "node:assert/strict";
|
||||
import { readFile } from "node:fs/promises";
|
||||
import { realpath } from "node:fs/promises";
|
||||
|
||||
const [mode, inspectPath] = process.argv.slice(2);
|
||||
assert.ok(["default", "opt-in"].includes(mode), `unsupported mode: ${mode}`);
|
||||
assert.ok(inspectPath, "inspect JSON path is required");
|
||||
|
||||
const data = JSON.parse(await readFile(inspectPath, "utf8"));
|
||||
const plugin = data.plugin;
|
||||
assert.equal(plugin.id, "aios-tenant-boundary");
|
||||
assert.equal(plugin.version, "2.1.0-rc.1");
|
||||
assert.equal(plugin.status, "loaded");
|
||||
assert.equal(plugin.activated, true);
|
||||
assert.equal(await realpath(plugin.rootDir), await realpath(new URL("..", import.meta.url)));
|
||||
assert.equal(await realpath(plugin.source), await realpath(new URL("../dist/index.js", import.meta.url)));
|
||||
assert.equal(data.install.source, "path");
|
||||
assert.equal(await realpath(data.install.installPath), await realpath(plugin.rootDir));
|
||||
|
||||
const hooks = data.typedHooks
|
||||
.map(({ name, priority }) => ({ name, priority }))
|
||||
.sort((a, b) => a.name.localeCompare(b.name));
|
||||
const expectedNames = mode === "default"
|
||||
? ["before_tool_call"]
|
||||
: ["agent_end", "before_agent_run", "before_tool_call"];
|
||||
assert.deepEqual(hooks.map(({ name }) => name), expectedNames);
|
||||
assert.ok(hooks.every(({ priority }) => priority === 100));
|
||||
|
||||
const diagnostics = data.diagnostics ?? [];
|
||||
assert.equal(
|
||||
diagnostics.filter(({ level, severity }) =>
|
||||
["error", "fatal"].includes(String(level ?? severity).toLowerCase())).length,
|
||||
0,
|
||||
);
|
||||
if (mode === "default") {
|
||||
assert.deepEqual(
|
||||
diagnostics.map(({ level, message }) => ({ level, message })).sort((a, b) => a.message.localeCompare(b.message)),
|
||||
["agent_end", "before_agent_run"].map((hook) => ({
|
||||
level: "warn",
|
||||
message: `typed hook "${hook}" blocked because non-bundled plugins must set plugins.entries.aios-tenant-boundary.hooks.allowConversationAccess=true`,
|
||||
})).sort((a, b) => a.message.localeCompare(b.message)),
|
||||
);
|
||||
} else {
|
||||
assert.deepEqual(diagnostics, []);
|
||||
}
|
||||
|
||||
const properties = plugin.configJsonSchema?.properties ?? {};
|
||||
for (const key of ["approvalTimeoutMs", "blockUnknownAgentRuns"]) {
|
||||
assert.ok(Object.hasOwn(properties, key), `missing runtime schema property: ${key}`);
|
||||
}
|
||||
@@ -0,0 +1,261 @@
|
||||
import assert from "node:assert/strict";
|
||||
import test from "node:test";
|
||||
|
||||
import plugin from "../dist/index.js";
|
||||
import {
|
||||
classifyRun,
|
||||
decideToolCall,
|
||||
resolveSenderId,
|
||||
runKey,
|
||||
} from "../dist/policy.js";
|
||||
|
||||
function registration(config = {}) {
|
||||
const handlers = new Map();
|
||||
plugin.register({
|
||||
pluginConfig: config,
|
||||
on(name, handler) {
|
||||
handlers.set(name, handler);
|
||||
},
|
||||
});
|
||||
return {
|
||||
beforeAgentRun: handlers.get("before_agent_run"),
|
||||
beforeToolCall: handlers.get("before_tool_call"),
|
||||
agentEnd: handlers.get("agent_end"),
|
||||
};
|
||||
}
|
||||
|
||||
function agentContext(id, senderId) {
|
||||
return {
|
||||
runId: `run-${id}`,
|
||||
agentId: "agent-main",
|
||||
sessionKey: `session-${id}`,
|
||||
...(senderId ? { senderId } : {}),
|
||||
};
|
||||
}
|
||||
|
||||
function toolContext(id, extra = {}) {
|
||||
return {
|
||||
runId: `run-${id}`,
|
||||
agentId: "agent-main",
|
||||
sessionId: `session-${id}`,
|
||||
...extra,
|
||||
};
|
||||
}
|
||||
|
||||
test("sender classification covers missing, blocked, allowlisted, and automation", () => {
|
||||
assert.equal(resolveSenderId({ channelContext: { sender: { id: " nested " } } }), "nested");
|
||||
assert.deepEqual(classifyRun({}, {}), {
|
||||
trusted: false,
|
||||
origin: "system_or_unknown",
|
||||
reason: "sender_id_missing",
|
||||
});
|
||||
assert.equal(
|
||||
classifyRun({ senderId: "blocked" }, { blockedSenderIds: ["blocked"] }).reason,
|
||||
"sender_blocked",
|
||||
);
|
||||
assert.equal(
|
||||
classifyRun(
|
||||
{ senderId: "alice" },
|
||||
{ requireExplicitTrustedSenders: true, trustedSenderIds: ["alice"] },
|
||||
).trusted,
|
||||
true,
|
||||
);
|
||||
assert.deepEqual(classifyRun({ jobId: "job-1" }, {}), {
|
||||
trusted: false,
|
||||
origin: "automation",
|
||||
reason: "job_id_present",
|
||||
});
|
||||
});
|
||||
|
||||
test("unknown agent runs default to pass but fail closed when explicitly enabled", async () => {
|
||||
const defaultHandlers = registration();
|
||||
assert.deepEqual(
|
||||
await defaultHandlers.beforeAgentRun({}, agentContext("default")),
|
||||
{ outcome: "pass" },
|
||||
);
|
||||
|
||||
const enforced = registration({ blockUnknownAgentRuns: true });
|
||||
const denied = await enforced.beforeAgentRun({}, agentContext("denied"));
|
||||
assert.equal(denied.outcome, "block");
|
||||
assert.equal(denied.reason, "sender_id_missing");
|
||||
assert.doesNotMatch(denied.reason + denied.message, /undefined|\r|\n/);
|
||||
|
||||
assert.deepEqual(
|
||||
await enforced.beforeAgentRun({}, { ...agentContext("job"), jobId: "job-1" }),
|
||||
{ outcome: "pass" },
|
||||
);
|
||||
});
|
||||
|
||||
test("read-only tools pass without provenance and side effects fail with a stable reason", async () => {
|
||||
assert.deepEqual(decideToolCall("read", undefined, {}), {
|
||||
action: "allow",
|
||||
code: "read_only",
|
||||
});
|
||||
assert.deepEqual(decideToolCall("shell", undefined, {}), {
|
||||
action: "block",
|
||||
code: "run_provenance_missing",
|
||||
});
|
||||
|
||||
const handlers = registration();
|
||||
assert.equal(await handlers.beforeToolCall({ toolName: "read" }, {}), undefined);
|
||||
const blocked = await handlers.beforeToolCall({ toolName: "shell" }, {});
|
||||
assert.equal(blocked.block, true);
|
||||
assert.equal(
|
||||
blocked.blockReason,
|
||||
"AIOS V2R1 origin policy denied tool call: run_provenance_missing",
|
||||
);
|
||||
});
