Compare commits
59 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 0a1f949937 | |||
| 64ca39ddd4 | |||
| 3c426f45f5 | |||
| 1d3e9e859c | |||
| 56d879f0b3 | |||
| 09393b354b | |||
| 77948ef56c | |||
| c10d1cb6e0 | |||
| 96b84eb84d | |||
| 910267b8a8 | |||
| 03eacd9f57 | |||
| c839cee319 | |||
| ea75fab3b4 | |||
| 13a8bdd7ca | |||
| 3318bdce28 | |||
| b2f61053ad | |||
| 485d101430 | |||
| e97366dad5 | |||
| 8e7f5c9572 | |||
| 69db629e16 | |||
| 96f75599a1 | |||
| 3062fc9230 | |||
| 404369a3e0 | |||
| 327e756eef | |||
| 444924d95d | |||
| 118d81533b | |||
| 353b1ad984 | |||
| 40ad2364ab | |||
| 9e5d00c6fa | |||
| 0c158c5718 | |||
| fe25ad7623 | |||
| 6570e9f044 | |||
| 39c823d3c0 | |||
| 8a44537f7e | |||
| 72ee1f77da | |||
| 00418a2834 | |||
| 2cbb178f88 | |||
| ed9a19bb38 | |||
| c5ae93c8ba | |||
| 186b905dff | |||
| 3519b924cb | |||
| c77f578fb4 | |||
| bc52c3525c | |||
| b70f3228ca | |||
| f7b3d6aaca | |||
| b05f245299 | |||
| 8d4e7f2582 | |||
| a0e17d56de | |||
| 934c1617b9 | |||
| bd964c0278 | |||
| 93756f2a8b | |||
| d9843fa41e | |||
| ae6c8b13d9 | |||
| 13a8d66c9b | |||
| c46d392b44 | |||
| 2a473eb404 | |||
| 4d89ffce8b | |||
| 822cff48ad | |||
| ce440fabc4 |
@@ -8,10 +8,10 @@ broad permissions inside a sandbox, so a misbehaving agent cannot reach the
|
||||
host. A Python CLI (entry point `cli.py`, package `bot_bottle/`) orchestrates
|
||||
the runtime lifecycle and the copying of skills and env vars into it.
|
||||
The default backend on compatible macOS hosts is macos-container:
|
||||
agents and sidecar bundles run through Apple's `container` CLI without
|
||||
agents and gateways run through Apple's `container` CLI without
|
||||
requiring Docker. On KVM-capable Linux hosts the default is firecracker:
|
||||
agents run in a Firecracker microVM reached over SSH on a point-to-point
|
||||
TAP, while the sidecar bundle still uses Docker. The legacy Docker
|
||||
TAP, while the gateway still uses Docker. The legacy Docker
|
||||
backend remains available with `BOT_BOTTLE_BACKEND=docker` or
|
||||
`--backend=docker`.
|
||||
|
||||
@@ -59,7 +59,7 @@ backend remains available with `BOT_BOTTLE_BACKEND=docker` or
|
||||
in a PRD, research note, or decision record.
|
||||
- Low dependencies by default. The project is Python, stdlib-first (no
|
||||
runtime pip dependencies in the package itself; the only language
|
||||
runtime is the Python 3.13 used by the CLI + sidecars). Ask before
|
||||
runtime is the Python 3.13 used by the CLI + companion containers). Ask before
|
||||
adding new tools, runtimes, or package managers.
|
||||
- Commit messages follow [Conventional Commits](https://www.conventionalcommits.org/en/v1.0.0/):
|
||||
`<type>[(scope)][!]: <description>`, where `<type>` is one of `feat`, `fix`,
|
||||
|
||||
@@ -1,8 +1,15 @@
|
||||
# Per-bottle sidecar bundle image (PRD 0024).
|
||||
# Gateway data-plane image (PRD 0024 bundle shape; PRD 0070 gateway).
|
||||
#
|
||||
# Collapses the prior per-sidecar images (egress, git-gate,
|
||||
# The egress / git-gate / supervise *data plane* — one image, run by
|
||||
# the consolidated per-host gateway (PRD 0070). It is NOT the
|
||||
# orchestrator control plane: that is the separate, lean
|
||||
# `bot-bottle-orchestrator` image (Dockerfile.orchestrator, #384), which
|
||||
# ships only python + the stdlib-only `bot_bottle` package and none of
|
||||
# this image's mitmproxy / git / gitleaks payload.
|
||||
#
|
||||
# Collapses the prior per-daemon images (egress, git-gate,
|
||||
# supervise) into one. A small stdlib-Python init supervisor at
|
||||
# /app/sidecar_init.py spawns all daemons, forwards SIGTERM, and
|
||||
# /app/gateway_init.py spawns all daemons, forwards SIGTERM, and
|
||||
# propagates per-daemon stdout/stderr to the container log with a
|
||||
# `[name]` prefix. See PRD 0024 for the rationale.
|
||||
#
|
||||
@@ -12,7 +19,7 @@
|
||||
# /app/egress_addon.py + siblings mitmproxy addon (egress)
|
||||
# /app/egress-entrypoint.sh mitmdump launcher
|
||||
# /app/supervise_server.py + .py supervise MCP server
|
||||
# /app/sidecar_init.py PID 1 supervisor
|
||||
# /app/gateway_init.py PID 1 supervisor
|
||||
# /etc/egress/routes.yaml bind-mounted at run time
|
||||
# /etc/git-gate/pre-receive docker-cp'd at start time
|
||||
# /git-gate-entrypoint.sh docker-cp'd at start time
|
||||
@@ -64,6 +71,7 @@ COPY --from=gitleaks-src /usr/bin/gitleaks /usr/bin/gitleaks
|
||||
COPY bot_bottle/egress_addon_core.py /app/egress_addon_core.py
|
||||
COPY bot_bottle/egress_dlp_config.py /app/egress_dlp_config.py
|
||||
COPY bot_bottle/egress_addon.py /app/egress_addon.py
|
||||
COPY bot_bottle/policy_resolver.py /app/policy_resolver.py
|
||||
COPY bot_bottle/dlp_detectors.py /app/dlp_detectors.py
|
||||
COPY bot_bottle/yaml_subset.py /app/yaml_subset.py
|
||||
COPY bot_bottle/paths.py /app/paths.py
|
||||
@@ -75,7 +83,7 @@ COPY bot_bottle/audit_store.py /app/audit_store.py
|
||||
COPY bot_bottle/store_manager.py /app/store_manager.py
|
||||
COPY bot_bottle/supervise.py /app/supervise.py
|
||||
COPY bot_bottle/supervise_server.py /app/supervise_server.py
|
||||
COPY bot_bottle/sidecar_init.py /app/sidecar_init.py
|
||||
COPY bot_bottle/gateway_init.py /app/gateway_init.py
|
||||
COPY bot_bottle/git_http_backend.py /app/git_http_backend.py
|
||||
COPY bot_bottle/egress_entrypoint.sh /app/egress-entrypoint.sh
|
||||
RUN chmod +x /app/egress-entrypoint.sh
|
||||
@@ -101,4 +109,4 @@ WORKDIR /app
|
||||
|
||||
# PID 1 is the supervisor. It owns signal handling and exit-code
|
||||
# propagation; no `exec` chain in the entrypoint itself.
|
||||
ENTRYPOINT ["python3", "/app/sidecar_init.py"]
|
||||
ENTRYPOINT ["python3", "/app/gateway_init.py"]
|
||||
@@ -0,0 +1,27 @@
|
||||
# Orchestrator control-plane image (PRD 0070, #384).
|
||||
#
|
||||
# The per-host orchestrator runs `python3 -m bot_bottle.orchestrator`.
|
||||
# The `bot_bottle` package is **stdlib-only** by design, so the control
|
||||
# plane needs nothing but a Python runtime — none of the gateway's
|
||||
# mitmproxy / git / gitleaks payload (that is the separate
|
||||
# `bot-bottle-gateway` image, Dockerfile.gateway). Splitting them keeps
|
||||
# the secret-dense control plane (it concentrates every bottle's egress
|
||||
# tokens — see PRD 0070's "secret concentration") on a minimal
|
||||
# dependency surface.
|
||||
#
|
||||
# The repo is bind-mounted read-only into the container at run time (see
|
||||
# `orchestrator/lifecycle.py`), so the source is NOT copied in here: the
|
||||
# image is just the runtime. `ensure_running` recreates the container
|
||||
# only when the bind-mounted source hash changes (#381), which is why
|
||||
# the code stays a mount rather than a baked layer.
|
||||
|
||||
FROM python:3.12-slim
|
||||
|
||||
# No third-party deps to install — stdlib only. Kept as an explicit,
|
||||
# self-documenting stage so a future confinement step (baking the
|
||||
# package, dropping the bind mount) has an obvious home.
|
||||
WORKDIR /app
|
||||
|
||||
# Documentation only; lifecycle.py overrides the entrypoint to
|
||||
# `python3 -m bot_bottle.orchestrator` with the runtime flags.
|
||||
ENTRYPOINT ["python3", "-m", "bot_bottle.orchestrator"]
|
||||
@@ -5,7 +5,7 @@
|
||||
# bot-bottle
|
||||
|
||||
[](https://gitea.dideric.is/didericis/bot-bottle/actions?workflow=test.yml)
|
||||
[](https://coverage.readthedocs.io/)
|
||||
[](https://coverage.readthedocs.io/)
|
||||
[](https://gitea.dideric.is/didericis/bot-bottle/src/branch/main/docs/decisions/0004-coverage-policy.md)
|
||||
|
||||
**Problem:** Developer wants to run a coding agent without supervision, but they don't want a prompt injected or misbehaving agent wrecking their environment or exfiltrating sensitive data.
|
||||
@@ -16,7 +16,7 @@
|
||||
|
||||
- **Per-bottle egress allowlist** — TLS-bumped HTTP/HTTPS chokepoint with a per-manifest host allowlist; per-route path/method/header `matches` filtering; outbound DLP scanning for known tokens and secrets, inbound DLP scanning for prompt-injection attempts; DoH and arbitrary hosts blocked by default.
|
||||
- **Per-route token-match policy** — each egress route picks what happens when the outbound DLP catches a token via `dlp.outbound_on_match`: `supervise` (default) holds the request and surfaces it in `./cli.py supervise` for approval (an approved value is remembered for the life of the proxy); `redact` scrubs the value and forwards; `block` is a hard `403`. Cuts false-positive friction without weakening default-deny.
|
||||
- **Tokens the agent never sees** — host secrets live in a sidecar; the agent dials `http://sidecar:9099/<path>` and the proxy strips inbound `Authorization` and injects the real token before forwarding. `printenv` in the agent shows proxy URLs only.
|
||||
- **Tokens the agent never sees** — host secrets live in a gateway; the agent dials `http://gateway:9099/<path>` and the proxy strips inbound `Authorization` and injects the real token before forwarding. `printenv` in the agent shows proxy URLs only.
|
||||
- **Gitleaks-scanned push (git-gate)** — `bottle.git` remotes route through a per-bottle `git daemon` that gitleaks-scans incoming refs pre-receive and forwards clean refs upstream over SSH. The agent never holds the upstream credential.
|
||||
- **Manifest-scoped skills + secrets** — each bottle declares its skills, env, git identity, remotes, and egress routes; unknown keys die at load.
|
||||
- **Trust boundary at `$HOME`** — bottles (credentials, egress, remotes) live only under `~/.bot-bottle/bottles/`. Repos may ship agents but not bottles, so a cloned repo can't redirect an env var to an attacker host.
|
||||
@@ -24,17 +24,17 @@
|
||||
- **Parallel, isolated bottles** — each bottle runs in its own backend-owned isolation boundary; bottles don't share state or talk to each other.
|
||||
- **Provider templates (Claude, Codex)** — `Dockerfile.claude` / `Dockerfile.codex`, or a bottle-supplied Dockerfile. Claude auth via long-lived OAuth token; Codex via opt-in host device-auth forwarding.
|
||||
- **gVisor auto-detect** — on Linux hosts where `runsc` is registered with Docker, every bottle launches under it for a userspace syscall barrier; no manifest config required.
|
||||
- **Apple Container backend (macOS default when available)** — runs the agent and sidecar bundle with Apple's `container` CLI, using a host-only agent network plus a separate sidecar egress network.
|
||||
- **Firecracker backend (Linux default when available)** — runs the agent in a KVM Firecracker microVM reached over SSH on a point-to-point TAP, with the sidecar bundle in Docker. A dedicated, fail-closed `nftables` table isolates the guest, closing the raw DNS/IP exfiltration gap that exists in the legacy Docker backend. Requires KVM (`/dev/kvm`) and a one-time privileged network-pool setup.
|
||||
- **Apple Container backend (macOS default when available)** — runs the agent and gateway with Apple's `container` CLI, using a host-only agent network plus a separate gateway egress network.
|
||||
- **Firecracker backend (Linux default when available)** — runs the agent in a KVM Firecracker microVM reached over SSH on a point-to-point TAP, with the gateway in Docker. A dedicated, fail-closed `nftables` table isolates the guest, closing the raw DNS/IP exfiltration gap that exists in the legacy Docker backend. Requires KVM (`/dev/kvm`) and a one-time privileged network-pool setup.
|
||||
- **Legacy Docker backend** — still available for examples, CI, and hosts without Apple Container or KVM via `BOT_BOTTLE_BACKEND=docker` or `--backend=docker`.
|
||||
|
||||
## Architecture
|
||||
|
||||
On the default macOS Apple Container backend, a bottle is an agent container on a host-only internal network plus a sidecar bundle attached to both that internal network and a NAT egress network. The agent gets HTTP(S)_PROXY and CA bundle env vars pointing at the sidecar's internal-network IP, so HTTP/HTTPS traffic flows through the sidecar instead of direct egress. `bottle.git` / git-gate is intentionally deferred on this backend until a safe Apple Container key-delivery path exists.
|
||||
On the default macOS Apple Container backend, a bottle is an agent container on a host-only internal network plus a gateway attached to both that internal network and a NAT egress network. The agent gets HTTP(S)_PROXY and CA bundle env vars pointing at the gateway's internal-network IP, so HTTP/HTTPS traffic flows through the gateway instead of direct egress. `bottle.git` / git-gate is intentionally deferred on this backend until a safe Apple Container key-delivery path exists.
|
||||
|
||||
On the Firecracker backend, a bottle is an agent microVM plus a Docker sidecar bundle for egress, git-gate, and supervise. The VM reaches the sidecars over a per-bottle point-to-point TAP link; a dedicated fail-closed `nftables` table (`inet bot_bottle_fc`) confines the guest to that link, so nothing leaves the box except through the sidecars. The TAP pool and nft table are provisioned once (root); per-launch needs no privilege.
|
||||
On the Firecracker backend, a bottle is an agent microVM plus a Docker gateway for egress, git-gate, and supervise. The VM reaches the gateway over a per-bottle point-to-point TAP link; a dedicated fail-closed `nftables` table (`inet bot_bottle_fc`) confines the guest to that link, so nothing leaves the box except through the gateway. The TAP pool and nft table are provisioned once (root); per-launch needs no privilege.
|
||||
|
||||
On the legacy Docker backend, the same logical bottle is two containers per agent: an `agent` container and a `sidecars` container. They share a per-agent Docker `--internal` network; the agent has no default route off-box.
|
||||
On the legacy Docker backend, the same logical bottle is two containers per agent: an `agent` container and a `companion containers` container. They share a per-agent Docker `--internal` network; the agent has no default route off-box.
|
||||
|
||||
The Docker topology looks like this:
|
||||
|
||||
@@ -67,11 +67,11 @@ The Docker topology looks like this:
|
||||
└─────────────────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
When the agent exits, `cli.py` tears down every sidecar and both networks; nothing about a bottle persists between runs.
|
||||
When the agent exits, `cli.py` tears down every gateway and both networks; nothing about a bottle persists between runs.
|
||||
|
||||
## Quickstart
|
||||
|
||||
On compatible macOS hosts, the default backend requires Apple's `container` CLI and does not require Docker. The Firecracker backend (Linux) requires Docker on the host for the sidecar bundle plus the `firecracker` binary and KVM. The legacy Docker backend requires Docker. Claude bottles also need a long-lived Claude Code OAuth token (`claude setup-token`) exported as `BOT_BOTTLE_CLAUDE_OAUTH_TOKEN`.
|
||||
On compatible macOS hosts, the default backend requires Apple's `container` CLI and does not require Docker. The Firecracker backend (Linux) requires Docker on the host for the gateway plus the `firecracker` binary and KVM. The legacy Docker backend requires Docker. Claude bottles also need a long-lived Claude Code OAuth token (`claude setup-token`) exported as `BOT_BOTTLE_CLAUDE_OAUTH_TOKEN`.
|
||||
|
||||
Use `BOT_BOTTLE_BACKEND=docker ./cli.py start <agent>` on hosts where neither Apple Container nor KVM is available and Docker is the desired backend.
|
||||
|
||||
@@ -81,7 +81,7 @@ On Linux, a KVM-capable host defaults to the Firecracker backend. It needs:
|
||||
|
||||
- **`/dev/kvm`** present and accessible. Load `kvm-intel` or `kvm-amd` (and enable virtualization in BIOS/firmware). The invoking user must be in the `kvm` group: `sudo usermod -aG kvm "$USER"` then re-login. bot-bottle preflights this and reports exactly what's missing.
|
||||
- **`firecracker`** on `PATH`: grab a release from <https://github.com/firecracker-microvm/firecracker/releases>. Start flows print this pointer when the binary is missing.
|
||||
- **Docker** for the sidecar bundle and image build.
|
||||
- **Docker** for the gateway and image build.
|
||||
- **A one-time privileged network setup** — the per-bottle TAP pool plus the fail-closed `nftables` isolation table. Run `./cli.py backend setup --backend=firecracker` for the host-appropriate config (a NixOS module, a `sudo` script elsewhere); `./cli.py backend status --backend=firecracker` reports what's present, including whether the pool range collides with an existing route. The pool defaults to `10.243.0.0/16` (an obscure RFC-1918 block that dodges docker/libvirt/LAN and, deliberately, Tailscale's `100.64.0.0/10` CGNAT range); override with `BOT_BOTTLE_FC_IP_BASE` if it clashes on your host.
|
||||
|
||||
```sh
|
||||
|
||||
@@ -61,6 +61,13 @@ class AgentProviderRuntime:
|
||||
prompt_mode: PromptMode
|
||||
bypass_args: tuple[str, ...]
|
||||
resume_args: tuple[str, ...]
|
||||
# argv run inside a throwaway container of a freshly built agent
|
||||
# image, right after `build_image()`, to catch a build that
|
||||
# exited 0 but produced a broken CLI (e.g. an npm
|
||||
# optionalDependencies fetch for a platform-native binary that
|
||||
# silently no-ops on a transient failure). Empty tuple skips the
|
||||
# check — not every provider has opted in yet.
|
||||
smoke_test: tuple[str, ...] = ()
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
@@ -204,9 +211,9 @@ class AgentProvider(ABC):
|
||||
bottle: "Bottle",
|
||||
supervise_url: str,
|
||||
) -> None:
|
||||
"""Register the per-bottle supervise sidecar as an MCP server
|
||||
"""Register the per-bottle supervise daemon as an MCP server
|
||||
in the provider's in-guest config. Called by the backend after
|
||||
the supervise sidecar is reachable. No-op when
|
||||
the supervise daemon is reachable. No-op when
|
||||
`plan.supervise_plan is None`."""
|
||||
|
||||
@abstractmethod
|
||||
|
||||
@@ -199,7 +199,7 @@ class ActiveAgent:
|
||||
bottle is the container, the agent is what runs in it.)
|
||||
|
||||
Fields are deliberately backend-neutral. `services` is the set
|
||||
of sidecar daemons currently up for this bottle (`egress`,
|
||||
of gateway daemons currently up for this bottle (`egress`,
|
||||
`git-gate`, `supervise`); the dashboard uses it to
|
||||
gate edit verbs. `backend_name` is the matching key in
|
||||
`_BACKENDS` (`docker` / `firecracker` / `macos-container`) — used by the active-
|
||||
@@ -251,7 +251,7 @@ class Bottle(ABC):
|
||||
`user` (default `node`, matching the agent image's USER
|
||||
directive) and return the captured stdout/stderr/returncode.
|
||||
The bottle's environment (including HTTPS_PROXY pointing at
|
||||
the egress sidecar) is inherited by the child. Non-zero
|
||||
the egress daemon) is inherited by the child. Non-zero
|
||||
exit does not raise — callers inspect `returncode`
|
||||
themselves.
|
||||
|
||||
@@ -454,7 +454,7 @@ class BottleBackend(ABC, Generic[PlanT, CleanupT]):
|
||||
declarative provision-plan apply, supervise MCP registration)
|
||||
live on the `AgentProvider` plugin. The backend only owns the
|
||||
steps that are about backend infrastructure (CA, workspace,
|
||||
git) and surfaces the supervise sidecar URL its launch step
|
||||
git) and surfaces the supervise daemon URL its launch step
|
||||
knows about via `supervise_mcp_url`.
|
||||
|
||||
PRD 0017: cred-proxy's agent-side dotfile rewrites (~/.npmrc,
|
||||
@@ -502,7 +502,7 @@ class BottleBackend(ABC, Generic[PlanT, CleanupT]):
|
||||
|
||||
def supervise_mcp_url(self, plan: PlanT) -> str:
|
||||
"""Return the agent-side URL of the per-bottle supervise
|
||||
sidecar, or "" when this bottle has no sidecar. The provider
|
||||
gateway, or "" when this bottle has no gateway. The provider
|
||||
plugin's `provision_supervise_mcp` uses it to register the
|
||||
MCP entry inside the guest.
|
||||
|
||||
@@ -524,7 +524,7 @@ class BottleBackend(ABC, Generic[PlanT, CleanupT]):
|
||||
def enumerate_active(self) -> Sequence[ActiveAgent]:
|
||||
"""Return every currently-running agent on this backend.
|
||||
Empty when none. Backend-specific: docker queries `docker
|
||||
compose ls`; firecracker cross-references its running sidecar
|
||||
compose ls`; firecracker cross-references its running gateway
|
||||
containers against per-bottle metadata."""
|
||||
|
||||
@classmethod
|
||||
|
||||
@@ -106,11 +106,16 @@ class DockerBottleBackend(BottleBackend["DockerBottlePlan", "DockerBottleCleanup
|
||||
yield bottle
|
||||
|
||||
def supervise_mcp_url(self, plan: DockerBottlePlan) -> str:
|
||||
"""Docker bottles reach the supervise sidecar via the
|
||||
"""Docker bottles reach the supervise daemon via the
|
||||
compose-network alias `supervise:9100`. No per-bottle URL
|
||||
plumbing needed; the alias resolves inside the bridge."""
|
||||
if plan.supervise_plan is None:
|
||||
return ""
|
||||
# Consolidated: the supervise daemon lives on the shared gateway, so
|
||||
# the agent registers the gateway address (NO_PROXY bypasses egress),
|
||||
# not the per-bottle `supervise` alias.
|
||||
if plan.agent_supervise_url:
|
||||
return plan.agent_supervise_url
|
||||
return f"http://{SUPERVISE_HOSTNAME}:{SUPERVISE_PORT}/"
|
||||
|
||||
def prepare_cleanup(self) -> DockerBottleCleanupPlan:
|
||||
|
||||
@@ -28,11 +28,30 @@ class DockerBottlePlan(BottlePlan):
|
||||
# accidental log of the plan dataclass.
|
||||
forwarded_env: dict[str, str] = field(repr=False)
|
||||
use_runsc: bool
|
||||
# Consolidated mode (PRD 0070): the agent reaches git-gate over HTTP at the
|
||||
# shared gateway's address (`http://<gateway_ip>:9420`), set at launch.
|
||||
# Empty → single-tenant defaults (the `git-gate` alias over git://).
|
||||
agent_git_gate_url: str = ""
|
||||
# Likewise the supervise MCP endpoint at the gateway (`http://<gw>:9100/`);
|
||||
# empty → the single-tenant `supervise` alias.
|
||||
agent_supervise_url: str = ""
|
||||
|
||||
@property
|
||||
def container_name(self) -> str:
|
||||
return self.agent_provision.instance_name
|
||||
|
||||
@property
|
||||
def git_gate_insteadof_host(self) -> str:
|
||||
if self.agent_git_gate_url.startswith("http://"):
|
||||
return self.agent_git_gate_url.removeprefix("http://").rstrip("/")
|
||||
return super().git_gate_insteadof_host
|
||||
|
||||
@property
|
||||
def git_gate_insteadof_scheme(self) -> str:
|
||||
if self.agent_git_gate_url.startswith("http://"):
|
||||
return "http"
|
||||
return super().git_gate_insteadof_scheme
|
||||
|
||||
@property
|
||||
def image(self) -> str:
|
||||
return self.agent_provision.image
|
||||
|
||||
@@ -1,20 +1,10 @@
|
||||
"""Compose-spec rendering for a Docker bottle (PRD 0018, chunk 1).
|
||||
"""Docker compose lifecycle helpers (PRD 0018).
|
||||
|
||||
`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.
|
||||
|
||||
Conditional services follow the plan content:
|
||||
|
||||
- agent + sidecars bundle: always.
|
||||
- git-gate: iff plan.git_gate_plan.upstreams.
|
||||
- egress: iff plan.egress_plan.routes.
|
||||
- supervise: iff plan.supervise_plan is not None.
|
||||
Serialize a compose spec to disk, drive `docker compose up/down`,
|
||||
dump the merged log on teardown, and enumerate `bot-bottle-*`
|
||||
projects. The spec itself is built by `consolidated_compose.py`
|
||||
(the consolidated per-host gateway topology); this module owns the
|
||||
I/O side that persists and runs it.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
@@ -25,233 +15,7 @@ import sys
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
from ...egress import (
|
||||
EGRESS_HOSTNAME,
|
||||
EGRESS_ROUTES_IN_CONTAINER,
|
||||
egress_agent_env_entries,
|
||||
egress_sidecar_env_entries,
|
||||
)
|
||||
from ...git_gate import GIT_GATE_HOSTNAME
|
||||
from ...log import die, warn
|
||||
from ...supervise import (
|
||||
DB_PATH_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_PORT,
|
||||
)
|
||||
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 . import network as network_mod
|
||||
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 (`git_gate_plan`,
|
||||
`egress_plan`, `supervise_plan`) populated with launch-time
|
||||
fields — network names, CA host paths. 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": network_mod.network_name_for_slug(plan.slug),
|
||||
"internal": True,
|
||||
},
|
||||
"egress": {
|
||||
"name": network_mod.network_egress_name_for_slug(plan.slug),
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
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 daemons under a Python init supervisor.
|
||||
|
||||
Daemon subset narrows via `BOT_BOTTLE_SIDECAR_DAEMONS` env.
|
||||
egress is always present; git-gate / supervise are conditional.
|
||||
"""
|
||||
daemons: list[str] = ["egress"]
|
||||
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]] = []
|
||||
|
||||
# --- egress -------------------------------------------------------
|
||||
ep = plan.egress_plan
|
||||
volumes.append(_bind(ep.mitmproxy_ca_host_path, EGRESS_CA_IN_CONTAINER))
|
||||
if ep.routes:
|
||||
volumes.append(_bind(ep.routes_path.parent, str(Path(EGRESS_ROUTES_IN_CONTAINER).parent)))
|
||||
env.extend(egress_sidecar_env_entries(ep))
|
||||
|
||||
# --- 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_DB_PATH={DB_PATH_IN_CONTAINER}",
|
||||
f"SUPERVISE_PORT={SUPERVISE_PORT}",
|
||||
]
|
||||
volumes.append({
|
||||
"type": "bind",
|
||||
"source": str(sp.db_path),
|
||||
"target": DB_PATH_IN_CONTAINER,
|
||||
"read_only": False,
|
||||
})
|
||||
internal_aliases = [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. HTTP_PROXY/HTTPS_PROXY point at the
|
||||
egress sidecar."""
|
||||
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)
|
||||
env.extend(egress_agent_env_entries(plan.egress_plan))
|
||||
|
||||
service: dict[str, Any] = {
|
||||
"image": plan.image,
|
||||
"container_name": plan.container_name,
|
||||
"command": ["sleep", "infinity"],
|
||||
"networks": {"internal": None},
|
||||
"environment": env,
|
||||
}
|
||||
if plan.use_runsc:
|
||||
service["runtime"] = "runsc"
|
||||
|
||||
# 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:
|
||||
"""Agent's HTTP_PROXY — always points at egress."""
|
||||
return f"http://{EGRESS_HOSTNAME}:{EGRESS_PORT}"
|
||||
|
||||
|
||||
def _agent_no_proxy(plan: DockerBottlePlan) -> str:
|
||||
"""NO_PROXY for the agent: loopback always; supervise hostname
|
||||
when the supervise sidecar is up (MCP long-poll must bypass
|
||||
the egress proxy)."""
|
||||
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) ----------------------------------
|
||||
@@ -442,7 +206,6 @@ __all__ = [
|
||||
"COMPOSE_FILE_NAME",
|
||||
"COMPOSE_LOG_NAME",
|
||||
"COMPOSE_PROJECT_PREFIX",
|
||||
"bottle_plan_to_compose",
|
||||
"compose_down",
|
||||
"compose_dump_logs",
|
||||
"compose_file_path",
|
||||
|
||||
@@ -0,0 +1,78 @@
|
||||
"""Agent-only compose for the consolidated docker backend (PRD 0070).
|
||||
|
||||
The per-bottle model rendered a compose project with the agent *and* a
|
||||
gateway on two per-bottle networks. In the consolidated model the
|
||||
per-bottle companion containers are gone — one shared gateway serves every bottle — so this renders
|
||||
just the agent, attached to the **external shared gateway network** with the
|
||||
pinned source IP the orchestrator allocated, and pointed at the gateway's
|
||||
address for egress (and, around the proxy, for git-http / supervise).
|
||||
|
||||
Pure: it takes the launch-time `LaunchContext` values (gateway address,
|
||||
source IP, network) and the prepared plan, and returns a compose dict — no
|
||||
docker, so it's testable in isolation.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any
|
||||
|
||||
from ...egress import egress_agent_env_entries
|
||||
from ..util import AGENT_CA_BUNDLE, AGENT_CA_PATH
|
||||
from .bottle_plan import DockerBottlePlan
|
||||
from .egress import EGRESS_PORT
|
||||
|
||||
|
||||
def consolidated_agent_compose(
|
||||
plan: DockerBottlePlan,
|
||||
*,
|
||||
gateway_ip: str,
|
||||
source_ip: str,
|
||||
network: str,
|
||||
) -> dict[str, Any]:
|
||||
"""A compose spec with only the agent service, on the external gateway
|
||||
network at `source_ip`, proxying egress through `gateway_ip`."""
|
||||
proxy_url = f"http://{gateway_ip}:{EGRESS_PORT}"
|
||||
# git-http + supervise live on the gateway too and must NOT go through the
|
||||
# egress proxy — the agent reaches them directly by the gateway address.
|
||||
no_proxy = f"localhost,127.0.0.1,{gateway_ip}"
|
||||
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: bare name → inherits from the compose-up process env so
|
||||
# the secret value never lands on argv or in the compose file.
|
||||
for name in sorted(plan.forwarded_env.keys()):
|
||||
env.append(name)
|
||||
env.extend(egress_agent_env_entries(plan.egress_plan))
|
||||
|
||||
service: dict[str, Any] = {
|
||||
"image": plan.image,
|
||||
"container_name": plan.container_name,
|
||||
"command": ["sleep", "infinity"],
|
||||
# Pinned address on the shared gateway network — the orchestrator
|
||||
# registered this IP, and the gateway attributes the bottle by it.
|
||||
"networks": {network: {"ipv4_address": source_ip}},
|
||||
"environment": env,
|
||||
}
|
||||
if plan.use_runsc:
|
||||
service["runtime"] = "runsc"
|
||||
|
||||
return {
|
||||
"name": f"bot-bottle-{plan.slug}",
|
||||
"services": {"agent": service},
|
||||
# The gateway network is created + owned by the orchestrator; compose
|
||||
# attaches to it (external) and must not create or destroy it.
|
||||
"networks": {network: {"external": True}},
|
||||
}
|
||||
|
||||
|
||||
__all__ = ["consolidated_agent_compose"]
|
||||
@@ -0,0 +1,153 @@
|
||||
"""Consolidated bottle launch sequence for the docker backend (PRD 0070).
|
||||
|
||||
Composes the orchestrator primitives into the register/teardown sequence that
|
||||
replaces the per-bottle gateway:
|
||||
|
||||
1. ensure the orchestrator control plane + shared gateway are up;
|
||||
2. allocate the bottle a pinned source IP on the gateway network (the
|
||||
attribution key), skipping the gateway's own address + live bottles;
|
||||
3. register it (egress policy blob + slug metadata) → bottle id + identity
|
||||
token;
|
||||
4. provision its git-gate repos/creds into the running gateway.
|
||||
|
||||
It returns a `LaunchContext` with everything the agent container needs to
|
||||
attach — network, pinned IP, the gateway's address (its proxy target), the
|
||||
orchestrator URL, and the identity token. The agent `docker run` itself is
|
||||
the backend's job (it owns provider provisioning); this owns the
|
||||
orchestrator-facing wiring so that sequence stays testable in isolation.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
|
||||
from ...docker_cmd import run_docker
|
||||
from ...egress import EgressPlan
|
||||
from ...git_gate import GitGatePlan
|
||||
from ...orchestrator.client import OrchestratorClient
|
||||
from ...orchestrator.gateway import GATEWAY_NAME, GATEWAY_NETWORK
|
||||
from ...orchestrator.lifecycle import OrchestratorService
|
||||
from ...orchestrator.registration import registration_inputs
|
||||
from .gateway_net import next_free_ip
|
||||
from .gateway_provision import deprovision_git_gate, provision_git_gate
|
||||
|
||||
|
||||
class ConsolidatedLaunchError(RuntimeError):
|
||||
"""The consolidated register/provision sequence could not complete."""
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class LaunchContext:
|
||||
"""What the agent container needs to join the shared gateway."""
|
||||
|
||||
bottle_id: str
|
||||
identity_token: str
|
||||
source_ip: str # the agent's pinned address (attribution key)
|
||||
network: str # the shared gateway network to attach to
|
||||
gateway_ip: str # the gateway's address — the agent's proxy target
|
||||
orchestrator_url: str
|
||||
|
||||
|
||||
def _network_cidr(network: str) -> str:
|
||||
"""The gateway network's IPv4 subnet, or raise."""
|
||||
proc = run_docker([
|
||||
"docker", "network", "inspect",
|
||||
"--format", "{{range .IPAM.Config}}{{.Subnet}}{{end}}", network,
|
||||
])
|
||||
cidr = proc.stdout.strip()
|
||||
if proc.returncode != 0 or not cidr:
|
||||
raise ConsolidatedLaunchError(
|
||||
f"gateway network {network} has no subnet: {proc.stderr.strip()}"
|
||||
)
|
||||
return cidr
|
||||
|
||||
|
||||
def _container_ip(name: str, network: str) -> str:
|
||||
"""A container's IPv4 address on `network`, or raise."""
|
||||
proc = run_docker([
|
||||
"docker", "inspect", "--format",
|
||||
f'{{{{(index .NetworkSettings.Networks "{network}").IPAddress}}}}', name,
|
||||
])
|
||||
ip = proc.stdout.strip()
|
||||
if proc.returncode != 0 or not ip:
|
||||
raise ConsolidatedLaunchError(
|
||||
f"gateway {name} has no address on {network}: {proc.stderr.strip()}"
|
||||
)
|
||||
return ip
|
||||
|
||||
|
||||
def _network_container_ips(network: str) -> list[str]:
|
||||
"""Every address currently assigned on the gateway network — the ground
|
||||
truth for "in use": the gateway + orchestrator infrastructure containers
|
||||
and every live agent. Read from the network so a new bottle can't collide
|
||||
with anything actually attached (a registry-only view would miss the
|
||||
orchestrator/gateway containers)."""
|
||||
proc = run_docker([
|
||||
"docker", "network", "inspect", "--format",
|
||||
"{{range .Containers}}{{.IPv4Address}} {{end}}", network,
|
||||
])
|
||||
ips: list[str] = []
|
||||
for entry in proc.stdout.split():
|
||||
# entries look like "172.20.0.2/16" — keep the address.
|
||||
ips.append(entry.split("/", 1)[0])
|
||||
return ips
|
||||
|
||||
|
||||
def launch_consolidated(
|
||||
egress_plan: EgressPlan,
|
||||
git_gate_plan: GitGatePlan,
|
||||
*,
|
||||
image_ref: str = "",
|
||||
tokens: dict[str, str] | None = None,
|
||||
service: OrchestratorService | None = None,
|
||||
gateway_name: str = GATEWAY_NAME,
|
||||
network: str = GATEWAY_NETWORK,
|
||||
) -> LaunchContext:
|
||||
"""Ensure the orchestrator + gateway are up, allocate + register the
|
||||
bottle, and provision its git-gate state. Returns the agent's attach
|
||||
context. Raises `ConsolidatedLaunchError` (or the primitives' own errors)
|
||||
if any step fails — the caller tears down on failure."""
|
||||
service = service or OrchestratorService()
|
||||
url = service.ensure_running()
|
||||
client = OrchestratorClient(url)
|
||||
|
||||
cidr = _network_cidr(network)
|
||||
gateway_ip = _container_ip(gateway_name, network)
|
||||
source_ip = next_free_ip(cidr, _network_container_ips(network))
|
||||
|
||||
inputs = registration_inputs(egress_plan)
|
||||
reg = client.register_bottle(
|
||||
source_ip, image_ref=image_ref, policy=inputs.policy,
|
||||
metadata=inputs.metadata, tokens=tokens,
|
||||
)
|
||||
try:
|
||||
provision_git_gate(gateway_name, reg.bottle_id, git_gate_plan)
|
||||
except Exception:
|
||||
# Roll the registration back so a provisioning failure leaves no orphan.
|
||||
client.teardown_bottle(reg.bottle_id)
|
||||
raise
|
||||
return LaunchContext(
|
||||
bottle_id=reg.bottle_id,
|
||||
identity_token=reg.identity_token,
|
||||
source_ip=source_ip,
|
||||
network=network,
|
||||
gateway_ip=gateway_ip,
|
||||
orchestrator_url=url,
|
||||
)
|
||||
|
||||
|
||||
def teardown_consolidated(
|
||||
bottle_id: str, *, orchestrator_url: str, gateway_name: str = GATEWAY_NAME,
|
||||
) -> None:
|
||||
"""Deregister the bottle and remove its git-gate state from the gateway.
|
||||
Both steps are idempotent so this is safe from a cleanup trap."""
|
||||
OrchestratorClient(orchestrator_url).teardown_bottle(bottle_id)
|
||||
deprovision_git_gate(gateway_name, bottle_id)
|
||||
|
||||
|
||||
__all__ = [
|
||||
"LaunchContext",
|
||||
"launch_consolidated",
|
||||
"teardown_consolidated",
|
||||
"ConsolidatedLaunchError",
|
||||
]
|
||||
@@ -4,7 +4,7 @@ prepare-time routes-yaml rendering itself lives on the
|
||||
platform-neutral `Egress` ABC — backends instantiate it directly.
|
||||
|
||||
The per-container `.start()` / `.stop()` lifecycle was removed in
|
||||
PRD 0024 chunk 3; the sidecar bundle (PRD 0024) runs egress
|
||||
PRD 0024 chunk 3; the gateway (PRD 0024) runs egress
|
||||
under its python init supervisor."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
@@ -1,60 +1,29 @@
|
||||
"""Host-side helper for egress sidecar inspection and live updates.
|
||||
"""Host-side egress route-apply for the docker backend.
|
||||
|
||||
The approve path uses this module to validate a proposed routes file,
|
||||
write it to the bottle's live egress state dir, and signal the sidecar
|
||||
bundle so the mitmproxy addon reloads it.
|
||||
The per-bottle companion container this used to signal (`docker kill
|
||||
--signal HUP <container>`) was removed in the companion-container removal (#385).
|
||||
In the consolidated model the shared gateway resolves egress policy
|
||||
per-request against the orchestrator rather than reloading a per-bottle
|
||||
routes file, so the live per-bottle reload is not supported here and
|
||||
fails closed until the gateway-side apply lands.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import subprocess
|
||||
|
||||
from ...egress import EGRESS_ROUTES_IN_CONTAINER
|
||||
from ...log import warn
|
||||
from ..egress_apply import EgressApplicator, EgressApplyError
|
||||
from .sidecar_bundle import sidecar_bundle_container_name
|
||||
|
||||
|
||||
def fetch_current_routes(slug: str) -> str:
|
||||
container = sidecar_bundle_container_name(slug)
|
||||
r = subprocess.run(
|
||||
["docker", "exec", container, "cat", EGRESS_ROUTES_IN_CONTAINER],
|
||||
capture_output=True, text=True, check=False,
|
||||
)
|
||||
if r.returncode != 0:
|
||||
raise EgressApplyError(
|
||||
f"could not read routes.yaml from {container}: "
|
||||
f"{(r.stderr or '').strip() or 'container not running?'}"
|
||||
)
|
||||
return r.stdout
|
||||
|
||||
|
||||
class DockerEgressApplicator(EgressApplicator):
|
||||
def _signal_bundle_reload(self, slug: str) -> None:
|
||||
container = sidecar_bundle_container_name(slug)
|
||||
result = subprocess.run(
|
||||
["docker", "kill", "--signal", "HUP", container],
|
||||
capture_output=True, text=True, check=False, env=os.environ,
|
||||
del slug
|
||||
raise EgressApplyError(
|
||||
"live egress route-apply was removed with the per-bottle "
|
||||
"companion container (#385); route changes will flow through "
|
||||
"the consolidated gateway in a follow-up."
|
||||
)
|
||||
if result.returncode != 0:
|
||||
last_error = (result.stderr or "").strip() or (result.stdout or "").strip()
|
||||
warn(
|
||||
f"egress: routes updated on disk for {slug}, but bundle reload failed: "
|
||||
f"{last_error or 'docker kill failed'}"
|
||||
)
|
||||
raise EgressApplyError(
|
||||
f"could not reload egress bundle {container}: "
|
||||
f"{last_error or 'docker kill failed'}"
|
||||
)
|
||||
|
||||
|
||||
applicator = DockerEgressApplicator()
|
||||
|
||||
|
||||
__all__ = [
|
||||
"DockerEgressApplicator",
|
||||
"EgressApplyError",
|
||||
"applicator",
|
||||
"fetch_current_routes",
|
||||
]
|
||||
__all__ = ["DockerEgressApplicator", "EgressApplyError", "applicator"]
|
||||
|
||||
@@ -0,0 +1,47 @@
|
||||
"""Shared-gateway source-IP allocation for the consolidated docker backend
|
||||
(PRD 0070).
|
||||
|
||||
In the consolidated model one gateway container serves every bottle over a
|
||||
single shared docker network, and each agent bottle attaches with a pinned,
|
||||
deterministic address that the gateway uses as its **attribution key**. This
|
||||
allocates those addresses from the network's subnet, skipping the reserved
|
||||
ones — the network address and broadcast (excluded by `hosts()`), docker's
|
||||
router `.1`, and everything already in use (`taken`: the gateway container
|
||||
plus every live bottle, which the caller reads from the registry).
|
||||
|
||||
Pure `ipaddress` logic — the docker-specific bits (the subnet CIDR, the
|
||||
gateway container's own address) are gathered by the caller and passed in, so
|
||||
this stays testable without docker.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import ipaddress
|
||||
from collections.abc import Iterable
|
||||
|
||||
|
||||
class NoFreeAddressError(RuntimeError):
|
||||
"""The shared gateway network's subnet is exhausted — every host address
|
||||
is reserved or already assigned to a bottle."""
|
||||
|
||||
|
||||
def next_free_ip(cidr: str, taken: Iterable[str]) -> str:
|
||||
"""The lowest host address in `cidr` not in `taken` and not docker's
|
||||
router (`.1`). `taken` must include the gateway container's own address
|
||||
and every live bottle's. Raises `NoFreeAddressError` if the subnet is
|
||||
full."""
|
||||
net = ipaddress.ip_network(cidr, strict=False)
|
||||
reserved = {str(a) for a in taken}
|
||||
# Docker assigns the network's first host (.1) to the bridge router; a
|
||||
# bottle must never be handed that address.
|
||||
reserved.add(str(net.network_address + 1))
|
||||
for host in net.hosts(): # hosts() already excludes network + broadcast
|
||||
candidate = str(host)
|
||||
if candidate not in reserved:
|
||||
return candidate
|
||||
raise NoFreeAddressError(
|
||||
f"no free address in {cidr} ({len(reserved)} reserved/assigned)"
|
||||
)
|
||||
|
||||
|
||||
__all__ = ["next_free_ip", "NoFreeAddressError"]
|
||||
@@ -0,0 +1,100 @@
|
||||
"""Provision one bottle's git-gate state into the running shared gateway
|
||||
(PRD 0070, docker slice).
|
||||
|
||||
The consolidated gateway serves every bottle's repos under `/git/<bottle_id>/`
|
||||
with per-repo credentials under `/git-gate/creds/<bottle_id>/`. When a bottle
|
||||
is registered the launcher must place *its* deploy keys + known_hosts into
|
||||
that per-bottle creds dir and init its bare repos there — so this copies the
|
||||
credential files into the live gateway container and runs the (namespaced,
|
||||
init-only) provisioning script produced by `git_gate_render_provision`.
|
||||
|
||||
Isolating each bottle's creds dir + repo root by id is what keeps one
|
||||
bottle's push credentials out of another's repos on the shared gateway.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import re
|
||||
|
||||
from ...docker_cmd import run_docker
|
||||
from ...git_gate import GitGatePlan, git_gate_render_provision
|
||||
|
||||
# bottle ids index the gateway's per-bottle repo + creds dirs; they land in
|
||||
# `docker cp`/`rm` path arguments, so validate before any path is built (a
|
||||
# traversal id like "../etc" must never reach the container). Registry ids are
|
||||
# token_hex — this is defense in depth at the docker boundary.
|
||||
_SAFE_BOTTLE_ID = re.compile(r"[A-Za-z0-9_-]+")
|
||||
|
||||
|
||||
class GatewayProvisionError(RuntimeError):
|
||||
"""A git-gate provisioning step against the running gateway failed."""
|
||||
|
||||
|
||||
def _require_safe(bottle_id: str) -> None:
|
||||
if not _SAFE_BOTTLE_ID.fullmatch(bottle_id):
|
||||
raise GatewayProvisionError(f"unsafe bottle id {bottle_id!r}")
|
||||
|
||||
|
||||
def _creds_dir(bottle_id: str) -> str:
|
||||
return f"/git-gate/creds/{bottle_id}"
|
||||
|
||||
|
||||
def _exec(gateway: str, argv: list[str]) -> None:
|
||||
"""`docker exec` a command in the gateway, raising on non-zero exit."""
|
||||
proc = run_docker(["docker", "exec", gateway, *argv])
|
||||
if proc.returncode != 0:
|
||||
raise GatewayProvisionError(
|
||||
f"gateway exec {argv!r} failed: {proc.stderr.strip()}"
|
||||
)
|
||||
|
||||
|
||||
def _cp_into(gateway: str, src: str, dest: str) -> None:
|
||||
"""`docker cp` a host file into the gateway, raising on non-zero exit."""
|
||||
proc = run_docker(["docker", "cp", src, f"{gateway}:{dest}"])
|
||||
if proc.returncode != 0:
|
||||
raise GatewayProvisionError(
|
||||
f"gateway cp {src} -> {dest} failed: {proc.stderr.strip()}"
|
||||
)
|
||||
|
||||
|
||||
def provision_git_gate(gateway: str, bottle_id: str, plan: GitGatePlan) -> None:
|
||||
"""Place `bottle_id`'s git-gate credentials into the running `gateway`
|
||||
container and init its bare repos under `/git/<bottle_id>/`.
|
||||
|
||||
Copies each upstream's identity key (and known_hosts, when present) into
|
||||
`/git-gate/creds/<bottle_id>/`, then runs the namespaced provisioning
|
||||
script. No-op for a bottle with no git upstreams."""
|
||||
_require_safe(bottle_id)
|
||||
if not plan.upstreams:
|
||||
return
|
||||
# The pre-receive + access hooks are bottle-agnostic and shared by every
|
||||
# bottle's repos; install them into the gateway (idempotent — same content
|
||||
# each time). The per-bottle model cp'd these into each bundle at start.
|
||||
_exec(gateway, ["mkdir", "-p", "/etc/git-gate"])
|
||||
_cp_into(gateway, str(plan.hook_script), "/etc/git-gate/pre-receive")
|
||||
_cp_into(gateway, str(plan.access_hook_script), "/etc/git-gate/access-hook")
|
||||
creds = _creds_dir(bottle_id)
|
||||
_exec(gateway, ["mkdir", "-p", creds])
|
||||
for u in plan.upstreams:
|
||||
if u.identity_file:
|
||||
_cp_into(gateway, u.identity_file, f"{creds}/{u.name}-key")
|
||||
known_hosts = str(u.known_hosts_file)
|
||||
if known_hosts and known_hosts != ".":
|
||||
_cp_into(gateway, known_hosts, f"{creds}/{u.name}-known_hosts")
|
||||
# Init the bare repos + per-repo credential config for this namespace.
|
||||
script = git_gate_render_provision(bottle_id, plan.upstreams)
|
||||
_exec(gateway, ["sh", "-c", script])
|
||||
|
||||
|
||||
def deprovision_git_gate(gateway: str, bottle_id: str) -> None:
|
||||
"""Remove a bottle's repos + creds from the gateway on teardown. Idempotent
|
||||
— an already-absent namespace is a clean no-op (best effort; a stray dir
|
||||
can't leak, since attribution is by source IP and the bottle is gone)."""
|
||||
_require_safe(bottle_id)
|
||||
run_docker([
|
||||
"docker", "exec", gateway, "rm", "-rf",
|
||||
f"/git/{bottle_id}", _creds_dir(bottle_id),
|
||||
])
|
||||
|
||||
|
||||
__all__ = ["provision_git_gate", "deprovision_git_gate", "GatewayProvisionError"]
|
||||
@@ -2,7 +2,7 @@
|
||||
bind-mounts target + the listening port. The prepare-time entrypoint
|
||||
/ hook render lives on the platform-neutral `GitGate` ABC — backends
|
||||
instantiate it directly. The git-gate daemon's container lifecycle
|
||||
is owned by the sidecar bundle (PRD 0024)."""
|
||||
is owned by the gateway (PRD 0024)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
|
||||
@@ -5,7 +5,7 @@ PRD 0018 chunk 3: each instance is one `docker compose` project.
|
||||
The flow is:
|
||||
|
||||
1. Build the agent image from the provider Dockerfile (compose
|
||||
builds the sidecar images via the `build:` directive on first up).
|
||||
builds the gateway image on first up).
|
||||
2. Mint the per-bottle egress CA (chunk 2 writes it under
|
||||
state/<slug>/egress/).
