Files
bot-bottle/bot_bottle/backend/docker/compose.py
T

543 lines
19 KiB
Python

"""Compose-spec rendering for a Docker bottle (PRD 0018, chunk 1).
`bottle_plan_to_compose(plan)` returns a Compose v2 spec dict
describing the per-bottle container topology — one project per
bottle instance, services for the agent + every applicable sidecar,
two networks, no named volumes.
Pure function. No I/O, no subprocess. Expects every launch-time
field (network names, CA host paths, etc.) on the plan's inner
plans to be populated; chunks 2+3 own that ordering. Chunk 1 just
encodes the translation so it can be unit-tested in isolation.
Conditional services follow the plan content (matches the
SDK-call branching in `launch.py` today):
- pipelock + agent: always.
- git-gate: iff plan.git_gate_plan.upstreams.
- egress: iff plan.egress_plan.routes.
- supervise: iff plan.supervise_plan is not None.
Naming:
- Compose project: `bot-bottle-<slug>`.
- Service names (inside the file): `agent`, `pipelock`,
`egress`, `git-gate`, `supervise`.
- `container_name:` matches today's pattern
(`bot-bottle-<service>-<slug>`) so dashboard/cleanup discovery
via the prefix scan keeps working through the transition.
- Network aliases preserve the current dial-by-shortname pattern
for `egress` / `supervise`, and add the long container-name as
an internal-network alias for `pipelock` / `git-gate` so any
caller still referencing the long name resolves.
Sidecars that are built (egress, git-gate, supervise) get a
compose `build:` block pointing at the repo Dockerfile; the
`image:` tag is set explicitly so cached images on the daemon
aren't rebuilt on every up.
"""
from __future__ import annotations
import json
import subprocess
import sys
from pathlib import Path
from typing import Any
from ...egress import (
EGRESS_HOSTNAME,
EGRESS_ROUTES_IN_CONTAINER,
)
from ...git_gate import GIT_GATE_HOSTNAME
from ...log import die, warn
from ...pipelock import PIPELOCK_HOSTNAME
from ...supervise import (
CURRENT_CONFIG_DIR_IN_AGENT,
QUEUE_DIR_IN_CONTAINER,
SUPERVISE_HOSTNAME,
SUPERVISE_PORT,
)
from ...util import expand_tilde
from ..util import AGENT_CA_BUNDLE, AGENT_CA_PATH
from .bottle_plan import DockerBottlePlan
from .egress import (
EGRESS_CA_IN_CONTAINER,
EGRESS_PIPELOCK_CA_IN_CONTAINER,
)
from .git_gate import (
GIT_GATE_ACCESS_HOOK_IN_CONTAINER,
GIT_GATE_CREDS_DIR_IN_CONTAINER,
GIT_GATE_ENTRYPOINT_IN_CONTAINER,
GIT_GATE_HOOK_IN_CONTAINER,
)
from .pipelock import (
PIPELOCK_CA_CERT_IN_CONTAINER,
PIPELOCK_CA_KEY_IN_CONTAINER,
PIPELOCK_PORT,
)
from .sidecar_bundle import (
SIDECAR_BUNDLE_DOCKERFILE,
SIDECAR_BUNDLE_IMAGE,
sidecar_bundle_container_name,
)
# Repo root, used as the build context for the bundle Dockerfile.
_REPO_DIR = str(Path(__file__).resolve().parent.parent.parent.parent)
def bottle_plan_to_compose(plan: DockerBottlePlan) -> dict[str, Any]:
"""Render a Compose v2 spec dict from a fully-resolved
DockerBottlePlan.
The plan must have its inner plans (`proxy_plan`,
`git_gate_plan`, `egress_plan`, `supervise_plan`) populated
with launch-time fields — network names, CA host paths,
pipelock_proxy_url. The renderer doesn't validate; callers
feed it a fully-resolved plan or get an incomplete compose
spec back.