|
||||
|
||||
test("trusted human side effects request approval with exact timeout validation", async () => {
|
||||
for (const [configured, expected] of [
|
||||
[undefined, 60000],
|
||||
[1000, 1000],
|
||||
[300000, 300000],
|
||||
[999, 60000],
|
||||
[300001, 60000],
|
||||
[60000.5, 60000],
|
||||
["1000", 60000],
|
||||
[null, 60000],
|
||||
]) {
|
||||
const config = {
|
||||
requireExplicitTrustedSenders: true,
|
||||
trustedSenderIds: ["alice"],
|
||||
};
|
||||
if (configured !== undefined) config.approvalTimeoutMs = configured;
|
||||
const handlers = registration(config);
|
||||
const id = `approval-${String(configured)}`;
|
||||
await handlers.beforeAgentRun({}, agentContext(id, "alice"));
|
||||
const result = await handlers.beforeToolCall({ toolName: "shell" }, toolContext(id));
|
||||
assert.equal(result.requireApproval.timeoutMs, expected, String(configured));
|
||||
assert.deepEqual(result.requireApproval.allowedDecisions, ["allow-once", "deny"]);
|
||||
}
|
||||
});
|
||||
|
||||
test("active run provenance is isolated by registration, run, and sender", async () => {
|
||||
const config = {
|
||||
requireExplicitTrustedSenders: true,
|
||||
trustedSenderIds: ["alice", "bob"],
|
||||
};
|
||||
const first = registration(config);
|
||||
const second = registration(config);
|
||||
await first.beforeAgentRun({}, agentContext("shared", "alice"));
|
||||
|
||||
const otherSender = await first.beforeToolCall(
|
||||
{ toolName: "shell" },
|
||||
toolContext("shared", { senderId: "bob" }),
|
||||
);
|
||||
assert.equal(otherSender.block, true);
|
||||
assert.match(otherSender.blockReason, /run_scope_sender_conflict$/);
|
||||
|
||||
const otherRegistration = await second.beforeToolCall(
|
||||
{ toolName: "shell" },
|
||||
toolContext("shared"),
|
||||
);
|
||||
assert.equal(otherRegistration.block, true);
|
||||
assert.match(otherRegistration.blockReason, /run_provenance_missing$/);
|
||||
});
|
||||
|
||||
test("agent_end cleanup removes only the matching shared scope", async () => {
|
||||
const handlers = registration({
|
||||
requireExplicitTrustedSenders: true,
|
||||
trustedSenderIds: ["alice", "bob"],
|
||||
});
|
||||
await handlers.beforeAgentRun({}, agentContext("alice-scope", "alice"));
|
||||
await handlers.beforeAgentRun({}, agentContext("bob-scope", "bob"));
|
||||
await handlers.agentEnd({}, toolContext("alice-scope"));
|
||||
|
||||
const alice = await handlers.beforeToolCall(
|
||||
{ toolName: "shell" },
|
||||
toolContext("alice-scope"),
|
||||
);
|
||||
assert.equal(alice.block, true);
|
||||
|
||||
const bob = await handlers.beforeToolCall(
|
||||
{ toolName: "shell" },
|
||||
toolContext("bob-scope"),
|
||||
);
|
||||
assert.ok(bob.requireApproval);
|
||||
});
|
||||
|
||||
test("run provenance expires after the bounded age", async (t) => {
|
||||
const originalNow = Date.now;
|
||||
t.after(() => { Date.now = originalNow; });
|
||||
let now = 1_000_000;
|
||||
Date.now = () => now;
|
||||
const handlers = registration({
|
||||
requireExplicitTrustedSenders: true,
|
||||
trustedSenderIds: ["alice"],
|
||||
});
|
||||
await handlers.beforeAgentRun({}, agentContext("expiring", "alice"));
|
||||
now += 60 * 60 * 1000 + 1;
|
||||
const result = await handlers.beforeToolCall(
|
||||
{ toolName: "shell" },
|
||||
toolContext("expiring"),
|
||||
);
|
||||
assert.equal(result.block, true);
|
||||
assert.match(result.blockReason, /run_provenance_missing$/);
|
||||
});
|
||||
|
||||
test("host-shaped tool context without sender reuses trusted shared scope", async () => {
|
||||
const handlers = registration({
|
||||
requireExplicitTrustedSenders: true,
|
||||
trustedSenderIds: ["alice"],
|
||||
});
|
||||
await handlers.beforeAgentRun({}, agentContext("host-shape", "alice"));
|
||||
const result = await handlers.beforeToolCall(
|
||||
{ toolName: "shell" },
|
||||
toolContext("host-shape"),
|
||||
);
|
||||
assert.ok(result.requireApproval);
|
||||
assert.equal(result.block, undefined);
|
||||
});
|
||||
|
||||
test("shared scope collision fails closed without overwriting original sender", async () => {
|
||||
const handlers = registration({
|
||||
requireExplicitTrustedSenders: true,
|
||||
trustedSenderIds: ["alice", "bob"],
|
||||
});
|
||||
assert.deepEqual(
|
||||
await handlers.beforeAgentRun({}, agentContext("collision", "alice")),
|
||||
{ outcome: "pass" },
|
||||
);
|
||||
const collision = await handlers.beforeAgentRun(
|
||||
{},
|
||||
agentContext("collision", "bob"),
|
||||
);
|
||||
assert.equal(collision.outcome, "block");
|
||||
assert.equal(collision.reason, "run_scope_sender_conflict");
|
||||
assert.doesNotMatch(collision.message, /alice|bob/);
|
||||
|
||||
const original = await handlers.beforeToolCall(
|
||||
{ toolName: "shell" },
|
||||
toolContext("collision"),
|
||||
);
|
||||
assert.ok(original.requireApproval);
|
||||
});
|
||||
|
||||
test("shared scope normalization is exact and incomplete scope fails closed", async () => {
|
||||
const sessionId = runKey({}, {
|
||||
runId: " run-1 ", agentId: " agent-1 ", sessionId: " session-1 ",
|
||||
});
|
||||
const sessionKey = runKey({}, {
|
||||
runId: "run-1", agentId: "agent-1", sessionKey: "session-1",
|
||||
});
|
||||
assert.equal(sessionId, JSON.stringify(["run-1", "agent-1", "session-1"]));
|
||||
assert.equal(sessionKey, sessionId);
|
||||
assert.equal(runKey({}, {
|
||||
runId: "run-1",
|
||||
agentId: "agent-1",
|
||||
sessionId: "session-1",
|
||||
sessionKey: "different-session",
|
||||
}), undefined);
|
||||
assert.equal(runKey({}, { agentId: "agent-1", sessionId: "session-1" }), undefined);
|
||||
|
||||
const handlers = registration();
|
||||
const missing = await handlers.beforeToolCall(
|
||||
{ toolName: "shell" },
|
||||
{ agentId: "agent-1", sessionId: "session-1" },
|
||||
);
|
||||
assert.equal(missing.block, true);
|
||||
assert.match(missing.blockReason, /run_provenance_missing$/);
|
||||
});
|
||||
@@ -0,0 +1,36 @@
|
||||
# AIOS V2R1C0 RC1
|
||||
|
||||
## Architecture
|
||||
|
||||
OpenClaw Tenant Cell + Hermes Shared Agent Fabric.