|
||||
3. Populate the inner plans with launch-time fields so the
|
||||
@@ -36,13 +36,13 @@ from contextlib import ExitStack, contextmanager
|
||||
from pathlib import Path
|
||||
from typing import Callable, Generator
|
||||
|
||||
from ...agent_provider import runtime_for
|
||||
from ...egress import egress_resolve_token_values
|
||||
from ...git_gate import (
|
||||
provision_git_gate_dynamic_keys,
|
||||
revoke_git_gate_provisioned_keys,
|
||||
)
|
||||
from ...log import info, warn
|
||||
from . import network as network_mod
|
||||
from . import util as docker_mod
|
||||
from .bottle import DockerBottle
|
||||
from .bottle_plan import DockerBottlePlan
|
||||
@@ -53,7 +53,6 @@ from ...bottle_state import (
|
||||
read_committed_image,
|
||||
)
|
||||
from .compose import (
|
||||
bottle_plan_to_compose,
|
||||
compose_down,
|
||||
compose_dump_logs,
|
||||
compose_file_path,
|
||||
@@ -62,7 +61,9 @@ from .compose import (
|
||||
compose_up,
|
||||
write_compose_file,
|
||||
)
|
||||
from .egress import egress_tls_init
|
||||
from .consolidated_compose import consolidated_agent_compose
|
||||
from .consolidated_launch import launch_consolidated, teardown_consolidated
|
||||
from ...orchestrator.gateway import DockerGateway
|
||||
|
||||
|
||||
# Where the repo root lives, for `docker build` context. Computed once.
|
||||
@@ -97,8 +98,7 @@ def launch(
|
||||
try:
|
||||
# Step 1: agent image. Use a committed snapshot when one exists
|
||||
# and is present in the local daemon; otherwise build from the
|
||||
# Dockerfile. Sidecar images get built lazily by `docker compose
|
||||
# up` via the renderer's `build:` directives.
|
||||
# Dockerfile. (The gateway image is built by the orchestrator.)
|
||||
committed = read_committed_image(plan.slug)
|
||||
if committed and docker_mod.image_exists(committed):
|
||||
info(f"using committed image {committed!r}")
|
||||
@@ -111,83 +111,86 @@ def launch(
|
||||
plan.image, _REPO_DIR,
|
||||
dockerfile=plan.dockerfile_path,
|
||||
)
|
||||
docker_mod.verify_agent_image(
|
||||
plan.image, runtime_for(plan.agent_provider_template).smoke_test,
|
||||
)
|
||||
|
||||
internal_network = network_mod.network_name_for_slug(plan.slug)
|
||||
egress_network = network_mod.network_egress_name_for_slug(plan.slug)
|
||||
|
||||
egress_ca_host, egress_ca_cert_only = egress_tls_init(
|
||||
egress_state_dir(plan.slug),
|
||||
)
|
||||
|
||||
# Step 2: mint the git-gate dynamic (gitea) deploy keys, if any, before
|
||||
# provisioning the bottle's repos into the shared gateway.
|
||||
git_gate_plan = plan.git_gate_plan
|
||||
if git_gate_plan.upstreams:
|
||||
git_gate_plan = provision_git_gate_dynamic_keys(
|
||||
plan.manifest.bottle,
|
||||
git_gate_plan,
|
||||
git_gate_state_dir(plan.slug),
|
||||
)
|
||||
git_gate_plan = dataclasses.replace(
|
||||
git_gate_plan,
|
||||
internal_network=internal_network,
|
||||
egress_network=egress_network,
|
||||
plan.manifest.bottle, git_gate_plan, git_gate_state_dir(plan.slug),
|
||||
)
|
||||
|
||||
# Step 3: register on the orchestrator + provision this bottle's
|
||||
# git-gate state into the shared gateway; get the agent's attach
|
||||
# context (pinned source IP, gateway address, shared network). The
|
||||
# per-bottle egress auth tokens are resolved from the host env now and
|
||||
# handed to the orchestrator (in memory) for the gateway to inject —
|
||||
# the agent never sees them.
|
||||
effective_env = {**os.environ, **plan.agent_provision.provisioned_env}
|
||||
token_values = egress_resolve_token_values(
|
||||
plan.egress_plan.token_env_map, effective_env,
|
||||
)
|
||||
ctx = launch_consolidated(
|
||||
plan.egress_plan, git_gate_plan, image_ref=plan.image, tokens=token_values,
|
||||
)
|
||||
stack.callback(
|
||||
teardown_consolidated, ctx.bottle_id, orchestrator_url=ctx.orchestrator_url,
|
||||
)
|
||||
|
||||
# Step 4: install the SHARED gateway CA into the agent (replaces the
|
||||
# per-bottle CA) — read it out of the running gateway.
|
||||
ca_dir = egress_state_dir(plan.slug) / "gateway-ca"
|
||||
ca_dir.mkdir(parents=True, exist_ok=True)
|
||||
ca_file = ca_dir / "gateway-ca.pem"
|
||||
ca_file.write_text(DockerGateway(network=ctx.network).ca_cert_pem())
|
||||
egress_plan = dataclasses.replace(
|
||||
plan.egress_plan,
|
||||
internal_network=internal_network,
|
||||
egress_network=egress_network,
|
||||
mitmproxy_ca_host_path=egress_ca_host,
|
||||
mitmproxy_ca_cert_only_host_path=egress_ca_cert_only,
|
||||
mitmproxy_ca_host_path=ca_file,
|
||||
mitmproxy_ca_cert_only_host_path=ca_file,
|
||||
)
|
||||
# Point the agent's git-gate insteadOf rewrites at the shared gateway's
|
||||
# HTTP git endpoint (9420) instead of the dead per-bottle `git-gate`
|
||||
# alias. git-http + supervise on the gateway bypass the egress proxy
|
||||
# (NO_PROXY includes the gateway address).
|
||||
git_gate_url = (
|
||||
f"http://{ctx.gateway_ip}:9420" if git_gate_plan.upstreams else ""
|
||||
)
|
||||
supervise_url = (
|
||||
f"http://{ctx.gateway_ip}:9100/" if plan.supervise_plan is not None else ""
|
||||
)
|
||||
supervise_plan = plan.supervise_plan
|
||||
if supervise_plan is not None:
|
||||
supervise_plan = dataclasses.replace(
|
||||
supervise_plan,
|
||||
internal_network=internal_network,
|
||||
)
|
||||
plan = dataclasses.replace(
|
||||
plan,
|
||||
git_gate_plan=git_gate_plan,
|
||||
egress_plan=egress_plan,
|
||||
supervise_plan=supervise_plan,
|
||||
agent_git_gate_url=git_gate_url,
|
||||
agent_supervise_url=supervise_url,
|
||||
)
|
||||
|
||||
# Step 6: render + write the compose file. metadata.json
|
||||
# was written at prepare time and already carries
|
||||
# compose_project; nothing to update here.
|
||||
# Step 5: render + up the agent-only compose, pinned on the shared
|
||||
# gateway network and proxied through the gateway's address.
|
||||
state_dir = bottle_state_dir(plan.slug)
|
||||
spec = bottle_plan_to_compose(plan)
|
||||
spec = consolidated_agent_compose(
|
||||
plan, gateway_ip=ctx.gateway_ip, source_ip=ctx.source_ip, network=ctx.network,
|
||||
)
|
||||
compose_file = write_compose_file(spec, compose_file_path(state_dir))
|
||||
project = compose_project_name(plan.slug)
|
||||
|
||||
# Step 7: compose up. Token values + the OAuth placeholder
|
||||
# flow through subprocess env; the compose file holds only
|
||||
# bare names for the secret-carrying entries.
|
||||
effective_env = {**dict(os.environ), **plan.agent_provision.provisioned_env}
|
||||
token_values = egress_resolve_token_values(
|
||||
plan.egress_plan.token_env_map, effective_env,
|
||||
)
|
||||
compose_env: dict[str, str] = {
|
||||
**os.environ,
|
||||
**plan.forwarded_env,
|
||||
**token_values,
|
||||
}
|
||||
# Forwarded vars (OAuth token, host interpolations) flow through the
|
||||
# subprocess env as bare names so values never land in the file.
|
||||
compose_env: dict[str, str] = {**os.environ, **plan.forwarded_env}
|
||||
info(
|
||||
f"docker compose up -d (project {project}, "
|
||||
f"{len(spec['services'])} services)"
|
||||
f"docker compose up -d (project {project}, agent on shared "
|
||||
f"gateway {ctx.gateway_ip}, ip {ctx.source_ip})"
|
||||
)
|
||||
compose_up(project, compose_file, env=compose_env)
|
||||
|
||||
# Register teardown in reverse order: log dump first, then
|
||||
# `compose down`. Networks come down last via callbacks
|
||||
# registered in step 2.
|
||||
stack.callback(compose_down, project, compose_file)
|
||||
stack.callback(
|
||||
compose_dump_logs, project, compose_file, compose_log_path(state_dir),
|
||||
)
|
||||
|
||||
# Step 8: provision. Create the bottle first so provisioners
|
||||
# can use bottle.exec / bottle.cp_in; set the prompt path
|
||||
# returned by provision_prompt after the fact.
|
||||
# Step 6: provision (CA install now uses the gateway CA) + yield.
|
||||
bottle = DockerBottle(
|
||||
plan.container_name,
|
||||
teardown,
|
||||
@@ -200,10 +203,6 @@ def launch(
|
||||
agent_workdir=plan.workspace_plan.workdir,
|
||||
)
|
||||
bottle.prompt_path = provision(plan, bottle)
|
||||
|
||||
# Step 9: yield. exec_agent continues to use `docker exec -it`
|
||||
# — the agent runs `sleep infinity` per the renderer's
|
||||
# service spec.
|
||||
yield bottle
|
||||
finally:
|
||||
teardown()
|
||||
|
||||
@@ -76,7 +76,7 @@ def network_create_internal(slug: str) -> str:
|
||||
|
||||
def network_create_egress(slug: str) -> str:
|
||||
"""Create a per-agent user-defined bridge (NOT the legacy `bridge`)
|
||||
so the egress sidecar has working DNS for upstream hostnames."""
|
||||
so the egress daemon has working DNS for upstream hostnames."""
|
||||
return _network_create_with_prefix(network_egress_name_for_slug(slug), internal=False)
|
||||
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
"""Host setup + status for the Docker backend.
|
||||
|
||||
Unlike Firecracker, the Docker backend needs no privileged one-time
|
||||
host provisioning (no TAP pool / nft table) — networks and the sidecar
|
||||
host provisioning (no TAP pool / nft table) — networks and the gateway
|
||||
bundle are created per-launch. So `setup()` is mostly an install/daemon
|
||||
pointer, and `status()` reports whether docker is usable.
|
||||
|
||||
@@ -45,7 +45,7 @@ def setup() -> int:
|
||||
return 1
|
||||
sys.stderr.write(
|
||||
"Docker backend: no privileged host setup required — networks and "
|
||||
"the sidecar bundle are created per-launch.\n"
|
||||
"the gateway are created per-launch.\n"
|
||||
)
|
||||
if not _daemon_reachable():
|
||||
sys.stderr.write(
|
||||
@@ -64,7 +64,7 @@ def setup() -> int:
|
||||
def teardown() -> int:
|
||||
sys.stderr.write(
|
||||
"Docker backend: nothing to undo — it provisions no privileged host "
|
||||
"state (networks and the sidecar bundle are per-launch and are "
|
||||
"state (networks and the gateway are per-launch and are "
|
||||
"removed by `./cli.py cleanup`). Docker itself is left installed.\n"
|
||||
)
|
||||
return 0
|
||||
|
||||
@@ -1,30 +0,0 @@
|
||||
"""Sidecar bundle constants + helpers for the Docker backend
|
||||
(PRD 0024).
|
||||
|
||||
The bundle image (built by Dockerfile.sidecars, PRD 0024 chunk 1)
|
||||
runs egress + git-gate + supervise as one container per bottle
|
||||
under a small Python init supervisor. As of chunk 5 the bundle
|
||||
is the only shape — the legacy four-sidecar topology and its
|
||||
`BOT_BOTTLE_SIDECAR_BUNDLE` feature flag are gone."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
|
||||
|
||||
# Bundle image. Defaults to a built-locally tag (built from the
|
||||
# repo's Dockerfile.sidecars via compose `build:`). Operators
|
||||
# pinning to a published digest can override via env.
|
||||
SIDECAR_BUNDLE_IMAGE = os.environ.get(
|
||||
"BOT_BOTTLE_SIDECAR_IMAGE",
|
||||
"bot-bottle-sidecars:latest",
|
||||
)
|
||||
|
||||
SIDECAR_BUNDLE_DOCKERFILE = "Dockerfile.sidecars"
|
||||
|
||||
|
||||
def sidecar_bundle_container_name(slug: str) -> str:
|
||||
"""`bot-bottle-sidecars-<slug>`. Same prefix scheme as the
|
||||
per-sidecar containers it replaces, so the dashboard's
|
||||
discovery-by-prefix logic keeps working."""
|
||||
return f"bot-bottle-sidecars-{slug}"
|
||||
@@ -4,11 +4,13 @@ existence, and building images."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import re
|
||||
import shutil
|
||||
import subprocess
|
||||
from typing import Iterable, Iterator
|
||||
|
||||
from ...docker_cmd import run_docker
|
||||
from ...log import die, info
|
||||
# from ...workspace import WorkspacePlan
|
||||
|
||||
@@ -88,6 +90,29 @@ def docker_exec_root(container: str, argv: list[str]) -> None:
|
||||
)
|
||||
|
||||
|
||||
def docker_exec(container: str, argv: list[str], *, user: str = "") -> None:
|
||||
"""Run `docker exec` in the named container, dying with the
|
||||
command's own stderr on failure. Pass `user=\"0\"` to run as root."""
|
||||
cmd = ["docker", "exec"]
|
||||
if user:
|
||||
cmd += ["-u", user]
|
||||
cmd += [container, *argv]
|
||||
result = run_docker(cmd)
|
||||
if result.returncode != 0:
|
||||
die(
|
||||
f"docker exec in {container} failed: "
|
||||
f"{(result.stderr or '').strip() or '<no stderr>'}"
|
||||
)
|
||||
|
||||
|
||||
def docker_cp(src: str, dest: str) -> None:
|
||||
"""Run `docker cp`, dying with the command's own stderr on failure."""
|
||||
result = run_docker(["docker", "cp", src, dest])
|
||||
if result.returncode != 0:
|
||||
die(f"docker cp {src} -> {dest} failed: "
|
||||
f"{(result.stderr or '').strip() or '<no stderr>'}")
|
||||
|
||||
|
||||
_SLUG_RE = re.compile(r"[^a-z0-9]+")
|
||||
|
||||
|
||||
@@ -108,15 +133,40 @@ def build_image(ref: str, context: str, *, dockerfile: str = "") -> None:
|
||||
|
||||
`dockerfile` is an optional path (relative to `context`, or
|
||||
absolute) for callers that need to build from a non-default
|
||||
Dockerfile in the same context — e.g. `Dockerfile.git-gate`."""
|
||||
Dockerfile in the same context — e.g. `Dockerfile.git-gate`.
|
||||
|
||||
Set `BOT_BOTTLE_NO_CACHE=1` (the `start --no-cache` flag) to force
|
||||
`--no-cache`. The npm/curl installers some provider Dockerfiles
|
||||
shell out to can silently no-op on a transient network failure —
|
||||
e.g. an `optionalDependencies` fetch for a platform-native binary —
|
||||
and Docker will then cache that broken layer indefinitely."""
|
||||
info(f"building image {ref} from {context} (layer cache keeps repeat builds fast)")
|
||||
args = ["docker", "build", "-t", ref]
|
||||
if os.environ.get("BOT_BOTTLE_NO_CACHE") == "1":
|
||||
args.append("--no-cache")
|
||||
if dockerfile:
|
||||
args.extend(["-f", dockerfile])
|
||||
args.append(context)
|
||||
subprocess.run(args, check=True)
|
||||
|
||||
|
||||
def verify_agent_image(image: str, argv: tuple[str, ...]) -> None:
|
||||
"""Run `argv` inside a throwaway container of a freshly built agent
|
||||
image and die loudly if it fails, instead of shipping an image
|
||||
whose CLI only breaks at first real use. No-op when the provider
|
||||
hasn't declared a smoke test (`AgentProviderRuntime.smoke_test`)."""
|
||||
if not argv:
|
||||
return
|
||||
result = run_docker(["docker", "run", "--rm", "--entrypoint", argv[0], image, *argv[1:]])
|
||||
if result.returncode != 0:
|
||||
detail = (result.stderr or result.stdout or "").strip()
|
||||
die(
|
||||
f"agent image {image!r} failed its post-build smoke test "
|
||||
f"({' '.join(argv)}): {detail}\n"
|
||||
f"Try rebuilding from scratch: bot-bottle start --no-cache"
|
||||
)
|
||||
|
||||
|
||||
# def build_image_with_cwd(
|
||||
# derived: str,
|
||||
# base: str,
|
||||
|
||||
@@ -7,7 +7,7 @@ session. `ssh -t` forwards the host terminal's SIGWINCH to the remote
|
||||
PTY natively, so no separate resize bridge is needed.
|
||||
|
||||
Commands run as the image's `node` user via `runuser`, with HOME/USER/
|
||||
PATH and the bottle env (HTTPS_PROXY at the sidecar, CA paths, …) set
|
||||
PATH and the bottle env (HTTPS_PROXY at the gateway, CA paths, …) set
|
||||
per-invocation through `env` (the VM itself just runs the init; it has
|
||||
no baked-in process env like a `docker run` container would).
|
||||
"""
|
||||
|
||||
@@ -10,10 +10,9 @@ from .. import BottleCleanupPlan
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class FirecrackerBottleCleanupPlan(BottleCleanupPlan):
|
||||
# PIDs of orphaned firecracker VMM processes and the sidecar
|
||||
# containers left behind by previous bottles.
|
||||
# PIDs of orphaned firecracker VMM processes and the per-bottle run
|
||||
# dirs left behind by previous bottles.
|
||||
vm_pids: tuple[int, ...] = ()
|
||||
containers: tuple[str, ...] = ()
|
||||
run_dirs: tuple[str, ...] = ()
|
||||
|
||||
def print(self) -> None:
|
||||
@@ -22,11 +21,9 @@ class FirecrackerBottleCleanupPlan(BottleCleanupPlan):
|
||||
return
|
||||
for pid in self.vm_pids:
|
||||
info(f"firecracker VM process: pid {pid}")
|
||||
for name in self.containers:
|
||||
info(f"firecracker sidecar container: {name}")
|
||||
for path in self.run_dirs:
|
||||
info(f"firecracker run dir: {path}")
|
||||
|
||||
@property
|
||||
def empty(self) -> bool:
|
||||
return not (self.vm_pids or self.containers or self.run_dirs)
|
||||
return not (self.vm_pids or self.run_dirs)
|
||||
|
||||
@@ -13,7 +13,7 @@ from .. import BottlePlan
|
||||
class FirecrackerBottlePlan(BottlePlan):
|
||||
slug: str
|
||||
forwarded_env: dict[str, str] = field(repr=False)
|
||||
# Stamped by launch once the sidecar is up and its ports are
|
||||
# Stamped by launch once the gateway is up and its ports are
|
||||
# published on the host-side TAP IP (empty at prepare time).
|
||||
agent_proxy_url: str = ""
|
||||
agent_git_gate_url: str = ""
|
||||
@@ -21,7 +21,7 @@ class FirecrackerBottlePlan(BottlePlan):
|
||||
|
||||
@property
|
||||
def container_name(self) -> str:
|
||||
"""Instance name, reused for the sidecar container + VM run dir.
|
||||
"""Instance name, reused for the gateway container + VM run dir.
|
||||
Matches the `bot-bottle-<slug>` convention the other backends
|
||||
use so cleanup/enumerate discovery-by-prefix keeps working."""
|
||||
return self.agent_provision.instance_name
|
||||
|
||||
@@ -1,9 +1,8 @@
|
||||
"""Cleanup for the Firecracker backend.
|
||||
|
||||
Orphans are: firecracker VMM processes whose config lives under our run
|
||||
dir, the `bot-bottle-sidecars-*` containers, and the per-bottle run
|
||||
dirs. TAP slots free themselves (the flock drops when the launcher
|
||||
exits), so there is nothing to reclaim there.
|
||||
dir, and the per-bottle run dirs. TAP slots free themselves (the flock
|
||||
drops when the launcher exits), so there is nothing to reclaim there.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
@@ -18,8 +17,6 @@ from ...log import info
|
||||
from . import util
|
||||
from .bottle_cleanup_plan import FirecrackerBottleCleanupPlan
|
||||
|
||||
_SIDECAR_PREFIX = "bot-bottle-sidecars-"
|
||||
|
||||
|
||||
def _run_root() -> Path:
|
||||
return util.cache_dir() / "run"
|
||||
@@ -46,17 +43,6 @@ def _orphan_vm_pids() -> list[int]:
|
||||
return pids
|
||||
|
||||
|
||||
def _sidecar_containers() -> list[str]:
|
||||
result = subprocess.run(
|
||||
["docker", "ps", "-a", "--format", "{{.Names}}",
|
||||
"--filter", f"name={_SIDECAR_PREFIX}"],
|
||||
capture_output=True, text=True, check=False,
|
||||
)
|
||||
if result.returncode != 0:
|
||||
return []
|
||||
return sorted(n.strip() for n in result.stdout.splitlines() if n.strip())
|
||||
|
||||
|
||||
def _run_dirs() -> list[str]:
|
||||
run_root = _run_root()
|
||||
if not run_root.is_dir():
|
||||
@@ -67,7 +53,6 @@ def _run_dirs() -> list[str]:
|
||||
def prepare_cleanup() -> FirecrackerBottleCleanupPlan:
|
||||
return FirecrackerBottleCleanupPlan(
|
||||
vm_pids=tuple(_orphan_vm_pids()),
|
||||
containers=tuple(_sidecar_containers()),
|
||||
run_dirs=tuple(_run_dirs()),
|
||||
)
|
||||
|
||||
@@ -79,12 +64,6 @@ def cleanup(plan: FirecrackerBottleCleanupPlan) -> None:
|
||||
os.kill(pid, signal.SIGTERM)
|
||||
except ProcessLookupError:
|
||||
pass
|
||||
for name in plan.containers:
|
||||
info(f"docker rm -f {name}")
|
||||
subprocess.run(
|
||||
["docker", "rm", "-f", name],
|
||||
stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False,
|
||||
)
|
||||
for path in plan.run_dirs:
|
||||
info(f"rm -rf {path}")
|
||||
shutil.rmtree(path, ignore_errors=True)
|
||||
|
||||
@@ -0,0 +1,164 @@
|
||||
"""Consolidated bottle launch sequence for the Firecracker backend (PRD 0070).
|
||||
|
||||
Mirrors bot_bottle.backend.docker.consolidated_launch but wired for
|
||||
Firecracker's TAP-based network topology instead of a shared Docker bridge.
|
||||
|
||||
The per-bottle sidecar bundle (one `docker run` per bottle, published on the
|
||||
slot's host-side TAP IP) is replaced by a single persistent gateway that
|
||||
every Firecracker VM shares. The gateway runs as a Docker container in the
|
||||
dev-harness (a Firecracker VM is stage B per PRD 0070), with its ports
|
||||
published on the host (`0.0.0.0:PORT`). VMs reach it at their slot's
|
||||
host-side TAP IP because Docker's iptables PREROUTING DNAT redirects
|
||||
port 9099/9100/9420 traffic to the gateway container — a path the nft
|
||||
isolation table already allows via `ct status dnat accept` in the forward
|
||||
chain.
|
||||
|
||||
Attribution is by the VM's guest IP, which is unspoofable by construction:
|
||||
the /31 point-to-point TAP topology + the `bot_bottle_fc` nft table ensure
|
||||
that only the expected VM can source-IP that address.
|
||||
|
||||
Sequence:
|
||||
1. ensure the Firecracker-flavoured orchestrator + gateway are up;
|
||||
2. register the bottle by its guest IP (attribution key) → bottle id +
|
||||
identity token;
|
||||
3. provision its git-gate repos/creds into the running gateway;
|
||||
4. fetch the shared gateway CA for the provisioner to install in the rootfs.
|
||||
|
||||
The TAP slot allocation, rootfs build, and VM boot are the caller's job.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
|
||||
from ...egress import EgressPlan
|
||||
from ...git_gate import GitGatePlan
|
||||
from ...orchestrator.client import OrchestratorClient
|
||||
from ...orchestrator.gateway import (
|
||||
GATEWAY_NETWORK,
|
||||
DockerGateway,
|
||||
)
|
||||
from ...orchestrator.lifecycle import (
|
||||
OrchestratorService,
|
||||
OrchestratorStartError, # re-exported so callers can catch it
|
||||
)
|
||||
from ...orchestrator.registration import registration_inputs
|
||||
from ..docker.egress import EGRESS_PORT
|
||||
from ..docker.gateway_provision import deprovision_git_gate, provision_git_gate
|
||||
from ...supervise import SUPERVISE_PORT
|
||||
|
||||
_GIT_HTTP_PORT = 9420
|
||||
|
||||
# Separate names from the Docker gateway so both backends can coexist on one
|
||||
# host (and for clarity in `docker ps` output).
|
||||
_FC_GATEWAY_NAME = "bot-bottle-fc-gateway"
|
||||
_FC_ORCHESTRATOR_NAME = "bot-bottle-fc-orchestrator"
|
||||
_FC_ORCHESTRATOR_LABEL = "bot-bottle-fc-orchestrator=1"
|
||||
# Ports the gateway publishes on the host so Firecracker VMs can reach it
|
||||
# via their TAP link. Docker's PREROUTING DNAT + nft's `ct status dnat
|
||||
# accept` in the forward chain route the traffic.
|
||||
_FC_GATEWAY_HOST_PORTS = (EGRESS_PORT, SUPERVISE_PORT, _GIT_HTTP_PORT)
|
||||
|
||||
|
||||
class ConsolidatedLaunchError(RuntimeError):
|
||||
"""The consolidated register/provision sequence could not complete."""
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class LaunchContext:
|
||||
"""What the Firecracker launch needs from the consolidated sequence."""
|
||||
|
||||
bottle_id: str
|
||||
identity_token: str
|
||||
source_ip: str # the VM's guest IP — the attribution key
|
||||
gateway_ca_pem: str # the shared gateway CA the provisioner installs
|
||||
orchestrator_url: str
|
||||
|
||||
|
||||
class _FirecrackerOrchestratorService(OrchestratorService):
|
||||
"""Dev-harness orchestrator for the Firecracker backend.
|
||||
|
||||
Uses a gateway that publishes its ports on the host so Firecracker VMs can
|
||||
reach it via their TAP link. The gateway and orchestrator containers use
|
||||
`*-fc-*` names so both backends can run independently on the same host.
|
||||
"""
|
||||
|
||||
def __init__(self, **kwargs: object) -> None:
|
||||
super().__init__(
|
||||
orchestrator_name=_FC_ORCHESTRATOR_NAME,
|
||||
orchestrator_label=_FC_ORCHESTRATOR_LABEL,
|
||||
**kwargs, # type: ignore[arg-type]
|
||||
)
|
||||
|
||||
def _gateway(self) -> DockerGateway:
|
||||
# The heavy data-plane image (#384 split it from the lean control-plane
|
||||
# `image` this service's orchestrator container runs).
|
||||
return DockerGateway(
|
||||
self._gateway_image,
|
||||
name=_FC_GATEWAY_NAME,
|
||||
network=self.network,
|
||||
orchestrator_url=self.internal_url,
|
||||
host_port_bindings=_FC_GATEWAY_HOST_PORTS,
|
||||
)
|
||||
|
||||
|
||||
def launch_consolidated(
|
||||
egress_plan: EgressPlan,
|
||||
git_gate_plan: GitGatePlan,
|
||||
*,
|
||||
guest_ip: str,
|
||||
image_ref: str = "",
|
||||
tokens: dict[str, str] | None = None,
|
||||
service: OrchestratorService | None = None,
|
||||
gateway_name: str = _FC_GATEWAY_NAME,
|
||||
) -> LaunchContext:
|
||||
"""Ensure the orchestrator + Firecracker gateway are up, register the
|
||||
bottle by its guest IP, and provision its git-gate state. Returns the
|
||||
context the VM launch needs. Raises `ConsolidatedLaunchError` (or the
|
||||
primitives' own errors) on failure — the caller tears down on failure."""
|
||||
service = service or _FirecrackerOrchestratorService()
|
||||
url = service.ensure_running()
|
||||
client = OrchestratorClient(url)
|
||||
|
||||
inputs = registration_inputs(egress_plan)
|
||||
reg = client.register_bottle(
|
||||
guest_ip, image_ref=image_ref, policy=inputs.policy,
|
||||
metadata=inputs.metadata, tokens=tokens,
|
||||
)
|
||||
try:
|
||||
provision_git_gate(gateway_name, reg.bottle_id, git_gate_plan)
|
||||
except Exception:
|
||||
client.teardown_bottle(reg.bottle_id)
|
||||
raise
|
||||
|
||||
# Fetch the shared gateway CA here so the caller can install it in the
|
||||
# rootfs (the same CA every agent on this host trusts for TLS interception).
|
||||
gateway_ca_pem = DockerGateway(
|
||||
name=gateway_name, network=GATEWAY_NETWORK,
|
||||
).ca_cert_pem()
|
||||
|
||||
return LaunchContext(
|
||||
bottle_id=reg.bottle_id,
|
||||
identity_token=reg.identity_token,
|
||||
source_ip=guest_ip,
|
||||
gateway_ca_pem=gateway_ca_pem,
|
||||
orchestrator_url=url,
|
||||
)
|
||||
|
||||
|
||||
def teardown_consolidated(
|
||||
bottle_id: str, *, orchestrator_url: str, gateway_name: str = _FC_GATEWAY_NAME,
|
||||
) -> None:
|
||||
"""Deregister the bottle and remove its git-gate state from the gateway.
|
||||
Both steps are idempotent so this is safe from a cleanup trap."""
|
||||
OrchestratorClient(orchestrator_url).teardown_bottle(bottle_id)
|
||||
deprovision_git_gate(gateway_name, bottle_id)
|
||||
|
||||
|
||||
__all__ = [
|
||||
"LaunchContext",
|
||||
"launch_consolidated",
|
||||
"teardown_consolidated",
|
||||
"ConsolidatedLaunchError",
|
||||
"OrchestratorStartError",
|
||||
]
|
||||
@@ -1,43 +1,14 @@
|
||||
"""Active-agent enumeration for the Firecracker backend.
|
||||
|
||||
The agent runs in a VM (no container to list), so a live bottle is
|
||||
identified by its running sidecar container `bot-bottle-sidecars-<slug>`
|
||||
— the same discovery-by-prefix the other backends use.
|
||||
The backend is disabled during the companion-container removal (#385) — it can't
|
||||
launch bottles, so there are none to enumerate. Real enumeration returns
|
||||
with the backend's consolidated relaunch (#354).
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import subprocess
|
||||
|
||||
from ...bottle_state import read_metadata
|
||||
from .. import ActiveAgent
|
||||
|
||||
_SIDECAR_PREFIX = "bot-bottle-sidecars-"
|
||||
|
||||
|
||||
def enumerate_active() -> list[ActiveAgent]:
|
||||
result = subprocess.run(
|
||||
["docker", "ps", "--format", "{{.Names}}",
|
||||
"--filter", f"name={_SIDECAR_PREFIX}"],
|
||||
capture_output=True, text=True, check=False,
|
||||
)
|
||||
if result.returncode != 0:
|
||||
return []
|
||||
out: list[ActiveAgent] = []
|
||||
for name in sorted(n.strip() for n in result.stdout.splitlines() if n.strip()):
|
||||
slug = name[len(_SIDECAR_PREFIX):]
|
||||
metadata = read_metadata(slug)
|
||||
if metadata is None or metadata.backend != "firecracker":
|
||||
# Skip sidecars owned by another backend (docker shares the
|
||||
# container-name prefix).
|
||||
continue
|
||||
out.append(ActiveAgent(
|
||||
backend_name="firecracker",
|
||||
slug=slug,
|
||||
agent_name=metadata.agent_name,
|
||||
started_at=metadata.started_at,
|
||||
services=(),
|
||||
label=metadata.label,
|
||||
color=metadata.color,
|
||||
))
|
||||
return out
|
||||
return []
|
||||
|
||||
@@ -1,75 +1,64 @@
|
||||
"""Launch flow for the Firecracker backend.
|
||||
"""Launch flow for the Firecracker backend (PRD 0070, consolidated).
|
||||
|
||||
Per bottle:
|
||||
1. mint the egress CA, build the agent image (docker), export it to a
|
||||
cached ext4 rootfs;
|
||||
2. claim a free TAP pool slot (rootless flock);
|
||||
3. bring up the Docker sidecar bundle, publishing egress / git-gate /
|
||||
supervise on the slot's host-side TAP IP at fixed ports;
|
||||
4. boot the microVM on that TAP; wait for SSH;
|
||||
5. provision (CA, prompt, skills, workspace, git, supervise) over SSH.
|
||||
1. build the agent image (docker), export it to a cached ext4 rootfs;
|
||||
2. ensure the per-host orchestrator + shared gateway are up;
|
||||
3. claim a free TAP pool slot (rootless flock);
|
||||
4. register the bottle on the orchestrator by the VM's guest IP (the
|
||||
attribution key) and provision its git-gate state into the gateway;
|
||||
5. boot the microVM on that TAP; wait for SSH;
|
||||
6. provision (shared gateway CA, prompt, skills, workspace, git, supervise)
|
||||
over SSH.
|
||||
|
||||
The per-bottle Docker sidecar bundle is gone. The shared gateway handles
|
||||
egress / git-gate / supervise for every VM; Docker's PREROUTING DNAT routes
|
||||
the VMs' traffic to it, and the nft table's `ct status dnat accept` rule
|
||||
in the forward chain lets it pass. The VM still sends to `host_tap_ip:PORT`
|
||||
— the address its world is, by nft design, limited to.
|
||||
|
||||
Isolation is enforced by the operator-provisioned nft table (checked
|
||||
fail-closed in preflight): a VM reaches only its sidecar (DNAT'd from
|
||||
the host TAP IP) and nothing else. The agent's HTTPS_PROXY therefore
|
||||
points at `http://<host_tap_ip>:9099`, its only route to the world.
|
||||
fail-closed in preflight): a VM reaches only the sidecar (DNAT'd from
|
||||
the host TAP IP) and nothing else.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import dataclasses
|
||||
import os
|
||||
import subprocess
|
||||
from contextlib import ExitStack, contextmanager
|
||||
from pathlib import Path
|
||||
from typing import Callable, Generator
|
||||
|
||||
from ...agent_provider import runtime_for
|
||||
from ...bottle_state import (
|
||||
egress_state_dir,
|
||||
git_gate_state_dir,
|
||||
read_committed_image,
|
||||
)
|
||||
from ...egress import (
|
||||
EGRESS_ROUTES_IN_CONTAINER,
|
||||
egress_agent_env_entries,
|
||||
egress_resolve_token_values,
|
||||
egress_sidecar_env_entries,
|
||||
)
|
||||
from ...git_gate import (
|
||||
provision_git_gate_dynamic_keys,
|
||||
revoke_git_gate_provisioned_keys,
|
||||
)
|
||||
from ...log import die, info, warn
|
||||
from ...supervise import DB_PATH_IN_CONTAINER, SUPERVISE_PORT
|
||||
from ...util import expand_tilde
|
||||
from ..docker.egress import (
|
||||
EGRESS_CA_IN_CONTAINER,
|
||||
EGRESS_PORT,
|
||||
egress_tls_init,
|
||||
)
|
||||
from ..docker.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 ..docker.sidecar_bundle import (
|
||||
SIDECAR_BUNDLE_DOCKERFILE,
|
||||
SIDECAR_BUNDLE_IMAGE,
|
||||
)
|
||||
from ...log import info, warn
|
||||
from ...supervise import SUPERVISE_PORT
|
||||
from ..docker import util as docker_mod
|
||||
from ..docker.egress import EGRESS_PORT
|
||||
from ..util import AGENT_CA_BUNDLE, AGENT_CA_PATH
|
||||
from . import firecracker_vm, isolation_probe, netpool, util
|
||||
from .bottle import FirecrackerBottle
|
||||
from .bottle_plan import FirecrackerBottlePlan
|
||||
from .consolidated_launch import (
|
||||
launch_consolidated,
|
||||
teardown_consolidated,
|
||||
)
|
||||
|
||||
|
||||
_REPO_DIR = str(Path(__file__).resolve().parent.parent.parent.parent)
|
||||
_GIT_HTTP_PORT = 9420
|
||||
_GIT_GATE_READY_FILE = "/run/git-gate/ready"
|
||||
|
||||
|
||||
def sidecar_container_name(slug: str) -> str:
|
||||
return f"bot-bottle-sidecars-{slug}"
|
||||
|
||||
|
||||
@contextmanager
|
||||
@@ -78,6 +67,8 @@ def launch(
|
||||
*,
|
||||
provision: Callable[[FirecrackerBottlePlan, "FirecrackerBottle"], str | None],
|
||||
) -> Generator[FirecrackerBottle, None, None]:
|
||||
"""Build, launch, and provision a Firecracker bottle via the consolidated
|
||||
orchestrator. Teardown on exit."""
|
||||
stack = ExitStack()
|
||||
bottle_for_revoke = plan.manifest.bottle
|
||||
git_gate_dir_for_revoke = git_gate_state_dir(plan.slug)
|
||||
@@ -94,26 +85,75 @@ def launch(
|
||||
raise teardown_exc
|
||||
|
||||
try:
|
||||
plan = _mint_certs(plan)
|
||||
# Step 1: agent image. The sidecar bundle image is built by the
|
||||
# orchestrator service (ensure_running → ensure_built); we only
|
||||
# build the agent image here. Use a committed snapshot when available.
|
||||
plan = _build_agent_image(plan)
|
||||
|
||||
# Claim a TAP slot; the flock is held until teardown closes it.
|
||||
# Step 2: mint the git-gate dynamic (gitea) deploy keys, if any.
|
||||
git_gate_plan = plan.git_gate_plan
|
||||
if git_gate_plan.upstreams:
|
||||
git_gate_plan = provision_git_gate_dynamic_keys(
|
||||
plan.manifest.bottle, git_gate_plan, git_gate_state_dir(plan.slug),
|
||||
)
|
||||
|
||||
# Step 3: claim a TAP slot; the flock is held until teardown.
|
||||
slot, lock = netpool.allocate(plan.slug)
|
||||
stack.callback(lock.close)
|
||||
info(f"firecracker slot {slot.iface}: host={slot.host_ip} "
|
||||
f"guest={slot.guest_ip}")
|
||||
|
||||
plan = _provision_git_gate_keys(plan)
|
||||
# Step 4: register on the orchestrator + provision this bottle's
|
||||
# git-gate state into the shared gateway. The per-bottle egress tokens
|
||||
# are resolved from the host env now and handed to the orchestrator
|
||||
# (in memory) for the gateway to inject — the agent never sees them.
|
||||
# Attribution is by the VM's guest IP (unspoofable via /31 TAP + nft).
|
||||
effective_env = {**os.environ, **plan.agent_provision.provisioned_env}
|
||||
token_values = egress_resolve_token_values(
|
||||
plan.egress_plan.token_env_map, effective_env,
|
||||
)
|
||||
ctx = launch_consolidated(
|
||||
plan.egress_plan, git_gate_plan,
|
||||
guest_ip=slot.guest_ip,
|
||||
image_ref=plan.image,
|
||||
tokens=token_values,
|
||||
)
|
||||
stack.callback(
|
||||
teardown_consolidated, ctx.bottle_id,
|
||||
orchestrator_url=ctx.orchestrator_url,
|
||||
)
|
||||
|
||||
sidecar_name = sidecar_container_name(plan.slug)
|
||||
_force_remove_container(sidecar_name)
|
||||
_start_sidecar_bundle(plan, sidecar_name, slot.host_ip)
|
||||
stack.callback(_force_remove_container, sidecar_name)
|
||||
_stage_git_gate(plan, sidecar_name)
|
||||
# Step 5: install the SHARED gateway CA (replaces the per-bottle CA).
|
||||
# Write it to a stable host path so the provisioner can copy it over SSH.
|
||||
ca_dir = egress_state_dir(plan.slug) / "gateway-ca"
|
||||
ca_dir.mkdir(parents=True, exist_ok=True)
|
||||
ca_file = ca_dir / "gateway-ca.pem"
|
||||
ca_file.write_text(ctx.gateway_ca_pem)
|
||||
egress_plan = dataclasses.replace(
|
||||
plan.egress_plan,
|
||||
mitmproxy_ca_host_path=ca_file,
|
||||
mitmproxy_ca_cert_only_host_path=ca_file,
|
||||
)
|
||||
# Point the agent's git-gate insteadOf rewrites and supervise MCP URL
|
||||
# at the shared gateway (reached at the slot's host TAP IP — the VM
|
||||
# sends there and Docker DNAT routes to the gateway container).
|
||||
git_gate_url = (
|
||||
f"http://{slot.host_ip}:{_GIT_HTTP_PORT}" if git_gate_plan.upstreams else ""
|
||||
)
|
||||
supervise_url = (
|
||||
f"http://{slot.host_ip}:{SUPERVISE_PORT}/"
|
||||
if plan.supervise_plan is not None else ""
|
||||
)
|
||||
plan = dataclasses.replace(
|
||||
plan,
|
||||
git_gate_plan=git_gate_plan,
|
||||
egress_plan=egress_plan,
|
||||
agent_proxy_url=f"http://{slot.host_ip}:{EGRESS_PORT}",
|
||||
agent_git_gate_url=git_gate_url,
|
||||
agent_supervise_url=supervise_url,
|
||||
)
|
||||
|
||||
plan = _stamp_agent_urls(plan, slot.host_ip)
|
||||
|
||||
# Build the per-bottle rootfs + SSH key, then boot.
|
||||
# Step 6: build the per-bottle rootfs + SSH key, then boot.
|
||||
base_dir = util.build_base_rootfs_dir(plan.image)
|
||||
run_dir = util.cache_dir() / "run" / plan.slug
|
||||
run_dir.mkdir(parents=True, exist_ok=True)
|
||||
@@ -133,8 +173,8 @@ def launch(
|
||||
stack.callback(vm.terminate)
|
||||
firecracker_vm.wait_for_ssh(vm, private_key)
|
||||
|
||||
# Authoritative fail-closed egress-boundary check, before the
|
||||
# agent runs: prove the VM cannot reach the host directly.
|
||||
# Authoritative fail-closed egress-boundary check, before the agent
|
||||
# runs: prove the VM cannot reach the host directly.
|
||||
isolation_probe.verify_isolation(private_key, slot.guest_ip)
|
||||
|
||||
bottle = FirecrackerBottle(
|
||||
@@ -159,171 +199,21 @@ def launch(
|
||||
teardown()
|
||||
|
||||
|
||||
def _mint_certs(plan: FirecrackerBottlePlan) -> FirecrackerBottlePlan:
|
||||
egress_ca_host, egress_ca_cert_only = egress_tls_init(egress_state_dir(plan.slug))
|
||||
egress_plan = dataclasses.replace(
|
||||
plan.egress_plan,
|
||||
mitmproxy_ca_host_path=egress_ca_host,
|
||||
mitmproxy_ca_cert_only_host_path=egress_ca_cert_only,
|
||||
)
|
||||
return dataclasses.replace(plan, egress_plan=egress_plan)
|
||||
|
||||
|
||||
def _build_agent_image(plan: FirecrackerBottlePlan) -> FirecrackerBottlePlan:
|
||||
_docker_build(SIDECAR_BUNDLE_IMAGE, _REPO_DIR, dockerfile=SIDECAR_BUNDLE_DOCKERFILE)
|
||||
committed = read_committed_image(plan.slug)
|
||||
if committed and _image_exists(committed):
|
||||
if committed and docker_mod.image_exists(committed):
|
||||
info(f"using committed image {committed!r}")
|
||||
return dataclasses.replace(
|
||||
plan,
|
||||
agent_provision=dataclasses.replace(plan.agent_provision, image=committed),
|
||||
)
|
||||
_docker_build(plan.image, _REPO_DIR, dockerfile=plan.dockerfile_path)
|
||||
docker_mod.build_image(plan.image, _REPO_DIR, dockerfile=plan.dockerfile_path)
|
||||
docker_mod.verify_agent_image(
|
||||
plan.image, runtime_for(plan.agent_provider_template).smoke_test,
|
||||
)
|
||||
return plan
|
||||
|
||||
|
||||
def _provision_git_gate_keys(plan: FirecrackerBottlePlan) -> FirecrackerBottlePlan:
|
||||
if not plan.git_gate_plan.upstreams:
|
||||
return plan
|
||||
git_gate_plan = provision_git_gate_dynamic_keys(
|
||||
plan.manifest.bottle, plan.git_gate_plan, git_gate_state_dir(plan.slug),
|
||||
)
|
||||
return dataclasses.replace(plan, git_gate_plan=git_gate_plan)
|
||||
|
||||
|
||||
def _stamp_agent_urls(
|
||||
plan: FirecrackerBottlePlan, host_ip: str,
|
||||
) -> FirecrackerBottlePlan:
|
||||
proxy_url = f"http://{host_ip}:{EGRESS_PORT}"
|
||||
supervise_url = (
|
||||
f"http://{host_ip}:{SUPERVISE_PORT}/" if plan.supervise_plan is not None else ""
|
||||
)
|
||||
git_gate_url = (
|
||||
f"http://{host_ip}:{_GIT_HTTP_PORT}" if plan.git_gate_plan.upstreams else ""
|
||||
)
|
||||
return dataclasses.replace(
|
||||
plan,
|
||||
agent_proxy_url=proxy_url,
|
||||
agent_git_gate_url=git_gate_url,
|
||||
agent_supervise_url=supervise_url,
|
||||
)
|
||||
|
||||
|
||||
# --- sidecar bundle (Docker) ----------------------------------------
|
||||
|
||||
def _start_sidecar_bundle(
|
||||
plan: FirecrackerBottlePlan, sidecar_name: str, host_ip: str,
|
||||
) -> None:
|
||||
argv = ["docker", "run", "--name", sidecar_name, "--detach", "--rm",
|
||||
"-e", f"BOT_BOTTLE_SIDECAR_DAEMONS={','.join(_sidecar_daemons(plan))}"]
|
||||
for entry in _sidecar_env_entries(plan):
|
||||
argv += ["-e", entry]
|
||||
for host_path, container_path, read_only in _sidecar_mounts(plan):
|
||||
argv += ["-v", f"{host_path}:{container_path}{':ro' if read_only else ''}"]
|
||||
# Publish on the slot's host TAP IP at fixed ports — each bottle
|
||||
# has a distinct host_ip, so fixed ports never collide, and the VM
|
||||
# reaches them at a stable, well-known address (its only route out).
|
||||
for port in _sidecar_ports(plan):
|
||||
argv += ["-p", f"{host_ip}:{port}:{port}"]
|
||||
argv.append(SIDECAR_BUNDLE_IMAGE)
|
||||
|
||||
effective_env = {**dict(os.environ), **plan.agent_provision.provisioned_env}
|
||||
token_values = egress_resolve_token_values(
|
||||
plan.egress_plan.token_env_map, effective_env,
|
||||
)
|
||||
env = {**os.environ, **token_values}
|
||||
info(f"docker run sidecar bundle {sidecar_name} (published on {host_ip})")
|
||||
result = subprocess.run(argv, capture_output=True, text=True, env=env, check=False)
|
||||
if result.returncode != 0:
|
||||
die(f"docker run for sidecar bundle {sidecar_name} failed: "
|
||||
f"{(result.stderr or '').strip() or '<no stderr>'}")
|
||||
|
||||
|
||||
def _sidecar_daemons(plan: FirecrackerBottlePlan) -> tuple[str, ...]:
|
||||
daemons = ["egress"]
|
||||
if plan.git_gate_plan.upstreams:
|
||||
daemons += ["git-gate", "git-http"]
|
||||
if plan.supervise_plan is not None:
|
||||
daemons.append("supervise")
|
||||
return tuple(daemons)
|
||||
|
||||
|
||||
def _sidecar_ports(plan: FirecrackerBottlePlan) -> tuple[int, ...]:
|
||||
ports = [EGRESS_PORT]
|
||||
if plan.git_gate_plan.upstreams:
|
||||
ports.append(_GIT_HTTP_PORT)
|
||||
if plan.supervise_plan is not None:
|
||||
ports.append(SUPERVISE_PORT)
|
||||
return tuple(ports)
|
||||
|
||||
|
||||
def _sidecar_env_entries(plan: FirecrackerBottlePlan) -> tuple[str, ...]:
|
||||
env: list[str] = list(egress_sidecar_env_entries(plan.egress_plan))
|
||||
if plan.git_gate_plan.upstreams:
|
||||
env.append(f"BOT_BOTTLE_GIT_GATE_READY_FILE={_GIT_GATE_READY_FILE}")
|
||||
if plan.supervise_plan is not None:
|
||||
env += [
|
||||
f"SUPERVISE_BOTTLE_SLUG={plan.slug}",
|
||||
f"SUPERVISE_DB_PATH={DB_PATH_IN_CONTAINER}",
|
||||
f"SUPERVISE_PORT={SUPERVISE_PORT}",
|
||||
]
|
||||
return tuple(env)
|
||||
|
||||
|
||||
def _sidecar_mounts(
|
||||
plan: FirecrackerBottlePlan,
|
||||
) -> tuple[tuple[str, str, bool], ...]:
|
||||
mounts: list[tuple[str, str, bool]] = []
|
||||
ep = plan.egress_plan
|
||||
mounts.append((str(ep.mitmproxy_ca_host_path.parent),
|
||||
str(Path(EGRESS_CA_IN_CONTAINER).parent), False))
|
||||
if ep.routes:
|
||||
mounts.append((str(ep.routes_path.parent),
|
||||
str(Path(EGRESS_ROUTES_IN_CONTAINER).parent), True))
|
||||
sp = plan.supervise_plan
|
||||
if sp is not None:
|
||||
mounts.append((str(sp.db_path.parent),
|
||||
str(Path(DB_PATH_IN_CONTAINER).parent), False))
|
||||
return tuple(mounts)
|
||||
|
||||
|
||||
def _stage_git_gate(plan: FirecrackerBottlePlan, sidecar_name: str) -> None:
|
||||
gp = plan.git_gate_plan
|
||||
if not gp.upstreams:
|
||||
return
|
||||
_docker_exec(sidecar_name, [
|
||||
"mkdir", "-p",
|
||||
str(Path(GIT_GATE_HOOK_IN_CONTAINER).parent),
|
||||
GIT_GATE_CREDS_DIR_IN_CONTAINER, "/git",
|
||||
str(Path(_GIT_GATE_READY_FILE).parent),
|
||||
])
|
||||
for host_path, container_path in _git_gate_files(plan):
|
||||
_docker_cp(host_path, f"{sidecar_name}:{container_path}")
|
||||
_docker_exec(sidecar_name, [
|
||||
"sh", "-c",
|
||||
f"chmod 755 {GIT_GATE_ENTRYPOINT_IN_CONTAINER} "
|
||||
f"{GIT_GATE_HOOK_IN_CONTAINER} {GIT_GATE_ACCESS_HOOK_IN_CONTAINER} && "
|
||||
f"chmod 600 {GIT_GATE_CREDS_DIR_IN_CONTAINER}/* && "
|
||||
f"touch {_GIT_GATE_READY_FILE}",
|
||||
])
|
||||
|
||||
|
||||
def _git_gate_files(plan: FirecrackerBottlePlan) -> tuple[tuple[str, str], ...]:
|
||||
gp = plan.git_gate_plan
|
||||
files: list[tuple[str, str]] = [
|
||||
(str(gp.entrypoint_script), GIT_GATE_ENTRYPOINT_IN_CONTAINER),
|
||||
(str(gp.hook_script), GIT_GATE_HOOK_IN_CONTAINER),
|
||||
(str(gp.access_hook_script), GIT_GATE_ACCESS_HOOK_IN_CONTAINER),
|
||||
]
|
||||
for upstream in gp.upstreams:
|
||||
files.append((expand_tilde(upstream.identity_file),
|
||||
f"{GIT_GATE_CREDS_DIR_IN_CONTAINER}/{upstream.name}-key"))
|
||||
if upstream.known_hosts_file:
|
||||
files.append((str(upstream.known_hosts_file),
|
||||
f"{GIT_GATE_CREDS_DIR_IN_CONTAINER}/{upstream.name}-known_hosts"))
|
||||
return tuple(files)
|
||||
|
||||
|
||||
# --- agent guest env -------------------------------------------------
|
||||
|
||||
def _agent_guest_env(plan: FirecrackerBottlePlan, host_ip: str) -> dict[str, str]:
|
||||
@@ -355,50 +245,3 @@ def _agent_guest_env(plan: FirecrackerBottlePlan, host_ip: str) -> dict[str, str
|
||||
if value is not None:
|
||||
env[name] = value
|
||||
return env
|
||||
|
||||
|
||||
# --- docker helpers --------------------------------------------------
|
||||
|
||||
def _docker_build(ref: str, context: str, *, dockerfile: str = "") -> None:
|
||||
info(f"docker build {ref}")
|
||||
args = ["docker", "build", "-t", ref]
|
||||
if dockerfile:
|
||||
if not os.path.isabs(dockerfile):
|
||||
dockerfile = os.path.join(context, dockerfile)
|
||||
args += ["-f", dockerfile]
|
||||
args.append(context)
|
||||
result = subprocess.run(args, check=False)
|
||||
if result.returncode != 0:
|
||||
die(f"docker build for {ref!r} failed")
|
||||
|
||||
|
||||
def _image_exists(ref: str) -> bool:
|
||||
return subprocess.run(
|
||||
["docker", "image", "inspect", ref],
|
||||
stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False,
|
||||
).returncode == 0
|
||||
|
||||
|
||||
def _force_remove_container(name: str) -> None:
|
||||
subprocess.run(
|
||||
["docker", "rm", "-f", name],
|
||||
stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False,
|
||||
)
|
||||
|
||||
|
||||
def _docker_exec(name: str, argv: list[str]) -> None:
|
||||
result = subprocess.run(
|
||||
["docker", "exec", name, *argv], capture_output=True, text=True, check=False,
|
||||
)
|
||||
if result.returncode != 0:
|
||||
die(f"docker exec in {name} failed: "
|
||||
f"{(result.stderr or '').strip() or '<no stderr>'}")
|
||||
|
||||
|
||||
def _docker_cp(host_path: str, dest: str) -> None:
|
||||
result = subprocess.run(
|
||||
["docker", "cp", host_path, dest], capture_output=True, text=True, check=False,
|
||||
)
|
||||
if result.returncode != 0:
|
||||
die(f"docker cp {host_path} -> {dest} failed: "
|
||||
f"{(result.stderr or '').strip() or '<no stderr>'}")
|
||||
|
||||
@@ -18,7 +18,7 @@ Topology (per slot i):
|
||||
* a /31 host<->guest link: host = base + 2i (the gateway the VM
|
||||
routes through), guest = base + 2i + 1 (the VM's address).
|
||||
* isolation via ``table inet bot_bottle_fc``: a VM reaches only its
|
||||
own sidecar (DNAT'd from the host TAP IP) and nothing else.
|
||||
own gateway (DNAT'd from the host TAP IP) and nothing else.
|
||||
|
||||
The default IP block is ``10.243.0.0/16`` — an intentionally obscure
|
||||
corner of RFC-1918 private space. RFC-1918 is the range *designated*
|
||||
@@ -88,10 +88,10 @@ def ip_base() -> str:
|
||||
return _cfg("BOT_BOTTLE_FC_IP_BASE")
|
||||
|
||||
|
||||
# Sidecar ports the VM reaches at its host-side TAP IP. Kept in sync
|
||||
# Gateway ports the VM reaches at its host-side TAP IP. Kept in sync
|
||||
# with the backend constants (egress 9099, supervise 9100, git-http
|
||||
# 9420); rendered into the setup output for operator visibility.
|
||||
SIDECAR_PORTS = (9099, 9100, 9420)
|
||||
GATEWAY_PORTS = (9099, 9100, 9420)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
Selectable via `BOT_BOTTLE_BACKEND=macos-container`. This package owns
|
||||
the Apple `container` CLI integration; launch remains gated until the
|
||||
sidecar network enforcement shape is implemented.
|
||||
gateway network enforcement shape is implemented.
