Compare commits

..

6 Commits

Author SHA1 Message Date
didericis bd663196dc docs: reposition README around provider-neutral secure substrate
test / unit (pull_request) Successful in 36s
test / integration (pull_request) Successful in 17s
Lead with the agnostic + security story instead of the single-user
security framing. New hero positions bot-bottle as a neutral control
plane that runs any agent (Claude, Codex, or a drop-in contrib plugin)
inside an isolation boundary the agent can't touch.

Restructure Features into three pillars — neutral substrate, isolation
boundary, host-matched isolation — promoting provider-agnosticism (PRD
0053 user plugins) from a buried bullet to a headline. No capability
claims changed; per-provider auth/image detail preserved as a note
linking to Manifest.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01YcU7nerbg8cVj9R4EkpfLJ
2026-06-24 01:21:05 -04:00
didericis-codex 6b0de88be6 docs: activate install script prd
lint / lint (push) Successful in 1m39s
test / unit (pull_request) Successful in 31s
test / integration (pull_request) Successful in 16s
2026-06-23 21:47:12 -04:00
didericis-codex 9a941e59be feat: add install script packaging 2026-06-23 21:47:12 -04:00
didericis d7a3539755 ci(prd): rename PRD to prd-new placeholder per new convention 2026-06-23 21:46:44 -04:00
didericis cfe57a50d0 docs(prd): renumber PRD 0054 → 0057 (0054 slot taken by named-labelled-agents) 2026-06-23 21:46:44 -04:00
didericis e5d551861c docs(prd): PRD 0054 - install script 2026-06-23 21:46:44 -04:00
98 changed files with 1432 additions and 5992 deletions
-9
View File
@@ -1,9 +0,0 @@
[run]
branch = True
source = .
[report]
omit =
bot_bottle/egress_addon.py
bot_bottle/cli/tui.py
tests/*
+1 -7
View File
@@ -39,14 +39,8 @@ jobs:
with:
python-version: "3.12"
- name: Install dev requirements
run: python3 -m pip install -r requirements-dev.txt
- name: Run unit tests
run: python3 -m coverage run -m unittest discover -t . -s tests/unit -v
- name: Report unit coverage
run: python3 -m coverage report -m
run: python3 -m unittest discover -t . -s tests/unit -v
integration:
runs-on: ubuntu-latest
+2 -15
View File
@@ -8,7 +8,6 @@ on:
- '**.py'
- '.pylintrc'
- 'pyrightconfig.json'
- '.coveragerc'
workflow_dispatch:
jobs:
@@ -46,19 +45,10 @@ jobs:
echo "errors=$ERRORS" >> $GITHUB_OUTPUT
echo "Pyright errors: $ERRORS"
- name: Run coverage and extract percentage
id: coverage
run: |
python -m coverage run -m unittest discover -t . -s tests/unit > /dev/null 2>&1 || true
PERCENT=$(python -m coverage report 2>/dev/null | grep '^TOTAL' | grep -oP '\d+(?=%)' | tail -1)
echo "percent=$PERCENT" >> $GITHUB_OUTPUT
echo "Coverage: $PERCENT%"
- name: Update badges in README
run: |
PYLINT_SCORE="${{ steps.pylint.outputs.score }}"
PYRIGHT_ERRORS="${{ steps.pyright.outputs.errors }}"
COVERAGE_PERCENT="${{ steps.coverage.outputs.percent }}"
PYLINT_SCORE_ENCODED=$(echo "$PYLINT_SCORE" | sed 's|/|%2F|g')
@@ -68,12 +58,9 @@ jobs:
if [ -n "$PYRIGHT_ERRORS" ]; then
sed -i "s|/badge/pyright-[^)]*|/badge/pyright-${PYRIGHT_ERRORS}%20errors-brightgreen|" README.md
fi
if [ -n "$COVERAGE_PERCENT" ]; then
sed -i "s|/badge/coverage-[^)]*|/badge/coverage-${COVERAGE_PERCENT}%25-brightgreen|" README.md
fi
echo "Updated badges:"
grep -E "pylint|pyright|coverage" README.md | head -3
grep -E "pylint|pyright" README.md | head -2
- name: Commit and push badge updates
run: |
@@ -86,7 +73,7 @@ jobs:
else
echo "Badge changes detected, committing..."
git add README.md
MSG="chore: update quality badges"$'\n\n'"- Pylint: ${{ steps.pylint.outputs.score }}"$'\n'"- Pyright: ${{ steps.pyright.outputs.errors }} errors"$'\n'"- Coverage: ${{ steps.coverage.outputs.percent }}%"$'\n\n'"[skip ci]"
MSG="chore: update quality badges"$'\n\n'"- Pylint: ${{ steps.pylint.outputs.score }}"$'\n'"- Pyright: ${{ steps.pyright.outputs.errors }} errors"$'\n\n'"[skip ci]"
git commit -m "$MSG"
git push
fi
-1
View File
@@ -22,4 +22,3 @@ venv/
.pytest_cache/
.mypy_cache/
.ruff_cache/
.coverage
+42 -27
View File
@@ -7,28 +7,41 @@
[![test](https://gitea.dideric.is/didericis/bot-bottle/actions/workflows/test.yml/badge.svg?branch=main)](https://gitea.dideric.is/didericis/bot-bottle/actions?workflow=test.yml)
[![pylint](https://img.shields.io/badge/pylint-9.93%2F10-brightgreen)](https://github.com/PyCQA/pylint)
[![pyright](https://img.shields.io/badge/pyright-0%20errors-brightgreen)](https://github.com/microsoft/pyright)
[![coverage](https://img.shields.io/badge/coverage-79%25-brightgreen)](https://coverage.readthedocs.io/)
**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.
**Run any coding agent like it might be compromised — and lose nothing when it is.**
**Solution:** Ephemeral, per agent "bottles" the agent cannot modify that scan all traffic for data exfiltration and limit capabilities and egress to only what the agent needs.
bot-bottle is a provider-neutral, security-first substrate for autonomous agents. Bring Claude Code, Codex, or your own harness; each one runs in an ephemeral, per-agent "bottle" it cannot modify, where every byte of egress is scanned for exfiltration and capabilities are narrowed to exactly what the task declares.
## Features
**Problem:** You want to let a coding agent run unsupervised, but a prompt-injected or misbehaving agent — or a poisoned repo, MCP server, or skill — can wreck your environment or exfiltrate your secrets. Locking yourself to one vendor's cloud doesn't fix that; it just moves the blast radius.
**Solution:** A neutral control plane that runs *whatever agent you choose* inside an isolation boundary the agent can't touch: TLS-bumped egress allowlisting, outbound/inbound DLP, gitleaks-gated pushes, and host secrets the agent never sees. Swap the agent; keep the guarantees.
## Why bot-bottle
### A neutral substrate — bring your own agent
- **Provider-agnostic by design** — Claude and Codex ship built in; any other agent (Gemini, Aider, a local-model wrapper) is a drop-in plugin at `~/.bot-bottle/contrib/<name>/` — no fork, no PR against this repo. The manifest accepts any provider template, and the isolation, egress, and git guarantees are identical across all of them.
- **One control plane, every harness** — the same bottle, egress policy, and supervise flow wrap whichever agent you run, so switching or mixing providers doesn't change your security posture.
- **Composable bottles (`extends:`)** — keep provider/runtime policy in one base bottle (e.g. `claude.md`) and overlay task bottles on top.
### An isolation boundary the agent can't touch
- **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.
- **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.
- **Composable bottles (`extends:`)** — keep provider/runtime policy in one base bottle (e.g. `claude.md`) and overlay task bottles on top.
### Isolation that matches your host
- **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.
- **Smolmachines backend** — runs the agent in a libkrun micro-VM while the sidecar bundle stays in Docker. TSI and smolmachines DNS filtering close the raw DNS exfiltration gap that exists in the legacy Docker backend. Runs on macOS (Hypervisor.framework) and Linux (KVM, `/dev/kvm`).
- **Smolmachines backend** — runs the agent in a libkrun micro-VM while the sidecar bundle stays in Docker. TSI and smolmachines DNS filtering close the raw DNS exfiltration gap that exists in the legacy Docker backend.
- **Legacy Docker backend** — still available for examples, CI, and hosts without Apple Container via `BOT_BOTTLE_BACKEND=docker` or `--backend=docker`.
Per-provider auth (Claude long-lived OAuth token; Codex opt-in host device-auth forwarding) and per-provider images (`Dockerfile.claude` / `Dockerfile.codex`, or a bottle-supplied Dockerfile) are configured on the bottle — see [Manifest](#manifest).
## 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.
@@ -70,27 +83,32 @@ 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.
## Quickstart
## Install
On compatible macOS hosts, the default backend requires Apple's `container` CLI and does not require Docker. The smolmachines backend requires Docker on the host for the sidecar bundle plus `smolvm` (macOS or Linux). 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 Apple Container is not installed and Docker is the desired backend.
### smolmachines on Linux
The smolmachines backend runs on Linux as well as macOS. On Linux, `smolvm`/libkrun use KVM, so the host 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.
- **`smolvm`** on `PATH`: `curl -sSL https://smolmachines.com/install.sh | sh`.
- **Docker** for the sidecar bundle and image build, same as macOS.
Per-bottle isolation works the same as macOS without any `ifconfig`/sudo step — all of `127.0.0.0/8` is already loopback on Linux, so each bottle's sidecar bundle is published on its own `127.0.0.<N>` and TSI's allowlist is scoped to that `/32`.
Install the CLI with the bootstrap script:
```sh
BOT_BOTTLE_BACKEND=smolmachines ./cli.py start <agent>
curl -fsSL https://gitea.dideric.is/didericis/bot-bottle/raw/branch/main/install.sh | sh
```
> **NixOS:** enable `virtualisation.docker`, ensure the KVM module is loaded (`boot.kernelModules = [ "kvm-intel" ];` or `kvm-amd`), and add your user to the `kvm` and `docker` groups. If you run bottles from a Gitea Actions runner, use a `host`-label runner so Docker, `smolvm`, and `/dev/kvm` are all reachable from the job. `smolvm` isn't in nixpkgs — install the release binary (pin the version) and put it on the runner's `PATH`.
The script checks Python 3.11+, checks Docker daemon reachability, creates the `~/.bot-bottle/` config directories, installs the Python package with `pipx` when available or `pip --user` otherwise, then runs:
```sh
bot-bottle doctor
```
Python-native installers can use the package metadata directly:
```sh
pipx install git+https://gitea.dideric.is/didericis/bot-bottle.git
uv tool install git+https://gitea.dideric.is/didericis/bot-bottle.git
```
## Quickstart
On compatible macOS hosts, the default backend requires Apple's `container` CLI and does not require Docker. The smolmachines backend requires Docker on the host for the sidecar bundle plus smolvm. 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 Apple Container is not installed and Docker is the desired backend.
```sh
./cli.py start <agent> # builds the image on first run, drops you into claude
@@ -166,11 +184,8 @@ You help maintain Gitea-hosted projects.
| `dlp` | no | Per-route DLP overrides. Omit to use defaults (all detectors on). |
| `dlp.outbound_detectors` | no | `false` disables outbound scanning; list restricts to named detectors (`token_patterns`, `known_secrets`). |
| `dlp.inbound_detectors` | no | `false` disables inbound scanning; list restricts to named detectors (`naive_injection_detection`). |
| `dlp.outbound_on_match` | no | What to do when an outbound token is detected: `supervise` (default for manifest routes — hold for operator approval), `redact` (scrub the value and forward), or `block` (hard 403). Agent-provider routes (e.g. `api.anthropic.com`) default to `redact`. |
| `git.fetch` | no | `true` permits smart HTTP clone/fetch (`git-upload-pack`) for this host. Push (`git-receive-pack`) remains blocked. |
When an outbound DLP detector matches a token, the route's `dlp.outbound_on_match` policy decides what happens. Under the default `supervise`, the proxy queues an `egress-token-allow` proposal for the operator's `./cli.py supervise` TUI and holds the request open until it is answered (or `EGRESS_TOKEN_ALLOW_TIMEOUT_SECONDS`, default 300s, elapses — after which it fails closed). The operator never sees the raw token, only the host, method, path, and a redacted snippet; approving adds the value to an in-memory safelist for the life of the egress proxy. Under `redact`, the matched value is scrubbed from the body, headers, and path and the request is forwarded (failing closed if a match lands somewhere unredactable, like the hostname). Under `block` it stays a hard `403`. Structural blocks (CRLF injection) and not-in-allowlist host blocks are always hard `403`s regardless of policy.
More examples in `examples/`. Full design lives under `docs/prds/`; the trust-boundary rationale is in `docs/prds/0011-per-file-md-manifest.md`.
## Trademarks
+96
View File
@@ -0,0 +1,96 @@
# Per-bottle sidecar bundle image (PRD 0024).
#
# Collapses the prior per-sidecar images (egress, git-gate,
# supervise) into one. A small stdlib-Python init supervisor at
# /app/sidecar_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.
#
# Layout:
#
# /usr/bin/gitleaks gitleaks binary
# /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
# /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
# /git-gate/creds/* docker-cp'd at start time
# /git/* bare repos, populated at runtime
# /run/supervise/queue/ bind-mounted at run time
# /home/mitmproxy/.mitmproxy/ mitmproxy CA dir
#
# Exposed ports inside the container:
# 9099 egress (mitmproxy, agent-facing HTTPS proxy)
# 9418 git-gate (git-daemon)
# 9420 git-gate smart HTTP (smolmachines agent-facing transport)
# 9100 supervise (MCP HTTP)
# Stage 1: gitleaks binary. The upstream gitleaks image is alpine
# with the binary at /usr/bin/gitleaks. Pinned by digest in lockstep
# with Dockerfile.git-gate's prior base (now deleted at chunk 3).
FROM zricethezav/gitleaks@sha256:c00b6bd0aeb3071cbcb79009cb16a60dd9e0a7c60e2be9ab65d25e6bc8abbb7f AS gitleaks-src
# Stage 2: assembly. mitmproxy/mitmproxy is debian-slim-based with
# Python + mitmdump pre-installed — heavier than the others, so
# this stage starts there and pulls the standalone binaries in.
FROM mitmproxy/mitmproxy:11.1.3
# Run as root inside the bundle. The bundle is the isolation
# boundary; per-daemon user separation inside it is not load-bearing
# and complicates the supervisor's spawn path.
USER root
# Runtime system deps:
# git supplies the `git daemon` subcommand (no separate package)
# plus the core `git` binary the pre-receive hook invokes.
# openssh-client supplies the upstream SSH transport the
# pre-receive hook uses to forward accepted refs.
# ca-certificates is needed for mitmdump upstream TLS (the
# base image already has it; listed for explicitness).
RUN apt-get update \
&& apt-get install -y --no-install-recommends \
git openssh-client ca-certificates \
&& rm -rf /var/lib/apt/lists/*
# Pull the standalone binaries into the final image.
COPY --from=gitleaks-src /usr/bin/gitleaks /usr/bin/gitleaks
# Project Python: addon + server modules + the init supervisor.
# Kept flat under /app/ so mitmdump's loader resolves them as
# top-level siblings (absolute imports), matching the prior
# Dockerfile.egress / Dockerfile.supervise layout.
COPY bot_bottle/egress_addon_core.py /app/egress_addon_core.py
COPY bot_bottle/egress_addon.py /app/egress_addon.py
COPY bot_bottle/dlp_detectors.py /app/dlp_detectors.py
COPY bot_bottle/yaml_subset.py /app/yaml_subset.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/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
# Pre-create runtime directories the compose renderer + start
# step expect to exist. `docker cp` does not create intermediate
# dirs, and bind mounts won't either if the parent is missing.
RUN mkdir -p \
/etc/egress \
/etc/git-gate \
/git-gate/creds \
/git \
/run/supervise/queue \
/home/mitmproxy/.mitmproxy
# Documentation only — the compose renderer publishes whichever
# subset the bottle uses.
EXPOSE 8888 9099 9418 9420 9100
# WORKDIR matches Dockerfile.supervise's prior layout so the
# in-app same-dir import in supervise_server.py stays deterministic.
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"]
+2 -10
View File
@@ -61,6 +61,7 @@ class AgentProviderRuntime:
prompt_mode: PromptMode
bypass_args: tuple[str, ...]
resume_args: tuple[str, ...]
remote_control_args: tuple[str, ...]
@dataclass(frozen=True)
@@ -370,15 +371,6 @@ def build_agent_provision_plan(
)
def provider_startup_args(
provider_settings: dict[str, object] | None,
) -> tuple[str, ...]:
raw = (provider_settings or {}).get("startup_args", ())
if not isinstance(raw, (list, tuple)):
return ()
return tuple(arg for arg in raw if isinstance(arg, str))
def prompt_args(
prompt_mode: PromptMode,
prompt_path: str | None,
@@ -390,7 +382,7 @@ def prompt_args(
if prompt_mode == "append_file":
return ["--append-system-prompt-file", prompt_path]
if prompt_mode == "read_prompt_file":
if argv and ("resume" in argv or "remote-control" in argv):
if argv and "resume" in argv:
return []
return [f"Read and follow the instructions in {prompt_path}."]
if prompt_mode == "print_read_prompt_file":
+5 -14
View File
@@ -72,9 +72,6 @@ class BottleSpec:
identity: str = ""
label: str = ""
color: str = ""
# Ordered bottle names selected at launch (issue #269). When non-empty
# they are merged in order and replace the agent's `bottle:` field.
bottle_names: tuple[str, ...] = ()
@dataclass(frozen=True)
@@ -112,8 +109,9 @@ class BottlePlan(ABC):
def workspace_plan(self) -> WorkspacePlan:
return workspace_plan(self.spec, guest_home=self.guest_home)
def print(self) -> None:
def print(self, *, remote_control: bool) -> None:
"""Render the y/N preflight summary to stderr."""
del remote_control
spec = self.spec
manifest = self.manifest
agent = manifest.agent
@@ -132,11 +130,7 @@ class BottlePlan(ABC):
info(f"provider : {self.agent_provision.template}")
print_multi("env ", env_names)
print_multi("skills ", list(agent.skills))
effective_bottles = (
list(spec.bottle_names) if spec.bottle_names
else ([agent.bottle] if agent.bottle else [])
)
print_multi("bottle ", effective_bottles)
info(f"bottle : {agent.bottle}")
identity = manifest.git_identity_summary()
if identity:
@@ -370,7 +364,7 @@ class BottleBackend(ABC, Generic[PlanT, CleanupT]):
Returns the loaded Manifest for the selected agent. Subclasses with
additional preconditions should override and call
`super()._validate(spec)` first."""
manifest = spec.manifest.load_for_agent(spec.agent_name, spec.bottle_names)
manifest = spec.manifest.load_for_agent(spec.agent_name)
self._validate_skills(manifest.agent.skills)
self._validate_agent_provider_dockerfile(spec, manifest)
return manifest
@@ -396,12 +390,9 @@ class BottleBackend(ABC, Generic[PlanT, CleanupT]):
if not path.is_absolute():
path = Path(spec.user_cwd) / path
if not path.is_file():
effective = (
", ".join(spec.bottle_names) if spec.bottle_names else manifest.agent.bottle
)
die(
f"agent_provider.dockerfile for bottle "
f"'{effective}' not found: {path}"
f"'{manifest.agent.bottle}' not found: {path}"
)
@abstractmethod
@@ -0,0 +1,211 @@
"""capability_apply — host-side orchestrator for capability-block
remediation (PRD 0016).
On approval of a capability-block proposal, the dashboard calls
apply_capability_change(slug, new_dockerfile) which:
1. Snapshots the agent's transcript dir to
~/.bot-bottle/state/<slug>/transcript/ (best-effort).
2. Pushes the agent's working tree via `git push` (best-effort —
no upstream / no commits / no git repo all skip with a log).
3. Writes the new Dockerfile to
~/.bot-bottle/state/<slug>/Dockerfile (PRD 0016 Phase 1
state). The next `cli.py start <agent>` picks it up.
4. Force-removes the agent container + all sidecars + the
per-bottle networks. Idempotent missing resources are not
errors.
Returns (before, after) Dockerfile contents so the dashboard can
record / render the diff. (capability-block has no audit log per
PRD 0013 the per-bottle Dockerfile state is its own record.)
This is "fire-and-forget" from the agent's perspective: by the time
the dashboard writes the response file the supervise sidecar is
gone, so the agent's tool call connection drops without ever
receiving the response. The replacement agent (next manual
`cli.py start`) sees the new Dockerfile and starts from there.
v1 does not auto-relaunch see PRD 0016's capability-block return
semantics open question.
"""
from __future__ import annotations
import shutil
import subprocess
from ...agent_provider import get_provider
from ...log import info, warn
from ...bottle_state import (
mark_preserved,
per_bottle_dockerfile,
transcript_snapshot_dir,
write_per_bottle_dockerfile,
)
from .sidecar_bundle import sidecar_bundle_container_name
# Agent home inside the container (per the repo Dockerfile's
# `USER node` + `WORKDIR /home/node`). Used to locate the transcript
# dir + the workspace dir for git push.
_AGENT_HOME_IN_CONTAINER = "/home/node"
_AGENT_TRANSCRIPT_IN_CONTAINER = f"{_AGENT_HOME_IN_CONTAINER}/.claude"
_AGENT_WORKSPACE_IN_CONTAINER = f"{_AGENT_HOME_IN_CONTAINER}/workspace"
# Per-bottle resource name patterns (mirroring prepare.py).
def _agent_container_name(slug: str) -> str:
return f"bot-bottle-{slug}"
def _per_bottle_container_names(slug: str) -> list[str]:
"""All container names that belong to this bottle. Missing
containers are silently skipped by the teardown helper, so it's
fine to include names that don't exist for a given bottle."""
return [
_agent_container_name(slug),
sidecar_bundle_container_name(slug),
]
def _per_bottle_network_names(slug: str) -> list[str]:
return [
f"bot-bottle-net-{slug}",
f"bot-bottle-egress-{slug}",
]
class CapabilityApplyError(RuntimeError):
"""Raised when the apply fails in a way that should keep the
proposal pending (so the operator can retry). Best-effort
failures (transcript snapshot, git push) do not raise they
just log and proceed."""
# --- Public helpers --------------------------------------------------------
def fetch_current_dockerfile(slug: str) -> str:
"""Return the Dockerfile content the next `cli.py start <agent>`
would use for this bottle. If a per-bottle override exists, that
one; otherwise the repo's Dockerfile.
Used by the operator-edit verb to show the current source of
truth, and by apply_capability_change for the before-diff."""
override = per_bottle_dockerfile(slug)
if override is not None:
return override
repo_dockerfile = get_provider("claude").dockerfile
if repo_dockerfile.is_file():
return repo_dockerfile.read_text()
raise CapabilityApplyError(
f"no per-bottle Dockerfile for {slug} and no provider Dockerfile at "
f"{repo_dockerfile}"
)
def apply_capability_change(slug: str, new_dockerfile: str) -> tuple[str, str]:
"""End-to-end capability-block remediation. See module docstring
for the sequence. Returns (before, after) Dockerfile content."""
if not new_dockerfile.strip():
raise CapabilityApplyError("proposed Dockerfile is empty")
before = fetch_current_dockerfile(slug)
snapshot_transcript(slug)
_push_working_tree(slug)
write_per_bottle_dockerfile(slug, new_dockerfile)
# Set the preserve marker BEFORE teardown so cli.py's session-end
# cleanup sees it and keeps the state dir intact for the
# operator's `cli.py resume <identity>`. Without the marker the
# state dir would be deleted as part of normal session end.
mark_preserved(slug)
_teardown_bottle(slug)
return before, new_dockerfile
# --- Internals -------------------------------------------------------------
def snapshot_transcript(slug: str) -> None:
"""`docker cp` /home/node/.claude out of the agent container into
~/.bot-bottle/state/<slug>/transcript/. Best-effort: missing
container, missing dir, or cp error all log a warning and return.
The transcript is what `claude --resume` reads to pick up where
the agent left off.
Called from two places:
- capability-apply, before tearing the bottle down.
- cli.py's session-end path, before the launch context closes,
so a crash or normal exit also leaves a transcript on disk
(deleted along with the state dir on clean exit, kept on
crash or capability-block per the preserve marker)."""
container = _agent_container_name(slug)
dest = transcript_snapshot_dir(slug)
if dest.exists():
# Remove any prior snapshot so the new one is a clean copy.
shutil.rmtree(dest, ignore_errors=True)
dest.parent.mkdir(parents=True, exist_ok=True)
r = subprocess.run(
["docker", "cp", f"{container}:{_AGENT_TRANSCRIPT_IN_CONTAINER}", str(dest)],
capture_output=True, text=True, check=False,
)
if r.returncode != 0:
warn(
f"transcript snapshot skipped "
f"({(r.stderr or '').strip() or 'no transcript dir in container?'})"
)
return
info(f"transcript snapshotted to {dest}")
def _push_working_tree(slug: str) -> None:
"""`docker exec <agent> git push` from /home/node/workspace.
Best-effort: not-a-git-repo, no upstream, nothing-to-push, no
network all log a warning and return. The replacement bottle
will pick up whatever's actually upstream."""
container = _agent_container_name(slug)
r = subprocess.run(
[
"docker", "exec", container, "sh", "-c",
f"cd {_AGENT_WORKSPACE_IN_CONTAINER} && "
f"git rev-parse --is-inside-work-tree >/dev/null 2>&1 && "
f"git push origin HEAD 2>&1 || true",
],
capture_output=True, text=True, check=False,
)
if r.returncode != 0:
warn(
f"capability-apply: git push skipped "
f"({(r.stderr or '').strip() or 'docker exec failed'})"
)
return
output = (r.stdout or "").strip()
if output:
info(f"capability-apply: git push: {output}")
else:
info("capability-apply: git push ran (no output — likely not a git workspace)")
def _teardown_bottle(slug: str) -> None:
"""Force-remove all per-bottle docker resources. Idempotent —
`docker rm -f` / `docker network rm` silently ignore missing
names, so this can be called even mid-rebuild."""
info(f"capability-apply: tearing down bottle {slug}")
for name in _per_bottle_container_names(slug):
subprocess.run(
["docker", "rm", "-f", name],
stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False,
)
for net in _per_bottle_network_names(slug):
subprocess.run(
["docker", "network", "rm", net],
stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False,
)
__all__ = [
"CapabilityApplyError",
"apply_capability_change",
"fetch_current_dockerfile",
"snapshot_transcript",
]
+21 -6
View File
@@ -28,12 +28,11 @@ 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 (
CURRENT_CONFIG_DIR_IN_AGENT,
QUEUE_DIR_IN_CONTAINER,
SUPERVISE_HOSTNAME,
SUPERVISE_PORT,
@@ -59,10 +58,17 @@ from .sidecar_bundle import (
)
# Repo root, used as the build context for the bundle Dockerfile.
# Repo root or installed site-packages root, used as the build context for
# Dockerfiles that COPY bot_bottle source files.
_REPO_DIR = str(Path(__file__).resolve().parent.parent.parent.parent)
def _sidecar_bundle_dockerfile() -> str:
if (Path(_REPO_DIR) / SIDECAR_BUNDLE_DOCKERFILE).is_file():
return SIDECAR_BUNDLE_DOCKERFILE
return f"bot_bottle/{SIDECAR_BUNDLE_DOCKERFILE}"
def bottle_plan_to_compose(plan: DockerBottlePlan) -> dict[str, Any]:
"""Render a Compose v2 spec dict from a fully-resolved
DockerBottlePlan.
@@ -136,7 +142,8 @@ def _sidecar_bundle_service(plan: DockerBottlePlan) -> dict[str, Any]:
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))
for token_env in sorted(ep.token_env_map.keys()):
env.append(token_env)
# --- git-gate -----------------------------------------------------
gp = plan.git_gate_plan
@@ -183,7 +190,7 @@ def _sidecar_bundle_service(plan: DockerBottlePlan) -> dict[str, Any]:
"image": SIDECAR_BUNDLE_IMAGE,
"build": {
"context": _REPO_DIR,
"dockerfile": SIDECAR_BUNDLE_DOCKERFILE,
"dockerfile": _sidecar_bundle_dockerfile(),
},
"container_name": sidecar_bundle_container_name(plan.slug),
"networks": {
@@ -220,7 +227,6 @@ def _agent_service(plan: DockerBottlePlan) -> dict[str, Any]:
# 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,
@@ -232,6 +238,15 @@ def _agent_service(plan: DockerBottlePlan) -> dict[str, Any]:
if plan.use_runsc:
service["runtime"] = "runsc"
volumes: list[dict[str, Any]] = []
if plan.supervise_plan is not None:
volumes.append(_bind(
plan.supervise_plan.current_config_dir,
CURRENT_CONFIG_DIR_IN_AGENT,
))
if volumes:
service["volumes"] = volumes
# The init supervisor inside the bundle owns intra-bundle
# daemon ordering, so the agent only waits for the bundle
# container itself.
+4 -3
View File
@@ -12,9 +12,10 @@ 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.
# Bundle image. Defaults to a built-locally tag. Source checkouts
# build from the repo-root Dockerfile.sidecars; installed packages
# build from the packaged copy under bot_bottle/.
# Operators pinning to a published digest can override via env.
SIDECAR_BUNDLE_IMAGE = os.environ.get(
"BOT_BOTTLE_SIDECAR_IMAGE",
"bot-bottle-sidecars:latest",
+2 -6
View File
@@ -11,7 +11,7 @@ from pathlib import Path
from ..bottle_state import egress_state_dir
from ..egress import EGRESS_ROUTES_FILENAME
from ..egress_addon_core import LOG_OFF, load_config
from ..egress_addon_core import load_routes
class EgressApplyError(RuntimeError):
@@ -33,15 +33,11 @@ class EgressApplicator(ABC):
@staticmethod
def validate_routes_content(content: str) -> None:
try:
config = load_config(content)
load_routes(content)
except ValueError as e:
raise EgressApplyError(
f"proposed routes.yaml is not valid: {e}"
) from e
if config.log != LOG_OFF:
raise EgressApplyError(
"proposed routes.yaml must not change egress logging"
)
@staticmethod
def _routes_path(slug: str) -> Path:
+4 -8
View File
@@ -22,12 +22,7 @@ from ...bottle_state import (
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 ...egress import EGRESS_ROUTES_IN_CONTAINER, egress_resolve_token_values
from ...git_gate import revoke_git_gate_provisioned_keys
from ...log import die, info, warn
from ...supervise import QUEUE_DIR_IN_CONTAINER, SUPERVISE_PORT
@@ -355,7 +350,9 @@ def _sidecar_daemons(plan: MacosContainerBottlePlan) -> tuple[str, ...]:
def _sidecar_env_entries(plan: MacosContainerBottlePlan) -> tuple[str, ...]:
env: list[str] = list(egress_sidecar_env_entries(plan.egress_plan))
env: list[str] = []
if plan.egress_plan.routes:
env.extend(sorted(plan.egress_plan.token_env_map.keys()))
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:
@@ -423,7 +420,6 @@ def _agent_env_entries(
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)
@@ -68,11 +68,6 @@ def build_image(ref: str, context: str, *, dockerfile: str = "") -> None:
_ensure_builder_dns()
args = [_CONTAINER, "build", "-t", ref, "--dns", dns_server()]
if dockerfile:
# `container build` resolves -f relative to the current working
# directory, not the build context. Anchor a relative Dockerfile to
# the context so builds work from any cwd.
if not os.path.isabs(dockerfile):
dockerfile = os.path.join(context, dockerfile)
args.extend(["-f", dockerfile])
args.append(context)
subprocess.run(args, check=True)
-1
View File
@@ -63,7 +63,6 @@ def write_launch_metadata(
backend=backend,
label=spec.label,
color=spec.color,
bottle_names=spec.bottle_names,
))
+20 -29
View File
@@ -23,9 +23,7 @@ from typing import Callable, Generator
from ...egress import (
EGRESS_ROUTES_IN_CONTAINER,
egress_agent_env_entries,
egress_resolve_token_values,
egress_sidecar_env_entries,
)
from ...supervise import QUEUE_DIR_IN_CONTAINER, SUPERVISE_PORT
from ...util import expand_tilde
@@ -141,12 +139,10 @@ def _allocate_resources(
) -> tuple[str, str]:
"""Reserve a loopback alias and create the per-bottle docker bridge.
