4b2dbcdefd
Phase 3 of PRD 0013. Wires the supervise sidecar into bottle launch: - Manifest: bottle.supervise (bool, default False). Opt-in for v1 so existing bottles are unchanged. - supervise.py: adds SupervisePlan + abstract Supervise(ABC) with a prepare template that stages the per-bottle queue dir on the host and the current-config dir under stage_dir (routes.json + allowlist + Dockerfile). Stdlib-only so it still runs as the in-container shared helper. - backend/docker/supervise.py: DockerSupervise concrete start/stop. No egress network (the sidecar doesn't make outbound calls); just the bottle's internal network with network-alias "supervise" and a bind-mount of the host queue dir at /run/supervise/queue. - Prepare wires supervise.prepare into the DockerBottlePlan, derives routes_content from cred_proxy_plan, allowlist_content from pipelock_effective_allowlist, and dockerfile_content from the repo's Dockerfile. supervise sidecar added to the orphan probe. - Launch starts the supervise sidecar after pipelock + cred-proxy but before the agent (so DNS resolution for `supervise` is up on the agent's first tool call). - Agent container gets a read-only bind-mount of the current-config dir at /etc/claude-bottle/current-config when supervise is enabled. - bottle_plan print + to_dict surface the supervise state. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
214 lines
9.0 KiB
Python
214 lines
9.0 KiB
Python
"""Prepare step for the Docker bottle backend.
|
|
|
|
`resolve_plan` does all host-side resolution (image and container
|
|
names, env-file, prompt-file, proxy plan, runtime detection) and
|
|
returns a frozen DockerBottlePlan. No Docker resources are created;
|
|
the only side effects are scratch files under `stage_dir` and a probe
|
|
of `docker info`. Cross-backend host-side validation has already run
|
|
via the base class's `prepare` template before this is called.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import os
|
|
from pathlib import Path
|
|
|
|
from ... import pipelock
|
|
from ...cred_proxy import cred_proxy_render_routes
|
|
from ...env import ResolvedEnv, resolve_env
|
|
from ...log import die
|
|
from .. import BottleSpec
|
|
from . import util as docker_mod
|
|
from .bottle_plan import DockerBottlePlan
|
|
from .cred_proxy import (
|
|
DockerCredProxy,
|
|
cred_proxy_container_name,
|
|
cred_proxy_url,
|
|
)
|
|
from .git_gate import DockerGitGate, git_gate_container_name
|
|
from .pipelock import DockerPipelockProxy, pipelock_container_name
|
|
from .supervise import DockerSupervise, supervise_container_name
|
|
|
|
|
|
def resolve_plan(
|
|
spec: BottleSpec,
|
|
*,
|
|
stage_dir: Path,
|
|
proxy: DockerPipelockProxy,
|
|
git_gate: DockerGitGate,
|
|
cred_proxy: DockerCredProxy,
|
|
supervise: DockerSupervise,
|
|
) -> DockerBottlePlan:
|
|
"""Resolve Docker-specific names and write scratch files. Trusts
|
|
that the agent and its skills/git-gate keys are present —
|
|
validation already ran in the base class."""
|
|
docker_mod.require_docker()
|
|
|
|
manifest = spec.manifest
|
|
agent = manifest.agents[spec.agent_name]
|
|
bottle = manifest.bottle_for(spec.agent_name)
|
|
|
|
slug = docker_mod.slugify(spec.agent_name)
|
|
|
|
image = os.environ.get("CLAUDE_BOTTLE_IMAGE", "claude-bottle:latest")
|
|
derived_image = ""
|
|
runtime_image = image
|
|
if spec.copy_cwd:
|
|
derived_image = os.environ.get(
|
|
"CLAUDE_BOTTLE_DERIVED_IMAGE", f"claude-bottle:cwd-{slug}"
|
|
)
|
|
runtime_image = derived_image
|
|
|
|
default_container = f"claude-bottle-{slug}"
|
|
pinned_container = os.environ.get("CLAUDE_BOTTLE_CONTAINER", "")
|
|
container_name_pinned = bool(pinned_container)
|
|
if container_name_pinned:
|
|
container_name = pinned_container
|
|
if docker_mod.container_exists(container_name):
|
|
die(
|
|
f"container '{container_name}' already exists "
|
|
f"(pinned via CLAUDE_BOTTLE_CONTAINER). "
|
|
f"Remove it with 'docker rm -f {container_name}' or unset the override."