|
||||
"""
|
||||
|
||||
from .backend import MacosContainerBottleBackend
|
||||
|
||||
@@ -9,7 +9,6 @@ from . import util as container_mod
|
||||
from .bottle_cleanup_plan import MacosContainerBottleCleanupPlan
|
||||
|
||||
_PREFIX = "bot-bottle-"
|
||||
_BUNDLE_PREFIX = "bot-bottle-sidecars-"
|
||||
|
||||
|
||||
def _list_prefixed_containers() -> list[str]:
|
||||
@@ -24,7 +23,7 @@ def _list_prefixed_containers() -> list[str]:
|
||||
return []
|
||||
return sorted(
|
||||
name for name in (line.strip() for line in result.stdout.splitlines())
|
||||
if name.startswith(_PREFIX) or name.startswith(_BUNDLE_PREFIX)
|
||||
if name.startswith(_PREFIX)
|
||||
)
|
||||
|
||||
|
||||
|
||||
@@ -1,36 +1,24 @@
|
||||
"""Host-side egress apply for the macos-container backend.
|
||||
"""Host-side egress route-apply for the macos-container backend.
|
||||
|
||||
Uses `container kill --signal HUP` (Apple Container framework) instead
|
||||
of `docker kill` to signal the sidecar bundle.
|
||||
The per-bottle companion container this used to signal (`container kill
|
||||
--signal HUP <container>`) was removed in the companion-container removal (#385),
|
||||
along with the disabled macOS launch path. Fails closed until the macOS
|
||||
backend grows the consolidated gateway.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import subprocess
|
||||
|
||||
from ...log import warn
|
||||
from ..egress_apply import EgressApplicator, EgressApplyError
|
||||
from .launch import sidecar_container_name
|
||||
|
||||
|
||||
class MacOSContainerEgressApplicator(EgressApplicator):
|
||||
def _signal_bundle_reload(self, slug: str) -> None:
|
||||
container = sidecar_container_name(slug)
|
||||
result = subprocess.run(
|
||||
["container", "kill", "--signal", "HUP", container],
|
||||
capture_output=True, text=True, check=False, env=os.environ,
|
||||
del slug
|
||||
raise EgressApplyError(
|
||||
"live egress route-apply was removed with the per-bottle "
|
||||
"companion container (#385); the macos-container backend is "
|
||||
"disabled until it uses the consolidated gateway."
|
||||
)
|
||||
if result.returncode != 0:
|
||||
last_error = (result.stderr or "").strip() or (result.stdout or "").strip()
|
||||
warn(
|
||||
f"egress: routes updated on disk for {slug}, but bundle reload failed: "
|
||||
f"{last_error or 'container kill failed'}"
|
||||
)
|
||||
raise EgressApplyError(
|
||||
f"could not reload egress bundle {container}: "
|
||||
f"{last_error or 'container kill failed'}"
|
||||
)
|
||||
|
||||
|
||||
applicator = MacOSContainerEgressApplicator()
|
||||
|
||||
@@ -1,40 +1,14 @@
|
||||
"""Active-agent enumeration for the macOS Apple Container backend."""
|
||||
"""Active-agent enumeration for the macOS Apple Container backend.
|
||||
|
||||
The backend is disabled during the companion-container removal (#385) — it can't
|
||||
launch bottles, so there are none to enumerate. Enumeration returns when
|
||||
the backend grows the consolidated gateway.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import subprocess
|
||||
|
||||
from ...bottle_state import read_metadata
|
||||
from .. import ActiveAgent
|
||||
|
||||
_PREFIX = "bot-bottle-"
|
||||
_SIDECAR_PREFIX = "bot-bottle-sidecars-"
|
||||
|
||||
|
||||
def enumerate_active() -> list[ActiveAgent]:
|
||||
result = subprocess.run(
|
||||
["container", "list", "--quiet"],
|
||||
capture_output=True,
|
||||
text=True,
|
||||
check=False,
|
||||
)
|
||||
if result.returncode != 0:
|
||||
return []
|
||||
out: list[ActiveAgent] = []
|
||||
for name in sorted(line.strip() for line in result.stdout.splitlines()):
|
||||
if not name.startswith(_PREFIX):
|
||||
continue
|
||||
if name.startswith(_SIDECAR_PREFIX):
|
||||
continue
|
||||
slug = name[len(_PREFIX):]
|
||||
metadata = read_metadata(slug)
|
||||
out.append(ActiveAgent(
|
||||
backend_name="macos-container",
|
||||
slug=slug,
|
||||
agent_name=metadata.agent_name if metadata else "?",
|
||||
started_at=metadata.started_at if metadata else "",
|
||||
services=(),
|
||||
label=metadata.label if metadata else "",
|
||||
color=metadata.color if metadata else "",
|
||||
))
|
||||
return out
|
||||
return []
|
||||
|
||||
@@ -1,458 +1,39 @@
|
||||
"""Launch flow for the macOS Apple Container backend.
|
||||
"""Launch flow for the macOS Apple Container backend — disabled (#385).
|
||||
|
||||
This backend keeps the explicit proxy-env enforcement model for v1:
|
||||
the agent container is attached only to a host-only Apple Container
|
||||
network, while the sidecar bundle is attached to a NAT network first
|
||||
and the host-only network second. The sidecar's host-only IP is
|
||||
discovered from `container inspect` and stamped into the agent's
|
||||
HTTP_PROXY / HTTPS_PROXY env vars.
|
||||
This backend launched a per-bottle companion container (the egress /
|
||||
git-gate / supervise data plane) alongside the agent container, with the
|
||||
agent's proxy env pointed at the companion's host-only IP. That
|
||||
per-bottle-companion architecture was removed in the companion-container removal;
|
||||
the macOS backend will be re-enabled once it grows the consolidated
|
||||
per-host gateway the docker backend already uses.
|
||||
|
||||
Until then, launching a macOS bottle fails closed. `prepare` / `status`
|
||||
/ cleanup still work.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import dataclasses
|
||||
import os
|
||||
import subprocess
|
||||
from contextlib import ExitStack, contextmanager
|
||||
from pathlib import Path
|
||||
from contextlib import contextmanager
|
||||
from typing import Callable, Generator
|
||||
|
||||
from ...bottle_state import (
|
||||
egress_state_dir,
|
||||
git_gate_state_dir,
|
||||
read_committed_image,
|
||||
)
|
||||
from ...egress import (
|
||||
EGRESS_ROUTES_IN_CONTAINER,
|
||||
egress_agent_env_entries,
|
||||
egress_resolve_token_values,
|
||||
egress_sidecar_env_entries,
|
||||
)
|
||||
from ...git_gate import (
|
||||
provision_git_gate_dynamic_keys,
|
||||
revoke_git_gate_provisioned_keys,
|
||||
)
|
||||
from ...log import die, info, warn
|
||||
from ...supervise import DB_PATH_IN_CONTAINER, SUPERVISE_PORT
|
||||
from ...util import expand_tilde
|
||||
from ..docker.egress import EGRESS_CA_IN_CONTAINER, EGRESS_PORT
|
||||
from ..docker.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 ..docker.sidecar_bundle import (
|
||||
SIDECAR_BUNDLE_DOCKERFILE,
|
||||
SIDECAR_BUNDLE_IMAGE,
|
||||
)
|
||||
from ..docker.egress import egress_tls_init
|
||||
from ..util import AGENT_CA_BUNDLE, AGENT_CA_PATH
|
||||
from . import util as container_mod
|
||||
from ...log import die
|
||||
from .bottle import MacosContainerBottle
|
||||
from .bottle_plan import MacosContainerBottlePlan
|
||||
|
||||
|
||||
_REPO_DIR = str(Path(__file__).resolve().parent.parent.parent.parent)
|
||||
_AGENT_SLEEP_SECONDS = "2147483647"
|
||||
_GIT_HTTP_PORT = 9420
|
||||
_GIT_GATE_READY_FILE = "/run/git-gate/ready"
|
||||
|
||||
|
||||
def internal_network_name(slug: str) -> str:
|
||||
return f"bot-bottle-net-{slug}"
|
||||
|
||||
|
||||
def egress_network_name(slug: str) -> str:
|
||||
return f"bot-bottle-egress-{slug}"
|
||||
|
||||
|
||||
def sidecar_container_name(slug: str) -> str:
|
||||
return f"bot-bottle-sidecars-{slug}"
|
||||
|
||||
|
||||
@contextmanager
|
||||
def launch(
|
||||
plan: MacosContainerBottlePlan,
|
||||
*,
|
||||
provision: Callable[[MacosContainerBottlePlan, "MacosContainerBottle"], str | None],
|
||||
) -> Generator[MacosContainerBottle, None, None]:
|
||||
"""Build, run, provision, and yield an Apple Container bottle."""
|
||||
stack = ExitStack()
|
||||
bottle_for_revoke = plan.manifest.bottle
|
||||
git_gate_dir_for_revoke = git_gate_state_dir(plan.slug)
|
||||
|
||||
def teardown() -> None:
|
||||
teardown_exc: BaseException | None = None
|
||||
try:
|
||||
stack.close()
|
||||
except BaseException as exc: # noqa: W0718 - teardown must continue
|
||||
teardown_exc = exc
|
||||
warn(f"macos-container teardown failed: {exc!r}")
|
||||
revoke_git_gate_provisioned_keys(bottle_for_revoke, git_gate_dir_for_revoke)
|
||||
if teardown_exc is not None:
|
||||
raise teardown_exc
|
||||
|
||||
try:
|
||||
plan = _mint_certs(plan)
|
||||
plan = _build_images(plan)
|
||||
|
||||
internal_network = internal_network_name(plan.slug)
|
||||
egress_network = egress_network_name(plan.slug)
|
||||
_create_networks(internal_network, egress_network, stack)
|
||||
|
||||
plan = _provision_git_gate_keys(plan)
|
||||
|
||||
sidecar_name = sidecar_container_name(plan.slug)
|
||||
container_mod.force_remove_container(sidecar_name)
|
||||
_start_sidecar_bundle(plan, sidecar_name, internal_network, egress_network)
|
||||
stack.callback(container_mod.force_remove_container, sidecar_name)
|
||||
_stage_git_gate(plan, sidecar_name)
|
||||
|
||||
sidecar_ip = container_mod.container_ipv4_on_network(
|
||||
sidecar_name, internal_network,
|
||||
)
|
||||
plan = _stamp_agent_urls(plan, sidecar_ip)
|
||||
|
||||
container_mod.force_remove_container(plan.container_name)
|
||||
_start_agent(plan, internal_network, sidecar_ip)
|
||||
stack.callback(container_mod.force_remove_container, plan.container_name)
|
||||
|
||||
bottle = MacosContainerBottle(
|
||||
plan.container_name,
|
||||
teardown,
|
||||
None,
|
||||
agent_command=plan.agent_command,
|
||||
agent_prompt_mode=plan.agent_prompt_mode,
|
||||
agent_provider_template=plan.agent_provider_template,
|
||||
terminal_title=f"{plan.spec.label} ({plan.spec.agent_name})" if plan.spec.label else plan.spec.agent_name,
|
||||
terminal_color=plan.spec.color,
|
||||
agent_workdir=plan.workspace_plan.workdir,
|
||||
)
|
||||
bottle.prompt_path = provision(plan, bottle)
|
||||
|
||||
yield bottle
|
||||
finally:
|
||||
teardown()
|
||||
|
||||
|
||||
def _mint_certs(plan: MacosContainerBottlePlan) -> MacosContainerBottlePlan:
|
||||
egress_ca_host, egress_ca_cert_only = egress_tls_init(
|
||||
egress_state_dir(plan.slug),
|
||||
"""Fail closed: the macOS backend is disabled until it grows the
|
||||
consolidated per-host gateway (the companion-container path it used
|
||||
was removed in #385)."""
|
||||
del plan, provision
|
||||
die(
|
||||
"the macos-container backend is temporarily disabled during the "
|
||||
"companion-container removal (#385); it will return once it uses "
|
||||
"the consolidated gateway. Use --backend=docker for now."
|
||||
)
|
||||
egress_plan = dataclasses.replace(
|
||||
plan.egress_plan,
|
||||
mitmproxy_ca_host_path=egress_ca_host,
|
||||
mitmproxy_ca_cert_only_host_path=egress_ca_cert_only,
|
||||
)
|
||||
return dataclasses.replace(plan, egress_plan=egress_plan)
|
||||
|
||||
|
||||
def _build_images(plan: MacosContainerBottlePlan) -> MacosContainerBottlePlan:
|
||||
container_mod.build_image(
|
||||
SIDECAR_BUNDLE_IMAGE,
|
||||
_REPO_DIR,
|
||||
dockerfile=SIDECAR_BUNDLE_DOCKERFILE,
|
||||
)
|
||||
committed = read_committed_image(plan.slug)
|
||||
if committed and container_mod.image_exists(committed):
|
||||
info(f"using committed image {committed!r}")
|
||||
return dataclasses.replace(
|
||||
plan,
|
||||
agent_provision=dataclasses.replace(
|
||||
plan.agent_provision,
|
||||
image=committed,
|
||||
),
|
||||
)
|
||||
container_mod.build_image(
|
||||
plan.image,
|
||||
_REPO_DIR,
|
||||
dockerfile=plan.dockerfile_path,
|
||||
)
|
||||
return plan
|
||||
|
||||
|
||||
def _create_networks(
|
||||
internal_network: str,
|
||||
egress_network: str,
|
||||
stack: ExitStack,
|
||||
) -> None:
|
||||
container_mod.create_network(internal_network, internal=True)
|
||||
stack.callback(container_mod.remove_network, internal_network)
|
||||
container_mod.create_network(egress_network)
|
||||
stack.callback(container_mod.remove_network, egress_network)
|
||||
|
||||
|
||||
def _start_sidecar_bundle(
|
||||
plan: MacosContainerBottlePlan,
|
||||
sidecar_name: str,
|
||||
internal_network: str,
|
||||
egress_network: str,
|
||||
) -> None:
|
||||
argv = _sidecar_run_argv(plan, sidecar_name, internal_network, egress_network)
|
||||
effective_env = {**dict(os.environ), **plan.agent_provision.provisioned_env}
|
||||
token_values = egress_resolve_token_values(
|
||||
plan.egress_plan.token_env_map, effective_env,
|
||||
)
|
||||
env = {**os.environ, **token_values}
|
||||
info(f"container run sidecar bundle {sidecar_name}")
|
||||
result = subprocess.run(
|
||||
argv, capture_output=True, text=True, env=env, check=False,
|
||||
)
|
||||
if result.returncode != 0:
|
||||
die(
|
||||
f"container run for sidecar bundle {sidecar_name} failed: "
|
||||
f"{(result.stderr or '').strip() or '<no stderr>'}"
|
||||
)
|
||||
|
||||
|
||||
def _start_agent(
|
||||
plan: MacosContainerBottlePlan,
|
||||
internal_network: str,
|
||||
sidecar_ip: str,
|
||||
) -> None:
|
||||
argv = _agent_run_argv(plan, internal_network, sidecar_ip)
|
||||
env = {
|
||||
**os.environ,
|
||||
**plan.forwarded_env,
|
||||
}
|
||||
info(f"container run agent {plan.container_name}")
|
||||
result = subprocess.run(
|
||||
argv, capture_output=True, text=True, env=env, check=False,
|
||||
)
|
||||
if result.returncode != 0:
|
||||
die(
|
||||
f"container run for agent {plan.container_name} failed: "
|
||||
f"{(result.stderr or '').strip() or '<no stderr>'}"
|
||||
)
|
||||
|
||||
|
||||
def _stamp_agent_urls(
|
||||
plan: MacosContainerBottlePlan,
|
||||
sidecar_ip: str,
|
||||
) -> MacosContainerBottlePlan:
|
||||
proxy_url = f"http://{sidecar_ip}:{EGRESS_PORT}"
|
||||
supervise_url = ""
|
||||
if plan.supervise_plan is not None:
|
||||
supervise_url = f"http://{sidecar_ip}:{SUPERVISE_PORT}/"
|
||||
git_gate_url = ""
|
||||
if plan.git_gate_plan.upstreams:
|
||||
git_gate_url = f"http://{sidecar_ip}:{_GIT_HTTP_PORT}"
|
||||
return dataclasses.replace(
|
||||
plan,
|
||||
agent_proxy_url=proxy_url,
|
||||
agent_git_gate_url=git_gate_url,
|
||||
agent_supervise_url=supervise_url,
|
||||
)
|
||||
|
||||
|
||||
def _provision_git_gate_keys(
|
||||
plan: MacosContainerBottlePlan,
|
||||
) -> MacosContainerBottlePlan:
|
||||
if not plan.git_gate_plan.upstreams:
|
||||
return plan
|
||||
git_gate_plan = provision_git_gate_dynamic_keys(
|
||||
plan.manifest.bottle,
|
||||
plan.git_gate_plan,
|
||||
git_gate_state_dir(plan.slug),
|
||||
)
|
||||
return dataclasses.replace(plan, git_gate_plan=git_gate_plan)
|
||||
|
||||
|
||||
def _stage_git_gate(plan: MacosContainerBottlePlan, sidecar_name: str) -> None:
|
||||
gp = plan.git_gate_plan
|
||||
if not gp.upstreams:
|
||||
return
|
||||
|
||||
container_mod.exec_container(
|
||||
sidecar_name,
|
||||
[
|
||||
"mkdir",
|
||||
"-p",
|
||||
str(Path(GIT_GATE_HOOK_IN_CONTAINER).parent),
|
||||
GIT_GATE_CREDS_DIR_IN_CONTAINER,
|
||||
"/git",
|
||||
str(Path(_GIT_GATE_READY_FILE).parent),
|
||||
],
|
||||
)
|
||||
|
||||
for host_path, container_path in _git_gate_files(plan):
|
||||
container_mod.copy_into_container(
|
||||
sidecar_name, host_path, container_path,
|
||||
)
|
||||
|
||||
container_mod.exec_container(
|
||||
sidecar_name,
|
||||
[
|
||||
"sh",
|
||||
"-c",
|
||||
"chmod 755 "
|
||||
f"{GIT_GATE_ENTRYPOINT_IN_CONTAINER} "
|
||||
f"{GIT_GATE_HOOK_IN_CONTAINER} "
|
||||
f"{GIT_GATE_ACCESS_HOOK_IN_CONTAINER} && "
|
||||
f"chmod 600 {GIT_GATE_CREDS_DIR_IN_CONTAINER}/* && "
|
||||
f"touch {_GIT_GATE_READY_FILE}",
|
||||
],
|
||||
)
|
||||
|
||||
|
||||
def _git_gate_files(
|
||||
plan: MacosContainerBottlePlan,
|
||||
) -> tuple[tuple[str, str], ...]:
|
||||
gp = plan.git_gate_plan
|
||||
files: list[tuple[str, str]] = [
|
||||
(str(gp.entrypoint_script), GIT_GATE_ENTRYPOINT_IN_CONTAINER),
|
||||
(str(gp.hook_script), GIT_GATE_HOOK_IN_CONTAINER),
|
||||
(str(gp.access_hook_script), GIT_GATE_ACCESS_HOOK_IN_CONTAINER),
|
||||
]
|
||||
for upstream in gp.upstreams:
|
||||
files.append((
|
||||
expand_tilde(upstream.identity_file),
|
||||
f"{GIT_GATE_CREDS_DIR_IN_CONTAINER}/{upstream.name}-key",
|
||||
))
|
||||
if upstream.known_hosts_file:
|
||||
files.append((
|
||||
str(upstream.known_hosts_file),
|
||||
f"{GIT_GATE_CREDS_DIR_IN_CONTAINER}/{upstream.name}-known_hosts",
|
||||
))
|
||||
return tuple(files)
|
||||
|
||||
|
||||
def _sidecar_run_argv(
|
||||
plan: MacosContainerBottlePlan,
|
||||
sidecar_name: str,
|
||||
internal_network: str,
|
||||
egress_network: str,
|
||||
) -> list[str]:
|
||||
argv = [
|
||||
"container", "run",
|
||||
"--name", sidecar_name,
|
||||
"--detach",
|
||||
"--rm",
|
||||
"--network", egress_network,
|
||||
"--network", internal_network,
|
||||
"--dns", _sidecar_dns(),
|
||||
"--env", f"BOT_BOTTLE_SIDECAR_DAEMONS={','.join(_sidecar_daemons(plan))}",
|
||||
]
|
||||
for entry in _sidecar_env_entries(plan):
|
||||
argv += ["--env", entry]
|
||||
for host_path, container_path, read_only in _sidecar_mounts(plan):
|
||||
argv += ["--mount", _mount_spec(host_path, container_path, read_only)]
|
||||
argv.append(SIDECAR_BUNDLE_IMAGE)
|
||||
return argv
|
||||
|
||||
|
||||
def _agent_run_argv(
|
||||
plan: MacosContainerBottlePlan,
|
||||
internal_network: str,
|
||||
sidecar_ip: str,
|
||||
) -> list[str]:
|
||||
argv = [
|
||||
"container", "run",
|
||||
"--name", plan.container_name,
|
||||
"--detach",
|
||||
"--network", internal_network,
|
||||
]
|
||||
for entry in _agent_env_entries(plan, sidecar_ip):
|
||||
argv += ["--env", entry]
|
||||
argv += [plan.image, "sleep", _AGENT_SLEEP_SECONDS]
|
||||
return argv
|
||||
|
||||
|
||||
def _sidecar_dns() -> str:
|
||||
return container_mod.dns_server()
|
||||
|
||||
|
||||
def _sidecar_daemons(plan: MacosContainerBottlePlan) -> tuple[str, ...]:
|
||||
daemons = ["egress"]
|
||||
if plan.git_gate_plan.upstreams:
|
||||
daemons += ["git-gate", "git-http"]
|
||||
if plan.supervise_plan is not None:
|
||||
daemons.append("supervise")
|
||||
return tuple(daemons)
|
||||
|
||||
|
||||
def _sidecar_env_entries(plan: MacosContainerBottlePlan) -> tuple[str, ...]:
|
||||
env: list[str] = list(egress_sidecar_env_entries(plan.egress_plan))
|
||||
if plan.git_gate_plan.upstreams:
|
||||
env.append(f"BOT_BOTTLE_GIT_GATE_READY_FILE={_GIT_GATE_READY_FILE}")
|
||||
if plan.supervise_plan is not None:
|
||||
env += [
|
||||
f"SUPERVISE_BOTTLE_SLUG={plan.slug}",
|
||||
f"SUPERVISE_DB_PATH={DB_PATH_IN_CONTAINER}",
|
||||
f"SUPERVISE_PORT={SUPERVISE_PORT}",
|
||||
]
|
||||
return tuple(env)
|
||||
|
||||
|
||||
def _sidecar_mounts(
|
||||
plan: MacosContainerBottlePlan,
|
||||
) -> tuple[tuple[str, str, bool], ...]:
|
||||
mounts: list[tuple[str, str, bool]] = []
|
||||
|
||||
ep = plan.egress_plan
|
||||
mounts.append((
|
||||
str(ep.mitmproxy_ca_host_path.parent),
|
||||
str(Path(EGRESS_CA_IN_CONTAINER).parent),
|
||||
False,
|
||||
))
|
||||
if ep.routes:
|
||||
mounts.append((
|
||||
str(ep.routes_path.parent),
|
||||
str(Path(EGRESS_ROUTES_IN_CONTAINER).parent),
|
||||
True,
|
||||
))
|
||||
|
||||
sp = plan.supervise_plan
|
||||
if sp is not None:
|
||||
# `container run --mount type=bind` only accepts directory
|
||||
# sources (a file source fails with "is not a directory") —
|
||||
# mount db_path's dedicated parent dir instead of the file
|
||||
# itself, same as the CA/routes mounts above.
|
||||
mounts.append((
|
||||
str(sp.db_path.parent),
|
||||
str(Path(DB_PATH_IN_CONTAINER).parent),
|
||||
False,
|
||||
))
|
||||
|
||||
return tuple(mounts)
|
||||
|
||||
def _mount_spec(host_path: str, container_path: str, read_only: bool) -> str:
|
||||
spec = f"type=bind,source={host_path},target={container_path}"
|
||||
if read_only:
|
||||
spec += ",readonly"
|
||||
return spec
|
||||
|
||||
|
||||
def _agent_env_entries(
|
||||
plan: MacosContainerBottlePlan,
|
||||
sidecar_ip: str,
|
||||
) -> tuple[str, ...]:
|
||||
proxy_url = f"http://{sidecar_ip}:{EGRESS_PORT}"
|
||||
no_proxy = _agent_no_proxy(plan, sidecar_ip)
|
||||
env = [
|
||||
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}",
|
||||
]
|
||||
if plan.agent_git_gate_url:
|
||||
env.append(f"GIT_GATE_URL={plan.agent_git_gate_url}")
|
||||
if plan.agent_supervise_url:
|
||||
env.append(f"MCP_SUPERVISE_URL={plan.agent_supervise_url}")
|
||||
for name, value in sorted(plan.agent_provision.guest_env.items()):
|
||||
env.append(f"{name}={value}")
|
||||
for name in sorted(plan.forwarded_env.keys()):
|
||||
env.append(name)
|
||||
env.extend(egress_agent_env_entries(plan.egress_plan))
|
||||
return tuple(env)
|
||||
|
||||
|
||||
def _agent_no_proxy(plan: MacosContainerBottlePlan, sidecar_ip: str) -> str:
|
||||
hosts = ["localhost", "127.0.0.1", sidecar_ip]
|
||||
return ",".join(hosts)
|
||||
yield # unreachable — `die` raises; keeps this a generator/contextmanager
|
||||
|
||||
@@ -60,13 +60,21 @@ def dns_server() -> str:
|
||||
|
||||
|
||||
def build_image(ref: str, context: str, *, dockerfile: str = "") -> None:
|
||||
"""Build an OCI image with Apple's BuildKit-backed `container build`."""
|
||||
"""Build an OCI image with Apple's BuildKit-backed `container build`.
|
||||
|
||||
Set `BOT_BOTTLE_NO_CACHE=1` (the `start --no-cache` flag) to force
|
||||
`--no-cache`. The npm/curl installers some provider Dockerfiles
|
||||
shell out to can silently no-op on a transient network failure —
|
||||
e.g. an `optionalDependencies` fetch for a platform-native binary —
|
||||
and the builder will then cache that broken layer indefinitely."""
|
||||
info(
|
||||
f"building image {ref} from {context} with Apple Container "
|
||||
"(layer cache keeps repeat builds fast)"
|
||||
)
|
||||
_ensure_builder_dns()
|
||||
args = [_CONTAINER, "build", "-t", ref, "--dns", dns_server()]
|
||||
if os.environ.get("BOT_BOTTLE_NO_CACHE") == "1":
|
||||
args.append("--no-cache")
|
||||
if dockerfile:
|
||||
# `container build` resolves -f relative to the current working
|
||||
# directory, not the build context. Anchor a relative Dockerfile to
|
||||
@@ -78,6 +86,28 @@ def build_image(ref: str, context: str, *, dockerfile: str = "") -> None:
|
||||
subprocess.run(args, check=True)
|
||||
|
||||
|
||||
def verify_agent_image(image: str, argv: tuple[str, ...]) -> None:
|
||||
"""Run `argv` inside a throwaway container of a freshly built agent
|
||||
image and die loudly if it fails, instead of shipping an image
|
||||
whose CLI only breaks at first real use. No-op when the provider
|
||||
hasn't declared a smoke test (`AgentProviderRuntime.smoke_test`)."""
|
||||
if not argv:
|
||||
return
|
||||
result = subprocess.run(
|
||||
[_CONTAINER, "run", "--rm", "--entrypoint", argv[0], image, *argv[1:]],
|
||||
capture_output=True,
|
||||
text=True,
|
||||
check=False,
|
||||
)
|
||||
if result.returncode != 0:
|
||||
detail = (result.stderr or result.stdout or "").strip()
|
||||
die(
|
||||
f"agent image {image!r} failed its post-build smoke test "
|
||||
f"({' '.join(argv)}): {detail}\n"
|
||||
f"Try rebuilding from scratch: bot-bottle start --no-cache"
|
||||
)
|
||||
|
||||
|
||||
def commit_container(container_name: str, image_tag: str) -> None:
|
||||
"""Snapshot a running Apple Container as a local image.
|
||||
|
||||
|
||||
@@ -94,7 +94,7 @@ def prepare_egress(
|
||||
|
||||
|
||||
def prepare_supervise(bottle: ManifestBottle, slug: str) -> SupervisePlan | None:
|
||||
"""Prepare the supervise sidecar state dir. Returns None when
|
||||
"""Prepare the supervise daemon state dir. Returns None when
|
||||
bottle.supervise is falsy."""
|
||||
if not bottle.supervise:
|
||||
return None
|
||||
|
||||
@@ -44,16 +44,16 @@ _STATE_SUBDIR = "state"
|
||||
_PER_BOTTLE_DOCKERFILE_NAME = "Dockerfile"
|
||||
_COMMITTED_IMAGE_NAME = "committed-image"
|
||||
_TRANSCRIPT_SUBDIR = "transcript"
|
||||
# Per-sidecar scratch subdirs. PRD 0018 chunk 2: bind-mount sources
|
||||
# Per-daemon scratch subdirs. PRD 0018 chunk 2: bind-mount sources
|
||||
# live here so chunk 3's `docker compose up` can find them at stable
|
||||
# paths. Each sidecar's `prepare()` writes config + CAs into its own
|
||||
# paths. Each daemon's `prepare()` writes config + CAs into its own
|
||||
# subdir; the launch step is unchanged today (still `docker cp`).
|
||||
_EGRESS_SUBDIR = "egress"
|
||||
_GIT_GATE_SUBDIR = "git-gate"
|
||||
_SUPERVISE_SUBDIR = "supervise"
|
||||
_AGENT_SUBDIR = "agent"
|
||||
_METADATA_NAME = "metadata.json"
|
||||
# Live-config dir bind-mounted into the supervise sidecar (read-only).
|
||||
# Live-config dir bind-mounted into the supervise daemon (read-only).
|
||||
# Host's apply paths keep these files fresh so supervise's
|
||||
# `list-egress-routes` MCP tool returns the current state —
|
||||
# not a snapshot from launch time.
|
||||
@@ -222,7 +222,7 @@ def per_bottle_image_tag(identity: str) -> str:
|
||||
|
||||
def live_config_dir(identity: str) -> Path:
|
||||
"""Per-bottle live-config dir. Bind-mounted read-only into the
|
||||
supervise sidecar; the host's apply paths refresh the files on
|
||||
supervise daemon; the host's apply paths refresh the files on
|
||||
every operator approval so the agent's `list-*` MCP tools always
|
||||
return current state."""
|
||||
return bottle_state_dir(identity) / _LIVE_CONFIG_SUBDIR
|
||||
@@ -260,9 +260,9 @@ def transcript_snapshot_dir(identity: str) -> Path:
|
||||
return bottle_state_dir(identity) / _TRANSCRIPT_SUBDIR
|
||||
|
||||
|
||||
# --- Per-sidecar scratch subdirs (PRD 0018 chunk 2) ------------------------
|
||||
# --- Per-daemon scratch subdirs (PRD 0018 chunk 2) ------------------------
|
||||
#
|
||||
# Each sidecar gets its own subdir under the bottle's state dir for
|
||||
# Each daemon gets its own subdir under the bottle's state dir for
|
||||
# bind-mount sources (config, CAs, hooks, etc.). Prepare-time writes
|
||||
# land here; the state dir's normal cleanup (`cleanup_state`) reaps
|
||||
# them along with everything else when the bottle session ends and
|
||||
@@ -270,20 +270,20 @@ def transcript_snapshot_dir(identity: str) -> Path:
|
||||
|
||||
|
||||
def egress_state_dir(identity: str) -> Path:
|
||||
"""State subdir for the egress sidecar: routes.yaml + the
|
||||
"""State subdir for the egress daemon: routes.yaml + the
|
||||
per-bottle mitmproxy CA. Bind-mount source from chunk 3 onward."""
|
||||
return bottle_state_dir(identity) / _EGRESS_SUBDIR
|
||||
|
||||
|
||||
def git_gate_state_dir(identity: str) -> Path:
|
||||
"""State subdir for the git-gate sidecar: entrypoint + hooks +
|
||||
"""State subdir for the git-gate daemon: entrypoint + hooks +
|
||||
per-upstream known_hosts. Bind-mount source from chunk 3
|
||||
onward."""
|
||||
return bottle_state_dir(identity) / _GIT_GATE_SUBDIR
|
||||
|
||||
|
||||
def supervise_state_dir(identity: str) -> Path:
|
||||
"""State subdir reserved for supervise sidecar bind-mount sources.
|
||||
"""State subdir reserved for supervise daemon bind-mount sources.
|
||||
Runtime queue/audit rows live in the host-level bot-bottle SQLite
|
||||
database, so they survive state-dir cleanup."""
|
||||
return bottle_state_dir(identity) / _SUPERVISE_SUBDIR
|
||||
|
||||
@@ -2,8 +2,8 @@
|
||||
|
||||
Walks every registered backend (docker, firecracker, macos-container)
|
||||
so a single `./cli.py cleanup` reaps every backend's leftovers — a
|
||||
firecracker bottle's sidecars won't survive a docker-only cleanup pass
|
||||
(issue addressed alongside #77).
|
||||
firecracker bottle's VM processes and run dirs won't survive a
|
||||
docker-only cleanup pass (issue addressed alongside #77).
|
||||
|
||||
Each backend's `prepare_cleanup` enumerates its own resources;
|
||||
docker's `_list_orphan_state_dirs` consults
|
||||
|
||||
@@ -46,6 +46,17 @@ def cmd_start(argv: list[str]) -> int:
|
||||
parser = argparse.ArgumentParser(prog=f"{PROG} start", add_help=True)
|
||||
parser.add_argument("--dry-run", action="store_true")
|
||||
parser.add_argument("--cwd", action="store_true", help="copy host cwd into the running bottle")
|
||||
parser.add_argument(
|
||||
"--no-cache",
|
||||
action="store_true",
|
||||
help=(
|
||||
"rebuild agent/sidecar images from scratch, bypassing the "
|
||||
"build layer cache. Use when an image looks broken after a "
|
||||
"dependency bump — e.g. an installer's optionalDependencies "
|
||||
"fetch silently no-op'd on a transient failure and got baked "
|
||||
"into a cached layer."
|
||||
),
|
||||
)
|
||||
parser.add_argument(
|
||||
"--backend",
|
||||
choices=known_backend_names(),
|
||||
@@ -97,6 +108,11 @@ def cmd_start(argv: list[str]) -> int:
|
||||
args = parser.parse_args(argv)
|
||||
|
||||
dry_run = args.dry_run or os.environ.get("BOT_BOTTLE_DRY_RUN") == "1"
|
||||
if args.no_cache or os.environ.get("BOT_BOTTLE_NO_CACHE") == "1":
|
||||
# Read by build_image() in each backend's util module — set here
|
||||
# so both the interactive and --headless paths pick it up without
|
||||
# threading a no_cache field through every backend's plan dataclass.
|
||||
os.environ["BOT_BOTTLE_NO_CACHE"] = "1"
|
||||
|
||||
manifest = ManifestIndex.resolve(USER_CWD)
|
||||
backend_name: str | None = args.backend
|
||||
|
||||
@@ -4,7 +4,7 @@ The Claude-specific behavior previously inlined under
|
||||
`agent_provider.agent_provision_plan` (claude.json trust marker,
|
||||
api.anthropic.com egress route, OAuth-token placeholder), plus
|
||||
the `claude mcp add` invocation that registers the supervise
|
||||
sidecar in claude-code's user config (PRD 0013)."""
|
||||
gateway in claude-code's user config (PRD 0013)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
@@ -91,6 +91,7 @@ _RUNTIME = AgentProviderRuntime(
|
||||
prompt_mode="append_file",
|
||||
bypass_args=("--dangerously-skip-permissions",),
|
||||
resume_args=("--continue",),
|
||||
smoke_test=("claude", "--version"),
|
||||
)
|
||||
|
||||
|
||||
@@ -293,7 +294,7 @@ class ClaudeAgentProvider(AgentProvider):
|
||||
supervise_url: str,
|
||||
) -> None:
|
||||
"""Run `claude mcp add` inside the agent guest to register the
|
||||
supervise sidecar in claude-code's user config (~/.claude.json).
|
||||
supervise daemon in claude-code's user config (~/.claude.json).
|
||||
|
||||
Failure is logged but not fatal — the bottle still works without
|
||||
the entry; the operator can register it manually."""
|
||||
|
||||
@@ -4,7 +4,7 @@ The Codex-specific behavior previously inlined under
|
||||
`agent_provider.agent_provision_plan` (config.toml trust marker,
|
||||
chatgpt.com / api.openai.com egress routes, optional host-credential
|
||||
forwarding with dummy-auth.json + verify), plus the `codex mcp add`
|
||||
invocation that registers the supervise sidecar in Codex's
|
||||
invocation that registers the supervise daemon in Codex's
|
||||
~/.codex/config.toml (PRD 0050)."""
|
||||
|
||||
from __future__ import annotations
|
||||
@@ -61,6 +61,7 @@ _RUNTIME = AgentProviderRuntime(
|
||||
prompt_mode="read_prompt_file",
|
||||
bypass_args=("--dangerously-bypass-approvals-and-sandbox",),
|
||||
resume_args=("resume", "--last"),
|
||||
smoke_test=(_CODEX_CLI, "--version"),
|
||||
)
|
||||
|
||||
|
||||
@@ -266,7 +267,7 @@ class CodexAgentProvider(AgentProvider):
|
||||
supervise_url: str,
|
||||
) -> None:
|
||||
"""Run `codex mcp add` inside the agent guest to register the
|
||||
supervise sidecar in Codex's user config (~/.codex/config.toml).
|
||||
supervise daemon in Codex's user config (~/.codex/config.toml).
|
||||
|
||||
Mirrors the Claude provider's `claude mcp add` flow — failure
|
||||
is logged but not fatal."""
|
||||
|
||||
@@ -3,7 +3,7 @@
|
||||
Pure Python, no mitmproxy dependency. Each detector is a module-level
|
||||
function returning `ScanResult | None`.
|
||||
|
||||
Ships flat into the sidecar bundle image alongside
|
||||
Ships flat into the gateway image alongside
|
||||
`egress_addon_core.py` — both this file and the package source use
|
||||
the same try/except import shim pattern.
|
||||
"""
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
This module defines the abstract proxy (`Egress`), its plan
|
||||
dataclass (`EgressPlan`), and the resolved per-route shape
|
||||
(`EgressRoute`). The sidecar's start/stop lifecycle is backend-
|
||||
(`EgressRoute`). The gateway's start/stop lifecycle is backend-
|
||||
specific and lives on concrete subclasses (see
|
||||
`bot_bottle/backend/docker/egress.py`).
|
||||
"""
|
||||
@@ -63,8 +63,8 @@ def _random_canary_env() -> str:
|
||||
return f"{first}_{second}_SECRET"
|
||||
|
||||
|
||||
def egress_sidecar_env_entries(plan: "EgressPlan") -> tuple[str, ...]:
|
||||
"""Return sidecar env entries needed by egress across all backends."""
|
||||
def egress_gateway_env_entries(plan: "EgressPlan") -> tuple[str, ...]:
|
||||
"""Return gateway env entries needed by egress across all backends."""
|
||||
env: list[str] = []
|
||||
if plan.routes:
|
||||
env.extend(sorted(plan.token_env_map.keys()))
|
||||
@@ -87,7 +87,7 @@ class EgressRoute(Route):
|
||||
|
||||
Inherits `host`, `matches`, `auth_scheme`, and `token_env`
|
||||
from `egress_addon_core.Route` — those are the fields that cross the
|
||||
YAML wire into the sidecar. The fields below are host-only and
|
||||
YAML wire into the gateway. The fields below are host-only and
|
||||
are never serialised to the addon.
|
||||
|
||||
`token_ref` is the host env var the CLI reads at launch and forwards
|
||||
@@ -386,7 +386,7 @@ class Egress(ABC):
|
||||
routes_path.write_text(egress_render_routes(routes, log=log))
|
||||
routes_path.chmod(0o600)
|
||||
# Generate a per-session fake secret under a plausible random env name.
|
||||
# The sidecar marks that exact env name as sensitive for known-secret
|
||||
# The gateway marks that exact env name as sensitive for known-secret
|
||||
# scanning; the agent receives the same name/value as exfil bait.
|
||||
canary = secrets.token_urlsafe(32)
|
||||
return EgressPlan(
|
||||
@@ -412,6 +412,6 @@ __all__ = [
|
||||
"egress_resolve_token_values",
|
||||
"egress_routes_for_bottle",
|
||||
"egress_agent_env_entries",
|
||||
"egress_sidecar_env_entries",
|
||||
"egress_gateway_env_entries",
|
||||
"egress_token_env_map",
|
||||
]
|
||||
|
||||
+117
-41
@@ -1,4 +1,4 @@
|
||||
"""mitmproxy addon entrypoint for the egress sidecar (PRD 0017, PRD 0053).
|
||||
"""mitmproxy addon entrypoint for the egress gateway (PRD 0017, PRD 0053).
|
||||
|
||||
Loaded by `mitmdump -s /app/egress_addon.py` inside the
|
||||
egress container."""
|
||||
@@ -10,6 +10,7 @@ import json
|
||||
import os
|
||||
import signal
|
||||
import sys
|
||||
import typing
|
||||
from pathlib import Path
|
||||
|
||||
from mitmproxy import http # type: ignore[import-not-found] # pylint: disable=import-error
|
||||
@@ -32,6 +33,7 @@ from egress_addon_core import ( # type: ignore[import-not-found] # pylint: dis
|
||||
is_git_push_request,
|
||||
load_config,
|
||||
match_route,
|
||||
resolve_client_context,
|
||||
outbound_scan_headers,
|
||||
route_to_yaml_dict,
|
||||
scan_inbound,
|
||||
@@ -51,11 +53,26 @@ try:
|
||||
except ImportError: # pragma: no cover - host-side path
|
||||
from bot_bottle import supervise as _sv # type: ignore[import-not-found]
|
||||
|
||||
try:
|
||||
from policy_resolver import PolicyResolver # type: ignore[import-not-found]
|
||||
except ImportError: # pragma: no cover - host-side path
|
||||
from bot_bottle.policy_resolver import PolicyResolver
|
||||
|
||||
|
||||
DEFAULT_ROUTES_PATH = "/etc/egress/routes.yaml"
|
||||
|
||||
INTROSPECT_HOST = "_egress.local"
|
||||
|
||||
# Consolidated (multi-tenant) mode: when this points at the per-host
|
||||
# orchestrator's control plane, the addon resolves each client's Config by
|
||||
# source IP per request instead of using a single static routes file. Unset
|
||||
# → legacy per-bottle single-tenant mode (unchanged).
|
||||
ORCHESTRATOR_URL_ENV = "BOT_BOTTLE_ORCHESTRATOR_URL"
|
||||
|
||||
# App-layer identity token (defense-in-depth over the source-IP invariant);
|
||||
# the agent injects it, the addon strips it so it never leaks upstream.
|
||||
IDENTITY_HEADER = "x-bot-bottle-identity"
|
||||
|
||||
# Seconds the egress proxy holds a token-blocked request open waiting for the
|
||||
# operator's supervisor decision (PRD 0062), overridable via env.
|
||||
DEFAULT_TOKEN_ALLOW_TIMEOUT_SECONDS = 300.0
|
||||
@@ -72,20 +89,40 @@ _TOKEN_ALLOW_JUSTIFICATION = (
|
||||
|
||||
|
||||
class EgressAddon:
|
||||
# Class default so addons built via __new__ (e.g. in tests) default to
|
||||
# single-tenant; __init__ sets the instance attribute for real runs.
|
||||
_resolver: "PolicyResolver | None" = None
|
||||
|
||||
def __init__(self) -> None:
|
||||
self.routes_path = os.environ.get("EGRESS_ROUTES", DEFAULT_ROUTES_PATH)
|
||||
self.config: Config = Config(routes=())
|
||||
# Tokens the operator has approved this session (PRD 0062). In-memory
|
||||
# only — a restart re-prompts. Mutated only from the asyncio loop that
|
||||
# runs the addon hooks, so no lock is needed.
|
||||
self.safe_tokens: set[str] = set()
|
||||
# Consolidated mode: resolve per-client Config from the orchestrator.
|
||||
# Absent → single-tenant (static routes file); behaviour unchanged.
|
||||
orch_url = os.environ.get(ORCHESTRATOR_URL_ENV, "").strip()
|
||||
self._resolver = PolicyResolver(orch_url) if orch_url else None
|
||||
# Tokens the operator has approved this session (PRD 0062), keyed by
|
||||
# bottle so the shared gateway keeps each bottle's safelist separate —
|
||||
# a global set would let bottle A's approved secret pass bottle B's DLP
|
||||
# scan. In-memory only (a restart re-prompts); mutated only from the
|
||||
# asyncio loop that runs the addon hooks, so no lock is needed.
|
||||
self._safe_tokens: dict[str, set[str]] = {}
|
||||
self._supervise_slug = os.environ.get("SUPERVISE_BOTTLE_SLUG", "").strip()
|
||||
self._token_allow_timeout = _token_allow_timeout_from_env(os.environ)
|
||||
self._reload(initial=True)
|
||||
self._install_sighup()
|
||||
|
||||
def _supervise_available(self) -> bool:
|
||||
return bool(self._supervise_slug)
|
||||
@staticmethod
|
||||
def _supervise_available(slug: str) -> bool:
|
||||
"""Supervise is reachable for this request iff we resolved a bottle to
|
||||
attribute its proposals to (single-tenant env slug, or a source-IP
|
||||
-attributed bottle id). Empty → fail closed (no queue to write to)."""
|
||||
return bool(slug)
|
||||
|
||||
def _safe_tokens_for(self, slug: str) -> set[str]:
|
||||
"""This bottle's operator-approved DLP safelist (PRD 0062), created on
|
||||
first use. Keyed by bottle so the shared gateway never leaks one
|
||||
bottle's approved token into another's scan."""
|
||||
return self._safe_tokens.setdefault(slug, set())
|
||||
|
||||
def _reload(self, *, initial: bool = False) -> None:
|
||||
try:
|
||||
@@ -194,6 +231,28 @@ class EgressAddon:
|
||||
+ "\n"
|
||||
)
|
||||
|
||||
def _resolve_flow(
|
||||
self, flow: http.HTTPFlow,
|
||||
) -> "tuple[Config, str, typing.Mapping[str, str]]":
|
||||
"""The `(Config, supervise slug, env)` to apply to this request.
|
||||
Single-tenant → the static `self.config`, the env slug, and the process
|
||||
env. Consolidated → the calling bottle's Config + bottle id + auth
|
||||
tokens, resolved by source IP in one round-trip (fail-closed to deny-all
|
||||
+ empty slug if unattributed); `env` is the process env overlaid with
|
||||
the bottle's tokens, so upstream-auth injection (and DLP) use *this*
|
||||
bottle's credentials — exactly what the per-bottle gateway daemon's env did.
|
||||
The identity token, if the agent injected one, is read then stripped so
|
||||
it never leaks upstream."""
|
||||
if self._resolver is None:
|
||||
return self.config, self._supervise_slug, os.environ
|
||||
conn = flow.client_conn
|
||||
client_ip = conn.peername[0] if conn and conn.peername else ""
|
||||
token = flow.request.headers.get(IDENTITY_HEADER, "")
|
||||
flow.request.headers.pop(IDENTITY_HEADER, None)
|
||||
config, slug, tokens = resolve_client_context(self._resolver, client_ip, token)
|
||||
env = {**os.environ, **tokens} if tokens else os.environ
|
||||
return config, slug, env
|
||||
|
||||
async def request(self, flow: http.HTTPFlow) -> None:
|
||||
request_path, _, query = flow.request.path.partition("?")
|
||||
|
||||
@@ -201,12 +260,14 @@ class EgressAddon:
|
||||
self._serve_introspection(flow, request_path)
|
||||
return
|
||||
|
||||
config, slug, env = self._resolve_flow(flow)
|
||||
|
||||
# DLP outbound scan BEFORE stripping auth — catches tokens the
|
||||
# agent tried to smuggle in any header, path, query param, or body.
|
||||
# Hostname is included to catch DNS-tunnelling exfiltration attempts.
|
||||
route = match_route(self.config.routes, flow.request.pretty_host)
|
||||
route = match_route(config.routes, flow.request.pretty_host)
|
||||
if route is not None:
|
||||
if not await self._handle_outbound_dlp(flow, route):
|
||||
if not await self._handle_outbound_dlp(flow, route, slug, env):
|
||||
return
|
||||
# The redact policy may have rewritten the request line; recompute
|
||||
# the path/query the git checks below rely on.
|
||||
@@ -224,7 +285,7 @@ class EgressAddon:
|
||||
|
||||
if is_git_fetch_request(request_path, query):
|
||||
git_decision = decide_git_fetch(
|
||||
self.config.routes, flow.request.pretty_host,
|
||||
config.routes, flow.request.pretty_host,
|
||||
)
|
||||
if git_decision.action == "block":
|
||||
self._block(
|
||||
@@ -235,17 +296,17 @@ class EgressAddon:
|
||||
return
|
||||
|
||||
# Strip agent-set Authorization after DLP scan so smuggled tokens
|
||||
# are caught above; the route may inject sidecar-owned auth below.
|
||||
# are caught above; the route may inject gateway-owned auth below.
|
||||
flow.request.headers.pop("authorization", None)
|
||||
|
||||
# Build headers mapping for match evaluation
|
||||
req_headers = {k.lower(): v for k, v in flow.request.headers.items()}
|
||||
|
||||
decision = decide(
|
||||
self.config.routes,
|
||||
config.routes,
|
||||
flow.request.pretty_host,
|
||||
request_path,
|
||||
os.environ,
|
||||
env,
|
||||
request_method=flow.request.method,
|
||||
request_headers=req_headers,
|
||||
)
|
||||
@@ -257,7 +318,7 @@ class EgressAddon:
|
||||
if decision.inject_authorization is not None:
|
||||
flow.request.headers["authorization"] = decision.inject_authorization
|
||||
|
||||
if self.config.log >= LOG_FULL:
|
||||
if config.log >= LOG_FULL:
|
||||
self._log_request(flow)
|
||||
|
||||
def _block_dlp(self, flow: http.HTTPFlow, result: ScanResult) -> None:
|
||||
@@ -270,10 +331,13 @@ class EgressAddon:
|
||||
self,
|
||||
flow: http.HTTPFlow,
|
||||
route: Route,
|
||||
slug: str,
|
||||
env: "typing.Mapping[str, str]",
|
||||
) -> bool:
|
||||
"""Scan the outbound request and apply the route's on-match policy
|
||||
(PRD 0062). Returns True if the request may be forwarded, False if a
|
||||
403 response has been written to `flow`.
|
||||
(PRD 0062). `env` is the per-bottle env overlay (process env + this
|
||||
bottle's tokens) used for DLP detection. Returns True if the request may
|
||||
be forwarded, False if a 403 response has been written to `flow`.
|
||||
|
||||
Loops so the supervise policy can re-scan after each approval — a
|
||||
second, un-approved token in the same request is still caught."""
|
||||
@@ -290,8 +354,8 @@ class EgressAddon:
|
||||
flow.request.pretty_host, request_path, query, headers, "",
|
||||
)
|
||||
result = scan_outbound(
|
||||
route, scan_text, os.environ,
|
||||
safe_tokens=self.safe_tokens, crlf_text=crlf_text,
|
||||
route, scan_text, env,
|
||||
safe_tokens=self._safe_tokens_for(slug), crlf_text=crlf_text,
|
||||
)
|
||||
if result is None or result.severity != "block":
|
||||
return True
|
||||
@@ -301,7 +365,7 @@ class EgressAddon:
|
||||
# redact scrubs every detection (tokens and structural CRLF) and
|
||||
# forwards; it fails closed only if a match survives the scrub.
|
||||
if policy == ON_MATCH_REDACT:
|
||||
if self._redact_outbound(flow, route):
|
||||
if self._redact_outbound(flow, route, env):
|
||||
if self.config.log >= LOG_BLOCKS:
|
||||
sys.stderr.write(json.dumps({
|
||||
"event": "egress_redacted",
|
||||
@@ -326,32 +390,34 @@ class EgressAddon:
|
||||
|
||||
# supervise (default): hold the request for operator approval.
|
||||
# Fall back to a hard 403 when supervise isn't wired for the bottle.
|
||||
if not self._supervise_available():
|
||||
if not self._supervise_available(slug):
|
||||
self._block_dlp(flow, result)
|
||||
return False
|
||||
approved = await self._supervise_token_block(flow, request_path, result)
|
||||
approved = await self._supervise_token_block(flow, request_path, result, slug, env)
|
||||
if not approved:
|
||||
return False # _supervise_token_block wrote the 403 response
|
||||
# loop: the approved value is now in safe_tokens; re-scan.
|
||||
|
||||
def _redact_outbound(self, flow: http.HTTPFlow, route: Route) -> bool:
|
||||
def _redact_outbound(
|
||||
self, flow: http.HTTPFlow, route: Route, env: "typing.Mapping[str, str]",
|
||||
) -> bool:
|
||||
"""Scrub detected tokens (and CRLF injection sequences) from the mutable
|
||||
request surfaces (body, headers, path/query) and re-scan. Returns True
|
||||
if the request is now clean; False if a block-severity match remains on
|
||||
a surface redaction cannot rewrite (the hostname) so the caller fails
|
||||
closed."""
|
||||
request surfaces (body, headers, path/query) and re-scan. `env` is the
|
||||
per-bottle env overlay. Returns True if the request is now clean; False
|
||||
if a block-severity match remains on a surface redaction cannot rewrite
|
||||
(the hostname) so the caller fails closed."""