|
||||
|
||||
## Included
|
||||
|
||||
- Signed Tenant Context
|
||||
- Canonical Message Envelope
|
||||
- Tenant Router
|
||||
- OpenClaw Cell lifecycle adapter
|
||||
- Exact Message Ledger
|
||||
- Hermes tenant partitioned scheduler
|
||||
- Memory Namespace policy
|
||||
- Secret Scope references
|
||||
- Append-only Audit Chain
|
||||
- Hermes Profile isolation
|
||||
- OpenClaw tenant boundary plugin
|
||||
|
||||
## Release Gates
|
||||
|
||||
Before production:
|
||||
|
||||
- automated isolation tests pass
|
||||
- OpenClaw plugin runtime inspect passes
|
||||
- Cell health probes pass
|
||||
- running commit matches release commit
|
||||
- rollback test passes
|
||||
|
||||
## Security Rules
|
||||
|
||||
Unknown provenance fails closed.
|
||||
Quoted text is data, not command input.
|
||||
Cross-tenant access is denied.
|
||||
Shared Fabric does not share tenant state.
|
||||
@@ -0,0 +1,143 @@
|
||||
"""End-to-end boundary tests for the V2R1 authenticated ingress runtime."""
|
||||
from __future__ import annotations
|
||||
|
||||
import hashlib
|
||||
import hmac
|
||||
import sys
|
||||
from datetime import datetime, timezone
|
||||
from tempfile import TemporaryDirectory
|
||||
|
||||
from aios_v2r1.runtime import RuntimeWiring
|
||||
from aios_v2r1.message_ledger import MessageLedger
|
||||
from aios_v2r1.tenant_context import canonical_json
|
||||
|
||||
|
||||
class FixedClock:
|
||||
def __init__(self) -> None:
|
||||
self.now = datetime(2026, 7, 13, tzinfo=timezone.utc)
|
||||
|
||||
def __call__(self) -> datetime:
|
||||
return self.now
|
||||
|
||||
|
||||
class TestRuntimeIngressFlow:
|
||||
"""Use the public ingress boundary; do not reach into router internals."""
|
||||
|
||||
internal_key = b"runtime-integration-internal-key-32bytes"
|
||||
ingress_key = b"runtime-integration-ingress-key-32bytes!"
|
||||
|
||||
def setup_method(self) -> None:
|
||||
self.directory = TemporaryDirectory()
|
||||
self.clock = FixedClock()
|
||||
self.runtime = RuntimeWiring.create(
|
||||
self.directory.name,
|
||||
signing_key=self.internal_key,
|
||||
ingress_hmac_key=self.ingress_key,
|
||||
clock=self.clock,
|
||||
)
|
||||
self.runtime.router.register_tenant("tenant-a", "cell-a")
|
||||
self.runtime.router.register_tenant("tenant-b", "cell-b")
|
||||
self.runtime.router.bind_channel(
|
||||
tenant_id="tenant-a", channel="weixin", channel_account_id="account-a"
|
||||
)
|
||||
self.runtime.router.bind_channel(
|
||||
tenant_id="tenant-b", channel="weixin", channel_account_id="account-b"
|
||||
)
|
||||
self.runtime.router.bind_principal(
|
||||
tenant_id="tenant-a",
|
||||
channel="weixin",
|
||||
channel_account_id="account-a",
|
||||
principal_id="user-a",
|
||||
)
|
||||
self.runtime.router.bind_session(
|
||||
tenant_id="tenant-a",
|
||||
session_id="session-a",
|
||||
cell_id="cell-a",
|
||||
principal_id="user-a",
|
||||
ttl_seconds=60,
|
||||
)
|
||||
|
||||
def teardown_method(self) -> None:
|
||||
self.directory.cleanup()
|
||||
|
||||
def _message(self, *, event_id: str = "event-a", message_id: str = "message-a",
|
||||
body: str = "hello", **changes: object) -> dict[str, object]:
|
||||
values: dict[str, object] = {
|
||||
"tenant_id": "tenant-a", "cell_id": "cell-a", "principal_id": "user-a",
|
||||
"principal_type": "authenticated_user", "origin_type": "channel_user",
|
||||
"channel": "weixin", "channel_account_id": "account-a", "peer_id": "peer-a",
|
||||
"conversation_id": "conversation-a", "session_id": "session-a", "task_id": None,
|
||||
"event_id": event_id, "message_id": message_id, "reply_to_message_id": None,
|
||||
"direction": "inbound", "command_capable": True,
|
||||
"occurred_at": "2026-07-13T00:00:00+00:00",
|
||||
"received_at": "2026-07-13T00:00:01+00:00",
|
||||
"content": {"body": body, "quoted_body": None},
|
||||
"adapter": {"name": "weixin", "version": "v2"},
|
||||
}
|
||||
values.update(changes)
|
||||
return values
|
||||
|
||||
def _request(self, **changes: object) -> dict[str, object]:
|
||||
values: dict[str, object] = {
|
||||
"principal_id": "user-a", "tenant_id": "tenant-a", "cell_id": "cell-a",
|
||||
"channel": "weixin", "channel_account_id": "account-a", "session_id": "session-a",
|
||||
"message": self._message(),
|
||||
}
|
||||
values.update(changes)
|
||||
values["signature"] = hmac.new(
|
||||
self.ingress_key, canonical_json(values), hashlib.sha256
|
||||
).hexdigest()
|
||||
return values
|
||||
|
||||
def test_authenticated_ingress_uses_direct_append_and_acquires_session(self) -> None:
|
||||
# Observe the real MessageLedger object while preserving every method
|
||||
# implementation. This proves the public ingress path never calls
|
||||
# the legacy compatibility entrypoint; it is not a mock or bypass.
|
||||
remember_code = MessageLedger.remember.__code__
|
||||
remember_calls = 0
|
||||
previous_profile = sys.getprofile()
|
||||
|
||||
def observe(frame: object, event: str, arg: object) -> None:
|
||||
nonlocal remember_calls
|
||||
if event == "call" and getattr(frame, "f_code", None) is remember_code:
|
||||
remember_calls += 1
|
||||
|
||||
sys.setprofile(observe)
|
||||
try:
|
||||
response = self.runtime.ingest(request=self._request())
|
||||
finally:
|
||||
sys.setprofile(previous_profile)
|
||||
|
||||
assert response.status == "ACCEPTED"
|
||||
assert response.result is not None
|
||||
assert response.result.record.message_id == "message-a"
|
||||
assert response.result.session.session_id == "session-a"
|
||||
assert self.runtime.ledger.count() == 1
|
||||
assert self.runtime.session_pool.active_count() == 1
|
||||
assert remember_calls == 0
|
||||
|
||||
def test_forged_tenant_claim_is_rejected_before_ledger_or_session_mutation(self) -> None:
|
||||
response = self.runtime.ingest(request=self._request(
|
||||
tenant_id="tenant-b",
|
||||
cell_id="cell-b",
|
||||
message=self._message(tenant_id="tenant-b", cell_id="cell-b"),
|
||||
))
|
||||
|
||||
assert response.status == "AUTH_FAILED"
|
||||
assert response.result is None
|
||||
assert self.runtime.ledger.count() == 0
|
||||
assert self.runtime.session_pool.active_count() == 0
|
||||
|
||||
def test_conflicting_duplicate_message_is_mapped_at_the_ingress_boundary(self) -> None:
|
||||
assert self.runtime.ingest(request=self._request(
|
||||
message=self._message(body="first")
|
||||
)).status == "ACCEPTED"
|
||||
|
||||
response = self.runtime.ingest(request=self._request(
|
||||
message=self._message(event_id="event-b", body="second")
|
||||
))
|
||||
|
||||
assert response.status == "CONFLICT"
|
||||
assert response.result is None
|
||||
assert self.runtime.ledger.count() == 1
|
||||
assert self.runtime.session_pool.active_count() == 1
|
||||
@@ -0,0 +1,33 @@
|
||||
# AIOS V2R1C0 RC1 Acceptance
|
||||
|
||||
## Tenant Isolation
|
||||
|
||||
- cross tenant memory access: DENY
|
||||
- cross cell context: DENY
|
||||
- cross tenant secret scope: DENY
|
||||
- cross tenant queue claim: DENY
|
||||
|
||||
## Message Safety
|
||||
|
||||
- unsafe numeric message id: DENY
|
||||
- exact reply resolution only: PASS
|
||||
- quote text separate from command body: PASS
|
||||
- heartbeat side effects: DENY
|
||||
- cron side effects: DENY
|
||||
- assistant output execution: DENY
|
||||
|
||||
## Hermes
|
||||
|
||||
- profile HOME isolation: PASS
|
||||
- workspace escape: DENY
|
||||
- tenant queue partition: PASS
|
||||
|
||||
## OpenClaw
|
||||
|
||||
- plugin manifest validation: PASS
|
||||
- runtime hook registration: REQUIRED
|
||||
- side effect approval: REQUIRED
|
||||
|
||||
## Release Gate
|
||||
|
||||
No production deployment until executable tests and runtime evidence pass.
|
||||
@@ -0,0 +1,16 @@
|
||||
# Hermes Fabric Contract Tests
|
||||
|
||||
Required executable assertions:
|
||||
|
||||
1. Duplicate event_id must raise ConflictError, never raw sqlite3.IntegrityError.
|
||||
2. Same tenant/cell/profile worker can claim its own queue.
|
||||
3. Cross tenant queue claim must return no task or be denied.
|
||||
4. Non-command messages cannot enqueue execution jobs.
|
||||
5. Unknown provenance cannot create execution jobs.
|
||||
|
||||
Evidence required:
|
||||
|
||||
- command
|
||||
- exit code
|
||||
- pass count
|
||||
- commit
|
||||
@@ -0,0 +1,88 @@
|
||||
"""Gate 1 contract tests for the Hermes shared agent fabric."""
|
||||
from __future__ import annotations
|
||||
|
||||
import sqlite3
|
||||
from tempfile import TemporaryDirectory
|
||||
import unittest
|
||||
|
||||
from aios_v2r1.hermes_fabric import HermesFabric
|
||||
from aios_v2r1.tenant_context import CanonicalMessage, ConflictError, ScopeError
|
||||
|
||||
|
||||
def authenticated_command(
|
||||
event_id: str,
|
||||
*,
|
||||
command_capable: bool = True,
|
||||
origin_type: str = "channel_user",
|
||||
) -> CanonicalMessage:
|
||||
return CanonicalMessage(
|
||||
tenant_id="tenant-a",
|
||||
cell_id="cell-a",
|
||||
principal_id="user-a",
|
||||
principal_type="authenticated_user",
|
||||
origin_type=origin_type,
|
||||
channel="weixin",
|
||||
channel_account_id="account-a",
|
||||
peer_id="peer-a",
|
||||
conversation_id="conversation-a",
|
||||
session_id="session-a",
|
||||
task_id=None,
|
||||
event_id=event_id,
|
||||
message_id="1234567890123456789",
|
||||
reply_to_message_id=None,
|
||||
direction="inbound",
|
||||
command_capable=command_capable,
|
||||
occurred_at="2026-07-13T00:00:00+00:00",
|
||||
received_at="2026-07-13T00:00:01+00:00",
|
||||
body="/run",
|
||||
quoted_body=None,
|
||||
adapter_name="weixin",
|
||||
adapter_version="v2",
|
||||
)
|
||||
|
||||
|
||||
class HermesFabricContractTests(unittest.TestCase):
|
||||
def test_duplicate_event_returns_sanitized_conflict(self) -> None:
|
||||
with TemporaryDirectory() as directory:
|
||||
fabric = HermesFabric(f"{directory}/fabric.sqlite3")
|
||||
message = authenticated_command("event-a")
|
||||
|
||||
first = fabric.enqueue(message=message, profile_id="profile-a")
|
||||
self.assertEqual(first.event_id, "event-a")
|
||||
|
||||
with self.assertRaises(ConflictError) as raised:
|
||||
fabric.enqueue(message=message, profile_id="profile-a")
|
||||
|
||||
error = raised.exception
|
||||
self.assertNotIsInstance(error, sqlite3.IntegrityError)
|
||||
self.assertNotIn("sqlite", str(error).lower())
|
||||
self.assertIsNone(error.__cause__)
|
||||
self.assertIsNone(error.__context__)
|
||||
|
||||
def test_non_command_event_cannot_enqueue(self) -> None:
|
||||
with TemporaryDirectory() as directory:
|
||||
fabric = HermesFabric(f"{directory}/fabric.sqlite3")
|
||||
|
||||
with self.assertRaises(ScopeError):
|
||||
fabric.enqueue(
|
||||
message=authenticated_command(
|
||||
"event-non-command", command_capable=False
|
||||
),
|
||||
profile_id="profile-a",
|
||||
)
|
||||
|
||||
def test_heartbeat_provenance_cannot_enqueue(self) -> None:
|
||||
with TemporaryDirectory() as directory:
|
||||
fabric = HermesFabric(f"{directory}/fabric.sqlite3")
|
||||
|
||||
with self.assertRaises(ScopeError):
|
||||
fabric.enqueue(
|
||||
message=authenticated_command(
|
||||
"event-heartbeat", origin_type="heartbeat"
|
||||
),
|
||||
profile_id="profile-a",
|
||||
)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,73 @@
|
||||
"""Contract tests for the runtime-facing direct MessageLedger append path."""