|
|
)
|
|
else:
|
|
container_name = ""
|
|
for candidate in docker_mod.container_name_candidates(default_container):
|
|
if not docker_mod.container_exists(candidate):
|
|
container_name = candidate
|
|
break
|
|
if not container_name:
|
|
die(
|
|
f"could not find a free container name after "
|
|
f"{default_container}-{docker_mod.MAX_CONTAINER_SUFFIX}; "
|
|
f"clean up old containers with 'docker rm -f <name>'"
|
|
)
|
|
|
|
# Probe sidecar container names for orphans from a previous run.
|
|
# Sidecar names are deterministic from the slug; an orphan would
|
|
# surface as a docker-create conflict deep inside launch() with no
|
|
# actionable hint. Fail fast here with a cleanup pointer instead.
|
|
# Only probe sidecars this launch will actually try to create:
|
|
# pipelock always; git-gate when bottle.git is non-empty; cred-proxy
|
|
# when bottle.cred_proxy.routes is non-empty.
|
|
sidecar_probes: list[tuple[str, str]] = [
|
|
("pipelock", pipelock_container_name(slug)),
|
|
]
|
|
if bottle.git:
|
|
sidecar_probes.append(("git-gate", git_gate_container_name(slug)))
|
|
if bottle.cred_proxy.routes:
|
|
sidecar_probes.append(("cred-proxy", cred_proxy_container_name(slug)))
|
|
if bottle.supervise:
|
|
sidecar_probes.append(("supervise", supervise_container_name(slug)))
|
|
for label, sidecar_name in sidecar_probes:
|
|
if docker_mod.container_exists(sidecar_name):
|
|
die(
|
|
f"{label} sidecar container '{sidecar_name}' already exists. "
|
|
f"This is an orphan from a previous run; clean it up with "
|
|
f"'./cli.py cleanup' (or 'docker rm -f {sidecar_name}') and "
|
|
f"retry."
|
|
)
|
|
|
|
env_file = stage_dir / "agent.env"
|
|
prompt_file = stage_dir / "prompt.txt"
|
|
prompt_file.write_text("")
|
|
prompt_file.chmod(0o600)
|
|
|
|
proxy_plan = proxy.prepare(bottle, slug, stage_dir)
|
|
git_gate_plan = git_gate.prepare(bottle, slug, stage_dir)
|
|
cred_proxy_plan = cred_proxy.prepare(bottle, slug, stage_dir)
|
|
supervise_plan = None
|
|
if bottle.supervise:
|
|
routes_content = cred_proxy_render_routes(cred_proxy_plan.routes) if cred_proxy_plan.routes else ""
|
|
allowlist_content = "\n".join(pipelock.pipelock_effective_allowlist(bottle)) + "\n"
|
|
# Current Dockerfile for the agent image. Read from the repo
|
|
# root; for `--cwd` derived images the base Dockerfile is what
|
|
# the agent should propose changes against (the derived layer
|
|
# is just a workspace copy).
|
|
dockerfile_path = Path(__file__).resolve().parent.parent.parent.parent / "Dockerfile"
|
|
dockerfile_content = dockerfile_path.read_text() if dockerfile_path.is_file() else ""
|
|
supervise_plan = supervise.prepare(
|
|
slug, stage_dir,
|
|
routes_content=routes_content,
|
|
allowlist_content=allowlist_content,
|
|
dockerfile_content=dockerfile_content,
|
|
)
|
|
resolved = resolve_env(manifest, spec.agent_name)