|
||||
body = flow.request.get_text(strict=False)
|
||||
if body:
|
||||
redacted_body = redact_tokens(body, env=os.environ)
|
||||
redacted_body = redact_tokens(body, env=env)
|
||||
if redacted_body != body:
|
||||
flow.request.text = redacted_body
|
||||
for name, value in list(flow.request.headers.items()):
|
||||
if name.lower() == "host":
|
||||
continue # routing-critical; never a legitimate token
|
||||
redacted = strip_crlf(redact_tokens(value, env=os.environ))
|
||||
redacted = strip_crlf(redact_tokens(value, env=env))
|
||||
if redacted != value:
|
||||
flow.request.headers[name] = redacted
|
||||
redacted_path = strip_crlf(redact_tokens(flow.request.path, env=os.environ))
|
||||
redacted_path = strip_crlf(redact_tokens(flow.request.path, env=env))
|
||||
if redacted_path != flow.request.path:
|
||||
flow.request.path = redacted_path
|
||||
|
||||
@@ -364,7 +430,7 @@ class EgressAddon:
|
||||
crlf_text = build_outbound_scan_text(
|
||||
flow.request.pretty_host, request_path, query, headers, "",
|
||||
)
|
||||
result = scan_outbound(route, scan_text, os.environ, crlf_text=crlf_text)
|
||||
result = scan_outbound(route, scan_text, env, crlf_text=crlf_text)
|
||||
return result is None or result.severity != "block"
|
||||
|
||||
async def _supervise_token_block(
|
||||
@@ -372,21 +438,27 @@ class EgressAddon:
|
||||
flow: http.HTTPFlow,
|
||||
request_path: str,
|
||||
result: ScanResult,
|
||||
slug: str,
|
||||
env: "typing.Mapping[str, str]",
|
||||
) -> bool:
|
||||
"""Route a token DLP block to the operator's supervisor queue and wait.
|
||||
|
||||
Returns True if the operator approved (the matched value is added to
|
||||
`self.safe_tokens` and the caller re-scans); False if the request must
|
||||
be blocked (a 403 response has been written to `flow`)."""
|
||||
`slug` attributes the proposal to the calling bottle (its own queue +
|
||||
safelist) — in the shared gateway this is what keeps one bottle's
|
||||
approval from unblocking another's request. `env` is the per-bottle env
|
||||
overlay used to redact secrets from the proposal text. Returns True if
|
||||
the operator approved (the matched value is added to that bottle's
|
||||
safelist and the caller re-scans); False if the request must be blocked
|
||||
(a 403 response has been written to `flow`)."""
|
||||
host = flow.request.pretty_host
|
||||
payload = build_token_allow_payload(
|
||||
redact_tokens(host, env=os.environ),
|
||||
redact_tokens(host, env=env),
|
||||
flow.request.method,
|
||||
redact_tokens(request_path, env=os.environ),
|
||||
redact_tokens(request_path, env=env),
|
||||
result,
|
||||
)
|
||||
proposal = _sv.Proposal.new(
|
||||
bottle_slug=self._supervise_slug,
|
||||
bottle_slug=slug,
|
||||
tool=_sv.TOOL_EGRESS_TOKEN_ALLOW,
|
||||
proposed_file=payload,
|
||||
justification=_TOKEN_ALLOW_JUSTIFICATION,
|
||||
@@ -409,13 +481,13 @@ class EgressAddon:
|
||||
**self._req_ctx(flow),
|
||||
}) + "\n")
|
||||
|
||||
response = await self._await_token_response(proposal.id)
|
||||
_sv.archive_proposal(self._supervise_slug, proposal.id)
|
||||
response = await self._await_token_response(proposal.id, slug)
|
||||
_sv.archive_proposal(slug, proposal.id)
|
||||
|
||||
if response is not None and response.status in (
|
||||
_sv.STATUS_APPROVED, _sv.STATUS_MODIFIED,
|
||||
):
|
||||
self.safe_tokens.add(result.matched)
|
||||
self._safe_tokens_for(slug).add(result.matched)
|
||||
if self.config.log >= LOG_BLOCKS:
|
||||
sys.stderr.write(json.dumps({
|
||||
"event": "egress_token_allowed",
|
||||
@@ -438,6 +510,7 @@ class EgressAddon:
|
||||
async def _await_token_response(
|
||||
self,
|
||||
proposal_id: str,
|
||||
slug: str,
|
||||
) -> "_sv.Response | None":
|
||||
"""Poll the DB for the operator's response without blocking the
|
||||
proxy event loop. Returns the Response, or None on timeout."""
|
||||
@@ -445,7 +518,7 @@ class EgressAddon:
|
||||
deadline = loop.time() + self._token_allow_timeout
|
||||
while True:
|
||||
try:
|
||||
return _sv.read_response(self._supervise_slug, proposal_id)
|
||||
return _sv.read_response(slug, proposal_id)
|
||||
except (OSError, ValueError, KeyError):
|
||||
# Not written yet, or a partial/malformed write — retry until
|
||||
# the deadline, then fail closed.
|
||||
@@ -499,6 +572,9 @@ class EgressAddon:
|
||||
"""
|
||||
if flow.websocket is None: # type: ignore[union-attr]
|
||||
return
|
||||
# WebSocket DLP runs against the static config only (single-tenant); in
|
||||
# the consolidated gateway self.config has no routes, so this is inert
|
||||
# until websocket routing is made source-IP-aware (a separate slice).
|
||||
route = match_route(self.config.routes, flow.request.pretty_host)
|
||||
if route is None:
|
||||
return
|
||||
@@ -509,7 +585,7 @@ class EgressAddon:
|
||||
# not an injection vector here — scan only for credential leakage.
|
||||
result = scan_outbound(
|
||||
route, content, os.environ,
|
||||
safe_tokens=self.safe_tokens, crlf_text="",
|
||||
safe_tokens=self._safe_tokens_for(self._supervise_slug), crlf_text="",
|
||||
)
|
||||
if result is not None and result.severity == "block":
|
||||
sys.stderr.write(f"egress DLP: {result.reason}\n")
|
||||
|
||||
@@ -3,12 +3,12 @@
|
||||
Split out of `egress_addon.py` so the host's unit tests can
|
||||
exercise the parse + decision functions without depending on the
|
||||
`mitmproxy` package. The companion module wraps these with the
|
||||
`mitmproxy.http.HTTPFlow` API and is loaded inside the sidecar
|
||||
`mitmproxy.http.HTTPFlow` API and is loaded inside the gateway
|
||||
container.
|
||||
|
||||
Imports: stdlib + `yaml_subset` (which is itself stdlib-only and
|
||||
ships flat into the sidecar bundle image alongside this file —
|
||||
see `Dockerfile.sidecars`)."""
|
||||
ships flat into the gateway image alongside this file —
|
||||
see `Dockerfile.gateway`)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
@@ -22,7 +22,7 @@ except ImportError: # pragma: no cover - host-side path
|
||||
from .yaml_subset import YamlSubsetError, parse_yaml_subset
|
||||
|
||||
# DLP detector-config parsing lives in a sibling module (also flat-bundled
|
||||
# into the sidecar — see Dockerfile.sidecars). Re-exported below so existing
|
||||
# into the gateway — see Dockerfile.gateway). Re-exported below so existing
|
||||
# `from egress_addon_core import ON_MATCH_*` callers keep working.
|
||||
try:
|
||||
from egress_dlp_config import ( # type: ignore[import-not-found]
|
||||
@@ -120,7 +120,7 @@ class ScanResult:
|
||||
reason: str
|
||||
location: str = "" # where the match was found, e.g. "body", "authorization header"
|
||||
context: str = "" # surrounding text with the match replaced by REDACT
|
||||
# Raw substring the detector matched. Used inside the sidecar to key the
|
||||
# Raw substring the detector matched. Used inside the gateway to key the
|
||||
# supervisor-approved "safe tokens" set (PRD 0062); never logged or written
|
||||
# to a proposal file. Empty for structural detectors (CRLF) that carry no
|
||||
# safelist-able value.
|
||||
@@ -413,6 +413,70 @@ def load_config(text: str) -> "Config":
|
||||
return parse_config(payload)
|
||||
|
||||
|
||||
class PolicyResolverLike(typing.Protocol):
|
||||
"""The bit of `policy_resolver.PolicyResolver` this module needs — kept a
|
||||
Protocol so egress_addon_core stays free of that import."""
|
||||
|
||||
def resolve(self, source_ip: str, identity_token: str = ...) -> "str | None":
|
||||
...
|
||||
|
||||
|
||||
def _config_from_policy(policy: "str | None") -> "Config":
|
||||
"""Parse a resolved policy blob into a Config, fail-closed: None / empty /
|
||||
unparseable all become a deny-all Config (no routes → every request
|
||||
blocked)."""
|
||||
if not policy:
|
||||
return Config(routes=()) # unattributed or empty → deny-all
|
||||
try:
|
||||
return load_config(policy)
|
||||
except ValueError:
|
||||
return Config(routes=()) # unparseable policy → deny
|
||||
|
||||
|
||||
def resolve_client_config(
|
||||
resolver: PolicyResolverLike, client_ip: str, identity_token: str = ""
|
||||
) -> "Config":
|
||||
"""The calling client's egress Config, resolved from the orchestrator via
|
||||
`resolver` and parsed — **fail-closed**. An unattributed client (None), a
|
||||
resolver error, or an unparseable policy all yield a deny-all Config (no
|
||||
routes → every request blocked). A compromised, absent, or confused
|
||||
orchestrator must never *widen* a bottle's egress."""
|
||||
try:
|
||||
policy = resolver.resolve(client_ip, identity_token)
|
||||
except Exception: # noqa: BLE001 # pylint: disable=broad-exception-caught
|
||||
return Config(routes=()) # orchestrator unreachable/errored → deny
|
||||
return _config_from_policy(policy)
|
||||
|
||||
|
||||
class ContextResolverLike(typing.Protocol):
|
||||
"""The bit of `policy_resolver.PolicyResolver` `resolve_client_context`
|
||||
needs — one round-trip returning policy, bottle id, and auth tokens."""
|
||||
|
||||
def resolve_policy_and_bottle_id(
|
||||
self, source_ip: str, identity_token: str = ...,
|
||||
) -> "tuple[str | None, str | None, dict[str, str]]":
|
||||
...
|
||||
|
||||
|
||||
def resolve_client_context(
|
||||
resolver: ContextResolverLike, client_ip: str, identity_token: str = "",
|
||||
) -> "tuple[Config, str, dict[str, str]]":
|
||||
"""The calling client's `(Config, bottle_id, tokens)` in one round-trip —
|
||||
**fail-closed**. The Config follows `resolve_client_config`'s deny-all
|
||||
rules; the bottle id is `""` whenever unattributed or the orchestrator
|
||||
errored (caller treats as "supervise unavailable", never another bottle's
|
||||
queue); `tokens` are the per-bottle upstream auth values the addon injects.
|
||||
One `/resolve` keys the egress policy, the supervise queue + safelist, and
|
||||
auth injection."""
|
||||
try:
|
||||
policy, bottle_id, tokens = resolver.resolve_policy_and_bottle_id(
|
||||
client_ip, identity_token,
|
||||
)
|
||||
except Exception: # noqa: BLE001 # pylint: disable=broad-exception-caught
|
||||
return Config(routes=()), "", {} # orchestrator unreachable/errored → deny
|
||||
return _config_from_policy(policy), (bottle_id or ""), tokens
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Match evaluation
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -613,7 +677,7 @@ def outbound_scan_headers(
|
||||
) -> dict[str, str]:
|
||||
"""Return request headers that should be included in outbound DLP.
|
||||
|
||||
Routes that inject sidecar-owned auth always strip the agent's
|
||||
Routes that inject gateway-owned auth always strip the agent's
|
||||
Authorization header before forwarding. Scanning that header first
|
||||
creates false positives for provider clients that insist on sending
|
||||
their own bearer-shaped placeholder, while still not changing what
|
||||
@@ -664,7 +728,7 @@ def scan_outbound(
|
||||
crlf_text: str | None = None,
|
||||
) -> ScanResult | None:
|
||||
# Lazy import to avoid circular deps and keep dlp_detectors optional
|
||||
# at import time (the sidecar copies it flat alongside this file).
|
||||
# at import time (the gateway copies it flat alongside this file).
|
||||
try:
|
||||
from dlp_detectors import ( # type: ignore[import-not-found]
|
||||
scan_crlf_injection,
|
||||
@@ -804,6 +868,10 @@ __all__ = [
|
||||
"is_git_push_request",
|
||||
"is_git_fetch_request",
|
||||
"load_config",
|
||||
"resolve_client_config",
|
||||
"resolve_client_context",
|
||||
"PolicyResolverLike",
|
||||
"ContextResolverLike",
|
||||
"match_route",
|
||||
"outbound_scan_headers",
|
||||
"parse_config",
|
||||
|
||||
@@ -6,8 +6,8 @@ and what the proxy does when an outbound detector matches a token
|
||||
kept apart from the request-time scan/decision flow in `egress_addon_core`
|
||||
so each half reads top-to-bottom without scrolling past the other.
|
||||
|
||||
Stdlib-only; ships flat into the sidecar bundle image alongside
|
||||
`egress_addon_core.py` — see `Dockerfile.sidecars`."""
|
||||
Stdlib-only; ships flat into the gateway image alongside
|
||||
`egress_addon_core.py` — see `Dockerfile.gateway`."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
#!/bin/sh
|
||||
# Egress daemon entrypoint inside the sidecar bundle (PRD 0024).
|
||||
# Egress daemon entrypoint inside the gateway (PRD 0024).
|
||||
#
|
||||
# Extracted verbatim from Dockerfile.egress's prior inline `sh -c`
|
||||
# ENTRYPOINT so the supervisor in bot_bottle/sidecar_init.py can
|
||||
# ENTRYPOINT so the supervisor in bot_bottle/gateway_init.py can
|
||||
# call it as a normal child. Behavior is unchanged:
|
||||
#
|
||||
# * Upstream proxy: when EGRESS_UPSTREAM_PROXY is set, switch
|
||||
@@ -22,7 +22,7 @@ set -e
|
||||
|
||||
# Pin mitmproxy's config dir to the bind-mount location of its CA
|
||||
# regardless of which user mitmdump runs as. In the legacy
|
||||
# four-sidecar setup (Dockerfile.egress, USER mitmproxy) this
|
||||
# four-daemon setup (Dockerfile.egress, USER mitmproxy) this
|
||||
# resolved naturally to `~mitmproxy/.mitmproxy`. In the PRD 0024
|
||||
# bundle (USER root) `~root/.mitmproxy` is empty, so without this
|
||||
# flag mitmdump would generate a fresh CA on the wrong path and
|
||||
|
||||
@@ -1,26 +1,26 @@
|
||||
"""Per-bottle sidecar supervisor (PRD 0024 chunk 1).
|
||||
"""Gateway data-plane supervisor (PRD 0070; PRD 0024 bundle shape).
|
||||
|
||||
PID 1 inside the `bot-bottle-sidecars` bundle image. Spawns
|
||||
PID 1 inside the `bot-bottle-gateway` data-plane image. Spawns
|
||||
the configured daemons (egress, git-gate, supervise),
|
||||
forwards SIGTERM/SIGINT to each child, and propagates per-daemon
|
||||
stdout+stderr to the container log with a `[name] ` prefix.
|
||||
|
||||
Failure policy (interim): when a child dies unexpectedly, the
|
||||
supervisor logs the death and leaves the surviving children
|
||||
running. The bundle stays up; whatever the dead daemon served
|
||||
running. The gateway stays up; whatever the dead daemon served
|
||||
will start failing, surfacing in the agent's own error path.
|
||||
The supervisor itself exits only when (a) the operator/compose
|
||||
sends SIGTERM/SIGINT, or (b) every child has died.
|
||||
The supervisor itself exits only when (a) the operator sends
|
||||
SIGTERM/SIGINT, or (b) every child has died.
|
||||
|
||||
Failure policy (eventual): on unexpected death, the supervisor
|
||||
restarts the daemon and emits a notification to the supervise
|
||||
sidecar so the operator sees the event. That lands in a later
|
||||
PR; the interim policy is "don't take the bundle down for one
|
||||
daemon so the operator sees the event. That lands in a later
|
||||
PR; the interim policy is "don't take the gateway down for one
|
||||
sick daemon."
|
||||
|
||||
Daemon subset is env-driven. The compose renderer narrows it via
|
||||
`BOT_BOTTLE_SIDECAR_DAEMONS=egress` for bottles that
|
||||
don't use git-gate or supervise. Default: all daemons.
|
||||
Daemon subset is env-driven via `BOT_BOTTLE_GATEWAY_DAEMONS=egress`
|
||||
for callers that don't use git-gate or supervise. Default: all
|
||||
daemons.
|
||||
|
||||
Stdlib-only by design — adding supervisord/s6/runit for four
|
||||
daemons is heavier than this script.
|
||||
@@ -103,8 +103,8 @@ def _selected_daemons(
|
||||
env: dict[str, str],
|
||||
all_daemons: Sequence[_DaemonSpec] | None = None,
|
||||
) -> tuple[_DaemonSpec, ...]:
|
||||
"""Filter the daemon set by the BOT_BOTTLE_SIDECAR_DAEMONS env
|
||||
var. Unknown names in the list are ignored — the renderer is the
|
||||
"""Filter the daemon set by the BOT_BOTTLE_GATEWAY_DAEMONS env
|
||||
var. Unknown names in the list are ignored — the caller is the
|
||||
source of truth for which daemons are wired.
|
||||
|
||||
`all_daemons` defaults to `_DAEMONS` resolved at call time (not
|
||||
@@ -112,7 +112,7 @@ def _selected_daemons(
|
||||
`_DAEMONS` and have the new value take effect."""
|
||||
if all_daemons is None:
|
||||
all_daemons = _DAEMONS
|
||||
raw = env.get("BOT_BOTTLE_SIDECAR_DAEMONS", "").strip()
|
||||
raw = env.get("BOT_BOTTLE_GATEWAY_DAEMONS", "").strip()
|
||||
if not raw:
|
||||
return tuple(all_daemons)
|
||||
wanted = {n.strip() for n in raw.split(",") if n.strip()}
|
||||
@@ -120,7 +120,7 @@ def _selected_daemons(
|
||||
|
||||
|
||||
def _log(msg: str) -> None:
|
||||
sys.stdout.write(f"sidecar-init: {msg}\n")
|
||||
sys.stdout.write(f"gateway-init: {msg}\n")
|
||||
sys.stdout.flush()
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
"""Per-agent git-gate (PRD 0008).
|
||||
|
||||
A third per-agent sidecar that fronts the bottle's declared git
|
||||
A third per-agent daemon that fronts the bottle's declared git
|
||||
upstreams as a transparent mirror. Each `bottle.git` entry maps to
|
||||
a bare repo on the gate; `git daemon` serves the bare repos over
|
||||
`git://<gate>/<name>.git`. Two hooks make the mirror bidirectional:
|
||||
@@ -15,7 +15,7 @@ a bare repo on the gate; `git daemon` serves the bare repos over
|
||||
|
||||
The agent never sees the upstream credential under either path.
|
||||
|
||||
Why a separate sidecar (not folded into egress or ssh-gate): the
|
||||
Why a separate daemon (not folded into egress or ssh-gate): the
|
||||
gate is the only one of the three that holds upstream push
|
||||
credentials. Mixing it with egress would put push creds in the
|
||||
same blast radius as internet-facing TLS interception; mixing it
|
||||
@@ -23,7 +23,7 @@ with ssh-gate would force ssh-gate above L4 and into git-protocol
|
||||
land. See `docs/prds/0008-git-gate.md`.
|
||||
|
||||
This module defines the abstract gate (`GitGate`) and its plan
|
||||
dataclass (`GitGatePlan`). The sidecar's start/stop lifecycle is
|
||||
dataclass (`GitGatePlan`). The gateway's start/stop lifecycle is
|
||||
backend-specific and lives on concrete subclasses (see
|
||||
`bot_bottle/backend/docker/git_gate.py`)."""
|
||||
|
||||
@@ -46,6 +46,7 @@ from .git_gate_render import (
|
||||
git_gate_known_hosts_line,
|
||||
git_gate_render_access_hook,
|
||||
git_gate_render_entrypoint,
|
||||
git_gate_render_provision,
|
||||
git_gate_render_gitconfig,
|
||||
git_gate_render_hook,
|
||||
git_gate_upstreams_for_bottle,
|
||||
@@ -85,7 +86,7 @@ class GitGatePlan:
|
||||
|
||||
class GitGate(ABC):
|
||||
"""The per-agent git-gate. Encapsulates the host-side prepare
|
||||
(upstream lift + entrypoint/hook render); the sidecar's
|
||||
(upstream lift + entrypoint/hook render); the gateway's
|
||||
start/stop lifecycle is backend-specific and lives on concrete
|
||||
subclasses."""
|
||||
|
||||
@@ -155,6 +156,7 @@ __all__ = [
|
||||
"git_gate_render_gitconfig",
|
||||
"git_gate_known_hosts_line",
|
||||
"git_gate_render_entrypoint",
|
||||
"git_gate_render_provision",
|
||||
"git_gate_render_hook",
|
||||
"git_gate_render_access_hook",
|
||||
"provision_git_gate_dynamic_keys",
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
"""Pure host-side rendering for the per-agent git-gate (PRD 0008).
|
||||
|
||||
Builds the agent's `.gitconfig` insteadOf rewrites, the known_hosts
|
||||
line, and the entrypoint / pre-receive / access-hook scripts the sidecar
|
||||
line, and the entrypoint / pre-receive / access-hook scripts the gateway
|
||||
runs. No docker or forge calls — exposed for tests and reuse across
|
||||
backends. Split out of `git_gate.py` so the control surface (`GitGate`)
|
||||
and the deploy-key lifecycle (`git_gate_provision`) each read on their
|
||||
@@ -9,13 +9,14 @@ own; `git_gate` re-exports these names for API stability."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import re
|
||||
import shlex
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
|
||||
from .manifest import ManifestBottle, ManifestGitEntry
|
||||
|
||||
# Short network alias for git-gate inside the sidecar bundle. The
|
||||
# Short network alias for git-gate inside the gateway. The
|
||||
# agent's `.gitconfig` insteadOf rewrites resolve through this name.
|
||||
GIT_GATE_HOSTNAME = "git-gate"
|
||||
# Shared timeout (seconds) for all git-gate subprocess and CGI calls:
|
||||
@@ -37,7 +38,7 @@ class GitGateUpstream:
|
||||
KnownHostKey string from the manifest; the gate's start step
|
||||
materialises it into a known_hosts file if non-empty.
|
||||
|
||||
the gate credential paths inside the running sidecar."""
|
||||
the gate credential paths inside the running gateway."""
|
||||
|
||||
name: str
|
||||
upstream_url: str
|
||||
@@ -125,22 +126,18 @@ def git_gate_known_hosts_line(host: str, port: str, key: str) -> str:
|
||||
return f"{target} {key}\n"
|
||||
|
||||
|
||||
def git_gate_render_entrypoint(upstreams: tuple[GitGateUpstream, ...]) -> str:
|
||||
"""Posix-sh entrypoint. One `init_repo` call per upstream, then
|
||||
`exec git daemon`. The function reads
|
||||
`/git-gate/creds/<name>-{key,known_hosts}` (bind-mounted into
|
||||
the bundle by the renderer) and wires them into each bare repo's
|
||||
config; the access-hook + pre-receive hook pick those paths up
|
||||
at fetch / push time."""
|
||||
lines = [
|
||||
"#!/bin/sh",
|
||||
"set -eu",
|
||||
"",
|
||||
def _git_gate_init_repo_fn(repo_root: str, creds_dir: str) -> list[str]:
|
||||
"""The `init_repo` shell function, parameterized by the bare-repo root
|
||||
and the per-bottle creds dir. Single source of the credential-wiring
|
||||
logic, shared by the single-tenant daemon entrypoint (`/git`,
|
||||
`/git-gate/creds`) and the consolidated per-bottle provisioning
|
||||
(`/git/<bottle_id>`, `/git-gate/creds/<bottle_id>`)."""
|
||||
return [
|
||||
"init_repo() {",
|
||||
" name=$1",
|
||||
" upstream_url=$2",
|
||||
" keyfile=/git-gate/creds/${name}-key",
|
||||
" hostsfile=/git-gate/creds/${name}-known_hosts",
|
||||
f" keyfile={creds_dir}/${{name}}-key",
|
||||
f" hostsfile={creds_dir}/${{name}}-known_hosts",
|
||||
"",
|
||||
# `|| true`: PRD 0018 chunk 3+ bind-mounts these RO from the
|
||||
# host, so chmod-syscalls fail with EROFS. The files already
|
||||
@@ -153,14 +150,14 @@ def git_gate_render_entrypoint(upstreams: tuple[GitGateUpstream, ...]) -> str:
|
||||
" chmod 600 \"$hostsfile\" 2>/dev/null || true",
|
||||
" fi",
|
||||
"",
|
||||
" repo=/git/${name}.git",
|
||||
f" repo={repo_root}/${{name}}.git",
|
||||
" if [ ! -d \"$repo\" ]; then",
|
||||
" git init --bare \"$repo\" >/dev/null",
|
||||
# --mirror=fetch sets remote.origin.fetch = +refs/*:refs/* so",
|
||||
# a later `git fetch origin` mirrors the upstream's full ref",
|
||||
# graph (heads, tags, notes) into the bare repo at canonical",
|
||||
# paths. It does NOT set remote.origin.mirror=true, so an",
|
||||
# explicit `git push origin <ref>:<ref>` still pushes one ref.",
|
||||
# --mirror=fetch sets remote.origin.fetch = +refs/*:refs/* so a later
|
||||
# `git fetch origin` mirrors the upstream's full ref graph (heads,
|
||||
# tags, notes) into the bare repo at canonical paths. It does NOT set
|
||||
# remote.origin.mirror=true, so an explicit `git push origin
|
||||
# <ref>:<ref>` still pushes one ref.
|
||||
" git -C \"$repo\" remote add --mirror=fetch origin \"$upstream_url\"",
|
||||
" fi",
|
||||
" git -C \"$repo\" config git-gate.identityFile \"$keyfile\"",
|
||||
@@ -170,9 +167,19 @@ def git_gate_render_entrypoint(upstreams: tuple[GitGateUpstream, ...]) -> str:
|
||||
" git -C \"$repo\" config http.receivepack true",
|
||||
" install -m 755 /etc/git-gate/pre-receive \"$repo/hooks/pre-receive\"",
|
||||
"}",
|
||||
"",
|
||||
"mkdir -p /git",
|
||||
]
|
||||
|
||||
|
||||
def git_gate_render_entrypoint(upstreams: tuple[GitGateUpstream, ...]) -> str:
|
||||
"""Posix-sh entrypoint. One `init_repo` call per upstream, then
|
||||
`exec git daemon`. The function reads
|
||||
`/git-gate/creds/<name>-{key,known_hosts}` (bind-mounted into
|
||||
the bundle by the renderer) and wires them into each bare repo's
|
||||
config; the access-hook + pre-receive hook pick those paths up
|
||||
at fetch / push time."""
|
||||
lines = ["#!/bin/sh", "set -eu", ""]
|
||||
lines += _git_gate_init_repo_fn("/git", "/git-gate/creds")
|
||||
lines += ["", "mkdir -p /git"]
|
||||
for u in upstreams:
|
||||
lines.append(f"init_repo {shlex.quote(u.name)} {shlex.quote(u.upstream_url)}")
|
||||
lines.extend([
|
||||
@@ -190,6 +197,35 @@ def git_gate_render_entrypoint(upstreams: tuple[GitGateUpstream, ...]) -> str:
|
||||
return "\n".join(lines) + "\n"
|
||||
|
||||
|
||||
# A bottle id namespaces the consolidated gateway's repo + creds dirs; it is
|
||||
# embedded unquoted in the provisioning script, so restrict it to a shell- and
|
||||
# path-safe alphabet (registry ids are token_hex — this is defense in depth).
|
||||
_SAFE_BOTTLE_ID = re.compile(r"[A-Za-z0-9_-]+")
|
||||
|
||||
|
||||
def git_gate_render_provision(
|
||||
bottle_id: str, upstreams: tuple[GitGateUpstream, ...],
|
||||
) -> str:
|
||||
"""Posix-sh script that provisions ONE bottle's bare repos into the
|
||||
consolidated gateway (PRD 0070), under `/git/<bottle_id>/` with creds
|
||||
read from `/git-gate/creds/<bottle_id>/`. Init-only — no `git daemon`,
|
||||
since the shared gateway already serves every bottle; run inside the
|
||||
running gateway when the bottle is registered.
|
||||
|
||||
Isolating each bottle's repo root and creds dir by id is what keeps one
|
||||
bottle's push credentials out of another's repos on the shared gateway."""
|
||||
if not _SAFE_BOTTLE_ID.fullmatch(bottle_id):
|
||||
raise ValueError(f"git-gate: unsafe bottle id {bottle_id!r}")
|
||||
repo_root = f"/git/{bottle_id}"
|
||||
creds_dir = f"/git-gate/creds/{bottle_id}"
|
||||
lines = ["#!/bin/sh", "set -eu", ""]
|
||||
lines += _git_gate_init_repo_fn(repo_root, creds_dir)
|
||||
lines += ["", f"mkdir -p {shlex.quote(repo_root)}"]
|
||||
for u in upstreams:
|
||||
lines.append(f"init_repo {shlex.quote(u.name)} {shlex.quote(u.upstream_url)}")
|
||||
return "\n".join(lines) + "\n"
|
||||
|
||||
|
||||
def git_gate_render_hook() -> str:
|
||||
"""The shared pre-receive hook: gitleaks-scan all incoming refs,
|
||||
then forward each accepted ref to the real upstream (`origin`)
|
||||
|
||||
@@ -2,10 +2,19 @@
|
||||
|
||||
Used where `git://` push traffic over a host-published Docker port can
|
||||
hang before receive-pack reaches hooks (e.g. the firecracker backend,
|
||||
where the guest reaches the sidecar over the point-to-point TAP). The
|
||||
where the guest reaches the gateway over the point-to-point TAP). The
|
||||
wrapper serves the same `/git/*.git` bare repos through
|
||||
`git http-backend`, so pre-receive and upstream forwarding remain the
|
||||
git-gate enforcement point.
|
||||
|
||||
Consolidated (PRD 0070): when `BOT_BOTTLE_ORCHESTRATOR_URL` is set, one
|
||||
shared gateway serves every bottle, and each request is served from the
|
||||
calling bottle's repo namespace (`<root>/<bottle_id>`), attributed from
|
||||
the unspoofable source IP via the orchestrator. Per-repo credentials +
|
||||
hooks scope by repo directory, so isolating the *root* per bottle isolates
|
||||
its creds too. Unattributed clients fail closed (404). Unset → the legacy
|
||||
per-bottle single-tenant flat root, unchanged — a transitional path that
|
||||
gets stripped out once every backend runs the consolidated gateway.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
@@ -13,16 +22,89 @@ from __future__ import annotations
|
||||
import os
|
||||
import subprocess
|
||||
import sys
|
||||
import typing
|
||||
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
|
||||
from pathlib import Path
|
||||
from urllib.parse import urlsplit
|
||||
|
||||
# policy_resolver ships flat alongside this file in the gateway
|
||||
# image (see Dockerfile.gateway); the bot_bottle.* fallback is the
|
||||
# host-side / test path. Mirrors egress_addon's import shape.
|
||||
try:
|
||||
from policy_resolver import ( # type: ignore[import-not-found]
|
||||
PolicyResolveError,
|
||||
PolicyResolver,
|
||||
)
|
||||
except ImportError: # pragma: no cover - host-side path
|
||||
from bot_bottle.policy_resolver import PolicyResolveError, PolicyResolver
|
||||
|
||||
|
||||
DEFAULT_PORT = 9420
|
||||
|
||||
# Consolidated (multi-tenant) mode: when this points at the per-host
|
||||
# orchestrator's control plane, the backend serves each request from the
|
||||
# *calling* bottle's repo namespace, selected by source IP, instead of a
|
||||
# single flat repo root. Unset → legacy per-bottle single-tenant mode
|
||||
# (unchanged). Same env the egress addon reads, so one orchestrator setting
|
||||
# flips the whole shared gateway multi-tenant.
|
||||
ORCHESTRATOR_URL_ENV = "BOT_BOTTLE_ORCHESTRATOR_URL"
|
||||
|
||||
# App-layer identity token (defense-in-depth over the source-IP invariant);
|
||||
# the agent injects it, the backend reads it for attribution and never
|
||||
# forwards it to `git http-backend`. Mirrors egress_addon.IDENTITY_HEADER
|
||||
# (duplicated, not imported: egress_addon pulls in mitmproxy).
|
||||
IDENTITY_HEADER = "x-bot-bottle-identity"
|
||||
|
||||
# Default flat repo root (single-tenant, and the base under which
|
||||
# consolidated mode nests each sandbox's namespace).
|
||||
DEFAULT_REPO_ROOT = "/git"
|
||||
|
||||
|
||||
class ResolverLike(typing.Protocol):
|
||||
"""Structural type for the resolver `resolve_sandbox_root` needs — just
|
||||
`resolve_bottle_id`. A Protocol so tests can pass a fake without
|
||||
importing PolicyResolver (mirrors egress_addon_core.PolicyResolverLike)."""
|
||||
|
||||
def resolve_bottle_id(
|
||||
self, source_ip: str, identity_token: str = ...,
|
||||
) -> "str | None": ...
|
||||
|
||||
|
||||
def resolve_sandbox_root(
|
||||
resolver: "ResolverLike | None",
|
||||
base_root: Path,
|
||||
source_ip: str,
|
||||
identity_token: str = "",
|
||||
) -> Path | None:
|
||||
"""The per-sandbox repo root to serve this request from, or None to
|
||||
deny (404).
|
||||
|
||||
Single-tenant (`resolver is None`): the flat `base_root`, unchanged.
|
||||
NOTE: this legacy per-bottle single-tenant path is transitional — it
|
||||
will be stripped out once every backend runs the consolidated gateway
|
||||
(PRD 0070), leaving only the source-IP-attributed path below.
|
||||
|
||||
Consolidated: `base_root/<bottle_id>`, where the sandbox is attributed
|
||||
from the source IP via the orchestrator. Fail-closed — an unattributed
|
||||
client, a resolver error, or a namespace that would escape `base_root`
|
||||
all deny, so one sandbox can never reach another's repos."""
|
||||
if resolver is None:
|
||||
return base_root
|
||||
try:
|
||||
bottle_id = resolver.resolve_bottle_id(source_ip, identity_token)
|
||||
except PolicyResolveError:
|
||||
return None # orchestrator unreachable/errored → deny
|
||||
if not bottle_id:
|
||||
return None # unattributed → deny
|
||||
base = base_root.resolve()
|
||||
namespace = (base / bottle_id).resolve()
|
||||
if base not in namespace.parents:
|
||||
return None # bottle_id tried to escape the root → deny
|
||||
return namespace
|
||||
|
||||
# Mirrors git_gate_render.GIT_GATE_TIMEOUT_SECS. Duplicated rather than
|
||||
# imported: this module ships as a flat top-level sibling in the sidecar
|
||||
# bundle image (see Dockerfile.sidecars), not as part of the bot_bottle
|
||||
# imported: this module ships as a flat top-level sibling in the gateway
|
||||
# bundle image (see Dockerfile.gateway), not as part of the bot_bottle
|
||||
# package, so `bot_bottle.git_gate` and its dependency chain aren't
|
||||
# available at runtime.
|
||||
GIT_GATE_TIMEOUT_SECS = 15
|
||||
@@ -40,10 +122,25 @@ class GitHttpHandler(BaseHTTPRequestHandler):
|
||||
def do_POST(self) -> None:
|
||||
self._run_backend()
|
||||
|
||||
def _sandbox_root(self) -> Path | None:
|
||||
"""This request's per-sandbox repo root, or None to deny. Single-tenant
|
||||
unless the server was started with a resolver (consolidated mode), in
|
||||
which case the root is the calling sandbox's source-IP-selected
|
||||
namespace. `GIT_PROJECT_ROOT` keeps git's own env-var name."""
|
||||
base = Path(os.environ.get("GIT_PROJECT_ROOT", DEFAULT_REPO_ROOT))
|
||||
resolver = getattr(self.server, "policy_resolver", None)
|
||||
token = self.headers.get(IDENTITY_HEADER, "")
|
||||
return resolve_sandbox_root(resolver, base, self.client_address[0], token)
|
||||
|
||||
def _run_backend(self) -> None:
|
||||
sandbox_root = self._sandbox_root()
|
||||
if sandbox_root is None:
|
||||
# Unattributed / resolver error: deny before touching any repo.
|
||||
self.send_error(404)
|
||||
return
|
||||
parsed = urlsplit(self.path)
|
||||
if self._is_upload_pack(parsed.path, parsed.query):
|
||||
repo_dir = self._repo_dir(parsed.path)
|
||||
repo_dir = self._repo_dir(sandbox_root, parsed.path)
|
||||
if repo_dir is None:
|
||||
self.send_error(404)
|
||||
return
|
||||
@@ -77,7 +174,7 @@ class GitHttpHandler(BaseHTTPRequestHandler):
|
||||
return
|
||||
env = os.environ.copy()
|
||||
env.update({
|
||||
"GIT_PROJECT_ROOT": os.environ.get("GIT_PROJECT_ROOT", "/git"),
|
||||
"GIT_PROJECT_ROOT": str(sandbox_root),
|
||||
"GIT_HTTP_EXPORT_ALL": "1",
|
||||
"REQUEST_METHOD": self.command,
|
||||
"PATH_INFO": parsed.path,
|
||||
@@ -91,6 +188,14 @@ class GitHttpHandler(BaseHTTPRequestHandler):
|
||||
"SERVER_PORT": str(self.server.server_port), # type: ignore
|
||||
"SERVER_PROTOCOL": self.request_version,
|
||||
})
|
||||
# Consolidated mode: attribute the gitleaks-allow supervise proposal
|
||||
# (written by receive-pack's pre-receive hook, a child of the CGI we
|
||||
# spawn below) to the calling bottle. The namespaced root is
|
||||
# `<base>/<bottle_id>`, so its final component is the bottle id — the
|
||||
# same per-bottle key egress uses. Single-tenant leaves the hook's
|
||||
# container-stamped SUPERVISE_BOTTLE_SLUG untouched.
|
||||
if getattr(self.server, "policy_resolver", None) is not None:
|
||||
env["SUPERVISE_BOTTLE_SLUG"] = sandbox_root.name
|
||||
for header, variable in (
|
||||
("accept", "HTTP_ACCEPT"),
|
||||
("content-encoding", "HTTP_CONTENT_ENCODING"),
|
||||
@@ -123,8 +228,8 @@ class GitHttpHandler(BaseHTTPRequestHandler):
|
||||
)
|
||||
self._write_cgi_response(proc.stdout)
|
||||
|
||||
def _repo_dir(self, path: str) -> Path | None:
|
||||
root = Path(os.environ.get("GIT_PROJECT_ROOT", "/git")).resolve()
|
||||
def _repo_dir(self, sandbox_root: Path, path: str) -> Path | None:
|
||||
root = sandbox_root.resolve()
|
||||
relative = path.lstrip("/").split(".git", 1)[0] + ".git"
|
||||
candidate = (root / relative).resolve()
|
||||
if root not in (candidate, *candidate.parents):
|
||||
@@ -181,7 +286,13 @@ class GitHttpHandler(BaseHTTPRequestHandler):
|
||||
def main() -> int:
|
||||
port = int(os.environ.get("GIT_HTTP_PORT", str(DEFAULT_PORT)))
|
||||
server = ThreadingHTTPServer(("0.0.0.0", port), GitHttpHandler)
|
||||
sys.stdout.write(f"git-http listening on 0.0.0.0:{port}\n")
|
||||
orch_url = os.environ.get(ORCHESTRATOR_URL_ENV, "").strip()
|
||||
# Consolidated mode: resolve each request's sandbox namespace by source
|
||||
# IP. Absent → single-tenant (flat repo root); behaviour unchanged.
|
||||
resolver = PolicyResolver(orch_url) if orch_url else None
|
||||
server.policy_resolver = resolver # type: ignore[attr-defined]
|
||||
mode = "multi-tenant" if orch_url else "single-tenant"
|
||||
sys.stdout.write(f"git-http listening on 0.0.0.0:{port} ({mode})\n")
|
||||
sys.stdout.flush()
|
||||
server.serve_forever()
|
||||
return 0
|
||||
|
||||
@@ -17,7 +17,7 @@ class ManifestAgentProvider:
|
||||
|
||||
`template` selects a built-in launch/runtime contract. `dockerfile`
|
||||
optionally points at a custom agent-image Dockerfile while leaving
|
||||
bot-bottle's sidecar infrastructure intact.
|
||||
bot-bottle's gateway infrastructure intact.
|
||||
|
||||
`auth_token` names the host env var that holds the provider's OAuth
|
||||
token (Claude only). The provisioner injects a provider-owned egress
|
||||
@@ -26,7 +26,7 @@ class ManifestAgentProvider:
|
||||
so the Claude Code CLI starts.
|
||||
|
||||
`forward_host_credentials` forwards the host Codex auth token into
|
||||
the egress sidecar (Codex only).
|
||||
the egress daemon (Codex only).
|
||||
"""
|
||||
|
||||
template: str = "claude"
|
||||
|
||||
@@ -39,10 +39,10 @@ class ManifestBottle:
|
||||
# identity without any git-gate.repos upstreams, and vice versa.
|
||||
git_user: ManifestGitUser = field(default_factory=ManifestGitUser)
|
||||
egress: ManifestEgressConfig = field(default_factory=ManifestEgressConfig)
|
||||
# Per-bottle stuck-recovery sidecar (PRD 0013). When true (the
|
||||
# Per-bottle stuck-recovery daemon (PRD 0013). When true (the
|
||||
# default, issue #249), the launch step brings up a supervise
|
||||
# sidecar that exposes egress MCP tools to the agent. Set
|
||||
# `supervise: false` to skip the sidecar.
|
||||
# daemon that exposes egress MCP tools to the agent. Set
|
||||
# `supervise: false` to skip the gateway.
|
||||
supervise: bool = True
|
||||
|
||||
@classmethod
|
||||
@@ -61,7 +61,7 @@ class ManifestBottle:
|
||||
raise ManifestError(
|
||||
f"bottle '{name}' has an 'ssh' field, which has been removed "
|
||||
f"(PRD 0009). Declare upstreams under 'git-gate.repos' with "
|
||||
f"url + identity + host_key; the git-gate sidecar (PRD 0008) "
|
||||
f"url + identity + host_key; the git-gate daemon (PRD 0008) "
|
||||
f"holds the credential and gitleaks-scans pushes."
|
||||
)
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
"""Per-host orchestrator service (PRD 0070).
|
||||
|
||||
A single persistent per-host service that will run the sidecar functions
|
||||
A single persistent per-host service that will run the gateway functions
|
||||
(egress / git-gate / supervise), coordinate with the console, and broker
|
||||
agent launches. This package is being built bottom-up, starting with the
|
||||
backend-neutral "consolidation core" that needs no VM packaging:
|
||||
@@ -10,15 +10,15 @@ backend-neutral "consolidation core" that needs no VM packaging:
|
||||
* `broker` — the signed, structured launch-request contract + a
|
||||
`LaunchBroker` (stub for the harness) that verifies
|
||||
provenance before acting.
|
||||
* `sidecar` — the consolidated per-host sidecar: a `Sidecar`
|
||||
* `gateway` — the consolidated per-host gateway: a `Gateway`
|
||||
lifecycle contract (idempotent singleton) + a
|
||||
`DockerSidecar` impl. One sidecar shared by all
|
||||
`DockerGateway` impl. One gateway shared by all
|
||||
bottles instead of one per bottle.
|
||||
* `service` — the `Orchestrator`: owns the registry, brokers the
|
||||
launch lifecycle (launch/teardown), manages the
|
||||
shared sidecar, attributes.
|
||||
shared gateway, attributes.
|
||||
* `control_plane` — the HTTP control-plane RPC (launch / teardown /
|
||||
list / attribute / sidecar / health).
|
||||
list / attribute / gateway / health).
|
||||
|
||||
The actual backend-native launch (a real docker/firecracker broker) and
|
||||
the egress/git/supervise data plane land in later slices once this core is
|
||||
@@ -38,7 +38,7 @@ from .broker import (
|
||||
verify_request,
|
||||
)
|
||||
from .docker_broker import DockerBroker, DockerBrokerError
|
||||
from .sidecar import DockerSidecar, Sidecar, SidecarError
|
||||
from .gateway import DockerGateway, Gateway, GatewayError
|
||||
from .service import Orchestrator
|
||||
from .control_plane import ControlPlaneServer, dispatch, make_server
|
||||
|
||||
@@ -52,9 +52,9 @@ __all__ = [
|
||||
"StubBroker",
|
||||
"DockerBroker",
|
||||
"DockerBrokerError",
|
||||
"Sidecar",
|
||||
"DockerSidecar",
|
||||
"SidecarError",
|
||||
"Gateway",
|
||||
"DockerGateway",
|
||||
"GatewayError",
|
||||
"sign_request",
|
||||
"verify_request",
|
||||
"Orchestrator",
|
||||
|
||||
@@ -21,7 +21,7 @@ from .control_plane import make_server
|
||||
from .docker_broker import DockerBroker
|
||||
from .registry import RegistryStore, default_db_path
|
||||
from .service import Orchestrator
|
||||
from .sidecar import DockerSidecar, Sidecar
|
||||
from .gateway import DockerGateway, Gateway
|
||||
|
||||
|
||||
def main(argv: list[str] | None = None) -> int:
|
||||
@@ -38,8 +38,8 @@ def main(argv: list[str] | None = None) -> int:
|
||||
help="launch broker: 'stub' records requests; 'docker' runs containers",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--sidecar-image", default=None,
|
||||
help="if set, run one consolidated per-host sidecar from this image",
|
||||
"--gateway", action="store_true",
|
||||
help="run one consolidated per-host gateway (build-if-missing)",
|
||||
)
|
||||
args = parser.parse_args(argv)
|
||||
|
||||
@@ -51,13 +51,20 @@ def main(argv: list[str] | None = None) -> int:
|
||||
# anything; 'docker' runs real containers (firecracker drops in later).
|
||||
secret = secrets.token_bytes(32)
|
||||
broker: LaunchBroker = DockerBroker(secret) if args.broker == "docker" else StubBroker(secret)
|
||||
sidecar: Sidecar | None = DockerSidecar(args.sidecar_image) if args.sidecar_image else None
|
||||
orchestrator = Orchestrator(registry, broker, secret, sidecar)
|
||||
# Standalone `--gateway` (not the consolidated flow, where the host
|
||||
# lifecycle runs the gateway). The gateway resolves against this same
|
||||
# process; the URL is only reachable when they share a docker network.
|
||||
gateway: Gateway | None = (
|
||||
DockerGateway(orchestrator_url=f"http://{args.host}:{args.port}")
|
||||
if args.gateway else None
|
||||
)
|
||||
orchestrator = Orchestrator(registry, broker, secret, gateway)
|
||||
|
||||
# One persistent per-host sidecar, shared by every bottle (idempotent).
|
||||
if sidecar is not None:
|
||||
orchestrator.ensure_sidecar()
|
||||
log.info("consolidated sidecar ensured", context={"name": sidecar.name})
|
||||
# One persistent per-host gateway, shared by every bottle: build the
|
||||
# bundle image if missing, then bring the singleton up (idempotent).
|
||||
if gateway is not None:
|
||||
orchestrator.ensure_gateway()
|
||||
log.info("consolidated gateway ensured", context={"name": gateway.name})
|
||||
|
||||
server = make_server(orchestrator, host=args.host, port=args.port)
|
||||
bound_host, bound_port = server.server_address[0], server.server_address[1]
|
||||
|
||||
@@ -9,7 +9,7 @@ The request it sends is:
|
||||
request can't be coerced into launching an arbitrary payload; and
|
||||
* **signed** — wrapped as a compact JWS/JWT the broker verifies before
|
||||
acting, so a *compromised co-located component* (an agent-facing
|
||||
sidecar, say) can't forge a launch. This is the concrete form of the
|
||||
gateway, say) can't forge a launch. This is the concrete form of the
|
||||
"structured requests only" rule in the PRD security review.
|
||||
|
||||
Signing is **HS256** over a secret shared by the orchestrator (signer) and
|
||||
|
||||
@@ -0,0 +1,144 @@
|
||||
"""Host-side control-plane client (PRD 0070).
|
||||
|
||||
The launch path talks to the orchestrator over its HTTP control plane to
|
||||
register, re-policy, and tear down bottles — the counterpart to the
|
||||
gateway-side `PolicyResolver` (which only reads `/resolve`). Where
|
||||
`PolicyResolver` is fail-closed and lives in the untrusted data plane, this
|
||||
is the trusted control-plane caller: a non-success response is an error the
|
||||
launch path must surface, not silently swallow.
|
||||
|
||||
Stdlib-only, so the CLI can drive the orchestrator without any dependency.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import urllib.error
|
||||
import urllib.request
|
||||
from dataclasses import dataclass
|
||||
|
||||
DEFAULT_TIMEOUT_SECONDS = 5.0
|
||||
|
||||
|
||||
class OrchestratorClientError(RuntimeError):
|
||||
"""A control-plane call failed (unreachable, or an unexpected status)."""