"""
project = f"bot-bottle-{plan.slug}"
services: dict[str, Any] = {
"sidecars": _sidecar_bundle_service(plan),
"agent": _agent_service(plan),
}
return {
"name": project,
"services": services,
"networks": _networks(plan),
}
def _networks(plan: DockerBottlePlan) -> dict[str, Any]:
"""Compose-managed networks with explicit `name:` matching the
existing slug-suffixed convention. Compose creates them on `up`
and destroys them on `down`. The internal one is `--internal`
(no default gateway); the egress one is a normal user-defined
bridge."""
return {
"internal": {
"name": plan.proxy_plan.internal_network,
"internal": True,
},
"egress": {
"name": plan.proxy_plan.egress_network,
},
}
def _bind(host: str | Path, target: str, *, read_only: bool = True) -> dict[str, Any]:
"""One bind-mount entry in the long-form `volumes:` shape.
Long form is preferred over `host:target:ro` strings because
it's easier to inspect in tests and survives whitespace in
host paths."""
return {
"type": "bind",
"source": str(host),
"target": target,
"read_only": read_only,
}
def _sidecar_bundle_service(plan: DockerBottlePlan) -> dict[str, Any]:
"""The `sidecars` service: one container per bottle, bundle
image, all four daemons under a Python init supervisor.
Mechanics:
- Daemon subset narrows via `BOT_BOTTLE_SIDECAR_DAEMONS`
env. pipelock is always present; egress / git-gate /
supervise are conditional on the plan.
- Volumes are the union of the four daemons' bind-mounts,
preserving the same in-container paths so each daemon
finds its config / hooks / CA where it expects.
- Environment is the union of *daemon-private* env vars
(EGRESS_UPSTREAM_PROXY, SUPERVISE_BOTTLE_SLUG, etc).
HTTPS_PROXY is NOT propagated here — see the comment in
egress_entrypoint.sh; setting it at the container level
would route git-gate's git fetches through pipelock,
which is wrong.
- Network aliases register every legacy short/long
hostname (pipelock, egress, git-gate, supervise plus
their `bot-bottle-<service>-<slug>` long forms) so
the agent's HTTPS_PROXY URL and any other inter-service
reference resolves to the bundle.
"""
daemons: list[str] = ["egress", "pipelock"]
if plan.git_gate_plan.upstreams:
daemons.append("git-gate")
if plan.supervise_plan is not None:
daemons.append("supervise")
env: list[str] = [f"BOT_BOTTLE_SIDECAR_DAEMONS={','.join(daemons)}"]
volumes: list[dict[str, Any]] = []
# --- pipelock ----------------------------------------------------
pp = plan.proxy_plan
volumes += [
_bind(pp.yaml_path, "/etc/pipelock.yaml"),
_bind(pp.ca_cert_host_path, PIPELOCK_CA_CERT_IN_CONTAINER),
_bind(pp.ca_key_host_path, PIPELOCK_CA_KEY_IN_CONTAINER),
]
# --- egress (always part of the bundle; the EGRESS_UPSTREAM_*
# env vars + ca bind-mounts are needed iff routes exist; when
# the bottle has no routes the egress daemon falls back to its
# `regular@9099` mode and is unused) -----------------------------
ep = plan.egress_plan
if ep.routes:
env.append(f"EGRESS_UPSTREAM_PROXY={ep.pipelock_proxy_url}")
env.append(f"EGRESS_UPSTREAM_CA={EGRESS_PIPELOCK_CA_IN_CONTAINER}")
volumes += [
_bind(ep.routes_path, EGRESS_ROUTES_IN_CONTAINER),
_bind(ep.mitmproxy_ca_host_path, EGRESS_CA_IN_CONTAINER),
_bind(ep.pipelock_ca_host_path, EGRESS_PIPELOCK_CA_IN_CONTAINER),
]
for token_env in sorted(ep.token_env_map.keys()):