The per-bottle alias scopes TSI's allowlist to this bottle's
published ports so the agent can't reach other bottles' or host
services' ports on loopback. On macOS `ensure_pool` first
sudo-aliases the pool on `lo0`; on Linux that's a no-op since
all of 127.0.0.0/8 is already loopback, but the per-bottle
allocation runs on both."""
macOS only routes 127.0.0.1 by default; the per-bottle alias
scopes TSI's allowlist to this bottle's published ports so the
agent can't reach other bottles' or host services' ports on
loopback. No-op on Linux."""
_loopback.ensure_pool()
loopback_ip = _loopback.allocate(plan.slug)
network = _bundle.bundle_network_name(plan.slug)
@@ -192,11 +188,9 @@ def _discover_urls(
return the plan with URLs + guest_env stamped in.
Docker container IPs (192.168.x.x in the daemon's bridge)
aren't reachable from the smolvm guest — TSI proxies the
guest's connects through the host, and the host reaches the
bundle only via its published-port loopback forward (the
daemon's bridge isn't on the TSI allowlist). The agent dials
the published port on the per-bottle loopback alias.
aren't reachable from the smolvm guest on macOS — TSI uses
macOS networking, and macOS sees the daemon's bridge via the
published-port loopback forward only.
NO_PROXY includes the per-bottle loopback alias so the
supervise + git-gate URLs bypass HTTPS_PROXY."""
@@ -234,9 +228,6 @@ def _discover_urls(
guest_env["GIT_GATE_URL"] = f"http://{agent_git_gate_host}"
if agent_supervise_url:
guest_env["MCP_SUPERVISE_URL"] = agent_supervise_url
for entry in egress_agent_env_entries(plan.egress_plan):
name, value = entry.split("=", 1)
guest_env[name] = value
return dataclasses.replace(
plan,
@@ -256,11 +247,10 @@ def _launch_vm(
"""Create, patch, and start the smolvm VM; register teardown.
--allow-cidr is the per-bottle loopback alias so the guest can
only reach this bottle's bundle ports. force_allowlist then
confirms the allowlist persisted (patching smolvm 0.8.0's
silent-drop of --allow-cidr when combined with --from) and
fails closed if it can't. Smolfile isn't usable here smolvm
0.8.0 makes --from and --smolfile mutually exclusive."""
only reach this bottle's bundle ports. force_allowlist patches
smolvm 0.8.0's silent-drop of --allow-cidr when combined with
--from. Smolfile isn't usable here — smolvm 0.8.0 makes --from
and --smolfile mutually exclusive."""
_smolvm.machine_create(
plan.machine_name,
from_path=agent_from_path,
@@ -268,10 +258,9 @@ def _launch_vm(
env=plan.guest_env,
)
stack.callback(_smolvm.machine_delete, plan.machine_name)
# Confirm the booted VM's TSI allowlist will actually enforce the
# /32 before start (smolvm 0.8.0 silently drops `--allow-cidr`
# with `--from`, so the persisted state DB is patched if needed).
# Fails closed if enforcement can't be confirmed.
# Workaround smolvm 0.8.0: `--allow-cidr` is silently dropped
# when combined with `--from`. Patch the persisted state DB
# before start so the booted VM's TSI actually enforces.
_loopback.force_allowlist(plan.machine_name, [f"{loopback_ip}/32"])
_smolvm.machine_start(plan.machine_name)
stack.callback(_smolvm.machine_stop, plan.machine_name)
@@ -281,9 +270,7 @@ def _init_vm(plan: SmolmachinesBottlePlan) -> None:
"""Repair filesystem ownership and wait for exec channel readiness.
Ownership repair: smolvm's pack process remaps files to the host
invoker's uid (e.g. 501 on macOS, 1000 on Linux). The chowns use
names not numbers so they're correct on either. /home/node must
be node:node so
invoker's uid (501 on macOS). /home/node must be node:node so
Claude Code can write ~/.claude.json; /tmp + /var/tmp need root
mode 1777 so non-root processes can create per-uid scratch dirs.
All folded into one sh -c to avoid back-to-back exec calls
@@ -329,7 +316,11 @@ def _bundle_launch_spec(
volumes.append((str(ep.mitmproxy_ca_host_path), EGRESS_CA_IN_CONTAINER, True))
if ep.routes:
volumes.append((str(ep.routes_path.parent), str(Path(EGRESS_ROUTES_IN_CONTAINER).parent), True))
env.extend(egress_sidecar_env_entries(ep))
# Bare-name entries for upstream-token slots. Their values
# come from the docker-run subprocess env (inherited from
# the operator's shell), never landing on argv.
for token_env in sorted(ep.token_env_map.keys()):
env.append(token_env)
# --- git-gate ---------------------------------------------
gp = plan.git_gate_plan
@@ -33,13 +33,10 @@ sudo-add the missing pool on first use per boot — the aliases
persist on `lo0` until reboot, so subsequent launches don't
prompt.
On Linux the whole `127.0.0.0/8` is already routed to `lo`, so
docker can publish a bundle's ports directly on `127.0.0.<N>`
with no `ifconfig`/sudo step. `ensure_pool` is therefore a no-op
on Linux, but per-bottle alias *allocation* and the TSI allowlist
DB patch run on both platforms the isolation property is
identical, it's just cheaper to set up on Linux. The state-DB
path differs per platform (see `_smolvm_db_path`).
Linux native daemons share the host's network namespace; the
whole `127.0.0.0/8` is reachable by default and aliases are
unnecessary. The pool logic detects native-Linux and skips sudo
entirely; the DB patch is also gated on macOS.
Allocation is coordinated by inspecting running bundle
containers' published host IPs — each bottle's bundle owns the
@@ -50,7 +47,6 @@ from __future__ import annotations
import fcntl
import json
import os
import platform
import re
import sqlite3
@@ -61,34 +57,20 @@ from typing import Iterable
from ...log import die, info
def _smolvm_db_path() -> Path:
"""smolvm's persistent VM state — a SQLite DB whose `vms` table
holds one JSON BLOB per machine. macOS stores it under
`Application Support`; Linux follows the XDG base-dir spec
(`$XDG_DATA_HOME`, default `~/.local/share`).
NOTE: the Linux location is inferred from smolvm's documented
`~/.local/share` install layout and must be confirmed against a
real Linux smolvm install. If it's wrong, `force_allowlist`'s
fail-closed check turns it into a clear launch-time error rather
than a silent escape."""
if platform.system() == "Darwin":
return (
Path.home()
/ "Library"
/ "Application Support"
/ "smolvm"
/ "server"
/ "smolvm.db"
)
xdg_data = os.environ.get("XDG_DATA_HOME")
base = Path(xdg_data) if xdg_data else Path.home() / ".local" / "share"
return base / "smolvm" / "server" / "smolvm.db"
# Resolved once at import: the host platform doesn't change within a
# process. Tests patch this attribute directly.
_SMOLVM_DB_PATH = _smolvm_db_path()
# smolvm's persistent VM state on macOS — a SQLite DB whose `vms`
# table holds one JSON BLOB per machine. The Linux path is
# different, but smolmachines is macOS-only in v1 (PRD 0023) so
# we hard-code this. If the file moves under us we'll see a
# clear FileNotFoundError; not worth defensive cross-platform
# detection until the backend actually needs Linux.
_SMOLVM_DB_PATH = (
Path.home()
/ "Library"
/ "Application Support"
/ "smolvm"
/ "server"
/ "smolvm.db"
)
# Sixteen aliases by default. Tunable for hosts that want more
@@ -149,74 +131,51 @@ def ensure_pool() -> None:
def force_allowlist(machine_name: str, allowed_cidrs: list[str]) -> None:
"""Ensure the machine's persisted TSI allowlist equals
`allowed_cidrs`, failing **closed** if that can't be confirmed.
"""Patch smolvm's persistent VM-state DB to set the machine's
`allowed_cidrs` to the given list. Workaround for smolvm
0.8.0's silent-drop of `--allow-cidr` when used with `--from`.
Runs on both macOS and Linux. It exists because smolvm 0.8.0
silently drops `--allow-cidr` when combined with `--from`, so
the allowlist has to be written into smolvm's persistent state
DB before `machine start`. Rather than assume the flag was
dropped, we read the persisted row and only patch when it
doesn't already match — so a newer smolvm that honors the flag
is left untouched.
Must run AFTER `smolvm machine create` (the row has to
exist) and BEFORE `smolvm machine start` (smolvm reads the
row on start; in-flight VMs don't pick up changes). Once
smolvm honors the CLI flag upstream this whole function is
redundant flag-respecting create + remove this call from
launch.
Must run AFTER `smolvm machine create` (the row has to exist)
and BEFORE `smolvm machine start` (smolvm reads the row on
start; in-flight VMs don't pick up changes).
Fail-closed: if the state DB is missing, the row is missing, or
the allowlist still doesn't match after patching, we `die()`
rather than boot a VM whose egress confinement we can't verify
an unconfirmed allowlist is a sandbox-escape risk (the agent
VM could reach all of host loopback)."""
want = list(allowed_cidrs)
No-op on non-macOS the DB path differs and the Linux
smolmachines code path isn't exercised in v1."""
if not _is_macos():
return
if not _SMOLVM_DB_PATH.is_file():
die(
f"smolvm state DB not found at {_SMOLVM_DB_PATH}; cannot "
f"confirm the TSI allowlist is enforced. Refusing to launch "
f"(fail-closed). Check `smolvm --version` and the DB "
f"location for your platform."
f"smolvm state DB not found at {_SMOLVM_DB_PATH}. "
f"smolvm 0.8.0 expected? `smolvm --version` to check."
)
con = sqlite3.connect(str(_SMOLVM_DB_PATH))
try:
cfg = _read_machine_cfg(con, machine_name)
if cfg.get("allowed_cidrs") != want:
cfg["allowed_cidrs"] = want
# Write as BLOB (the column type smolvm uses) — passing a
# plain str makes sqlite store it as Text and smolvm then
# fails to read it.
con.execute(
"UPDATE vms SET data = ? WHERE name = ?",
(sqlite3.Binary(json.dumps(cfg).encode()), machine_name),
)
con.commit()
cfg = _read_machine_cfg(con, machine_name)
if cfg.get("allowed_cidrs") != want:
cur = con.cursor()
row = cur.execute(
"SELECT data FROM vms WHERE name = ?", (machine_name,),
).fetchone()
if row is None:
die(
f"could not enforce TSI allowlist {want!r} for machine "
f"{machine_name!r} (persisted value is "
f"{cfg.get('allowed_cidrs')!r}). Refusing to launch "
f"(fail-closed)."
f"smolvm DB has no row for machine {machine_name!r} "
f"machine_create must run before force_allowlist."
)
cfg = json.loads(row[0])
cfg["allowed_cidrs"] = list(allowed_cidrs)
# Write as BLOB (the column type smolvm uses) — passing a
# plain str makes sqlite store it as Text and smolvm then
# fails to read it.
cur.execute(
"UPDATE vms SET data = ? WHERE name = ?",
(sqlite3.Binary(json.dumps(cfg).encode()), machine_name),
)
con.commit()
finally:
con.close()
def _read_machine_cfg(con: sqlite3.Connection, machine_name: str) -> dict[str, object]:
"""Read + JSON-decode a machine's `data` BLOB from the smolvm
state DB. Dies (fail-closed) if the row is missing the caller
can't confirm enforcement without it."""
row = con.execute(
"SELECT data FROM vms WHERE name = ?", (machine_name,),
).fetchone()
if row is None:
die(
f"smolvm DB has no row for machine {machine_name!r}"
f"machine_create must run before force_allowlist."
)
return json.loads(row[0])
def allocate(_slug: str) -> str:
"""Pick the lowest-numbered alias from the pool not already
in use by a running smolmachines bundle. Bails when the pool
@@ -225,17 +184,16 @@ def allocate(_slug: str) -> str:
used (no on-disk reservation, allocation is purely
docker-state-driven).
Runs on both platforms: the allocation logic (docker-state
inspection + the file lock) is platform-independent. macOS
needs `ensure_pool` to have aliased the addresses on `lo0`
first; on Linux all of `127.0.0.0/8` is already loopback, so
docker can publish on the chosen `127.0.0.<N>` with no setup.
Per-bottle scoping (so the agent can't reach other bottles' or
host services' loopback ports) therefore holds on both.
On non-macOS the whole `127.0.0.0/8` is loopback by default;
`127.0.0.1` is fine to share and we skip the alias dance.
This still returns a deterministic address so launch.py's
callers don't have to branch on platform.
An exclusive file lock serialises concurrent calls so two
simultaneous launches don't read the same docker state and
claim the same alias."""
if not _is_macos():
return "127.0.0.1"
_ALLOC_LOCK_PATH.parent.mkdir(parents=True, exist_ok=True)
with open(_ALLOC_LOCK_PATH, "w", encoding="utf-8") as lf:
fcntl.flock(lf, fcntl.LOCK_EX)
+14 -46
View File
@@ -5,58 +5,26 @@ unit-tested without importing the docker subprocess paths."""
from __future__ import annotations
import hashlib
import os
import platform
import shutil
from ...log import die
# libkrun's Linux backend drives the guest through KVM, so the host
# must expose `/dev/kvm` and the invoking user must be able to open
# it. macOS uses Hypervisor.framework and needs no device node.
_KVM_DEVICE = "/dev/kvm"
def smolmachines_preflight() -> None:
"""Ensure the host can run the smolmachines backend before the
launch flow starts. Called from `_resolve_plan`; surfaces a
clear, actionable error instead of a cryptic `smolvm` failure
deep in launch.
Checks `smolvm` is on PATH (both platforms) and, on Linux,
that `/dev/kvm` exists and is accessible. `gvproxy` is no
longer required see the PRD's design pivot section."""
if shutil.which("smolvm") is None:
die(
"BOT_BOTTLE_BACKEND=smolmachines requires `smolvm` on "
"PATH. Install with: "
"curl -sSL https://smolmachines.com/install.sh | sh. "
"To use the legacy Docker backend instead, set "
"BOT_BOTTLE_BACKEND=docker or pass --backend=docker."
)
if platform.system() == "Linux":
_preflight_kvm()
def _preflight_kvm() -> None:
"""Linux-only: libkrun needs `/dev/kvm`. Distinguish 'KVM not
enabled' from 'no permission' so the operator knows which to
fix."""
if not os.path.exists(_KVM_DEVICE):
die(
f"BOT_BOTTLE_BACKEND=smolmachines needs {_KVM_DEVICE} on "
"Linux but it is missing. Enable KVM: load the kvm-intel "
"or kvm-amd kernel module (and confirm virtualization is "
"enabled in BIOS/firmware). To use the legacy Docker "
"backend instead, set BOT_BOTTLE_BACKEND=docker."
)
if not os.access(_KVM_DEVICE, os.R_OK | os.W_OK):
die(
f"{_KVM_DEVICE} exists but is not readable/writable by the "
"current user. Add your user to the `kvm` group "
"(`sudo usermod -aG kvm \"$USER\"`) and re-login, or run "
"with access to the device."
)
"""Ensure `smolvm` is on PATH before the launch flow runs.
Called from `_resolve_plan`; gives the operator a clear
install pointer rather than a cryptic FileNotFoundError
later. `gvproxy` is no longer required see the PRD's design
pivot section."""
if shutil.which("smolvm") is not None:
return
die(
"BOT_BOTTLE_BACKEND=smolmachines requires `smolvm` on "
"PATH. Install with: "
"curl -sSL https://smolmachines.com/install.sh | sh. "
"To use the legacy Docker backend instead, set "
"BOT_BOTTLE_BACKEND=docker or pass --backend=docker."
)
def smolmachines_bundle_subnet(slug: str) -> tuple[str, str, str]:
+16 -19
View File
@@ -1,7 +1,8 @@
"""Per-bottle persistent state.
"""Per-bottle persistent state (PRD 0016).
Holds optional per-bottle Dockerfile overrides, the transcript snapshot
the state-preservation helper saves before teardown, and the launch metadata that lets
Holds the per-bottle Dockerfile override that capability-block
remediation writes, the transcript snapshot the state-preservation
helper saves before teardown, and the launch metadata that lets
`cli.py resume <identity>` reconstruct a bottle's spec. State
lives at:
@@ -60,7 +61,7 @@ _METADATA_NAME = "metadata.json"
_LIVE_CONFIG_SUBDIR = "live-config"
LIVE_CONFIG_ROUTES_NAME = "routes.yaml"
LIVE_CONFIG_ALLOWLIST_NAME = "allowlist"
# Empty marker file. Session preservation writes it before teardown so
# Empty marker file. capability_apply writes it before teardown so
# cli.py's session-end cleanup knows to preserve the state dir for
# `cli.py resume <identity>`. Absent = clean up.
_PRESERVE_MARKER = ".preserve"
@@ -111,10 +112,6 @@ class BottleMetadata:
backend: str = ""
label: str = ""
color: str = ""
# Ordered bottle names selected at launch (issue #269). Empty tuple
# for state dirs written before this change; resume falls back to
# the agent's `bottle:` field in that case.
bottle_names: tuple[str, ...] = ()
def metadata_path(identity: str) -> Path:
@@ -142,10 +139,6 @@ def read_metadata(identity: str) -> BottleMetadata | None:
if not isinstance(raw, dict):
return None
raw_typed = cast(dict[str, object], raw)
raw_bottle_names = raw_typed.get("bottle_names", [])
bottle_names: tuple[str, ...] = ()
if isinstance(raw_bottle_names, list):
bottle_names = tuple(str(n) for n in raw_bottle_names if isinstance(n, str))
return BottleMetadata(
identity=str(raw_typed.get("identity", identity)),
agent_name=str(raw_typed.get("agent_name", "")),
@@ -156,7 +149,6 @@ def read_metadata(identity: str) -> BottleMetadata | None:
backend=str(raw_typed.get("backend", "")),
label=str(raw_typed.get("label", "")),
color=str(raw_typed.get("color", "")),
bottle_names=bottle_names,
)
@@ -172,7 +164,8 @@ def per_bottle_dockerfile_path(identity: str) -> Path:
def per_bottle_dockerfile(identity: str) -> str | None:
"""Return the per-bottle Dockerfile content if present, else
None. None means: use the provider or manifest Dockerfile."""
None. None means: use the repo's Dockerfile (the original
pre-capability-block behavior)."""
p = per_bottle_dockerfile_path(identity)
if p.is_file():
return p.read_text()
@@ -256,7 +249,9 @@ def write_live_config(
def transcript_snapshot_dir(identity: str) -> Path:
"""Where agent session snapshots are kept for resume flows."""
"""Where capability_apply stashes the agent's transcript before
teardown, so the next `cli.py start <agent>` can offer to
resume from it."""
return bottle_state_dir(identity) / _TRANSCRIPT_SUBDIR
@@ -283,7 +278,8 @@ def git_gate_state_dir(identity: str) -> Path:
def supervise_state_dir(identity: str) -> Path:
"""State subdir reserved for supervise sidecar bind-mount sources.
"""State subdir for the supervise sidecar's current-config dir
(bind-mounted into the agent at /etc/bot-bottle/current-config).
The queue dir is intentionally NOT under here it lives at
~/.bot-bottle/queue/<slug>/ alongside the audit logs, so it
survives state-dir cleanup."""
@@ -305,8 +301,9 @@ def preserve_marker_path(identity: str) -> Path:
def mark_preserved(identity: str) -> Path:
"""Mark this bottle's state for preservation across session
teardown so cli.py's session-end cleanup leaves the state dir
intact for a subsequent `cli.py resume`."""
teardown. Written by capability_apply.apply_capability_change so
cli.py's session-end cleanup leaves the state dir intact for a
subsequent `cli.py resume`."""
path = preserve_marker_path(identity)
path.parent.mkdir(parents=True, exist_ok=True)
path.touch()
@@ -319,7 +316,7 @@ def is_preserved(identity: str) -> bool:
def clear_preserve_marker(identity: str) -> None:
"""Idempotent removal. Called at fresh launch (start or resume)
so a marker left from a prior preserved session doesn't keep
so a marker left from a prior capability-block doesn't keep
state alive past the next normal session-end."""
try:
preserve_marker_path(identity).unlink()
+4 -1
View File
@@ -1,6 +1,6 @@
"""Main CLI dispatcher.
Commands: cleanup, commit, edit, info, init, list, resume, start, supervise
Commands: cleanup, commit, doctor, edit, info, init, list, resume, start, supervise
"""
from __future__ import annotations
@@ -13,6 +13,7 @@ from ._common import PROG
from . import list as _list_mod
from .cleanup import cmd_cleanup
from .commit import cmd_commit
from .doctor import cmd_doctor
from .edit import cmd_edit
from .info import cmd_info
from .init import cmd_init
@@ -25,6 +26,7 @@ cmd_list = _list_mod.cmd_list
COMMANDS = {
"cleanup": cmd_cleanup,
"commit": cmd_commit,
"doctor": cmd_doctor,
"edit": cmd_edit,
"info": cmd_info,
"init": cmd_init,
@@ -40,6 +42,7 @@ def usage() -> None:
sys.stderr.write("Commands:\n")
sys.stderr.write(" cleanup stop and remove all active bot-bottle containers\n")
sys.stderr.write(" commit snapshot a running bottle's container state to a Docker image\n")
sys.stderr.write(" doctor check Python, Docker, and bot-bottle config prerequisites\n")
sys.stderr.write(" edit open an agent in vim for editing\n")
sys.stderr.write(" info print env, skills, and prompt details for a named agent\n")
sys.stderr.write(" init interactively create a new agent and add it to bot-bottle.json\n")
+1 -1
View File
@@ -6,7 +6,7 @@ import os
import sys
from pathlib import Path
PROG = "cli.py"
PROG = Path(sys.argv[0]).name or "bot-bottle"
USER_CWD = os.getcwd()
REPO_DIR = str(Path(__file__).resolve().parent.parent.parent)
+3 -2
View File
@@ -13,8 +13,9 @@ dirs are shared layout, so docker is the single owner of that
bucket.
State dirs with `.preserve` are intentionally never touched they
hold preserved sessions the operator may want to `resume`. Manual
`rm -rf ~/.bot-bottle/state/<identity>` is the path for those.
hold capability-block rebuilds or crash snapshots the operator may
want to `resume`. Manual `rm -rf ~/.bot-bottle/state/<identity>`
is the path for those.
"""
from __future__ import annotations
+73
View File
@@ -0,0 +1,73 @@
"""doctor: validate host prerequisites for running bot-bottle."""
from __future__ import annotations
import argparse
import shutil
import subprocess
import sys
from pathlib import Path
from ._common import PROG
def _ok(label: str, detail: str) -> None:
print(f"ok: {label}: {detail}")
def _fail(label: str, detail: str) -> None:
print(f"fail: {label}: {detail}")
def _check_python() -> bool:
version = sys.version_info
detail = f"{version.major}.{version.minor}.{version.micro}"
if version >= (3, 11):
_ok("python", detail)
return True
_fail("python", f"{detail}; need 3.11 or newer")
return False
def _check_docker() -> bool:
docker = shutil.which("docker")
if not docker:
_fail("docker", "docker command not found")
return False
try:
result = subprocess.run(
[docker, "info"],
stdout=subprocess.DEVNULL,
stderr=subprocess.DEVNULL,
check=False,
timeout=10,
)
except (OSError, subprocess.TimeoutExpired) as exc:
_fail("docker", f"daemon check failed: {exc}")
return False
if result.returncode == 0:
_ok("docker", "daemon reachable")
return True
_fail("docker", "daemon not reachable")
return False
def _check_config_dir() -> bool:
config = Path.home() / ".bot-bottle"
if config.is_dir():
_ok("config", str(config))
return True
_fail("config", f"{config} does not exist")
return False
def cmd_doctor(argv: list[str]) -> int:
parser = argparse.ArgumentParser(prog=f"{PROG} doctor", add_help=True)
parser.parse_args(argv)
checks = (
_check_python(),
_check_docker(),
_check_config_dir(),
)
return 0 if all(checks) else 1
+7 -5
View File
@@ -4,12 +4,13 @@ Reads ~/.bot-bottle/state/<identity>/metadata.json to recover the
(agent_name, cwd, copy_cwd) the bottle was originally started with,
then runs the same launch core as `start` but pinned to the
recorded identity so the new bottle picks up any per-bottle Dockerfile
override and transcript snapshot under the same state dir.
(from capability-block apply) and transcript snapshot under the same
state dir.
Use case: an interrupted or preserved bottle needs to be relaunched;
the operator runs
Use case: an agent calls capability-block, the dashboard approves
and tears down the bottle, the operator runs
./cli.py resume <identity>
to bring up the replacement from the recorded state.
to bring up the replacement with the new capabilities baked in.
"""
from __future__ import annotations
@@ -27,6 +28,7 @@ from .start import _launch_bottle
def cmd_resume(argv: list[str]) -> int:
parser = argparse.ArgumentParser(prog=f"{PROG} resume", add_help=True)
parser.add_argument("--dry-run", action="store_true")
parser.add_argument("--remote-control", action="store_true")
parser.add_argument(
"identity",
help="bottle identity from a prior `start` (see its session-end output)",
@@ -49,11 +51,11 @@ def cmd_resume(argv: list[str]) -> int:
copy_cwd=metadata.copy_cwd,
user_cwd=metadata.cwd or USER_CWD,
identity=metadata.identity,
bottle_names=tuple(metadata.bottle_names),
)
backend_name = metadata.backend or None
return _launch_bottle(
spec,
dry_run=args.dry_run,
remote_control=args.remote_control,
backend_name=backend_name,
)
+18 -159
View File
@@ -31,8 +31,9 @@ from ..bottle_state import (
is_preserved,
mark_preserved,
)
# from ..backend.docker.capability_apply import snapshot_transcript
from ..log import info
from ..manifest import Manifest, ManifestIndex
from ..manifest import ManifestIndex
from ._common import PROG, USER_CWD, read_tty_line
from . import tui
@@ -41,6 +42,7 @@ 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("--remote-control", action="store_true")
parser.add_argument(
"--backend",
choices=known_backend_names(),
@@ -73,23 +75,6 @@ def cmd_start(argv: list[str]) -> int:
backend_name: str | None = args.backend
# Bottle multiselect: always show after agent selection so operators
# can compose bottles at launch time without editing agent manifests.
available_bottles = manifest.all_bottle_names
lineage_map = _bottle_lineage(manifest)
display_labels = [lineage_map.get(n, n) for n in available_bottles]
label_to_name = {lineage_map.get(n, n): n for n in available_bottles}
initial_bottle = _peek_agent_bottle(manifest, agent_name)
initial_labels = [lineage_map.get(initial_bottle, initial_bottle)] if initial_bottle else []
selected_labels = tui.filter_multiselect(
display_labels,
title="Select bottles",
initial=initial_labels,
)
if selected_labels is None:
return 0
bottle_names = tuple(label_to_name.get(lbl, lbl) for lbl in selected_labels)
label, color = tui.name_color_modal(default_label=agent_name)
label, color = _resolve_unique_label(label, color)
@@ -100,11 +85,11 @@ def cmd_start(argv: list[str]) -> int:
user_cwd=USER_CWD,
label=label,
color=color,
bottle_names=bottle_names,
)
return _launch_bottle(
spec,
dry_run=dry_run,
remote_control=args.remote_control,
backend_name=backend_name,
)
@@ -149,7 +134,7 @@ def prepare_with_preflight(
def attach_agent(
bottle: Bottle, *, resume: bool = False,
bottle: Bottle, *, remote_control: bool = False, resume: bool = False,
agent_provider_template: str = "claude",
startup_args: tuple[str, ...] = (),
) -> int:
@@ -168,6 +153,8 @@ def attach_agent(
"(Ctrl-D or 'exit' to leave; container will be removed)"
)
agent_args = list(runtime.bypass_args)
if remote_control:
agent_args.extend(runtime.remote_control_args)
agent_args.extend(startup_args)
if resume:
agent_args.extend(runtime.resume_args)
@@ -207,38 +194,6 @@ def _identity_from_plan(plan: object) -> str:
return getattr(plan, "slug", "")
def _peek_agent_bottle(manifest: ManifestIndex, agent_name: str) -> str:
"""Return the `bottle:` value from the named agent's frontmatter without
fully parsing the agent file, or "" when absent or unreadable.
Used to pre-populate the bottle multiselect with the agent's default
bottle so operators who haven't removed `bottle:` from their manifests
don't need to re-select it every time."""
if manifest.home_md is None:
# Eager mode (from_json_obj): agent is pre-parsed.
if agent_name in manifest.agents:
return manifest.agents[agent_name].bottle
return ""
from ..manifest_loader import scan_agent_names
from ..yaml_subset import YamlSubsetError, parse_frontmatter
home_agents = scan_agent_names(manifest.home_md / "agents")
cwd_agents: dict[str, Path] = {}
if manifest.cwd_md is not None:
cwd_agents = scan_agent_names(manifest.cwd_md / "agents")
merged = {**home_agents, **cwd_agents}
path = merged.get(agent_name)
if path is None:
return ""
try:
fm, _ = parse_frontmatter(path.read_text())
bottle = fm.get("bottle", "")
return str(bottle) if isinstance(bottle, str) else ""
except (OSError, YamlSubsetError):
return ""
def _resolve_unique_label(label: str, color: str) -> tuple[str, str]:
"""Re-prompt with a disclaimer until the label's slug is not already
in use among running bottles. Passes through unchanged when no
@@ -263,118 +218,17 @@ def _text_prompt_yes() -> bool:
return reply in ("y", "Y", "yes", "YES")
def _text_render_preflight():
def _text_render_preflight(*, remote_control: bool):
def _render(plan: DockerBottlePlan) -> None:
print(file=sys.stderr)
print(_manifest_to_yaml(plan.manifest), file=sys.stderr)
plan.print(remote_control=remote_control)
return _render
def _bottle_lineage(manifest: ManifestIndex) -> dict[str, str]:
"""Return {bottle_name: lineage_label} for bottles that have an extends chain.
Bottles without a parent are omitted (the caller falls back to the bare name).