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class RegisteredBottle:
|
||||
"""What `POST /bottles` returns: the minted bottle id and the per-bottle
|
||||
identity token the agent presents for app-layer attribution."""
|
||||
|
||||
bottle_id: str
|
||||
identity_token: str
|
||||
|
||||
|
||||
class OrchestratorClient:
|
||||
"""Trusted host-side client for the orchestrator control plane."""
|
||||
|
||||
def __init__(self, base_url: str, *, timeout: float = DEFAULT_TIMEOUT_SECONDS) -> None:
|
||||
self._base = base_url.rstrip("/")
|
||||
self._timeout = timeout
|
||||
|
||||
def _request(
|
||||
self, method: str, path: str, body: dict[str, object] | None = None,
|
||||
) -> tuple[int, dict[str, object]]:
|
||||
"""Send one request; return `(status, payload)`. Raises
|
||||
`OrchestratorClientError` only when the orchestrator can't be reached
|
||||
or returns malformed data — HTTP *status* codes are returned so
|
||||
callers can treat 404 as a meaningful "no such bottle"."""
|
||||
data = json.dumps(body).encode() if body is not None else None
|
||||
headers = {"Content-Type": "application/json"} if data is not None else {}
|
||||
req = urllib.request.Request(
|
||||
f"{self._base}{path}", data=data, method=method, headers=headers,
|
||||
)
|
||||
try:
|
||||
with urllib.request.urlopen(req, timeout=self._timeout) as resp:
|
||||
raw = resp.read()
|
||||
payload = json.loads(raw) if raw else {}
|
||||
return resp.status, payload if isinstance(payload, dict) else {}
|
||||
except urllib.error.HTTPError as e:
|
||||
# A structured error response still carries a usable status.
|
||||
try:
|
||||
payload = json.loads(e.read() or b"{}")
|
||||
except (ValueError, OSError):
|
||||
payload = {}
|
||||
return e.code, payload if isinstance(payload, dict) else {}
|
||||
except (urllib.error.URLError, TimeoutError, OSError, ValueError) as e:
|
||||
raise OrchestratorClientError(f"{method} {path}: {e}") from e
|
||||
|
||||
def _ok(self, method: str, path: str, body: dict[str, object] | None = None) -> dict[str, object]:
|
||||
"""`_request` that requires a 2xx, raising otherwise."""
|
||||
status, payload = self._request(method, path, body)
|
||||
if not 200 <= status < 300:
|
||||
detail = payload.get("error", "")
|
||||
raise OrchestratorClientError(f"{method} {path}: HTTP {status} {detail}".rstrip())
|
||||
return payload
|
||||
|
||||
def health(self) -> bool:
|
||||
"""True iff the control plane answers `GET /health` with 200."""
|
||||
try:
|
||||
status, _ = self._request("GET", "/health")
|
||||
except OrchestratorClientError:
|
||||
return False
|
||||
return status == 200
|
||||
|
||||
def register_bottle(
|
||||
self,
|
||||
source_ip: str,
|
||||
*,
|
||||
image_ref: str = "",
|
||||
metadata: str = "",
|
||||
policy: str = "",
|
||||
tokens: dict[str, str] | None = None,
|
||||
) -> RegisteredBottle:
|
||||
"""Register a bottle and broker its launch (`POST /bottles`). `tokens`
|
||||
are the per-bottle egress auth values (env_name -> value) the
|
||||
orchestrator holds in memory for the gateway to inject. Returns the
|
||||
minted id + identity token."""
|
||||
payload = self._ok("POST", "/bottles", {
|
||||
"source_ip": source_ip,
|
||||
"image_ref": image_ref,
|
||||
"metadata": metadata,
|
||||
"policy": policy,
|
||||
"tokens": tokens or {},
|
||||
})
|
||||
bottle_id = payload.get("bottle_id")
|
||||
token = payload.get("identity_token")
|
||||
if not isinstance(bottle_id, str) or not isinstance(token, str):
|
||||
raise OrchestratorClientError("register: response missing bottle_id/identity_token")
|
||||
return RegisteredBottle(bottle_id=bottle_id, identity_token=token)
|
||||
|
||||
def teardown_bottle(self, bottle_id: str) -> bool:
|
||||
"""Tear a bottle down (`DELETE /bottles/<id>`). False if the
|
||||
orchestrator didn't know it (404) — idempotent for cleanup paths."""
|
||||
status, _ = self._request("DELETE", f"/bottles/{bottle_id}")
|
||||
if status == 404:
|
||||
return False
|
||||
if not 200 <= status < 300:
|
||||
raise OrchestratorClientError(f"teardown {bottle_id}: HTTP {status}")
|
||||
return True
|
||||
|
||||
def set_policy(self, bottle_id: str, policy: str) -> bool:
|
||||
"""Live-reload a bottle's policy (`PUT /bottles/<id>/policy`). False on
|
||||
404 (unknown bottle)."""
|
||||
status, _ = self._request("PUT", f"/bottles/{bottle_id}/policy", {"policy": policy})
|
||||
if status == 404:
|
||||
return False
|
||||
if not 200 <= status < 300:
|
||||
raise OrchestratorClientError(f"set_policy {bottle_id}: HTTP {status}")
|
||||
return True
|
||||
|
||||
def list_bottles(self) -> list[dict[str, object]]:
|
||||
"""Every registered bottle's redacted record (`GET /bottles`)."""
|
||||
payload = self._ok("GET", "/bottles")
|
||||
bottles = payload.get("bottles")
|
||||
return bottles if isinstance(bottles, list) else []
|
||||
|
||||
|
||||
__all__ = [
|
||||
"OrchestratorClient",
|
||||
"OrchestratorClientError",
|
||||
"RegisteredBottle",
|
||||
"DEFAULT_TIMEOUT_SECONDS",
|
||||
]
|
||||
@@ -4,14 +4,18 @@ The backend-agnostic control-plane RPC (CLI / console -> orchestrator) over
|
||||
**HTTP** — the universal transport chosen in 0070 (works on every host; no
|
||||
vsock / unix-socket portability caveats):
|
||||
|
||||
GET /health -> 200 {"status": "ok"}
|
||||
GET /sidecar -> 200 {"configured", ["name", "running"]}
|
||||
GET /bottles -> 200 {"bottles": [ <redacted record>, ... ]}
|
||||
POST /bottles -> 201 {"bottle_id", "identity_token"} (launch)
|
||||
body: {"source_ip", ["image_ref"], ["metadata"]}
|
||||
DELETE /bottles/<bottle_id> -> 200 {"torn_down": true} | 404 (teardown)
|
||||
POST /attribute -> 200 {"bottle_id"} | 403
|
||||
body: {"source_ip", "identity_token"}
|
||||
GET /health -> 200 {"status": "ok"}
|
||||
GET /gateway -> 200 {"configured", ["name","running"]}
|
||||
GET /bottles -> 200 {"bottles": [ <redacted record>, ...]}
|
||||
POST /bottles -> 201 {"bottle_id","identity_token"} (launch)
|
||||
body: {"source_ip", ["image_ref"],
|
||||
["metadata"], ["policy"]}
|
||||
PUT /bottles/<bottle_id>/policy -> 200 {"updated": true} | 404 (live reload)
|
||||
body: {"policy"}
|
||||
DELETE /bottles/<bottle_id> -> 200 {"torn_down": true} | 404 (teardown)
|
||||
POST /attribute -> 200 {"bottle_id"} | 403
|
||||
POST /resolve -> 200 {"bottle_id","policy"} | 403
|
||||
body: {"source_ip","identity_token"}
|
||||
|
||||
`POST /bottles` / `DELETE` drive the full launch lifecycle: they mint (or
|
||||
tear down) the bottle in the registry AND broker the backend-native launch
|
||||
@@ -30,6 +34,7 @@ import http.server
|
||||
import json
|
||||
import os
|
||||
import socketserver
|
||||
import sys
|
||||
import typing
|
||||
from urllib.parse import urlsplit
|
||||
|
||||
@@ -49,7 +54,7 @@ def _parse_json_object(body: bytes) -> Json:
|
||||
return obj
|
||||
|
||||
|
||||
def dispatch( # pylint: disable=too-many-return-statements
|
||||
def dispatch( # pylint: disable=too-many-return-statements,too-many-branches
|
||||
orch: Orchestrator, method: str, path: str, body: bytes
|
||||
) -> tuple[int, Json]:
|
||||
"""Route one control-plane request to a (status, payload) pair. Pure —
|
||||
@@ -59,8 +64,8 @@ def dispatch( # pylint: disable=too-many-return-statements
|
||||
if method == "GET" and route == "/health":
|
||||
return 200, {"status": "ok"}
|
||||
|
||||
if method == "GET" and route == "/sidecar":
|
||||
return 200, orch.sidecar_status()
|
||||
if method == "GET" and route == "/gateway":
|
||||
return 200, orch.gateway_status()
|
||||
|
||||
if method == "GET" and route == "/bottles":
|
||||
return 200, {"bottles": [r.redacted() for r in orch.registry.all()]}
|
||||
@@ -75,13 +80,33 @@ def dispatch( # pylint: disable=too-many-return-statements
|
||||
return 400, {"error": "source_ip (string) is required"}
|
||||
image_ref = data.get("image_ref")
|
||||
metadata = data.get("metadata")
|
||||
policy = data.get("policy")
|
||||
raw_tokens = data.get("tokens")
|
||||
tokens = {
|
||||
k: v for k, v in raw_tokens.items() if isinstance(k, str) and isinstance(v, str)
|
||||
} if isinstance(raw_tokens, dict) else {}
|
||||
rec = orch.launch_bottle(
|
||||
source_ip,
|
||||
image_ref=image_ref if isinstance(image_ref, str) else "",
|
||||
metadata=metadata if isinstance(metadata, str) else "",
|
||||
policy=policy if isinstance(policy, str) else "",
|
||||
tokens=tokens,
|
||||
)
|
||||
return 201, {"bottle_id": rec.bottle_id, "identity_token": rec.identity_token}
|
||||
|
||||
if method == "PUT" and route.startswith("/bottles/") and route.endswith("/policy"):
|
||||
bottle_id = route[len("/bottles/"):-len("/policy")]
|
||||
try:
|
||||
data = _parse_json_object(body)
|
||||
except ValueError as e:
|
||||
return 400, {"error": f"invalid JSON: {e}"}
|
||||
policy = data.get("policy")
|
||||
if not isinstance(policy, str):
|
||||
return 400, {"error": "policy (string) is required"}
|
||||
if orch.set_policy(bottle_id, policy):
|
||||
return 200, {"updated": True}
|
||||
return 404, {"error": "no such bottle"}
|
||||
|
||||
if method == "DELETE" and route.startswith("/bottles/"):
|
||||
bottle_id = route[len("/bottles/"):]
|
||||
if orch.teardown_bottle(bottle_id):
|
||||
@@ -102,6 +127,29 @@ def dispatch( # pylint: disable=too-many-return-statements
|
||||
return 403, {"error": "unattributed"}
|
||||
return 200, {"bottle_id": rec.bottle_id}
|
||||
|
||||
if method == "POST" and route == "/resolve":
|
||||
# The per-request lookup the multi-tenant gateway makes: returns the
|
||||
# bottle's policy. identity_token is OPTIONAL — absent means resolve
|
||||
# by source IP alone (network-layer attribution).
|
||||
try:
|
||||
data = _parse_json_object(body)
|
||||
except ValueError as e:
|
||||
return 400, {"error": f"invalid JSON: {e}"}
|
||||
source_ip = data.get("source_ip")
|
||||
token = data.get("identity_token")
|
||||
if not isinstance(source_ip, str) or not source_ip:
|
||||
return 400, {"error": "source_ip (string) is required"}
|
||||
rec = orch.resolve(source_ip, token if isinstance(token, str) else "")
|
||||
if rec is None:
|
||||
return 403, {"error": "unattributed"}
|
||||
# tokens are the in-memory per-bottle egress auth values the gateway
|
||||
# injects; served here, never persisted.
|
||||
return 200, {
|
||||
"bottle_id": rec.bottle_id,
|
||||
"policy": rec.policy,
|
||||
"tokens": orch.tokens_for(rec.bottle_id),
|
||||
}
|
||||
|
||||
return 404, {"error": "not found"}
|
||||
|
||||
|
||||
@@ -115,12 +163,20 @@ class Handler(http.server.BaseHTTPRequestHandler):
|
||||
super().log_message(format, *args)
|
||||
|
||||
def _serve(self, method: str) -> None:
|
||||
"""Read the request body, dispatch it, and write the JSON reply."""
|
||||
"""Read the request body, dispatch it, and write the JSON reply. A
|
||||
dispatch failure (e.g. a broker error) returns a 500 rather than
|
||||
crashing the connection, so one bad request can't take the control
|
||||
plane down for the caller."""
|
||||
server = self.server
|
||||
assert isinstance(server, ControlPlaneServer)
|
||||
length = int(self.headers.get("Content-Length") or 0)
|
||||
body = self.rfile.read(length) if length > 0 else b""
|
||||
status, payload = dispatch(server.orchestrator, method, self.path, body)
|
||||
try:
|
||||
status, payload = dispatch(server.orchestrator, method, self.path, body)
|
||||
except Exception as e: # noqa: BLE001 — the control plane must stay up
|
||||
sys.stderr.write(f"orchestrator: {method} {self.path} failed: {e!r}\n")
|
||||
sys.stderr.flush()
|
||||
status, payload = 500, {"error": f"internal error: {e}"}
|
||||
data = json.dumps(payload).encode()
|
||||
self.send_response(status)
|
||||
self.send_header("Content-Type", "application/json")
|
||||
@@ -134,6 +190,9 @@ class Handler(http.server.BaseHTTPRequestHandler):
|
||||
def do_POST(self) -> None:
|
||||
self._serve("POST")
|
||||
|
||||
def do_PUT(self) -> None:
|
||||
self._serve("PUT")
|
||||
|
||||
def do_DELETE(self) -> None:
|
||||
self._serve("DELETE")
|
||||
|
||||
|
||||
@@ -2,12 +2,12 @@
|
||||
|
||||
On a verified launch request it starts a Docker container; on teardown it
|
||||
removes it. This proves the orchestrator -> backend seam on the cheapest
|
||||
backend (the sidecar bundle is already containers). Only the request's
|
||||
backend (the gateway is already containers). Only the request's
|
||||
static ids/flags reach `docker`, so nothing free-form crosses the boundary.
|
||||
|
||||
Slice 3 launches a single container from the request's `image_ref`, named
|
||||
after the bottle id and labelled for cleanup. Wiring the full agent +
|
||||
sidecar bundle (networks, mounts, the consolidated sidecar) is a later
|
||||
gateway (networks, mounts, the consolidated gateway) is a later
|
||||
slice — this is the seam, not the finished launcher.
|
||||
"""
|
||||
|
||||
|
||||
@@ -0,0 +1,235 @@
|
||||
"""The consolidated per-host gateway (PRD 0070).
|
||||
|
||||
The core consolidation win: **one** persistent gateway per host, shared by
|
||||
every bottle, instead of a gateway per bottle. It's safe to share
|
||||
because the attribution invariant (source IP + identity token, see
|
||||
`registry`) lets the gateway attribute each request to the right bottle —
|
||||
so per-bottle policy lives in one long-lived process keyed on who's calling.
|
||||
|
||||
`Gateway` is the backend-neutral lifecycle contract (mirrors `LaunchBroker`):
|
||||
ensure the single instance is up, report it, tear it down. `DockerGateway`
|
||||
is the docker implementation; a firecracker gateway VM slots in later.
|
||||
|
||||
The defining behaviour is **idempotent singleton**: `ensure_running` starts
|
||||
the instance if absent and is a no-op if it's already up, so N bottle
|
||||
launches never spawn N gateways.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import abc
|
||||
import os
|
||||
import time
|
||||
from pathlib import Path
|
||||
|
||||
from ..docker_cmd import run_docker
|
||||
|
||||
# The gateway's mitmproxy writes its CA a beat after the container starts, so
|
||||
# reads poll for it rather than assuming it's there on a fresh launch.
|
||||
_CA_POLL_SECONDS = 0.5
|
||||
DEFAULT_CA_TIMEOUT_SECONDS = 30.0
|
||||
|
||||
GATEWAY_NAME = "bot-bottle-orch-gateway"
|
||||
GATEWAY_LABEL = "bot-bottle-orch-gateway=1"
|
||||
# The single user-defined network the gateway and every agent bottle share.
|
||||
# Agents attach here with a pinned IP and reach the gateway's egress /
|
||||
# git-http / supervise ports by its address — no host port publishing, and
|
||||
# the source IP the gateway attributes by is the address on this network.
|
||||
GATEWAY_NETWORK = "bot-bottle-gateway"
|
||||
|
||||
# mitmproxy's CA dir in the bundle. A persistent named volume here keeps the
|
||||
# gateway's self-generated CA STABLE across container recreation — every agent
|
||||
# installs this one CA to trust the shared gateway's TLS interception, so it
|
||||
# must not rotate when the gateway restarts.
|
||||
MITMPROXY_HOME = "/home/mitmproxy/.mitmproxy"
|
||||
GATEWAY_CA_VOLUME = "bot-bottle-gateway-mitmproxy"
|
||||
GATEWAY_CA_CERT = f"{MITMPROXY_HOME}/mitmproxy-ca-cert.pem"
|
||||
|
||||
# The gateway data-plane image + its Dockerfile. Kept as a local constant
|
||||
# rather than imported from the backend layer, which would drag
|
||||
# the whole backend layer into the lean orchestrator (see #359); unify when
|
||||
# that lands. Env override matches the backend's BOT_BOTTLE_GATEWAY_IMAGE.
|
||||
GATEWAY_IMAGE = os.environ.get("BOT_BOTTLE_GATEWAY_IMAGE", "bot-bottle-gateway:latest")
|
||||
GATEWAY_DOCKERFILE = "Dockerfile.gateway"
|
||||
_REPO_ROOT = Path(__file__).resolve().parents[2]
|
||||
|
||||
|
||||
class GatewayError(Exception):
|
||||
"""The shared gateway failed to build/start/stop (non-zero `docker` exit)."""
|
||||
|
||||
|
||||
class Gateway(abc.ABC):
|
||||
"""Lifecycle of the single per-host gateway. Backend-neutral."""
|
||||
|
||||
name: str
|
||||
|
||||
def ensure_built(self) -> None:
|
||||
"""Ensure the gateway's image / rootfs exists, building it if needed.
|
||||
Default: nothing to build (e.g. a stub or a pre-pulled image)."""
|
||||
return
|
||||
|
||||
@abc.abstractmethod
|
||||
def ensure_running(self) -> None:
|
||||
"""Start the gateway if it isn't already up. Idempotent: a no-op
|
||||
when it's already running (that's the whole point — one per host).
|
||||
Assumes the image exists — call `ensure_built()` first."""
|
||||
|
||||
@abc.abstractmethod
|
||||
def is_running(self) -> bool:
|
||||
"""True iff the gateway instance is currently up."""
|
||||
|
||||
@abc.abstractmethod
|
||||
def stop(self) -> None:
|
||||
"""Remove the gateway. Idempotent — absent is success."""
|
||||
|
||||
|
||||
class DockerGateway(Gateway):
|
||||
"""The consolidated gateway as a single, fixed-name Docker container.
|
||||
|
||||
`image_ref` defaults to the gateway data-plane image; `ensure_built`
|
||||
builds it from `Dockerfile.gateway` when it's missing. (Note: slice 5
|
||||
builds + launches the bundle container; wiring its per-bottle,
|
||||
source-IP-keyed config is a later slice — see PRD 0070.)"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
image_ref: str = GATEWAY_IMAGE,
|
||||
*,
|
||||
name: str = GATEWAY_NAME,
|
||||
network: str = GATEWAY_NETWORK,
|
||||
orchestrator_url: str = "",
|
||||
build_context: Path | None = None,
|
||||
dockerfile: str | None = GATEWAY_DOCKERFILE,
|
||||
host_port_bindings: tuple[int, ...] = (),
|
||||
) -> None:
|
||||
self.image_ref = image_ref
|
||||
self.name = name
|
||||
self.network = network
|
||||
# The control-plane URL the gateway's data plane resolves per bottle
|
||||
# against — reached by container name over docker DNS on the shared
|
||||
# network (container↔container, no host firewall). Empty → single-tenant.
|
||||
self._orchestrator_url = orchestrator_url
|
||||
self._build_context = build_context or _REPO_ROOT
|
||||
self._dockerfile = dockerfile
|
||||
# Ports published on the host (0.0.0.0). Used by the Firecracker
|
||||
# backend's dev-harness gateway so VMs can reach it via their TAP link;
|
||||
# Docker's DNAT + the nft `ct status dnat accept` rule handle the rest.
|
||||
self._host_port_bindings = host_port_bindings
|
||||
|
||||
def image_exists(self) -> bool:
|
||||
return run_docker(["docker", "image", "inspect", self.image_ref]).returncode == 0
|
||||
|
||||
def ensure_built(self) -> None:
|
||||
"""Build the bundle image from its Dockerfile, **cache-aware** — cheap
|
||||
(a cache check) when nothing changed, a real rebuild when the flat
|
||||
sources (egress addon / git-http / policy_resolver / supervise) moved.
|
||||
|
||||
This deliberately builds every time rather than build-if-missing: the
|
||||
per-bottle model kept the image fresh via compose's `build:` on up, and
|
||||
a stale image silently runs the OLD single-tenant daemons. No-op only
|
||||
when no dockerfile is configured (a pre-pulled image). BOT_BOTTLE_NO_CACHE
|
||||
forces a full rebuild (parity with `start --no-cache`)."""
|
||||
if self._dockerfile is None:
|
||||
return
|
||||
argv = ["docker", "build", "-t", self.image_ref,
|
||||
"-f", str(self._build_context / self._dockerfile),
|
||||
str(self._build_context)]
|
||||
if os.environ.get("BOT_BOTTLE_NO_CACHE"):
|
||||
argv.insert(2, "--no-cache")
|
||||
proc = run_docker(argv)
|
||||
if proc.returncode != 0:
|
||||
raise GatewayError(f"gateway image build failed: {proc.stderr.strip()}")
|
||||
|
||||
def is_running(self) -> bool:
|
||||
proc = run_docker([
|
||||
"docker", "ps",
|
||||
"--filter", f"name=^{self.name}$",
|
||||
"--filter", "status=running",
|
||||
"--format", "{{.Names}}",
|
||||
])
|
||||
return self.name in proc.stdout.split()
|
||||
|
||||
def _running_image_is_current(self) -> bool:
|
||||
"""True iff the running gateway was created from the *current*
|
||||
`image_ref`. When `ensure_built` rebuilds the image (a source change),
|
||||
the running container is still the OLD image running the OLD flat
|
||||
daemons — so this is how a rebuild actually takes effect: a mismatch
|
||||
means recreate."""
|
||||
running = run_docker(["docker", "inspect", "--format", "{{.Image}}", self.name])
|
||||
current = run_docker(["docker", "image", "inspect", "--format", "{{.Id}}", self.image_ref])
|
||||
if running.returncode != 0 or current.returncode != 0:
|
||||
return True # can't compare → don't churn a working container
|
||||
return running.stdout.strip() == current.stdout.strip()
|
||||
|
||||
def _ensure_network(self) -> None:
|
||||
"""Create the shared gateway network if it doesn't exist. Idempotent —
|
||||
a concurrent create loses harmlessly (the loser sees 'already exists').
|
||||
Docker picks the subnet; the launcher reads it back to allocate IPs."""
|
||||
if run_docker(["docker", "network", "inspect", self.network]).returncode == 0:
|
||||
return
|
||||
proc = run_docker(["docker", "network", "create", self.network])
|
||||
if proc.returncode != 0 and "already exists" not in proc.stderr:
|
||||
raise GatewayError(
|
||||
f"gateway network {self.network} failed to create: {proc.stderr.strip()}"
|
||||
)
|
||||
|
||||
def ensure_running(self) -> None:
|
||||
# Recreate when the running container's image is stale (a rebuild),
|
||||
# so source changes to the gateway's flat daemons take effect — not
|
||||
# just when the container is absent.
|
||||
if self.is_running() and self._running_image_is_current():
|
||||
return
|
||||
self._ensure_network()
|
||||
# Clear any stale (stopped OR outdated-image) container holding the
|
||||
# fixed name, then start fresh. `rm --force` on an absent name is a
|
||||
# tolerated no-op.
|
||||
run_docker(["docker", "rm", "--force", self.name])
|
||||
argv = [
|
||||
"docker", "run", "--detach",
|
||||
"--name", self.name,
|
||||
"--label", GATEWAY_LABEL,
|
||||
"--network", self.network,
|
||||
# Persist the self-generated CA so it survives restarts (agents
|
||||
# trust it) — see GATEWAY_CA_VOLUME.
|
||||
"--volume", f"{GATEWAY_CA_VOLUME}:{MITMPROXY_HOME}",
|
||||
]
|
||||
for port in self._host_port_bindings:
|
||||
argv += ["--publish", f"0.0.0.0:{port}:{port}"]
|
||||
if self._orchestrator_url:
|
||||
# Makes the gateway's egress / git / supervise daemons multi-tenant:
|
||||
# each request resolves source-IP -> policy against the control plane.
|
||||
argv += ["--env", f"BOT_BOTTLE_ORCHESTRATOR_URL={self._orchestrator_url}"]
|
||||
argv.append(self.image_ref)
|
||||
proc = run_docker(argv)
|
||||
if proc.returncode != 0:
|
||||
raise GatewayError(f"gateway failed to start: {proc.stderr.strip()}")
|
||||
|
||||
def ca_cert_pem(self, *, timeout: float = DEFAULT_CA_TIMEOUT_SECONDS) -> str:
|
||||
"""The gateway's CA certificate (PEM) that agents install to trust its
|
||||
TLS interception. mitmproxy generates it a moment after the container
|
||||
starts, so this **polls** for it (up to `timeout`) rather than assuming
|
||||
it's already there on a fresh gateway — raising only if it never
|
||||
appears."""
|
||||
deadline = time.monotonic() + timeout
|
||||
while True:
|
||||
proc = run_docker(["docker", "exec", self.name, "cat", GATEWAY_CA_CERT])
|
||||
if proc.returncode == 0 and proc.stdout.strip():
|
||||
return proc.stdout
|
||||
if time.monotonic() >= deadline:
|
||||
raise GatewayError(
|
||||
f"gateway CA cert not available after {timeout:g}s: "
|
||||
f"{proc.stderr.strip() or 'empty'}"
|
||||
)
|
||||
time.sleep(_CA_POLL_SECONDS)
|
||||
|
||||
def stop(self) -> None:
|
||||
proc = run_docker(["docker", "rm", "--force", self.name])
|
||||
if proc.returncode != 0 and "No such container" not in proc.stderr:
|
||||
raise GatewayError(f"gateway failed to stop: {proc.stderr.strip()}")
|
||||
|
||||
|
||||
__all__ = [
|
||||
"Gateway", "DockerGateway", "GatewayError",
|
||||
"GATEWAY_NAME", "GATEWAY_LABEL", "GATEWAY_IMAGE", "GATEWAY_NETWORK",
|
||||
"GATEWAY_CA_VOLUME", "GATEWAY_CA_CERT",
|
||||
]
|
||||
@@ -0,0 +1,261 @@
|
||||
"""Orchestrator + gateway lifecycle (PRD 0070, docker slice).
|
||||
|
||||
Runs the orchestrator control plane **as a container** on the shared gateway
|
||||
network, alongside the gateway container. This is the PRD's "virtualize the
|
||||
orchestrator": container↔container between the gateway and the orchestrator
|
||||
avoids the host firewall (which drops container→host traffic), and the gateway
|
||||
reaches the control plane by container name over docker DNS. The host CLI
|
||||
reaches it via a published loopback port.
|
||||
|
||||
The orchestrator runs with the **register-only broker** — the *backend*
|
||||
launches agent containers (compose), so the orchestrator needs no docker
|
||||
socket. That keeps this control-plane container unprivileged; the host manages
|
||||
both containers. `ensure_running` is an idempotent singleton (fixed container
|
||||
names + the published port).
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import hashlib
|
||||
import os
|
||||
import time
|
||||
import urllib.error
|
||||
import urllib.request
|
||||
from pathlib import Path
|
||||
|
||||
from .. import log
|
||||
from ..docker_cmd import run_docker
|
||||
from ..paths import bot_bottle_root
|
||||
from .gateway import GATEWAY_IMAGE, GATEWAY_NETWORK, DockerGateway, GatewayError
|
||||
|
||||
DEFAULT_PORT = 8099
|
||||
ORCHESTRATOR_NAME = "bot-bottle-orchestrator"
|
||||
ORCHESTRATOR_LABEL = "bot-bottle-orchestrator=1"
|
||||
# The control-plane's own runtime image — lean (python + the stdlib-only
|
||||
# `bot_bottle` package, bind-mounted at run time), distinct from the heavy
|
||||
# gateway data-plane image it used to borrow (#384). Env override for
|
||||
# operators pinning a published build.
|
||||
ORCHESTRATOR_IMAGE = os.environ.get(
|
||||
"BOT_BOTTLE_ORCHESTRATOR_IMAGE", "bot-bottle-orchestrator:latest"
|
||||
)
|
||||
ORCHESTRATOR_DOCKERFILE = "Dockerfile.orchestrator"
|
||||
# Baked onto the container as a label so `ensure_running` can tell whether the
|
||||
# running process is executing the *current* bind-mounted source — see
|
||||
# `_source_hash`.
|
||||
ORCHESTRATOR_SOURCE_HASH_LABEL = "bot-bottle-orchestrator-source-hash"
|
||||
|
||||
# The repo root is bind-mounted into the control-plane container so
|
||||
# `python -m bot_bottle.orchestrator` resolves the package (the orchestrator
|
||||
# is stdlib-only, so the lean orchestrator image's python is enough).
|
||||
_REPO_ROOT = Path(__file__).resolve().parents[2]
|
||||
_APP_DIR = "/app"
|
||||
_ROOT_IN_CONTAINER = "/bot-bottle-root"
|
||||
|
||||
_HEALTH_POLL_SECONDS = 0.25
|
||||
DEFAULT_STARTUP_TIMEOUT_SECONDS = 45.0
|
||||
_HEALTH_REQUEST_TIMEOUT_SECONDS = 1.0
|
||||
|
||||
|
||||
class OrchestratorStartError(RuntimeError):
|
||||
"""The orchestrator container did not become healthy within the timeout."""
|
||||
|
||||
|
||||
def _source_hash(repo_root: Path) -> str:
|
||||
"""Content hash of the orchestrator's bind-mounted Python source (the
|
||||
`bot_bottle` package the control-plane process imports). This only
|
||||
changes when the code that would actually run inside the container
|
||||
changes — `ensure_running` recreates the container on a mismatch and
|
||||
otherwise leaves a healthy one alone, so a bottle launch that isn't
|
||||
accompanied by a code change doesn't restart the process and drop every
|
||||
*other* active bottle's in-memory egress tokens (`Orchestrator._tokens`
|
||||
in `service.py`, never persisted to disk by design)."""
|
||||
h = hashlib.sha256()
|
||||
for path in sorted((repo_root / "bot_bottle").rglob("*.py")):
|
||||
h.update(str(path.relative_to(repo_root)).encode())
|
||||
h.update(path.read_bytes())
|
||||
return h.hexdigest()
|
||||
|
||||
|
||||
class OrchestratorService:
|
||||
"""Manages the orchestrator control-plane container + the shared gateway.
|
||||
Callers only need `ensure_running()` + `url`.
|
||||
|
||||
`orchestrator_name` / `orchestrator_label` let backends run independent
|
||||
orchestrators on the same host without name collisions (e.g. the
|
||||
Firecracker backend uses `bot-bottle-fc-orchestrator` alongside the Docker
|
||||
backend's `bot-bottle-orchestrator`). Subclass and override `_gateway()`
|
||||
to supply a backend-specific gateway variant."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
*,
|
||||
port: int = DEFAULT_PORT,
|
||||
network: str = GATEWAY_NETWORK,
|
||||
image: str = ORCHESTRATOR_IMAGE,
|
||||
gateway_image: str = GATEWAY_IMAGE,
|
||||
repo_root: Path = _REPO_ROOT,
|
||||
host_root: Path | None = None,
|
||||
orchestrator_name: str = ORCHESTRATOR_NAME,
|
||||
orchestrator_label: str = ORCHESTRATOR_LABEL,
|
||||
) -> None:
|
||||
self.port = port
|
||||
self.network = network
|
||||
# Two distinct images (#384): `image` is the lean control-plane
|
||||
# runtime this container runs; `_gateway_image` is the heavy egress /
|
||||
# git-gate / supervise data plane the gateway container runs. They
|
||||
# were one conflated image before the split.
|
||||
self.image = image
|
||||
self._gateway_image = gateway_image
|
||||
self._repo_root = repo_root
|
||||
self._host_root = host_root or bot_bottle_root()
|
||||
self._orchestrator_name = orchestrator_name
|
||||
self._orchestrator_label = orchestrator_label
|
||||
|
||||
@property
|
||||
def url(self) -> str:
|
||||
"""Host-side control-plane URL (published loopback port)."""
|
||||
return f"http://127.0.0.1:{self.port}"
|
||||
|
||||
@property
|
||||
def internal_url(self) -> str:
|
||||
"""Control-plane URL as the gateway container reaches it — by name over
|
||||
docker DNS on the shared network. This is the gateway's
|
||||
BOT_BOTTLE_ORCHESTRATOR_URL."""
|
||||
return f"http://{self._orchestrator_name}:{self.port}"
|
||||
|
||||
def is_healthy(self, *, timeout: float = _HEALTH_REQUEST_TIMEOUT_SECONDS) -> bool:
|
||||
try:
|
||||
with urllib.request.urlopen(f"{self.url}/health", timeout=timeout) as resp:
|
||||
return resp.status == 200
|
||||
except (urllib.error.URLError, TimeoutError, OSError):
|
||||
return False
|
||||
|
||||
def _container_running(self, name: str) -> bool:
|
||||
proc = run_docker(["docker", "ps", "--filter", f"name=^/{name}$", "--format", "{{.Names}}"])
|
||||
return name in proc.stdout.split()
|
||||
|
||||
def _run_orchestrator_container(self, source_hash: str) -> None:
|
||||
"""Start the control-plane container (idempotent: clears a stale
|
||||
fixed-name container first). Register-only broker → no docker socket.
|
||||
Labels the container with `source_hash` so a later `ensure_running`
|
||||
can detect a real code change (see `_source_hash`)."""
|
||||
run_docker(["docker", "rm", "--force", self._orchestrator_name])
|
||||
proc = run_docker([
|
||||
"docker", "run", "--detach",
|
||||
"--name", self._orchestrator_name,
|
||||
"--label", self._orchestrator_label,
|
||||
"--label", f"{ORCHESTRATOR_SOURCE_HASH_LABEL}={source_hash}",
|
||||
"--network", self.network,
|
||||
# Host CLI reaches the control plane here; bound to loopback so it
|
||||
# is not exposed on the host's external interfaces.
|
||||
"--publish", f"127.0.0.1:{self.port}:{self.port}",
|
||||
"--volume", f"{self._repo_root}:{_APP_DIR}:ro",
|
||||
"--workdir", _APP_DIR,
|
||||
# Persist the registry DB on the host (sole-owner: only the
|
||||
# orchestrator opens bot-bottle.db).
|
||||
"--volume", f"{self._host_root}:{_ROOT_IN_CONTAINER}",
|
||||
"--env", f"BOT_BOTTLE_ROOT={_ROOT_IN_CONTAINER}",
|
||||
"--entrypoint", "python3",
|
||||
self.image,
|
||||
"-m", "bot_bottle.orchestrator",
|
||||
"--host", "0.0.0.0", "--port", str(self.port), "--broker", "stub",
|
||||
])
|
||||
if proc.returncode != 0:
|
||||
raise OrchestratorStartError(
|
||||
f"orchestrator container failed to start: {proc.stderr.strip()}"
|
||||
)
|
||||
|
||||
def _gateway(self) -> DockerGateway:
|
||||
return DockerGateway(
|
||||
self._gateway_image, network=self.network, orchestrator_url=self.internal_url
|
||||
)
|
||||
|
||||
def _ensure_orchestrator_image(self) -> None:
|
||||
"""Build the lean control-plane image from `Dockerfile.orchestrator`
|
||||
when it's missing (#384). Cheap — a `FROM python:*-slim` base with no
|
||||
deps to install, so the layer cache makes rebuilds a no-op. Unlike the
|
||||
gateway image this is build-if-missing, not build-every-time: the
|
||||
control plane bind-mounts its source, so a code change is caught by the
|
||||
source-hash recreate (below), not by an image rebuild."""
|
||||
if run_docker(["docker", "image", "inspect", self.image]).returncode == 0:
|
||||
return
|
||||
argv = ["docker", "build", "-t", self.image,
|
||||
"-f", str(self._repo_root / ORCHESTRATOR_DOCKERFILE),
|
||||
str(self._repo_root)]
|
||||
if os.environ.get("BOT_BOTTLE_NO_CACHE"):
|
||||
argv.insert(2, "--no-cache")
|
||||
proc = run_docker(argv)
|
||||
if proc.returncode != 0:
|
||||
raise GatewayError(
|
||||
f"orchestrator image build failed: {proc.stderr.strip()}"
|
||||
)
|
||||
|
||||
def _orchestrator_source_current(self, current_hash: str) -> bool:
|
||||
"""True iff the running orchestrator container was created from the
|
||||
*current* bind-mounted source. Mirrors `DockerGateway`'s
|
||||
image-staleness check, but by content hash rather than image id since
|
||||
the orchestrator runs bind-mounted source, not a built image."""
|
||||
if not self._container_running(self._orchestrator_name):
|
||||
return False
|
||||
proc = run_docker([
|
||||
"docker", "inspect", "--format",
|
||||
"{{ index .Config.Labels \"" + ORCHESTRATOR_SOURCE_HASH_LABEL + "\" }}",
|
||||
self._orchestrator_name,
|
||||
])
|
||||
if proc.returncode != 0:
|
||||
return True # can't compare -> don't churn a working container
|
||||
return proc.stdout.strip() == current_hash
|
||||
|
||||
def ensure_running(
|
||||
self, *, startup_timeout: float = DEFAULT_STARTUP_TIMEOUT_SECONDS,
|
||||
) -> str:
|
||||
"""Ensure the control plane + shared gateway are up; return the host
|
||||
control-plane URL. Idempotent — a healthy control plane running
|
||||
current code and a running gateway are left untouched. Raises
|
||||
`OrchestratorStartError` on timeout."""
|
||||
gateway = self._gateway()
|
||||
gateway.ensure_built() # rebuild the bundle image on a source change
|
||||
gateway.ensure_running() # creates the shared network + (re)starts gateway
|
||||
|
||||
# Recreate the orchestrator container only when its bind-mounted
|
||||
# source has actually changed since it started — its Python process
|
||||
# loaded that code at startup and won't reload, so a stale container
|
||||
# would keep running OLD control-plane code. Recreating on *every*
|
||||
# launch (the prior behaviour) would drop every other active
|
||||
# bottle's in-memory egress tokens each time a new bottle starts,
|
||||
# since the orchestrator process holds them only in memory (#381).
|
||||
current_hash = _source_hash(self._repo_root)
|
||||
if self.is_healthy() and self._orchestrator_source_current(current_hash):
|
||||
return self.url
|
||||
|
||||
self._ensure_orchestrator_image()
|
||||
log.info(
|
||||
"starting orchestrator container",
|
||||
context={"name": self._orchestrator_name},
|
||||
)
|
||||
self._run_orchestrator_container(current_hash)
|
||||
|
||||
deadline = time.monotonic() + startup_timeout
|
||||
while time.monotonic() < deadline:
|
||||
if self.is_healthy():
|
||||
log.info("orchestrator healthy", context={"url": self.url})
|
||||
return self.url
|
||||
time.sleep(_HEALTH_POLL_SECONDS)
|
||||
raise OrchestratorStartError(
|
||||
f"orchestrator at {self.url} did not become healthy within {startup_timeout:g}s"
|
||||
)
|
||||
|
||||
def stop(self) -> None:
|
||||
"""Remove the orchestrator + gateway containers (idempotent)."""
|
||||
run_docker(["docker", "rm", "--force", self._orchestrator_name])
|
||||
self._gateway().stop()
|
||||
|
||||
|
||||
__all__ = [
|
||||
"OrchestratorService",
|
||||
"OrchestratorStartError",
|
||||
"ORCHESTRATOR_NAME",
|
||||
"ORCHESTRATOR_IMAGE",
|
||||
"DEFAULT_PORT",
|
||||
"DEFAULT_STARTUP_TIMEOUT_SECONDS",
|
||||
]
|
||||
@@ -0,0 +1,57 @@
|
||||
"""Consolidated registration inputs (PRD 0070, docker slice).
|
||||
|
||||
Bridges the existing per-bottle `prepare` output to the consolidated
|
||||
registry: turns a prepared bottle's egress plan into the backend-neutral
|
||||
inputs `Orchestrator.launch_bottle` takes — the egress **policy** blob and
|
||||
launch **metadata**.
|
||||
|
||||
The policy blob is the exact routes YAML the per-bottle egress daemon used
|
||||
to read from a file; in the consolidated model the multi-tenant gateway's
|
||||
`PolicyResolver` fetches it from the registry per request (keyed by source
|
||||
IP) instead. Same render, so consolidated and single-tenant egress apply
|
||||
byte-identical policy — a bottle's allow-list doesn't change when it moves
|
||||
onto the shared gateway.
|
||||
|
||||
Host-side glue (imports `bot_bottle.egress`), used by the launch path — not
|
||||
by the lean orchestrator control-plane process itself.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
from dataclasses import dataclass
|
||||
|
||||
from ..egress import EgressPlan, egress_render_routes
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class RegistrationInputs:
|
||||
"""What `Orchestrator.launch_bottle` needs to register a bottle, derived
|
||||
from its prepared plan. `policy` is served verbatim by the gateway's
|
||||
`/resolve`; `metadata` is opaque forward-compat state — it carries the
|
||||
human slug so the console / supervise can show a name, not just the
|
||||
minted bottle id."""
|
||||
|
||||
policy: str
|
||||
metadata: str
|
||||
|
||||
|
||||
def egress_policy(plan: EgressPlan) -> str:
|
||||
"""The bottle's egress policy blob: the routes YAML the gateway serves
|
||||
and the addon parses with `load_config`. Identical to the per-bottle
|
||||
`routes.yaml` render, so the consolidated path applies the same
|
||||
allow-list."""
|
||||
return egress_render_routes(plan.routes, log=plan.log)
|
||||
|
||||
|
||||
def registration_inputs(plan: EgressPlan) -> RegistrationInputs:
|
||||
"""Assemble the orchestrator registration inputs from a prepared egress
|
||||
plan. `metadata` records the slug so the shared registry can map a minted
|
||||
bottle id back to its human name."""
|
||||
return RegistrationInputs(
|
||||
policy=egress_policy(plan),
|
||||
metadata=json.dumps({"slug": plan.slug}),
|
||||
)
|
||||
|
||||
|
||||
__all__ = ["RegistrationInputs", "egress_policy", "registration_inputs"]
|
||||
@@ -64,9 +64,13 @@ class BottleRecord:
|
||||
identity_token: str
|
||||
state: str = "active"
|
||||
created_at: float = 0.0
|
||||
# Opaque JSON blob for forward-compat (policy refs, pool slot, ...) —
|
||||
# the registry doesn't interpret it, so new fields need no migration.
|
||||
# Opaque JSON blob for forward-compat (pool slot, ...) — the registry
|
||||
# doesn't interpret it, so new fields need no migration.
|
||||
metadata: str = ""
|
||||
# The bottle's gateway policy (opaque JSON — egress allowlist / routes /
|
||||
# git config). The registry stores and serves it verbatim, keyed by
|
||||
# source IP; the multi-tenant gateway interprets it.
|
||||
policy: str = ""
|
||||
|
||||
def redacted(self) -> dict[str, object]:
|
||||
"""Public view for listing — never exposes the identity token."""
|
||||
@@ -76,6 +80,7 @@ class BottleRecord:
|
||||
"state": self.state,
|
||||
"created_at": self.created_at,
|
||||
"metadata": self.metadata,
|
||||
"policy": self.policy,
|
||||
}
|
||||
|
||||
|
||||
@@ -97,6 +102,10 @@ _MIGRATIONS = TableMigrations(
|
||||
# the "one active bottle per source IP" check cheap.
|
||||
"CREATE INDEX IF NOT EXISTS idx_orchestrator_bottles_source_ip "
|
||||
"ON orchestrator_bottles (source_ip)",
|
||||
# v3 — per-bottle policy (opaque JSON the gateway interprets): the
|
||||
# egress allowlist / routes / git config selected by source IP. The
|
||||
# multi-tenant gateway resolves it per request via `attribute`.
|
||||
"ALTER TABLE orchestrator_bottles ADD COLUMN policy TEXT NOT NULL DEFAULT ''",
|
||||
],
|
||||
)
|
||||
|
||||
@@ -110,6 +119,7 @@ def _row_to_record(row: sqlite3.Row) -> BottleRecord:
|
||||
state=row["state"],
|
||||
created_at=row["created_at"],
|
||||
metadata=row["metadata"],
|
||||
policy=row["policy"],
|
||||
)
|
||||
|
||||
|
||||
@@ -136,9 +146,18 @@ class RegistryStore(DbStore):
|
||||
bottle_id: str | None = None,
|
||||
identity_token: str | None = None,
|
||||
metadata: str = "",
|
||||
policy: str = "",
|
||||
) -> BottleRecord:
|
||||
"""Register (or replace) a bottle. Mints a bottle_id / identity token
|
||||
when not supplied. Live — this is the control-plane reload path."""
|
||||
when not supplied. Live — this is the control-plane reload path.
|
||||
|
||||
Supersedes any *other* active bottle at the same source IP first:
|
||||
`by_source_ip` fail-closes on ambiguity (>1 active row → None), so a
|
||||
leftover row at a reused IP — from an untorn-down bottle, crash
|
||||
recovery, or a persisted DB — would otherwise *brick* the new bottle's
|
||||
attribution. The new registration is authoritative for its IP; the
|
||||
stale rows go. INSERT OR REPLACE handles a same-`bottle_id` reload in
|
||||
place (its own row is exempt from the sweep)."""
|
||||
rec = BottleRecord(
|
||||
bottle_id=bottle_id or secrets.token_hex(8),
|
||||
source_ip=source_ip,
|
||||
@@ -146,12 +165,18 @@ class RegistryStore(DbStore):
|
||||
state="active",
|
||||
created_at=time.time(),
|
||||
metadata=metadata,
|
||||
policy=policy,
|
||||
)
|
||||
with self._connect() as conn:
|
||||
conn.execute(
|
||||
"DELETE FROM orchestrator_bottles "
|
||||
"WHERE source_ip = ? AND state = 'active' AND bottle_id != ?",
|
||||
(rec.source_ip, rec.bottle_id),
|
||||
)
|
||||
conn.execute(
|
||||
"INSERT OR REPLACE INTO orchestrator_bottles "
|
||||
"(bottle_id, source_ip, identity_token, state, created_at, metadata) "
|
||||
"VALUES (?, ?, ?, ?, ?, ?)",
|
||||
"(bottle_id, source_ip, identity_token, state, created_at, metadata, policy) "
|
||||
"VALUES (?, ?, ?, ?, ?, ?, ?)",
|
||||
(
|
||||
rec.bottle_id,
|
||||
rec.source_ip,
|
||||
@@ -159,11 +184,23 @@ class RegistryStore(DbStore):
|
||||
rec.state,
|
||||
rec.created_at,
|
||||
rec.metadata,
|
||||
rec.policy,
|
||||
),
|
||||
)
|
||||
self._chmod()
|
||||
return rec
|
||||
|
||||
def set_policy(self, bottle_id: str, policy: str) -> bool:
|
||||
"""Update a bottle's policy in place (live reload). Returns True if
|
||||
the bottle exists."""
|
||||
with self._connect() as conn:
|
||||
cur = conn.execute(
|
||||
"UPDATE orchestrator_bottles SET policy = ? WHERE bottle_id = ?",
|
||||
(policy, bottle_id),
|
||||
)
|
||||
self._chmod()
|
||||
return cur.rowcount > 0
|
||||
|
||||
def deregister(self, bottle_id: str) -> bool:
|
||||
"""Remove a bottle. Returns True if a row was deleted."""
|
||||
with self._connect() as conn:
|
||||
@@ -188,14 +225,13 @@ class RegistryStore(DbStore):
|
||||
).fetchall()
|
||||
return [_row_to_record(r) for r in rows]
|
||||
|
||||
def attribute(self, source_ip: str, identity_token: str) -> BottleRecord | None:
|
||||
"""Fail-closed attribution. Returns the bottle only when exactly one
|
||||
active record has this source IP AND its identity token matches
|
||||
(constant-time). Either signal alone is insufficient: an unknown IP,
|
||||
an ambiguous IP (more than one active bottle — a misconfiguration),
|
||||
an empty token, or a token mismatch all deny."""
|
||||
if not identity_token:
|
||||
return None
|
||||
def by_source_ip(self, source_ip: str) -> BottleRecord | None:
|
||||
"""Network-layer attribution: the single active bottle at this source
|
||||
IP, or None if unknown or ambiguous (more than one — a
|
||||
misconfiguration). Safe as the *sole* attributor only where the
|
||||
source IP is unspoofable (Firecracker `/31` + nft) and the control
|
||||
plane is reachable only by the trusted gateway; pair with the
|
||||
identity token (`attribute`) elsewhere."""
|
||||
with self._connect() as conn:
|
||||
rows = conn.execute(
|
||||
"SELECT * FROM orchestrator_bottles "
|
||||
@@ -204,7 +240,17 @@ class RegistryStore(DbStore):
|
||||
).fetchall()
|
||||
if len(rows) != 1:
|
||||
return None
|
||||
rec = _row_to_record(rows[0])
|
||||
return _row_to_record(rows[0])
|
||||
|
||||
def attribute(self, source_ip: str, identity_token: str) -> BottleRecord | None:
|
||||
"""Fail-closed attribution: `by_source_ip` AND a matching identity
|
||||
token (constant-time). Either signal alone is insufficient here — an
|
||||
unknown/ambiguous IP, an empty token, or a token mismatch all deny."""
|
||||
if not identity_token:
|
||||
return None
|
||||
rec = self.by_source_ip(source_ip)
|
||||
if rec is None:
|
||||
return None
|
||||
if not hmac.compare_digest(rec.identity_token, identity_token):
|
||||
return None
|
||||
return rec
|
||||
|
||||
@@ -19,12 +19,12 @@ from __future__ import annotations
|
||||
|
||||
from .broker import LaunchBroker, LaunchRequest, sign_request
|
||||
from .registry import BottleRecord, RegistryStore
|
||||
from .sidecar import Sidecar
|
||||
from .gateway import Gateway
|
||||
|
||||
|
||||
class Orchestrator:
|
||||
"""Owns the registry + brokers launches, and manages the single
|
||||
consolidated per-host sidecar. Backend-neutral (broker and sidecar
|
||||
consolidated per-host gateway. Backend-neutral (broker and gateway
|
||||
abstract the backend-native pieces)."""
|
||||
|
||||
def __init__(
|
||||
@@ -32,12 +32,18 @@ class Orchestrator:
|
||||
registry: RegistryStore,
|
||||
broker: LaunchBroker,
|
||||
sign_secret: bytes,
|
||||
sidecar: Sidecar | None = None,
|
||||
gateway: Gateway | None = None,
|
||||
) -> None:
|
||||
self.registry = registry
|
||||
self._broker = broker
|
||||
self._secret = sign_secret
|
||||
self._sidecar = sidecar
|
||||
self._gateway = gateway
|
||||
# Per-bottle egress auth tokens (env_name -> value), keyed by bottle_id.
|
||||
# Held **in memory only** — never written to the registry DB — so the
|
||||
# gateway can inject each bottle's upstream credential without secrets
|
||||
# at rest. Lost on restart (re-launch re-registers them); the future
|
||||
# SecretProvider (#355) replaces this with per-request minting.
|
||||
self._tokens: dict[str, dict[str, str]] = {}
|
||||
|
||||
def launch_bottle(
|
||||
self,
|
||||
@@ -46,10 +52,15 @@ class Orchestrator:
|
||||
image_ref: str = "",
|
||||
slot: int | None = None,
|
||||
metadata: str = "",
|
||||
policy: str = "",
|
||||
tokens: dict[str, str] | None = None,
|
||||
) -> BottleRecord:
|
||||
"""Register a bottle and broker its launch. Rolls the registry entry
|
||||
back if the launch doesn't take, so a failure leaves no orphan."""
|
||||
rec = self.registry.register(source_ip, metadata=metadata)
|
||||
"""Register a bottle (with its gateway policy + in-memory egress auth
|
||||
tokens) and broker its launch. Rolls the registry entry back if the
|
||||
launch doesn't take, so a failure leaves no orphan."""
|
||||
rec = self.registry.register(source_ip, metadata=metadata, policy=policy)
|
||||
if tokens:
|
||||
self._tokens[rec.bottle_id] = dict(tokens)
|
||||
req = LaunchRequest(
|
||||
op="launch",
|
||||
bottle_id=rec.bottle_id,
|
||||
@@ -64,6 +75,7 @@ class Orchestrator:
|
||||
finally:
|
||||
if not launched:
|
||||
self.registry.deregister(rec.bottle_id)
|
||||
self._tokens.pop(rec.bottle_id, None)
|
||||
return rec
|
||||
|
||||
def teardown_bottle(self, bottle_id: str) -> bool:
|
||||
@@ -74,28 +86,52 @@ class Orchestrator:
|
||||
req = LaunchRequest(op="teardown", bottle_id=bottle_id, source_ip=rec.source_ip)
|
||||
self._broker.submit(sign_request(req, self._secret))
|
||||
self.registry.deregister(bottle_id)
|
||||
self._tokens.pop(bottle_id, None)
|
||||
return True
|
||||
|
||||
def tokens_for(self, bottle_id: str) -> dict[str, str]:
|
||||
"""The bottle's in-memory egress auth tokens (env_name -> value), or
|
||||
empty. The gateway injects these per request; they are never
|
||||
persisted."""
|
||||
return dict(self._tokens.get(bottle_id, {}))
|
||||
|
||||
def attribute(self, source_ip: str, identity_token: str) -> BottleRecord | None:
|
||||
"""Fail-closed attribution (delegates to the registry)."""
|
||||
return self.registry.attribute(source_ip, identity_token)
|
||||
|
||||
# --- consolidated sidecar ----------------------------------------------
|
||||
def resolve(self, source_ip: str, identity_token: str = "") -> BottleRecord | None:
|
||||
"""Resolve the bottle behind a request — the source-IP-keyed lookup
|
||||
the multi-tenant gateway makes per request; the returned record
|
||||
carries its `policy`. With a token, full attribution (source IP +
|
||||
token); without, network-layer attribution by source IP alone
|
||||
(valid where the IP is unspoofable and the control plane is
|
||||
gateway-only)."""
|
||||
if identity_token:
|
||||
return self.registry.attribute(source_ip, identity_token)
|
||||
return self.registry.by_source_ip(source_ip)
|
||||
|
||||
def ensure_sidecar(self) -> None:
|
||||
"""Bring the single per-host sidecar up (idempotent). No-op when no
|
||||
sidecar is configured."""
|
||||
if self._sidecar is not None:
|
||||
self._sidecar.ensure_running()
|
||||
def set_policy(self, bottle_id: str, policy: str) -> bool:
|
||||
"""Update a bottle's gateway policy in place (live reload). False if
|
||||
the bottle is unknown."""
|
||||
return self.registry.set_policy(bottle_id, policy)
|
||||
|
||||
def sidecar_status(self) -> dict[str, object]:
|
||||
"""Report the shared sidecar for the control plane / console."""
|
||||
if self._sidecar is None:
|
||||
# --- consolidated gateway ----------------------------------------------
|
||||
|
||||
def ensure_gateway(self) -> None:
|
||||
"""Ensure the single per-host gateway is built and up (idempotent).
|
||||
No-op when no gateway is configured."""
|
||||
if self._gateway is not None:
|
||||
self._gateway.ensure_built()
|
||||
self._gateway.ensure_running()
|
||||
|
||||
def gateway_status(self) -> dict[str, object]:
|
||||
"""Report the shared gateway for the control plane / console."""
|
||||
if self._gateway is None:
|
||||
return {"configured": False}
|
||||
return {
|
||||
"configured": True,
|
||||
"name": self._sidecar.name,
|
||||
"running": self._sidecar.is_running(),
|
||||
"name": self._gateway.name,
|
||||
"running": self._gateway.is_running(),
|
||||
}
|
||||
|
||||
|
||||
|
||||
@@ -1,88 +0,0 @@
|
||||
"""The consolidated per-host sidecar (PRD 0070).
|
||||
|
||||
The core consolidation win: **one** persistent sidecar per host, shared by
|
||||
every bottle, instead of a sidecar bundle per bottle. It's safe to share
|
||||
because the attribution invariant (source IP + identity token, see
|
||||
`registry`) lets the sidecar attribute each request to the right bottle —
|
||||
so per-bottle policy lives in one long-lived process keyed on who's calling.
|
||||
|
||||
`Sidecar` is the backend-neutral lifecycle contract (mirrors `LaunchBroker`):
|
||||
ensure the single instance is up, report it, tear it down. `DockerSidecar`
|
||||
is the docker implementation; a firecracker sidecar VM slots in later.
|
||||
|
||||
The defining behaviour is **idempotent singleton**: `ensure_running` starts
|
||||
the instance if absent and is a no-op if it's already up, so N bottle
|
||||
launches never spawn N sidecars.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import abc
|
||||
|
||||
from ..docker_cmd import run_docker
|
||||
|
||||
SIDECAR_NAME = "bot-bottle-orch-sidecar"
|
||||
SIDECAR_LABEL = "bot-bottle-orch-sidecar=1"
|
||||
|
||||
|
||||
class SidecarError(Exception):
|
||||
"""The shared sidecar failed to start/stop (non-zero `docker` exit)."""
|
||||
|
||||
|
||||
class Sidecar(abc.ABC):
|
||||
"""Lifecycle of the single per-host sidecar. Backend-neutral."""
|
||||
|
||||
name: str
|
||||
|
||||
@abc.abstractmethod
|
||||
def ensure_running(self) -> None:
|
||||
"""Start the sidecar if it isn't already up. Idempotent: a no-op
|
||||
when it's already running (that's the whole point — one per host)."""
|
||||
|
||||
@abc.abstractmethod
|
||||
def is_running(self) -> bool:
|
||||
"""True iff the sidecar instance is currently up."""
|
||||
|
||||
@abc.abstractmethod
|
||||
def stop(self) -> None:
|
||||
"""Remove the sidecar. Idempotent — absent is success."""
|
||||
|
||||
|
||||
class DockerSidecar(Sidecar):
|
||||
"""The consolidated sidecar as a single, fixed-name Docker container."""
|
||||
|
||||
def __init__(self, image_ref: str, *, name: str = SIDECAR_NAME) -> None:
|
||||
self.image_ref = image_ref
|
||||
self.name = name
|
||||
|
||||
def is_running(self) -> bool:
|
||||
proc = run_docker([
|
||||
"docker", "ps",
|
||||
"--filter", f"name=^{self.name}$",
|
||||
"--filter", "status=running",
|
||||
"--format", "{{.Names}}",
|
||||
])
|
||||
return self.name in proc.stdout.split()
|
||||
|
||||
def ensure_running(self) -> None:
|
||||
if self.is_running():
|
||||
return
|
||||
# Clear any stale (stopped) container holding the fixed name, then
|
||||
# start fresh. `rm --force` on an absent name is a tolerated no-op.
|
||||
run_docker(["docker", "rm", "--force", self.name])
|
||||
proc = run_docker([
|
||||
"docker", "run", "--detach",
|
||||
"--name", self.name,
|
||||
"--label", SIDECAR_LABEL,
|
||||
self.image_ref,
|
||||
])
|
||||
if proc.returncode != 0:
|
||||
raise SidecarError(f"sidecar failed to start: {proc.stderr.strip()}")
|
||||
|
||||
def stop(self) -> None:
|
||||
proc = run_docker(["docker", "rm", "--force", self.name])
|
||||
if proc.returncode != 0 and "No such container" not in proc.stderr:
|
||||
raise SidecarError(f"sidecar failed to stop: {proc.stderr.strip()}")
|
||||
|
||||
|
||||
__all__ = ["Sidecar", "DockerSidecar", "SidecarError", "SIDECAR_NAME", "SIDECAR_LABEL"]
|
||||
+2
-2
@@ -10,7 +10,7 @@ suite points it at a throwaway dir instead of monkey-patching the function
|
||||
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 sidecar bundle).
|
||||
layer (and to COPY flat into the gateway).
