Files
bot-bottle/bot_bottle/paths.py
T
didericis-claude 1db2a9eb67
test / integration-docker (pull_request) Successful in 17s
tracker-policy-pr / check-pr (pull_request) Successful in 16s
test / unit (pull_request) Successful in 39s
lint / lint (push) Successful in 56s
test / integration-firecracker (pull_request) Successful in 3m21s
test / coverage (pull_request) Successful in 19s
test / publish-infra (pull_request) Has been skipped
feat(control-plane): role-scoped signed tokens so the gateway can't drive operator routes
Review follow-up on #469: the data plane held the same control-plane secret
that authorizes every route, so a compromised egress/git-gate could queue a
supervise proposal AND approve it (or rewrite policy, read injected tokens) —
the (source_ip, identity_token) checks attribute the *bottle*, not the caller.

Replace the single shared bearer secret with role-scoped, HMAC-signed tokens
(compact HS256 JWTs, stdlib-only — no new dependency):

  * new `control_auth` mints/verifies `{role}` tokens; roles are `gateway`
    (data plane) and `cli` (host operator/launcher).
  * the orchestrator holds only the signing *key* and verifies; `dispatch`
    gates each route by role — `gateway` reaches /resolve + /supervise/
    {propose,poll}, everything else is `cli`-only (401 unauthenticated,
    403 wrong role).
  * the gateway is handed a pre-minted `gateway` token it cannot rewrite into
    `cli`; the host CLI mints its own `cli` token from the host key.
  * `gateway_init` scopes the signing key to the orchestrator process and the
    gateway token to the data-plane daemons, so even in the combined infra
    container a compromised data-plane daemon never sees the key.

Launchers (docker gateway + infra, macOS infra) inject the minted token(s);
Firecracker stays open behind its nft boundary. Open mode (no key) still grants
full `cli` access — the fail-visible fallback for tests.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-24 05:22:56 +00:00