env.append(token_env)
# --- git-gate ----------------------------------------------------
gp = plan.git_gate_plan
if gp.upstreams:
volumes += [
_bind(gp.entrypoint_script, GIT_GATE_ENTRYPOINT_IN_CONTAINER),
_bind(gp.hook_script, GIT_GATE_HOOK_IN_CONTAINER),
_bind(gp.access_hook_script, GIT_GATE_ACCESS_HOOK_IN_CONTAINER),
]
for u in gp.upstreams:
keypath = expand_tilde(u.identity_file)
volumes.append(_bind(
keypath,
f"{GIT_GATE_CREDS_DIR_IN_CONTAINER}/{u.name}-key",
))
if u.known_hosts_file:
volumes.append(_bind(
u.known_hosts_file,
f"{GIT_GATE_CREDS_DIR_IN_CONTAINER}/{u.name}-known_hosts",
))
# --- supervise ---------------------------------------------------
sp = plan.supervise_plan
if sp is not None:
env += [
f"SUPERVISE_BOTTLE_SLUG={plan.slug}",
f"SUPERVISE_QUEUE_DIR={QUEUE_DIR_IN_CONTAINER}",
f"SUPERVISE_PORT={SUPERVISE_PORT}",
]
volumes.append({
"type": "bind",
"source": str(sp.queue_dir),
"target": QUEUE_DIR_IN_CONTAINER,
"read_only": False,
})
# Internal-network aliases: the agent reaches each daemon through
# its short name (pipelock / egress / git-gate / supervise) which
# the bundle answers as if it were the daemon itself.
internal_aliases = [
PIPELOCK_HOSTNAME,
EGRESS_HOSTNAME,
]
if gp.upstreams:
internal_aliases.append(GIT_GATE_HOSTNAME)
if sp is not None:
internal_aliases.append(SUPERVISE_HOSTNAME)
service: dict[str, Any] = {
"image": SIDECAR_BUNDLE_IMAGE,
"build": {
"context": _REPO_DIR,
"dockerfile": SIDECAR_BUNDLE_DOCKERFILE,
},
"container_name": sidecar_bundle_container_name(plan.slug),
"networks": {
"internal": {"aliases": internal_aliases},
"egress": None,
},
"environment": env,
"volumes": volumes,
}
return service
def _agent_service(plan: DockerBottlePlan) -> dict[str, Any]:
"""Agent container. Runs `sleep infinity`; claude is `docker
exec -it`'d into it later. No TTY at the container level —
interactivity is per-exec. HTTP_PROXY/HTTPS_PROXY point at the
egress short-alias when an egress is declared, otherwise
straight at pipelock's container name. CA trust trio matches
the existing launch.py wiring."""
proxy_url = _agent_proxy_url(plan)
no_proxy = _agent_no_proxy(plan)
env: list[str] = [
f"HTTPS_PROXY={proxy_url}",
f"HTTP_PROXY={proxy_url}",
f"https_proxy={proxy_url}",
f"http_proxy={proxy_url}",
f"NO_PROXY={no_proxy}",
f"no_proxy={no_proxy}",
f"NODE_EXTRA_CA_CERTS={AGENT_CA_PATH}",
f"SSL_CERT_FILE={AGENT_CA_BUNDLE}",
f"REQUESTS_CA_BUNDLE={AGENT_CA_BUNDLE}",
]
for name, value in sorted(plan.agent_provision.guest_env.items()):
env.append(f"{name}={value}")
# Forwarded vars (OAuth token, manifest host-interpolations):
# bare name → inherits from compose-up process env, value
# never lands on argv or in the compose file.
for name in sorted(plan.forwarded_env.keys()):
env.append(name)
service: dict[str, Any] = {
"image": plan.runtime_image,
"container_name": plan.container_name,
"command": ["sleep", "infinity"],
"networks": {"internal": None},
"environment": env,
}
if plan.use_runsc:
service["runtime"] = "runsc"
if plan.env_file and plan.env_file.exists() and plan.env_file.stat().st_size > 0:
service["env_file"] = [str(plan.env_file)]
volumes: list[dict[str, Any]] = []
if plan.supervise_plan is not None:
volumes.append(_bind(
plan.supervise_plan.current_config_dir,
CURRENT_CONFIG_DIR_IN_AGENT,
))
if volumes:
service["volumes"] = volumes
# The init supervisor inside the bundle owns intra-bundle
# daemon ordering, so the agent only waits for the bundle
# container itself.
service["depends_on"] = ["sidecars"]
return service
def _agent_proxy_url(plan: DockerBottlePlan) -> str:
"""Pick the agent's HTTP_PROXY. With egress declared, the agent
goes through egress (which in turn HTTPS_PROXYs to pipelock on
its outbound leg). Without egress, the agent talks straight to
pipelock."""
if plan.egress_plan.routes:
from .egress import EGRESS_PORT
return f"http://{EGRESS_HOSTNAME}:{EGRESS_PORT}"
return f"http://{PIPELOCK_HOSTNAME}:{PIPELOCK_PORT}"
def _agent_no_proxy(plan: DockerBottlePlan) -> str:
"""NO_PROXY for the agent. Matches the launch.py rules:
loopback always, supervise hostname when the supervise sidecar
is up (the MCP long-poll pattern needs to bypass pipelock's
idle timeout)."""
hosts = ["localhost", "127.0.0.1"]
if plan.supervise_plan is not None:
hosts.append(SUPERVISE_HOSTNAME)
return ",".join(hosts)
# --- Lifecycle helpers (PRD 0018 chunk 3) ----------------------------------
#
# The renderer above is pure. The helpers below own the I/O side:
# serialize the spec to disk, drive `docker compose up`, dump the
# merged log file on teardown, and `docker compose down` to clean up
# (networks are pre-created externally so `down` leaves them alone;
# the launch step removes them in its own teardown step).
COMPOSE_FILE_NAME = "docker-compose.yml"
COMPOSE_LOG_NAME = "compose.log"
COMPOSE_PROJECT_PREFIX = "bot-bottle-"
def compose_project_name(slug: str) -> str:
"""Stable mapping from slug → compose project. Matches the
`name:` field the renderer emits, so `docker compose ls`
enumeration and direct CLI invocations agree on the project
identifier."""
return f"{COMPOSE_PROJECT_PREFIX}{slug}"
def slug_from_compose_project(project: str) -> str:
"""Inverse of `compose_project_name`: strip the prefix to get
the underlying slug. Returns empty string if the project name
doesn't start with the expected prefix."""
if not project.startswith(COMPOSE_PROJECT_PREFIX):
return ""
return project[len(COMPOSE_PROJECT_PREFIX):]
def list_compose_projects(
*, include_stopped: bool = True, warn_on_error: bool = True,
) -> list[str]:
"""All compose project names starting with `bot-bottle-`.
`include_stopped=True` (default) runs `docker compose ls --all`
so exited projects appear too; pass False to get only projects
with at least one running container.
Returns [] on docker daemon errors or malformed output rather
than raising — callers should treat the empty list as "no
projects discoverable", not "no projects exist". `warn_on_error`
stays true for explicit operator commands like cleanup, but active
discovery paths set it false so dashboard refreshes don't spam
stderr while Docker Desktop is stopped."""
argv = ["docker", "compose", "ls", "--format", "json"]
if include_stopped:
argv.insert(3, "--all")
try:
result = subprocess.run(
argv, capture_output=True, text=True, check=False,
)
except FileNotFoundError:
# docker binary not on PATH — same shape as a daemon-down
# error from the caller's POV: no projects discoverable.
return []
if result.returncode != 0:
if warn_on_error:
warn(f"docker compose ls failed: {result.stderr.strip()}")
return []
try:
projects = json.loads(result.stdout or "[]")
except json.JSONDecodeError as e:
if warn_on_error:
warn(f"docker compose ls returned malformed JSON: {e}")
return []
names: list[str] = []
for p in projects:
if not isinstance(p, dict):
continue
name = str(p.get("Name", ""))
if name.startswith(COMPOSE_PROJECT_PREFIX):
names.append(name)
return sorted(set(names))
def list_active_slugs(
*, include_stopped: bool = False, warn_on_error: bool = True,
) -> list[str]:
"""Slugs (project name minus prefix) of currently-running
bottles. Used by the dashboard's operator-edit verbs to choose
a bottle to apply a config edit to."""