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
@@ -35,7 +35,7 @@ def host_db_path() -> Path:
|
||||
|
||||
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 sidecar without exposing the root's other contents (git-gate
|
||||
with a gateway without exposing the root's other contents (git-gate
|
||||
keys, per-bottle state, ...)."""
|
||||
return bot_bottle_root() / "db" / HOST_DB_FILENAME
|
||||
|
||||
|
||||
@@ -0,0 +1,128 @@
|
||||
"""Gateway-side per-client policy resolver (PRD 0070).
|
||||
|
||||
The consolidated gateway serves every bottle from one process, so for each
|
||||
request it must apply the *calling* bottle's policy, selected by the source
|
||||
IP the attribution invariant makes unspoofable. This resolves that policy
|
||||
from the orchestrator's control plane (`POST /resolve`), keyed on the
|
||||
`(source_ip, identity_token)` pair.
|
||||
|
||||
**Always fresh — no cache.** The resolver is called rarely enough that a
|
||||
round-trip doesn't matter, and correctness matters more than speed: every
|
||||
resolve reflects the orchestrator's *current* view, so a revocation, a
|
||||
policy change, or a bottle teardown the orchestrator knows about is honored
|
||||
immediately rather than lingering for a cache TTL. (If this ever becomes a
|
||||
hot path, add caching with orchestrator-driven invalidation — not a blind
|
||||
TTL.)
|
||||
|
||||
**Fail-closed:** an unattributed client (the orchestrator answers `403`)
|
||||
resolves to `None`, and the caller (the egress addon, git-gate) must then
|
||||
deny — exactly as an unknown bottle should be treated. Orchestrator
|
||||
*errors* (unreachable / unexpected status) raise, so the caller can fail
|
||||
closed too rather than silently serving stale or empty policy.
|
||||
|
||||
The resolved value is the policy blob the orchestrator stores verbatim; the
|
||||
consumer parses it (e.g. the egress addon's `load_config`). This module is
|
||||
stdlib-only and free of bot-bottle imports so it can be COPYed flat into
|
||||
the gateway.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import urllib.error
|
||||
import urllib.request
|
||||
|
||||
DEFAULT_TIMEOUT_SECONDS = 2.0
|
||||
|
||||
|
||||
class PolicyResolveError(RuntimeError):
|
||||
"""The orchestrator was unreachable or returned an unexpected status —
|
||||
distinct from a clean `403` (unattributed), which returns None."""
|
||||
|
||||
|
||||
class PolicyResolver:
|
||||
"""Resolves each client's policy from the orchestrator, fresh per call."""
|
||||
|
||||
def __init__(self, base_url: str, *, timeout: float = DEFAULT_TIMEOUT_SECONDS) -> None:
|
||||
self._base = base_url.rstrip("/")
|
||||
self._timeout = timeout
|
||||
|
||||
def _post_resolve(self, source_ip: str, identity_token: str) -> dict[str, object] | None:
|
||||
"""The orchestrator's `/resolve` payload for this client, or None if
|
||||
unattributed (a clean `403`). Raises `PolicyResolveError` on an
|
||||
unreachable / unexpected-status / malformed response so every caller
|
||||
can fail closed. Shared by `resolve` and `resolve_bottle_id`."""
|
||||
body = json.dumps(
|
||||
{"source_ip": source_ip, "identity_token": identity_token}
|
||||
).encode()
|
||||
req = urllib.request.Request(
|
||||
f"{self._base}/resolve", data=body, method="POST",
|
||||
headers={"Content-Type": "application/json"},
|
||||
)
|
||||
try:
|
||||
with urllib.request.urlopen(req, timeout=self._timeout) as resp:
|
||||
payload = json.loads(resp.read())
|
||||
except urllib.error.HTTPError as e:
|
||||
if e.code == 403:
|
||||
return None # unattributed → fail closed (caller denies)
|
||||
raise PolicyResolveError(f"/resolve returned HTTP {e.code}") from e
|
||||
except (urllib.error.URLError, TimeoutError, OSError, ValueError) as e:
|
||||
raise PolicyResolveError(f"/resolve unreachable or malformed: {e}") from e
|
||||
return payload if isinstance(payload, dict) else {}
|
||||
|
||||
def resolve(self, source_ip: str, identity_token: str = "") -> str | None:
|
||||
"""The calling bottle's policy blob, or None if unattributed. Always
|
||||
fetches from the orchestrator so revocations / changes / teardowns
|
||||
are honored immediately.
|
||||
|
||||
`identity_token` is optional *transitionally* — omitting it resolves
|
||||
by source IP alone (the network-layer attribution, sound by
|
||||
construction on Firecracker's `/31`+nft, weaker elsewhere). The
|
||||
consolidated end state makes the token mandatory so the app-layer
|
||||
defense is always enforced, not silently degraded; that flips at the
|
||||
`/resolve` boundary once identity-token *delivery* lands (a PRD 0070
|
||||
open question — we can't require what the agent can't yet present).
|
||||
Raises `PolicyResolveError` if the orchestrator can't be reached."""
|
||||
payload = self._post_resolve(source_ip, identity_token)
|
||||
if payload is None:
|
||||
return None
|
||||
policy = payload.get("policy")
|
||||
return policy if isinstance(policy, str) else ""
|
||||
|
||||
def resolve_bottle_id(self, source_ip: str, identity_token: str = "") -> str | None:
|
||||
"""The calling bottle's id, or None if unattributed. This is the
|
||||
source-IP-keyed identity the git-gate uses to select the bottle's
|
||||
repo namespace (there is no per-bottle policy blob to parse — the
|
||||
bottle *is* the namespace). Same fail-closed contract as `resolve`."""
|
||||
payload = self._post_resolve(source_ip, identity_token)
|
||||
if payload is None:
|
||||
return None
|
||||
bottle_id = payload.get("bottle_id")
|
||||
return bottle_id if isinstance(bottle_id, str) and bottle_id else None
|
||||
|
||||
def resolve_policy_and_bottle_id(
|
||||
self, source_ip: str, identity_token: str = "",
|
||||
) -> tuple[str | None, str | None, dict[str, str]]:
|
||||
"""The policy blob, bottle id, **and per-bottle egress auth tokens** in
|
||||
a single `/resolve` — so the egress addon gets everything it needs
|
||||
(policy for routing, bottle id for the supervise queue/safelist, tokens
|
||||
to inject upstream auth) in one round-trip. Returns `(None, None, {})`
|
||||
when unattributed (a clean `403`). Raises `PolicyResolveError` if the
|
||||
orchestrator can't be reached, so the caller still fails closed."""
|
||||
payload = self._post_resolve(source_ip, identity_token)
|
||||
if payload is None:
|
||||
return None, None, {}
|
||||
policy = payload.get("policy")
|
||||
bottle_id = payload.get("bottle_id")
|
||||
raw = payload.get("tokens")
|
||||
tokens = {
|
||||
k: v for k, v in raw.items() if isinstance(k, str) and isinstance(v, str)
|
||||
} if isinstance(raw, dict) else {}
|
||||
return (
|
||||
policy if isinstance(policy, str) else "",
|
||||
bottle_id if isinstance(bottle_id, str) and bottle_id else None,
|
||||
tokens,
|
||||
)
|
||||
|
||||
|
||||
__all__ = ["PolicyResolver", "PolicyResolveError"]
|
||||
@@ -26,7 +26,7 @@ class QueueStore(DbStore):
|
||||
if db_path is not None:
|
||||
resolved = db_path
|
||||
else:
|
||||
# In the sidecar container SUPERVISE_DB_PATH points at the
|
||||
# In the gateway container SUPERVISE_DB_PATH points at the
|
||||
# bind-mounted host DB. On the host this env var is never set,
|
||||
# so we always fall through to host_db_path().
|
||||
env_path = os.environ.get("SUPERVISE_DB_PATH", "").strip()
|
||||
|
||||
+14
-14
@@ -1,25 +1,25 @@
|
||||
"""Per-bottle supervise plane (PRD 0013).
|
||||
|
||||
The supervise plane is the per-bottle MCP sidecar plus its host-side
|
||||
queue/audit support. The sidecar (bot_bottle.supervise_server)
|
||||
The supervise plane is the per-bottle MCP daemon plus its host-side
|
||||
queue/audit support. The daemon (bot_bottle.supervise_server)
|
||||
sits on the bottle's internal network and exposes MCP tools the agent
|
||||
calls when it needs an operator-reviewed egress change:
|
||||
|
||||
* egress-block / allow — agent proposes a new routes.yaml
|
||||
|
||||
Each tool call: the agent passes the full proposed file plus a
|
||||
justification text. The sidecar validates the proposal syntactically,
|
||||
justification text. The gateway validates the proposal syntactically,
|
||||
writes it to the host SQLite queue table, and holds the tool-call
|
||||
connection open. The operator's supervise TUI
|
||||
(bot_bottle.cli.supervise) sees the proposal, accepts
|
||||
approve / modify / reject, and writes a response row. The sidecar sees
|
||||
approve / modify / reject, and writes a response row. The gateway sees
|
||||
the response and returns `{status, notes}` to the agent.
|
||||
|
||||
This module defines the host-side library: dataclasses for the queue
|
||||
record shapes, queue read/write helpers, the audit log writer, and the
|
||||
diff renderer. The in-container sidecar lives in
|
||||
diff renderer. The in-gateway daemon lives in
|
||||
bot_bottle/supervise_server.py; the supervise daemon's container
|
||||
lifecycle is owned by the sidecar bundle (PRD 0024).
|
||||
lifecycle is owned by the gateway (PRD 0024).
|
||||
|
||||
For 0013 the supervisor's approval handlers are deliberately no-ops:
|
||||
on approval the audit log is written and the response file is
|
||||
@@ -75,18 +75,18 @@ except ImportError:
|
||||
|
||||
try:
|
||||
from .paths import bot_bottle_root
|
||||
except ImportError: # flat imports inside the sidecar bundle
|
||||
except ImportError: # flat imports inside the gateway
|
||||
from paths import bot_bottle_root # type: ignore[import-not-found,no-redef] # pylint: disable=import-error,no-name-in-module
|
||||
|
||||
|
||||
SUPERVISE_HOSTNAME = "supervise"
|
||||
SUPERVISE_PORT = 9100
|
||||
|
||||
# The supervise sidecar uses these to query egress's
|
||||
# The supervise daemon uses these to query egress's
|
||||
# introspection endpoint for the `list-egress-routes` MCP
|
||||
# tool. The hostname + port match egress's docker network
|
||||
# listen port (see backend.docker.egress.EGRESS_PORT). The supervise
|
||||
# daemon runs inside the sidecar bundle alongside egress, so loopback
|
||||
# daemon runs inside the gateway alongside egress, so loopback
|
||||
# is the stable address across docker, firecracker, and Apple
|
||||
# Container backends.
|
||||
EGRESS_FORWARD_PROXY = "http://127.0.0.1:9099"
|
||||
@@ -117,7 +117,7 @@ try:
|
||||
from .audit_store import AuditStore
|
||||
from .store_manager import StoreManager
|
||||
except ImportError:
|
||||
# Sidecar bundle: files are flat-copied under /app, not a package.
|
||||
# Gateway: files are flat-copied under /app, not a package.
|
||||
from queue_store import QueueStore # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
|
||||
from audit_store import AuditStore # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
|
||||
from store_manager import StoreManager # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
|
||||
@@ -222,14 +222,14 @@ def sha256_hex(content: str) -> str:
|
||||
return hashlib.sha256(content.encode("utf-8")).hexdigest()
|
||||
|
||||
|
||||
# --- Sidecar plan + abstract lifecycle -------------------------------------
|
||||
# --- Gateway plan + abstract lifecycle -------------------------------------
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class SupervisePlan:
|
||||
"""Output of Supervise.prepare; consumed by .start.
|
||||
|
||||
`db_path` is the host database bind-mounted into the sidecar at
|
||||
`db_path` is the host database bind-mounted into the gateway at
|
||||
/run/supervise/bot-bottle.db. `internal_network` is empty at
|
||||
prepare time; the backend's launch step fills it via
|
||||
dataclasses.replace before calling .start."""
|
||||
@@ -240,8 +240,8 @@ class SupervisePlan:
|
||||
|
||||
|
||||
class Supervise(ABC):
|
||||
"""Per-bottle supervise sidecar. Encapsulates host-side database
|
||||
staging; the sidecar's start/stop lifecycle is backend-specific."""
|
||||
"""Per-bottle supervise daemon. Encapsulates host-side database
|
||||
staging; the gateway's start/stop lifecycle is backend-specific."""
|
||||
|
||||
def prepare(
|
||||
self,
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
"""Supervise sidecar HTTP server (PRD 0013).
|
||||
"""Supervise daemon HTTP server (PRD 0013).
|
||||
|
||||
Per-bottle MCP server exposing tools the agent calls to propose egress
|
||||
config changes when stuck. The tools are `egress-allow`,
|
||||
@@ -15,6 +15,12 @@ The bottle slug arrives via SUPERVISE_BOTTLE_SLUG env (stamped at
|
||||
container creation by the backend's start step). SUPERVISE_DB_PATH
|
||||
points at the bind-mounted host database.
|
||||
|
||||
Consolidated (PRD 0070): when BOT_BOTTLE_ORCHESTRATOR_URL is set, one
|
||||
shared server fronts every bottle and attributes each proposal to the
|
||||
calling bottle by source IP (resolved from the orchestrator) instead of a
|
||||
fixed slug — an unattributed source fails closed. Unset → the legacy
|
||||
per-bottle single-tenant server, unchanged.
|
||||
|
||||
Speaks MCP over HTTP+JSON-RPC. Methods handled:
|
||||
|
||||
* `initialize` — handshake; returns server info + caps.
|
||||
@@ -40,16 +46,18 @@ import time
|
||||
import typing
|
||||
import urllib.error
|
||||
import urllib.request
|
||||
from dataclasses import dataclass
|
||||
from dataclasses import dataclass, replace
|
||||
|
||||
try:
|
||||
# Same-directory imports inside the bundle container; these files are
|
||||
# COPYed flat under /app by Dockerfile.sidecars.
|
||||
# COPYed flat under /app by Dockerfile.gateway.
|
||||
from egress_addon_core import LOG_OFF, load_config
|
||||
from policy_resolver import PolicyResolveError, PolicyResolver
|
||||
import supervise as _sv
|
||||
except ModuleNotFoundError:
|
||||
# Package imports for host-side tests and tooling.
|
||||
from .egress_addon_core import LOG_OFF, load_config
|
||||
from .policy_resolver import PolicyResolveError, PolicyResolver
|
||||
from . import supervise as _sv
|
||||
|
||||
|
||||
@@ -73,6 +81,12 @@ DEFAULT_RESPONSE_TIMEOUT_SECONDS = 30.0
|
||||
MIN_RESPONSE_POLL_INTERVAL_SECONDS = 0.05
|
||||
EGRESS_LIST_TIMEOUT_SECONDS = 5.0
|
||||
|
||||
# Consolidated (multi-tenant) mode: when set, one shared supervise server
|
||||
# fronts every bottle and attributes each proposal to the calling bottle by
|
||||
# source IP (resolved from the orchestrator), instead of a single
|
||||
# SUPERVISE_BOTTLE_SLUG env. Unset → legacy per-bottle single-tenant.
|
||||
ORCHESTRATOR_URL_ENV = "BOT_BOTTLE_ORCHESTRATOR_URL"
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class JsonRpcRequest:
|
||||
@@ -511,9 +525,30 @@ class MCPHandler(http.server.BaseHTTPRequestHandler):
|
||||
if method == "tools/list":
|
||||
return handle_tools_list(req.params)
|
||||
if method == "tools/call":
|
||||
return handle_tools_call(req.params, config)
|
||||
# Attribute the proposal to the calling bottle. Single-tenant → the
|
||||
# env slug on `config`; consolidated → the source-IP-resolved
|
||||
# bottle id, so one shared server queues each bottle's proposal
|
||||
# under its own slug.
|
||||
return handle_tools_call(req.params, self._attributed_config(config))
|
||||
raise _RpcClientError(ERR_METHOD_NOT_FOUND, f"method not found: {method}")
|
||||
|
||||
def _attributed_config(self, config: ServerConfig) -> ServerConfig:
|
||||
"""The ServerConfig with `bottle_slug` bound to *this request's* bottle.
|
||||
Single-tenant (no resolver): unchanged. Consolidated: the bottle id
|
||||
attributed from the source IP — **fail-closed**, an unattributed or
|
||||
unreachable source raises so no proposal is queued under the wrong (or
|
||||
empty) slug."""
|
||||
resolver = getattr(self.server, "policy_resolver", None)
|
||||
if resolver is None:
|
||||
return config
|
||||
try:
|
||||
bottle_id = resolver.resolve_bottle_id(self.client_address[0])
|
||||
except PolicyResolveError as e:
|
||||
raise _RpcInternalError(f"orchestrator unreachable, cannot attribute: {e}") from e
|
||||
if not bottle_id:
|
||||
raise _RpcInternalError("request source is not attributed to a bottle")
|
||||
return replace(config, bottle_slug=bottle_id)
|
||||
|
||||
def _write_jsonrpc(self, body: bytes) -> None:
|
||||
self.send_response(200)
|
||||
self.send_header("Content-Type", "application/json")
|
||||
@@ -537,6 +572,9 @@ class MCPServer(socketserver.ThreadingMixIn, http.server.HTTPServer):
|
||||
allow_reuse_address = True
|
||||
daemon_threads = True
|
||||
config: ServerConfig = ServerConfig(bottle_slug="")
|
||||
# None → single-tenant (proposals use config.bottle_slug); set → consolidated
|
||||
# (each proposal attributed to the source-IP-resolved bottle).
|
||||
policy_resolver: "PolicyResolver | None" = None
|
||||
|
||||
|
||||
# --- Entry point -----------------------------------------------------------
|
||||
@@ -548,15 +586,17 @@ def serve(
|
||||
port: int = _sv.SUPERVISE_PORT,
|
||||
bind: str = "0.0.0.0",
|
||||
response_timeout_seconds: float = DEFAULT_RESPONSE_TIMEOUT_SECONDS,
|
||||
resolver: "PolicyResolver | None" = None,
|
||||
) -> typing.NoReturn:
|
||||
server = MCPServer((bind, port), MCPHandler)
|
||||
server.config = ServerConfig(
|
||||
bottle_slug=bottle_slug,
|
||||
response_timeout_seconds=response_timeout_seconds,
|
||||
)
|
||||
server.policy_resolver = resolver
|
||||
mode = "multi-tenant" if resolver else f"slug={bottle_slug!r}"
|
||||
sys.stderr.write(
|
||||
f"supervise listening on {bind}:{port}; "
|
||||
f"slug={bottle_slug!r}; "
|
||||
f"supervise listening on {bind}:{port}; {mode}; "
|
||||
f"tools: {', '.join(t['name'] for t in TOOL_DEFINITIONS)}\n" # type: ignore[arg-type]
|
||||
)
|
||||
sys.stderr.flush()
|
||||
@@ -571,8 +611,12 @@ def serve(
|
||||
|
||||
def main(argv: list[str]) -> int:
|
||||
del argv # config is env-only, no CLI flags
|
||||
orch_url = os.environ.get(ORCHESTRATOR_URL_ENV, "").strip()
|
||||
resolver = PolicyResolver(orch_url) if orch_url else None
|
||||
bottle_slug = os.environ.get("SUPERVISE_BOTTLE_SLUG", "")
|
||||
if not bottle_slug:
|
||||
# Consolidated mode resolves the slug per request, so the env slug is
|
||||
# optional there; single-tenant still requires it.
|
||||
if not bottle_slug and resolver is None:
|
||||
sys.stderr.write("supervise: SUPERVISE_BOTTLE_SLUG env is unset\n")
|
||||
return 2
|
||||
port = int(os.environ.get("SUPERVISE_PORT", str(_sv.SUPERVISE_PORT)))
|
||||
@@ -587,6 +631,7 @@ def main(argv: list[str]) -> int:
|
||||
port=port,
|
||||
bind=bind,
|
||||
response_timeout_seconds=response_timeout_seconds,
|
||||
resolver=resolver,
|
||||
)
|
||||
return 0 # serve() does not return
|
||||
|
||||
|
||||
@@ -71,7 +71,7 @@ class YamlSubsetError(ValueError):
|
||||
that want fatal-exit semantics (manifest loader, egress-apply,
|
||||
etc.) catch this at their own boundary and forward to `die`;
|
||||
callers running outside the bot-bottle CLI process (the
|
||||
egress sidecar's addon) handle it as a normal exception."""
|
||||
egress daemon's addon) handle it as a normal exception."""
|
||||
|
||||
|
||||
|
||||
|
||||
+1
-2
@@ -22,8 +22,7 @@ mounted in. That topology breaks two assumptions those tests make:
|
||||
`http://127.0.0.1:<host_port>` from inside the job time out.
|
||||
|
||||
The affected tests (`test_orphan_cleanup.test_create_and_remove`,
|
||||
`test_sidecar_bundle_image.TestSidecarBundleImage`,
|
||||
`test_sidecar_bundle_compose.TestSidecarBundleCompose`) still run
|
||||
`test_gateway_image.TestGatewayImage`) still run
|
||||
locally where the test process and Docker daemon share a host.
|
||||
Making them work in CI is a follow-up: either re-write them to
|
||||
discover container IPs via `docker inspect`, or reconfigure the
|
||||
|
||||
+2
-2
@@ -38,7 +38,7 @@ Type "y"
|
||||
Enter
|
||||
|
||||
# Wait for the bottle to launch: networks created, pipelock + git-gate
|
||||
# sidecars started, agent container started, claude boots.
|
||||
# companion containers started, agent container started, claude boots.
|
||||
Sleep 22s
|
||||
|
||||
# Probe 1 — warm-up. A reply at all proves api.anthropic.com is
|
||||
@@ -72,7 +72,7 @@ Type "init /tmp/r, commit AKIAQRJHK7N5ZPM2VXTL to leak.txt, push to ssh://git@up
|
||||
Enter
|
||||
Sleep 30s
|
||||
|
||||
# Leave claude. The launcher tears down the container, sidecars, and
|
||||
# Leave claude. The launcher tears down the container, companion containers, and
|
||||
# networks on session end.
|
||||
Ctrl+D
|
||||
Sleep 4s
|
||||
|
||||
@@ -10,8 +10,8 @@
|
||||
|
||||
## Summary
|
||||
|
||||
Replace the **per-bottle sidecar bundle** with a single **persistent,
|
||||
per-host orchestrator**: one long-lived service that runs the sidecar
|
||||
Replace the **per-bottle gateway bundle** with a single **persistent,
|
||||
per-host orchestrator**: one long-lived service that runs the gateway
|
||||
functions (egress / git-gate / supervise), coordinates with the console,
|
||||
and brokers agent launches and teardown. It is **virtualized from the
|
||||
start** using each backend's native isolation primitive — a Firecracker
|
||||
@@ -22,13 +22,13 @@ container on the legacy backend — and is fronted by a single
|
||||
|
||||
## Motivation
|
||||
|
||||
Today each bottle spins up its own sidecar bundle (egress mitmproxy +
|
||||
Today each bottle spins up its own gateway bundle (egress mitmproxy +
|
||||
git-gate + supervise). That costs:
|
||||
|
||||
- **Resources.** N bottles → N heavy bundles booting and idling.
|
||||
- **Operational churn.** Per-launch container/VM lifecycle for the
|
||||
sidecars, a control path baked at launch and torn down at exit.
|
||||
- **A blurry contract.** "How a bottle talks to its sidecar" is
|
||||
gateways, a control path baked at launch and torn down at exit.
|
||||
- **A blurry contract.** "How a bottle talks to its gateway" is
|
||||
re-implemented per backend instead of being one agreed interface.
|
||||
|
||||
A per-host orchestrator collapses the first two and forces the third to
|
||||
@@ -52,11 +52,11 @@ weaken, and the weakened ones must be mitigated by design, not hand-waved.
|
||||
structured, auditable privileged core instead of a fat socket.
|
||||
- **Attribution is enforced, not assumed.** Making source-IP identity a
|
||||
first-class contract invariant (below) means each backend must *prove*
|
||||
it, rather than the sidecar implicitly trusting network position.
|
||||
it, rather than the gateway implicitly trusting network position.
|
||||
|
||||
### What gets weaker, and the mitigation
|
||||
|
||||
1. **Secret concentration.** Per-bottle sidecars isolate secrets at the
|
||||
1. **Secret concentration.** Per-bottle gateways isolate secrets at the
|
||||
process boundary — each holds only its bottle's tokens/keys. A host
|
||||
orchestrator concentrates **every bottle's** egress tokens, git deploy
|
||||
keys, and the console credential in one long-lived process. A single
|
||||
@@ -75,7 +75,7 @@ weaken, and the weakened ones must be mitigated by design, not hand-waved.
|
||||
fleet, plus launch authority, plus the console token.
|
||||
- *Mitigation:* the orchestrator is itself confined (its own VM/container
|
||||
with its own fail-closed egress); make it **restartable without killing
|
||||
running agent VMs** (agents keep running; they briefly lose sidecar
|
||||
running agent VMs** (agents keep running; they briefly lose gateway
|
||||
connectivity until it's back); persist state to a host volume so a
|
||||
restart re-adopts live bottles rather than losing them.
|
||||
|
||||
@@ -114,13 +114,13 @@ responsibility** and part of the contract:
|
||||
- **Apple** — the host-only network.
|
||||
|
||||
If a backend can't honor the invariant, source-IP consolidation is not
|
||||
safe there and that backend keeps per-bottle sidecars. The invariant is a
|
||||
safe there and that backend keeps per-bottle gateways. The invariant is a
|
||||
hard precondition, not an aspiration.
|
||||
|
||||
**Defense-in-depth — a per-bottle identity token.** On top of the
|
||||
network-layer invariant, inject a per-bottle secret token into every
|
||||
request the agent makes to the orchestrator (the agent already egresses
|
||||
through the sidecar proxy, so this is cheap to add). It gives an
|
||||
through the gateway proxy, so this is cheap to add). It gives an
|
||||
**application-layer** proof of identity independent of the network layer:
|
||||
|
||||
- On **Firecracker** the `/31` + nft already make source IP unspoofable
|
||||
@@ -133,7 +133,7 @@ Requirements: the token is **per-bottle, unguessable, and
|
||||
non-cross-leakable** — a bottle can only ever prove it is *itself* (it
|
||||
can't learn another bottle's token, given bottle isolation), so a hostile
|
||||
agent gains nothing by presenting it. The orchestrator provisions the
|
||||
token at launch and the sidecar requires it to attribute + authorize.
|
||||
token at launch and the gateway requires it to attribute + authorize.
|
||||
Note this hardens *attribution*, not *secret exposure*: it's app-layer, so
|
||||
a compromised orchestrator still sees every token (that's the
|
||||
concentration problem, addressed separately under Secret handling).
|
||||
@@ -178,7 +178,7 @@ manifest anywhere a raw token value is accepted, discovered from
|
||||
`AgentProvider`s are — because maintaining every forge/cloud/OAuth
|
||||
provider in-tree is untenable. The orchestrator's vault mints via these
|
||||
providers; but the abstraction is shippable independently and today's
|
||||
per-bottle sidecars can use it too.
|
||||
per-bottle gateways can use it too.
|
||||
|
||||
## Design
|
||||
|
||||
@@ -195,7 +195,7 @@ Three surfaces; only one is per-backend.
|
||||
every host (no vsock/unix-socket portability caveats); a local unix
|
||||
socket is a fine optimization, but HTTP is the wire contract.
|
||||
2. **Data plane (agent → orchestrator)** — the egress / git / supervise
|
||||
endpoints. Already agnostic today (agents dial `http://sidecar:9099`);
|
||||
endpoints. Already agnostic today (agents dial `http://gateway:9099`);
|
||||
only the *address* and *how packets get there* are per-backend.
|
||||
3. **Launch / wire (orchestrator → backend)** — the irreducibly
|
||||
backend-specific part; lives on `BottleBackend`.
|
||||
@@ -249,7 +249,7 @@ forged one from a compromised co-located component. The orchestrator signs;
|
||||
the broker verifies with the orchestrator's public key (provisioned at
|
||||
broker install). This is the concrete form of security #3's "structured
|
||||
requests only." Same JSON-with-ids + JWT shape for all
|
||||
orchestrator↔broker/sidecar communication; cases that don't fit get
|
||||
orchestrator↔broker/gateway communication; cases that don't fit get
|
||||
handled as they arise, with this as the default.
|
||||
|
||||
If `BottleBackend` bloats, the pressure valve is composition one level
|
||||
@@ -299,10 +299,10 @@ and integrate a console against.
|
||||
the data plane and the console reach state through the control-plane RPC,
|
||||
never a direct file handle.** No agent-facing component gets the file, so
|
||||
none can forge attribution. (This supersedes the earlier `ro`-mount idea.)
|
||||
- *Transitional caveat:* today the per-bottle **supervise sidecar
|
||||
- *Transitional caveat:* today the per-bottle **supervise gateway
|
||||
rw-bind-mounts `bot-bottle.db`** to write proposals — exactly the
|
||||
pattern the orchestrator removes (supervise consolidates into the
|
||||
orchestrator; sidecar writes become RPC calls). Until that lands, don't
|
||||
orchestrator; gateway writes become RPC calls). Until that lands, don't
|
||||
put the attribution registry behind a data-plane-writable mount.
|
||||
|
||||
Implementation note for the VM slices: SQLite **WAL** over a guest share
|
||||
@@ -327,7 +327,7 @@ orchestrator becomes a VM. Decouple the two risks instead:
|
||||
|
||||
Backend order (cheapest proof → hardest → last):
|
||||
|
||||
1. **Docker orchestrator** — nearly free (the sidecar bundle is already
|
||||
1. **Docker orchestrator** — nearly free (the gateway bundle is already
|
||||
containers; collapse N bundles into one persistent container). Proves
|
||||
consolidation + the `BottleBackend` seam with the least moving parts.
|
||||
2. **Firecracker orchestrator** — the real work: the shim + VM-to-VM
|
||||
@@ -336,13 +336,13 @@ Backend order (cheapest proof → hardest → last):
|
||||
the dev-harness so the app logic is already proven.
|
||||
3. **macOS (Apple container)** — last (container-to-container networking).
|
||||
|
||||
Keep the sidecar **service one shared thing** throughout.
|
||||
Keep the gateway **service one shared thing** throughout.
|
||||
|
||||
## Non-goals
|
||||
|
||||
- Removing OCI/Dockerfile support for agent images (0069's concern).
|
||||
- A single database for *all* config (see the three-tier table).
|
||||
- Changing the per-bottle isolation of agent workloads — only the sidecar
|
||||
- Changing the per-bottle isolation of agent workloads — only the gateway
|
||||
is consolidated; agents stay one-VM/container-each.
|
||||
|
||||
## Relationship to other work
|
||||
@@ -393,7 +393,7 @@ Keep the sidecar **service one shared thing** throughout.
|
||||
`BottleBackend.wire()` (DNAT+forward for fc, shared-net for
|
||||
docker/apple), not orchestrator logic. **Not a blocker** — resolvable at
|
||||
implementation time (may require a bit of host modification, as the pool
|
||||
setup already does on NixOS); an earlier "sidecars in VMs" spike showed
|
||||
setup already does on NixOS); an earlier "gateways in VMs" spike showed
|
||||
it's feasible.
|
||||
- **Live-reload protocol** for per-bottle policy over the HTTP control
|
||||
plane (add/remove routes/keys/proposals without a restart).
|
||||
|
||||
@@ -15,6 +15,25 @@ the biggest credential risk).
|
||||
|
||||
## Summary
|
||||
|
||||
> **Status — implemented (2026-07-14).** This note's recommendation
|
||||
> shipped, so the "today" / "in-flight" tenses below are now historical
|
||||
> (kept as the reasoning that led here). Current reality: bot-bottle no
|
||||
> longer injects raw provider tokens into the agent. The agent's environ
|
||||
> carries only a **placeholder** (e.g.
|
||||
> `CLAUDE_CODE_OAUTH_TOKEN=egress-placeholder`); the real token is held
|
||||
> in the egress sidecar and injected as the upstream `Authorization`
|
||||
> header. Rather than adding a *separate* in-container reverse proxy (as
|
||||
> proposed below), credential injection was folded into the **existing
|
||||
> pipelock/mitmproxy egress firewall**: an `EgressRoute` carries
|
||||
> `auth_scheme` + `token_ref`, the host token is forwarded into the
|
||||
> sidecar addon under an `EGRESS_TOKEN_N` slot, and the addon rewrites
|
||||
> `Authorization` on matching routes — **one MITM, not two** (this
|
||||
> resolves the Infisical-doubling concern noted later). The same
|
||||
> mechanism now covers Codex and Pi provider tokens and git-host PATs.
|
||||
> A `printenv` inside the bottle yields the placeholder, not the secret.
|
||||
> For current wiring see `bot_bottle/egress.py` and
|
||||
> `bot_bottle/contrib/*/agent_provider.py`.
|
||||
|
||||
Today every bot-bottle agent gets `CLAUDE_CODE_OAUTH_TOKEN` (and
|
||||
any `bottle.env` secrets like a Gitea PAT) injected as env vars,
|
||||
which means the agent process can read them with `printenv` or
|
||||
@@ -36,6 +55,24 @@ small bot-bottle-specific reverse proxy modeled on the
|
||||
phantom-token shape is probably the right call. For Gitea / GitHub /
|
||||
GitLab, the same proxy generalizes by config.
|
||||
|
||||
**Updated 2026-07-14:** OneCLI ([onecli.sh](https://onecli.sh/)) —
|
||||
already listed below — has matured into a GA, YC-backed Rust
|
||||
credential gateway ("The Identity Gateway for AI Agents", ~2.5k⭐,
|
||||
300k+ downloads) that implements the **same phantom-token pattern**
|
||||
this note recommends: the agent holds a placeholder token, the
|
||||
gateway swaps it for the real (AES-256-GCM-encrypted) credential at
|
||||
request time. It's now the most mature open-source realization of the
|
||||
exact design proposed here — a production-ready alternative to
|
||||
alpha-stage nono — at the cost of being a broader product (built-in
|
||||
vault + management dashboard + hosted cloud tier + 50+ app
|
||||
integrations) rather than a minimal proxy. Its managed/cloud tier and
|
||||
per-agent dashboard also overlap bot-bottle's own planned paid control
|
||||
plane (bot-bottle-console, issue #327), so it's worth tracking as both
|
||||
a build-vs-adopt option *and* a product-level competitor. The
|
||||
build-first recommendation still stands (see synthesis below), but
|
||||
adopting OneCLI's OSS core is now a credible alternative where nono was
|
||||
too green.
|
||||
|
||||
## The shared problem
|
||||
|
||||
Linux has no per-env-var ACL. Once a var is in a process's
|
||||
@@ -77,7 +114,9 @@ The remaining credible designs reduce to three:
|
||||
|
||||
### Anthropic / Claude Code
|
||||
|
||||
**Today's wiring** (`bot_bottle/cli/start.py`): the host's
|
||||
**Original wiring** (pre-gateway; **superseded 2026-07-14** — see the
|
||||
Status note in the Summary; the token now lives in the egress sidecar
|
||||
and the agent gets a placeholder): the host's
|
||||
`BOT_BOTTLE_CLAUDE_OAUTH_TOKEN` is forwarded into the bottle as
|
||||
`CLAUDE_CODE_OAUTH_TOKEN` via `docker run -e CLAUDE_CODE_OAUTH_TOKEN`
|
||||
(no `=value`, so the value never lands on argv — good). Inside the
|
||||
@@ -223,7 +262,7 @@ Two categories:
|
||||
| **Infisical Agent Vault** | B | MIT (EE carve-out) | In-process HTTPS_PROXY forward proxy | TLS MITM, dummy-to-real swap | No — HTTPS_PROXY model | Service-level | Active; v0.19.0 May 2026, ~1k⭐ |
|
||||
| **nono** | B | Apache-2.0 | In-process reverse proxy | Phantom token, explicit URL routing | **Yes** — `BASE_URL=http://127.0.0.1:PORT/…` | Host + endpoint | Early alpha; v0.53.0 May 2026, 2.4k⭐ |
|
||||
| **Aegis** | B | Apache-2.0 | In-process reverse proxy | Path routing (`localhost:3100/{svc}/…`) | Configurable, undocumented for Anthropic | Method/path/rate/time | Very new, 10⭐ |
|
||||
| **OneCLI** | B | Apache-2.0 | Reverse proxy + management UI | Host/path matching, Bitwarden integration | Configurable | Per-agent scoping | Active; v1.23.0 May 2026, 2.1k⭐ |
|
||||
| **OneCLI** | B | Apache-2.0 | Reverse proxy + built-in vault + dashboard | **Phantom token** (placeholder→real swap at request time), AES-256-GCM vault | Yes (host match) | Per-agent + endpoint/method + rate limits | GA; Rust; YC-backed; ~2.5k⭐, 300k+ downloads (Jul 2026) |
|
||||
| **Aembit** | B | Proprietary | Sidecar + cloud control plane | TLS intercept, SPIFFE, JIT creds | No — intercepts by destination | Policy-based | GA (Apr 2026) |
|
||||
| **LiteLLM Proxy** | A | MIT | Reverse proxy | Virtual key → upstream key | Yes — set base URL to LiteLLM | Route-level | 45k⭐; **CVE-2026-42208 exploited Apr 2026**, patch v1.83.7 |
|
||||
| **Portkey Gateway** | A | MIT (OSS core) | Reverse proxy | Virtual key vault (cloud or Enterprise self-host) | Yes — documented for Claude Code | Config-based | Production; virtual-key vault needs Enterprise for self-host |
|
||||
@@ -242,6 +281,18 @@ Two categories:
|
||||
`ANTHROPIC_BASE_URL`. **Blocker:** nono is explicitly
|
||||
"early alpha, not security audited."
|
||||
|
||||
**Update (2026-07-14):** OneCLI ([onecli.sh](https://onecli.sh/))
|
||||
ships the same phantom-token shape but is GA and YC-backed (Rust,
|
||||
~2.5k⭐, 300k+ downloads) — the maturity nono lacks. Trade-offs: it's
|
||||
a full identity-gateway *product* (encrypted vault, management
|
||||
dashboard, 50+ one-click app integrations, hosted cloud tier), much
|
||||
heavier than the ~100-line proxy proposed below, and its hosted tier
|
||||
is a third-party credential custodian — precisely the trust
|
||||
dependency bot-bottle's isolation model exists to avoid. So: its
|
||||
Apache-2.0 OSS core is a credible *adopt* candidate for the
|
||||
phantom-token slice; its managed offering is a *competitor*, not a
|
||||
dependency to lean on.
|
||||
|
||||
- **TLS-MITM forward proxies** (Infisical Agent Vault, Cloudflare
|
||||
Sandbox Auth, Aembit, the existing pipelock) all double up on
|
||||
the CA-trust machinery PRD 0006 already built for pipelock.
|
||||
@@ -273,6 +324,15 @@ routing matches the design recommended here exactly; zero TLS
|
||||
work. But "not security audited" + "early alpha" means adopting it
|
||||
is a bet on the project rather than a buy-vs-build win.
|
||||
|
||||
**Mature phantom-token option (added 2026-07-14):** OneCLI — same
|
||||
architecture as nono, but GA, Rust, and YC-backed. Its Apache-2.0 OSS
|
||||
core is now the strongest *adopt* candidate for the phantom-token slice
|
||||
if building is undesirable; the caveats are product surface you don't
|
||||
need (bundled vault + dashboard) and that its hosted tier is a
|
||||
competitor rather than a dependency. Doesn't change the build-first
|
||||
recommendation for the narrow Anthropic-token slice, but it does mean
|
||||
"is there a mature drop-in?" now has a real answer.
|
||||
|
||||
**Most mature OSS purpose-built:** Infisical Agent Vault. MIT,
|
||||
v0.19.0 active, v0.17.0 added a containerized agent mode that
|
||||
maps directly to bot-bottle. Friction is the TLS-MITM topology
|
||||
@@ -293,6 +353,12 @@ exposed.
|
||||
|
||||
## Recommended path forward
|
||||
|
||||
> **Mostly implemented (2026-07-14).** Steps 1–3 shipped — the token
|
||||
> injection moved into the egress sidecar (folded into pipelock rather
|
||||
> than a standalone reverse proxy) and generalized to Codex/Pi/git-host
|
||||
> tokens. Steps 4–5 (issuance-side scope narrowing, per-route allowlists)
|
||||
> remain good hygiene. See the Status note in the Summary.
|
||||
|
||||
In priority order:
|
||||
|
||||
1. **In-container reverse proxy holding `CLAUDE_CODE_OAUTH_TOKEN`.**
|
||||
@@ -376,6 +442,9 @@ already gives us for upstream push credentials.
|
||||
- [nono — phantom token blog](https://nono.sh/blog/blog-credential-injection)
|
||||
- [Aegis — GitHub](https://github.com/getaegis/aegis)
|
||||
- [OneCLI — GitHub](https://github.com/onecli/onecli)
|
||||
- [OneCLI — homepage](https://onecli.sh/)
|
||||
- [OneCLI — Y Combinator company page](https://www.ycombinator.com/companies/onecli)
|
||||
- [Show HN: OneCLI – Vault for AI Agents in Rust](https://news.ycombinator.com/item?id=47353558)
|
||||
- [Sandbox0 — GitHub](https://github.com/sandbox0-ai/sandbox0)
|
||||
- [Buildkite Cleanroom — GitHub](https://github.com/buildkite/cleanroom)
|
||||
- [Aembit IAM for Agentic AI — GA](https://aembit.io/blog/aembit-iam-for-agentic-ai-is-now-generally-available/)
|
||||
|
||||
@@ -71,6 +71,56 @@ manifest merge.
|
||||
network egress is logged by pipelock/mitmproxy, and per-run op-log/audit state
|
||||
is persisted to SQLite.
|
||||
|
||||
- **OneCLI** ([onecli.sh](https://onecli.sh/)) — YC-backed, GA, open-source
|
||||
(Apache-2.0, Rust) "identity gateway for AI agents": a credential/secret
|
||||
broker that holds API keys and OAuth tokens out of the agent's reach and
|
||||
injects them at the network layer (phantom-token — the agent sees a
|
||||
placeholder, the gateway swaps in the real, AES-256-GCM-encrypted credential
|
||||
at request time). Framework-agnostic and drop-in for any HTTP-calling agent,
|
||||
50+ app integrations, plus a hosted cloud tier with a per-agent dashboard and
|
||||
audit logs. Full technical breakdown in
|
||||
[`agent-credential-proxy-landscape.md`](agent-credential-proxy-landscape.md).
|
||||
|
||||
**How close a competitor:** near-exact on the *single axis of agent secret
|
||||
custody* — the exact thing bot-bottle sells as "the agent never sees real
|
||||
credentials, even via `printenv`." OneCLI does that one job well, is mature
|
||||
and funded, and is *more portable* (it sits in front of anything; bot-bottle
|
||||
only helps agents launched through bot-bottle). Takeaway: bot-bottle should
|
||||
stop treating secret custody as a *unique* differentiator. But OneCLI is
|
||||
**not** a competitor to bot-bottle's actual product — it does no agent
|
||||
sandboxing (containers/microVMs), no fleet/manifest layer, no named agents /
|
||||
skills / per-agent system prompts, no multi-provider launching, no egress
|
||||
firewall.
|
||||
|
||||
**Our edge:** (1) *Isolation is the product, not a proxy.* OneCLI keeps the
|
||||
key out of reach at the network layer, but the agent itself still runs
|
||||
unsandboxed — a hijacked agent behind OneCLI has full run of its host and can
|
||||
exfil captured data through any allowed host. bot-bottle runs the agent inside
|
||||
a kernel/VM-enforced sandbox, injects credentials across that same
|
||||
out-of-process boundary, *and* clamps egress with pipelock — defense in depth
|
||||
vs. a single network layer. (2) *Fleet + manifest model* with named agents,
|
||||
skills, per-agent system prompts, multi-provider and multi-backend — OneCLI
|
||||
has no equivalent. (3) *Trust posture:* OneCLI's managed tier reintroduces a
|
||||
third-party credential custodian, whereas bot-bottle's OSS-runtime +
|
||||
paid-control-plane split keeps custody inside the operator's own boundary —
|
||||
the stronger story for the security-minded self-hoster. (4) *Runs inside your
|
||||
network boundary — local/internal reach.* Because bot-bottle executes the
|
||||
agent on your own host (homelab, corporate LAN, a Tailnet) and egress is a
|
||||
manifest field, giving an agent *scoped* access to **internal** resources — a
|
||||
private Gitea, a LAN database, a Tailscale node — is just another egress-route
|
||||
line, not a networking project (the same move an operator already makes to
|
||||
reach their Tailscale services). OneCLI's OSS core can self-host too, but it's
|
||||
a credential *broker* for outbound API calls, not an agent runtime, and its
|
||||
managed tier + 50+ integrations are oriented at public SaaS — it doesn't put
|
||||
the agent behind your firewall for you. This is a reach advantage, distinct
|
||||
from the isolation ones above, and it's a wedge cloud-first agent products
|
||||
(Devin, Copilot Workspace, OneCLI Cloud) structurally can't match. **Tactical
|
||||
read:**
|
||||
adopt OneCLI's OSS core for the credential slice if building is undesirable
|
||||
(it's mature now); don't build atop its managed tier (competitor, not
|
||||
dependency); re-position bot-bottle on isolation + fleet + self-hosted custody
|
||||
rather than "we hide your secrets."
|
||||
|
||||
## What no found project does
|
||||
|
||||
None combine:
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
#
|
||||
# The one-time privileged setup the Firecracker backend needs: a pool of
|
||||
# user- (or group-) owned point-to-point TAP devices plus a fail-closed
|
||||
# nftables table that confines every microVM to its own sidecar.
|
||||
# nftables table that confines every microVM to its own gateway.
|
||||
#
|
||||
# NON-INVASIVE BY DESIGN. It does NOT flip `networking.nftables.enable`
|
||||
# (which would switch your whole host firewall backend) or
|
||||
@@ -150,7 +150,7 @@ in
|
||||
}
|
||||
];
|
||||
|
||||
# VM->sidecar traffic is DNAT'd and forwarded, so forwarding must be on.
|
||||
# VM->gateway traffic is DNAT'd and forwarded, so forwarding must be on.
|
||||
boot.kernel.sysctl."net.ipv4.ip_forward" = 1;
|
||||
|
||||
# One oneshot brings up the whole pool (TAPs + independent nft table)
|
||||
|
||||
@@ -4,7 +4,7 @@
|
||||
# Creates a pool of point-to-point TAP devices (owned by the invoking
|
||||
# user so the backend can open them without root at launch) and a
|
||||
# dedicated nftables table that isolates every VM: a bottle VM can
|
||||
# reach only its own sidecar (published on the host-side TAP IP) and
|
||||
# reach only its own gateway (published on the host-side TAP IP) and
|
||||
# nothing else on the host or network.
|
||||
#
|
||||
# Why a pool + one-time setup: creating a TAP and assigning it an IP
|
||||
@@ -72,9 +72,9 @@ for _v in POOL_SIZE IP_BASE PREFIX TABLE; do
|
||||
[ -n "${!_v}" ] || { echo "error: $_v unresolved (set BOT_BOTTLE_FC_* or fix $_DEFAULTS)" >&2; exit 1; }
|
||||
done
|
||||
|
||||
# Sidecar ports (must match the backend). egress=9099, supervise=9100,
|
||||
# Gateway ports (must match the backend). egress=9099, supervise=9100,
|
||||
# git-http=9420. Reached by the VM at its host-side TAP IP.
|
||||
SIDECAR_PORTS="9099,9100,9420"
|
||||
GATEWAY_PORTS="9099,9100,9420"
|
||||
|
||||
# --- IP math ---------------------------------------------------------
|
||||
# Slot i occupies the /31 {base+2i, base+2i+1}: host = base+2i (the
|
||||
@@ -107,7 +107,7 @@ cmd_up() {
|
||||
fi
|
||||
echo "firecracker net pool: $POOL_SIZE slots, base $IP_BASE, $own_desc"
|
||||
|
||||
# VM->sidecar traffic is DNAT'd to the sidecar container and
|
||||
# VM->gateway traffic is DNAT'd to the gateway container and
|
||||
# forwarded, so forwarding must be enabled (Docker also sets this).
|
||||
sysctl -qw net.ipv4.ip_forward=1
|
||||
|
||||
@@ -135,11 +135,11 @@ _install_nft() {
|
||||
# tool's traffic is affected. Priority -10 runs before Docker's
|
||||
# filter hooks (priority 0); a drop here is terminal for the packet.
|
||||
#
|
||||
# forward: VM egress is DNAT'd to the sidecar (established via
|
||||
# forward: VM egress is DNAT'd to the gateway (established via
|
||||
# `ct status dnat`); return traffic via `ct state established`.
|
||||
# Anything else from a VM is dropped -> no route to the internet
|
||||
# or the rest of the host except through the sidecar proxy.
|
||||
# input: a VM never needs host-local delivery (its sidecar is
|
||||
# or the rest of the host except through the gateway proxy.
|
||||
# input: a VM never needs host-local delivery (its gateway is
|
||||
# reached via DNAT->forward), so drop all direct input from VMs
|
||||
# -> host services bound on 0.0.0.0 are unreachable from the VM.
|
||||
nft -f - <<EOF
|
||||
|
||||
+3
-7
@@ -18,8 +18,7 @@ tests/
|
||||
test_manifest_runtime.py
|
||||
... # many others; see unit/ directory
|
||||
integration/
|
||||
test_sidecar_bundle_image.py
|
||||
test_sidecar_bundle_compose.py
|
||||
test_gateway_image.py
|
||||
test_dry_run_plan.py
|
||||
test_orphan_cleanup.py
|
||||
...
|
||||
@@ -48,12 +47,9 @@ Discovery is invoked with `-t .` (top-level dir = repo root) so the
|
||||
the bottle's runtime, and creates zero Docker resources.
|
||||
- `test_orphan_cleanup.py` — `network_remove` is idempotent against
|
||||
missing resources, so the EXIT trap can call it unconditionally.
|
||||
- `test_sidecar_bundle_image.py` — builds Dockerfile.sidecars and
|
||||
- `test_gateway_image.py` — builds Dockerfile.gateway and
|
||||
probes that gitleaks / mitmdump / supervise are all reachable
|
||||
inside the bundle.
|
||||
- `test_sidecar_bundle_compose.py` — end-to-end compose-up of an
|
||||
agent + bundle pair; verifies the agent reaches the bundle via
|
||||
the legacy network aliases.
|
||||
inside the gateway image.
|
||||
|
||||
## Canaries
|
||||
|
||||
|
||||
@@ -1,142 +0,0 @@
|
||||
"""Integration: Firecracker microVM launch.
|
||||
|
||||
End-to-end against a real Firecracker microVM: prepare + launch a bottle
|
||||
on the firecracker backend and verify the agent execs after provisioning
|
||||
and that the egress proxy env is wired to the sidecar.
|
||||
|
||||
Gated on the `backend status` result for firecracker (0 == the privileged
|
||||
TAP pool + nft isolation table are provisioned). Skips cleanly with setup
|
||||
instructions otherwise, so the suite runs on hosts without the pool.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import contextlib
|
||||
import io
|
||||
import os
|
||||
import shutil
|
||||
import tempfile
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
|
||||
from bot_bottle.backend import BottleSpec, get_bottle_backend
|
||||
from bot_bottle.backend.firecracker import FirecrackerBottleBackend
|
||||
from bot_bottle.manifest import ManifestIndex
|
||||
|
||||
|
||||
def _firecracker_status_ok() -> bool:
|
||||
"""Gate on `./cli.py backend status --backend=firecracker`: a 0 exit
|
||||
means the pool + nft table are ready. Output is captured so the
|
||||
decorator stays quiet during collection; any error → not ready."""