|
||||
from __future__ import annotations
|
||||
|
||||
from concurrent.futures import ThreadPoolExecutor
|
||||
from tempfile import TemporaryDirectory
|
||||
import unittest
|
||||
|
||||
from aios_v2r1.message_ledger import MessageLedger
|
||||
from aios_v2r1.tenant_context import CanonicalMessage, ConflictError
|
||||
|
||||
|
||||
def message(*, tenant_id: str = "tenant-a", cell_id: str = "cell-a",
|
||||
event_id: str = "event-a", message_id: str = "message-a",
|
||||
body: str = "hello", reply_to_message_id: str | None = None) -> CanonicalMessage:
|
||||
return CanonicalMessage(
|
||||
tenant_id=tenant_id, cell_id=cell_id, principal_id="user-a",
|
||||
principal_type="authenticated_user", origin_type="channel_user",
|
||||
channel="weixin", channel_account_id="account-a", peer_id="peer-a",
|
||||
conversation_id="conversation-a", session_id="session-a", task_id=None,
|
||||
event_id=event_id, message_id=message_id, reply_to_message_id=reply_to_message_id,
|
||||
direction="inbound", command_capable=True,
|
||||
occurred_at="2026-07-13T00:00:00+00:00",
|
||||
received_at="2026-07-13T00:00:01+00:00", body=body,
|
||||
quoted_body=None, adapter_name="weixin", adapter_version="v2",
|
||||
)
|
||||
|
||||
|
||||
class MessageLedgerAppendContractTests(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self.directory = TemporaryDirectory()
|
||||
self.addCleanup(self.directory.cleanup)
|
||||
self.ledger = MessageLedger(f"{self.directory.name}/ledger.sqlite3")
|
||||
|
||||
def test_append_writes_directly_without_using_remember(self) -> None:
|
||||
# A compatibility wrapper may remain, but the runtime append path may not
|
||||
# route through it: this catches append() -> remember() regressions.
|
||||
self.ledger.remember = lambda _: (_ for _ in ()).throw(AssertionError("remember called")) # type: ignore[method-assign]
|
||||
record = self.ledger.append(message())
|
||||
self.assertEqual("message-a", record.message_id)
|
||||
self.assertEqual(1, self.ledger.count())
|
||||
|
||||
def test_append_rejects_same_message_id_with_different_content(self) -> None:
|
||||
self.ledger.append(message(body="first"))
|
||||
with self.assertRaises(ConflictError):
|
||||
self.ledger.append(message(event_id="event-b", body="second"))
|
||||
self.assertEqual(1, self.ledger.count())
|
||||
|
||||
def test_append_is_idempotent_when_only_event_id_changes(self) -> None:
|
||||
stored = self.ledger.append(message(event_id="event-a", body="same body"))
|
||||
replay = self.ledger.append(message(event_id="event-b", body="same body"))
|
||||
|
||||
self.assertEqual(stored, replay)
|
||||
self.assertEqual("event-a", replay.event_id)
|
||||
self.assertEqual(1, self.ledger.count())
|
||||
|
||||
def test_append_keeps_tenants_isolated(self) -> None:
|
||||
self.ledger.append(message())
|
||||
self.ledger.append(message(tenant_id="tenant-b", cell_id="cell-b"))
|
||||
self.assertEqual(2, self.ledger.count())
|
||||
self.assertEqual("hello", self.ledger.resolve_quote(
|
||||
message(tenant_id="tenant-b", cell_id="cell-b", event_id="event-c",
|
||||
message_id="message-c", body="reply", reply_to_message_id="message-a")
|
||||
))
|
||||
|
||||
def test_concurrent_identical_append_is_one_record(self) -> None:
|
||||
with ThreadPoolExecutor(max_workers=16) as executor:
|
||||
records = list(executor.map(lambda _: self.ledger.append(message()), range(16)))
|
||||
self.assertEqual(1, self.ledger.count())
|
||||
self.assertEqual({"message-a"}, {record.message_id for record in records})
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,144 @@
|
||||
"""Gate 1 contract tests for authoritative TenantRouter isolation."""
|
||||
from __future__ import annotations
|
||||
|
||||
from datetime import datetime, timedelta, timezone
|
||||
from tempfile import TemporaryDirectory
|
||||
import unittest
|
||||
|
||||
from aios_v2r1.router import TenantRouter
|
||||
from aios_v2r1.tenant_context import CanonicalMessage, ConflictError, ScopeError
|
||||
|
||||
|
||||
class MutableClock:
|
||||
def __init__(self, now: datetime) -> None:
|
||||
self.now = now
|
||||
|
||||
def __call__(self) -> datetime:
|
||||
return self.now
|
||||
|
||||
|
||||
def canonical_message(*, tenant_id: str = "tenant-a", cell_id: str = "cell-a") -> CanonicalMessage:
|
||||
return CanonicalMessage(
|
||||
tenant_id=tenant_id,
|
||||
cell_id=cell_id,
|
||||
principal_id="user-a",
|
||||
principal_type="authenticated_user",
|
||||
origin_type="channel_user",
|
||||
channel="weixin",
|
||||
channel_account_id="account-a",
|
||||
peer_id="peer-a",
|
||||
conversation_id="conversation-a",
|
||||
session_id="session-a",
|
||||
task_id=None,
|
||||
event_id="event-a",
|
||||
message_id="message-a",
|
||||
reply_to_message_id=None,
|
||||
direction="inbound",
|
||||
command_capable=True,
|
||||
occurred_at="2026-07-13T00:00:00+00:00",
|
||||
received_at="2026-07-13T00:00:01+00:00",
|
||||
body="hello",
|
||||
quoted_body=None,
|
||||
adapter_name="weixin",
|
||||
adapter_version="v2",
|
||||
)
|
||||
|
||||
|
||||
class TenantRouterIsolationContractTests(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self.directory = TemporaryDirectory()
|
||||
self.addCleanup(self.directory.cleanup)
|
||||
self.database = f"{self.directory.name}/router.sqlite3"
|
||||
self.router = TenantRouter(self.database)
|
||||
self.router.register_tenant("tenant-a", "cell-a")
|
||||
self.router.register_tenant("tenant-b", "cell-b")
|
||||
self.router.bind_channel(
|
||||
tenant_id="tenant-a", channel="weixin", channel_account_id="account-a"
|
||||
)
|
||||
self.router.bind_channel(
|
||||
tenant_id="tenant-b", channel="weixin", channel_account_id="account-b"
|
||||
)
|
||||
|
||||
def test_channel_account_cannot_bind_two_tenants(self) -> None:
|
||||
with self.assertRaises(ConflictError):
|
||||
self.router.bind_channel(
|
||||
tenant_id="tenant-b", channel="weixin", channel_account_id="account-a"