Labels show the chain root-first: e.g. 'dev -> bot-bottle-dev -> claude-dev'."""
if manifest.home_md is None:
return {}
bottles_dir = manifest.home_md / "bottles"
if not bottles_dir.is_dir():
return {}
from ..yaml_subset import YamlSubsetError, parse_frontmatter
extends_of: dict[str, str] = {}
for path in bottles_dir.glob("*.md"):
try:
fm, _ = parse_frontmatter(path.read_text())
parent = fm.get("extends", "")
if isinstance(parent, str) and parent:
extends_of[path.stem] = parent
except (OSError, YamlSubsetError):
pass
labels: dict[str, str] = {}
for name in extends_of:
chain = [name]
seen = {name}
cur = name
while cur in extends_of:
par = extends_of[cur]
if par in seen:
break
chain.append(par)
seen.add(par)
cur = par
labels[name] = " -> ".join(reversed(chain))
return labels
def _manifest_to_yaml(manifest: Manifest) -> str:
"""Serialize the resolved Manifest to a YAML string for preflight display."""
lines: list[str] = []
agent = manifest.agent
lines.append("agent:")
if agent.skills:
lines.append(" skills:")
for s in agent.skills:
lines.append(f" - {s}")
if not agent.git_user.is_empty():
lines.append(" git-gate:")
lines.append(" user:")
if agent.git_user.name:
lines.append(f" name: {agent.git_user.name}")
if agent.git_user.email:
lines.append(f" email: {agent.git_user.email}")
bottle = manifest.bottle
lines.append("bottle:")
if bottle.agent_provider.template != "claude" or bottle.agent_provider.dockerfile:
lines.append(" agent_provider:")
lines.append(f" template: {bottle.agent_provider.template}")
if bottle.agent_provider.dockerfile:
lines.append(f" dockerfile: {bottle.agent_provider.dockerfile}")
if bottle.env:
lines.append(" env:")
for k, v in sorted(bottle.env.items()):
lines.append(f" {k}: {v}")
has_git_gate = not bottle.git_user.is_empty() or bottle.git
if has_git_gate:
lines.append(" git-gate:")
if not bottle.git_user.is_empty():
lines.append(" user:")
if bottle.git_user.name:
lines.append(f" name: {bottle.git_user.name}")
if bottle.git_user.email:
lines.append(f" email: {bottle.git_user.email}")
if bottle.git:
lines.append(" repos:")
for entry in bottle.git:
lines.append(f" {entry.Name}:")
lines.append(f" url: {entry.Upstream}")
if bottle.egress.routes:
lines.append(" egress:")
lines.append(" routes:")
for r in bottle.egress.routes:
lines.append(f" - host: {r.Host}")
if r.AuthScheme:
lines.append(f" auth:")
lines.append(f" scheme: {r.AuthScheme}")
lines.append(f" supervise: {'true' if bottle.supervise else 'false'}")
return "\n".join(lines)
def _launch_bottle(
spec: BottleSpec,
*,
dry_run: bool,
remote_control: bool,
backend_name: str | None = None,
) -> int:
"""Shared launch core for `start` and `resume`. Builds the plan,
@@ -386,7 +240,7 @@ def _launch_bottle(
plan, identity = prepare_with_preflight(
spec,
stage_dir=stage_dir,
render_preflight=_text_render_preflight(),
render_preflight=_text_render_preflight(remote_control=remote_control),
prompt_yes=_text_prompt_yes,
dry_run=dry_run,
backend_name=backend_name,
@@ -399,6 +253,7 @@ def _launch_bottle(
agent_provider_template = getattr(plan, "agent_provider_template", "claude")
exit_code = attach_agent(
bottle,
remote_control=remote_control,
agent_provider_template=agent_provider_template,
startup_args=plan.agent_provision.startup_args,
)
@@ -408,8 +263,12 @@ def _launch_bottle(
)
# While the container is still alive: always snapshot the
# transcript and — if the agent exited non-zero — mark
# the state for preservation. This picks up crashes /
# Ctrl-Cs / OOM kills before cleanup removes the state dir.
# the state for preservation. Capability-block already
# did both before triggering teardown from the dashboard;
# this picks up crashes / Ctrl-Cs / OOM kills the same
# way. snapshot_transcript is best-effort so the
# capability-block path's prior snapshot isn't clobbered
# when the container is already gone.
if agent_provider_template == "claude":
capture_claude_session_state(identity, exit_code)
return 0
+46 -28
View File
@@ -2,8 +2,9 @@
act on them (approve / modify / reject).
Curses-based TUI; modify-then-approve shells out to $EDITOR. The
Egress proposals are queued for operator review as full routes.yaml
updates.
approval handler wires to PRD 0016 (capability-block), which rebuilds
the bottle Dockerfile. Egress proposals are queued for operator review
as full routes.yaml updates.
"""
from __future__ import annotations
@@ -21,6 +22,10 @@ from pathlib import Path
from .. import supervise as _supervise
from ..bottle_state import read_metadata
# from ..backend.docker.capability_apply import (
# CapabilityApplyError,
# apply_capability_change,
# )
from ..backend.docker.egress_apply import (
EgressApplyError,
applicator as _docker_applicator,
@@ -33,6 +38,10 @@ from ..backend.smolmachines.egress_apply import (
)
from ..log import Die, error, info
class CapabilityApplyError(RuntimeError):
"""Placeholder while capability_apply is disabled."""
from ..supervise import (
COMPONENT_FOR_TOOL,
AuditEntry,
@@ -41,10 +50,11 @@ from ..supervise import (
STATUS_APPROVED,
STATUS_MODIFIED,
STATUS_REJECTED,
TOOL_EGRESS_ALLOW,
TOOL_CAPABILITY_BLOCK,
TOOL_ALLOW,
TOOL_EGRESS_BLOCK,
TOOL_GITLEAKS_ALLOW,
TOOL_EGRESS_TOKEN_ALLOW,
archive_proposal,
list_pending_proposals,
render_diff,
write_audit_entry,
@@ -55,11 +65,6 @@ from ._common import PROG
_REFRESH_INTERVAL_MS = 1000
# Proposal tools whose payload is a read-only report, not a file the operator
# edits: modify is unavailable and approval requires a recorded reason for the
# audit trail.
_REPORT_ONLY_TOOLS: tuple[str, ...] = (TOOL_GITLEAKS_ALLOW, TOOL_EGRESS_TOKEN_ALLOW)
@dataclass(frozen=True)
class QueuedProposal:
@@ -72,7 +77,7 @@ class QueuedProposal:
# Errors any remediation engine may raise. Caught by the TUI key
# handlers and surfaced in the status line so a failed apply keeps
# the proposal pending rather than crashing curses.
ApplyError = (EgressApplyError,)
ApplyError = (CapabilityApplyError, EgressApplyError)
def apply_routes_change(slug: str, content: str) -> tuple[str, str]:
@@ -132,9 +137,11 @@ def _detail_lines(
def _suffix_for_tool(tool: str) -> str:
if tool in (TOOL_EGRESS_ALLOW, TOOL_EGRESS_BLOCK):
if tool == TOOL_CAPABILITY_BLOCK:
return ".dockerfile"
if tool in (TOOL_ALLOW, TOOL_EGRESS_BLOCK):
return ".yaml"
if tool in (TOOL_GITLEAKS_ALLOW, TOOL_EGRESS_TOKEN_ALLOW):
if tool == TOOL_GITLEAKS_ALLOW:
return ".txt"
return ".txt"
@@ -153,7 +160,18 @@ def approve(
file_to_apply = final_file if final_file is not None else qp.proposal.proposed_file
diff_before, diff_after = "", ""
if qp.proposal.tool in (TOOL_EGRESS_ALLOW, TOOL_EGRESS_BLOCK):
# if qp.proposal.tool == TOOL_CAPABILITY_BLOCK:
# _meta = read_metadata(qp.proposal.bottle_slug)
# if _meta is not None and not _meta.compose_project:
# raise CapabilityApplyError(
# "capability-block remediation is not supported for smolmachines "
# "bottles. Reject this proposal or handle the capability change "
# "manually, then restart the bottle."
# )
# diff_before, diff_after = apply_capability_change(
# qp.proposal.bottle_slug, file_to_apply,
# )
if qp.proposal.tool in (TOOL_ALLOW, TOOL_EGRESS_BLOCK):
diff_before, diff_after = apply_routes_change(
qp.proposal.bottle_slug,
file_to_apply,
@@ -170,6 +188,9 @@ def approve(
qp, action=status, notes=notes,
diff_before=diff_before, diff_after=diff_after,
)
if qp.proposal.tool == TOOL_CAPABILITY_BLOCK:
archive_proposal(qp.queue_dir, qp.proposal.id)
def reject(qp: QueuedProposal, *, reason: str) -> None:
"""Write a rejection response and an audit entry."""
@@ -191,8 +212,8 @@ def _approve_from_tui(
notes: str = "",
) -> str:
"""Approve from curses, prompting for any tool-specific audit note."""
if qp.proposal.tool in _REPORT_ONLY_TOOLS and final_file is None:
notes = _prompt(stdscr, "allow reason (false positive / legitimately needed): ")
if qp.proposal.tool == TOOL_GITLEAKS_ALLOW and final_file is None:
notes = _prompt(stdscr, "allow reason (test fixture/false positive): ")
if not notes:
return "approve aborted (empty reason)"
approve(qp, final_file=final_file, notes=notes)
@@ -271,10 +292,7 @@ def cmd_supervise(argv: list[str]) -> int:
return e.code if isinstance(e.code, int) else 1
except Exception as e: # noqa: W0718 — catch supervise crash for logging
log_path = _write_crash_log(e)
error(
f"supervise crashed: {type(e).__name__}: {e}",
context={"error_type": type(e).__name__, "crash_log": str(log_path)},
)
error(f"supervise crashed: {type(e).__name__}: {e}")
error(f"full traceback written to {log_path}")
return 1
return 0
@@ -319,7 +337,7 @@ def _list_once() -> int:
return 0
def _try_init_green() -> int: # pragma: no cover
def _try_init_green() -> int:
"""Initialise a green color pair and return its attr, or 0."""
try:
curses.start_color()
@@ -330,7 +348,7 @@ def _try_init_green() -> int: # pragma: no cover
return 0
def _main_loop(stdscr: "curses._CursesWindow") -> None: # type: ignore # pragma: no cover
def _main_loop(stdscr: "curses._CursesWindow") -> None: # type: ignore
curses.curs_set(0)
stdscr.timeout(_REFRESH_INTERVAL_MS)
green_attr = _try_init_green()
@@ -390,8 +408,8 @@ def _main_loop(stdscr: "curses._CursesWindow") -> None: # type: ignore # pragm
except ApplyError as e:
status_line = f"apply failed: {e}"
elif key == ord("m"):
if qp.proposal.tool in _REPORT_ONLY_TOOLS:
status_line = f"modify unavailable for {qp.proposal.tool}"
if qp.proposal.tool == TOOL_GITLEAKS_ALLOW:
status_line = "modify unavailable for gitleaks-allow"
continue
edited = _modify(stdscr, qp)
if edited is None:
@@ -420,7 +438,7 @@ def _render(
status_line: str,
*,
green_attr: int = 0, # noqa: F841 — unused, but required by interface
) -> None: # pragma: no cover
) -> None:
stdscr.erase()
h, w = stdscr.getmaxyx()
header = f"bot-bottle supervise ({len(pending)} pending)"
@@ -471,7 +489,7 @@ def _detail_view(
qp: QueuedProposal,
*,
green_attr: int = 0,
) -> None: # pragma: no cover
) -> None:
"""Render the full proposal. Scrollable. Press q to return."""
lines = _detail_lines(qp, green_attr=green_attr)
offset = 0
@@ -504,7 +522,7 @@ def _detail_view(
pass
return
elif key == ord("m"):
if qp.proposal.tool in _REPORT_ONLY_TOOLS:
if qp.proposal.tool == TOOL_GITLEAKS_ALLOW:
return
edited = _modify(stdscr, qp)
if edited is not None:
@@ -523,7 +541,7 @@ def _detail_view(
return
def _modify(stdscr: "curses._CursesWindow", qp: QueuedProposal) -> str | None: # type: ignore # pragma: no cover
def _modify(stdscr: "curses._CursesWindow", qp: QueuedProposal) -> str | None: # type: ignore
"""Suspend curses, open $EDITOR on the proposed file, return edited content."""
suffix = _suffix_for_tool(qp.proposal.tool)
curses.endwin()
@@ -534,7 +552,7 @@ def _modify(stdscr: "curses._CursesWindow", qp: QueuedProposal) -> str | None:
return edited
def _prompt(stdscr: "curses._CursesWindow", label: str) -> str: # type: ignore # pragma: no cover
def _prompt(stdscr: "curses._CursesWindow", label: str) -> str: # type: ignore
"""One-line input at the bottom of the screen."""
curses.curs_set(1)
h, _ = stdscr.getmaxyx()
-292
View File
@@ -17,43 +17,6 @@ import sys
from typing import Any, Optional
def filter_multiselect(
items: list[str],
*,
title: str = "",
initial: Optional[list[str]] = None,
tty_path: str = "/dev/tty",
) -> Optional[list[str]]:
"""Render a multi-select picker over *items*.
Returns the ordered list of selected items, or ``None`` if the user
cancelled (Esc / ``q`` / Ctrl-C / Ctrl-D with no items).
Press Space to toggle the item under the cursor.
Press Enter to confirm the current selection.
Press Ctrl-D to confirm the current selection (returns even if empty).
Press Esc/q to cancel (returns None).
*initial* pre-populates the selection in insertion order. Items
added are appended; removed items leave the remaining order unchanged.
"""
if not items:
return []
try:
tty_fd = open(tty_path, "r+b", buffering=0)
except OSError:
return None
try:
fd_dup = os.dup(tty_fd.fileno())
return _run_multiselect(
items, title=title, initial=list(initial or []), tty_fd=fd_dup
)
finally:
tty_fd.close()
def filter_select(
items: list[str],
*,
@@ -258,261 +221,6 @@ def _addstr_safe(screen: Any, row: int, col: int, text: str, attr: int = curses.
pass
# ---------------------------------------------------------------------------
# filter_multiselect internals
# ---------------------------------------------------------------------------
_KEY_SPACE = 32
def _run_multiselect(
items: list[str], *, title: str, initial: list[str], tty_fd: int
) -> Optional[list[str]]:
"""Drive a curses multi-select session on *tty_fd*."""
os.environ.setdefault("TERM", "xterm-256color")
orig_stdin = sys.__stdin__
orig_stdout = sys.__stdout__
try:
import io
tty_text = io.TextIOWrapper(io.FileIO(tty_fd, mode='r+'), write_through=True)
sys.__stdin__ = tty_text # type: ignore[assignment]
sys.__stdout__ = tty_text # type: ignore[assignment]
screen = curses.initscr()
curses.noecho()
curses.cbreak()
screen.keypad(True)
try:
result = _multiselect_loop(screen, items, title=title, initial=initial)
finally:
screen.keypad(False)
curses.nocbreak()
curses.echo()
curses.endwin()
except Exception: # noqa: W0718
return None
finally:
sys.__stdin__ = orig_stdin # type: ignore[assignment]
sys.__stdout__ = orig_stdout # type: ignore[assignment]
return result
def _multiselect_loop(
screen: Any, items: list[str], *, title: str, initial: list[str]
) -> Optional[list[str]]:
query = ""
cursor = 0
selected: list[str] = [s for s in initial if s in items]
# focus = "filter": navigate + toggle items in the filterable list
# focus = "order": navigate + reorder items in the selected list
focus = "filter"
order_cursor = 0
while True:
filtered = _filter_items(items, query)
if not filtered:
cursor = 0
elif cursor >= len(filtered):
cursor = len(filtered) - 1
if not selected:
order_cursor = 0
if focus == "order":
focus = "filter"
elif order_cursor >= len(selected):
order_cursor = len(selected) - 1
try:
_render_multiselect(
screen, filtered, cursor,
query=query, title=title, selected=selected,
focus=focus, order_cursor=order_cursor,
)
except curses.error:
return None
try:
key = screen.getch()
except KeyboardInterrupt:
return None
if key in (_KEY_ESC, _KEY_CTRL_C, ord("q")):
return None
if key == _KEY_CTRL_D:
return list(selected)
# Tab toggles between filter and order focus.
if key == ord("\t"):
if focus == "filter" and selected:
focus = "order"
order_cursor = 0
else:
focus = "filter"
continue
if focus == "filter":
if key in (curses.KEY_ENTER, _KEY_ENTER_ALT, ord("\r")):
return list(selected)
elif key == _KEY_SPACE:
if filtered:
item = filtered[cursor]
if item in selected:
selected.remove(item)
else:
selected.append(item)
elif key in (curses.KEY_UP, ord("k")):
if cursor > 0:
cursor -= 1
elif key in (curses.KEY_DOWN, ord("j")):
if cursor < len(filtered) - 1:
cursor += 1
elif key in (curses.KEY_BACKSPACE, _KEY_BACKSPACE_WIN, 127):
query = query[:-1]
new_filtered = _filter_items(items, query)
if cursor >= len(new_filtered):
cursor = max(0, len(new_filtered) - 1)
elif 32 <= key <= 126 and key != _KEY_SPACE:
query += chr(key)
cursor = 0
else: # focus == "order"
if key in (curses.KEY_UP, ord("k")):
if order_cursor > 0:
order_cursor -= 1
elif key in (curses.KEY_DOWN, ord("j")):
if order_cursor < len(selected) - 1:
order_cursor += 1
elif key == ord("K"):
# Move selected item up (earlier in order).
if order_cursor > 0:
i = order_cursor
selected[i - 1], selected[i] = selected[i], selected[i - 1]
order_cursor -= 1
elif key == ord("J"):
# Move selected item down (later in order).
if order_cursor < len(selected) - 1:
i = order_cursor
selected[i], selected[i + 1] = selected[i + 1], selected[i]
order_cursor += 1
elif key in (curses.KEY_ENTER, _KEY_ENTER_ALT, ord("\r"), _KEY_SPACE):
# Remove item from selection while in order mode.
del selected[order_cursor]
if order_cursor >= len(selected) and order_cursor > 0:
order_cursor -= 1
def _render_multiselect(
screen: Any,
filtered: list[str],
cursor: int,
*,
query: str,
title: str,
selected: list[str],
focus: str = "filter",
order_cursor: int = 0,
) -> None:
screen.erase()
rows, cols = screen.getmaxyx()
min_rows = 7
if rows < min_rows:
raise curses.error("terminal too small")
sep = "" * min(cols - 1, 40)
row = 0
if title and row < rows - 1:
_addstr_safe(screen, row, 0, title[:cols - 1], curses.A_BOLD)
row += 1
# Filter line — dim when focus is on the order panel.
filter_label = f"Filter: {query}"
filter_hint = " [Tab: reorder]" if focus == "filter" and selected else ""
filter_attr = curses.A_DIM if focus == "order" else curses.A_NORMAL
if row < rows - 1:
_addstr_safe(screen, row, 0, (filter_label + filter_hint)[:cols - 1], filter_attr)
row += 1
if row < rows - 1:
_addstr_safe(screen, row, 0, sep)
row += 1
# Compute how many rows the bottom order panel needs.
# Cap the visible selected list to keep the filter list legible.
order_rows = min(len(selected), max(1, (rows - row) // 3)) if selected else 0
# Bottom reserved: sep + order_rows + sep + help = order_rows + 3
bottom_reserved = order_rows + 3
list_start = row
list_rows = rows - list_start - bottom_reserved
if list_rows < 1:
list_rows = 1
selected_set = set(selected)
filter_dim = focus == "order"
scroll = max(0, cursor - list_rows + 1)
visible = filtered[scroll: scroll + list_rows]
for idx, item in enumerate(visible):
abs_idx = scroll + idx
mark = "[*]" if item in selected_set else "[ ]"
prefix = "> " if (abs_idx == cursor and focus == "filter") else " "
line = (prefix + mark + " " + item)[:cols - 1]
item_attr = curses.A_DIM if filter_dim else (
curses.A_REVERSE if abs_idx == cursor else curses.A_NORMAL
)
if row < rows - bottom_reserved:
_addstr_safe(screen, row, 0, line, item_attr)
row += 1
# Separator before the order panel.
if row < rows - (order_rows + 2):
_addstr_safe(screen, row, 0, sep)
row += 1
# Order panel.
order_scroll = max(0, order_cursor - order_rows + 1)
order_visible = selected[order_scroll: order_scroll + order_rows]
for idx, item in enumerate(order_visible):
abs_idx = order_scroll + idx
is_active = focus == "order" and abs_idx == order_cursor
prefix = "> " if is_active else " "
line = (prefix + item)[:cols - 1]
attr = curses.A_REVERSE if is_active else curses.A_NORMAL
if row < rows - 2:
_addstr_safe(screen, row, 0, line, attr)
row += 1
if row < rows - 1:
_addstr_safe(screen, row, 0, sep)
row += 1
if focus == "filter":
help_line = "[↑↓/jk] move [Space] toggle [Enter] confirm [Tab] reorder [Esc/q] cancel"
else:
help_line = "[↑↓/jk] cursor [K/J] reorder [Space/Enter] remove [Tab] back [Ctrl-D] done"
if row < rows:
_addstr_safe(screen, min(rows - 1, row), 0, help_line[:cols - 1])
screen.refresh()
# ---------------------------------------------------------------------------
# name_color_modal — two-step label + color picker
# ---------------------------------------------------------------------------
+1 -1
View File
@@ -21,7 +21,7 @@ FROM node:22-slim
# to it) works against egress's bumped TLS without the agent needing
# local DNS.
RUN apt-get update \
&& apt-get install -y --no-install-recommends git ca-certificates curl ripgrep \
&& apt-get install -y --no-install-recommends git ca-certificates curl \
&& rm -rf /var/lib/apt/lists/*
# App-specific deps. Python isn't required by claude-code itself
+2 -4
View File
@@ -20,7 +20,6 @@ from ...agent_provider import (
AgentProvisionDir,
AgentProvisionFile,
AgentProvisionPlan,
provider_startup_args,
)
from ...backend.docker import util as docker_mod
from ...egress import EgressRoute
@@ -91,6 +90,7 @@ _RUNTIME = AgentProviderRuntime(
prompt_mode="append_file",
bypass_args=("--dangerously-skip-permissions",),
resume_args=("--continue",),
remote_control_args=("--remote-control",),
)
@@ -115,9 +115,8 @@ class ClaudeAgentProvider(AgentProvider):
color: str = "",
provider_settings: dict[str, object] | None = None,
) -> AgentProvisionPlan:
del forward_host_credentials, host_env
del forward_host_credentials, host_env, provider_settings
resolved_guest_env = dict(guest_env or {})
startup_args = provider_startup_args(provider_settings)
guest_home = self.guest_home
trusted_path = trusted_project_path or guest_home
@@ -200,7 +199,6 @@ class ClaudeAgentProvider(AgentProvider):
env_vars=env_vars,
guest_env=resolved_guest_env,
has_prompt=has_prompt,
startup_args=startup_args,
dirs=dirs,
files=tuple(files),
egress_routes=egress_routes,
+6 -9
View File
@@ -1,12 +1,12 @@
# bot-bottle Codex provider image.
#
# Mirrors the default Claude image shape: Node LTS, git/network tooling,
# non-root node user, and the provider CLI installed for that user.
# non-root node user, and the provider CLI installed globally.
FROM node:22-slim
RUN apt-get update \
&& apt-get install -y --no-install-recommends git ca-certificates curl procps ripgrep \
&& apt-get install -y --no-install-recommends git ca-certificates curl \
&& rm -rf /var/lib/apt/lists/*
# App-specific deps. Python isn't required by codex itself
@@ -17,15 +17,12 @@ RUN apt-get update \
&& apt-get install -y --no-install-recommends python3 python3-pip python3-venv \
&& rm -rf /var/lib/apt/lists/*
RUN npm install -g --no-fund --no-audit @openai/codex@0.136.0 \
&& npm cache clean --force
USER node
WORKDIR /home/node
ENV PATH="/home/node/.local/bin:${PATH}"
# Remote-control support requires the standalone Codex install layout
# under ~/.codex/packages/standalone/current. The npm package can run
# the TUI, but remote-control commands expect this installer-owned path.
RUN mkdir -p /home/node/.codex \
&& curl -fsSL https://chatgpt.com/codex/install.sh | sh
RUN mkdir -p /home/node/.codex
CMD ["codex"]
+2 -4
View File
@@ -22,7 +22,6 @@ from ...agent_provider import (
AgentProvisionCommand,
AgentProvisionFile,
AgentProvisionPlan,
provider_startup_args,
)
from .codex_auth import codex_host_access_token, write_codex_dummy_auth_file
from ...egress import CODEX_HOST_CREDENTIAL_TOKEN_REF, EgressRoute
@@ -55,6 +54,7 @@ _RUNTIME = AgentProviderRuntime(
prompt_mode="read_prompt_file",
bypass_args=("--dangerously-bypass-approvals-and-sandbox",),
resume_args=("resume", "--last"),
remote_control_args=(),
)
@@ -79,9 +79,8 @@ class CodexAgentProvider(AgentProvider):
color: str = "",
provider_settings: dict[str, object] | None = None,
) -> AgentProvisionPlan:
del auth_token, label, color
del auth_token, label, color, provider_settings
resolved_guest_env = dict(guest_env or {})
startup_args = provider_startup_args(provider_settings)
guest_home = self.guest_home
trusted_path = trusted_project_path or guest_home
@@ -164,7 +163,6 @@ class CodexAgentProvider(AgentProvider):
env_vars=env_vars,
guest_env=resolved_guest_env,
has_prompt=has_prompt,
startup_args=startup_args,
dirs=tuple(dirs),
files=tuple(files),
pre_copy=tuple(pre_copy),
@@ -19,12 +19,7 @@ import urllib.error
import urllib.request
from pathlib import Path
from ...deploy_key_provisioner import DeployKeyCollisionError, DeployKeyProvisioner
# Timeout for ssh-keygen and Gitea API HTTP calls. A hung Gitea instance at
# prepare time would stall bottle launch indefinitely without this bound.
_API_TIMEOUT_SECS = 30
_KEYGEN_TIMEOUT_SECS = 10
from ...deploy_key_provisioner import DeployKeyProvisioner
class GiteaDeployKeyProvisioner(DeployKeyProvisioner):
@@ -51,7 +46,6 @@ class GiteaDeployKeyProvisioner(DeployKeyProvisioner):
check=True,
stdout=subprocess.DEVNULL,
stderr=subprocess.DEVNULL,
timeout=_KEYGEN_TIMEOUT_SECS,
)
private_key = key_path.read_bytes()
public_key = key_path.with_suffix(".pub").read_text().strip()
@@ -73,15 +67,10 @@ class GiteaDeployKeyProvisioner(DeployKeyProvisioner):
method="POST",
)
try:
with urllib.request.urlopen(req, timeout=_API_TIMEOUT_SECS) as resp:
with urllib.request.urlopen(req) as resp:
body = json.loads(resp.read())
except urllib.error.HTTPError as exc:
_body = _read_error_body(exc)
if exc.code == 422:
raise DeployKeyCollisionError(
f"deploy key collision for {owner_repo!r} "
f"(title={title!r}): key title or content already registered — {_body}"
) from exc
raise RuntimeError(
f"failed to create deploy key for {owner_repo}: "
f"HTTP {exc.code}{_body}"
@@ -104,7 +93,7 @@ class GiteaDeployKeyProvisioner(DeployKeyProvisioner):
method="DELETE",
)
try:
with urllib.request.urlopen(req, timeout=_API_TIMEOUT_SECS):
with urllib.request.urlopen(req):
pass
except urllib.error.HTTPError as exc:
if exc.code == 404:
+1 -3
View File
@@ -21,7 +21,6 @@ from ...agent_provider import (
AgentProvisionDir,
AgentProvisionFile,
AgentProvisionPlan,
provider_startup_args,
)
from ...egress import EgressRoute
from ...log import die, info
@@ -166,6 +165,7 @@ _RUNTIME = AgentProviderRuntime(
prompt_mode="append_system_prompt",
bypass_args=(),
resume_args=(),
remote_control_args=(),
)
@@ -199,7 +199,6 @@ class PiAgentProvider(AgentProvider):
models_payload, base_url, api_key_env, models, provider_name = (
_pi_models_json(settings)
)
extra_startup_args = provider_startup_args(provider_settings)
models_file = state_dir / "pi-models.json"
models_file.write_text(json.dumps(models_payload, indent=2) + "\n")
models_file.chmod(0o600)
@@ -220,7 +219,6 @@ class PiAgentProvider(AgentProvider):
startup_args=(
"--models",
",".join(f"{provider_name}/{model}" for model in models),
*extra_startup_args,
),
dirs=(AgentProvisionDir(f"{guest_home}/.pi/agent"),),
files=(AgentProvisionFile(models_file, _models_path(guest_home)),),
-4
View File
@@ -11,10 +11,6 @@ from __future__ import annotations
from abc import ABC, abstractmethod
class DeployKeyCollisionError(RuntimeError):
"""Raised when a deploy key title or public key already exists on the repo."""
class DeployKeyProvisioner(ABC):
"""Manages a single deploy-key lifecycle on a remote forge."""
+7 -190
View File
@@ -15,8 +15,6 @@ import gzip
import re
import typing
import unicodedata
from math import log2
from collections import Counter
from urllib.parse import quote as url_quote
try:
@@ -80,27 +78,16 @@ TOKEN_PATTERNS: tuple[tuple[str, re.Pattern[str]], ...] = (
)
def scan_token_patterns(
text: str,
*,
location: str = "body",
safe_tokens: typing.AbstractSet[str] | None = None,
) -> ScanResult | None:
def scan_token_patterns(text: str, *, location: str = "body") -> ScanResult | None:
normalized = _normalize_text(text)
for name, pattern in TOKEN_PATTERNS:
for m in pattern.finditer(normalized):
value = m.group(0)
# A value the supervisor has approved (PRD 0062) is no longer a
# block — keep scanning so a second, un-approved token in the
# same request is still caught.
if safe_tokens is not None and value in safe_tokens:
continue
m = pattern.search(normalized)
if m is not None:
return ScanResult(
severity="block",
reason=f"{name} found in {location}",
location=location,
context=_snippet(normalized, m.start(), m.end()),
matched=value,
context=_snippet(text, m.start(), m.end()),
)
return None
@@ -109,21 +96,20 @@ def redact_tokens(
text: str,
*,
env: typing.Mapping[str, str] | None = None,
sensitive_prefixes: tuple[str, ...] = ("EGRESS_TOKEN_",),
) -> str:
"""Replace token pattern matches and (if env given) provisioned secrets with REDACT."""
for _, pattern in TOKEN_PATTERNS:
text = pattern.sub(REDACT, text)
if env is not None:
for key, value in env.items():
if any(key.startswith(p) for p in sensitive_prefixes) and value:
if key.startswith("EGRESS_TOKEN_") and value:
for variant in _encoded_variants(value):
text = text.replace(variant, REDACT)
return text
# ---------------------------------------------------------------------------
# Known secrets detector
# Known secrets detector (Phase 1b)
# ---------------------------------------------------------------------------
def _encoded_variants(secret: str) -> list[str]:
@@ -164,179 +150,26 @@ def _encoded_variants(secret: str) -> list[str]:
return variants
# ---------------------------------------------------------------------------
# Fragmentation-resistant helpers
# ---------------------------------------------------------------------------
# Minimum length of alnum projection for projection-based checks to run.
# Short secrets produce too many false positives in projection space.
_ALNUM_MIN_LEN = 8
# Minimum window length for the partial-substring sliding scan.
PARTIAL_MATCH_MIN_LEN = 12
def _alnum_projection(text: str) -> str:
"""Return text with every non-alphanumeric character stripped.
Used for fragmentation-resistant matching: separator-injected secrets
(spaces, hyphens, dots inserted between characters) are identical to
their originals in alnum projection space.
"""
return "".join(c for c in text if c.isalnum())
def _find_partial_window(secret_alnum: str, text_alnum: str, min_len: int) -> int | None:
"""Return the position in text_alnum where any min_len-char window of
secret_alnum first appears, or None.
Slides a window of width min_len across secret_alnum and searches for
each window in text_alnum. The first hit position is returned.