return sorted(
slug for slug in (
slug_from_compose_project(p)
for p in list_compose_projects(
include_stopped=include_stopped,
warn_on_error=warn_on_error,
)
) if slug
)
def compose_file_path(state_dir: Path) -> Path:
return state_dir / COMPOSE_FILE_NAME
def compose_log_path(state_dir: Path) -> Path:
return state_dir / COMPOSE_LOG_NAME
def write_compose_file(spec: dict[str, Any], path: Path) -> Path:
"""Serialize the compose dict to disk. JSON content with a
`.yml` filename — JSON is a strict subset of YAML 1.2 for the
constructs the renderer uses (mappings, lists, strings, bools,
nulls), and `docker compose -f file.yml` parses it as YAML.
Avoids a yaml dependency while keeping the file `cat`-readable.
"""
path.parent.mkdir(parents=True, exist_ok=True)
path.write_text(json.dumps(spec, indent=2, sort_keys=False) + "\n")
path.chmod(0o644)
return path
def _compose_argv(project: str, compose_file: Path, *cmd: str) -> list[str]:
return [
"docker", "compose",
"-p", project,
"-f", str(compose_file),
*cmd,
]
def compose_up(
project: str,
compose_file: Path,
*,
env: dict[str, str] | None = None,
) -> None:
"""`docker compose up -d` for the project. Env-inheritance is
via `env=` on the subprocess — every `environment: [NAME]` (bare
name) entry in the compose file resolves to whatever value
`NAME` has in `env` at exec time. Secrets never land on argv or
in the compose file."""
argv = _compose_argv(project, compose_file, "up", "-d")
result = subprocess.run(
argv, capture_output=True, text=True, env=env, check=False,
)
if result.returncode != 0:
sys.stderr.write(result.stderr)
die(f"docker compose up failed for project {project}")
def compose_dump_logs(project: str, compose_file: Path, output: Path) -> None:
"""Write the merged stdout/stderr of every service to `output`
using `docker compose logs --no-color --timestamps`. Best-effort
— failures here shouldn't block teardown. The interleaved single
file is what the user reads post-mortem; per-service tail still
works through `docker compose logs -f <service>` while the
project is up."""
output.parent.mkdir(parents=True, exist_ok=True)
argv = _compose_argv(project, compose_file, "logs", "--no-color", "--timestamps")
try:
with open(output, "wb") as f:
subprocess.run(
argv,
stdout=f,
stderr=subprocess.STDOUT,
check=False,
)
output.chmod(0o644)
except OSError as e:
warn(f"failed to write compose log to {output}: {e}")
def compose_down(project: str, compose_file: Path) -> None:
"""`docker compose down` for the project. External networks are
intentionally NOT removed by compose (`external: true` on the
networks block); the launch step's own teardown removes them
via `network_remove` so the per-bottle ephemeral subnet doesn't
accumulate."""
argv = _compose_argv(project, compose_file, "down")
result = subprocess.run(
argv, capture_output=True, text=True, check=False,
)
if result.returncode != 0:
warn(
f"docker compose down failed for project {project}: "
f"{result.stderr.strip()}"
)
__all__ = [
"COMPOSE_FILE_NAME",
"COMPOSE_LOG_NAME",
"COMPOSE_PROJECT_PREFIX",
"bottle_plan_to_compose",
"compose_down",
"compose_dump_logs",
"compose_file_path",
"compose_log_path",
"compose_project_name",
"compose_up",
"list_active_slugs",
"list_compose_projects",
"slug_from_compose_project",
"write_compose_file",
]