|
||||
)
|
||||
|
||||
def test_cell_cannot_bind_two_tenants(self) -> None:
|
||||
with self.assertRaises(ConflictError):
|
||||
self.router.register_tenant("tenant-c", "cell-a")
|
||||
|
||||
def test_principal_cannot_bind_across_tenant_boundary(self) -> None:
|
||||
with self.assertRaises(ScopeError):
|
||||
self.router.bind_principal(
|
||||
tenant_id="tenant-b",
|
||||
channel="weixin",
|
||||
channel_account_id="account-a",
|
||||
principal_id="user-a",
|
||||
)
|
||||
|
||||
def test_session_cannot_cross_cell(self) -> None:
|
||||
with self.assertRaises(ScopeError):
|
||||
self.router.bind_session(
|
||||
tenant_id="tenant-a",
|
||||
session_id="session-a",
|
||||
cell_id="cell-b",
|
||||
principal_id="user-a",
|
||||
)
|
||||
|
||||
def test_session_cannot_cross_principal(self) -> None:
|
||||
self.router.bind_session(
|
||||
tenant_id="tenant-a",
|
||||
session_id="session-a",
|
||||
cell_id="cell-a",
|
||||
principal_id="user-a",
|
||||
)
|
||||
|
||||
with self.assertRaises(ConflictError):
|
||||
self.router.bind_session(
|
||||
tenant_id="tenant-a",
|
||||
session_id="session-a",
|
||||
cell_id="cell-a",
|
||||
principal_id="user-b",
|
||||
)
|
||||
|
||||
def test_expired_session_is_rejected_without_private_storage_access(self) -> None:
|
||||
clock = MutableClock(datetime(2026, 7, 13, tzinfo=timezone.utc))
|
||||
router = TenantRouter(f"{self.directory.name}/expiry.sqlite3", clock=clock)
|
||||
router.register_tenant("tenant-a", "cell-a")
|
||||
router.bind_channel(
|
||||
tenant_id="tenant-a", channel="weixin", channel_account_id="account-a"
|
||||
)
|
||||
router.bind_session(
|
||||
tenant_id="tenant-a",
|
||||
session_id="session-a",
|
||||
cell_id="cell-a",
|
||||
principal_id="user-a",
|
||||
)
|
||||
clock.now += timedelta(days=2)
|
||||
|
||||
with self.assertRaises(ScopeError):
|
||||
router.resolve(
|
||||
channel="weixin",
|
||||
channel_account_id="account-a",
|
||||
principal_id="user-a",
|
||||
session_id="session-a",
|
||||
)
|
||||
|
||||
def test_self_reported_tenant_or_cell_mismatch_fails_against_authority(self) -> None:
|
||||
self.router.bind_session(
|
||||
tenant_id="tenant-a",
|
||||
session_id="session-a",
|
||||
cell_id="cell-a",
|
||||
principal_id="user-a",
|
||||
)
|
||||
expected = "message claims do not match authoritative route"
|
||||
with self.assertRaisesRegex(ScopeError, expected):
|
||||
self.router.assert_message_route(canonical_message(tenant_id="tenant-b"))
|
||||
with self.assertRaisesRegex(ScopeError, expected):
|
||||
self.router.assert_message_route(canonical_message(cell_id="cell-b"))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,159 @@
|
||||
"""Security contracts for authenticated OpenClaw runtime identity binding."""
|
||||
from __future__ import annotations
|
||||
|
||||
import hashlib
|
||||
import hmac
|
||||
from datetime import datetime, timezone
|
||||
from tempfile import TemporaryDirectory
|
||||
import unittest
|
||||
|
||||
from aios_v2r1.runtime import RuntimeWiring
|
||||
from aios_v2r1.tenant_context import canonical_json
|
||||
|
||||
|
||||
class MutableClock:
|
||||
def __init__(self, now: datetime) -> None:
|
||||
self.now = now
|
||||
|
||||
def __call__(self) -> datetime:
|
||||
return self.now
|
||||
|
||||
|
||||
class RuntimeIdentityBindingTests(unittest.TestCase):
|
||||
internal_key = b"internal-context-signing-key-is-32-bytes"
|
||||
ingress_key = b"external-ingress-hmac-key-is-32-bytes"
|
||||
|
||||
def setUp(self) -> None:
|
||||
self.directory = TemporaryDirectory()
|
||||
self.addCleanup(self.directory.cleanup)
|
||||
self.clock = MutableClock(datetime(2026, 7, 13, tzinfo=timezone.utc))
|
||||
self.runtime = RuntimeWiring.create(
|
||||
self.directory.name,
|
||||
signing_key=self.internal_key,
|
||||
ingress_hmac_key=self.ingress_key,
|
||||
clock=self.clock,
|
||||
)
|
||||
self.runtime.router.register_tenant("tenant-a", "cell-a")
|
||||
self.runtime.router.register_tenant("tenant-b", "cell-b")
|
||||
self.runtime.router.bind_channel(
|
||||
tenant_id="tenant-a", channel="weixin", channel_account_id="account-a"
|
||||
)
|
||||
self.runtime.router.bind_channel(
|
||||
tenant_id="tenant-b", channel="weixin", channel_account_id="account-b"
|
||||
)
|
||||
self.runtime.router.bind_principal(
|
||||
tenant_id="tenant-a", channel="weixin", channel_account_id="account-a",
|
||||
principal_id="user-a",
|
||||
)
|
||||
self.runtime.router.bind_session(
|
||||
tenant_id="tenant-a", session_id="session-a", cell_id="cell-a",
|
||||
principal_id="user-a", ttl_seconds=60,
|
||||
)
|
||||
|
||||
def message(self, **changes: object) -> dict[str, object]:
|
||||
values: dict[str, object] = {
|
||||
"tenant_id": "tenant-a", "cell_id": "cell-a", "principal_id": "user-a",
|
||||
"principal_type": "authenticated_user", "origin_type": "channel_user",
|
||||
"channel": "weixin", "channel_account_id": "account-a", "peer_id": "peer-a",
|
||||
"conversation_id": "conversation-a", "session_id": "session-a", "task_id": None,
|
||||
"event_id": "event-a", "message_id": "message-a", "reply_to_message_id": None,
|
||||
"direction": "inbound", "command_capable": True,
|
||||
"occurred_at": "2026-07-13T00:00:00+00:00",
|
||||
"received_at": "2026-07-13T00:00:01+00:00",
|
||||
"content": {"body": "hello", "quoted_body": None},
|
||||
"adapter": {"name": "weixin", "version": "v2"},
|
||||
}
|
||||
values.update(changes)
|
||||
return values
|
||||
|
||||
def authenticated_principal_type(self):
|
||||
try:
|
||||
from aios_v2r1.identity import AuthenticatedPrincipal
|
||||
except ImportError as exc:
|
||||
self.fail(f"Identity resolver contract is missing: {exc}")
|
||||
return AuthenticatedPrincipal
|
||||
|
||||
def signed_request(self, **changes: object) -> dict[str, object]:
|
||||
values: dict[str, object] = {
|
||||
"principal_id": "user-a",
|
||||
"tenant_id": "tenant-a",
|
||||