"""
if len(secret_alnum) < min_len or len(text_alnum) < min_len:
return None
for i in range(len(secret_alnum) - min_len + 1):
window = secret_alnum[i:i + min_len]
pos = text_alnum.find(window)
if pos >= 0:
return pos
return None
def scan_known_secrets(
text: str,
*,
location: str = "body",
env: typing.Mapping[str, str] | None = None,
sensitive_prefixes: tuple[str, ...] = ("EGRESS_TOKEN_",),
safe_tokens: typing.AbstractSet[str] | None = None,
) -> ScanResult | None:
if env is None:
return None
# Pre-compute alnum projection of the scan text once; reused per secret.
text_alnum: str | None = None
for key, value in env.items():
if not any(key.startswith(p) for p in sensitive_prefixes) or not value:
if not key.startswith("EGRESS_TOKEN_") or not value:
continue
# Pass 1: exact match across encoded variants (original behaviour).
approved_exact = False
for variant in _encoded_variants(value):
pos = text.find(variant)
if pos >= 0:
# The supervisor approves the exact encoded variant found
# (PRD 0062); a different encoding of the same secret is a
# fresh block.
if safe_tokens is not None and variant in safe_tokens:
approved_exact = True
continue
return ScanResult(
severity="block",
reason=f"provisioned secret from {key} found in {location}",
location=location,
context=_snippet(text, pos, pos + len(variant)),
matched=variant,
)
if approved_exact:
# Exact match was found and approved; projection passes would
# fire on the same value, so skip them for this secret.
continue
# Pass 2 & 3: fragmentation-resistant projection checks.
secret_alnum = _alnum_projection(value)
if len(secret_alnum) < _ALNUM_MIN_LEN:
continue
if text_alnum is None:
text_alnum = _alnum_projection(text)
# Pass 2: full alnum-projection exact match (catches separator injection).
pos2 = text_alnum.find(secret_alnum)
if pos2 >= 0:
return ScanResult(
severity="block",
reason=(
f"provisioned secret from {key} found in {location} "
f"(fragmented match — separator injection)"
),
location=location,
context=_snippet(text_alnum, pos2, pos2 + len(secret_alnum)),
)
# Pass 3: sliding-window partial match (catches chunked-substring leaks).
pos3 = _find_partial_window(secret_alnum, text_alnum, PARTIAL_MATCH_MIN_LEN)
if pos3 is not None:
return ScanResult(
severity="block",
reason=(
f"provisioned secret from {key} found in {location} "
f"(partial match — at least {PARTIAL_MATCH_MIN_LEN} consecutive "
f"alphanumeric chars)"
),
location=location,
context=_snippet(text_alnum, pos3, pos3 + PARTIAL_MATCH_MIN_LEN),
)
return None
# ---------------------------------------------------------------------------
# Entropy detector (warn-only)
# ---------------------------------------------------------------------------
# Sliding window size and step for the entropy scan.
ENTROPY_WINDOW = 64
ENTROPY_STEP = 32
# Bits-per-character threshold. Random ASCII printable ≈ 6.6 bits; random
# lowercase hex ≈ 4 bits; random base64url ≈ 6 bits. 5.5 sits above
# typical structured data (JSON, URLs) while staying below truly random
# content.
ENTROPY_BLOCK_THRESHOLD = 5.5
def _shannon_entropy(text: str) -> float:
if not text:
return 0.0
counts = Counter(text)
n = len(text)
return -sum((c / n) * log2(c / n) for c in counts.values())
def scan_entropy(
text: str,
*,
location: str = "body",
window: int = ENTROPY_WINDOW,
threshold: float = ENTROPY_BLOCK_THRESHOLD,
) -> ScanResult | None:
"""Warn-only detector: flag windows of `window` chars with Shannon entropy
above `threshold` bits per character.
Never blocks; always returns severity='warn'. Disabled by default
routes must opt in via dlp.outbound_detectors=['entropy'].
"""
if not text:
return None
step = max(1, window // 2)
end = len(text)
# Scan overlapping windows; also check the final tail if shorter than window.
positions = list(range(0, end - window + 1, step))
if end < window:
positions = [0]
elif (end - window) % step != 0:
positions.append(end - window)
for i in positions:
chunk = text[i:i + window]
if _shannon_entropy(chunk) >= threshold:
return ScanResult(
severity="warn",
reason=f"high-entropy content in {location} (possible encrypted exfil)",
location=location,
context=_snippet(text, i, i + len(chunk)),
)
return None
@@ -432,14 +265,6 @@ _CRLF_ENCODED_RE = re.compile(r"%0[dD]%0[aA]", re.ASCII)
_CRLF_HEADER_INJECT_RE = re.compile(r"\r\n[A-Za-z][A-Za-z0-9\-]+\s*:", re.ASCII)
def strip_crlf(text: str) -> str:
"""Remove URL-encoded and literal CRLF injection sequences from a request
surface (PRD 0062 redact policy). Used to scrub the request line / headers
so the request can be forwarded instead of hard-blocked."""
text = _CRLF_ENCODED_RE.sub("", text)
return _CRLF_HEADER_INJECT_RE.sub(lambda m: m.group(0)[2:], text)
def scan_crlf_injection(text: str) -> ScanResult | None:
if _CRLF_ENCODED_RE.search(text):
return ScanResult(
@@ -455,20 +280,12 @@ def scan_crlf_injection(text: str) -> ScanResult | None:
__all__ = [
"ENTROPY_BLOCK_THRESHOLD",
"ENTROPY_WINDOW",
"ENTROPY_STEP",
"PARTIAL_MATCH_MIN_LEN",
"REDACT",
"SNIPPET_CONTEXT",
"TOKEN_PATTERNS",
"_alnum_projection",
"_shannon_entropy",
"redact_tokens",
"scan_crlf_injection",
"scan_entropy",
"scan_known_secrets",
"scan_naive_injection",
"scan_token_patterns",
"strip_crlf",
]
+11 -102
View File
@@ -10,14 +10,12 @@ specific and lives on concrete subclasses (see
from __future__ import annotations
import dataclasses
import secrets
from abc import ABC
from dataclasses import dataclass
from pathlib import Path
from typing import TYPE_CHECKING
from .egress_addon_core import (
ON_MATCH_REDACT,
HeaderMatch as CoreHeaderMatch,
MatchEntry as CoreMatchEntry,
PathMatch as CorePathMatch,
@@ -35,50 +33,6 @@ EGRESS_HOSTNAME = "egress"
EGRESS_ROUTES_IN_CONTAINER = "/etc/egress/routes.yaml"
EGRESS_ROUTES_FILENAME = Path(EGRESS_ROUTES_IN_CONTAINER).name
_CANARY_ENV_WORDS = (
"ACCORD",
"ANCHOR",
"ATLAS",
"CANON",
"CIPHER",
"EMBER",
"FALCON",
"HARBOR",
"LANTERN",
"MARBLE",
"NOVA",
"ORBIT",
"PIVOT",
"RADIUS",
"SUMMIT",
"VECTOR",
)
def _random_canary_env() -> str:
first = secrets.choice(_CANARY_ENV_WORDS)
remaining = tuple(word for word in _CANARY_ENV_WORDS if word != first)
second = secrets.choice(remaining)
return f"{first}_{second}_SECRET"
def egress_sidecar_env_entries(plan: "EgressPlan") -> tuple[str, ...]:
"""Return sidecar env entries needed by egress across all backends."""
env: list[str] = []
if plan.routes:
env.extend(sorted(plan.token_env_map.keys()))
if plan.canary and plan.canary_env:
env.append(f"{plan.canary_env}={plan.canary}")
env.append(f"BOT_BOTTLE_SENSITIVE_PREFIXES={plan.canary_env}")
return tuple(env)
def egress_agent_env_entries(plan: "EgressPlan") -> tuple[str, ...]:
"""Return agent-visible egress env entries shared by all backends."""
if plan.canary and plan.canary_env:
return (f"{plan.canary_env}={plan.canary}",)
return ()
@dataclass(frozen=True)
class EgressRoute(Route):
@@ -110,8 +64,6 @@ class EgressPlan:
mitmproxy_ca_host_path: Path = Path()
mitmproxy_ca_cert_only_host_path: Path = Path()
log: int = 0
canary: str = ""
canary_env: str = ""
def egress_manifest_routes(
@@ -143,7 +95,6 @@ def egress_manifest_routes(
git_fetch=r.GitFetch,
outbound_detectors=r.OutboundDetectors,
inbound_detectors=r.InboundDetectors,
outbound_on_match=r.OutboundOnMatch,
))
return tuple(out)
@@ -154,27 +105,12 @@ def egress_routes_for_bottle(
) -> tuple[EgressRoute, ...]:
manifest = egress_manifest_routes(bottle)
provisioned_hosts = {pr.host.lower() for pr in provider_routes}
merged = list(_default_provider_on_match(provider_routes)) + [
merged = list(provider_routes) + [
r for r in manifest if r.host.lower() not in provisioned_hosts
]
return _assign_token_slots(merged)
def _default_provider_on_match(
provider_routes: tuple[EgressRoute, ...],
) -> tuple[EgressRoute, ...]:
"""Provider routes (the agent talking to its own LLM API) default to the
`redact` on-match policy (PRD 0062): high-volume conversation payloads are
the worst source of token-shaped false positives, so a match is scrubbed
and forwarded rather than hard-blocked or queued for the operator. A
provider that sets `outbound_on_match` explicitly keeps its choice."""
return tuple(
r if r.outbound_on_match
else dataclasses.replace(r, outbound_on_match=ON_MATCH_REDACT)
for r in provider_routes
)
def _assign_token_slots(
routes: list[EgressRoute],
) -> tuple[EgressRoute, ...]:
@@ -210,17 +146,6 @@ def egress_token_env_map(
return out
def _yaml_str_escape(s: str) -> str:
"""Escape a string for use inside a YAML double-quoted scalar."""
return (
s.replace("\\", "\\\\")
.replace('"', '\\"')
.replace("\n", "\\n")
.replace("\r", "\\r")
.replace("\t", "\\t")
)
def _route_to_yaml_fields(r: Route) -> dict[str, object]:
fields: dict[str, object] = {"host": r.host}
if r.auth_scheme and r.token_env:
@@ -252,11 +177,7 @@ def _route_to_yaml_fields(r: Route) -> dict[str, object]:
fields["matches"] = matches_data
if r.git_fetch:
fields["git"] = {"fetch": True}
if (
r.outbound_detectors is not None
or r.inbound_detectors is not None
or r.outbound_on_match
):
if r.outbound_detectors is not None or r.inbound_detectors is not None:
dlp: dict[str, object] = {}
if r.outbound_detectors is not None:
dlp["outbound_detectors"] = (
@@ -268,8 +189,6 @@ def _route_to_yaml_fields(r: Route) -> dict[str, object]:
False if not r.inbound_detectors
else list(r.inbound_detectors)
)
if r.outbound_on_match:
dlp["outbound_on_match"] = r.outbound_on_match
fields["dlp"] = dlp
return fields
@@ -283,12 +202,12 @@ def _render_match_entry(entry: dict[str, object]) -> list[str]:
for pd in entry["paths"]: # type: ignore[union-attr]
pd_dict: dict[str, str] = pd # type: ignore[assignment]
if "type" in pd_dict:
lines.append(f' - type: "{_yaml_str_escape(pd_dict["type"])}"')
lines.append(f' value: "{_yaml_str_escape(pd_dict["value"])}"')
lines.append(f' - type: "{pd_dict["type"]}"')
lines.append(f' value: "{pd_dict["value"]}"')
else:
lines.append(f' - value: "{_yaml_str_escape(pd_dict["value"])}"')
lines.append(f' - value: "{pd_dict["value"]}"')
if "methods" in entry:
methods_str = ", ".join(f'"{_yaml_str_escape(m)}"' for m in entry["methods"]) # type: ignore[union-attr]
methods_str = ", ".join(f'"{m}"' for m in entry["methods"]) # type: ignore[union-attr]
prefix = " - " if first_key else " "
lines.append(f'{prefix}methods: [{methods_str}]')
first_key = False
@@ -298,8 +217,8 @@ def _render_match_entry(entry: dict[str, object]) -> list[str]:
first_key = False
for hd in entry["headers"]: # type: ignore[union-attr]
hd_dict: dict[str, str] = hd # type: ignore[assignment]
lines.append(f' - name: "{_yaml_str_escape(hd_dict["name"])}"')
lines.append(f' value: "{_yaml_str_escape(hd_dict["value"])}"')
lines.append(f' - name: "{hd_dict["name"]}"')
lines.append(f' value: "{hd_dict["value"]}"')
if first_key:
lines.append(" - {}")
return lines
@@ -319,10 +238,10 @@ def egress_render_routes(
return "\n".join(lines) + "\n"
for r in routes:
f = _route_to_yaml_fields(r)
lines.append(f' - host: "{_yaml_str_escape(str(f["host"]))}"')
lines.append(f' - host: "{f["host"]}"')
if "auth_scheme" in f:
lines.append(f' auth_scheme: "{_yaml_str_escape(str(f["auth_scheme"]))}"')
lines.append(f' token_env: "{_yaml_str_escape(str(f["token_env"]))}"')
lines.append(f' auth_scheme: "{f["auth_scheme"]}"')
lines.append(f' token_env: "{f["token_env"]}"')
if "matches" in f:
lines.append(" matches:")
for entry in f["matches"]: # type: ignore[union-attr]
@@ -341,8 +260,6 @@ def egress_render_routes(
elif isinstance(dv, list):
items_str = ", ".join(f'"{x}"' for x in dv)
lines.append(f" {dk}: [{items_str}]")
elif isinstance(dv, str):
lines.append(f' {dk}: "{_yaml_str_escape(dv)}"')
return "\n".join(lines) + "\n"
@@ -382,18 +299,12 @@ class Egress(ABC):
routes_path = stage_dir / EGRESS_ROUTES_FILENAME
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
# scanning; the agent receives the same name/value as exfil bait.
canary = secrets.token_urlsafe(32)
return EgressPlan(
slug=slug,
routes_path=routes_path,
routes=routes,
token_env_map=egress_token_env_map(routes),
log=log,
canary=canary,
canary_env=_random_canary_env(),
)
__all__ = [
@@ -408,7 +319,5 @@ __all__ = [
"egress_render_routes",
"egress_resolve_token_values",
"egress_routes_for_bottle",
"egress_agent_env_entries",
"egress_sidecar_env_entries",
"egress_token_env_map",
]
+22 -282
View File
@@ -5,7 +5,6 @@ egress container."""
from __future__ import annotations
import asyncio
import json
import os
import signal
@@ -17,15 +16,9 @@ from mitmproxy import http # type: ignore[import-not-found] # pylint: disable=
from egress_addon_core import ( # type: ignore[import-not-found] # pylint: disable=import-error
LOG_BLOCKS,
LOG_FULL,
DEFAULT_OUTBOUND_ON_MATCH,
ON_MATCH_BLOCK,
ON_MATCH_REDACT,
Config,
Route,
ScanResult,
build_inbound_scan_text,
build_outbound_scan_text,
build_token_allow_payload,
decide,
decide_git_fetch,
is_git_fetch_request,
@@ -39,55 +32,23 @@ from egress_addon_core import ( # type: ignore[import-not-found] # pylint: dis
)
try:
from dlp_detectors import redact_tokens, strip_crlf # type: ignore[import-not-found]
from dlp_detectors import redact_tokens # type: ignore[import-not-found]
except ImportError: # pragma: no cover - host-side path
from bot_bottle.dlp_detectors import ( # type: ignore[import-not-found]
redact_tokens,
strip_crlf,
)
try:
import supervise as _sv # type: ignore[import-not-found]
except ImportError: # pragma: no cover - host-side path
from bot_bottle import supervise as _sv # type: ignore[import-not-found]
from bot_bottle.dlp_detectors import redact_tokens # type: ignore[import-not-found]
DEFAULT_ROUTES_PATH = "/etc/egress/routes.yaml"
INTROSPECT_HOST = "_egress.local"
# 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
# Filesystem poll cadence while awaiting the operator's response.
TOKEN_ALLOW_POLL_INTERVAL_SECONDS = 0.5
# Fixed operator guidance attached to every token-allow proposal.
_TOKEN_ALLOW_JUSTIFICATION = (
"egress DLP blocked an outbound request carrying a detected token. "
"Approve only if this value is a false positive or a credential this "
"request legitimately needs; the value is then allowed for the life of "
"this bottle's egress proxy."
)
class EgressAddon:
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()
self._supervise_queue_dir = os.environ.get("SUPERVISE_QUEUE_DIR", "").strip()
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_queue_dir and self._supervise_slug)
def _reload(self, *, initial: bool = False) -> None:
try:
text = Path(self.routes_path).read_text(encoding="utf-8")
@@ -160,42 +121,31 @@ class EgressAddon:
)
def _log_request(self, flow: http.HTTPFlow) -> None:
headers = {
k: redact_tokens(v, env=os.environ)
for k, v in flow.request.headers.items()
if k.lower() != "authorization"
}
body = redact_tokens(flow.request.get_text(strict=False) or "", env=os.environ)
sys.stderr.write(
json.dumps({
"event": "egress_request",
"host": redact_tokens(flow.request.pretty_host, env=os.environ),
"method": flow.request.method,
"path": redact_tokens(flow.request.path, env=os.environ),
"headers": headers,
"body": body,
"headers": dict(flow.request.headers),
"body": flow.request.get_text(strict=False) or "",
})
+ "\n"
)
def _log_response(self, flow: http.HTTPFlow) -> None:
headers = {
k: redact_tokens(v, env=os.environ)
for k, v in flow.response.headers.items()
}
body = redact_tokens(flow.response.get_text(strict=False) or "", env=os.environ)
sys.stderr.write(
json.dumps({
"event": "egress_response",
"host": flow.request.pretty_host,
"status": flow.response.status_code,
"headers": headers,
"body": body,
"headers": dict(flow.response.headers),
"body": flow.response.get_text(strict=False) or "",
})
+ "\n"
)
async def request(self, flow: http.HTTPFlow) -> None:
def request(self, flow: http.HTTPFlow) -> None:
request_path, _, query = flow.request.path.partition("?")
if flow.request.pretty_host == INTROSPECT_HOST:
@@ -207,11 +157,21 @@ class EgressAddon:
# Hostname is included to catch DNS-tunnelling exfiltration attempts.
route = match_route(self.config.routes, flow.request.pretty_host)
if route is not None:
if not await self._handle_outbound_dlp(flow, route):
body = flow.request.get_text(strict=False) or ""
scan_text = build_outbound_scan_text(
flow.request.pretty_host,
request_path,
query,
outbound_scan_headers(route, dict(flow.request.headers)),
body,
)
dlp_result = scan_outbound(route, scan_text, os.environ)
if dlp_result is not None and dlp_result.severity == "block":
ctx = self._req_ctx(flow)
if dlp_result.context:
ctx = {**ctx, "context": dlp_result.context}
self._block(flow, f"egress DLP: {dlp_result.reason}", ctx=ctx)
return
# The redact policy may have rewritten the request line; recompute
# the path/query the git checks below rely on.
request_path, _, query = flow.request.path.partition("?")
if is_git_push_request(request_path, query):
self._block(
@@ -261,202 +221,6 @@ class EgressAddon:
if self.config.log >= LOG_FULL:
self._log_request(flow)
def _block_dlp(self, flow: http.HTTPFlow, result: ScanResult) -> None:
ctx = self._req_ctx(flow)
if result.context:
ctx = {**ctx, "context": result.context}
self._block(flow, f"egress DLP: {result.reason}", ctx=ctx)
async def _handle_outbound_dlp(
self,
flow: http.HTTPFlow,
route: Route,
) -> 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`.
Loops so the supervise policy can re-scan after each approval a
second, un-approved token in the same request is still caught."""
while True:
request_path, _, query = flow.request.path.partition("?")
body = flow.request.get_text(strict=False) or ""
headers = outbound_scan_headers(route, dict(flow.request.headers))
scan_text = build_outbound_scan_text(
flow.request.pretty_host, request_path, query, headers, body,
)
# CRLF is scanned only over the request line + headers, never the
# body (see scan_outbound) — a body is not an injection vector.
crlf_text = build_outbound_scan_text(
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,
)
if result is None or result.severity != "block":
return True
policy = route.outbound_on_match or DEFAULT_OUTBOUND_ON_MATCH
# 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.config.log >= LOG_BLOCKS:
sys.stderr.write(json.dumps({
"event": "egress_redacted",
"reason": f"egress DLP: {result.reason}",
**self._req_ctx(flow),
}) + "\n")
return True
self._block(
flow,
f"egress DLP: {result.reason}; redaction could not remove "
"all matches (e.g. a match in the hostname)",
ctx=self._req_ctx(flow),
)
return False
# Structural blocks (CRLF, no safelist-able value) cannot be
# supervised — there is nothing to approve and remember — so under
# block/supervise they are a hard 403.
if policy == ON_MATCH_BLOCK or not result.matched:
self._block_dlp(flow, result)
return False
# 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():
self._block_dlp(flow, result)
return False
approved = await self._supervise_token_block(flow, request_path, result)
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:
"""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."""
body = flow.request.get_text(strict=False)
if body:
redacted_body = redact_tokens(body, env=os.environ)
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))
if redacted != value:
flow.request.headers[name] = redacted
redacted_path = strip_crlf(redact_tokens(flow.request.path, env=os.environ))
if redacted_path != flow.request.path:
flow.request.path = redacted_path
request_path, _, query = flow.request.path.partition("?")
new_body = flow.request.get_text(strict=False) or ""
headers = outbound_scan_headers(route, dict(flow.request.headers))
scan_text = build_outbound_scan_text(
flow.request.pretty_host, request_path, query, headers, new_body,
)
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)
return result is None or result.severity != "block"
async def _supervise_token_block(
self,
flow: http.HTTPFlow,
request_path: str,
result: ScanResult,
) -> 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`)."""
host = flow.request.pretty_host
payload = build_token_allow_payload(
redact_tokens(host, env=os.environ),
flow.request.method,
redact_tokens(request_path, env=os.environ),
result,
)
proposal = _sv.Proposal.new(
bottle_slug=self._supervise_slug,
tool=_sv.TOOL_EGRESS_TOKEN_ALLOW,
proposed_file=payload,
justification=_TOKEN_ALLOW_JUSTIFICATION,
current_file_hash=_sv.sha256_hex(payload),
)
queue_dir = Path(self._supervise_queue_dir)
try:
_sv.write_proposal(queue_dir, proposal)
except OSError as e:
sys.stderr.write(
f"egress: could not queue token-allow proposal: {e}; "
"blocking request\n"
)
self._block(flow, f"egress DLP: {result.reason}", ctx=self._req_ctx(flow))
return False
sys.stderr.write(json.dumps({
"event": "egress_token_supervise",
"reason": f"egress DLP: {result.reason}",
"proposal": proposal.id,
**self._req_ctx(flow),
}) + "\n")
response = await self._await_token_response(queue_dir, proposal.id)
_sv.archive_proposal(queue_dir, proposal.id)
if response is not None and response.status in (
_sv.STATUS_APPROVED, _sv.STATUS_MODIFIED,
):
self.safe_tokens.add(result.matched)
if self.config.log >= LOG_BLOCKS:
sys.stderr.write(json.dumps({
"event": "egress_token_allowed",
"reason": f"egress DLP: {result.reason}",
"proposal": proposal.id,
**self._req_ctx(flow),
}) + "\n")
return True
if response is None:
reason = (
f"egress DLP: {result.reason}; supervisor approval timed out "
f"after {self._token_allow_timeout:g}s"
)
else:
reason = f"egress DLP: {result.reason}; supervisor rejected the request"
self._block(flow, reason, ctx=self._req_ctx(flow))
return False
async def _await_token_response(
self,
queue_dir: Path,
proposal_id: str,
) -> "_sv.Response | None":
"""Poll the queue dir for the operator's response without blocking the
proxy event loop. Returns the Response, or None on timeout."""
loop = asyncio.get_running_loop()
deadline = loop.time() + self._token_allow_timeout
while True:
try:
return _sv.read_response(queue_dir, proposal_id)
except (OSError, ValueError, KeyError):
# Not written yet, or a partial/malformed write — retry until
# the deadline, then fail closed.
pass
if loop.time() >= deadline:
return None
await asyncio.sleep(TOKEN_ALLOW_POLL_INTERVAL_SECONDS)
def response(self, flow: http.HTTPFlow) -> None:
"""DLP inbound scan on response headers and body."""
route = match_route(self.config.routes, flow.request.pretty_host)
@@ -508,12 +272,7 @@ class EgressAddon:
message = flow.websocket.messages[-1] # type: ignore[union-attr]
content = message.content.decode("utf-8", errors="replace")
if message.from_client:
# A WebSocket data frame is not an HTTP request line, so CRLF is
# not an injection vector here — scan only for credential leakage.
result = scan_outbound(
route, content, os.environ,
safe_tokens=self.safe_tokens, crlf_text="",
)
result = scan_outbound(route, content, os.environ)
if result is not None and result.severity == "block":
sys.stderr.write(f"egress DLP: {result.reason}\n")
flow.kill() # type: ignore[union-attr]
@@ -527,23 +286,4 @@ class EgressAddon:
sys.stderr.write(f"egress DLP warn: {result.reason}\n")
def _token_allow_timeout_from_env(env: "os._Environ[str]") -> float:
"""Read EGRESS_TOKEN_ALLOW_TIMEOUT_SECONDS; fall back to the default on an
unset or invalid value (a bad value should not wedge egress at boot)."""
raw = env.get("EGRESS_TOKEN_ALLOW_TIMEOUT_SECONDS", "").strip()
if not raw:
return DEFAULT_TOKEN_ALLOW_TIMEOUT_SECONDS
try:
value = float(raw)
except ValueError:
value = 0.0
if value <= 0:
sys.stderr.write(
"egress: invalid EGRESS_TOKEN_ALLOW_TIMEOUT_SECONDS="
f"{raw!r}; using default {DEFAULT_TOKEN_ALLOW_TIMEOUT_SECONDS:g}s\n"
)
return DEFAULT_TOKEN_ALLOW_TIMEOUT_SECONDS
return value
addons = [EgressAddon()]
+24 -110
View File
@@ -34,18 +34,9 @@ VALID_METHODS = frozenset({
"CONNECT",
})
OUTBOUND_DETECTOR_NAMES = frozenset({"token_patterns", "known_secrets", "entropy"})
OUTBOUND_DETECTOR_NAMES = frozenset({"token_patterns", "known_secrets"})
INBOUND_DETECTOR_NAMES = frozenset({"naive_injection_detection"})
# Per-route policy for what the proxy does when an outbound DLP detector
# matches a token (PRD 0062).
ON_MATCH_BLOCK = "block" # hard 403, never overridable
ON_MATCH_REDACT = "redact" # scrub the matched value, forward the request
ON_MATCH_SUPERVISE = "supervise" # queue for operator approval, hold the request
OUTBOUND_ON_MATCH_VALUES = (ON_MATCH_BLOCK, ON_MATCH_REDACT, ON_MATCH_SUPERVISE)
# Unset resolves to supervise (fall back to block when supervise is not wired).
DEFAULT_OUTBOUND_ON_MATCH = ON_MATCH_SUPERVISE
@dataclass(frozen=True)
class PathMatch:
@@ -78,8 +69,6 @@ class Route:
git_fetch: bool = False
outbound_detectors: tuple[str, ...] | None = None
inbound_detectors: tuple[str, ...] | None = None
# "" means unset → DEFAULT_OUTBOUND_ON_MATCH. See OUTBOUND_ON_MATCH_VALUES.
outbound_on_match: str = ""
LOG_OFF = 0 # no logging
@@ -106,11 +95,6 @@ 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
# 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.
matched: str = ""
# ---------------------------------------------------------------------------
@@ -234,12 +218,12 @@ def _parse_detectors(
idx: int,
host: str,
raw_dict: dict[str, object],
) -> tuple[tuple[str, ...] | None, tuple[str, ...] | None, str]:
) -> tuple[tuple[str, ...] | None, tuple[str, ...] | None]:
"""Parse the optional `dlp` block on a route, returning
(outbound_detectors, inbound_detectors, outbound_on_match)."""