|
||||
buf = io.StringIO()
|
||||
try:
|
||||
with contextlib.redirect_stdout(buf), contextlib.redirect_stderr(buf):
|
||||
return FirecrackerBottleBackend.status() == 0
|
||||
except Exception:
|
||||
return False
|
||||
|
||||
|
||||
_SKIP_MSG = (
|
||||
"firecracker backend not ready — provision the network pool with "
|
||||
"`./cli.py backend setup --backend=firecracker`, then confirm with "
|
||||
"`./cli.py backend status --backend=firecracker`"
|
||||
)
|
||||
|
||||
|
||||
def _minimal_agent_dockerfile(path: Path) -> None:
|
||||
path.write_text(
|
||||
"\n".join((
|
||||
"FROM node:22-slim",
|
||||
"RUN apt-get update \\",
|
||||
" && apt-get install -y --no-install-recommends \\",
|
||||
" ca-certificates curl git \\",
|
||||
" && rm -rf /var/lib/apt/lists/*",
|
||||
"USER node",
|
||||
"WORKDIR /home/node",
|
||||
"CMD [\"sleep\", \"infinity\"]",
|
||||
"",
|
||||
)),
|
||||
encoding="utf-8",
|
||||
)
|
||||
|
||||
|
||||
def _minimal_manifest(dockerfile: Path) -> ManifestIndex:
|
||||
return ManifestIndex.from_json_obj({
|
||||
"bottles": {
|
||||
"dev": {
|
||||
"agent_provider": {
|
||||
"template": "pi",
|
||||
"dockerfile": str(dockerfile),
|
||||
"settings": {
|
||||
"provider": "example",
|
||||
"base_url": "https://example.com/v1",
|
||||
"models": ["smoke"],
|
||||
},
|
||||
},
|
||||
"egress": {"routes": [{"host": "example.com"}]},
|
||||
},
|
||||
},
|
||||
"agents": {
|
||||
"demo": {"skills": [], "prompt": "smoke", "bottle": "dev"},
|
||||
},
|
||||
})
|
||||
|
||||
|
||||
@unittest.skipIf(
|
||||
os.environ.get("GITEA_ACTIONS") == "true",
|
||||
"skipped under act_runner: cannot host Firecracker microVMs",
|
||||
)
|
||||
@unittest.skipUnless(_firecracker_status_ok(), _SKIP_MSG)
|
||||
class TestFirecrackerLaunch(unittest.TestCase):
|
||||
"""Launch once, reuse the bottle across probes."""
|
||||
|
||||
@classmethod
|
||||
def setUpClass(cls) -> None:
|
||||
cls.stage = Path(tempfile.mkdtemp(prefix="cb-firecracker-launch."))
|
||||
cls._launch = None
|
||||
cls.bottle = None
|
||||
dockerfile = cls.stage / "Dockerfile.agent-smoke"
|
||||
_minimal_agent_dockerfile(dockerfile)
|
||||
os.environ["BOT_BOTTLE_BACKEND"] = "firecracker"
|
||||
try:
|
||||
backend = get_bottle_backend()
|
||||
spec = BottleSpec(
|
||||
manifest=_minimal_manifest(dockerfile),
|
||||
agent_name="demo",
|
||||
copy_cwd=False,
|
||||
user_cwd=str(cls.stage),
|
||||
)
|
||||
cls.plan = backend.prepare(spec, stage_dir=cls.stage)
|
||||
cls._launch = backend.launch(cls.plan)
|
||||
cls.bottle = cls._launch.__enter__()
|
||||
except BaseException:
|
||||
if cls._launch is not None:
|
||||
cls._launch.__exit__(None, None, None)
|
||||
shutil.rmtree(cls.stage, ignore_errors=True)
|
||||
os.environ.pop("BOT_BOTTLE_BACKEND", None)
|
||||
raise
|
||||
|
||||
@classmethod
|
||||
def tearDownClass(cls) -> None:
|
||||
try:
|
||||
if cls._launch is not None:
|
||||
cls._launch.__exit__(None, None, None)
|
||||
finally:
|
||||
shutil.rmtree(cls.stage, ignore_errors=True)
|
||||
os.environ.pop("BOT_BOTTLE_BACKEND", None)
|
||||
|
||||
def test_smoke_exec_echo(self) -> None:
|
||||
r = self.bottle.exec("echo hello-from-firecracker") # type: ignore[union-attr]
|
||||
self.assertEqual(0, r.returncode, msg=r.stderr)
|
||||
self.assertIn("hello-from-firecracker", r.stdout)
|
||||
|
||||
def test_proxy_env_points_at_sidecar(self) -> None:
|
||||
r = self.bottle.exec( # type: ignore[union-attr]
|
||||
"printf '%s\\n' \"$HTTPS_PROXY\" \"$HTTP_PROXY\""
|
||||
)
|
||||
self.assertEqual(0, r.returncode, msg=r.stderr)
|
||||
self.assertIn("http", r.stdout.lower())
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
+8
-8
@@ -1,4 +1,4 @@
|
||||
"""Integration: PRD 0024 chunk 1 — the sidecar bundle image builds
|
||||
"""Integration: PRD 0024 chunk 1 — the gateway image builds
|
||||
and the daemon binaries are present + executable inside it.
|
||||
|
||||
This test does NOT exercise the daemons running against real
|
||||
@@ -6,11 +6,11 @@ config (routes.yaml, etc) — that lands in chunk 2 when the
|
||||
renderer wires the bundle into compose. What we verify here is
|
||||
the chunk-1 contract:
|
||||
|
||||
- Dockerfile.sidecars builds (multi-stage works, base layers
|
||||
- Dockerfile.gateway builds (multi-stage works, base layers
|
||||
pull, COPYs resolve).
|
||||
- gitleaks, mitmdump are at the documented paths and answer
|
||||
`--version`.
|
||||
- The Python init at /app/sidecar_init.py runs and prints the
|
||||
- The Python init at /app/gateway_init.py runs and prints the
|
||||
expected "no daemons selected" line when the supervisor is
|
||||
pointed at an empty daemon set.
|
||||
|
||||
@@ -28,18 +28,18 @@ import unittest
|
||||
from tests._docker import skip_unless_docker
|
||||
|
||||
|
||||
_IMAGE = "bot-bottle-sidecars-test:chunk1"
|
||||
_DOCKERFILE = "Dockerfile.sidecars"
|
||||
_IMAGE = "bot-bottle-gateway-test:chunk1"
|
||||
_DOCKERFILE = "Dockerfile.gateway"
|
||||
|
||||
|
||||
@skip_unless_docker()
|
||||
@unittest.skipIf(
|
||||
os.environ.get("GITEA_ACTIONS") == "true",
|
||||
"skipped under act_runner: multi-stage build pulls a 200+MB "
|
||||
"mitmproxy base + two upstream sidecar images; runner storage "
|
||||
"mitmproxy base + two upstream gateway images; runner storage "
|
||||
"+ time budget make this an interactive-only test",
|
||||
)
|
||||
class TestSidecarBundleImage(unittest.TestCase):
|
||||
class TestGatewayImage(unittest.TestCase):
|
||||
"""Builds the image once for the class, then runs a few
|
||||
`docker run` probes against it."""
|
||||
|
||||
@@ -103,7 +103,7 @@ class TestSidecarBundleImage(unittest.TestCase):
|
||||
# ENTRYPOINT wiring works.
|
||||
proc = subprocess.run(
|
||||
["docker", "run", "--rm",
|
||||
"-e", "BOT_BOTTLE_SIDECAR_DAEMONS=nothing",
|
||||
"-e", "BOT_BOTTLE_GATEWAY_DAEMONS=nothing",
|
||||
_IMAGE],
|
||||
stdout=subprocess.PIPE, stderr=subprocess.STDOUT,
|
||||
timeout=10.0,
|
||||
@@ -1,239 +0,0 @@
|
||||
"""Integration: macOS Container launch topology.
|
||||
|
||||
End-to-end against Apple's real `container` runtime. The smoke launches
|
||||
a bottle with the experimental macOS Container backend and verifies the
|
||||
properties that make the explicit-proxy launch acceptable:
|
||||
|
||||
- the agent can exec commands after provisioning;
|
||||
- HTTP(S)_PROXY points at the sidecar's internal-network IP;
|
||||
- allowlisted HTTPS reaches the egress sidecar;
|
||||
- direct egress with proxy env removed fails from the internal-only
|
||||
agent network;
|
||||
- non-allowlisted proxy traffic is blocked.
|
||||
|
||||
Skipped under Gitea Actions and on hosts without Apple's `container`.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import platform
|
||||
import shutil
|
||||
import subprocess
|
||||
import tempfile
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
|
||||
from bot_bottle.backend import BottleSpec, get_bottle_backend
|
||||
from bot_bottle.backend.macos_container.util import (
|
||||
dns_server as _container_dns_server,
|
||||
is_available as _container_available,
|
||||
)
|
||||
from bot_bottle.manifest import ManifestIndex
|
||||
|
||||
|
||||
_AGENT_PROMPT = "You are a launch smoke-test agent. Be brief."
|
||||
|
||||
|
||||
def _minimal_agent_dockerfile(path: Path) -> None:
|
||||
path.write_text(
|
||||
"\n".join((
|
||||
"FROM node:22-slim",
|
||||
"RUN apt-get update \\",
|
||||
" && apt-get install -y --no-install-recommends \\",
|
||||
" ca-certificates curl git \\",
|
||||
" && rm -rf /var/lib/apt/lists/*",
|
||||
"USER node",
|
||||
"WORKDIR /home/node",
|
||||
"CMD [\"sleep\", \"infinity\"]",
|
||||
"",
|
||||
)),
|
||||
encoding="utf-8",
|
||||
)
|
||||
|
||||
|
||||
def _minimal_manifest(dockerfile: Path) -> ManifestIndex:
|
||||
return ManifestIndex.from_json_obj({
|
||||
"bottles": {
|
||||
"dev": {
|
||||
"agent_provider": {
|
||||
"template": "pi",
|
||||
"dockerfile": str(dockerfile),
|
||||
"settings": {
|
||||
"provider": "example",
|
||||
"base_url": "https://example.com/v1",
|
||||
"models": ["smoke"],
|
||||
},
|
||||
},
|
||||
"egress": {
|
||||
"routes": [
|
||||
{"host": "example.com"},
|
||||
],
|
||||
},
|
||||
},
|
||||
},
|
||||
"agents": {
|
||||
"demo": {
|
||||
"skills": [],
|
||||
"prompt": _AGENT_PROMPT,
|
||||
"bottle": "dev",
|
||||
},
|
||||
},
|
||||
})
|
||||
|
||||
|
||||
def _buildkit_dns_available() -> bool:
|
||||
if platform.system() != "Darwin" or not _container_available():
|
||||
return False
|
||||
stage = Path(tempfile.mkdtemp(prefix="cb-container-buildkit-dns."))
|
||||
image = "bot-bottle-buildkit-dns-check:latest"
|
||||
try:
|
||||
dockerfile = stage / "Dockerfile"
|
||||
dockerfile.write_text(
|
||||
"FROM debian:bookworm-slim\n"
|
||||
"RUN getent hosts deb.debian.org\n",
|
||||
encoding="utf-8",
|
||||
)
|
||||
result = subprocess.run(
|
||||
[
|
||||
"container", "build",
|
||||
"--dns", _container_dns_server(),
|
||||
"-t", image,
|
||||
"-f", str(dockerfile),
|
||||
str(stage),
|
||||
],
|
||||
stdout=subprocess.DEVNULL,
|
||||
stderr=subprocess.DEVNULL,
|
||||
check=False,
|
||||
)
|
||||
return result.returncode == 0
|
||||
finally:
|
||||
subprocess.run(
|
||||
["container", "image", "delete", image],
|
||||
stdout=subprocess.DEVNULL,
|
||||
stderr=subprocess.DEVNULL,
|
||||
check=False,
|
||||
)
|
||||
shutil.rmtree(stage, ignore_errors=True)
|
||||
|
||||
|
||||
@unittest.skipIf(
|
||||
os.environ.get("GITEA_ACTIONS") == "true",
|
||||
"skipped under act_runner: cannot host Apple Container VMs",
|
||||
)
|
||||
@unittest.skipUnless(
|
||||
platform.system() == "Darwin",
|
||||
"Apple Container is macOS-only",
|
||||
)
|
||||
@unittest.skipUnless(
|
||||
_container_available(),
|
||||
"Apple Container not on PATH; install from "
|
||||
"https://github.com/apple/container/releases",
|
||||
)
|
||||
@unittest.skipUnless(
|
||||
_buildkit_dns_available(),
|
||||
"Apple Container BuildKit cannot resolve deb.debian.org on this host",
|
||||
)
|
||||
class TestMacosContainerLaunch(unittest.TestCase):
|
||||
"""Launch once and reuse the bottle across probes."""
|
||||
|
||||
@classmethod
|
||||
def setUpClass(cls) -> None:
|
||||
cls.stage = Path(tempfile.mkdtemp(prefix="cb-macos-container-launch."))
|
||||
cls._launch = None
|
||||
cls.bottle = None
|
||||
dockerfile = cls.stage / "Dockerfile.agent-smoke"
|
||||
_minimal_agent_dockerfile(dockerfile)
|
||||
os.environ["BOT_BOTTLE_BACKEND"] = "macos-container"
|
||||
try:
|
||||
backend = get_bottle_backend()
|
||||
spec = BottleSpec(
|
||||
manifest=_minimal_manifest(dockerfile),
|
||||
agent_name="demo",
|
||||
copy_cwd=False,
|
||||
user_cwd=str(cls.stage),
|
||||
)
|
||||
cls.plan = backend.prepare(spec, stage_dir=cls.stage)
|
||||
cls._launch = backend.launch(cls.plan)
|
||||
cls.bottle = cls._launch.__enter__()
|
||||
except BaseException:
|
||||
if cls._launch is not None:
|
||||
cls._launch.__exit__(None, None, None)
|
||||
shutil.rmtree(cls.stage, ignore_errors=True)
|
||||
os.environ.pop("BOT_BOTTLE_BACKEND", None)
|
||||
raise
|
||||
|
||||
@classmethod
|
||||
def tearDownClass(cls) -> None:
|
||||
try:
|
||||
if cls._launch is not None:
|
||||
cls._launch.__exit__(None, None, None)
|
||||
finally:
|
||||
shutil.rmtree(cls.stage, ignore_errors=True)
|
||||
os.environ.pop("BOT_BOTTLE_BACKEND", None)
|
||||
|
||||
def test_smoke_exec_echo(self):
|
||||
r = self.bottle.exec( # type: ignore[union-attr]
|
||||
"echo hello-from-macos-container"
|
||||
)
|
||||
self.assertEqual(0, r.returncode, msg=r.stderr)
|
||||
self.assertIn("hello-from-macos-container", r.stdout)
|
||||
|
||||
def test_proxy_env_points_at_sidecar_internal_ip(self):
|
||||
r = self.bottle.exec( # type: ignore[union-attr]
|
||||
"printf '%s\n' \"$HTTPS_PROXY\" \"$HTTP_PROXY\" "
|
||||
"\"$NO_PROXY\" \"$NODE_EXTRA_CA_CERTS\""
|
||||
)
|
||||
self.assertEqual(0, r.returncode, msg=r.stderr)
|
||||
values = [line.strip() for line in r.stdout.splitlines()]
|
||||
self.assertEqual(4, len(values), values)
|
||||
self.assertEqual(values[0], values[1], values)
|
||||
self.assertRegex(values[0], r"^http://[0-9.]+:9099$")
|
||||
self.assertNotIn("127.0.0.1", values[0])
|
||||
sidecar_host = values[0].removeprefix("http://").removesuffix(":9099")
|
||||
self.assertIn(sidecar_host, values[2])
|
||||
self.assertEqual(
|
||||
"/usr/local/share/ca-certificates/bot-bottle-mitm-ca.crt",
|
||||
values[3],
|
||||
)
|
||||
|
||||
def test_allowlisted_https_reaches_egress_proxy(self):
|
||||
r = self.bottle.exec( # type: ignore[union-attr]
|
||||
"curl -fsS --max-time 20 https://example.com >/dev/null && echo OK"
|
||||
)
|
||||
self.assertEqual(0, r.returncode, msg=r.stderr + r.stdout)
|
||||
self.assertIn("OK", r.stdout)
|
||||
|
||||
def test_direct_egress_bypass_without_proxy_fails(self):
|
||||
r = self.bottle.exec( # type: ignore[union-attr]
|
||||
"env -u HTTPS_PROXY -u HTTP_PROXY -u https_proxy -u http_proxy "
|
||||
"curl -s --show-error --max-time 5 https://example.com 2>&1 || true"
|
||||
)
|
||||
self.assertTrue(
|
||||
"refused" in r.stdout.lower()
|
||||
or "timed out" in r.stdout.lower()
|
||||
or "unreachable" in r.stdout.lower()
|
||||
or "failed" in r.stdout.lower()
|
||||
or "could not resolve" in r.stdout.lower()
|
||||
or "connection reset" in r.stdout.lower(),
|
||||
f"expected direct egress to fail; got: {r.stdout!r}",
|
||||
)
|
||||
|
||||
def test_non_allowlisted_host_fails_through_proxy(self):
|
||||
r = self.bottle.exec( # type: ignore[union-attr]
|
||||
"curl -s --show-error --max-time 10 https://iana.org 2>&1 || true"
|
||||
)
|
||||
self.assertTrue(
|
||||
"403" in r.stdout
|
||||
or "502" in r.stdout
|
||||
or "blocked" in r.stdout.lower()
|
||||
or "not allowed" in r.stdout.lower()
|
||||
or "not in the bottle's egress.routes allowlist" in r.stdout.lower()
|
||||
or "forbidden" in r.stdout.lower()
|
||||
or "failed" in r.stdout.lower(),
|
||||
f"expected non-allowlisted proxy request to fail; got: {r.stdout!r}",
|
||||
)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,161 @@
|
||||
"""Integration: two bottles share one gateway; source-IP attribution keeps
|
||||
their egress tokens *and* allowlists isolated (PRD 0070 multi-tenancy).
|
||||
|
||||
The whole premise of the consolidation is one shared gateway for every
|
||||
bottle, isolated only by the unspoofable source IP. A single-bottle test
|
||||
can't catch cross-bottle token bleed or an allowlist leak — this brings up
|
||||
the real orchestrator + gateway and drives two bottles through the one
|
||||
gateway to prove each gets exactly its own token and its own routes.
|
||||
|
||||
Gated on a reachable Docker daemon and builds the bundle image, so it runs
|
||||
with the other docker integration tests, not in unit CI. Uses the real
|
||||
fixed gateway/orchestrator names (that's what it's testing), so it can't run
|
||||
concurrently with a live per-host gateway; it points the orchestrator at a
|
||||
throwaway BOT_BOTTLE_ROOT for a clean registry and tears everything down.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import subprocess
|
||||
import tempfile
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
|
||||
from bot_bottle.backend.docker.consolidated_launch import (
|
||||
_network_cidr,
|
||||
_network_container_ips,
|
||||
)
|
||||
from bot_bottle.backend.docker.egress import EGRESS_PORT
|
||||
from bot_bottle.backend.docker.gateway_net import next_free_ip
|
||||
from bot_bottle.orchestrator.client import OrchestratorClient
|
||||
from bot_bottle.orchestrator.gateway import GATEWAY_IMAGE, GATEWAY_NAME, GATEWAY_NETWORK
|
||||
from bot_bottle.orchestrator.lifecycle import OrchestratorService
|
||||
from tests._docker import skip_unless_docker
|
||||
|
||||
# One upstream reachable under two names; reflects the Authorization header so
|
||||
# the probe can see exactly what the gateway injected (or didn't).
|
||||
_ECHO_NAME = "bot-bottle-mtitest-echo"
|
||||
_ECHO_ALIASES = ("echo-shared", "echo-bonly")
|
||||
_ECHO_SRC = (
|
||||
"from http.server import BaseHTTPRequestHandler, HTTPServer\n"
|
||||
"class H(BaseHTTPRequestHandler):\n"
|
||||
" def do_GET(s):\n"
|
||||
" a=s.headers.get('Authorization','NONE'); s.send_response(200); s.end_headers()\n"
|
||||
" s.wfile.write(('AUTH='+a).encode())\n"
|
||||
" def log_message(s,*a): pass\n"
|
||||
"HTTPServer(('0.0.0.0',80),H).serve_forever()\n"
|
||||
)
|
||||
|
||||
# A: echo-shared only, authed. B: echo-shared authed + echo-bonly open.
|
||||
_POLICY_A = (
|
||||
'routes:\n'
|
||||
' - host: echo-shared\n'
|
||||
' auth_scheme: "Bearer"\n'
|
||||
' token_env: "EGRESS_TOKEN_0"\n'
|
||||
)
|
||||
_POLICY_B = _POLICY_A + ' - host: echo-bonly\n'
|
||||
_TOKEN_A = "sk-AAA-alice"
|
||||
_TOKEN_B = "sk-BBB-bob"
|
||||
|
||||
# Client probe: open http://<host>/ through the gateway proxy from a container
|
||||
# pinned to the bottle's source IP, printing "<status> <body>". Uses only the
|
||||
# bundle image's python3 — no dependency on the agent image.
|
||||
_PROBE_SRC = (
|
||||
"import sys,urllib.request,urllib.error\n"
|
||||
"op=urllib.request.build_opener(urllib.request.ProxyHandler({'http':sys.argv[1]}))\n"
|
||||
"try:\n"
|
||||
" r=op.open('http://'+sys.argv[2]+'/',timeout=8)\n"
|
||||
" sys.stdout.write(str(r.status)+' '+r.read().decode())\n"
|
||||
"except urllib.error.HTTPError as e:\n"
|
||||
" sys.stdout.write(str(e.code)+' '+e.read().decode())\n"
|
||||
)
|
||||
|
||||
|
||||
@skip_unless_docker()
|
||||
@unittest.skipIf(
|
||||
os.environ.get("GITEA_ACTIONS") == "true",
|
||||
"skipped under act_runner: the orchestrator container bind-mounts the repo "
|
||||
"path into a container on the socket-shared host daemon, which can't see the "
|
||||
"runner's /workspace — same host-bind-mount constraint as the other "
|
||||
"bottle-bringup integration tests",
|
||||
)
|
||||
class TestMultitenantIsolation(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self._tmp = tempfile.TemporaryDirectory()
|
||||
self.addCleanup(self._tmp.cleanup)
|
||||
# Throwaway root → a clean registry DB, independent of the host's.
|
||||
self.svc = OrchestratorService(host_root=Path(self._tmp.name))
|
||||
self.addCleanup(self._teardown_docker)
|
||||
# ensure_running builds the bundle image (slow on a cold cache) and
|
||||
# brings up the shared network + gateway + orchestrator.
|
||||
url = self.svc.ensure_running(startup_timeout=300)
|
||||
self.client = OrchestratorClient(url)
|
||||
self.gw_ip = self._container_ip(GATEWAY_NAME)
|
||||
self._run_echo()
|
||||
|
||||
def _teardown_docker(self) -> None:
|
||||
subprocess.run(["docker", "rm", "--force", _ECHO_NAME],
|
||||
stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False)
|
||||
self.svc.stop()
|
||||
subprocess.run(["docker", "network", "rm", GATEWAY_NETWORK],
|
||||
stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False)
|
||||
# The orchestrator container wrote the registry DB as root into the
|
||||
# throwaway root; chown it back so the (non-root) tempdir cleanup can
|
||||
# remove it.
|
||||
subprocess.run(
|
||||
["docker", "run", "--rm", "-v", f"{self._tmp.name}:/r",
|
||||
"--entrypoint", "chown", GATEWAY_IMAGE, "-R",
|
||||
f"{os.getuid()}:{os.getgid()}", "/r"],
|
||||
stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False)
|
||||
|
||||
@staticmethod
|
||||
def _container_ip(name: str) -> str:
|
||||
proc = subprocess.run(
|
||||
["docker", "inspect", "-f",
|
||||
'{{(index .NetworkSettings.Networks "' + GATEWAY_NETWORK + '").IPAddress}}', name],
|
||||
stdout=subprocess.PIPE, text=True, check=True,
|
||||
)
|
||||
return proc.stdout.strip()
|
||||
|
||||
def _run_echo(self) -> None:
|
||||
argv = ["docker", "run", "--detach", "--name", _ECHO_NAME,
|
||||
"--network", GATEWAY_NETWORK]
|
||||
for alias in _ECHO_ALIASES:
|
||||
argv += ["--network-alias", alias]
|
||||
argv += ["--entrypoint", "python3", GATEWAY_IMAGE, "-c", _ECHO_SRC]
|
||||
proc = subprocess.run(argv, stdout=subprocess.PIPE, stderr=subprocess.PIPE,
|
||||
text=True, check=False)
|
||||
self.assertEqual(0, proc.returncode, f"echo upstream failed: {proc.stderr}")
|
||||
|
||||
def _free_ip(self, extra_taken: list[str]) -> str:
|
||||
taken = _network_container_ips(GATEWAY_NETWORK) + extra_taken
|
||||
return next_free_ip(_network_cidr(GATEWAY_NETWORK), taken)
|
||||
|
||||
def _probe(self, source_ip: str, host: str) -> str:
|
||||
proc = subprocess.run(
|
||||
["docker", "run", "--rm", "--network", GATEWAY_NETWORK, "--ip", source_ip,
|
||||
"--entrypoint", "python3", GATEWAY_IMAGE, "-c", _PROBE_SRC,
|
||||
f"http://{self.gw_ip}:{EGRESS_PORT}", host],
|
||||
stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True, check=False, timeout=90,
|
||||
)
|
||||
return proc.stdout.strip()
|
||||
|
||||
def test_two_bottles_share_gateway_with_isolated_tokens_and_allowlists(self) -> None:
|
||||
ip_a = self._free_ip([])
|
||||
ip_b = self._free_ip([ip_a])
|
||||
self.client.register_bottle(ip_a, policy=_POLICY_A, tokens={"EGRESS_TOKEN_0": _TOKEN_A})
|
||||
self.client.register_bottle(ip_b, policy=_POLICY_B, tokens={"EGRESS_TOKEN_0": _TOKEN_B})
|
||||
|
||||
# Each bottle gets its OWN token injected on the shared route — no bleed.
|
||||
self.assertEqual(f"200 AUTH=Bearer {_TOKEN_A}", self._probe(ip_a, "echo-shared"))
|
||||
self.assertEqual(f"200 AUTH=Bearer {_TOKEN_B}", self._probe(ip_b, "echo-shared"))
|
||||
|
||||
# Allowlist is per-bottle: echo-bonly is only in B's policy.
|
||||
self.assertTrue(self._probe(ip_a, "echo-bonly").startswith("403"), # fail-closed for A
|
||||
"A reached a host outside its allowlist")
|
||||
self.assertEqual("200 AUTH=NONE", self._probe(ip_b, "echo-bonly")) # allowed, unauthed for B
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
+6
-6
@@ -1,7 +1,7 @@
|
||||
"""Integration: the consolidated Docker sidecar is an idempotent singleton.
|
||||
"""Integration: the consolidated Docker gateway is an idempotent singleton.
|
||||
|
||||
Gated on a reachable Docker daemon. Uses a unique name so it never
|
||||
collides with a real per-host sidecar or a leftover from another run.
|
||||
collides with a real per-host gateway or a leftover from another run.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
@@ -10,17 +10,17 @@ import secrets
|
||||
import subprocess
|
||||
import unittest
|
||||
|
||||
from bot_bottle.orchestrator.sidecar import DockerSidecar
|
||||
from bot_bottle.orchestrator.gateway import DockerGateway
|
||||
from tests._docker import skip_unless_docker
|
||||
|
||||
IMAGE = "busybox"
|
||||
|
||||
|
||||
@skip_unless_docker()
|
||||
class TestDockerSidecarIntegration(unittest.TestCase):
|
||||
class TestDockerGatewayIntegration(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self.name = "bot-bottle-orch-sidecar-itest-" + secrets.token_hex(4)
|
||||
self.sc = DockerSidecar(IMAGE, name=self.name)
|
||||
self.name = "bot-bottle-orch-gateway-itest-" + secrets.token_hex(4)
|
||||
self.sc = DockerGateway(IMAGE, name=self.name)
|
||||
self.addCleanup(self.sc.stop)
|
||||
|
||||
def _count(self) -> int:
|
||||
@@ -0,0 +1,36 @@
|
||||
"""Integration: DockerGateway.image_exists reflects real docker state.
|
||||
|
||||
Gated on a reachable Docker daemon. Deliberately does NOT build the full
|
||||
gateway (a heavy, slow image build) — it exercises the `image_exists`
|
||||
primitive that `ensure_built` gates on, against a tiny pulled image and a
|
||||
name that can't exist.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import subprocess
|
||||
import unittest
|
||||
|
||||
from bot_bottle.orchestrator.gateway import DockerGateway
|
||||
from tests._docker import skip_unless_docker
|
||||
|
||||
IMAGE = "busybox"
|
||||
|
||||
|
||||
@skip_unless_docker()
|
||||
class TestDockerGatewayImageExists(unittest.TestCase):
|
||||
def test_image_exists_true_for_present_false_for_absent(self) -> None:
|
||||
# Ensure the tiny image is present (build_if_missing is disabled here
|
||||
# so this never triggers a Dockerfile.gateway build).
|
||||
subprocess.run(
|
||||
["docker", "pull", IMAGE],
|
||||
stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False,
|
||||
)
|
||||
self.assertTrue(DockerGateway(IMAGE, dockerfile=None).image_exists())
|
||||
self.assertFalse(
|
||||
DockerGateway("bot-bottle-nonexistent:doesnotexist", dockerfile=None).image_exists()
|
||||
)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -6,7 +6,7 @@ resources.
|
||||
|
||||
The PipelockProxy.stop idempotency case that used to live here was
|
||||
removed in PRD 0024 chunk 3 when the per-container .stop method
|
||||
went away — sidecar teardown is now compose's responsibility, and
|
||||
went away — gateway teardown is now compose's responsibility, and
|
||||
`compose down` already no-ops on missing containers."""
|
||||
|
||||
import os
|
||||
|
||||
@@ -72,7 +72,7 @@ _DUMMY_HOST_KEY = (
|
||||
os.environ.get("GITEA_ACTIONS") == "true",
|
||||
"skipped under act_runner: egress_tls_init uses a host bind mount "
|
||||
"the runner container can't see, and the network topology hides "
|
||||
"sibling-sidecar visibility — same constraint as the other "
|
||||
"sibling-gateway visibility — same constraint as the other "
|
||||
"bottle-bringup integration tests",
|
||||
)
|
||||
class TestSandboxEscape(unittest.TestCase):
|
||||
@@ -90,8 +90,8 @@ class TestSandboxEscape(unittest.TestCase):
|
||||
|
||||
@classmethod
|
||||
def setUpClass(cls) -> None:
|
||||
# Docker is always required (the agent + sidecars run under it,
|
||||
# and VM backends still use it for the sidecar bundle); the
|
||||
# Docker is always required (the agent + companion containers run under it,
|
||||
# and VM backends still use it for the gateway); the
|
||||
# class-level @skip_unless_docker already covers that. Pin
|
||||
# Docker when BOT_BOTTLE_BACKEND is unset to preserve the
|
||||
# Docker-backed CI path.
|
||||
@@ -121,7 +121,7 @@ class TestSandboxEscape(unittest.TestCase):
|
||||
"egress": {
|
||||
"routes": [{"host": "api.anthropic.com"}],
|
||||
},
|
||||
# git-gate sidecar so attack 5 can push. Upstream
|
||||
# git-gate daemon so attack 5 can push. Upstream
|
||||
# is intentionally unreachable — the pre-receive
|
||||
# gitleaks hook must reject BEFORE git-gate
|
||||
# attempts the upstream push. A preset `host_key`
|
||||
@@ -275,7 +275,7 @@ class TestSandboxEscape(unittest.TestCase):
|
||||
|
||||
def _assert_sandbox_block(self, label: str, r: object) -> None: # type: ignore
|
||||
"""A real sandbox block produces an HTTP 403 with a
|
||||
recognizable sandbox sidecar marker in the body. ANY
|
||||
recognizable sandbox gateway marker in the body. ANY
|
||||
other outcome (200 from upstream, 401/404 from upstream,
|
||||
non-marker 5xx) means the request escaped — the secret
|
||||
reached the network."""
|
||||
|
||||
@@ -1,106 +0,0 @@
|
||||
"""Integration: end-to-end smoke for the PRD 0024 bundle shape.
|
||||
|
||||
Verifies that flipping `BOT_BOTTLE_SIDECAR_BUNDLE=1` produces a
|
||||
working bottle: `docker compose up` brings the agent + bundle pair
|
||||
online, the daemons inside the bundle bind their ports, and the
|
||||
agent can reach egress + supervise via the bundle's network
|
||||
aliases (no agent-side config changes between flag positions).
|
||||
|
||||
Skipped under GITEA_ACTIONS — the bundle image is a multi-stage
|
||||
build pulling 200+MB of base layers, and the bind-mounts won't
|
||||
share filesystem with the runner container. Same constraint as
|
||||
the chunk-1 image-probe test.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import shutil
|
||||
import tempfile
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
from unittest.mock import patch
|
||||
|
||||
from bot_bottle.backend import BottleSpec, get_bottle_backend
|
||||
from bot_bottle.manifest import ManifestIndex
|
||||
from tests._docker import skip_unless_docker
|
||||
|
||||
|
||||
def _manifest() -> ManifestIndex:
|
||||
"""Bottle with supervise on so the bundle exercises egress +
|
||||
supervise. Git is off because a meaningful git-gate test needs
|
||||
a real upstream and SSH keys — out of scope for a bundle smoke."""
|
||||
return ManifestIndex.from_json_obj({
|
||||
"bottles": {
|
||||
"dev": {
|
||||
"supervise": True,
|
||||
},
|
||||
},
|
||||
"agents": {
|
||||
"demo": {"skills": [], "prompt": "", "bottle": "dev"},
|
||||
},
|
||||
})
|
||||
|
||||
|
||||
@skip_unless_docker()
|
||||
@unittest.skipIf(
|
||||
os.environ.get("GITEA_ACTIONS") == "true",
|
||||
"skipped under act_runner: multi-stage bundle build pulls 200+MB "
|
||||
"of base layers and bind-mounts don't share fs with the runner",
|
||||
)
|
||||
class TestSidecarBundleCompose(unittest.TestCase):
|
||||
"""One end-to-end pass with the bundle flag on. Skipping under
|
||||
act_runner; the local docker daemon does the work."""
|
||||
|
||||
def test_bottle_up_with_bundle_flag_on(self):
|
||||
stage_dir = Path(tempfile.mkdtemp(prefix="cb-bundle-smoke."))
|
||||
try:
|
||||
with patch.dict(os.environ, {"BOT_BOTTLE_SIDECAR_BUNDLE": "1"}):
|
||||
backend = get_bottle_backend("docker")
|
||||
spec = BottleSpec(
|
||||
manifest=_manifest(),
|
||||
agent_name="demo",
|
||||
copy_cwd=False,
|
||||
user_cwd=str(stage_dir),
|
||||
)
|
||||
plan = backend.prepare(spec, stage_dir=stage_dir)
|
||||
with backend.launch(plan) as bottle:
|
||||
# The agent's HTTPS_PROXY URL (resolved at
|
||||
# renderer-time) should reach egress inside
|
||||
# the bundle. A bare CONNECT with no upstream
|
||||
# URL gets rejected with 400 or 405 but proves
|
||||
# the listener is alive at the alias.
|
||||
probe = bottle.exec(
|
||||
"set -eu\n"
|
||||
"echo HTTPS_PROXY=$HTTPS_PROXY\n"
|
||||
"PORT=$(echo \"$HTTPS_PROXY\" | sed -E 's|.*:([0-9]+).*|\\1|')\n"
|
||||
"HOST=$(echo \"$HTTPS_PROXY\" | sed -E 's|http://([^:]+):.*|\\1|')\n"
|
||||
"echo HOST=$HOST PORT=$PORT\n"
|
||||
"curl -sS --max-time 5 -o /dev/null -w 'http=%{http_code}\\n' "
|
||||
" \"http://$HOST:$PORT/\" || true\n"
|
||||
)
|
||||
# The supervise URL resolves to the same bundle
|
||||
# via its supervise alias, on a different port.
|
||||
supervise_probe = bottle.exec(
|
||||
"set -eu\n"
|
||||
"curl -sS --max-time 5 -o /dev/null "
|
||||
" -w 'http=%{http_code}\\n' "
|
||||
" \"http://supervise:9100/health\" || true\n"
|
||||
)
|
||||
finally:
|
||||
shutil.rmtree(stage_dir, ignore_errors=True)
|
||||
|
||||
self.assertEqual(0, probe.returncode, msg=probe.stderr)
|
||||
# egress answered SOMETHING — any 4xx is fine, just proves
|
||||
# the egress daemon is listening at the proxy address.
|
||||
self.assertIn("http=", probe.stdout,
|
||||
f"no HTTP response from egress: {probe.stdout!r}")
|
||||
# supervise's /health endpoint exists (PRD 0013); it should
|
||||
# answer 200 or similar — anything non-empty proves the
|
||||
# third daemon's alias resolves to the same bundle.
|
||||
self.assertEqual(0, supervise_probe.returncode, msg=supervise_probe.stderr)
|
||||
self.assertIn("http=", supervise_probe.stdout)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -5,7 +5,7 @@ no test ever reads or writes the real ``~/.bot-bottle`` (state, queue,
|
||||
and audit dirs all derive from ``paths.bot_bottle_root()`` →
|
||||
``Path.home()``). Without this, a test that takes a ``flock`` on the
|
||||
real audit log can **block indefinitely** when a live bottle's supervise
|
||||
sidecar holds that lock — observed as a hung ``coverage run`` at 0% CPU —
|
||||
gateway holds that lock — observed as a hung ``coverage run`` at 0% CPU —
|
||||
and unisolated tests otherwise pollute the developer's home dir.
|
||||
|
||||
Individual tests that need their own ``HOME`` still override
|
||||
|
||||
@@ -0,0 +1,160 @@
|
||||
"""Shared in-memory `DockerBottlePlan` fixture for docker-backend tests.
|
||||
|
||||
A fully-resolved plan with toggles for the conditional-service matrix
|
||||
(git-gate / egress / supervise / canary). Consumed by the consolidated
|
||||
compose tests; kept here (rather than in a test module) so it survives
|
||||
independent of any one test file.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from pathlib import Path
|
||||
|
||||
from bot_bottle.agent_provider import AgentProvisionPlan
|
||||
from bot_bottle.backend import BottleSpec
|
||||
from bot_bottle.backend.docker.bottle_plan import DockerBottlePlan
|
||||
from bot_bottle.egress import EgressPlan, EgressRoute
|
||||
from bot_bottle.git_gate import GitGatePlan, GitGateUpstream
|
||||
from bot_bottle.manifest import ManifestIndex
|
||||
from bot_bottle.supervise import SupervisePlan
|
||||
|
||||
|
||||
SLUG = "demo-abc12"
|
||||
STAGE = Path("/tmp/cb-stage")
|
||||
STATE = Path("/tmp/cb-state")
|
||||
|
||||
# Exported to consumers (e.g. test_consolidated_compose); named with a
|
||||
# leading underscore for the historical fixture convention.
|
||||
__all__ = ["_plan"]
|
||||
|
||||
|
||||
def _manifest(*, supervise: bool, with_git: bool, with_egress: bool) -> ManifestIndex:
|
||||
"""Minimal manifest with the toggles the matrix needs. The renderer
|
||||
only reads from the plan, not the manifest, so this is just here to
|
||||
back BottleSpec."""
|
||||
bottle: dict[str, object] = {}
|
||||
if supervise:
|
||||
bottle["supervise"] = True
|
||||
if with_git:
|
||||
bottle["git-gate"] = {"repos": {
|
||||
"upstream": {
|
||||
"url": "ssh://git@example.com:22/x/y.git",
|
||||
"key": {"provider": "static", "path": "/etc/hostname"},
|
||||
},
|
||||
}}
|
||||
if with_egress:
|
||||
bottle["egress"] = {
|
||||
"routes": [{
|
||||
"host": "api.example",
|
||||
"auth": {"scheme": "Bearer", "token_ref": "TOK"},
|
||||
}],
|
||||
}
|
||||
return ManifestIndex.from_json_obj({
|
||||
"bottles": {"dev": bottle},
|
||||
"agents": {"demo": {"skills": [], "prompt": "", "bottle": "dev"}},
|
||||
})
|
||||
|
||||
|
||||
def _git_gate_plan(upstreams: tuple[GitGateUpstream, ...] = ()) -> GitGatePlan:
|
||||
return GitGatePlan(
|
||||
slug=SLUG,
|
||||
entrypoint_script=STATE / "git-gate" / "entrypoint.sh",
|
||||
hook_script=STATE / "git-gate" / "pre-receive",
|
||||
access_hook_script=STATE / "git-gate" / "access-hook",
|
||||
upstreams=upstreams,
|
||||
internal_network=f"bot-bottle-net-{SLUG}",
|
||||
egress_network=f"bot-bottle-egress-{SLUG}",
|
||||
)
|
||||
|
||||
|
||||
def _egress_plan(
|
||||
routes: tuple[EgressRoute, ...] = (),
|
||||
*,
|
||||
canary: bool = False,
|
||||
) -> EgressPlan:
|
||||
token_env_map = {
|
||||
r.token_env: r.token_ref
|
||||
for r in routes
|
||||
if r.token_env
|
||||
}
|
||||
return EgressPlan(
|
||||
slug=SLUG,
|
||||
routes_path=STATE / "egress" / "routes.yaml",
|
||||
routes=routes,
|
||||
token_env_map=token_env_map,
|
||||
internal_network=f"bot-bottle-net-{SLUG}",
|
||||
egress_network=f"bot-bottle-egress-{SLUG}",
|
||||
mitmproxy_ca_host_path=STATE / "egress-ca" / "mitmproxy-ca.pem",
|
||||
mitmproxy_ca_cert_only_host_path=STATE / "egress-ca" / "ca.pem",
|
||||
canary="fake-canary-value" if canary else "",
|
||||
canary_env="CANON_ALPHA_SECRET" if canary else "",
|
||||
)
|
||||
|
||||
|
||||
def _supervise_plan() -> SupervisePlan:
|
||||
return SupervisePlan(
|
||||
slug=SLUG,
|
||||
db_path=STATE / "bot-bottle.db",
|
||||
internal_network=f"bot-bottle-net-{SLUG}",
|
||||
)
|
||||
|
||||
|
||||
def _plan(
|
||||
*,
|
||||
with_git: bool = False,
|
||||
with_egress: bool = False,
|
||||
supervise: bool = False,
|
||||
canary: bool = False,
|
||||
) -> DockerBottlePlan:
|
||||
"""Build a fully-resolved DockerBottlePlan. Toggles cover the
|
||||
matrix the renderer's conditional-service logic branches on."""
|
||||
upstreams: tuple[GitGateUpstream, ...] = ()
|
||||
if with_git:
|
||||
upstreams = (GitGateUpstream(
|
||||
name="upstream",
|
||||
upstream_url="ssh://git@example.com:22/x/y.git",
|
||||
upstream_host="example.com",
|
||||
upstream_port="22",
|
||||
identity_file="/etc/hostname",
|
||||
known_host_key="",
|
||||
known_hosts_file=STATE / "git-gate" / "upstream-known_hosts",
|
||||
),)
|
||||
routes: tuple[EgressRoute, ...] = ()
|
||||
if with_egress:
|
||||
routes = (EgressRoute(
|
||||
host="api.example",
|
||||
auth_scheme="Bearer",
|
||||
token_env="EGRESS_TOKEN_0",
|
||||
token_ref="TOK",
|
||||
roles=(),
|
||||
),)
|
||||
|
||||
index = _manifest(supervise=supervise, with_git=with_git, with_egress=with_egress)
|
||||
spec = BottleSpec(
|
||||
manifest=index,
|
||||
agent_name="demo",
|
||||
copy_cwd=False,
|
||||
user_cwd="/tmp/x",
|
||||
)
|
||||
return DockerBottlePlan(
|
||||
spec=spec,
|
||||
manifest=index.load_for_agent("demo"),
|
||||
stage_dir=STAGE,
|
||||
slug=SLUG,
|
||||
forwarded_env={"CLAUDE_CODE_OAUTH_TOKEN": "x"},
|
||||
git_gate_plan=_git_gate_plan(upstreams),
|
||||
egress_plan=_egress_plan(routes, canary=canary),
|
||||
supervise_plan=_supervise_plan() if supervise else None,
|
||||
use_runsc=False,
|
||||
agent_provision=AgentProvisionPlan(
|
||||
template="claude",
|
||||
command="claude",
|
||||
prompt_mode="append_file",
|
||||
image="bot-bottle-claude:latest",
|
||||
dockerfile="",
|
||||
guest_home="/home/node",
|
||||
instance_name=f"bot-bottle-{SLUG}",
|
||||
prompt_file=STAGE / "prompt",
|
||||
guest_env={},
|
||||
),
|
||||
)
|
||||
+4
-415
@@ -1,434 +1,23 @@
|
||||
"""Unit: compose-spec renderer (PRD 0018 chunk 1).
|
||||
"""Unit: docker compose lifecycle helpers (PRD 0018).
|
||||
|
||||
Pure-function tests for `bottle_plan_to_compose`. Fixtures build a
|
||||
fully-resolved DockerBottlePlan in memory; the renderer just
|
||||
translates it to the compose dict. Conditional-service matrix is
|
||||
covered via parameterized cases (git on/off × egress on/off ×
|
||||
supervise on/off).
|
||||
The compose *spec* is built by `consolidated_compose.py`; these
|
||||
tests cover the I/O-side helpers in `compose.py` — the slug ↔
|
||||
project mapping and `docker compose ls` enumeration.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import subprocess
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
from unittest import mock
|
||||
|
||||
from bot_bottle.agent_provider import AgentProvisionPlan
|
||||
from bot_bottle.backend import BottleSpec
|
||||
from bot_bottle.backend.docker.bottle_plan import DockerBottlePlan
|
||||
from bot_bottle.backend.docker.compose import (
|
||||
COMPOSE_PROJECT_PREFIX,
|
||||
bottle_plan_to_compose,
|
||||
compose_project_name,
|
||||
list_active_slugs,
|
||||
list_compose_projects,
|
||||
slug_from_compose_project,
|
||||
)
|
||||
from bot_bottle.egress import (
|
||||
EgressPlan,
|
||||
EgressRoute,
|
||||
)
|
||||
from bot_bottle.git_gate import GitGatePlan, GitGateUpstream
|
||||
from bot_bottle.manifest import ManifestIndex
|
||||
from bot_bottle.supervise import SupervisePlan
|
||||
|
||||
|
||||
SLUG = "demo-abc12"
|
||||
STAGE = Path("/tmp/cb-stage")
|
||||
STATE = Path("/tmp/cb-state")
|
||||
|
||||
|
||||
def _manifest(*, supervise: bool, with_git: bool, with_egress: bool) -> ManifestIndex:
|
||||
"""Minimal manifest with the toggles the chunk-1 matrix needs.
|
||||
The renderer only reads from the plan, not the manifest, so this
|
||||
is just here to back BottleSpec."""
|
||||
bottle: dict[str, object] = {}
|
||||
if supervise:
|
||||
bottle["supervise"] = True
|
||||
if with_git:
|
||||
bottle["git-gate"] = {"repos": {
|
||||
"upstream": {
|
||||
"url": "ssh://git@example.com:22/x/y.git",
|
||||
"key": {"provider": "static", "path": "/etc/hostname"},
|
||||
},
|
||||
}}
|
||||
if with_egress:
|
||||
bottle["egress"] = {
|
||||
"routes": [{
|
||||
"host": "api.example",
|
||||
"auth": {"scheme": "Bearer", "token_ref": "TOK"},
|
||||
}],
|
||||
}
|
||||
return ManifestIndex.from_json_obj({
|
||||
"bottles": {"dev": bottle},
|
||||
"agents": {"demo": {"skills": [], "prompt": "", "bottle": "dev"}},
|
||||
})
|
||||
|
||||
|
||||
|
||||
def _git_gate_plan(upstreams: tuple[GitGateUpstream, ...] = ()) -> GitGatePlan:
|
||||
return GitGatePlan(
|
||||
slug=SLUG,
|
||||
entrypoint_script=STATE / "git-gate" / "entrypoint.sh",
|
||||
hook_script=STATE / "git-gate" / "pre-receive",
|
||||
access_hook_script=STATE / "git-gate" / "access-hook",
|
||||
upstreams=upstreams,
|
||||
internal_network=f"bot-bottle-net-{SLUG}",
|
||||
egress_network=f"bot-bottle-egress-{SLUG}",
|
||||
)
|
||||
|
||||
|
||||
def _egress_plan(
|
||||
routes: tuple[EgressRoute, ...] = (),
|
||||
*,
|
||||
canary: bool = False,
|
||||
) -> EgressPlan:
|
||||
token_env_map = {
|
||||
r.token_env: r.token_ref
|
||||
for r in routes
|
||||
if r.token_env
|
||||
}
|
||||
return EgressPlan(
|
||||
slug=SLUG,
|
||||
routes_path=STATE / "egress" / "routes.yaml",
|
||||
routes=routes,
|
||||
token_env_map=token_env_map,
|
||||
internal_network=f"bot-bottle-net-{SLUG}",
|
||||
egress_network=f"bot-bottle-egress-{SLUG}",
|
||||
mitmproxy_ca_host_path=STATE / "egress-ca" / "mitmproxy-ca.pem",
|
||||
mitmproxy_ca_cert_only_host_path=STATE / "egress-ca" / "ca.pem",
|
||||
canary="fake-canary-value" if canary else "",
|
||||
canary_env="CANON_ALPHA_SECRET" if canary else "",
|
||||
)
|
||||
|
||||
|
||||
def _supervise_plan() -> SupervisePlan:
|
||||
return SupervisePlan(
|
||||
slug=SLUG,
|
||||
db_path=STATE / "bot-bottle.db",
|
||||
internal_network=f"bot-bottle-net-{SLUG}",
|
||||
)
|
||||
|
||||
|
||||
def _plan(
|
||||
*,
|
||||
with_git: bool = False,
|
||||
with_egress: bool = False,
|
||||
supervise: bool = False,
|
||||
canary: bool = False,
|
||||
) -> DockerBottlePlan:
|
||||
"""Build a fully-resolved DockerBottlePlan. Toggles cover the
|
||||
matrix the renderer's conditional-service logic branches on."""
|
||||
upstreams: tuple[GitGateUpstream, ...] = ()
|
||||
if with_git:
|
||||
upstreams = (GitGateUpstream(
|
||||
name="upstream",
|
||||
upstream_url="ssh://git@example.com:22/x/y.git",
|
||||
upstream_host="example.com",
|
||||
upstream_port="22",
|
||||
identity_file="/etc/hostname",
|
||||
known_host_key="",
|
||||
known_hosts_file=STATE / "git-gate" / "upstream-known_hosts",
|
||||
),)
|
||||
routes: tuple[EgressRoute, ...] = ()
|
||||
if with_egress:
|
||||
routes = (EgressRoute(
|
||||
host="api.example",
|
||||
auth_scheme="Bearer",
|
||||
token_env="EGRESS_TOKEN_0",
|
||||
token_ref="TOK",
|
||||
roles=(),
|
||||
),)
|
||||
|
||||
index = _manifest(supervise=supervise, with_git=with_git, with_egress=with_egress)
|
||||
spec = BottleSpec(
|
||||
manifest=index,
|
||||
agent_name="demo",
|
||||
copy_cwd=False,
|
||||
user_cwd="/tmp/x",
|
||||
)
|
||||
return DockerBottlePlan(
|
||||
spec=spec,
|
||||
manifest=index.load_for_agent("demo"),
|
||||
stage_dir=STAGE,
|
||||
slug=SLUG,
|
||||
forwarded_env={"CLAUDE_CODE_OAUTH_TOKEN": "x"},
|
||||
git_gate_plan=_git_gate_plan(upstreams),
|
||||
egress_plan=_egress_plan(routes, canary=canary),
|
||||
supervise_plan=_supervise_plan() if supervise else None,
|
||||
use_runsc=False,
|
||||
agent_provision=AgentProvisionPlan(
|
||||
template="claude",
|
||||
command="claude",
|
||||
prompt_mode="append_file",
|
||||
image="bot-bottle-claude:latest",
|
||||
dockerfile="",
|
||||
guest_home="/home/node",
|
||||
instance_name=f"bot-bottle-{SLUG}",
|
||||
prompt_file=STAGE / "prompt",
|
||||
guest_env={},
|
||||
),
|
||||
)
|
||||
|
||||
|
||||
class TestProjectAndNetworks(unittest.TestCase):
|
||||
def test_project_name(self):
|
||||
spec = bottle_plan_to_compose(_plan())
|
||||
self.assertEqual(f"bot-bottle-{SLUG}", spec["name"])
|
||||
|
||||
def test_internal_network_is_internal(self):
|
||||
spec = bottle_plan_to_compose(_plan())
|
||||
net = spec["networks"]["internal"]
|
||||
self.assertEqual(f"bot-bottle-net-{SLUG}", net["name"])
|
||||
self.assertTrue(net["internal"])
|
||||
|
||||
def test_egress_network_is_external_bridge(self):
|
||||
spec = bottle_plan_to_compose(_plan())
|
||||
net = spec["networks"]["egress"]
|
||||
self.assertEqual(f"bot-bottle-egress-{SLUG}", net["name"])
|
||||
# No `internal:` key on the egress network — defaults to a
|
||||
# normal user-defined bridge.
|
||||
self.assertNotIn("internal", net)
|
||||
|
||||
|
||||
class TestAgentAlwaysPresent(unittest.TestCase):
|
||||
def test_agent_in_services(self):
|
||||
s = bottle_plan_to_compose(_plan())["services"]
|
||||
self.assertIn("agent", s)
|
||||
|
||||
def test_agent_command(self):
|
||||
s = bottle_plan_to_compose(_plan())["services"]["agent"]
|
||||
self.assertEqual(["sleep", "infinity"], s["command"])
|
||||
|
||||
def test_agent_image_uses_runtime_image(self):
|
||||
plan = _plan()
|
||||
s = bottle_plan_to_compose(plan)["services"]["agent"]
|
||||
self.assertEqual(plan.image, s["image"])
|
||||
|
||||
def test_agent_only_on_internal_network(self):
|
||||
s = bottle_plan_to_compose(_plan())["services"]["agent"]
|
||||
self.assertEqual({"internal"}, set(s["networks"].keys()))
|
||||
|
||||
def test_agent_proxy_always_via_egress(self):
|
||||
for with_egress in (False, True):
|
||||
with self.subTest(with_egress=with_egress):
|
||||
s = bottle_plan_to_compose(
|
||||
_plan(with_egress=with_egress)
|
||||
)["services"]["agent"]
|
||||
proxy_lines = [e for e in s["environment"] if e.startswith("HTTPS_PROXY=")]
|
||||
self.assertEqual(1, len(proxy_lines))
|
||||
self.assertEqual("HTTPS_PROXY=http://egress:9099", proxy_lines[0])
|
||||
|
||||
def test_agent_proxy_via_egress_when_egress_present(self):
|
||||
s = bottle_plan_to_compose(_plan(with_egress=True))["services"]["agent"]
|
||||
proxy = [e for e in s["environment"] if e.startswith("HTTPS_PROXY=")][0]
|
||||
self.assertEqual("HTTPS_PROXY=http://egress:9099", proxy)
|
||||
|
||||
def test_agent_no_proxy_adds_supervise_when_enabled(self):
|
||||
s = bottle_plan_to_compose(
|
||||
_plan(supervise=True)
|
||||
)["services"]["agent"]
|
||||
no_proxy = [e for e in s["environment"] if e.startswith("NO_PROXY=")][0]
|
||||
self.assertIn("supervise", no_proxy)
|
||||
|
||||
def test_agent_forwarded_env_uses_bare_names(self):
|
||||
# Bare NAME → compose inherits value from the up-process env,
|
||||
# so secret token values stay out of the file.
|
||||
s = bottle_plan_to_compose(_plan())["services"]["agent"]
|
||||
self.assertIn("CLAUDE_CODE_OAUTH_TOKEN", s["environment"])
|
||||
|
||||
def test_agent_provider_env_uses_literal_values(self):
|
||||
plan = _plan()
|
||||
provision = AgentProvisionPlan(
|
||||
template="codex",
|
||||
command="codex",
|
||||
prompt_mode="read_prompt_file",
|
||||
image="bot-bottle-codex:latest",
|
||||
dockerfile="",
|
||||
guest_home="/home/node",
|
||||
instance_name=f"bot-bottle-{SLUG}",
|
||||
prompt_file=STAGE / "prompt",
|
||||
guest_env={"CODEX_HOME": "/home/node/.codex"},
|
||||
)
|
||||
plan = type(plan)(**{**vars(plan), "agent_provision": provision}) # type: ignore
|
||||
s = bottle_plan_to_compose(plan)["services"]["agent"]
|
||||
self.assertIn("CODEX_HOME=/home/node/.codex", s["environment"])
|
||||
|
||||
def test_agent_runsc_runtime(self):
|
||||
plan = _plan()
|
||||
plan = type(plan)(**{**vars(plan), "use_runsc": True}) # type: ignore
|
||||
s = bottle_plan_to_compose(plan)["services"]["agent"]
|
||||
self.assertEqual("runsc", s["runtime"])
|
||||
|
||||
def test_agent_depends_only_on_sidecars(self):
|
||||
# Bundle shape: the init supervisor owns intra-bundle daemon
|
||||
# ordering, so the agent waits on the bundle container alone.
|
||||
for kwargs in [{}, {"with_git": True, "with_egress": True, "supervise": True}]:
|
||||
with self.subTest(**kwargs):
|
||||
s = bottle_plan_to_compose(_plan(**kwargs))["services"]["agent"]
|
||||
self.assertEqual(["sidecars"], s["depends_on"])
|
||||
|
||||
def test_agent_has_no_current_config_mount_with_supervise(self):
|
||||
with_sv = bottle_plan_to_compose(_plan(supervise=True))["services"]["agent"]
|
||||
self.assertNotIn("volumes", with_sv)
|
||||
without_sv = bottle_plan_to_compose(_plan(supervise=False))["services"]["agent"]
|
||||
self.assertNotIn("volumes", without_sv)
|
||||
|
||||
|
||||
class TestSidecarBundleShape(unittest.TestCase):
|
||||
"""The compose renderer emits exactly one `sidecars` service in
|
||||
place of the daemons it owns (egress + git-gate + supervise).