"cell_id": "cell-a",
|
||||
"channel": "weixin",
|
||||
"channel_account_id": "account-a",
|
||||
"session_id": "session-a",
|
||||
"message": self.message(),
|
||||
}
|
||||
values.update(changes)
|
||||
signed = canonical_json(values)
|
||||
values["signature"] = hmac.new(
|
||||
self.ingress_key, signed, hashlib.sha256
|
||||
).hexdigest()
|
||||
return values
|
||||
|
||||
def test_raw_payload_cannot_construct_authenticated_principal(self) -> None:
|
||||
AuthenticatedPrincipal = self.authenticated_principal_type()
|
||||
with self.assertRaises(TypeError):
|
||||
AuthenticatedPrincipal("user-a") # type: ignore[call-arg]
|
||||
|
||||
def test_forged_tenant_claim_is_rejected_after_valid_hmac(self) -> None:
|
||||
request = self.signed_request(
|
||||
tenant_id="tenant-b", cell_id="cell-b",
|
||||
message=self.message(tenant_id="tenant-b", cell_id="cell-b"),
|
||||
)
|
||||
|
||||
result = self.runtime.ingest(request=request)
|
||||
|
||||
self.assertEqual("AUTH_FAILED", result.status)
|
||||
self.assertIsNone(result.result)
|
||||
self.assertEqual(0, self.runtime.ledger.count())
|
||||
|
||||
def test_invalid_principal_is_rejected_after_valid_hmac(self) -> None:
|
||||
request = self.signed_request(
|
||||
principal_id="unknown-user",
|
||||
message=self.message(principal_id="unknown-user"),
|
||||
)
|
||||
|
||||
result = self.runtime.ingest(request=request)
|
||||
|
||||
self.assertEqual("AUTH_FAILED", result.status)
|
||||
self.assertIsNone(result.result)
|
||||
self.assertEqual(0, self.runtime.ledger.count())
|
||||
|
||||
def test_registered_principal_is_resolved_before_internal_context_is_issued(self) -> None:
|
||||
request = self.signed_request()
|
||||
result = self.runtime.ingest(request=request)
|
||||
|
||||
self.assertEqual("ACCEPTED", result.status)
|
||||
self.assertIsNotNone(result.result)
|
||||
assert result.result is not None
|
||||
self.assertEqual("tenant-a", result.result.route.tenant_id)
|
||||
self.assertEqual("message-a", result.result.record.message_id)
|
||||
self.assertEqual(1, self.runtime.ledger.count())
|
||||
self.assertEqual(1, self.runtime.session_pool.active_count())
|
||||
|
||||
def test_cross_tenant_channel_claim_cannot_retarget_authenticated_principal(self) -> None:
|
||||
request = self.signed_request(
|
||||
tenant_id="tenant-b", cell_id="cell-b", channel_account_id="account-b",
|
||||
message=self.message(
|
||||
tenant_id="tenant-b", cell_id="cell-b", channel_account_id="account-b"
|
||||
),
|
||||
)
|
||||
|
||||
result = self.runtime.ingest(request=request)
|
||||
|
||||
self.assertEqual("AUTH_FAILED", result.status)
|
||||
self.assertEqual(0, self.runtime.ledger.count())
|
||||
self.assertEqual(0, self.runtime.session_pool.active_count())
|
||||
|
||||
def test_hmac_binds_all_scope_claims(self) -> None:
|
||||
request = self.signed_request()
|
||||
request["tenant_id"] = "tenant-b"
|
||||
|
||||
result = self.runtime.ingest(request=request)
|
||||
|
||||
self.assertEqual("AUTH_FAILED", result.status)
|
||||
self.assertEqual(0, self.runtime.ledger.count())
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,154 @@
|
||||
"""Integration contracts for the V2R1 authenticated runtime composition root."""
|
||||
from __future__ import annotations
|
||||
|
||||
from concurrent.futures import ThreadPoolExecutor
|
||||
from datetime import datetime, timedelta, timezone
|
||||
import hashlib
|
||||
import hmac
|
||||
from tempfile import TemporaryDirectory
|
||||
import unittest
|
||||
|
||||
from aios_v2r1.runtime import RuntimeWiring
|
||||
from aios_v2r1.tenant_context import canonical_json
|
||||
|
||||
|
||||
class MutableClock:
|
||||
def __init__(self, now: datetime) -> None:
|
||||
self.now = now
|
||||
|
||||
def __call__(self) -> datetime:
|
||||
return self.now
|
||||
|
||||
|
||||
class RuntimeWiringIntegrationTests(unittest.TestCase):
|
||||
internal_key = b"runtime-internal-context-key-is-32bytes"
|
||||
ingress_key = b"runtime-external-ingress-key-is-32bytes"
|
||||
|
||||
def setUp(self) -> None:
|
||||
self.directory = TemporaryDirectory()
|
||||
self.addCleanup(self.directory.cleanup)
|
||||
self.clock = MutableClock(datetime(2026, 7, 13, tzinfo=timezone.utc))
|
||||
self.runtime = RuntimeWiring.create(
|
||||
self.directory.name,
|
||||
signing_key=self.internal_key,
|
||||
ingress_hmac_key=self.ingress_key,
|
||||
clock=self.clock,
|
||||
)
|
||||
self.runtime.router.register_tenant("tenant-a", "cell-a")
|
||||
self.runtime.router.register_tenant("tenant-b", "cell-b")
|
||||
self.runtime.router.bind_channel(
|
||||
tenant_id="tenant-a", channel="weixin", channel_account_id="account-a"
|
||||
)
|
||||
self.runtime.router.bind_channel(
|
||||
tenant_id="tenant-b", channel="weixin", channel_account_id="account-b"
|
||||
)
|
||||
self.runtime.router.bind_principal(
|
||||
tenant_id="tenant-a", channel="weixin", channel_account_id="account-a",
|
||||
principal_id="user-a",
|
||||
)
|
||||
self.runtime.router.bind_session(
|
||||
tenant_id="tenant-a", session_id="session-a", cell_id="cell-a",
|
||||
principal_id="user-a", ttl_seconds=60,
|
||||
)
|
||||
|
||||
def message(
|
||||
self, *, event_id: str = "event-a", message_id: str = "message-a",
|
||||
body: str = "hello", **changes: object,
|
||||
) -> dict[str, object]:
|
||||
values: dict[str, object] = {
|
||||
"tenant_id": "tenant-a", "cell_id": "cell-a", "principal_id": "user-a",
|
||||
"principal_type": "authenticated_user", "origin_type": "channel_user",
|
||||
"channel": "weixin", "channel_account_id": "account-a", "peer_id": "peer-a",
|
||||
"conversation_id": "conversation-a", "session_id": "session-a", "task_id": None,
|
||||
"event_id": event_id, "message_id": message_id, "reply_to_message_id": None,
|
||||
"direction": "inbound", "command_capable": True,
|
||||
"occurred_at": "2026-07-13T00:00:00+00:00",
|
||||
"received_at": "2026-07-13T00:00:01+00:00",
|