(outbound_detectors, inbound_detectors)."""
dlp_raw = raw_dict.get("dlp")
if dlp_raw is None:
return None, None, ""
return None, None
label = f"route[{idx}] ({host})"
if not isinstance(dlp_raw, dict):
raise ValueError(f"{label}: 'dlp' must be an object")
@@ -276,24 +260,13 @@ def _parse_detectors(
outbound = _parse_detector_field("outbound_detectors", OUTBOUND_DETECTOR_NAMES)
inbound = _parse_detector_field("inbound_detectors", INBOUND_DETECTOR_NAMES)
on_match = ""
on_match_raw = dlp.get("outbound_on_match")
if on_match_raw is not None:
if not isinstance(on_match_raw, str) or on_match_raw not in OUTBOUND_ON_MATCH_VALUES:
raise ValueError(
f"{label}: dlp.outbound_on_match must be one of "
f"{', '.join(OUTBOUND_ON_MATCH_VALUES)} (got {on_match_raw!r})"
)
on_match = on_match_raw
for k in dlp:
if k not in ("outbound_detectors", "inbound_detectors", "outbound_on_match"):
if k not in ("outbound_detectors", "inbound_detectors"):
raise ValueError(
f"{label}: dlp has unknown key {k!r}; accepted keys "
f"are 'outbound_detectors', 'inbound_detectors', "
f"'outbound_on_match'"
f"are 'outbound_detectors', 'inbound_detectors'"
)
return outbound, inbound, on_match
return outbound, inbound
def parse_routes(payload: object) -> tuple[Route, ...]:
@@ -364,7 +337,7 @@ def _parse_one(idx: int, raw: object) -> Route:
)
# dlp detectors
outbound_detectors, inbound_detectors, outbound_on_match = _parse_detectors(
outbound_detectors, inbound_detectors = _parse_detectors(
idx, host, raw_dict,
)
@@ -383,7 +356,6 @@ def _parse_one(idx: int, raw: object) -> Route:
git_fetch=git_fetch,
outbound_detectors=outbound_detectors,
inbound_detectors=inbound_detectors,
outbound_on_match=outbound_on_match,
)
@@ -432,13 +404,20 @@ def route_to_yaml_dict(r: Route) -> dict[str, object]:
dlp["outbound_detectors"] = list(r.outbound_detectors)
if r.inbound_detectors is not None:
dlp["inbound_detectors"] = list(r.inbound_detectors)
if r.outbound_on_match:
dlp["outbound_on_match"] = r.outbound_on_match
if dlp:
d["dlp"] = dlp
return d
def load_routes(text: str) -> tuple[Route, ...]:
"""Parse YAML text → routes."""
try:
payload = parse_yaml_subset(text)
except YamlSubsetError as e:
raise ValueError(f"routes payload: invalid YAML: {e}") from e
return parse_routes(payload)
def parse_config(payload: object) -> "Config":
"""Parse a full egress config payload (top-level log level + routes)."""
if not isinstance(payload, dict):
@@ -711,103 +690,43 @@ def scan_outbound(
route: Route,
body: str | bytes,
environ: typing.Mapping[str, str],
*,
safe_tokens: typing.AbstractSet[str] | None = None,
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).
try:
from dlp_detectors import ( # type: ignore[import-not-found]
scan_crlf_injection,
scan_entropy,
scan_known_secrets,
scan_token_patterns,
)
except ImportError: # pragma: no cover - host-side path
from .dlp_detectors import ( # type: ignore[import-not-found]
scan_crlf_injection,
scan_entropy,
scan_known_secrets,
scan_token_patterns,
)
# Binary bodies: latin-1 is a bijective byte↔codepoint mapping that
# preserves every byte value, so ASCII-range secret strings remain
# findable by str.find / regex. Prefer strict UTF-8 for valid text bodies.
if isinstance(body, bytes):
try:
text = body.decode("utf-8")
except UnicodeDecodeError:
text = body.decode("latin-1")
else:
text = body
text = body if isinstance(body, str) else body.decode("utf-8", errors="replace")
# CRLF injection is only an attack in the request line + headers, never the
# body: an HTTP body is delimited by Content-Length, so CRLF bytes there
# cannot split the request. Scanning the body produces false positives on
# legitimate form-encoded / multi-line content. Callers pass the
# body-excluded surfaces as `crlf_text`; `None` falls back to the full text
# for backward-compatible callers (host-side tests, websocket frames).
crlf_target = text if crlf_text is None else crlf_text
result = scan_crlf_injection(crlf_target)
# CRLF injection is never legitimate — runs unconditionally, not gated
# by outbound_detectors config.
result = scan_crlf_injection(text)
if result is not None:
return result
if _detector_enabled(route.outbound_detectors, "token_patterns"):
result = scan_token_patterns(text, location="body", safe_tokens=safe_tokens)
result = scan_token_patterns(text, location="body")
if result is not None:
return result
if _detector_enabled(route.outbound_detectors, "known_secrets"):
# BOT_BOTTLE_SENSITIVE_PREFIXES lets operators add extra env prefixes
# beyond EGRESS_TOKEN_* without changing the manifest schema.
extra_raw = environ.get("BOT_BOTTLE_SENSITIVE_PREFIXES", "")
extra = tuple(p for p in extra_raw.split(",") if p)
sensitive_prefixes = ("EGRESS_TOKEN_",) + extra
result = scan_known_secrets(
text, location="body", env=environ,
sensitive_prefixes=sensitive_prefixes, safe_tokens=safe_tokens,
)
if result is not None:
return result
# Entropy scanning requires explicit opt-in: it is NOT part of the
# default "all detectors" set because it produces false positives on
# legitimate base64 / binary payloads. Routes must list "entropy" in
# dlp.outbound_detectors to enable it.
if (
route.outbound_detectors is not None
and "entropy" in route.outbound_detectors
):
result = scan_entropy(text, location="body")
result = scan_known_secrets(text, location="body", env=environ)
if result is not None:
return result
return None
def build_token_allow_payload(
host: str,
method: str,
path: str,
result: ScanResult,
) -> str:
"""Render the human-readable supervisor proposal body for an outbound
token block (PRD 0062). Carries the host/method/path, the detector
reason, and the redacted context snippet never the raw token value."""
lines = [
"egress blocked an outbound request carrying a detected token",
f"host: {host}",
f"method: {method}",
f"path: {path}",
f"detector: {result.reason}",
]
if result.context:
lines.append(f"context: {result.context}")
return "\n".join(lines) + "\n"
def scan_inbound(
route: Route,
body: str | bytes,
@@ -832,11 +751,6 @@ __all__ = [
"route_to_yaml_dict",
"LOG_FULL",
"LOG_OFF",
"ON_MATCH_BLOCK",
"ON_MATCH_REDACT",
"ON_MATCH_SUPERVISE",
"OUTBOUND_ON_MATCH_VALUES",
"DEFAULT_OUTBOUND_ON_MATCH",
"Config",
"Decision",
"HeaderMatch",
@@ -846,13 +760,13 @@ __all__ = [
"ScanResult",
"build_inbound_scan_text",
"build_outbound_scan_text",
"build_token_allow_payload",
"decide",
"decide_git_fetch",
"evaluate_matches",
"is_git_push_request",
"is_git_fetch_request",
"load_config",
"load_routes",
"match_route",
"outbound_scan_headers",
"parse_config",
+6 -17
View File
@@ -43,10 +43,10 @@ from .manifest import ManifestBottle, ManifestGitEntry
# Short network alias for git-gate inside the sidecar bundle. 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:
# git daemon (--timeout/--init-timeout), the access-hook subprocess in
# git_http_backend, and the git http-backend CGI subprocess.
GIT_GATE_TIMEOUT_SECS = 15
# Bound half-open git client sessions. If an agent/tool runner is
# interrupted during push, git daemon should reap the receive-pack
# child instead of keeping the gate wedged indefinitely.
GIT_GATE_DAEMON_TIMEOUT_SECS = 15
@dataclass(frozen=True)
@@ -112,15 +112,6 @@ def git_gate_upstreams_for_bottle(bottle: ManifestBottle) -> tuple[GitGateUpstre
)
def _gitconfig_validate_value(field: str, value: str) -> None:
"""Raise ValueError if value contains characters that break gitconfig line syntax."""
if "\n" in value or "\r" in value:
raise ValueError(
f"git-gate: {field} contains a newline, which would inject "
f"arbitrary gitconfig keys; rejecting manifest entry"
)
def git_gate_render_gitconfig(
entries: tuple[ManifestGitEntry, ...], gate_host: str, *, scheme: str = "git",
) -> str:
@@ -145,7 +136,6 @@ def git_gate_render_gitconfig(
"# fetch-from-upstream-before-every-upload-pack via access-hook).\n",
]
for entry in entries:
_gitconfig_validate_value(f"repos[{entry.Name!r}].url", entry.Upstream)
out.append(f'[url "{scheme}://{gate_host}/{entry.Name}.git"]\n')
out.append(f"\tinsteadOf = {entry.Upstream}\n")
if entry.RemoteKey and entry.RemoteKey != entry.UpstreamHost:
@@ -158,7 +148,6 @@ def git_gate_render_gitconfig(
f"ssh://{entry.UpstreamUser}@{entry.RemoteKey}{port}/"
f"{entry.UpstreamPath}"
)
_gitconfig_validate_value(f"repos[{entry.Name!r}].url (resolved alias)", alias)
out.append(f"\tinsteadOf = {alias}\n")
return "".join(out)
@@ -228,8 +217,8 @@ def git_gate_render_entrypoint(upstreams: tuple[GitGateUpstream, ...]) -> str:
"",
"exec git daemon \\",
" --reuseaddr \\",
f" --timeout={GIT_GATE_TIMEOUT_SECS} \\",
f" --init-timeout={GIT_GATE_TIMEOUT_SECS} \\",
f" --timeout={GIT_GATE_DAEMON_TIMEOUT_SECS} \\",
f" --init-timeout={GIT_GATE_DAEMON_TIMEOUT_SECS} \\",
" --base-path=/git \\",
" --export-all \\",
" --enable=receive-pack \\",
+1 -11
View File
@@ -16,8 +16,6 @@ from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
from pathlib import Path
from urllib.parse import urlsplit
from .git_gate import GIT_GATE_TIMEOUT_SECS
DEFAULT_PORT = 9420
@@ -49,7 +47,6 @@ class GitHttpHandler(BaseHTTPRequestHandler):
[hook_path, "upload-pack", str(repo_dir), peer, peer],
capture_output=True,
check=False,
timeout=GIT_GATE_TIMEOUT_SECS,
)
if hook.returncode != 0:
detail = (hook.stderr or hook.stdout).decode(
@@ -113,7 +110,6 @@ class GitHttpHandler(BaseHTTPRequestHandler):
env=env,
capture_output=True,
check=False,
timeout=GIT_GATE_TIMEOUT_SECS,
)
self._write_cgi_response(proc.stdout)
@@ -152,13 +148,7 @@ class GitHttpHandler(BaseHTTPRequestHandler):
key, _, value = line.decode("latin1").partition(":")
value = value.strip()
if key.lower() == "status":
try:
status = int(value.split()[0])
except (ValueError, IndexError):
self.log_message(
"malformed CGI Status header %r; using 500", value,
)
status = 500
status = int(value.split()[0])
else:
headers.append((key, value))
self.send_response(status)
+10 -96
View File
@@ -1,107 +1,21 @@
"""Tiny logging wrappers. All output goes to stderr.
Two capabilities layer onto the bare wrappers (issue #252):
- **Levels.** `debug` / `info` / `warn` / `error` carry an ordered
severity. Output is gated by `BOT_BOTTLE_LOG_LEVEL` (debug | info |
warn | error; default `info`). A message emits when its severity is
at or above the threshold, so `debug` is silent by default and
`error` always surfaces (nothing sits above it) which keeps the
fatal `die` path visible regardless of the configured level.
- **Context.** Every wrapper takes an optional `context` mapping that
renders as a parseable ` [k=v ...]` suffix (keys sorted; values with
whitespace/quotes are quoted), so failures can be filtered and
correlated instead of being flat strings.
With no `context` and the default level, output is byte-identical to the
original `bot-bottle: <msg>` / `bot-bottle: warning: <msg>` /
`bot-bottle: error: <msg>` lines the 100+ existing call sites are
unaffected.
"""
"""Tiny logging wrappers. All output goes to stderr."""
from __future__ import annotations
import os
import sys
from typing import Mapping, NoReturn
# Ordered severities. Gaps left between values so intermediate levels
# can be added later without renumbering.
DEBUG = 10
INFO = 20
WARN = 30
ERROR = 40
_LEVEL_NAMES: dict[str, int] = {
"debug": DEBUG,
"info": INFO,
"warn": WARN,
"warning": WARN,
"error": ERROR,
}
# Default threshold when BOT_BOTTLE_LOG_LEVEL is unset or unrecognised.
_DEFAULT_THRESHOLD = INFO
_LOG_LEVEL_ENV = "BOT_BOTTLE_LOG_LEVEL"
from typing import NoReturn
def _threshold() -> int:
"""Resolve the active level threshold from the environment.
Read per-call (not cached) so the level can be changed at runtime
and so tests can patch `os.environ` without a reload. Unknown values
fall back to the default rather than raising logging must never be
the thing that crashes the process."""
raw = os.environ.get(_LOG_LEVEL_ENV, "")
return _LEVEL_NAMES.get(raw.strip().lower(), _DEFAULT_THRESHOLD)
def info(msg: str) -> None:
print(f"bot-bottle: {msg}", file=sys.stderr)
def _format_context(context: Mapping[str, object] | None) -> str:
"""Render a context mapping as a ` [k=v k2=v2]` suffix.
Keys are sorted for stable, diffable output. Values that are empty or
contain whitespace or a quote are wrapped in double quotes (with inner
quotes escaped) so each `k=v` pair stays parseable. Empty/None context
renders as the empty string."""
if not context:
return ""
parts: list[str] = []
for key in sorted(context):
value = str(context[key])
if value == "" or any(ch.isspace() for ch in value) or '"' in value:
value = '"' + value.replace('"', '\\"') + '"'
parts.append(f"{key}={value}")
return " [" + " ".join(parts) + "]"
def warn(msg: str) -> None:
print(f"bot-bottle: warning: {msg}", file=sys.stderr)
def _emit(
level: int,
label: str,
msg: str,
context: Mapping[str, object] | None,
) -> None:
if level < _threshold():
return
prefix = f"{label}: " if label else ""
sys.stderr.write(f"bot-bottle: {prefix}{msg}{_format_context(context)}\n")
def debug(msg: str, *, context: Mapping[str, object] | None = None) -> None:
_emit(DEBUG, "debug", msg, context)
def info(msg: str, *, context: Mapping[str, object] | None = None) -> None:
_emit(INFO, "", msg, context)
def warn(msg: str, *, context: Mapping[str, object] | None = None) -> None:
_emit(WARN, "warning", msg, context)
def error(msg: str, *, context: Mapping[str, object] | None = None) -> None:
_emit(ERROR, "error", msg, context)
def error(msg: str) -> None:
print(f"bot-bottle: error: {msg}", file=sys.stderr)
class Die(SystemExit):
@@ -117,6 +31,6 @@ class Die(SystemExit):
self.message = message
def die(msg: str, *, context: Mapping[str, object] | None = None) -> NoReturn:
error(msg, context=context)
def die(msg: str) -> NoReturn:
error(msg)
raise Die(1, msg)
+18 -105
View File
@@ -113,8 +113,10 @@ class ManifestBottle:
egress: ManifestEgressConfig = field(default_factory=ManifestEgressConfig)
# Per-bottle stuck-recovery sidecar (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.
# sidecar that exposes MCP tools to the agent (egress-block,
# capability-block) plus mounts the current-config dir read-only
# into the agent at /etc/bot-bottle/current-config. Set
# `supervise: false` to skip the sidecar and mount.
supervise: bool = True
@classmethod
@@ -213,65 +215,6 @@ def _merge_git_user(
)
def _resolve_effective_bottle_eager(
agent_name: str,
agent: "ManifestAgent",
bottle_names: "tuple[str, ...]",
bottles: "Mapping[str, ManifestBottle]",
) -> "ManifestBottle":
"""Return the effective ManifestBottle for the eager (from_json_obj) path.
When bottle_names is non-empty they are merged in order. When empty, falls
back to agent.bottle. Raises ManifestError when neither is set."""
from .manifest_extends import merge_bottles_runtime
if bottle_names:
resolved: list[ManifestBottle] = []
for bn in bottle_names:
if bn not in bottles:
available = ", ".join(sorted(bottles.keys())) or "(none)"
raise ManifestError(
f"bottle '{bn}' not defined. Available: {available}"
)
resolved.append(bottles[bn])
return merge_bottles_runtime(resolved)
if not agent.bottle:
raise ManifestError(
f"agent '{agent_name}' has no 'bottle' field and no bottles were "
f"selected at launch. Select at least one bottle or add "
f"'bottle: <name>' to the agent manifest."
)
return bottles[agent.bottle]
def _resolve_effective_bottle_lazy(
agent_name: str,
agent_bottle: str,
bottle_names: "tuple[str, ...]",
bottles_dir: "Path",
) -> "ManifestBottle":
"""Return the effective ManifestBottle for the lazy (from_md_dirs) path.
When bottle_names is non-empty they are resolved from disk and merged in
order. When empty, falls back to agent_bottle. Raises ManifestError when
neither is set."""
from .manifest_extends import merge_bottles_runtime
from .manifest_loader import load_bottle_chain_from_dir
if bottle_names:
resolved = [load_bottle_chain_from_dir(bn, bottles_dir) for bn in bottle_names]
return merge_bottles_runtime(resolved)
if not agent_bottle:
raise ManifestError(
f"agent '{agent_name}' has no 'bottle' field and no bottles were "
f"selected at launch. Select at least one bottle or add "
f"'bottle: <name>' to the agent manifest."
)
return load_bottle_chain_from_dir(agent_bottle, bottles_dir)
@dataclass(frozen=True)
class Manifest:
"""Single-agent/bottle value type. Returned by ManifestIndex.load_for_agent().
@@ -417,18 +360,6 @@ class ManifestIndex:
}
return cls(bottles=bottles, agents=agents)
@property
def all_bottle_names(self) -> list[str]:
"""Sorted list of all discoverable bottle names.
In names-only mode (from resolve/from_md_dirs) this scans bottle
filenames without reading their content. In eager mode (from
from_json_obj) it returns the pre-parsed bottles' names."""
if self.home_md is not None:
from .manifest_loader import scan_bottle_names
return scan_bottle_names(self.home_md / "bottles")
return sorted(self.bottles.keys())
@property
def all_agent_names(self) -> list[str]:
"""Sorted list of all discoverable agent names.
@@ -445,18 +376,9 @@ class ManifestIndex:
return sorted(home_names | cwd_names)
return sorted(self.agents.keys())
def load_for_agent(
self,
agent_name: str,
bottle_names: "tuple[str, ...] | None" = None,
) -> "Manifest":
def load_for_agent(self, agent_name: str) -> "Manifest":
"""Parse the named agent and its bottle; return a single-value Manifest.
`bottle_names` is an ordered list of bottles selected at launch time.
When non-empty they are resolved and merged in order (index 0 = base;
later entries override). When empty or None, falls back to the agent's
own `bottle:` field. Raises ManifestError when neither is set.
In lazy mode (from resolve/from_md_dirs) the agent file and its
bottle chain are read from disk for the first time here. In eager
mode (from_json_obj) the data is already parsed; this just filters
@@ -467,8 +389,6 @@ class ManifestIndex:
Always raises ManifestError if the agent is unknown or invalid.
Backends call this at preflight inside _validate."""
effective_bottle_names: tuple[str, ...] = bottle_names or ()
if self.home_md is None:
# Eager manifest (from_json_obj): data already parsed; filter to
# the one requested agent and its bottle so the returned Manifest
@@ -479,14 +399,12 @@ class ManifestIndex:
f"agent '{agent_name}' not defined. Available: {available}"
)
agent = self.agents[agent_name]
raw_bottle = _resolve_effective_bottle_eager(
agent_name, agent, effective_bottle_names, self.bottles
)
raw_bottle = self.bottles[agent.bottle]
merged = _merge_git_user(agent.git_user, raw_bottle.git_user)
bottle = raw_bottle if merged == raw_bottle.git_user else replace(raw_bottle, git_user=merged)
return Manifest(agent=agent, bottle=bottle)
from .manifest_loader import scan_agent_names
from .manifest_loader import load_bottle_chain_from_dir, scan_agent_names
from .manifest_schema import validate_agent_frontmatter_keys
from .yaml_subset import YamlSubsetError, parse_frontmatter
@@ -513,31 +431,26 @@ class ManifestIndex:
validate_agent_frontmatter_keys(agent_path, fm.keys())
# Determine the effective bottle name(s).
agent_bottle = fm.get("bottle") or ""
bottle_name = fm.get("bottle")
if not isinstance(bottle_name, str) or not bottle_name:
raise ManifestError(
f"agent '{agent_name}' must declare a 'bottle' field "
f"naming a defined bottle"
)
# Load the bottle chain (may raise ManifestError).
bottles_dir = self.home_md / "bottles"
raw_bottle = _resolve_effective_bottle_lazy(
agent_name, str(agent_bottle), effective_bottle_names, bottles_dir
)
effective_bottle_name = (
effective_bottle_names[-1] if effective_bottle_names
else str(agent_bottle)
)
raw_bottle = load_bottle_chain_from_dir(bottle_name, bottles_dir)
# Build and validate the full ManifestAgent.
agent_dict: dict[str, object] = {
"bottle": bottle_name,
"skills": fm.get("skills", []),
"prompt": body.strip(),
}
if agent_bottle:
agent_dict["bottle"] = agent_bottle
if "git-gate" in fm:
agent_dict["git-gate"] = fm["git-gate"]
# Pass the effective bottle name as the known-bottles set so agents
# that have bottle: set are validated; agents without bottle: pass {}
# since bottle_names were already resolved above.
known = {effective_bottle_name} if effective_bottle_name else set()
agent = ManifestAgent.from_dict(agent_name, agent_dict, known)
agent = ManifestAgent.from_dict(agent_name, agent_dict, {bottle_name})
merged_user = _merge_git_user(agent.git_user, raw_bottle.git_user)
bottle = raw_bottle if merged_user == raw_bottle.git_user else replace(raw_bottle, git_user=merged_user)
+19 -44
View File
@@ -109,8 +109,7 @@ class ManifestAgentProvider:
@dataclass(frozen=True)
class ManifestAgent:
# Optional: when empty the operator selects bottles at launch time.
bottle: str = ""
bottle: str
skills: tuple[str, ...] = ()
prompt: str = ""
# Per-agent git identity (issue #94). Overlays the referenced
@@ -130,20 +129,18 @@ class ManifestAgent:
f"allowed keys are {allowed}."
)
bottle_raw = d.get("bottle")
bottle = ""
if bottle_raw is not None:
if not isinstance(bottle_raw, str) or not bottle_raw:
raise ManifestError(
f"agent '{name}' bottle must be a non-empty string when declared"
)
if bottle_raw not in bottle_names:
available = ", ".join(sorted(bottle_names)) or "(none defined)"
raise ManifestError(
f"agent '{name}' references bottle '{bottle_raw}', which is not defined. "
f"Available: {available}"
)
bottle = bottle_raw
bottle = d.get("bottle")
if not isinstance(bottle, str) or not bottle:
raise ManifestError(
f"agent '{name}' must declare a 'bottle' field naming a "
f"defined bottle"
)
if bottle not in bottle_names:
available = ", ".join(sorted(bottle_names)) or "(none defined)"
raise ManifestError(
f"agent '{name}' references bottle '{bottle}', which is not defined. "
f"Available: {available}"
)
skills: tuple[str, ...] = ()
skills_raw = d.get("skills")
@@ -202,10 +199,13 @@ def _parse_provider_settings(
) -> dict[str, object]:
if raw is None:
return {}
if template != "pi":
raise ManifestError(
f"bottle '{bottle_name}' agent_provider.settings is only "
"supported for template 'pi'"
)
settings = as_json_object(raw, f"bottle '{bottle_name}' agent_provider.settings")
common_allowed = {"startup_args"}
pi_allowed = {
allowed = {
"provider",
"base_url",
"api",
@@ -218,37 +218,12 @@ def _parse_provider_settings(
"supports_developer_role",
"supports_reasoning_effort",
}
if template == "pi":
allowed = common_allowed | pi_allowed
elif template in ("claude", "codex"):
allowed = common_allowed
elif template not in PROVIDER_TEMPLATES:
return dict(settings)
else:
allowed = common_allowed
for key in settings:
if key not in allowed:
raise ManifestError(
f"bottle '{bottle_name}' agent_provider.settings has unknown "
f"key {key!r}; allowed: {', '.join(sorted(allowed))}"
)
startup_args = settings.get("startup_args")
if startup_args is not None:
if not isinstance(startup_args, list):
raise ManifestError(
f"bottle '{bottle_name}' agent_provider.settings.startup_args "
f"must be an array of strings"
)
for i, arg in enumerate(startup_args):
if not isinstance(arg, str) or not arg:
raise ManifestError(
f"bottle '{bottle_name}' agent_provider.settings."
f"startup_args[{i}] must be a non-empty string"
)
if template != "pi":
return dict(settings)
for key in ("provider", "base_url", "api", "api_key", "api_key_env"):
value = settings.get(key)
if value is not None and (not isinstance(value, str) or not value):
+5 -22
View File
@@ -21,9 +21,6 @@ VALID_METHODS = frozenset({
OUTBOUND_DETECTOR_NAMES = frozenset({"token_patterns", "known_secrets"})
INBOUND_DETECTOR_NAMES = frozenset({"naive_injection_detection"})
# What the proxy does on an outbound token match (PRD 0062).
OUTBOUND_ON_MATCH_VALUES = ("block", "redact", "supervise")
def validate_egress_routes(
bottle_name: str,
@@ -70,7 +67,6 @@ class ManifestEgressRoute:
GitFetch: bool = False
OutboundDetectors: tuple[str, ...] | None = None
InboundDetectors: tuple[str, ...] | None = None
OutboundOnMatch: str = ""
@classmethod
def from_dict(cls, bottle_name: str, idx: int, raw: object) -> "ManifestEgressRoute":
@@ -165,9 +161,8 @@ class ManifestEgressRoute:
# --- dlp ---
outbound_detectors: tuple[str, ...] | None = None
inbound_detectors: tuple[str, ...] | None = None
outbound_on_match = ""
if "dlp" in d:
outbound_detectors, inbound_detectors, outbound_on_match = _parse_dlp_block(
outbound_detectors, inbound_detectors = _parse_dlp_block(
label, d.get("dlp"),
)
@@ -206,7 +201,6 @@ class ManifestEgressRoute:
GitFetch=git_fetch,
OutboundDetectors=outbound_detectors,
InboundDetectors=inbound_detectors,
OutboundOnMatch=outbound_on_match,
)
@@ -329,7 +323,7 @@ def _parse_header_match(
def _parse_dlp_block(
route_label: str,
raw: object,
) -> tuple[tuple[str, ...] | None, tuple[str, ...] | None, str]:
) -> tuple[tuple[str, ...] | None, tuple[str, ...] | None]:
label = f"{route_label} dlp"
d = as_json_object(raw, label)
@@ -364,24 +358,13 @@ def _parse_dlp_block(
outbound = _parse_field("outbound_detectors", OUTBOUND_DETECTOR_NAMES)
inbound = _parse_field("inbound_detectors", INBOUND_DETECTOR_NAMES)
on_match = ""
on_match_raw = d.get("outbound_on_match")
if on_match_raw is not None:
if not isinstance(on_match_raw, str) or on_match_raw not in OUTBOUND_ON_MATCH_VALUES:
raise ManifestError(
f"{label} outbound_on_match must be one of "
f"{', '.join(OUTBOUND_ON_MATCH_VALUES)} (got {on_match_raw!r})"
)
on_match = on_match_raw
for k in d:
if k not in ("outbound_detectors", "inbound_detectors", "outbound_on_match"):
if k not in ("outbound_detectors", "inbound_detectors"):
raise ManifestError(
f"{label} has unknown key {k!r}; accepted keys are "
f"'outbound_detectors', 'inbound_detectors', "
f"'outbound_on_match'"
f"'outbound_detectors', 'inbound_detectors'"
)
return outbound, inbound, on_match
return outbound, inbound
LOG_LEVELS = frozenset({0, 1, 2})
+18 -162
View File
@@ -9,58 +9,6 @@ if TYPE_CHECKING:
from .manifest_egress import ManifestEgressConfig
def merge_bottles_runtime(bottles: "list[ManifestBottle]") -> "ManifestBottle":
"""Merge an ordered list of pre-resolved ManifestBottle objects.
Index 0 is the base; each subsequent entry is applied on top using
the same field-merge rules as the file-based extends machinery:
env: dict merge, later wins; git_user: per-field overlay, later
wins on non-empty; git (repos): union by name, later wins; egress
routes: concatenate; agent_provider, supervise: later replaces.
"""
if not bottles:
raise ValueError("merge_bottles_runtime requires at least one bottle")
result = bottles[0]
for override in bottles[1:]:
result = _merge_two_bottles_runtime(result, override)
return result
def _merge_two_bottles_runtime(base: "ManifestBottle", override: "ManifestBottle") -> "ManifestBottle":
from .manifest import ManifestBottle, ManifestGitUser
from .manifest_egress import ManifestEgressConfig
merged_env = {**base.env, **override.env}
merged_git_user = ManifestGitUser(
name=override.git_user.name or base.git_user.name,
email=override.git_user.email or base.git_user.email,
)
# git repos: union keyed by Name, override wins per-name.
base_repos_by_name = {entry.Name: entry for entry in base.git}
override_repos_by_name = {entry.Name: entry for entry in override.git}
merged_repos_names = list(base_repos_by_name) + [
n for n in override_repos_by_name if n not in base_repos_by_name
]
merged_git = tuple(
override_repos_by_name.get(n, base_repos_by_name[n])
for n in merged_repos_names
)
merged_routes = base.egress.routes + override.egress.routes
merged_egress = ManifestEgressConfig(routes=merged_routes, Log=override.egress.Log)
return ManifestBottle(
env=merged_env,
agent_provider=override.agent_provider,
git=merged_git,
git_user=merged_git_user,
egress=merged_egress,
supervise=override.supervise,
)
def resolve_bottles(raws: dict[str, dict[str, object]]) -> dict[str, ManifestBottle]:
"""Apply `extends:` chains and return resolved ManifestBottle objects."""
cache: dict[str, ManifestBottle] = {}
@@ -101,125 +49,33 @@ def _resolve_one_bottle(
repos_cache[name] = _resolve_repos_raw({}, child_raw)
return bottle
# Normalize to list, accepting both str and list[str].
raw_list: list[object]
if isinstance(parent_name_raw, str):
raw_list = [parent_name_raw]
elif isinstance(parent_name_raw, list):
raw_list = parent_name_raw
else:
if not isinstance(parent_name_raw, str):
raise ManifestError(
f"bottle '{name}' extends must be a string or list of strings "
f"bottle '{name}' extends must be a string "
f"(was {type(parent_name_raw).__name__})"
)
# Validate each entry before resolving any of them.
parent_names: list[str] = []
for i, pname in enumerate(raw_list):
if not isinstance(pname, str):
raise ManifestError(
f"bottle '{name}' extends[{i}] must be a string "
f"(was {type(pname).__name__})"
)
parent_names.append(pname)
if pname == name:
raise ManifestError(
f"bottle '{name}' extends itself; remove the self-reference"
)
if pname not in raws:
avail = ", ".join(sorted(raws.keys())) or "(none)"
raise ManifestError(
f"bottle '{name}' extends '{pname}' which is not "
f"defined. Available bottles: {avail}"
)
combined_parent, combined_repos_raw = _fold_parents(
parent_names, raws, cache, repos_cache, seen + (name,)
parent_name: str = parent_name_raw
if parent_name == name:
raise ManifestError(
f"bottle '{name}' extends itself; remove the "
f"self-reference"
)
if parent_name not in raws:
avail = ", ".join(sorted(raws.keys())) or "(none)"
raise ManifestError(
f"bottle '{name}' extends '{parent_name}' which is not "
f"defined. Available bottles: {avail}"
)
parent = _resolve_one_bottle(
parent_name, raws, cache, repos_cache, seen + (name,)
)
merged_repos_raw = _resolve_repos_raw(combined_repos_raw, child_raw)
bottle = _merge_bottles(combined_parent, child_raw, merged_repos_raw, name)
merged_repos_raw = _resolve_repos_raw(repos_cache[parent_name], child_raw)
bottle = _merge_bottles(parent, child_raw, merged_repos_raw, name)
cache[name] = bottle
repos_cache[name] = merged_repos_raw
return bottle
def _fold_parents(
parent_names: list[str],
raws: dict[str, dict[str, object]],
cache: dict[str, ManifestBottle],
repos_cache: dict[str, dict[str, object]],
seen: tuple[str, ...],
) -> tuple[ManifestBottle, dict[str, object]]:
"""Resolve each parent and fold them left-to-right.
Later parents win over earlier ones on conflict. The `seen` tuple
carries the current bottle's name so cycle detection works across
every parent edge in the multi-parent graph."""
first = parent_names[0]
effective = _resolve_one_bottle(first, raws, cache, repos_cache, seen)
effective_repos_raw = repos_cache[first]
for pname in parent_names[1:]:
later = _resolve_one_bottle(pname, raws, cache, repos_cache, seen)
later_repos_raw = repos_cache[pname]
effective, effective_repos_raw = _fold_two_bottles(
effective, effective_repos_raw, later, later_repos_raw
)
return effective, effective_repos_raw
def _fold_two_bottles(
earlier: ManifestBottle,
earlier_repos_raw: dict[str, object],
later: ManifestBottle,
later_repos_raw: dict[str, object],
) -> tuple[ManifestBottle, dict[str, object]]:
"""Combine two resolved parent bottles; later wins over earlier."""
from .manifest import ManifestBottle, ManifestGitUser
from .manifest_egress import ManifestEgressConfig
from .manifest_git import parse_git_gate_config
from .manifest_util import as_json_object
merged_env = {**earlier.env, **later.env}
merged_git_user = ManifestGitUser(
name=later.git_user.name or earlier.git_user.name,
email=later.git_user.email or earlier.git_user.email,
)
# Repos: union by name; for same-name entries, later wins per-field.
# Unlike _resolve_repos_raw, an empty later_repos_raw means "no repos
# declared" — it does NOT clear the earlier parent's repos.
names = list(earlier_repos_raw) + [
n for n in later_repos_raw if n not in earlier_repos_raw
]
merged_repos_raw: dict[str, object] = {
n: {
**as_json_object(earlier_repos_raw.get(n, {}), "earlier parent repo"),
**as_json_object(later_repos_raw.get(n, {}), "later parent repo"),
}
for n in names
}
if merged_repos_raw:
merged_git, _ = parse_git_gate_config("_fold", {"repos": merged_repos_raw})
else:
merged_git = ()
# Egress: routes concatenate; scalar fields use last-wins.
merged_egress = ManifestEgressConfig(
routes=earlier.egress.routes + later.egress.routes,
Log=later.egress.Log,
)
return ManifestBottle(
env=merged_env,
agent_provider=later.agent_provider,
git=merged_git,
git_user=merged_git_user,
egress=merged_egress,
supervise=later.supervise,
), merged_repos_raw
def _merge_bottles(
parent: ManifestBottle,
child_raw: dict[str, object],
-21
View File
@@ -32,25 +32,6 @@ def check_stale_json(dir_path: Path, md_dir: Path, label: str) -> None:
)
def scan_bottle_names(bottles_dir: Path) -> list[str]:
"""Scan `<bottles_dir>/*.md` for valid filenames and return sorted bottle names.