|
||||
PRD 0024 chunk 5 dropped the legacy four-sidecar shape entirely,
|
||||
so the bundle is the only thing exercised here."""
|
||||
|
||||
def _render(self, **plan_kwargs: object) -> Any: # type: ignore
|
||||
return bottle_plan_to_compose(_plan(**plan_kwargs)) # type: ignore
|
||||
|
||||
def test_emits_two_services_minimal(self):
|
||||
spec = self._render()
|
||||
self.assertEqual({"sidecars", "agent"}, set(spec["services"].keys()))
|
||||
|
||||
def test_emits_two_services_full_matrix(self):
|
||||
spec = self._render(with_git=True, with_egress=True, supervise=True)
|
||||
# Still two services — the bundle absorbs git-gate/egress/supervise.
|
||||
self.assertEqual({"sidecars", "agent"}, set(spec["services"].keys()))
|
||||
|
||||
def test_bundle_uses_bundle_image_and_dockerfile(self):
|
||||
sc = self._render()["services"]["sidecars"]
|
||||
self.assertEqual("bot-bottle-sidecars:latest", sc["image"])
|
||||
self.assertEqual("Dockerfile.sidecars", sc["build"]["dockerfile"])
|
||||
|
||||
def test_bundle_container_name_uses_sidecars_prefix(self):
|
||||
sc = self._render()["services"]["sidecars"]
|
||||
self.assertEqual(f"bot-bottle-sidecars-{SLUG}", sc["container_name"])
|
||||
|
||||
def test_bundle_joins_both_networks(self):
|
||||
sc = self._render()["services"]["sidecars"]
|
||||
self.assertEqual({"internal", "egress"}, set(sc["networks"].keys()))
|
||||
|
||||
def test_internal_aliases_include_egress_shortname(self):
|
||||
sc = self._render()["services"]["sidecars"]
|
||||
aliases = set(sc["networks"]["internal"]["aliases"])
|
||||
self.assertIn("egress", aliases)
|
||||
|
||||
def test_internal_aliases_omit_inactive_sidecars(self):
|
||||
# With no git-gate / supervise, those names are NOT aliased
|
||||
# — keeps the alias list honest about what's actually
|
||||
# listening inside the bundle.
|
||||
sc = self._render()["services"]["sidecars"]
|
||||
aliases = set(sc["networks"]["internal"]["aliases"])
|
||||
self.assertNotIn("git-gate", aliases)
|
||||
self.assertNotIn("supervise", aliases)
|
||||
|
||||
def test_internal_aliases_include_active_sidecars(self):
|
||||
sc = self._render(with_git=True, supervise=True)["services"]["sidecars"]
|
||||
aliases = set(sc["networks"]["internal"]["aliases"])
|
||||
self.assertIn("git-gate", aliases)
|
||||
self.assertIn("supervise", aliases)
|
||||
|
||||
def test_daemons_csv_lists_only_active(self):
|
||||
sc = self._render()["services"]["sidecars"]
|
||||
daemons = {
|
||||
line.split("=", 1)[1]
|
||||
for line in sc["environment"]
|
||||
if line.startswith("BOT_BOTTLE_SIDECAR_DAEMONS=")
|
||||
}
|
||||
self.assertEqual({"egress"}, daemons)
|
||||
|
||||
def test_daemons_csv_expands_with_optional_sidecars(self):
|
||||
sc = self._render(with_git=True, supervise=True)["services"]["sidecars"]
|
||||
for line in sc["environment"]:
|
||||
if line.startswith("BOT_BOTTLE_SIDECAR_DAEMONS="):
|
||||
csv = line.split("=", 1)[1]
|
||||
break
|
||||
else:
|
||||
self.fail("BOT_BOTTLE_SIDECAR_DAEMONS not in env")
|
||||
self.assertEqual(
|
||||
["egress", "git-gate", "supervise"],
|
||||
csv.split(","),
|
||||
)
|
||||
|
||||
def test_bundle_env_does_not_set_https_proxy(self):
|
||||
# HTTPS_PROXY at the container level would route git-gate's
|
||||
# git fetches through the proxy. Scoping it to mitmdump is
|
||||
# the job of egress_entrypoint.sh; the bundle env must not
|
||||
# leak it.
|
||||
sc = self._render(with_egress=True)["services"]["sidecars"]
|
||||
for line in sc["environment"]:
|
||||
self.assertFalse(
|
||||
line.startswith("HTTPS_PROXY=")
|
||||
or line.startswith("HTTP_PROXY=")
|
||||
or line.startswith("NO_PROXY="),
|
||||
f"bundle env must not set {line!r}",
|
||||
)
|
||||
|
||||
def test_egress_token_env_present_when_routes_declared(self):
|
||||
sc = self._render(with_egress=True)["services"]["sidecars"]
|
||||
env_strings = sc["environment"]
|
||||
self.assertIn("EGRESS_TOKEN_0", env_strings)
|
||||
|
||||
def test_egress_token_env_omitted_when_no_routes(self):
|
||||
sc = self._render()["services"]["sidecars"]
|
||||
env_strings = sc["environment"]
|
||||
self.assertNotIn("EGRESS_TOKEN_0", env_strings)
|
||||
|
||||
def test_canary_env_registered_as_sensitive_in_sidecar(self):
|
||||
sc = self._render(canary=True)["services"]["sidecars"]
|
||||
env_strings = sc["environment"]
|
||||
self.assertIn("CANON_ALPHA_SECRET=fake-canary-value", env_strings)
|
||||
self.assertIn(
|
||||
"BOT_BOTTLE_SENSITIVE_PREFIXES=CANON_ALPHA_SECRET",
|
||||
env_strings,
|
||||
)
|
||||
|
||||
def test_canary_env_visible_to_agent(self):
|
||||
agent = self._render(canary=True)["services"]["agent"]
|
||||
env_strings = agent["environment"]
|
||||
self.assertIn("CANON_ALPHA_SECRET=fake-canary-value", env_strings)
|
||||
|
||||
def test_supervise_env_present_when_active(self):
|
||||
sc = self._render(supervise=True)["services"]["sidecars"]
|
||||
env_strings = sc["environment"]
|
||||
self.assertIn(f"SUPERVISE_BOTTLE_SLUG={SLUG}", env_strings)
|
||||
self.assertIn("SUPERVISE_DB_PATH=/run/supervise/bot-bottle.db", env_strings)
|
||||
self.assertTrue(any(e.startswith("SUPERVISE_PORT=") for e in env_strings))
|
||||
|
||||
def test_volumes_always_includes_egress_ca(self):
|
||||
sc = self._render()["services"]["sidecars"]
|
||||
targets = {v["target"] for v in sc["volumes"]}
|
||||
self.assertIn("/home/mitmproxy/.mitmproxy/mitmproxy-ca.pem", targets)
|
||||
|
||||
def test_volumes_union_full_matrix(self):
|
||||
sc = self._render(with_git=True, with_egress=True, supervise=True)[
|
||||
"services"]["sidecars"]
|
||||
targets = {v["target"] for v in sc["volumes"]}
|
||||
self.assertIn("/home/mitmproxy/.mitmproxy/mitmproxy-ca.pem", targets)
|
||||
self.assertIn("/etc/egress", targets)
|
||||
self.assertIn("/git-gate-entrypoint.sh", targets)
|
||||
self.assertIn("/git-gate/creds/upstream-known_hosts", targets)
|
||||
self.assertIn("/run/supervise/bot-bottle.db", targets)
|
||||
|
||||
def test_extra_hosts_omitted_for_git_upstreams(self):
|
||||
sc = self._render(with_git=True)["services"]["sidecars"]
|
||||
self.assertNotIn("extra_hosts", sc)
|
||||
|
||||
def test_agent_depends_on_bundle_only(self):
|
||||
sc = self._render(with_git=True, with_egress=True, supervise=True)[
|
||||
"services"]["agent"]
|
||||
self.assertEqual(["sidecars"], sc["depends_on"])
|
||||
|
||||
def test_agent_proxy_url_resolves_via_bundle_alias(self):
|
||||
# With egress active, the agent's HTTPS_PROXY points at
|
||||
# `egress` shortname; bundle aliases `egress` to itself so
|
||||
# the URL keeps working without an agent-side change.
|
||||
spec = self._render(with_egress=True)
|
||||
sc = spec["services"]["agent"]
|
||||
proxy = next(e for e in sc["environment"] if e.startswith("HTTPS_PROXY="))
|
||||
self.assertIn("egress", proxy)
|
||||
self.assertIn("egress",
|
||||
spec["services"]["sidecars"]["networks"]["internal"]["aliases"])
|
||||
|
||||
|
||||
class TestProjectNaming(unittest.TestCase):
|
||||
|
||||
@@ -0,0 +1,51 @@
|
||||
"""Unit: agent-only consolidated compose render (PRD 0070)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import unittest
|
||||
|
||||
from bot_bottle.backend.docker.consolidated_compose import consolidated_agent_compose
|
||||
from tests.unit._docker_bottle_plan import _plan
|
||||
|
||||
_GW = "172.18.0.2"
|
||||
_IP = "172.18.0.5"
|
||||
_NET = "bot-bottle-gateway"
|
||||
|
||||
|
||||
class TestConsolidatedAgentCompose(unittest.TestCase):
|
||||
def _spec(self, *, runsc: bool = False):
|
||||
plan = _plan(with_egress=True, supervise=True, with_git=True)
|
||||
if runsc:
|
||||
plan = type(plan)(**{**vars(plan), "use_runsc": True}) # type: ignore[arg-type]
|
||||
return consolidated_agent_compose(plan, gateway_ip=_GW, source_ip=_IP, network=_NET)
|
||||
|
||||
def test_only_agent_service_no_companion_container(self) -> None:
|
||||
# The whole point of consolidation: no per-bottle gateway.
|
||||
self.assertEqual(["agent"], list(self._spec()["services"]))
|
||||
|
||||
def test_agent_pinned_on_external_gateway_network(self) -> None:
|
||||
spec = self._spec()
|
||||
self.assertEqual({"external": True}, spec["networks"][_NET])
|
||||
agent_net = spec["services"]["agent"]["networks"][_NET]
|
||||
self.assertEqual(_IP, agent_net["ipv4_address"])
|
||||
|
||||
def test_proxy_and_ca_point_at_gateway(self) -> None:
|
||||
env = self._spec()["services"]["agent"]["environment"]
|
||||
self.assertIn(f"HTTPS_PROXY=http://{_GW}:9099", env)
|
||||
# git-http + supervise on the gateway must bypass the egress proxy.
|
||||
self.assertTrue(any(e.startswith("NO_PROXY=") and _GW in e for e in env))
|
||||
|
||||
def test_no_companion_container_dependency(self) -> None:
|
||||
self.assertNotIn("depends_on", self._spec()["services"]["agent"])
|
||||
|
||||
def test_runsc_runtime_when_enabled(self) -> None:
|
||||
self.assertEqual("runsc", self._spec(runsc=True)["services"]["agent"]["runtime"])
|
||||
|
||||
def test_forwarded_env_stays_bare_names(self) -> None:
|
||||
env = self._spec()["services"]["agent"]["environment"]
|
||||
# forwarded secrets are bare names (value inherited from process env).
|
||||
self.assertIn("CLAUDE_CODE_OAUTH_TOKEN", env)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,95 @@
|
||||
"""Unit: consolidated launch sequence — compose the orchestrator primitives (PRD 0070)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
from unittest.mock import MagicMock, Mock, patch
|
||||
|
||||
from bot_bottle.backend.docker.consolidated_launch import (
|
||||
launch_consolidated,
|
||||
teardown_consolidated,
|
||||
)
|
||||
from bot_bottle.egress import EgressPlan, EgressRoute
|
||||
from bot_bottle.git_gate import GitGatePlan
|
||||
from bot_bottle.orchestrator.client import RegisteredBottle
|
||||
|
||||
_MOD = "bot_bottle.backend.docker.consolidated_launch"
|
||||
|
||||
|
||||
def _egress_plan() -> EgressPlan:
|
||||
return EgressPlan(
|
||||
slug="demo", routes_path=Path("/x"), routes=(EgressRoute(host="api.example.com"),),
|
||||
token_env_map={},
|
||||
)
|
||||
|
||||
|
||||
def _git_plan() -> GitGatePlan:
|
||||
return GitGatePlan(
|
||||
slug="demo", entrypoint_script=Path(), hook_script=Path(),
|
||||
access_hook_script=Path(), upstreams=(),
|
||||
)
|
||||
|
||||
|
||||
def _client(*, bottles: list[dict[str, object]] | None = None) -> Mock:
|
||||
c = Mock()
|
||||
c.list_bottles.return_value = bottles or []
|
||||
c.register_bottle.return_value = RegisteredBottle("b1", "tok")
|
||||
return c
|
||||
|
||||
|
||||
class TestLaunchConsolidated(unittest.TestCase):
|
||||
def _run(
|
||||
self, client: Mock, provision: Mock | None = None,
|
||||
*, on_network: tuple[str, ...] = ("172.18.0.2",),
|
||||
):
|
||||
service = MagicMock()
|
||||
service.ensure_running.return_value = "http://orch:8080"
|
||||
with patch(f"{_MOD}._network_cidr", return_value="172.18.0.0/16"), \
|
||||
patch(f"{_MOD}._container_ip", return_value="172.18.0.2"), \
|
||||
patch(f"{_MOD}._network_container_ips", return_value=list(on_network)), \
|
||||
patch(f"{_MOD}.OrchestratorClient", return_value=client), \
|
||||
patch(f"{_MOD}.provision_git_gate", provision or Mock()):
|
||||
return launch_consolidated(_egress_plan(), _git_plan(), service=service)
|
||||
|
||||
def test_allocates_ip_registers_and_provisions(self) -> None:
|
||||
client = _client()
|
||||
provision = Mock()
|
||||
ctx = self._run(client, provision)
|
||||
# .1 is the router, .2 is the gateway → first bottle gets .3.
|
||||
self.assertEqual("172.18.0.3", ctx.source_ip)
|
||||
self.assertEqual("172.18.0.2", ctx.gateway_ip)
|
||||
self.assertEqual("b1", ctx.bottle_id)
|
||||
self.assertEqual("tok", ctx.identity_token)
|
||||
self.assertEqual("http://orch:8080", ctx.orchestrator_url)
|
||||
# Registered with the source IP + the egress policy blob.
|
||||
kwargs = client.register_bottle.call_args
|
||||
self.assertEqual("172.18.0.3", kwargs.args[0])
|
||||
self.assertIn("api.example.com", kwargs.kwargs["policy"])
|
||||
provision.assert_called_once()
|
||||
|
||||
def test_skips_all_addresses_on_the_network(self) -> None:
|
||||
# Gateway .2 + orchestrator .3 already attached -> agent gets .4.
|
||||
ctx = self._run(_client(), on_network=("172.18.0.2", "172.18.0.3"))
|
||||
self.assertEqual("172.18.0.4", ctx.source_ip)
|
||||
|
||||
def test_provision_failure_rolls_back_registration(self) -> None:
|
||||
client = _client()
|
||||
provision = Mock(side_effect=RuntimeError("provision boom"))
|
||||
with self.assertRaises(RuntimeError):
|
||||
self._run(client, provision)
|
||||
client.teardown_bottle.assert_called_once_with("b1") # no orphan left
|
||||
|
||||
|
||||
class TestTeardownConsolidated(unittest.TestCase):
|
||||
def test_deregisters_and_deprovisions(self) -> None:
|
||||
client = Mock()
|
||||
with patch(f"{_MOD}.OrchestratorClient", return_value=client), \
|
||||
patch(f"{_MOD}.deprovision_git_gate") as deprov:
|
||||
teardown_consolidated("b1", orchestrator_url="http://orch:8080")
|
||||
client.teardown_bottle.assert_called_once_with("b1")
|
||||
deprov.assert_called_once()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -1,4 +1,4 @@
|
||||
"""Unit: Docker launch step uses committed image when available."""
|
||||
"""Unit: Docker launch step uses committed image when available (consolidated)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
@@ -6,6 +6,7 @@ import contextlib
|
||||
import io
|
||||
import tempfile
|
||||
import unittest
|
||||
from collections.abc import Callable, Generator
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
from unittest import mock
|
||||
@@ -14,9 +15,11 @@ from bot_bottle.agent_provider import AgentProvisionPlan
|
||||
from bot_bottle.backend import BottleSpec
|
||||
from bot_bottle.backend.docker import launch as launch_mod
|
||||
from bot_bottle.backend.docker.bottle_plan import DockerBottlePlan
|
||||
from bot_bottle.backend.docker.consolidated_launch import LaunchContext
|
||||
from bot_bottle.egress import EgressPlan
|
||||
from bot_bottle.git_gate import GitGatePlan
|
||||
from bot_bottle.manifest import ManifestIndex
|
||||
from tests.unit import use_bottle_root
|
||||
|
||||
|
||||
_SLUG = "dev-abc12"
|
||||
@@ -28,163 +31,112 @@ _IDX = ManifestIndex.from_json_obj({
|
||||
"agents": {"demo": {"skills": [], "prompt": "", "bottle": "dev"}},
|
||||
})
|
||||
|
||||
_CTX = LaunchContext(
|
||||
bottle_id="b1", identity_token="t", source_ip="172.20.0.4",
|
||||
network="bot-bottle-gateway", gateway_ip="172.20.0.2",
|
||||
orchestrator_url="http://orch:8099",
|
||||
)
|
||||
|
||||
|
||||
def _plan(tmp: str) -> DockerBottlePlan:
|
||||
stage = Path(tmp)
|
||||
spec = BottleSpec(
|
||||
manifest=_IDX,
|
||||
agent_name="demo",
|
||||
copy_cwd=False,
|
||||
user_cwd=tmp,
|
||||
identity=_SLUG,
|
||||
manifest=_IDX, agent_name="demo", copy_cwd=False, user_cwd=tmp, identity=_SLUG,
|
||||
)
|
||||
return DockerBottlePlan(
|
||||
spec=spec,
|
||||
manifest=_IDX.load_for_agent("demo"),
|
||||
stage_dir=stage,
|
||||
git_gate_plan=GitGatePlan(
|
||||
slug=_SLUG,
|
||||
entrypoint_script=stage / "entrypoint.sh",
|
||||
hook_script=stage / "hook.sh",
|
||||
access_hook_script=stage / "access-hook.sh",
|
||||
upstreams=(),
|
||||
slug=_SLUG, entrypoint_script=stage / "e.sh", hook_script=stage / "h.sh",
|
||||
access_hook_script=stage / "a.sh", upstreams=(),
|
||||
),
|
||||
egress_plan=EgressPlan(
|
||||
slug=_SLUG,
|
||||
routes_path=stage / "egress.yaml",
|
||||
routes=(),
|
||||
token_env_map={},
|
||||
slug=_SLUG, routes_path=stage / "egress.yaml", routes=(), token_env_map={},
|
||||
),
|
||||
supervise_plan=None,
|
||||
agent_provision=AgentProvisionPlan(
|
||||
template="claude",
|
||||
command="claude",
|
||||
prompt_mode="append_file",
|
||||
image=_DEFAULT_IMAGE,
|
||||
dockerfile="",
|
||||
guest_home="/home/node",
|
||||
instance_name=f"bot-bottle-{_SLUG}",
|
||||
prompt_file=stage / "prompt.txt",
|
||||
template="claude", command="claude", prompt_mode="append_file",
|
||||
image=_DEFAULT_IMAGE, dockerfile="", guest_home="/home/node",
|
||||
instance_name=f"bot-bottle-{_SLUG}", prompt_file=stage / "prompt.txt",
|
||||
guest_env={},
|
||||
),
|
||||
slug=_SLUG,
|
||||
forwarded_env={},
|
||||
use_runsc=False,
|
||||
slug=_SLUG, forwarded_env={}, use_runsc=False,
|
||||
)
|
||||
|
||||
|
||||
class TestLaunchCommittedImage(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self._tmp = tempfile.mkdtemp(prefix="launch-committed-test.")
|
||||
self.addCleanup(lambda: __import__("shutil").rmtree(self._tmp, ignore_errors=True))
|
||||
# The launch writes the gateway CA under the bottle root — sandbox it.
|
||||
self.addCleanup(use_bottle_root(Path(self._tmp)))
|
||||
|
||||
def tearDown(self) -> None:
|
||||
import shutil
|
||||
shutil.rmtree(self._tmp, ignore_errors=True)
|
||||
|
||||
def _run_launch(
|
||||
@contextlib.contextmanager
|
||||
def _patched(
|
||||
self,
|
||||
plan: DockerBottlePlan,
|
||||
*,
|
||||
committed_tag: str | None = None,
|
||||
image_present: bool = True,
|
||||
) -> list[str]:
|
||||
"""Drive launch() through its full sequence with the committed-image
|
||||
behaviour controlled by the arguments. Returns the images that were
|
||||
passed to `build_image` (empty list if it was never called)."""
|
||||
committed_tag: str | None,
|
||||
image_present: bool,
|
||||
compose: Callable[..., dict[str, Any]],
|
||||
) -> Generator[list[str], None, None]:
|
||||
built: list[str] = []
|
||||
gw = mock.Mock()
|
||||
gw.ca_cert_pem.return_value = "-----BEGIN CERTIFICATE-----\nx\n-----END CERTIFICATE-----\n"
|
||||
|
||||
def fake_build(image: str, ctx: str, *, dockerfile: str = "") -> None:
|
||||
def _build(image: str, ctx: str, *, dockerfile: str = "") -> None:
|
||||
del ctx, dockerfile
|
||||
built.append(image)
|
||||
|
||||
with mock.patch.object(
|
||||
launch_mod, "read_committed_image", return_value=committed_tag,
|
||||
), mock.patch.object(
|
||||
launch_mod.docker_mod, "image_exists", return_value=image_present,
|
||||
), mock.patch.object(
|
||||
launch_mod.docker_mod, "build_image", side_effect=fake_build,
|
||||
), mock.patch.object(
|
||||
launch_mod, "egress_tls_init",
|
||||
return_value=(Path("/egress_ca"), Path("/egress_cert")),
|
||||
), mock.patch.object(
|
||||
launch_mod.network_mod, "network_name_for_slug",
|
||||
return_value="bb-internal",
|
||||
), mock.patch.object(
|
||||
launch_mod.network_mod, "network_egress_name_for_slug",
|
||||
return_value="bb-egress",
|
||||
), mock.patch.object(
|
||||
launch_mod, "bottle_plan_to_compose",
|
||||
return_value={"services": {"agent": {}}},
|
||||
), mock.patch.object(
|
||||
launch_mod, "write_compose_file",
|
||||
return_value=Path("/tmp/compose.yml"),
|
||||
), mock.patch.object(launch_mod, "compose_up"), \
|
||||
mock.patch.object(launch_mod, "compose_dump_logs"), \
|
||||
mock.patch.object(launch_mod, "compose_down"), \
|
||||
contextlib.redirect_stderr(io.StringIO()):
|
||||
provision = mock.Mock(return_value=None)
|
||||
with launch_mod.launch(plan, provision=provision):
|
||||
pass
|
||||
with mock.patch.object(launch_mod, "read_committed_image", return_value=committed_tag), \
|
||||
mock.patch.object(launch_mod.docker_mod, "image_exists", return_value=image_present), \
|
||||
mock.patch.object(launch_mod.docker_mod, "build_image", side_effect=_build), \
|
||||
mock.patch.object(launch_mod.docker_mod, "verify_agent_image"), \
|
||||
mock.patch.object(launch_mod, "launch_consolidated", return_value=_CTX), \
|
||||
mock.patch.object(launch_mod, "teardown_consolidated"), \
|
||||
mock.patch.object(launch_mod, "DockerGateway", return_value=gw), \
|
||||
mock.patch.object(launch_mod, "consolidated_agent_compose", side_effect=compose), \
|
||||
mock.patch.object(launch_mod, "write_compose_file", return_value=Path("/tmp/c.yml")), \
|
||||
mock.patch.object(launch_mod, "compose_up"), \
|
||||
mock.patch.object(launch_mod, "compose_dump_logs"), \
|
||||
mock.patch.object(launch_mod, "compose_down"), \
|
||||
contextlib.redirect_stderr(io.StringIO()):
|
||||
yield built
|
||||
|
||||
def _run_launch(
|
||||
self, plan: DockerBottlePlan, *,
|
||||
committed_tag: str | None = None, image_present: bool = True,
|
||||
) -> list[str]:
|
||||
def compose(_p: DockerBottlePlan, **_kw: Any) -> dict[str, Any]:
|
||||
return {"services": {"agent": {}}}
|
||||
with self._patched(
|
||||
committed_tag=committed_tag, image_present=image_present, compose=compose,
|
||||
) as built:
|
||||
with launch_mod.launch(plan, provision=mock.Mock(return_value=None)):
|
||||
pass
|
||||
return built
|
||||
|
||||
def test_skips_build_when_committed_image_present(self) -> None:
|
||||
plan = _plan(self._tmp)
|
||||
built = self._run_launch(plan, committed_tag=_COMMITTED_TAG, image_present=True)
|
||||
self.assertEqual([], built, "build_image should not be called when committed image exists")
|
||||
built = self._run_launch(_plan(self._tmp), committed_tag=_COMMITTED_TAG, image_present=True)
|
||||
self.assertEqual([], built) # committed image reused, no build
|
||||
|
||||
def test_uses_committed_image_in_compose_spec(self) -> None:
|
||||
"""The compose spec renderer receives the committed image tag via
|
||||
plan.image — captured here by checking what bottle_plan_to_compose
|
||||
was called with."""
|
||||
plan = _plan(self._tmp)
|
||||
captured_plans: list[DockerBottlePlan] = []
|
||||
captured: list[DockerBottlePlan] = []
|
||||
|
||||
def fake_compose(p: DockerBottlePlan) -> dict[str, Any]:
|
||||
captured_plans.append(p)
|
||||
def compose(p: DockerBottlePlan, **_kw: Any) -> dict[str, Any]:
|
||||
captured.append(p)
|
||||
return {"services": {"agent": {}}}
|
||||
|
||||
with mock.patch.object(
|
||||
launch_mod, "read_committed_image", return_value=_COMMITTED_TAG,
|
||||
), mock.patch.object(
|
||||
launch_mod.docker_mod, "image_exists", return_value=True,
|
||||
), mock.patch.object(
|
||||
launch_mod.docker_mod, "build_image",
|
||||
), mock.patch.object(
|
||||
launch_mod, "egress_tls_init",
|
||||
return_value=(Path("/egress_ca"), Path("/egress_cert")),
|
||||
), mock.patch.object(
|
||||
launch_mod.network_mod, "network_name_for_slug",
|
||||
return_value="bb-internal",
|
||||
), mock.patch.object(
|
||||
launch_mod.network_mod, "network_egress_name_for_slug",
|
||||
return_value="bb-egress",
|
||||
), mock.patch.object(
|
||||
launch_mod, "bottle_plan_to_compose", side_effect=fake_compose,
|
||||
), mock.patch.object(
|
||||
launch_mod, "write_compose_file",
|
||||
return_value=Path("/tmp/compose.yml"),
|
||||
), mock.patch.object(launch_mod, "compose_up"), \
|
||||
mock.patch.object(launch_mod, "compose_dump_logs"), \
|
||||
mock.patch.object(launch_mod, "compose_down"), \
|
||||
contextlib.redirect_stderr(io.StringIO()):
|
||||
provision = mock.Mock(return_value=None)
|
||||
with launch_mod.launch(plan, provision=provision):
|
||||
with self._patched(committed_tag=_COMMITTED_TAG, image_present=True, compose=compose):
|
||||
with launch_mod.launch(_plan(self._tmp), provision=mock.Mock(return_value=None)):
|
||||
pass
|
||||
|
||||
self.assertEqual(1, len(captured_plans))
|
||||
self.assertEqual(_COMMITTED_TAG, captured_plans[0].image)
|
||||
self.assertEqual(_COMMITTED_TAG, captured[0].image)
|
||||
|
||||
def test_falls_back_to_build_when_no_committed_image(self) -> None:
|
||||
plan = _plan(self._tmp)
|
||||
built = self._run_launch(plan, committed_tag=None)
|
||||
self.assertEqual([_DEFAULT_IMAGE], built)
|
||||
self.assertEqual([_DEFAULT_IMAGE], self._run_launch(_plan(self._tmp), committed_tag=None))
|
||||
|
||||
def test_falls_back_to_build_when_committed_image_missing_from_daemon(self) -> None:
|
||||
plan = _plan(self._tmp)
|
||||
built = self._run_launch(
|
||||
plan, committed_tag=_COMMITTED_TAG, image_present=False,
|
||||
)
|
||||
built = self._run_launch(_plan(self._tmp), committed_tag=_COMMITTED_TAG, image_present=False)
|
||||
self.assertEqual([_DEFAULT_IMAGE], built)
|
||||
|
||||
|
||||
|
||||
@@ -19,9 +19,11 @@ from bot_bottle.agent_provider import AgentProvisionPlan
|
||||
from bot_bottle.backend import BottleSpec
|
||||
from bot_bottle.backend.docker import launch as launch_mod
|
||||
from bot_bottle.backend.docker.bottle_plan import DockerBottlePlan
|
||||
from bot_bottle.backend.docker.consolidated_launch import LaunchContext
|
||||
from bot_bottle.egress import EgressPlan
|
||||
from bot_bottle.git_gate import GitGatePlan
|
||||
from bot_bottle.manifest import ManifestIndex
|
||||
from tests.unit import use_bottle_root
|
||||
|
||||
_INDEX = ManifestIndex.from_json_obj({
|
||||
"bottles": {"dev": {}},
|
||||
@@ -77,41 +79,37 @@ def _plan(tmp: str) -> DockerBottlePlan:
|
||||
class TestTeardownWarning(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self._tmp = tempfile.mkdtemp(prefix="docker-launch-teardown-test.")
|
||||
|
||||
def tearDown(self) -> None:
|
||||
import shutil
|
||||
shutil.rmtree(self._tmp, ignore_errors=True)
|
||||
self.addCleanup(lambda: __import__("shutil").rmtree(self._tmp, ignore_errors=True))
|
||||
self.addCleanup(use_bottle_root(Path(self._tmp))) # sandbox the gateway CA write
|
||||
|
||||
def test_teardown_failure_emits_warning_with_container_and_operation(self):
|
||||
plan = _plan(self._tmp)
|
||||
buf = io.StringIO()
|
||||
gw = mock.Mock()
|
||||
gw.ca_cert_pem.return_value = "-----BEGIN CERTIFICATE-----\nx\n-----END CERTIFICATE-----\n"
|
||||
ctx = LaunchContext(
|
||||
bottle_id="b1", identity_token="t", source_ip="172.20.0.4",
|
||||
network="bot-bottle-gateway", gateway_ip="172.20.0.2",
|
||||
orchestrator_url="http://orch:8099",
|
||||
)
|
||||
|
||||
with mock.patch.object(launch_mod.docker_mod, "build_image"), \
|
||||
mock.patch.object(launch_mod.docker_mod, "verify_agent_image"), \
|
||||
mock.patch.object(launch_mod, "launch_consolidated", return_value=ctx), \
|
||||
mock.patch.object(launch_mod, "teardown_consolidated"), \
|
||||
mock.patch.object(launch_mod, "DockerGateway", return_value=gw), \
|
||||
mock.patch.object(
|
||||
launch_mod, "egress_tls_init",
|
||||
return_value=(Path("/egress_ca"), Path("/egress_cert")),
|
||||
), \
|
||||
mock.patch.object(
|
||||
launch_mod.network_mod, "network_name_for_slug",
|
||||
return_value="bb-internal-test",
|
||||
), \
|
||||
mock.patch.object(
|
||||
launch_mod.network_mod, "network_egress_name_for_slug",
|
||||
return_value="bb-egress-test",
|
||||
), \
|
||||
mock.patch.object(
|
||||
launch_mod, "bottle_plan_to_compose",
|
||||
launch_mod, "consolidated_agent_compose",
|
||||
return_value={"services": {"agent": {}}},
|
||||
), \
|
||||
mock.patch.object(
|
||||
launch_mod, "write_compose_file",
|
||||
return_value=Path("/tmp/compose.yml"),
|
||||
launch_mod, "write_compose_file", return_value=Path("/tmp/compose.yml"),
|
||||
), \
|
||||
mock.patch.object(launch_mod, "compose_up"), \
|
||||
mock.patch.object(launch_mod, "compose_dump_logs"), \
|
||||
mock.patch.object(
|
||||
launch_mod, "compose_down",
|
||||
side_effect=RuntimeError("network remove failed"),
|
||||
side_effect=RuntimeError("compose down failed"),
|
||||
), \
|
||||
contextlib.redirect_stderr(buf):
|
||||
provision = mock.Mock(return_value=None)
|
||||
|
||||
@@ -16,7 +16,7 @@ from bot_bottle.egress import (
|
||||
egress_render_routes,
|
||||
egress_resolve_token_values,
|
||||
egress_routes_for_bottle,
|
||||
egress_sidecar_env_entries,
|
||||
egress_gateway_env_entries,
|
||||
egress_token_env_map,
|
||||
)
|
||||
from bot_bottle.errors import MissingEnvVarError
|
||||
@@ -586,7 +586,7 @@ class TestCanaryGeneration(unittest.TestCase):
|
||||
|
||||
|
||||
class TestEgressEnvEntries(unittest.TestCase):
|
||||
def test_sidecar_entries_include_route_tokens_and_canary_scan_prefix(self):
|
||||
def test_gateway_entries_include_route_tokens_and_canary_scan_prefix(self):
|
||||
plan = EgressPlan(
|
||||
slug="s",
|
||||
routes_path=Path("/tmp/r.yaml"),
|
||||
@@ -603,7 +603,7 @@ class TestEgressEnvEntries(unittest.TestCase):
|
||||
"CANON_ALPHA_SECRET=fake-canary-value",
|
||||
"BOT_BOTTLE_SENSITIVE_PREFIXES=CANON_ALPHA_SECRET",
|
||||
),
|
||||
egress_sidecar_env_entries(plan),
|
||||
egress_gateway_env_entries(plan),
|
||||
)
|
||||
|
||||
def test_agent_entries_include_only_canary_bait(self):
|
||||
@@ -630,7 +630,7 @@ class TestEgressEnvEntries(unittest.TestCase):
|
||||
canary="fake-canary-value",
|
||||
)
|
||||
|
||||
self.assertEqual((), egress_sidecar_env_entries(plan))
|
||||
self.assertEqual((), egress_gateway_env_entries(plan))
|
||||
self.assertEqual((), egress_agent_env_entries(plan))
|
||||
|
||||
|
||||
|
||||
@@ -951,7 +951,7 @@ class TestScanOutbound(unittest.TestCase):
|
||||
body='{"jsonrpc":"2.0","method":"initialize"}',
|
||||
)
|
||||
self.assertIsNone(scan_outbound(route, text, {
|
||||
"EGRESS_TOKEN_0": "sidecar-owned-secret",
|
||||
"EGRESS_TOKEN_0": "gateway-owned-secret",
|
||||
}))
|
||||
|
||||
def test_token_in_body_blocked(self):
|
||||
@@ -1302,7 +1302,7 @@ class TestScanOutboundEnhanced(unittest.TestCase):
|
||||
self.assertEqual("warn", result.severity)
|
||||
|
||||
def test_bot_bottle_sensitive_prefixes_env_var(self):
|
||||
# When the sidecar env contains BOT_BOTTLE_SENSITIVE_PREFIXES,
|
||||
# When the gateway env contains BOT_BOTTLE_SENSITIVE_PREFIXES,
|
||||
# scan_outbound should scan those additional prefixes.
|
||||
secret = "extra-sensitive-value-abc"
|
||||
env = {
|
||||
@@ -1324,7 +1324,7 @@ class TestScanOutboundEnhanced(unittest.TestCase):
|
||||
self.assertIsNotNone(result)
|
||||
|
||||
def test_canary_detected_via_random_secret_env_name(self):
|
||||
# The fake secret uses a randomized env name that the sidecar marks
|
||||
# The fake secret uses a randomized env name that the gateway marks
|
||||
# as sensitive through BOT_BOTTLE_SENSITIVE_PREFIXES.
|
||||
canary = "canaryvalue12345abcdef"
|
||||
env = {
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
"""Unit: LOG_FULL credential redaction in _log_request / _log_response (issue #257).
|
||||
|
||||
egress_addon.py is sidecar-only code that depends on mitmproxy, which is
|
||||
egress_addon.py is gateway-only code that depends on mitmproxy, which is
|
||||
not installed on the host. This file pre-populates sys.modules with the
|
||||
minimum mocks needed so EgressAddon can be imported and tested without the
|
||||
real mitmproxy package."""
|
||||
@@ -17,7 +17,7 @@ from unittest.mock import patch
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Sidecar-import shims — must run before importing egress_addon
|
||||
# Gateway-import shims — must run before importing egress_addon
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def _ensure_shims() -> None:
|
||||
@@ -46,7 +46,7 @@ def _addon() -> EgressAddon:
|
||||
"""Return a bare EgressAddon with LOG_FULL config and no routes file."""
|
||||
a: EgressAddon = EgressAddon.__new__(EgressAddon)
|
||||
a.config = Config(routes=(), log=LOG_FULL)
|
||||
a.safe_tokens = set()
|
||||
a._safe_tokens = {}
|
||||
a._supervise_slug = ""
|
||||
a._token_allow_timeout = 300.0
|
||||
return a
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
"""Unit: EgressAddon request/response decision flow (issue #286).
|
||||
|
||||
`egress_addon.py` is the sidecar-only mitmproxy adapter that wires the
|
||||
`egress_addon.py` is the gateway-only mitmproxy adapter that wires the
|
||||
host-importable decision logic in `egress_addon_core` into mitmproxy's
|
||||
request/response hooks. The core logic is exercised directly by
|
||||
`test_egress_addon_core.py`; the redaction logging by
|
||||
@@ -13,7 +13,7 @@ from coverage.
|
||||
mitmproxy is not installed on the host, so we pre-populate `sys.modules`
|
||||
with the minimum stubs needed to import the adapter (a `mitmproxy.http`
|
||||
module exposing a `Response` with `.make`, plus the flat
|
||||
`egress_addon_core` name the sidecar uses)."""
|
||||
`egress_addon_core` name the gateway uses)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
@@ -158,7 +158,7 @@ class _WebSocketData:
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Sidecar-import shims — must run before importing egress_addon
|
||||
# Gateway-import shims — must run before importing egress_addon
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
@@ -211,7 +211,7 @@ def _addon(config: Config) -> EgressAddon:
|
||||
"""Bare EgressAddon with a supplied config and no supervise wiring."""
|
||||
a: EgressAddon = EgressAddon.__new__(EgressAddon)
|
||||
a.config = config
|
||||
a.safe_tokens = set()
|
||||
a._safe_tokens = {}
|
||||
a._supervise_slug = ""
|
||||
a._token_allow_timeout = 300.0
|
||||
a.routes_path = "/nonexistent/routes.yaml"
|
||||
@@ -222,6 +222,32 @@ def _run_request(addon: EgressAddon, flow: _Flow) -> None:
|
||||
asyncio.run(addon.request(flow)) # type: ignore[arg-type]
|
||||
|
||||
|
||||
def _with_client_ip(flow: _Flow, ip: str) -> _Flow:
|
||||
"""Attach a mitmproxy-style client_conn so consolidated resolution can read
|
||||
the source IP (`flow.client_conn.peername[0]`)."""
|
||||
flow.client_conn = types.SimpleNamespace(peername=(ip, 54321)) # type: ignore[attr-defined]
|
||||
return flow
|
||||
|
||||
|
||||
class _CtxResolver:
|
||||
"""Fake orchestrator resolver: maps source IP -> bottle id, and grants the
|
||||
same allow-list to any attributed bottle (unattributed -> deny)."""
|
||||
|
||||
def __init__(
|
||||
self, ip_to_bottle: dict[str, str], tokens: dict[str, str] | None = None,
|
||||
) -> None:
|
||||
self._map = ip_to_bottle
|
||||
self._tokens = tokens or {}
|
||||
|
||||
def resolve_policy_and_bottle_id(
|
||||
self, source_ip: str, identity_token: str = "",
|
||||
) -> tuple[str | None, str | None, dict[str, str]]:
|
||||
del identity_token
|
||||
bottle_id = self._map.get(source_ip)
|
||||
policy = "routes:\n - host: api.example.com\n" if bottle_id else None
|
||||
return policy, bottle_id, (self._tokens if bottle_id else {})
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Introspection endpoint
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -277,9 +303,9 @@ class TestAuthInjection(unittest.TestCase):
|
||||
route = Route(host="api.example.com", auth_scheme="Bearer", token_env="EGRESS_TOKEN_0")
|
||||
addon = _addon(Config(routes=(route,)))
|
||||
flow = _Flow(_Request(host="api.example.com", headers={"authorization": "Bearer agent-faked"}))
|
||||
with patch.dict("os.environ", {"EGRESS_TOKEN_0": "real-sidecar-token"}):
|
||||
with patch.dict("os.environ", {"EGRESS_TOKEN_0": "real-gateway-token"}):
|
||||
_run_request(addon, flow)
|
||||
self.assertEqual("Bearer real-sidecar-token", flow.request.headers.get("authorization"))
|
||||
self.assertEqual("Bearer real-gateway-token", flow.request.headers.get("authorization"))
|
||||
self.assertIsNone(flow.response)
|
||||
|
||||
def test_auth_route_with_unset_env_blocks(self) -> None:
|
||||
@@ -418,7 +444,8 @@ class TestSuperviseBranch(unittest.TestCase):
|
||||
with patch.object(_ea_mod, "_sv", _fake_sv("approved")):
|
||||
_run_request(addon, flow)
|
||||
self.assertIsNone(flow.response) # forwarded after approval
|
||||
self.assertIn(_OPENAI_KEY, addon.safe_tokens)
|
||||
# Approval lands in the calling bottle's safelist (keyed by slug).
|
||||
self.assertIn(_OPENAI_KEY, addon._safe_tokens_for("test-bottle"))
|
||||
|
||||
def test_operator_rejection_blocks(self) -> None:
|
||||
addon = self._supervised_addon()
|
||||
@@ -735,5 +762,102 @@ class TestLogFullRequest(unittest.TestCase):
|
||||
self.assertTrue(any(e.get("event") == "egress_request" for e in logged))
|
||||
|
||||
|
||||
class TestSuperviseMultiTenant(unittest.TestCase):
|
||||
"""Consolidated gateway: supervise proposals + the DLP safelist are keyed
|
||||
per bottle, resolved by source IP (PRD 0070)."""
|
||||
|
||||
def _consolidated_addon(self) -> EgressAddon:
|
||||
# Static config is empty; the resolver supplies each bottle's config.
|
||||
addon = _addon(Config(routes=()))
|
||||
addon._resolver = cast(Any, _CtxResolver({"10.0.0.1": "bottle-a", "10.0.0.2": "bottle-b"}))
|
||||
addon._token_allow_timeout = 0.05
|
||||
return addon
|
||||
|
||||
def test_approval_is_scoped_to_the_calling_bottle(self) -> None:
|
||||
addon = self._consolidated_addon()
|
||||
# bottle-a (10.0.0.1) sends the token; the operator approves.
|
||||
flow = _with_client_ip(
|
||||
_Flow(_Request(host="api.example.com", method="POST", body=f"k={_OPENAI_KEY}")),
|
||||
"10.0.0.1",
|
||||
)
|
||||
with patch.object(_ea_mod, "_sv", _fake_sv("approved")):
|
||||
_run_request(addon, flow)
|
||||
self.assertIsNone(flow.response) # forwarded after approval
|
||||
# The approval lands ONLY in bottle-a's safelist — never bottle-b's.
|
||||
# A global set here would be the cross-tenant leak this slice closes.
|
||||
self.assertIn(_OPENAI_KEY, addon._safe_tokens_for("bottle-a"))
|
||||
self.assertNotIn(_OPENAI_KEY, addon._safe_tokens_for("bottle-b"))
|
||||
|
||||
def test_proposal_is_attributed_to_the_source_ip_bottle(self) -> None:
|
||||
addon = self._consolidated_addon()
|
||||
seen: list[str] = []
|
||||
fake = _fake_sv("approved")
|
||||
|
||||
def _capture(**kw: Any) -> Any:
|
||||
seen.append(kw["bottle_slug"])
|
||||
return types.SimpleNamespace(id="p")
|
||||
|
||||
fake.Proposal = types.SimpleNamespace(new=_capture)
|
||||
flow = _with_client_ip(
|
||||
_Flow(_Request(host="api.example.com", method="POST", body=f"k={_OPENAI_KEY}")),
|
||||
"10.0.0.2",
|
||||
)
|
||||
with patch.object(_ea_mod, "_sv", fake):
|
||||
_run_request(addon, flow)
|
||||
self.assertEqual(["bottle-b"], seen) # proposal keyed by the resolved bottle
|
||||
|
||||
def test_auth_token_injected_from_resolved_tokens(self) -> None:
|
||||
# The bottle's upstream token comes from /resolve (in-memory on the
|
||||
# orchestrator), NOT the gateway's env — the request is forwarded with
|
||||
# Authorization injected. This is the token-injection cut-over fix.
|
||||
policy = (
|
||||
'routes:\n - host: api.example.com\n'
|
||||
' auth_scheme: "Bearer"\n token_env: "EGRESS_TOKEN_0"\n'
|
||||
)
|
||||
|
||||
class _AuthResolver:
|
||||
def resolve_policy_and_bottle_id(self, ip: str, identity_token: str = ""):
|
||||
del ip, identity_token
|
||||
return policy, "bottle-a", {"EGRESS_TOKEN_0": "sk-secret"}
|
||||
|
||||
addon = _addon(Config(routes=()))
|
||||
addon._resolver = cast(Any, _AuthResolver())
|
||||
flow = _with_client_ip(_Flow(_Request(host="api.example.com", method="GET")), "10.0.0.1")
|
||||
_run_request(addon, flow)
|
||||
self.assertIsNone(flow.response) # forwarded, not blocked
|
||||
self.assertEqual("Bearer sk-secret", flow.request.headers.get("authorization"))
|
||||
|
||||
def test_authed_route_without_token_is_blocked(self) -> None:
|
||||
# No token resolved for the bottle → the authed route can't inject, so
|
||||
# the request is blocked (the error the cut-over originally produced).
|
||||
policy = (
|
||||
'routes:\n - host: api.example.com\n'
|
||||
' auth_scheme: "Bearer"\n token_env: "EGRESS_TOKEN_0"\n'
|
||||
)
|
||||
|
||||
class _NoTokenResolver:
|
||||
def resolve_policy_and_bottle_id(self, ip: str, identity_token: str = ""):
|
||||
del ip, identity_token
|
||||
return policy, "bottle-a", {} # no tokens
|
||||
|
||||
addon = _addon(Config(routes=()))
|
||||
addon._resolver = cast(Any, _NoTokenResolver())
|
||||
flow = _with_client_ip(_Flow(_Request(host="api.example.com", method="GET")), "10.0.0.1")
|
||||
_run_request(addon, flow)
|
||||
self.assertIsNotNone(flow.response) # blocked — token unset
|
||||
|
||||
def test_unattributed_source_ip_cannot_supervise(self) -> None:
|
||||
addon = self._consolidated_addon()
|
||||
# 10.9.9.9 is not in the resolver map -> deny-all config, empty slug.
|
||||
flow = _with_client_ip(
|
||||
_Flow(_Request(host="api.example.com", method="POST", body=f"k={_OPENAI_KEY}")),
|
||||
"10.9.9.9",
|
||||
)
|
||||
with patch.object(_ea_mod, "_sv", _fake_sv("approved")):
|
||||
_run_request(addon, flow)
|
||||
self.assertIsNotNone(flow.response) # blocked (no route, no supervise)
|
||||
self.assertNotIn(_OPENAI_KEY, addon._safe_tokens_for(""))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
|
||||
@@ -5,8 +5,6 @@ integration test)."""
|
||||
import tempfile
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
from types import SimpleNamespace
|
||||
from unittest.mock import patch
|
||||
|
||||
from tests.unit import use_bottle_root
|
||||
from bot_bottle.backend.egress_apply import EgressApplyError
|
||||
@@ -70,32 +68,16 @@ class TestApplyRoutesChange(unittest.TestCase):
|
||||
self.addCleanup(self._tmp.cleanup)
|
||||
self.addCleanup(use_bottle_root(Path(self._tmp.name) / ".bot-bottle"))
|
||||
|
||||
def test_writes_live_routes_and_signals_reload(self):
|
||||
calls: list[list[str]] = []
|
||||
|
||||
def fake_run(argv: list[str], **kwargs: object) -> SimpleNamespace:
|
||||
calls.append(list(argv))
|
||||
return SimpleNamespace(returncode=0, stdout="", stderr="")
|
||||
|
||||
with patch(
|
||||
"bot_bottle.backend.docker.egress_apply.subprocess.run",
|
||||
side_effect=fake_run,
|
||||
):
|
||||
before, after = applicator.apply_routes_change(
|
||||
def test_apply_routes_change_fails_closed_after_companion_removal(self):
|
||||
# The per-bottle companion container that live route-apply used to
|
||||
# signal was removed in the companion-container removal (#385); apply now
|
||||
# fails closed until the gateway-side apply lands.
|
||||
with self.assertRaises(EgressApplyError) as cm:
|
||||
applicator.apply_routes_change(
|
||||
"dev",
|
||||
"routes:\n - host: google.com\n",
|
||||
)
|
||||
|
||||
self.assertEqual("", before)
|
||||
self.assertEqual("routes:\n - host: google.com\n", after)
|
||||
self.assertEqual(
|
||||
"routes:\n - host: google.com\n",
|
||||
(Path(self._tmp.name) / ".bot-bottle/state/dev/egress/routes.yaml").read_text(encoding="utf-8"),
|
||||
)
|
||||
self.assertEqual(
|
||||
["docker", "kill", "--signal", "HUP", "bot-bottle-sidecars-dev"],
|
||||
calls[0],
|
||||
)
|
||||
self.assertIn("consolidated gateway", str(cm.exception))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user