144 lines
6.2 KiB
Python

"""Foundational filesystem paths for bot-bottle.
`bot_bottle_root()` is the app data root — per-bottle state, git-gate
keys, the gateway CA, and the shared SQLite DB all live under it. It
defaults to `~/.bot-bottle` and is overridable with the
**`BOT_BOTTLE_ROOT`** env var.
Note that the supervise queue and the audit log are *tables in the shared
DB*, not directories under the root — see `queue_store.py` / `audit_store.py`.
The root held a `queue/` directory before the SQLite migration (PRD 0067);
nothing writes there now.
The env override is the single knob for redirecting the root: the test
suite points it at a throwaway dir instead of monkey-patching the function
(every module and every flat/package copy reads the same env var, so one
override covers them all), and operators can relocate the root if needed.
This module has no bot-bottle imports, so it is safe to import from any
layer (and to COPY flat into the gateway).
"""
from __future__ import annotations
import os
import secrets
import stat
from pathlib import Path
# The single shared host state DB. All bot-bottle SQLite stores (supervise
# queue, audit, the orchestrator registry) co-tenant this one file — the
# TableMigrations schema_key namespaces each store's tables.
HOST_DB_FILENAME = "bot-bottle.db"
# The per-host control-plane secret file, and the env var the launchers inject
# its value into. The control plane requires this secret on every mutating /
# reading route (see orchestrator/control_plane.py); it is held only by the
# trusted callers (control plane, gateway, host CLI) and never handed to an
# agent, so an agent that can reach the control-plane port still can't drive it.
CONTROL_PLANE_TOKEN_FILENAME = "control-plane-token"
# The env var carrying the control-plane *signing key* — held only by the
# orchestrator (to verify tokens) and the host CLI (to mint its own), never by
# the data plane. Same value as the host token file; the name is unchanged for
# backward compatibility with existing launchers.
CONTROL_PLANE_TOKEN_ENV = "BOT_BOTTLE_CONTROL_PLANE_TOKEN"
# The env var carrying the data plane's pre-minted `gateway`-role token (a
# signed JWT the launcher mints from the signing key). The gateway presents this
# on /resolve + /supervise/{propose,poll}; it never holds the signing key, so it
# cannot forge a higher-privilege `cli` token (issue #469 review).
CONTROL_AUTH_JWT_ENV = "BOT_BOTTLE_CONTROL_AUTH_JWT"
# The host directory holding the gateway's persistent mitmproxy CA. Bind-mounted
# into the infra/gateway container at mitmproxy's confdir so the self-generated
# CA survives container recreation — every agent installs this one CA to trust
# the shared gateway's TLS interception, so it must not rotate on restart. See
# host_gateway_ca_dir() for why this is a host bind-mount, not a named volume.
GATEWAY_CA_DIRNAME = "gateway-ca"
def bot_bottle_root() -> Path:
"""The app data root — `$BOT_BOTTLE_ROOT` if set, else `~/.bot-bottle`."""
override = os.environ.get("BOT_BOTTLE_ROOT")
return Path(override) if override else Path.home() / ".bot-bottle"
def host_db_path() -> Path:
"""Path to the shared host state DB, `<root>/db/bot-bottle.db`.
Kept in its own `db/` subdirectory (not directly under the root) so a
backend that can only bind-mount *directories* can share this one file
with a gateway without exposing the root's other contents (git-gate
keys, per-bottle state, ...)."""
return bot_bottle_root() / "db" / HOST_DB_FILENAME
def host_db_dir() -> Path:
"""The directory holding the shared host state DB, created if missing.
Backends bind-mount this into their gateway so the supervise daemon writes
to the one DB the orchestrator (and the operator over HTTP) reads."""
db_dir = host_db_path().parent
db_dir.mkdir(parents=True, exist_ok=True)
return db_dir
def host_gateway_ca_dir() -> Path:
"""The directory holding the gateway's persistent mitmproxy CA, created if
missing. Backends bind-mount this into the infra/gateway container at
mitmproxy's confdir so the CA persists across container recreation.
A host bind-mount under the app-data root — deliberately NOT a Docker
named volume. A named volume survives `docker rm` but is silently wiped by
`docker volume prune` / `docker system prune --volumes` during routine host
maintenance; the gateway then mints a fresh CA that every already-running
bottle distrusts, failing the TLS handshake even after it reconnects to the
moved gateway (issue #450). A path under the root docker never prunes it,
and it stays directly inspectable + rotatable from the host."""
ca_dir = bot_bottle_root() / GATEWAY_CA_DIRNAME
ca_dir.mkdir(parents=True, exist_ok=True)
return ca_dir
def host_control_plane_token() -> str:
"""The per-host control-plane secret, minted (256-bit, url-safe) and
persisted 0600 on first use, then reused.
This is the shared secret the launchers inject into the control-plane and
gateway containers and that the host CLI presents on every call. It is a
*host* artifact — the file lives under the root the agent never mounts, and
the env var is set only on the trusted containers — so reading it here is
safe on the host launch path but the value never reaches a bottle."""
path = bot_bottle_root() / CONTROL_PLANE_TOKEN_FILENAME
try:
existing = path.read_text().strip()
if existing:
return existing
except OSError:
pass
path.parent.mkdir(parents=True, exist_ok=True)
token = secrets.token_urlsafe(32)
# Create 0600 up front (O_EXCL loses a concurrent race harmlessly — we
# re-read the winner's token below) so the secret is never briefly world-
# readable between write and chmod.
try:
fd = os.open(path, os.O_WRONLY | os.O_CREAT | os.O_EXCL, 0o600)
except FileExistsError:
return path.read_text().strip()
with os.fdopen(fd, "w") as f:
f.write(token)
os.chmod(path, stat.S_IRUSR | stat.S_IWUSR)
return token
__all__ = [
"HOST_DB_FILENAME",
"CONTROL_PLANE_TOKEN_FILENAME",
"CONTROL_PLANE_TOKEN_ENV",
"CONTROL_AUTH_JWT_ENV",
"GATEWAY_CA_DIRNAME",
"bot_bottle_root",
"host_db_path",
"host_db_dir",
"host_gateway_ca_dir",
"host_control_plane_token",
]