No file content is read. Invalid filenames are skipped with a warning."""
result: list[str] = []
if not bottles_dir.is_dir():
return result
for path in sorted(bottles_dir.glob("*.md")):
name = entity_name_from_path(path)
if name is None:
warn(
f"skipping {path}: filename must match "
f"[a-z][a-z0-9-]*.md (got {path.name!r})"
)
continue
result.append(name)
return result
def scan_agent_names(agents_dir: Path) -> dict[str, Path]:
"""Scan `<agents_dir>/*.md` for valid filenames and return `{name: path}`.
@@ -106,7 +87,5 @@ def load_bottle_chain_from_dir(
parent = fm.get("extends")
if isinstance(parent, str):
to_load.append(parent)
elif isinstance(parent, list):
to_load.extend(p for p in parent if isinstance(p, str))
return resolve_bottles(raws)[bottle_name]
+2 -2
View File
@@ -18,8 +18,8 @@ _FILENAME_RX = re.compile(r"^[a-z][a-z0-9-]*$")
BOTTLE_KEYS = frozenset(
{"env", "extends", "agent_provider", "git-gate", "egress", "supervise"}
)
AGENT_KEYS_REQUIRED: frozenset[str] = frozenset()
AGENT_KEYS_OPTIONAL = frozenset({"bottle", "skills", "git-gate"})
AGENT_KEYS_REQUIRED = frozenset({"bottle"})
AGENT_KEYS_OPTIONAL = frozenset({"skills", "git-gate"})
# Claude Code subagent fields bot-bottle ignores at launch but does
# not reject. This lets the same file double as
+45 -20
View File
@@ -2,10 +2,11 @@
The supervise plane is the per-bottle MCP sidecar plus its host-side
queue/audit support. The sidecar (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:
sits on the bottle's internal network and exposes three MCP tools the
agent calls when it hits a stuck-recovery category:
* egress-block / allow agent proposes a new routes.yaml
* capability-block agent proposes a new agent Dockerfile
Each tool call: the agent passes the full proposed file plus a
justification text. The sidecar validates the proposal syntactically,
@@ -47,18 +48,16 @@ from pathlib import Path
SUPERVISE_HOSTNAME = "supervise"
SUPERVISE_PORT = 9100
TOOL_CAPABILITY_BLOCK = "capability-block"
TOOL_EGRESS_BLOCK = "egress-block"
TOOL_EGRESS_ALLOW = "egress-allow"
TOOL_ALLOW = "allow"
TOOL_GITLEAKS_ALLOW = "gitleaks-allow"
# Written directly by the egress addon (not an agent-facing MCP tool) when an
# outbound DLP token block is routed to the operator for override (PRD 0062).
TOOL_EGRESS_TOKEN_ALLOW = "egress-token-allow"
TOOL_LIST_EGRESS_ROUTES = "list-egress-routes"
TOOLS: tuple[str, ...] = (
TOOL_EGRESS_ALLOW,
TOOL_ALLOW,
TOOL_CAPABILITY_BLOCK,
TOOL_EGRESS_BLOCK,
TOOL_GITLEAKS_ALLOW,
TOOL_EGRESS_TOKEN_ALLOW,
TOOL_LIST_EGRESS_ROUTES,
)
@@ -72,8 +71,12 @@ TOOLS: tuple[str, ...] = (
EGRESS_FORWARD_PROXY = "http://127.0.0.1:9099"
EGRESS_INTROSPECT_URL = "http://_egress.local/allowlist"
# capability-block has no on-disk config the operator edits in place
# (the Dockerfile is rebuilt, not patched), so it has no audit log
# here — those changes are captured by git history + the rebuild record
# laid down in PRD 0016.
COMPONENT_FOR_TOOL: dict[str, str] = {
TOOL_EGRESS_ALLOW: "egress",
TOOL_ALLOW: "egress",
TOOL_EGRESS_BLOCK: "egress",
}
@@ -87,6 +90,8 @@ STATUSES: tuple[str, ...] = (STATUS_APPROVED, STATUS_MODIFIED, STATUS_REJECTED)
ACTION_OPERATOR_EDIT = "operator-edit"
QUEUE_DIR_IN_CONTAINER = "/run/supervise/queue"
CURRENT_CONFIG_DIR_IN_AGENT = "/etc/bot-bottle/current-config"
DEFAULT_POLL_INTERVAL_SEC = 0.5
@@ -429,39 +434,59 @@ def sha256_hex(content: str) -> str:
# --- Sidecar plan + abstract lifecycle -------------------------------------
# Filename of the staged Dockerfile inside the agent's read-only
# current-config mount. The capability-block tool's description
# points the agent at this exact path so it can read the current
# Dockerfile and propose modifications.
#
# routes.yaml + allowlist used to live here too; PRD 0017 chunk 3
# moved them behind the `list-egress-routes` MCP tool (live state
# from egress's introspection endpoint) so the agent always sees
# current data rather than a launch-time snapshot.
CURRENT_CONFIG_DOCKERFILE = "Dockerfile"
@dataclass(frozen=True)
class SupervisePlan:
"""Output of Supervise.prepare; consumed by .start.
`queue_dir` is the host directory bind-mounted into the sidecar
at /run/supervise/queue. `internal_network` is empty at prepare
time; the backend's launch step fills it via dataclasses.replace
before calling .start."""
at /run/supervise/queue. `current_config_dir` is the host
directory bind-mounted (read-only) into the *agent* container
at /etc/bot-bottle/current-config currently holds only the
Dockerfile snapshot (routes.yaml + allowlist moved to the
`list-egress-routes` MCP tool). `internal_network` is
empty at prepare time; the backend's launch step fills it via
dataclasses.replace before calling .start."""
slug: str
queue_dir: Path
current_config_dir: Path
internal_network: str = ""
class Supervise(ABC):
"""Per-bottle supervise sidecar. Encapsulates the host-side
prepare (queue dir staging); the sidecar's start/stop lifecycle
is backend-specific."""
prepare (queue dir + current-config staging); the sidecar's
start/stop lifecycle is backend-specific."""
def prepare(
self,
slug: str,
stage_dir: Path,
) -> SupervisePlan:
"""Stage the per-bottle queue dir on the host. Returns the
plan; `internal_network` must be set by the launch step before
"""Stage the per-bottle queue dir on the host and the
current-config dir under `stage_dir`. Returns the plan;
`internal_network` must be set by the launch step before
.start runs."""
del stage_dir
queue_dir = queue_dir_for_slug(slug)
queue_dir.mkdir(parents=True, exist_ok=True)
current_config_dir = stage_dir / "current-config"
current_config_dir.mkdir(parents=True, exist_ok=True)
return SupervisePlan(
slug=slug,
queue_dir=queue_dir,
current_config_dir=current_config_dir,
)
# --- Helpers ---------------------------------------------------------------
@@ -512,6 +537,8 @@ __all__ = [
"ACTION_OPERATOR_EDIT",
"AuditEntry",
"COMPONENT_FOR_TOOL",
"CURRENT_CONFIG_DIR_IN_AGENT",
"CURRENT_CONFIG_DOCKERFILE",
"DEFAULT_POLL_INTERVAL_SEC",
"Proposal",
"QUEUE_DIR_IN_CONTAINER",
@@ -527,10 +554,8 @@ __all__ = [
"TOOLS",
"EGRESS_FORWARD_PROXY",
"EGRESS_INTROSPECT_URL",
"TOOL_EGRESS_ALLOW",
"TOOL_EGRESS_BLOCK",
"TOOL_CAPABILITY_BLOCK",
"TOOL_GITLEAKS_ALLOW",
"TOOL_EGRESS_TOKEN_ALLOW",
"TOOL_LIST_EGRESS_ROUTES",
"archive_proposal",
"audit_dir",
+66 -64
View File
@@ -1,8 +1,8 @@
"""Supervise sidecar 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`,
`egress-block`, and `list-egress-routes`.
Per-bottle MCP server exposing tools the agent calls to propose config
changes when stuck. The tools are `allow`, `egress-block`,
`capability-block`, and `list-egress-routes`.
Each queued tool call:
@@ -47,11 +47,11 @@ from pathlib import Path
try:
# Same-directory imports inside the bundle container; these files are
# COPYed flat under /app by Dockerfile.sidecars.
from egress_addon_core import LOG_OFF, load_config
from egress_addon_core import load_routes
import supervise as _sv
except ModuleNotFoundError:
# Package imports for host-side tests and tooling.
from .egress_addon_core import LOG_OFF, load_config
from .egress_addon_core import load_routes
from . import supervise as _sv
@@ -90,19 +90,19 @@ def parse_jsonrpc(body: bytes) -> JsonRpcRequest:
try:
raw = json.loads(body)
except json.JSONDecodeError as e:
raise _RpcClientError(ERR_PARSE, f"parse error: {e}") from e
raise _RpcError(ERR_PARSE, f"parse error: {e}") from e
if not isinstance(raw, dict):
raise _RpcClientError(ERR_INVALID_REQUEST, "request must be a JSON object")
raise _RpcError(ERR_INVALID_REQUEST, "request must be a JSON object")
if raw.get("jsonrpc") != JSONRPC_VERSION:
raise _RpcClientError(ERR_INVALID_REQUEST, "jsonrpc field must be '2.0'")
raise _RpcError(ERR_INVALID_REQUEST, "jsonrpc field must be '2.0'")
method = raw.get("method")
if not isinstance(method, str):
raise _RpcClientError(ERR_INVALID_REQUEST, "method must be a string")
raise _RpcError(ERR_INVALID_REQUEST, "method must be a string")
params = raw.get("params", {})
if params is None:
params = {}
if not isinstance(params, dict):
raise _RpcClientError(ERR_INVALID_PARAMS, "params must be an object")
raise _RpcError(ERR_INVALID_PARAMS, "params must be an object")
rpc_id = raw.get("id", _NO_ID)
is_notification = rpc_id is _NO_ID
return JsonRpcRequest(
@@ -117,23 +117,12 @@ _NO_ID = object()
class _RpcError(Exception):
"""Base class for all typed RPC errors that surface as JSON-RPC error responses."""
def __init__(self, code: int, message: str):
super().__init__(message)
self.code = code
self.message = message
class _RpcClientError(_RpcError):
"""Caller sent a bad request; returned verbatim, no server-side logging."""
class _RpcInternalError(_RpcError):
"""Server-side fault; logged at ERROR with cause, always returns ERR_INTERNAL."""
def __init__(self, message: str) -> None:
super().__init__(ERR_INTERNAL, message)
def jsonrpc_result(request_id: object, result: object) -> bytes:
payload = {"jsonrpc": JSONRPC_VERSION, "id": request_id, "result": result}
return (json.dumps(payload) + "\n").encode("utf-8")
@@ -159,7 +148,7 @@ TOOL_DEFINITIONS: list[dict[str, object]] = [
"allowlist. Returns JSON with one entry per allowed host, "
"each carrying its matches rules (if any) and whether "
"the proxy injects Authorization for the route. Use this "
"before composing an `egress-allow` or `egress-block` proposal so "
"before composing an `allow` or `egress-block` proposal so "
"the new routes file extends the live one rather than "
"replacing it."
),
@@ -170,7 +159,7 @@ TOOL_DEFINITIONS: list[dict[str, object]] = [
},
},
{
"name": _sv.TOOL_EGRESS_ALLOW,
"name": _sv.TOOL_ALLOW,
"description": (
"Request operator approval to change the bottle's egress "
"allowlist. Pass the full proposed routes.yaml content, not "
@@ -198,7 +187,6 @@ TOOL_DEFINITIONS: list[dict[str, object]] = [
" dlp: (optional DLP scanner overrides)\n"
" outbound_detectors: [token_patterns, known_secrets]\n"
" inbound_detectors: [naive_injection_detection]\n"
" outbound_on_match: block|redact|supervise (default supervise)\n"
"Omit any key that should use its default. "
"`list-egress-routes` returns routes in this same format."
),
@@ -240,7 +228,6 @@ TOOL_DEFINITIONS: list[dict[str, object]] = [
" dlp: (optional DLP scanner overrides)\n"
" outbound_detectors: [token_patterns, known_secrets]\n"
" inbound_detectors: [naive_injection_detection]\n"
" outbound_on_match: block|redact|supervise (default supervise)\n"
"Omit any key that should use its default. "
"`list-egress-routes` returns routes in this same format."
),
@@ -253,13 +240,42 @@ TOOL_DEFINITIONS: list[dict[str, object]] = [
"required": ["routes_yaml", "justification"],
},
},
{
"name": _sv.TOOL_CAPABILITY_BLOCK,
"description": (
"Call when the bottle is missing a tool, skill, permission, "
"or env var you need — something that lives in the agent "
"Dockerfile rather than in the egress routes. "
"Read the current Dockerfile from "
"/etc/bot-bottle/current-config/Dockerfile, compose a "
"modified version, and pass the full new file plus a "
"justification. On approval the supervisor rebuilds the "
"bottle from the new Dockerfile and starts a replacement on "
"the same branch (wired in PRD 0016; v1 acknowledges only)."
),
"inputSchema": {
"type": "object",
"properties": {
"dockerfile": {
"type": "string",
"description": "Full proposed Dockerfile content.",
},
"justification": {
"type": "string",
"description": "Why this capability is needed.",
},
},
"required": ["dockerfile", "justification"],
},
},
]
# Map each proposal tool to the input field that carries the agent's
# payload (stored in Proposal.proposed_file).
PROPOSED_FILE_FIELD: dict[str, str] = {
_sv.TOOL_EGRESS_ALLOW: "routes_yaml",
_sv.TOOL_ALLOW: "routes_yaml",
_sv.TOOL_CAPABILITY_BLOCK: "dockerfile",
_sv.TOOL_EGRESS_BLOCK: "routes_yaml",
}
@@ -272,22 +288,21 @@ def validate_proposed_file(tool: str, content: str) -> None:
catches obvious paste-errors / wrong-tool selections before they
enter the queue."""
if not content.strip():
raise _RpcClientError(ERR_INVALID_PARAMS, f"{tool}: proposed file is empty")
if tool in (_sv.TOOL_EGRESS_ALLOW, _sv.TOOL_EGRESS_BLOCK):
raise _RpcError(ERR_INVALID_PARAMS, f"{tool}: proposed file is empty")
if tool == _sv.TOOL_CAPABILITY_BLOCK:
# Dockerfiles are too varied to validate syntactically beyond
# non-empty. The operator reads the diff in the TUI.
pass
elif tool in (_sv.TOOL_ALLOW, _sv.TOOL_EGRESS_BLOCK):
try:
config = load_config(content)
load_routes(content)
except ValueError as e:
raise _RpcClientError(
raise _RpcError(
ERR_INVALID_PARAMS,
f"{tool}: proposed routes.yaml is not valid: {e}",
) from e
if config.log != LOG_OFF:
raise _RpcClientError(
ERR_INVALID_PARAMS,
f"{tool}: proposed routes.yaml must not change egress logging",
)
else:
raise _RpcClientError(ERR_INVALID_PARAMS, f"unknown tool {tool!r}")
raise _RpcError(ERR_INVALID_PARAMS, f"unknown tool {tool!r}")
# --- MCP handlers ----------------------------------------------------------
@@ -360,17 +375,17 @@ def handle_tools_call(
doesn't need operator approval."""
name = params.get("name")
if not isinstance(name, str):
raise _RpcClientError(ERR_INVALID_PARAMS, "tools/call missing 'name'")
raise _RpcError(ERR_INVALID_PARAMS, "tools/call missing 'name'")
if name == _sv.TOOL_LIST_EGRESS_ROUTES:
return handle_list_egress_routes(typing.cast(dict[str, object], params.get("arguments", {})), config)
args_raw = params.get("arguments", {})
if not isinstance(args_raw, dict):
raise _RpcClientError(ERR_INVALID_PARAMS, "tools/call 'arguments' must be an object")
raise _RpcError(ERR_INVALID_PARAMS, "tools/call 'arguments' must be an object")
justification = args_raw.get("justification")
if not isinstance(justification, str) or not justification.strip():
raise _RpcClientError(
raise _RpcError(
ERR_INVALID_PARAMS,
f"{name}: 'justification' is required and must be a non-empty string",
)
@@ -379,13 +394,13 @@ def handle_tools_call(
file_field = PROPOSED_FILE_FIELD[name]
proposed_file = args_raw.get(file_field)
if not isinstance(proposed_file, str):
raise _RpcClientError(
raise _RpcError(
ERR_INVALID_PARAMS,
f"{name}: '{file_field}' is required and must be a string",
)
validate_proposed_file(name, proposed_file)
else:
raise _RpcClientError(ERR_INVALID_PARAMS, f"unknown tool {name!r}")
raise _RpcError(ERR_INVALID_PARAMS, f"unknown tool {name!r}")
proposal = _sv.Proposal.new(
bottle_slug=config.bottle_slug,
@@ -394,10 +409,7 @@ def handle_tools_call(
justification=justification,
current_file_hash=_sv.sha256_hex(proposed_file),
)
try:
_sv.write_proposal(config.queue_dir, proposal)
except OSError as e:
raise _RpcInternalError(f"failed to write proposal to queue: {e}") from e
_sv.write_proposal(config.queue_dir, proposal)
sys.stderr.write(
f"supervise: queued proposal {proposal.id} ({name}) "
f"for bottle {config.bottle_slug}; waiting for operator...\n"
@@ -417,10 +429,7 @@ def handle_tools_call(
"content": [{"type": "text", "text": text}],
"isError": False,
}
try:
_sv.archive_proposal(config.queue_dir, proposal.id)
except OSError as e:
raise _RpcInternalError(f"failed to archive proposal: {e}") from e
_sv.archive_proposal(config.queue_dir, proposal.id)
text = format_response_text(response)
return {
@@ -454,8 +463,9 @@ def format_pending_response_text(timeout_seconds: float) -> str:
# --- HTTP transport --------------------------------------------------------
# Max request body the server accepts. 1 MB is well above any realistic
# routes.yaml proposal.
# Max request body the server accepts. Generous because Dockerfile
# proposals can be a few KB; routes.json is small. 1 MB is well above
# any realistic config file.
MAX_BODY_BYTES = 1 * 1024 * 1024
@@ -495,7 +505,7 @@ class MCPHandler(http.server.BaseHTTPRequestHandler):
try:
req = parse_jsonrpc(body)
except _RpcClientError as e:
except _RpcError as e:
self._write_jsonrpc(jsonrpc_error(None, e.code, e.message))
return
@@ -503,19 +513,11 @@ class MCPHandler(http.server.BaseHTTPRequestHandler):
try:
result = self._dispatch(req, config)
except _RpcClientError as e:
except _RpcError as e:
self._write_jsonrpc(jsonrpc_error(req.id, e.code, e.message))
return
except _RpcInternalError as e:
cause = e.__cause__
detail = f": {cause}" if cause else ""
sys.stderr.write(f"supervise: internal error: {e.message}{detail}\n")
sys.stderr.flush()
self._write_jsonrpc(jsonrpc_error(req.id, ERR_INTERNAL, "internal error"))
return
except Exception as e: # noqa: W0718 — unexpected errors
sys.stderr.write(f"supervise: unexpected error: {type(e).__name__}: {e}\n")
sys.stderr.flush()
except Exception as e: # noqa: W0718 — catch-all for RPC dispatch errors
sys.stderr.write(f"supervise: internal error: {e}\n")
self._write_jsonrpc(jsonrpc_error(req.id, ERR_INTERNAL, "internal error"))
return
@@ -534,7 +536,7 @@ class MCPHandler(http.server.BaseHTTPRequestHandler):
return handle_tools_list(req.params)
if method == "tools/call":
return handle_tools_call(req.params, config)
raise _RpcClientError(ERR_METHOD_NOT_FOUND, f"method not found: {method}")
raise _RpcError(ERR_METHOD_NOT_FOUND, f"method not found: {method}")
def _write_jsonrpc(self, body: bytes) -> None:
self.send_response(200)
@@ -1,210 +0,0 @@
# PRD 0062: Supervisor override for egress token blocks
- **Status:** Active
- **Author:** claude
- **Created:** 2026-06-24
- **Issue:** #261
## Summary
Give each egress route a policy for what happens when an outbound DLP detector
matches a token, via `dlp.outbound_on_match: block | redact | supervise`
(default `supervise`):
- **`supervise`** (default) — route the block through the existing supervisor
approval queue instead of returning `403` immediately. The proxy holds the
request open until the operator approves or rejects it. On approval the
matched token is added to an in-memory "safe tokens" set so the request — and
any later request carrying the same token — flows through without
re-prompting.
- **`redact`** — scrub the matched value(s) from the request and forward it,
no operator in the loop. For routes where a token-shaped value is noise the
upstream doesn't need (telemetry/log sinks). Fails closed if a match lands on
a surface redaction can't rewrite (the hostname).
- **`block`** — the original hard `403`; never overridable. For routes where a
detected token must always stop.
The motivating goal is reducing friction from false positives without weakening
the default-deny posture: supervise keeps a human in the loop, redact is an
explicit per-route opt-in, and block stays available for sensitive routes.
## Problem
The outbound DLP detectors (`token_patterns`, `known_secrets`) are
deliberately aggressive: any string that looks like a credential is blocked
before it leaves the bottle. That is the right default, but it produces false
positives — a token-shaped value that is not actually a secret, or a credential
the agent legitimately needs to send to a declared host. Today the only
recovery is for the operator to notice the `egress DLP` 403 in the logs and
hand-edit the route's `dlp.outbound_detectors`, which disables the detector for
the whole route rather than allowing the one value.
The operator has no in-the-loop signal that a token block happened and no
fine-grained way to say "this specific value is fine."
## Goals / Success Criteria
1. An outbound DLP **token** block (a `ScanResult` carrying a matched secret
value) creates a supervisor proposal instead of an immediate `403`.
2. The egress proxy holds the blocked request open, polling for the operator's
response up to a bounded timeout.
3. The proposal shows the operator the host, method, path, the detector reason,
and a **redacted** context snippet — never the raw token value.
4. On `approved`/`modified`, the matched token value is added to an in-memory
safe-tokens set and the request proceeds normally; later requests carrying
the same value skip the block.
5. On `rejected`, timeout, malformed response, or missing supervisor wiring,
the request fails closed with the same `403` as today.
6. Structural blocks that carry no token value (CRLF injection) and the
route-not-allowlisted / git blocks are unchanged — they stay hard `403`s and
keep their existing agent-driven `allow` / `egress-block` MCP path.
7. The proxy event loop is not stalled while waiting: the wait is asynchronous,
so other flows keep being served.
## Non-goals
- Persisting the safe-tokens set across egress restarts. It lives in process
memory only; a restart re-prompts. (The issue explicitly defers persistence.)
- Supervising inbound (prompt-injection) blocks or WebSocket frame blocks.
WebSocket frames still honour the safe-tokens set for already-approved values
but cannot wait for approval (there is no response surface after upgrade).
- Generalising an approved secret across encodings. The safe-tokens set matches
the exact value the detector found.
- Replacing the per-route `dlp.outbound_detectors` override. That remains the
way to turn a detector off wholesale.
- Making `redact` the default. Silent redaction of a true false positive
corrupts legitimate data, so it is opt-in per route; `supervise` (human in
the loop) stays the default.
## Scope
### In scope
The minimum cut that ships, in build order:
1. **Core**`ScanResult.matched`; thread `safe_tokens` through
`scan_outbound` / the token detectors; `build_token_allow_payload`.
2. **Supervise + TUI**`TOOL_EGRESS_TOKEN_ALLOW`; TUI suffix, modify guard,
required approval reason.
3. **Addon glue** — async `request`, safe-tokens set, proposal write + async
poll, allow/block decision; pass `safe_tokens` into the WebSocket path.
4. **On-match policy**`dlp.outbound_on_match` through manifest → render →
addon; `redact` surface scrub with fail-closed re-scan; policy dispatch in
the addon's outbound handler.
5. **Tests + docs** — core/supervise/TUI/manifest/render unit tests; README
egress + supervisor notes.
### Out of scope
The deferrals enumerated under **Non-goals** — restart persistence, inbound /
WebSocket-frame supervision, cross-encoding generalisation, replacing
`dlp.outbound_detectors`, and making `redact` the default.
## Proposed Design
### New services / components
A new proposal tool constant `egress-token-allow` (`TOOL_EGRESS_TOKEN_ALLOW`)
is added to `supervise.TOOLS`, and the egress addon gains an in-memory
safe-tokens set plus the policy-dispatch path that drives it.
On an outbound block the addon dispatches on the resolved policy:
- **Structural blocks always 403.** A `ScanResult` with no `matched` value
(CRLF injection) is a hard `403` regardless of policy — there is nothing to
redact or safelist.
- **`redact`** runs `redact_tokens` over the body, non-`host` header values,
and path/query, then re-scans. If the re-scan is clean the (rewritten)
request is forwarded; if a block-severity match remains (e.g. in the
hostname, or a unicode-evasion token redaction can't reach) it fails closed
with a `403`.
- **`block`** writes the `403` immediately.
- **`supervise`** runs the queue-and-wait loop, falling back to `block` when
supervise isn't wired for the bottle.
For `supervise`, the addon writes the proposal directly to
`SUPERVISE_QUEUE_DIR` (the queue is bind-mounted into the sidecar bundle and
shared by every daemon, exactly as git-gate's `gitleaks-allow` proposal in PRD
0061 does). The proposal's `proposed_file` is a human-readable text payload
built by `build_token_allow_payload`:
```
egress blocked an outbound request carrying a detected token
host: api.example.com
method: POST
path: /v1/ingest
detector: OpenAI API key found in body
context: ...before ******** after...
```
The justification tells the operator to approve only if the value is a false
positive or a credential the request legitimately needs. The addon then polls
`<proposal-id>.response.json` for `EGRESS_TOKEN_ALLOW_TIMEOUT_SECONDS` (default
300). `approved`/`modified` allow the request and add the value to the
safe-tokens set; `rejected`, malformed responses, and timeout fail the request
closed. The proposal + response are archived to `processed/` after a decision.
Because the wait happens inside mitmproxy's asyncio loop, the addon's `request`
hook is async and polls with `asyncio.sleep`, so concurrent flows are
unaffected.
### Existing code touched
- **Policy threading.** `dlp.outbound_on_match` is a per-route enum threaded
from the bottle manifest (`manifest_egress`) through the resolved route
(`egress.EgressRoute`), the rendered `routes.yaml` (`egress_render_routes`),
and the addon's `Route` (`egress_addon_core`). Unset renders nothing and
resolves to `supervise` at request time. The `list-egress-routes`
introspection endpoint round-trips it so the agent's proposals preserve it.
- **Provider-route default.** Agent-provider routes (the agent talking to its
own LLM API — `api.anthropic.com`, the Codex backend, etc.) are the worst
source of token-shaped false positives because the whole conversation payload
flows through them. `egress_routes_for_bottle` fills `outbound_on_match=redact`
on any provider route that doesn't set it explicitly; a provider that sets the
policy keeps its choice, and manifest routes are unaffected (they default to
`supervise`).
- **Scanners.** `scan_outbound` (and the token detectors `scan_token_patterns`
/ `scan_known_secrets` it calls) accept a `safe_tokens` set. A match whose
value is in `safe_tokens` is skipped, so an approved token no longer blocks;
the scanners keep searching past a safelisted match so a second, un-approved
secret in the same request is still caught. The WebSocket path is passed the
same `safe_tokens` set.
- **Supervisor UI.** `cli/supervise.py` renders `egress-token-allow` like
`gitleaks-allow`: the text payload is shown, modify is unavailable (there is
no file patch to edit), and approval prompts for a non-empty reason recorded
in the response notes. There is no on-disk config diff, so — like
`gitleaks-allow` and `capability-block` — it writes no egress audit-log entry.
- **Failure handling.** If `SUPERVISE_QUEUE_DIR` / `SUPERVISE_BOTTLE_SLUG` are
unset (supervise disabled for the bottle), the addon skips the queue and
returns the existing `403`. Any error writing the proposal or reading the
response also fails closed.
### Data model changes
- New per-route manifest field `dlp.outbound_on_match: block | redact |
supervise`, rendered into `routes.yaml` (omitted when unset).
- `ScanResult` gains a `matched: str = ""` field carrying the raw substring the
detector matched. The token detectors populate it; the structural CRLF
detector leaves it empty. The value stays inside the egress sidecar process —
never written to a log line (logs use the redacted `context`) nor to the
proposal file.
- Proposal text payload (above) plus `<proposal-id>.response.json` in
`SUPERVISE_QUEUE_DIR`, archived to `processed/` after a decision.
- New env var `EGRESS_TOKEN_ALLOW_TIMEOUT_SECONDS` (default 300).
### External dependencies
None. Reuses the existing supervisor queue (`SUPERVISE_QUEUE_DIR`) and the
mitmproxy addon framework already in the egress sidecar.
## Open questions
- Should `known_secrets` (provisioned `EGRESS_TOKEN_*` exfiltration) be
override-able at all, or only `token_patterns`? This PRD allows both —
approval is an explicit operator decision and the safe-tokens set matches the
exact found value — but a future revision could restrict `known_secrets` to
reject-only.
## References
- Issue #261
- PRD 0061 — `gitleaks-allow` supervisor proposal pattern this reuses.
@@ -1,189 +0,0 @@
# PRD 0063: Strengthen outbound exfiltration detection
- **Status:** Active
- **Author:** claude
- **Created:** 2026-06-25
- **Issue:** #259
## Summary
The current DLP system has two detection tiers: weak (vendor token regexes)
and strong (exact matching of provisioned `EGRESS_TOKEN_*` values in multiple
encodings). This PRD adds four complementary hardening layers in ranked order
of impact:
1. **Canary tokens** — inject a per-session fake secret into the agent's
environment; any outbound appearance is a zero-false-positive exfil signal.
2. **Broadened known-value scanning** — extend the strong tier beyond
`EGRESS_TOKEN_*` via a `BOT_BOTTLE_SENSITIVE_PREFIXES` sidecar env var.
3. **Fragmentation-resistant matching** — catch separator injection and
long-substring leaks via alnum projection and sliding-window substring
search.
4. **Entropy scoring** — warn-only flag on high-entropy blobs as a
complementary signal for encrypted exfil.
## Problem
After PRD 0056 the outbound scan covers all HTTP request surfaces (host, path,
query, headers, body). But the content-based strong tier only matches
`EGRESS_TOKEN_*` values and their encodings. Three gaps remain:
| Gap | How an agent exploits it |
|-----|--------------------------|
| No canary | There is no "can't be false-positive" signal |
| Narrow prefix filter | Sensitive values provisioned under other env prefixes (MCP keys, API keys injected via the agent provider) are invisible to `scan_known_secrets` |
| Fragmentation blindness | Inserting `-`, space, or `\n` between secret characters turns an exact-match into a miss |
## Goals / Success Criteria
1. Each launched bottle has a unique canary token in the agent's environment
under a randomized `WORD_WORD_SECRET` env var name. The egress sidecar gets
the same env var and registers that exact name through
`BOT_BOTTLE_SENSITIVE_PREFIXES`. Any outbound appearance of the canary
blocks the request as a known-secret match.