|
|
# Everything that should reach the bottle by-name (so its value
|
|
# never lands on argv or in env_file) goes into one dict. Nothing
|
|
# mutates the host os.environ.
|
|
forwarded_env: dict[str, str] = dict(resolved.forwarded)
|
|
# Find the (at most one) cred-proxy route claiming the
|
|
# anthropic-base-url role. Manifest validation enforces the
|
|
# singleton constraint. cred-proxy is the only path the Anthropic
|
|
# OAuth token reaches the bottle — there is no fallback that
|
|
# forwards it into the agent's environ directly. Bottles that
|
|
# need claude-code to authenticate must declare an
|
|
# anthropic-base-url route.
|
|
anthropic_route = next(
|
|
(r for r in cred_proxy_plan.routes if "anthropic-base-url" in r.roles),
|
|
None,
|
|
)
|
|
if anthropic_route is not None:
|
|
# Point claude-code at the cred-proxy. The sidecar holds the
|
|
# OAuth token; the agent's environ does not. Strip the
|
|
# trailing slash so claude-code's path-join produces e.g.
|
|
# http://cred-proxy:9099/anthropic/v1/messages.
|
|
forwarded_env["ANTHROPIC_BASE_URL"] = (
|
|
f"{cred_proxy_url()}{anthropic_route.path}".rstrip("/")
|
|
)
|
|
# claude-code refuses to start without *some* credential in
|
|
# its env. The proxy strips inbound Authorization on every
|
|
# request and injects the real one — so a non-secret
|
|
# placeholder is sufficient and the SC1 test still holds
|
|
# (the placeholder is not a `cred_proxy.routes[].TokenRef`
|
|
# value). The agent cannot exfiltrate this string because
|
|
# it carries no meaning to api.anthropic.com.
|
|
forwarded_env["CLAUDE_CODE_OAUTH_TOKEN"] = "cred-proxy-placeholder"
|
|
# Belt-and-braces: turn off telemetry endpoints that don't
|
|
# route through ANTHROPIC_BASE_URL (statsig, error reporting).
|
|
# PRD 0010 open question default.
|
|
forwarded_env.setdefault("CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC", "1")
|
|
forwarded_env.setdefault("DISABLE_ERROR_REPORTING", "1")
|
|
_write_env_file(resolved, env_file)
|
|
prompt_file.write_text(agent.prompt)
|
|
|
|
allowlist_summary = pipelock.pipelock_allowlist_summary(bottle)
|
|
use_runsc = docker_mod.runsc_available()
|
|
|
|
return DockerBottlePlan(
|
|
spec=spec,
|
|
stage_dir=stage_dir,
|
|
slug=slug,
|
|
container_name=container_name,
|
|
container_name_pinned=container_name_pinned,
|
|
image=image,
|
|
derived_image=derived_image,
|
|
runtime_image=runtime_image,
|
|
env_file=env_file,
|
|
forwarded_env=forwarded_env,
|
|
prompt_file=prompt_file,
|
|
proxy_plan=proxy_plan,
|
|
git_gate_plan=git_gate_plan,
|
|
cred_proxy_plan=cred_proxy_plan,
|
|
supervise_plan=supervise_plan,
|
|
allowlist_summary=allowlist_summary,
|
|
use_runsc=use_runsc,
|
|
)
|
|
|
|
|
|
def _write_env_file(resolved: ResolvedEnv, env_file: Path) -> None:
|
|
"""Serialize the literal portion of a ResolvedEnv into docker's
|
|
`--env-file` syntax (NAME=VALUE per line, mode 600 since the file
|
|
may carry verbatim values from the manifest). Forwarded names ride
|
|
on the plan as a structured tuple instead."""
|
|
env_lines: list[str] = []
|
|
for name, value in resolved.literals.items():
|
|
if "\n" in value:
|
|
die(
|
|
f"env entry {name} (literal) contains a newline; "
|
|
f"docker --env-file cannot represent multi-line values."
|
|
)
|
|
env_lines.append(f"{name}={value}")
|
|
env_file.write_text("\n".join(env_lines) + ("\n" if env_lines else ""))
|
|
env_file.chmod(0o600)
|