Files
bot-bottle/bot_bottle/paths.py
T
didericis dff811f190
tracker-policy-pr / check-pr (pull_request) Successful in 12s
lint / lint (push) Successful in 59s
test / unit (pull_request) Successful in 53s
test / integration-docker (pull_request) Successful in 1m7s
test / coverage (pull_request) Successful in 19s
fix(gateway): persist git-gate state across gateway restarts
Per-bottle git-gate state (bare repos under /git/<id>, deploy creds under
/git-gate/creds/<id>) was provisioned once at bottle launch and lived only
in the gateway's ephemeral storage. A gateway rebuild/restart wiped it and
nothing re-provisioned already-running bottles, so their agents 404'd on
fetch/push. Same class of bug as the CA (#510); the orchestrator restores
only egress tokens, not git-gate declarations.

Persist the state on both backends, mirroring the CA-persistence approach:

- firecracker: attach a second persistent data drive (/dev/vdc) to the
  gateway VM and bind-mount its git/ + creds/ subdirs onto /git and
  /git-gate/creds in the gateway guest init, before the data plane starts.
  Generalize the VM config to a stable-ordered data_drives tuple (CA=vdb,
  git=vdc; orchestrator registry stays vdb).
- docker: bind-mount host dirs (host_gateway_git_dir / creds_dir, under the
  never-pruned app-data root) onto /git and /git-gate/creds, with
  BOT_BOTTLE_DOCKER_GIT_MOUNT / _CREDS_MOUNT env overrides so CI isolates
  them to per-run volumes it cleans up.

Teardown already rm -rf's /git/<id> + creds, so the persistent store
self-cleans over the normal lifecycle.

Closes #512

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-26 17:34:22 -04:00

187 lines
8.2 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/server.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.
ORCHESTRATOR_TOKEN_FILENAME = "orchestrator-token"
# The env var carrying the orchestrator's *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.
ORCHESTRATOR_TOKEN_ENV = "BOT_BOTTLE_ORCHESTRATOR_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).
ORCHESTRATOR_AUTH_JWT_ENV = "BOT_BOTTLE_ORCHESTRATOR_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"
# The host directories holding the gateway's persistent git-gate state — the
# per-bottle bare repos (`gateway-git`) and deploy creds (`gateway-creds`).
# Bind-mounted into the gateway container at /git and /git-gate/creds so they
# survive container recreation; without it a gateway restart drops every
# already-running bottle's git-gate state and its agent 404s on fetch/push
# (issue #512). Host bind-mounts (not named volumes) for the same reason as the
# CA dir — see host_gateway_ca_dir().
GATEWAY_GIT_DIRNAME = "gateway-git"
GATEWAY_CREDS_DIRNAME = "gateway-creds"
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_gateway_git_dir() -> Path:
"""The directory holding the gateway's persistent per-bottle bare repos,
created if missing. Bind-mounted into the gateway container at /git so the
repos survive container recreation (issue #512). A host bind-mount under the
app-data root, never pruned — same rationale as host_gateway_ca_dir()."""
git_dir = bot_bottle_root() / GATEWAY_GIT_DIRNAME
git_dir.mkdir(parents=True, exist_ok=True)
return git_dir
def host_gateway_creds_dir() -> Path:
"""The directory holding the gateway's persistent per-bottle git-gate deploy
creds, created if missing. Bind-mounted into the gateway container at
/git-gate/creds so the creds survive container recreation (issue #512). A
host bind-mount under the app-data root — same rationale as
host_gateway_ca_dir()."""
creds_dir = bot_bottle_root() / GATEWAY_CREDS_DIRNAME
creds_dir.mkdir(parents=True, exist_ok=True)
return creds_dir
def host_signing_key(filename: str) -> str:
"""A per-host signing key at `<root>/<filename>`, minted (256-bit, url-safe)
and persisted 0600 on first use, then reused.
The generic form of `host_orchestrator_token()`: each service names its own
key file (`trust_domain.py`), so the orchestrator and a separate service like
the host controller (#468) get distinct keys neither can read. It is a *host*
artifact — the file lives under the root the agent never mounts, and its value
is injected only into the trusted control-plane process — so reading it here
is safe on the launch path but the value never reaches a bottle."""
path = bot_bottle_root() / 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
def host_orchestrator_token() -> str:
"""The per-host control-plane signing key — the host-canonical key the
launchers inject into the control-plane process and the host CLI mints its
own `cli` token from. The `control-plane` trust domain's specialization of
`host_signing_key()`."""
return host_signing_key(ORCHESTRATOR_TOKEN_FILENAME)
__all__ = [
"HOST_DB_FILENAME",
"ORCHESTRATOR_TOKEN_FILENAME",
"ORCHESTRATOR_TOKEN_ENV",
"ORCHESTRATOR_AUTH_JWT_ENV",
"GATEWAY_CA_DIRNAME",
"GATEWAY_GIT_DIRNAME",
"GATEWAY_CREDS_DIRNAME",
"bot_bottle_root",
"host_db_path",
"host_db_dir",
"host_gateway_ca_dir",
"host_gateway_git_dir",
"host_gateway_creds_dir",
"host_signing_key",
"host_orchestrator_token",
]