2. `scan_known_secrets` accepts a `sensitive_prefixes` parameter (default:
`("EGRESS_TOKEN_",)`). `scan_outbound` reads
`BOT_BOTTLE_SENSITIVE_PREFIXES` from `environ` and merges those prefixes
in, so operators can mark additional env vars as scanned values without
changing the manifest schema.
3. For every secret that passes exact-match, a secondary alnum-projection pass
checks for the secret with all non-alphanumeric characters stripped. This
catches separator-injection evasion (`MY-SECRET` → body contains
`MY SECRET`).
4. A sliding-window partial-match pass checks for long-enough contiguous
substrings of the secret's alnum projection in the text's alnum projection.
Any match ≥ `PARTIAL_MATCH_MIN_LEN` (12 chars) blocks with reason
`"partial match"`.
5. A new `scan_entropy` detector flags outbound text windows with Shannon
entropy ≥ `ENTROPY_BLOCK_THRESHOLD` (5.5 bits/char) at **warn** severity
only. It is registered under the new detector name `"entropy"` in
`OUTBOUND_DETECTOR_NAMES` and disabled by default (routes must opt in).
6. Binary request bodies are decoded via `latin-1` instead of
`utf-8 errors="replace"`, preserving every byte value and allowing
ASCII-range secrets to be found within binary payloads.
7. All new behaviour is unit-tested; existing tests pass unchanged.
## Non-goals
- Rolling per-host buffer for split-across-requests detection (state in the
stateless addon is complex; deferred).
- Additional vendor regexes.
- ML / embedding-based detection.
- Entropy-based hard blocks (warn only per the issue).
## Design
### Canary token flow
```
Egress.prepare()
canary = secrets.token_urlsafe(32)
canary_env = <random WORD_WORD_SECRET>
EgressPlan(canary=canary, canary_env=canary_env, ...)
Docker compose render:
sidecar env: <canary_env>=<canary>
sidecar env: BOT_BOTTLE_SENSITIVE_PREFIXES=<canary_env>
agent env: <canary_env>=<canary> ← visible to agent as a "secret"
macos-container launch: same literals added to sidecar + agent env entries
```
The sidecar uses `BOT_BOTTLE_SENSITIVE_PREFIXES` to make the random canary env
name part of the existing `scan_known_secrets` detector without adding a
manifest schema field.
### Broadened known-value scanning
`scan_known_secrets` gains a `sensitive_prefixes` parameter:
```python
def scan_known_secrets(
text: str,
*,
location: str = "body",
env: Mapping[str, str] | None = None,
sensitive_prefixes: tuple[str, ...] = ("EGRESS_TOKEN_",),
) -> ScanResult | None:
```
`scan_outbound` reads `BOT_BOTTLE_SENSITIVE_PREFIXES` (comma-separated list
of additional prefixes) from `environ` and appends them:
```python
extra = tuple(
p for p in environ.get("BOT_BOTTLE_SENSITIVE_PREFIXES", "").split(",") if p
)
sensitive_prefixes = ("EGRESS_TOKEN_",) + extra
```
`redact_tokens` receives the same treatment for consistent redaction.
### Fragmentation-resistant matching
A new helper `_alnum_projection(text)` strips all non-alphanumeric characters.
`scan_known_secrets` runs two passes per secret:
1. **Exact pass** — existing encoded-variant loop (unchanged).
2. **Alnum-projection pass** — if the secret's alnum projection has ≥ 8 chars,
check if it appears in the text's alnum projection. Match → block with
`"fragmented match (separator injection)"` reason.
3. **Partial-substring pass** — if the secret's alnum projection has ≥
`PARTIAL_MATCH_MIN_LEN` chars (12), slide a window of that length across the
secret's projection and look for each window in the text's alnum projection.
First match → block with `"partial match"` reason.
All three passes run only for the `"known_secrets"` detector; the token-pattern
and entropy detectors are unchanged.
### Entropy scoring
New public function:
```python
def scan_entropy(
text: str,
*,
location: str = "body",
window: int = ENTROPY_WINDOW, # 64
threshold: float = ENTROPY_BLOCK_THRESHOLD, # 5.5
) -> ScanResult | None:
```
Slides a window of `window` characters across `text` in steps of `window // 2`.
If any window's Shannon entropy exceeds `threshold`, returns a **warn**-severity
`ScanResult`. Never blocks.
`OUTBOUND_DETECTOR_NAMES` gains `"entropy"`. Routes opt in via their `dlp`
block; entropy scanning is **off by default** to avoid false-positive noise on
legitimate binary payloads.
### Binary body handling
In `scan_outbound`, the bytes → str decoding changes from:
```python
body.decode("utf-8", errors="replace")
```
to:
```python
body.decode("utf-8") if body is str else body.decode("latin-1")
```
`latin-1` is a bijective byte↔codepoint mapping; every byte value is preserved
as its corresponding Latin-1 code point, so ASCII-range secret strings remain
intact and `str.find` / regex still locate them correctly. The fallback from
strict UTF-8 is tried first so valid UTF-8 bodies are decoded faithfully.
## Implementation
Delivered in three commits on the same branch:
1. **DLP detector changes**`_alnum_projection`, fragmentation passes,
`scan_entropy`, broadened `scan_known_secrets`, updated `scan_outbound` and
`redact_tokens`; all accompanying unit tests.
2. **Canary injection**`EgressPlan.canary`, `Egress.prepare()`,
Docker compose + macos-container backend injection.
3. **PRD flip**`Status: Draft → Active`.
@@ -1,85 +0,0 @@
# PRD 0064: LOG_FULL egress logging credential redaction
- **Status:** Active
- **Author:** claude
- **Created:** 2026-06-25
- **Issue:** #257
## Summary
The `LOG_FULL` egress logging path (`_log_request` and `_log_response` in `egress_addon.py`) writes request/response headers and bodies to stderr without redaction and includes the sidecar-injected upstream `Authorization` header verbatim. This PR applies `redact_tokens` to header values and bodies in both log functions and strips the injected `Authorization` header from request logs entirely.
## Problem
`LOG_FULL` (log level 2) is intended for debugging egress traffic. When active it calls `_log_request` and `_log_response`. Both functions have two related bugs:
1. **Injected `Authorization` header exposure.** `_log_request` is called *after* the sidecar injects upstream credentials (`flow.request.headers["authorization"] = decision.inject_authorization`). The full header dict — including the live credential — is serialized to stderr. Any log collector that ingests the egress container's stderr will receive the upstream bearer token in plaintext.
2. **Unredacted bodies and header values.** Neither `_log_request` nor `_log_response` passes body or header values through `redact_tokens`. By contrast, `_req_ctx` (used for block/warn events) already calls `redact_tokens` on path and host. Any provisioned secret or recognized token pattern that appears in a request body, response body, or non-Authorization header value will be logged verbatim under `LOG_FULL`.
These two bugs compose: an agent that enables `LOG_FULL` and simultaneously triggers a request that carries a known token gains a write path from credentials → egress logs.
## Goals / Success Criteria
- `_log_request` never logs the `authorization` header in any form.
- `_log_request` applies `redact_tokens(value, env=os.environ)` to every other header value before serializing.
- `_log_request` applies `redact_tokens(body, env=os.environ)` to the request body before logging.
- `_log_response` applies `redact_tokens(value, env=os.environ)` to every response header value before logging.
- `_log_response` applies `redact_tokens(body, env=os.environ)` to the response body before logging.
- Unit tests cover each of the five cases above.
## Non-goals
- Redacting host or path in the full-log path (already covered by `_req_ctx` for block/warn events; `_log_request` already calls `redact_tokens` on host and path).
- Suppressing `LOG_FULL` or adding a new log level.
- Changing the outbound DLP scan logic.
## Design
### `_log_request`
```python
def _log_request(self, flow: http.HTTPFlow) -> None:
headers = {
k: redact_tokens(v, env=os.environ)
for k, v in flow.request.headers.items()
if k.lower() != "authorization"
}
body = redact_tokens(flow.request.get_text(strict=False) or "", env=os.environ)
sys.stderr.write(
json.dumps({
"event": "egress_request",
"host": redact_tokens(flow.request.pretty_host, env=os.environ),
"method": flow.request.method,
"path": redact_tokens(flow.request.path, env=os.environ),
"headers": headers,
"body": body,
})
+ "\n"
)
```
The `authorization` key is excluded because by the time `_log_request` is called the sidecar has already injected the upstream credential (`decision.inject_authorization`). Logging it would write a live bearer token to stderr on every allowed request. There is no safe subset to log — the value is always a live credential or empty.
### `_log_response`
```python
def _log_response(self, flow: http.HTTPFlow) -> None:
headers = {
k: redact_tokens(v, env=os.environ)
for k, v in flow.response.headers.items()
}
body = redact_tokens(flow.response.get_text(strict=False) or "", env=os.environ)
sys.stderr.write(
json.dumps({
"event": "egress_response",
"host": flow.request.pretty_host,
"status": flow.response.status_code,
"headers": headers,
"body": body,
})
+ "\n"
)
```
Response headers don't carry injected credentials, so no header name is suppressed — only the values are scrubbed by `redact_tokens`.
-166
View File
@@ -1,166 +0,0 @@
# PRD 0065: Multi-parent `extends:` for bottles
- **Status:** Active
- **Author:** didericis
- **Created:** 2026-06-25
- **Issue:** #268
- **Extends:** PRD 0025 (`0025-bottle-extends.md`)
## Summary
Allow a bottle's `extends:` field to accept either a single bottle name (existing
behavior) or a list of bottle names (new). Multiple parents are resolved
independently and folded left-to-right into a single effective parent before the
child is merged on top. This lets orthogonal concerns (base env, networking/egress,
agent provider) live in separate bottles and be composed without forcing them into a
linear chain.
## Problem
PRD 0025 shipped single-parent `extends:` and listed "No multi-parent inheritance"
as a non-goal. In practice, users want to compose multiple orthogonal bottles — a
base environment, a networking profile, and an agent-provider override — without
creating a three-level linear chain that couples unrelated parents to each other.
The linear chain workaround has two problems:
1. **Ordering constraint.** `networking extends base` works, but then
`agent extends networking` can't also pick up `base` without going through
`networking`, coupling two unrelated concerns.
2. **Quadratic duplication.** N orthogonal bottles require O(N²) chain variants
(one chain per permutation of applied concerns).
Multi-parent `extends:` removes both constraints: each orthogonal concern stays in
its own bottle, and the child bottle is the only place that names the combination.
## Goals / Success Criteria
- `extends:` accepts a list of strings in addition to a plain string.
- Backward compat: existing single-string `extends:` is unchanged.
- Parents are resolved left-to-right; later entries win on conflict.
- Child wins over all parents (unchanged from PRD 0025).
- Cycle detection covers multi-parent graphs, not just linear chains.
- Diamond inheritance: a shared ancestor is resolved once (via the existing cache).
- Invalid list entries (non-string, undefined bottle, self-reference) die at parse
with clear messages.
- `manifest_loader.py`'s `load_bottle_chain_from_dir` enqueues all parents from a
list `extends:` so the resolver sees every bottle in the graph.
## Non-goals
- No change to the agent-vs-bottle trust boundary (PRD 0025 "Alternatives
considered" option 2 stays rejected).
- No MRO / C3 linearization. Left-to-right fold is sufficient for the expected use
cases.
- No preflight display of per-field provenance across multiple parents (same open
question as PRD 0025; remains a follow-up).
## Design
### Schema
`extends:` now accepts either form:
```yaml
# single parent (unchanged)
extends: base
# multiple parents (new)
extends: [base, networking]
```
Both forms are normalized to a list internally. A list with one element behaves
identically to the string form.
### Merge rules for multi-parent fold
Parents are folded pairwise left-to-right before the child merge. For each step in
the fold, the "earlier" bottle is the running accumulator and the "later" bottle is
the next parent. Rules per field:
| Field | Fold rule |
|--------------------|--------------------------------------------------------------|
| `env` | dict merge; later wins on key collision |
| `git-gate.user` | per-field overlay; later's non-empty fields win |
| `git-gate.repos` | union by name; for same-name entries, later wins per-field |
| `egress.routes` | concatenate (earlier first, later appended) |
| `egress.log` | later wins (last-wins) |
| `agent_provider` | later wins (last-wins) |
| `supervise` | later wins (last-wins) |
After the fold, the combined parent is merged against the child using the existing
PRD 0025 rules (child always wins). The child's `egress.routes` appends to the
combined parent's concatenated routes; `validate_egress_routes` runs once on the
final merged set and catches duplicate hosts.
### Algorithm
```
extends: [p1, p2, p3]
fold:
combined = resolve(p1)
combined = fold_two(combined, resolve(p2))
combined = fold_two(combined, resolve(p3))
merge:
result = _merge_bottles(combined, child_raw, name)
```
`fold_two(earlier, later)` applies the rules in the table above. Cycle detection
(the `seen` tuple) is passed to each parent resolution call unchanged — if any
parent's chain circles back to the current bottle, it is caught. The `cache` dict
ensures a shared ancestor is only resolved once across all parents.
### Error cases
| Condition | Error message shape |
|----------------------------------------|------------------------------------------------------------------|
| `extends` is not a string or list | `extends must be a string or list of strings (was <type>)` |
| A list entry is not a string | `extends[<i>] must be a string (was <type>)` |
| A list entry names an undefined bottle | `extends '<name>' which is not defined. Available bottles: ...` |
| A list entry is the bottle itself | `extends itself; remove the self-reference` |
| Cycle through any parent edge | `is in an extends cycle: <chain>` |
## Implementation
### `bot_bottle/manifest_extends.py`
- `_resolve_one_bottle`: accept `str | list[str]` for `extends`; normalize to list;
validate each entry; for a single-entry list fall through to the existing
single-parent path; for multiple entries call `_fold_parents` then
`_merge_bottles`.
- `_fold_parents(parent_names, raws, cache, repos_cache, seen)`: resolve each
parent and fold pairwise left-to-right; return `(effective_bottle,
effective_repos_raw)`.
- `_fold_two_bottles(earlier, earlier_repos_raw, later, later_repos_raw)`: apply
the fold rules above; return `(folded_bottle, folded_repos_raw)`.
### `bot_bottle/manifest_loader.py`
- `load_bottle_chain_from_dir`: when `extends` is a list, enqueue all parent names
for loading (previously only `isinstance(parent, str)` was handled).
### `tests/unit/test_manifest_extends.py`
- `TestExtendsErrors.test_non_string_extends_dies`: update to use an integer
`extends` value (a list is now valid).
- New class `TestExtendsMultiParent` covering all cases listed in the issue.
## Testing strategy
Unit tests via `ManifestIndex.from_json_obj` (same resolver surface used by all
paths). No integration test changes needed — downstream code consumes the already-
merged bottle and is unchanged.
Test cases:
- Two-parent list: env union, egress routes concat, git repos union
- Last-parent-wins on scalar (supervise, agent_provider)
- Child wins over all parents on conflict
- Diamond: two parents share an ancestor; ancestor resolved once
- Single-element list: identical to string form
- Non-string extends value → ManifestError
- Non-string list entry → ManifestError
- Undefined bottle in list → ManifestError
- Self-reference in list → ManifestError
- Cycle through multi-parent edge → ManifestError
@@ -1,216 +0,0 @@
# PRD 0066: Separate agent and bottle selection
- **Status:** Active
- **Author:** claude
- **Created:** 2026-06-25
- **Issue:** #269
## Summary
Agents and bottles are two separate concerns: agents carry a system prompt and
skills; bottles carry infrastructure configuration (egress, git-gate, env,
agent provider). Today an agent's manifest file hard-codes a single `bottle:`
reference, which prevents the same agent prompt from being reused across
projects that need different bottle configurations. This PRD decouples them: at
launch time, after choosing the agent, the operator picks an ordered list of
bottles via a multi-select picker. The selected bottles are merged in order
(later entries override earlier ones) to produce the effective bottle for the
session.
## Problem
The current `bottle: <name>` field on an agent manifest file binds the agent
permanently to one bottle. To use the same system prompt with a different bottle
(e.g. `claude-implementer` at home vs. at a client site that needs a different
egress policy), the operator must duplicate the agent file and change the
`bottle:` field. Duplicate agent files drift out of sync.
## Goals / Success Criteria
1. `bottle:` in an agent's frontmatter becomes optional. Existing manifests with
`bottle:` continue to work unchanged (backward compat).
2. After selecting an agent (via the existing single-select picker), a new
multi-select bottle picker appears showing all available bottles.
3. The multi-select picker pre-populates with the agent's `bottle:` value when
present.
4. Confirming with one or more bottles selected uses those bottles, merged in
selection order, as the effective bottle for the session.
5. Confirming with an empty selection falls back to the agent's `bottle:` field.
If neither is set, a ManifestError is raised pointing the operator at the fix.
6. The ordered bottle list is stored in launch metadata so `./cli.py resume`
uses the same bottles.
7. The preflight summary (`y/N` screen) shows the effective bottle name(s).
8. The multi-select picker supports incremental filtering, Space/Enter to toggle
selection, an ordered "Selected: ..." summary line, Ctrl-D to confirm, and
Esc/q to cancel the whole start operation.
9. Unit tests cover: multi-select widget (filter, toggle, confirm, cancel),
the `cmd_start` bottle-picker step, and the manifest `load_for_agent`
runtime-bottle-merge path.
## Non-goals
- Reordering the selection list from within the picker (order = insertion order;
drag-and-drop is out of scope).
- Storing bottle selection history / MRU.
- Changes to `./cli.py edit`, `./cli.py list`, or `./cli.py info`.
- Removing the `bottle:` key from the agent schema (it stays, now optional).
## Design
### `bot_bottle/cli/tui.py``filter_multiselect`
```python
def filter_multiselect(
items: list[str],
*,
title: str = "",
initial: list[str] | None = None,
tty_path: str = "/dev/tty",
) -> list[str] | None:
"""Multi-select variant of filter_select.
Returns the ordered list of selected items, or None on cancel.
Press Space/Enter to toggle the item under the cursor.
Press Ctrl-D to confirm. Press Esc/q to cancel.
"""
```
Layout:
```
Select bottles
Filter: _
─────────────────────────────────────────
> [*] claude
[ ] dev
[ ] codex
─────────────────────────────────────────
Selected (in order): claude
─────────────────────────────────────────
[↑↓/jk] move [Space] toggle [Ctrl-D] done [Esc] cancel
```
`initial` pre-populates the ordered selection. `None` means no pre-selection.
Items added are appended in insertion order; items removed leave the remaining
order unchanged.
### `bot_bottle/manifest_schema.py` — optional `bottle:`
`bottle` moves from `AGENT_KEYS_REQUIRED` to `AGENT_KEYS_OPTIONAL`.
### `bot_bottle/manifest_agent.py` — optional `bottle:`
`ManifestAgent.bottle` changes from `str` (required) to `str = ""`.
`from_dict` no longer requires the key to be present; the bottle-exists
validation is skipped when the key is absent.
### `bot_bottle/manifest_loader.py``scan_bottle_names`
```python
def scan_bottle_names(bottles_dir: Path) -> list[str]:
"""Scan <bottles_dir>/*.md and return sorted bottle names."""
```
### `bot_bottle/manifest.py``ManifestIndex` changes
**`all_bottle_names` property** — analogous to `all_agent_names`; scans
`home_md / "bottles"` in lazy mode, returns `sorted(self.bottles.keys())` in
eager mode.
**`load_for_agent(agent_name, bottle_names: tuple[str, ...] = ())`** — new
`bottle_names` parameter. When non-empty, the listed bottles are resolved and
merged in order (index 0 is the base; each subsequent bottle is applied on top
using the same field-merge rules as `extends:`). The result replaces the bottle
that `agent.bottle` would have provided. When empty, falls back to `agent.bottle`.
Raises ManifestError if neither `bottle_names` nor `agent.bottle` is set.
### `bot_bottle/manifest_extends.py``merge_bottles_runtime`
```python
def merge_bottles_runtime(bottles: list[ManifestBottle]) -> ManifestBottle:
"""Merge an ordered list of pre-resolved ManifestBottle objects.
Index 0 is the base; each subsequent entry overrides the previous using
the same rules as the file-based extends machinery:
- env: dict merge, later wins
- git_user: per-field overlay, later wins on non-empty
- git (repos): union by name, later wins per-name
- egress.routes: concatenate
- agent_provider, supervise: later bottle's value replaces earlier
"""
```
This function operates on already-parsed `ManifestBottle` objects, so it does
not need to touch the raw-dict path.
### `bot_bottle/backend/__init__.py``BottleSpec` + `_validate`
`BottleSpec` gains `bottle_names: tuple[str, ...] = ()`.
`BottleBackend._validate` passes `spec.bottle_names` to `load_for_agent`:
```python
manifest = spec.manifest.load_for_agent(spec.agent_name, spec.bottle_names)
```
The preflight print updates `info(f"bottle: {agent.bottle}")` to display the
effective bottle name(s). When `spec.bottle_names` is non-empty those are
shown; when empty and `agent.bottle` is set, the agent's `bottle:` is shown.
### `bot_bottle/bottle_state.py` — persist bottle names
`BottleMetadata` gains `bottle_names: tuple[str, ...] = ()`. `read_metadata`
reads this from JSON (default `()`). `write_launch_metadata` passes
`spec.bottle_names` through.
### `bot_bottle/cli/start.py` — bottle multiselect step
After agent selection, before the name/color modal:
```python
available_bottle_names = manifest.all_bottle_names
# Peek at agent's bottle default for pre-population
initial_bottle = _peek_agent_bottle(manifest, agent_name)
initial = [initial_bottle] if initial_bottle else []
bottle_names_list = tui.filter_multiselect(
available_bottle_names,
title="Select bottles",
initial=initial,
)
if bottle_names_list is None:
return 0 # user cancelled
bottle_names = tuple(bottle_names_list)
```
`_peek_agent_bottle` reads the agent file's frontmatter without full parsing,
returning the `bottle:` value or `""` when absent.
`BottleSpec` is built with `bottle_names=bottle_names`.
### `bot_bottle/cli/resume.py` — bottle names from metadata
```python
spec = BottleSpec(
...
bottle_names=tuple(metadata.bottle_names),
)
```
## Implementation chunks
1. **Schema + model**`manifest_schema.py`, `manifest_agent.py` (optional
`bottle:`), `manifest_loader.py` (`scan_bottle_names`), `manifest.py`
(`all_bottle_names`, `load_for_agent` signature), `manifest_extends.py`
(`merge_bottles_runtime`), `bottle_state.py` (`bottle_names` field),
`resolve_common.py` (thread through).
2. **Backend**`BottleSpec.bottle_names`, `_validate`, preflight print.
3. **TUI**`filter_multiselect` in `tui.py` + unit tests.
4. **CLI wiring**`start.py` bottle picker step, `resume.py` metadata load.
5. **Tests**`test_cli_start_selector.py` bottle-picker cases,
`test_manifest_agent.py` optional-bottle cases, new
`test_manifest_bottle_merge.py` for `merge_bottles_runtime`.
## Open questions
None.
+75
View File
@@ -0,0 +1,75 @@
# PRD prd-new: Install script
- **Status:** Active
- **Author:** didericis
- **Created:** 2026-06-06
- **Issue:** #197
## Summary
Add a proper Python package distribution and a thin `install.sh` bootstrapper so users can install bot-bottle with a single command without cloning the repo.
## Problem
There is currently no install path for new users. The only way to run bot-bottle is to clone the repo and invoke `cli.py` directly. This blocks any HN-style public demo: readers want `curl | sh` or `pipx install`, not a manual clone-and-configure flow.
## Goals / Success Criteria
- `curl -fsSL <url>/install.sh | sh` (or equivalent) leaves a working `bot-bottle` command on PATH.
- Python-native users can install with `pipx install bot-bottle` or `uv tool install bot-bottle`.
- `install.sh` validates prerequisites (Python ≥ 3.11, Docker) and exits with a clear message if they are missing. It does not silently install Docker.
- `install.sh` runs `bot-bottle doctor` (or equivalent diagnostic) after install to confirm the environment is ready.
- The package has no runtime pip dependencies (stdlib-only, matching the existing constraint).
## Non-goals
- Bundling a Python runtime or producing a standalone binary.
- Automatic Docker installation.
- Plugin architecture changes (out of scope; see issue #197 for future direction).
- Publishing to PyPI in this PR — the package structure is the deliverable; publishing is a separate step.
## Design
### Package structure
Add a minimal `pyproject.toml` at the repo root:
```toml
[project]
name = "bot-bottle"
version = "0.1.0"
requires-python = ">=3.11"
dependencies = []
[project.scripts]
bot-bottle = "bot_bottle.cli:main"
```
The existing `bot_bottle/` package and `cli.py` entry point already contain the logic; this just wires up the standard entry point. `cli.py` may need a small refactor to expose a `main()` callable if it uses `if __name__ == "__main__"` only.
### `install.sh`
A thin bootstrapper that:
1. Checks `python3 --version` ≥ 3.11; exits with instructions if not met.
2. Checks `docker info` exits 0; exits with instructions if Docker is not running.
3. Installs via `pipx` if available, otherwise falls back to `pip install --user`.
4. Runs `bot-bottle doctor` to verify the install.
The script must be idempotent (safe to re-run) and must not require `sudo`.
### `bot-bottle doctor`
A new subcommand that checks and reports:
- Python version.
- Docker daemon reachability.
- Whether `~/.bot-bottle/` config directory exists.
Exits 0 if all checks pass, non-zero otherwise.
## Decisions
- `install.sh` is hosted from the repo's raw Gitea URL for now:
`https://gitea.dideric.is/didericis/bot-bottle/raw/branch/main/install.sh`.
- Should `version` in `pyproject.toml` be driven by a git tag at build time (e.g. via `hatch-vcs`) or kept as a static string? Static is simpler for now.
-227
View File
@@ -1,227 +0,0 @@
# PRD prd-new: smolmachines backend on Linux
- **Status:** Draft
- **Author:** Claude
- **Created:** 2026-06-25
- **Issue:** #283
## Summary
Make the `smolmachines` backend (PRD 0023) runnable on Linux, not
just macOS. `smolvm` already supports Linux via KVM (`/dev/kvm`);
the gap is entirely in bot-bottle's host-side glue, which hard-codes
macOS assumptions in three places:
1. **Preflight** only checks that `smolvm` is on `PATH` — it never
checks the Linux KVM prerequisite, so a misconfigured host fails
deep in the launch flow with an opaque `smolvm` error.
2. **The TSI allowlist enforcement** (`force_allowlist`) — the
security property that confines the agent VM to its sidecar
bundle's `/32`**no-ops on Linux today, failing _open_**. The
smolvm state-DB path it patches is hard-coded to macOS's
`~/Library/Application Support/...`.
3. **Per-bottle loopback scoping** (`allocate`) returns the shared
`127.0.0.1` on Linux, which would let the agent VM reach every
service on host loopback — a downgrade from the per-bottle alias
isolation macOS gets.
This PRD closes all three so a bottle launched with
`BOT_BOTTLE_BACKEND=smolmachines` on Linux gets the same isolation
guarantee it gets on macOS, and documents the Linux/NixOS host
setup. The primary validation target is NixOS, but the changes are
distro-agnostic.
## Problem
The smolmachines backend runs each bottle's agent inside a libkrun
microVM via `smolvm`, with egress confined by TSI's `--allow-cidr`
allowlist set to a single `/32` — the sidecar bundle's loopback
address. Everything else (host loopback, LAN, internet) is denied at
the VMM layer. That security property is the entire reason the
backend exists.
libkrun runs on Hypervisor.framework (macOS) **and** KVM (Linux), and
`smolvm` ships Linux x86_64 / aarch64 builds that require `/dev/kvm`.
So the microVM layer already works on Linux. What does not work is
bot-bottle's host integration, which PRD 0023 explicitly scoped to
macOS-only for v1. Three concrete blockers:
- **No KVM preflight.** On a Linux host without `/dev/kvm` (kernel
module not loaded) or without access to it (user not in the `kvm`
group), the failure surfaces as a cryptic `smolvm` non-zero exit
mid-launch instead of an actionable message.
- **TSI enforcement fails open on Linux.** `force_allowlist`
early-returns on non-macOS. It exists because `smolvm` 0.8.0
silently drops `--allow-cidr` when combined with `--from`, so the
allowlist has to be patched into smolvm's persisted state DB before
`machine start`. On Linux that patch never runs **and** the DB path
is the macOS path, so the booted VM's TSI allowlist is whatever
smolvm defaulted to — potentially all of `127.0.0.0/8`. That is the
exact sandbox-escape the backend is supposed to prevent.
- **No per-bottle loopback isolation on Linux.** `allocate` returns
`127.0.0.1` on Linux. Even with a correct allowlist, `127.0.0.1/32`
is shared by every service on host loopback, so the agent could
reach other bottles' published ports and host services. On macOS
this is solved with per-bottle `127.0.0.16..31` aliases added via
`sudo ifconfig lo0 alias`. On Linux the whole `127.0.0.0/8` is
already routed to `lo`, so docker can publish to `127.0.0.<N>`
with **no `ifconfig`/sudo step at all** — the isolation is actually
cheaper to achieve than on macOS.
## Goals / Success Criteria
- `BOT_BOTTLE_BACKEND=smolmachines ./cli.py start <agent>` launches,
runs, and tears down a bottle on a Linux host with `/dev/kvm`.
- The TSI allowlist is enforced on Linux: PRD 0022's
`tests/integration/test_sandbox_escape.py` passes against
`BOT_BOTTLE_BACKEND=smolmachines` on Linux (the acceptance gate).
- Each Linux bottle is scoped to its own `127.0.0.<N>/32`, matching
the macOS per-bottle isolation property.
- A clear, actionable preflight error when `/dev/kvm` is missing or
inaccessible, with remediation (load `kvm-intel`/`kvm-amd`, join the
`kvm` group).
- **Fail-closed:** if bot-bottle cannot positively confirm the TSI
allowlist was persisted for a machine (DB missing, row missing,
patch didn't take), it `die()`s before `machine start` rather than
booting a VM with an unverified allowlist.
- macOS behavior is unchanged.
- README documents Linux + NixOS host setup.
## Non-goals
- Rootless / non-KVM fallbacks (e.g. software emulation). Linux
smolmachines requires `/dev/kvm`, full stop.
- Removing Docker as a host dependency — the sidecar bundle and
image-build pipeline still use Docker on Linux, same as macOS.
- Auto-installing `smolvm` or configuring KVM on the operator's
behalf. Preflight reports; the operator remediates.
- Nested-virtualization tuning for running the runner itself inside a
VM (documented as a caveat, not solved here).
## Design
### Platform detection
Reuse the existing `platform.system()` check already in
`loopback_alias.py` (`_is_macos()`). "Linux" is "not macOS" for every
branch below; no new third-platform path.
### Preflight: KVM gate (`util.smolmachines_preflight`)
After the existing `smolvm`-on-`PATH` check, add a Linux-only gate:
- `/dev/kvm` must exist → else `die()` with "enable KVM
(`kvm-intel`/`kvm-amd` kernel module)".
- `/dev/kvm` must be readable + writable by the current user
(`os.access(..., R_OK | W_OK)`) → else `die()` with "add your user
to the `kvm` group (and re-login)".
macOS is unaffected (Hypervisor.framework needs no device node).
### smolvm state-DB path (platform-aware)
`loopback_alias._SMOLVM_DB_PATH` becomes platform-derived:
- macOS: `~/Library/Application Support/smolvm/server/smolvm.db`
(unchanged).