||||
"content": {"body": body, "quoted_body": None},
|
||||
"adapter": {"name": "weixin", "version": "v2"},
|
||||
}
|
||||
values.update(changes)
|
||||
return values
|
||||
|
||||
def request(self, **changes: object) -> dict[str, object]:
|
||||
values: dict[str, object] = {
|
||||
"principal_id": "user-a", "tenant_id": "tenant-a", "cell_id": "cell-a",
|
||||
"channel": "weixin", "channel_account_id": "account-a", "session_id": "session-a",
|
||||
"message": self.message(),
|
||||
}
|
||||
values.update(changes)
|
||||
values["signature"] = hmac.new(
|
||||
self.ingress_key, canonical_json(values), hashlib.sha256
|
||||
).hexdigest()
|
||||
return values
|
||||
|
||||
def ingest(self, **changes: object):
|
||||
return self.runtime.ingest(request=self.request(**changes))
|
||||
|
||||
def test_real_ingress_appends_exact_record_and_reopens(self) -> None:
|
||||
first = self.ingest()
|
||||
self.assertEqual("ACCEPTED", first.status)
|
||||
assert first.result is not None
|
||||
self.assertEqual("message-a", first.result.record.message_id)
|
||||
self.assertEqual("tenant-a", first.result.route.tenant_id)
|
||||
self.assertEqual(1, self.runtime.ledger.count())
|
||||
self.assertEqual(1, self.runtime.session_pool.active_count())
|
||||
|
||||
reopened = RuntimeWiring.create(
|
||||
self.directory.name, signing_key=self.internal_key,
|
||||
ingress_hmac_key=self.ingress_key, clock=self.clock,
|
||||
)
|
||||
repeated = reopened.ingest(request=self.request())
|
||||
self.assertEqual("ACCEPTED", repeated.status)
|
||||
assert repeated.result is not None
|
||||
self.assertEqual(first.result.record, repeated.result.record)
|
||||
self.assertEqual(1, reopened.ledger.count())
|
||||
self.assertEqual(1, reopened.session_pool.active_count())
|
||||
|
||||
def test_authoritative_tenant_route_rejects_cross_tenant_ingress_without_mutation(self) -> None:
|
||||
result = self.ingest(
|
||||
tenant_id="tenant-b", cell_id="cell-b",
|
||||
message=self.message(tenant_id="tenant-b", cell_id="cell-b"),
|
||||
)
|
||||
self.assertEqual("AUTH_FAILED", result.status)
|
||||
self.assertIsNone(result.result)
|
||||
self.assertEqual(0, self.runtime.ledger.count())
|
||||
self.assertEqual(0, self.runtime.session_pool.active_count())
|
||||
|
||||
def test_identical_concurrent_ingress_is_one_exact_ledger_record_and_one_session(self) -> None:
|
||||
with ThreadPoolExecutor(max_workers=24) as executor:
|
||||
results = list(executor.map(lambda _: self.ingest(), range(24)))
|
||||
self.assertEqual({"ACCEPTED"}, {result.status for result in results})
|
||||
self.assertEqual(1, self.runtime.ledger.count())
|
||||
self.assertEqual(1, self.runtime.session_pool.active_count())
|
||||
|
||||
def test_collision_is_sanitized_and_does_not_leave_partial_session_or_ledger_state(self) -> None:
|
||||
self.assertEqual("ACCEPTED", self.ingest(
|
||||
message=self.message(event_id="event-a", message_id="message-a", body="first")
|
||||
).status)
|
||||
collision = self.ingest(
|
||||
message=self.message(event_id="event-a", message_id="message-b", body="second")
|
||||
)
|
||||
self.assertEqual("CONFLICT", collision.status)
|
||||
self.assertIsNone(collision.result)
|
||||
self.assertEqual(1, self.runtime.ledger.count())
|
||||
self.assertEqual(1, self.runtime.session_pool.active_count())
|
||||
|
||||
def test_unknown_cross_and_expired_sessions_fail_closed_without_mutation(self) -> None:
|
||||
unknown = self.ingest(
|
||||
session_id="unknown-session", message=self.message(session_id="unknown-session")
|
||||
)
|
||||
self.assertEqual("AUTH_FAILED", unknown.status)
|
||||
cross = self.ingest(
|
||||
principal_id="user-b", message=self.message(principal_id="user-b")
|
||||
)
|
||||
self.assertEqual("AUTH_FAILED", cross.status)
|
||||
self.clock.now += timedelta(seconds=61)
|
||||
expired = self.ingest()
|
||||
self.assertEqual("AUTH_FAILED", expired.status)
|
||||
self.assertEqual(0, self.runtime.ledger.count())
|
||||
self.assertEqual(0, self.runtime.session_pool.active_count())
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,51 @@
|
||||
"""Gate 1 contract tests for canonical tenant-context signatures."""
|
||||
from __future__ import annotations
|
||||
|
||||
from datetime import datetime, timezone
|
||||
import unittest
|
||||
|
||||
from aios_v2r1.tenant_context import TenantContext, ValidationError
|
||||
|
||||
|
||||
class TenantContextSignatureContractTests(unittest.TestCase):
|
||||
key = b"k" * 32
|
||||
now = datetime(2026, 7, 13, tzinfo=timezone.utc)
|
||||
|
||||
def setUp(self) -> None:
|
||||
self.context = TenantContext(
|
||||
tenant_id="tenant-a",
|
||||
cell_id="cell-a",
|
||||
principal_id="user-a",
|
||||
principal_type="user",
|
||||
session_id="session-a",
|
||||
task_id=None,
|
||||
channel="hermes",
|
||||
channel_account_id="account-a",
|
||||
issued_at="2026-07-13T00:00:00+00:00",
|
||||
expires_at="2026-07-13T00:05:00+00:00",
|
||||
nonce="nonce-b",
|
||||
)
|
||||
self.token = self.context.sign(self.key)
|
||||
|
||||
def test_valid_canonical_token_verifies(self) -> None:
|
||||
verified = TenantContext.verify(self.token, self.key, now=self.now)
|
||||
|
||||
self.assertEqual(verified, self.context)
|
||||
|
||||
def test_rejects_padded_signature_encoding(self) -> None:
|
||||
with self.assertRaises(ValidationError):
|
||||
TenantContext.verify(f"{self.token}=", self.key, now=self.now)
|
||||
|
||||
def test_rejects_standard_base64_signature_encoding(self) -> None:
|
||||
payload, signature = self.token.rsplit(".", 1)
|
||||
standard_signature = signature.replace("-", "+").replace("_", "/")
|
||||
self.assertNotEqual(signature, standard_signature)
|
||||
|
||||
with self.assertRaises(ValidationError):
|
||||
TenantContext.verify(
|
||||
f"{payload}.{standard_signature}", self.key, now=self.now
|
||||
)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
Reference in New Issue
Block a user