- Linux: `$XDG_DATA_HOME/smolvm/server/smolvm.db`, defaulting to
`~/.local/share/smolvm/server/smolvm.db`.
> **Verification note:** the Linux DB location is inferred from
> smolvm's documented `~/.local/share` install layout and the XDG
> base-dir spec. It must be confirmed on a real Linux smolvm install;
> if smolvm uses a different path or schema, the fail-closed check
> below turns that into a clear `die()` at launch rather than a silent
> escape.
### TSI enforcement: cross-platform + fail-closed (`force_allowlist`)
Rework `force_allowlist(machine_name, allowed_cidrs)` to run on
**both** platforms and to fail closed:
1. Resolve the state DB; if the file is missing, `die()` (cannot
confirm enforcement → refuse to launch).
2. Read the machine's persisted row; if the row is missing, `die()`.
3. If the row's `allowed_cidrs` already equals the requested list
(e.g. a newer `smolvm` that honors `--allow-cidr` at create), do
nothing — no write.
4. Otherwise patch `allowed_cidrs` (the existing BLOB-encoded write)
and re-read.
5. If, after the patch, `allowed_cidrs` still does not equal the
requested list, `die()`.
This is robust across smolvm versions: it works whether `--allow-cidr`
is silently dropped (0.8.0) or honored (newer), and it never boots a
VM whose persisted allowlist it could not confirm. It is a strict
improvement on macOS too (today's code writes unconditionally and
never verifies).
> The persisted-row check confirms our write took, not that smolvm's
> runtime TSI enforces it. The runtime guarantee is covered by the
> sandbox-escape acceptance test; the persisted check is the cheap
> fail-closed guard at launch.
### Per-bottle loopback scoping on Linux (`allocate`)
`allocate` runs the same docker-state-driven allocation on Linux as on
macOS (`_allocate_locked`, the file lock, and `_aliases_in_use` via
`docker inspect` are all already cross-platform). The only macOS-only
step, `ensure_pool` (the `sudo ifconfig lo0 alias` dance), stays
macOS-only: on Linux `127.0.0.0/8` is already loopback, so docker can
publish bundle ports directly on `127.0.0.<N>` with no setup.
Net effect: Linux bottles get per-bottle `127.0.0.16..31/32` scoping
identical to macOS, without sudo.
### Launch flow
`launch.py` needs no structural change — `_allocate_resources` already
calls `ensure_pool()` (now a Linux no-op) then `allocate()` (now
per-bottle on Linux), and `_launch_vm` already calls
`force_allowlist()` (now active on Linux). Only the macOS-specific
docstrings are updated to describe the cross-platform behavior.
## Implementation chunks
1. **Preflight KVM gate**`util.smolmachines_preflight` +
unit tests for the missing-device and no-access branches.
2. **Platform-aware DB path + fail-closed `force_allowlist`**
`loopback_alias.py`; update/extend `TestForceAllowlist`.
3. **Cross-platform `allocate`** — drop the Linux early-return; update
`TestAllocate` / `TestAllocateLock` for the new Linux behavior.
4. **Docstring + comment cleanup** in `launch.py` and module headers.
5. **Docs** — README requirements + a Linux/NixOS host-setup section.
## Testing Strategy
- **Unit (CI, any OS):** the suite mocks `platform.system()` /
`subprocess` and patches `_SMOLVM_DB_PATH`, so the new Linux
branches are testable on the macOS/Linux CI runner without `smolvm`
or KVM. Covers: KVM preflight branches, fail-closed `force_allowlist`
(DB missing, row missing, patch-doesn't-take), per-bottle Linux
allocation + locking, platform-derived DB path.
- **Integration (Linux host with KVM — the acceptance gate):**
`tests/integration/test_sandbox_escape.py` against
`BOT_BOTTLE_BACKEND=smolmachines`. This cannot run on the macOS dev
box and must be executed on NixOS before merge.
## Open questions / verification pending
- **Confirm the Linux smolvm state-DB path and schema** on a real
install (the `~/.local/share/...` inference above).
- **Confirm whether the current smolvm Linux build still drops
`--allow-cidr` with `--from`** (the 0.8.0 bug). The fail-closed
design handles either answer, but knowing lets us drop the DB patch
if upstream fixed it.
- **Confirm docker publishing to `127.0.0.<N>` on Linux** behaves as
expected end-to-end with TSI (high confidence; standard loopback
behavior, but unverified on the target host).
## References
- PRD 0023 — smolmachines bottle backend (macOS v1).
- PRD 0022 — `test_sandbox_escape.py` acceptance gate.
- PRD 0024 — sidecar bundle image.
- smolvm: https://github.com/smol-machines/smolvm
@@ -22,7 +22,7 @@ escapes**, and **whether credentials are short-lived and scoped**.
- Outbound: Docker containers have full internet access by default; no egress monitoring on most home networks
- Lateral movement: compromised container can reach the LAN — NAS, other machines, internal services
- Notable: CVE-2025-59536 (CVSS 8.7, Feb 2026) — a poisoned `.claude/settings.json` in a repo gives RCE when Claude Code opens it. `--dangerously-skip-permissions` removes the last gate.
- Supply chain: MCP servers, skills, and npm packages pulled during agent execution. A Jan 2026 large-scale empirical study of a 98,380-skill snapshot confirmed 157 malicious skills, ~71% of them credential harvesters. Exfiltration was overwhelmingly naive — plaintext HTTP to hardcoded endpoints; under 10% used any code obfuscation, and concealment was mostly at the documentation level, not the code level. ([Malicious Agent Skills in the Wild](https://arxiv.org/html/2602.06547v1), arXiv:2602.06547)
- Supply chain: MCP servers, skills, and npm packages pulled during agent execution. ~20% of ClawHub skills were found malicious in early 2026.
**What local topology protects:**
- No inbound attack surface — nothing listening on a public port
Executable
+50
View File
@@ -0,0 +1,50 @@
#!/bin/sh
set -eu
PACKAGE_SPEC="${BOT_BOTTLE_INSTALL_SPEC:-git+https://gitea.dideric.is/didericis/bot-bottle.git}"
MIN_PYTHON="3.11"
say() {
printf 'bot-bottle install: %s\n' "$*" >&2
}
die() {
say "error: $*"
exit 1
}
command -v python3 >/dev/null 2>&1 || die "python3 is required (version ${MIN_PYTHON} or newer)"
python3 - <<'PY' || die "python3 3.11 or newer is required"
import sys
raise SystemExit(0 if sys.version_info >= (3, 11) else 1)
PY
command -v docker >/dev/null 2>&1 || die "Docker is required; install Docker and start the daemon, then re-run this script"
docker info >/dev/null 2>&1 || die "Docker is installed but the daemon is not reachable; start Docker and re-run this script"
mkdir -p \
"${HOME}/.bot-bottle/agents" \
"${HOME}/.bot-bottle/bottles" \
"${HOME}/.bot-bottle/contrib"
if command -v pipx >/dev/null 2>&1; then
say "installing with pipx"
pipx install --force "${PACKAGE_SPEC}"
else
say "pipx not found; installing with python3 -m pip --user"
python3 -m pip install --user --upgrade "${PACKAGE_SPEC}"
fi
if command -v bot-bottle >/dev/null 2>&1; then
BOT_BOTTLE_BIN="bot-bottle"
elif [ -x "${HOME}/.local/bin/bot-bottle" ]; then
BOT_BOTTLE_BIN="${HOME}/.local/bin/bot-bottle"
say "using ${BOT_BOTTLE_BIN}; add ${HOME}/.local/bin to PATH for future shells"
else
die "bot-bottle was installed but is not on PATH"
fi
say "running bot-bottle doctor"
"${BOT_BOTTLE_BIN}" doctor
+27
View File
@@ -0,0 +1,27 @@
[build-system]
requires = ["setuptools>=68"]
build-backend = "setuptools.build_meta"
[project]
name = "bot-bottle"
version = "0.1.0"
description = "Self-hosted sandbox for AI coding agents with egress controls"
readme = "README.md"
requires-python = ">=3.11"
license = { text = "Apache-2.0" }
dependencies = []
[project.scripts]
bot-bottle = "bot_bottle.cli:main"
[tool.setuptools.packages.find]
include = ["bot_bottle*"]
[tool.setuptools.package-data]
bot_bottle = [
"Dockerfile.sidecars",
"egress_entrypoint.sh",
"contrib/claude/Dockerfile",
"contrib/codex/Dockerfile",
"contrib/pi/Dockerfile",
]
-1
View File
@@ -4,4 +4,3 @@
pylint>=3.0.0
pyright>=1.1.300
coverage>=7.0.0
+4 -7
View File
@@ -92,9 +92,9 @@ class TestSandboxEscape(unittest.TestCase):
"on PATH: curl -sSL https://smolmachines.com/install.sh | sh"
)
# Throwaway static key for the git-gate fixture. It need not
# be a real SSH key: test 5 reaches gitleaks before any SSH
# attempt anyway.
# Throwaway "identity file" for the git-gate's `identity` field.
# It need not be a real SSH key: test 5 reaches gitleaks before
# any SSH attempt anyway.
fd, kp = tempfile.mkstemp(prefix="sandbox-test-key.")
os.close(fd)
cls._key_path = Path(kp)
@@ -123,10 +123,7 @@ class TestSandboxEscape(unittest.TestCase):
"git-gate": {"repos": {
"throwaway": {
"url": "ssh://git@unreachable.invalid:22/throwaway.git",
"key": {
"provider": "static",
"path": str(cls._key_path),
},
"identity": str(cls._key_path),
},
}},
},
@@ -198,7 +198,6 @@ class TestSmolmachinesLaunch(unittest.TestCase):
# connect fails, which is the property chunk 3 will
# preserve once egress is actually running.
r = self.bottle.exec(
"env -u HTTPS_PROXY -u HTTP_PROXY -u https_proxy -u http_proxy "
f"curl -s --show-error --max-time 3 http://{self.plan.bundle_ip}:9099 "
"2>&1 || true"
)
-46
View File
@@ -168,34 +168,6 @@ class TestAgentProviderRuntime(unittest.TestCase):
self.assertEqual("~/.claude/statusline.sh", settings["statusLine"]["command"])
self.assertEqual("custom:bot-bottle-research-ui", settings["theme"])
def test_claude_plan_uses_startup_args_from_provider_settings(self):
with tempfile.TemporaryDirectory(prefix="bb-provider.") as tmp:
plan = build_agent_provision_plan(
template="claude",
dockerfile="",
state_dir=Path(tmp),
instance_name="bot-bottle-test",
prompt_file=Path(tmp) / "prompt.txt",
provider_settings={
"startup_args": ["--model", "opus"],
},
)
self.assertEqual(("--model", "opus"), plan.startup_args)
def test_codex_plan_uses_startup_args_from_provider_settings(self):
with tempfile.TemporaryDirectory(prefix="bb-provider.") as tmp:
plan = build_agent_provision_plan(
template="codex",
dockerfile="",
state_dir=Path(tmp),
instance_name="bot-bottle-test",
prompt_file=Path(tmp) / "prompt.txt",
provider_settings={
"startup_args": ["--model", "gpt-5-codex"],
},
)
self.assertEqual(("--model", "gpt-5-codex"), plan.startup_args)
def test_codex_forward_host_credentials_populates_egress_routes(self):
with tempfile.TemporaryDirectory(prefix="bb-provider.") as tmp:
home = Path(tmp) / "host-codex"
@@ -422,24 +394,6 @@ class TestAgentProviderRuntime(unittest.TestCase):
self.assertNotIn("OPENROUTER_API_KEY", plan.guest_env)
self.assertTrue(provider["compat"]["supportsReasoningEffort"])
def test_pi_plan_appends_startup_args_from_provider_settings(self):
with tempfile.TemporaryDirectory(prefix="bb-provider.") as tmp:
plan = build_agent_provision_plan(
template="pi",
dockerfile="",
state_dir=Path(tmp),
instance_name="bot-bottle-test",
prompt_file=Path(tmp) / "prompt.txt",
provider_settings={
"models": ["qwen3:14b"],
"startup_args": ["--no-stream"],
},
)
self.assertEqual(
("--models", "ollama/qwen3:14b", "--no-stream"),
plan.startup_args,
)
def test_pi_prompt_mode_appends_system_prompt_interactively(self):
self.assertEqual(
["--append-system-prompt", "/home/node/.bot-bottle-prompt.txt"],
+2 -2
View File
@@ -115,8 +115,8 @@ class TestBottleIdentity(unittest.TestCase):
class TestPreserveMarker(_FakeHomeMixin, unittest.TestCase):
"""The .preserve marker tells cli.py's session-end cleanup to keep
the state dir instead of removing it."""
"""The .preserve marker is how capability_apply tells cli.py's
session-end cleanup to keep the state dir instead of removing it."""
def setUp(self):
self._setup_fake_home()
+51
View File
@@ -0,0 +1,51 @@
"""Unit: `bot-bottle doctor` host prerequisite checks."""
from __future__ import annotations
import tempfile
import unittest
from pathlib import Path
from unittest.mock import MagicMock, patch
from bot_bottle.cli import doctor
class TestDoctor(unittest.TestCase):
def test_success_when_prerequisites_present(self):
with tempfile.TemporaryDirectory() as tmp, patch.object(
doctor.Path, "home", return_value=Path(tmp),
), patch.object(
doctor.shutil, "which", return_value="/usr/bin/docker",
), patch.object(
doctor.subprocess, "run",
return_value=MagicMock(returncode=0),
):
Path(tmp, ".bot-bottle").mkdir()
self.assertEqual(0, doctor.cmd_doctor([]))
def test_missing_config_fails(self):
with tempfile.TemporaryDirectory() as tmp, patch.object(
doctor.Path, "home", return_value=Path(tmp),
), patch.object(
doctor.shutil, "which", return_value="/usr/bin/docker",
), patch.object(
doctor.subprocess, "run",
return_value=MagicMock(returncode=0),
):
self.assertEqual(1, doctor.cmd_doctor([]))
def test_missing_docker_fails_before_daemon_check(self):
with tempfile.TemporaryDirectory() as tmp, patch.object(
doctor.Path, "home", return_value=Path(tmp),
), patch.object(
doctor.shutil, "which", return_value=None,
), patch.object(
doctor.subprocess, "run",
) as run:
Path(tmp, ".bot-bottle").mkdir()
self.assertEqual(1, doctor.cmd_doctor([]))
run.assert_not_called()
if __name__ == "__main__":
unittest.main()
+61 -224
View File
@@ -1,8 +1,7 @@
"""Unit: cmd_start selector dispatch (PRD 0051, issue #269).
"""Unit: cmd_start selector dispatch (PRD 0051).
Tests that cmd_start calls filter_select only when the agent name is
absent, shows the bottle multiselect after agent selection, and skips
pickers when both are explicitly set.
absent, skips it when the agent is explicit, and returns 0 on cancel.
All actual launch work is stubbed so no container is created.
"""
@@ -11,7 +10,6 @@ from __future__ import annotations
import os
import unittest
from collections.abc import Mapping, Sequence
from unittest.mock import MagicMock, patch
import bot_bottle.cli.start as start_mod
@@ -19,16 +17,10 @@ import bot_bottle.cli.tui as tui_mod
from bot_bottle.backend import ActiveAgent
def _make_manifest(
agent_names: list[str],
bottle_names: list[str] | None = None,
agent_bottle: str = "",
):
def _make_manifest(agent_names: list[str]):
manifest = MagicMock()
manifest.agents = {name: MagicMock(bottle=agent_bottle) for name in agent_names}
manifest.agents = {name: MagicMock() for name in agent_names}
manifest.all_agent_names = sorted(agent_names)
manifest.all_bottle_names = sorted(bottle_names or [])
manifest.home_md = None # eager mode so _peek_agent_bottle uses agents dict
return manifest
@@ -36,27 +28,27 @@ class TestCmdStartSelector(unittest.TestCase):
"""Drive cmd_start with a minimal set of stubs."""
def setUp(self):
self._manifest = _make_manifest(["researcher", "implementer"], ["claude", "dev"])
# Stub Manifest.resolve so no on-disk manifest is needed.
self._manifest = _make_manifest(["researcher", "implementer"])
self._resolve_patch = patch(
"bot_bottle.cli.start.ManifestIndex.resolve",
return_value=self._manifest,
)
self._resolve_patch.start()
# Stub _launch_bottle so no real container work happens.
self._launch_patch = patch(
"bot_bottle.cli.start._launch_bottle",
return_value=0,
)
self._launch_mock = self._launch_patch.start()
# Stub filter_select (agent picker) and filter_multiselect (bottle picker).
self._agent_picker_patch = patch.object(tui_mod, "filter_select")
self._agent_picker_mock = self._agent_picker_patch.start()
self._bottle_picker_patch = patch.object(tui_mod, "filter_multiselect")
self._bottle_picker_mock = self._bottle_picker_patch.start()
self._bottle_picker_mock.return_value = ["claude"] # default: one bottle selected
# Stub filter_select to avoid opening /dev/tty.
self._tui_patch = patch.object(tui_mod, "filter_select")
self._tui_mock = self._tui_patch.start()
# Ensure BOT_BOTTLE_BACKEND is absent so omitted --backend
# flows through to the resolver default.
self._env_patch = patch.dict(os.environ, {}, clear=False)
self._env_patch.start()
os.environ.pop("BOT_BOTTLE_BACKEND", None)
@@ -64,108 +56,50 @@ class TestCmdStartSelector(unittest.TestCase):
def tearDown(self):
self._resolve_patch.stop()
self._launch_patch.stop()
self._agent_picker_patch.stop()
self._bottle_picker_patch.stop()
self._tui_patch.stop()
self._env_patch.stop()
# ------------------------------------------------------------------
# Agent explicit — agent picker skipped; bottle picker always shown
# Both explicit — no picker shown
# ------------------------------------------------------------------
def test_explicit_agent_skips_agent_picker(self):
def test_both_explicit_skips_picker(self):
self._tui_mock.return_value = "researcher"
rc = start_mod.cmd_start(["--backend=docker", "researcher"])
self.assertEqual(0, rc)
self._agent_picker_mock.assert_not_called()
self._bottle_picker_mock.assert_called_once()
self._tui_mock.assert_not_called()
self._launch_mock.assert_called_once()
def test_explicit_agent_bottle_picker_shows_available_bottles(self):
start_mod.cmd_start(["researcher"])
call_kwargs = self._bottle_picker_mock.call_args
self.assertEqual(["claude", "dev"], call_kwargs[0][0])
self.assertIn("bottle", call_kwargs[1]["title"].lower())
# ------------------------------------------------------------------
# Agent absent → agent picker fires; bottle picker always follows
# ------------------------------------------------------------------
def test_agent_absent_shows_agent_picker(self):
self._agent_picker_mock.return_value = "researcher"
rc = start_mod.cmd_start(["--backend=docker"])
self.assertEqual(0, rc)
self._agent_picker_mock.assert_called_once()
call_kwargs = self._agent_picker_mock.call_args
self.assertEqual(["implementer", "researcher"], call_kwargs[0][0])
self.assertIn("agent", call_kwargs[1]["title"].lower())
# Bottle picker must also fire after agent selection.
self._bottle_picker_mock.assert_called_once()
def test_agent_picker_cancel_skips_bottle_picker(self):
self._agent_picker_mock.return_value = None
rc = start_mod.cmd_start(["--backend=docker"])
self.assertEqual(0, rc)
self._bottle_picker_mock.assert_not_called()
self._launch_mock.assert_not_called()
def test_bottle_picker_cancel_returns_0(self):
self._bottle_picker_mock.return_value = None
rc = start_mod.cmd_start(["researcher"])
self.assertEqual(0, rc)
self._launch_mock.assert_not_called()
# ------------------------------------------------------------------
# Bottle selection is forwarded to BottleSpec
# ------------------------------------------------------------------
def test_selected_bottles_forwarded_to_spec(self):
self._bottle_picker_mock.return_value = ["claude", "dev"]
start_mod.cmd_start(["researcher"])
self._launch_mock.assert_called_once()
spec = self._launch_mock.call_args[0][0]
self.assertEqual(("claude", "dev"), spec.bottle_names)
def test_empty_bottle_selection_forwarded(self):
self._bottle_picker_mock.return_value = []
start_mod.cmd_start(["researcher"])
self._launch_mock.assert_called_once()
spec = self._launch_mock.call_args[0][0]
self.assertEqual((), spec.bottle_names)
# ------------------------------------------------------------------
# Agent default bottle pre-populates the picker
# ------------------------------------------------------------------
def test_agent_bottle_prepopulates_bottle_picker(self):
manifest = _make_manifest(
["implementer"], ["claude", "dev"], agent_bottle="claude"
)
with patch(
"bot_bottle.cli.start.ManifestIndex.resolve", return_value=manifest
):
start_mod.cmd_start(["implementer"])
call_kwargs = self._bottle_picker_mock.call_args
self.assertEqual(["claude"], call_kwargs[1]["initial"])
def test_no_agent_bottle_empty_initial(self):
manifest = _make_manifest(["researcher"], ["claude", "dev"], agent_bottle="")
with patch(
"bot_bottle.cli.start.ManifestIndex.resolve", return_value=manifest
):
start_mod.cmd_start(["researcher"])
call_kwargs = self._bottle_picker_mock.call_args
self.assertEqual([], call_kwargs[1]["initial"])
# ------------------------------------------------------------------
# Backend wiring
# ------------------------------------------------------------------
def test_explicit_backend_forwarded(self):
start_mod.cmd_start(["--backend=docker", "researcher"])
_, kwargs = self._launch_mock.call_args
self.assertEqual("docker", kwargs["backend_name"])
def test_absent_backend_uses_default(self):
start_mod.cmd_start(["researcher"])
# ------------------------------------------------------------------
# Agent absent → agent picker fires; backend explicit
# ------------------------------------------------------------------
def test_agent_absent_shows_agent_picker(self):
self._tui_mock.return_value = "researcher"
rc = start_mod.cmd_start(["--backend=docker"])
self.assertEqual(0, rc)
self._tui_mock.assert_called_once()
call_kwargs = self._tui_mock.call_args
self.assertEqual(["implementer", "researcher"], call_kwargs[0][0])
self.assertIn("agent", call_kwargs[1]["title"].lower())
def test_agent_picker_cancel_returns_0(self):
self._tui_mock.return_value = None
rc = start_mod.cmd_start(["--backend=docker"])
self.assertEqual(0, rc)
self._launch_mock.assert_not_called()
# ------------------------------------------------------------------
# Agent explicit, backend absent → no picker
# ------------------------------------------------------------------
def test_backend_absent_uses_default_without_picker(self):
rc = start_mod.cmd_start(["researcher"])
self.assertEqual(0, rc)
self._tui_mock.assert_not_called()
self._launch_mock.assert_called_once()
_, kwargs = self._launch_mock.call_args
self.assertIsNone(kwargs["backend_name"])
@@ -176,21 +110,28 @@ class TestCmdStartSelector(unittest.TestCase):
finally:
os.environ.pop("BOT_BOTTLE_BACKEND", None)
self.assertEqual(0, rc)
self._tui_mock.assert_not_called()
def test_both_absent_shows_agent_picker_then_bottle_picker(self):
self._agent_picker_mock.return_value = "researcher"
# ------------------------------------------------------------------
# Both absent → only agent picker
# ------------------------------------------------------------------
def test_both_absent_shows_only_agent_picker(self):
self._tui_mock.return_value = "researcher"
rc = start_mod.cmd_start([])
self.assertEqual(0, rc)
self._agent_picker_mock.assert_called_once()
self._bottle_picker_mock.assert_called_once()
self._tui_mock.assert_called_once()
title = self._tui_mock.call_args[1]["title"].lower()
self.assertIn("agent", title)
self._launch_mock.assert_called_once()
_, kwargs = self._launch_mock.call_args
self.assertIsNone(kwargs["backend_name"])
def test_both_absent_agent_cancel_skips_bottle_and_launch(self):
self._agent_picker_mock.return_value = None
def test_both_absent_agent_cancel_skips_backend_picker(self):
self._tui_mock.side_effect = [None]
rc = start_mod.cmd_start([])
self.assertEqual(0, rc)
self._agent_picker_mock.assert_called_once()
self._bottle_picker_mock.assert_not_called()
self.assertEqual(1, self._tui_mock.call_count)
self._launch_mock.assert_not_called()
@@ -208,13 +149,11 @@ class TestCmdStartLabelCollision(unittest.TestCase):
"""cmd_start re-prompts when the label's slug is already running."""
def setUp(self):
self._manifest = _make_manifest(["researcher"], ["claude"])
self._manifest = _make_manifest(["researcher"])
patch("bot_bottle.cli.start.ManifestIndex.resolve", return_value=self._manifest).start()
self._launch_mock = patch(
"bot_bottle.cli.start._launch_bottle", return_value=0,
).start()
# Stub the bottle picker to always return a selection.
patch.object(tui_mod, "filter_multiselect", return_value=["claude"]).start()
self.addCleanup(patch.stopall)
def test_no_collision_proceeds_without_reprompt(self):
@@ -254,107 +193,5 @@ class TestCmdStartLabelCollision(unittest.TestCase):
self.assertIn("already in use", second_call_kwargs.get("disclaimer", ""))
class TestBottleLineage(unittest.TestCase):
"""Unit tests for _bottle_lineage."""
def test_returns_empty_in_eager_mode(self):
manifest = _make_manifest(["agent"], ["base", "dev"])
# home_md is None in eager mode → no file reads, returns {}
result = start_mod._bottle_lineage(manifest)
self.assertEqual({}, result)
def test_reads_extends_chain_from_files(self):
import tempfile
from pathlib import Path
with tempfile.TemporaryDirectory() as tmp:
bottles_dir = Path(tmp) / "bottles"
bottles_dir.mkdir()
(bottles_dir / "base.md").write_text("---\n{}\n---\n")
(bottles_dir / "mid.md").write_text("---\nextends: base\n---\n")
(bottles_dir / "leaf.md").write_text("---\nextends: mid\n---\n")
manifest = MagicMock()
manifest.home_md = Path(tmp)
result = start_mod._bottle_lineage(manifest)
self.assertNotIn("base", result) # no parent → not in map
self.assertEqual("base -> mid", result["mid"])
self.assertEqual("base -> mid -> leaf", result["leaf"])
def test_cycle_protection(self):
import tempfile
from pathlib import Path
with tempfile.TemporaryDirectory() as tmp:
bottles_dir = Path(tmp) / "bottles"
bottles_dir.mkdir()
(bottles_dir / "a.md").write_text("---\nextends: b\n---\n")
(bottles_dir / "b.md").write_text("---\nextends: a\n---\n")
manifest = MagicMock()
manifest.home_md = Path(tmp)
result = start_mod._bottle_lineage(manifest)
# Cycle must not hang; each should get a two-element chain.
for name in ("a", "b"):
self.assertIn(name, result)
self.assertIn("->", result[name])
class TestManifestToYaml(unittest.TestCase):
"""Unit tests for _manifest_to_yaml."""
def _make_manifest_obj(
self,
*,
skills: Sequence[str] = (),
env: Mapping[str, str] | None = None,
supervise: bool = True,
agent_provider_template: str = "claude",
):
from bot_bottle.manifest import Manifest, ManifestBottle
from bot_bottle.manifest_agent import ManifestAgent, ManifestAgentProvider
agent = ManifestAgent(skills=tuple(skills))
bottle = ManifestBottle(
env=env or {},
supervise=supervise,
agent_provider=ManifestAgentProvider(template=agent_provider_template),
)
return Manifest(agent=agent, bottle=bottle)
def test_includes_agent_section(self):
m = self._make_manifest_obj(skills=["researcher"])
yaml = start_mod._manifest_to_yaml(m)
self.assertIn("agent:", yaml)
self.assertIn("- researcher", yaml)
def test_includes_bottle_section(self):
m = self._make_manifest_obj(env={"FOO": "bar"})
yaml = start_mod._manifest_to_yaml(m)
self.assertIn("bottle:", yaml)
self.assertIn("FOO: bar", yaml)
def test_supervise_rendered(self):
m_true = self._make_manifest_obj(supervise=True)
m_false = self._make_manifest_obj(supervise=False)
self.assertIn("supervise: true", start_mod._manifest_to_yaml(m_true))
self.assertIn("supervise: false", start_mod._manifest_to_yaml(m_false))
def test_non_claude_provider_shown(self):
m = self._make_manifest_obj(agent_provider_template="codex")
yaml = start_mod._manifest_to_yaml(m)
self.assertIn("agent_provider:", yaml)
self.assertIn("template: codex", yaml)
def test_default_claude_provider_omitted(self):
m = self._make_manifest_obj(agent_provider_template="claude")
yaml = start_mod._manifest_to_yaml(m)
self.assertNotIn("agent_provider:", yaml)
if __name__ == "__main__":
unittest.main()
+2 -23
View File
@@ -29,8 +29,8 @@ class _FakeHomeMixin:
class TestCaptureSessionState(_FakeHomeMixin, unittest.TestCase):
# capture_claude_session_state handles the preserve marker for
# non-zero agent exits.
# snapshot_transcript is commented out (capability_apply is disabled);
# capture_claude_session_state now only handles the preserve marker.
def setUp(self):
self._setup_fake_home()
@@ -102,27 +102,6 @@ class TestAttachAgent(unittest.TestCase):
bottle.argv,
)
def test_remote_control_is_provider_startup_arg(self):
class Bottle:
argv: list[str] = []
def exec_agent(self, argv: list[str], *, tty: bool = True) -> int:
self.argv = list(argv)
return 0
bottle = Bottle()
exit_code = start_mod.attach_agent(
bottle, # type: ignore[arg-type]
agent_provider_template="codex",
startup_args=("remote-control",),
)
self.assertEqual(0, exit_code)
self.assertEqual(
["--dangerously-bypass-approvals-and-sandbox", "remote-control"],
bottle.argv,
)
if __name__ == "__main__":
unittest.main()
+2 -128
View File
@@ -1,4 +1,4 @@
"""Unit tests for bot_bottle.cli.tui — filter_select and filter_multiselect.
"""Unit tests for bot_bottle.cli.tui — filter_select internals.
We test the pure-Python logic (_filter_items, cursor movement, confirm,
cancel) by exercising the internal helpers directly, without spinning up
@@ -8,15 +8,8 @@ a real curses session (which requires a TTY).
from __future__ import annotations
import unittest
from typing import Any, Optional
from bot_bottle.cli.tui import _filter_items, _multiselect_loop, filter_multiselect, filter_select
_KEY_SPACE = 32
_KEY_ENTER = 10
_KEY_ESC = 27
_KEY_CTRL_D = 4
from bot_bottle.cli.tui import _filter_items, filter_select
class TestFilterItems(unittest.TestCase):
@@ -53,124 +46,5 @@ class TestFilterSelectEmptyItems(unittest.TestCase):
self.assertIsNone(result)
class TestFilterMultiselectEmptyItems(unittest.TestCase):
def test_returns_empty_list_for_empty_items(self):
# No TTY needed — short-circuits before opening tty.
result = filter_multiselect([], title="Select", tty_path="/dev/null")
self.assertEqual([], result)
def test_returns_none_when_tty_unavailable(self):
result = filter_multiselect(["a", "b"], tty_path="/nonexistent/tty")
self.assertIsNone(result)
class TestMultiselectLoopReordering(unittest.TestCase):
"""Exercise _multiselect_loop key handling without a real curses terminal.
We drive the loop via a fake screen that feeds a pre-recorded key sequence
and records what was drawn we only need the return value, so the fake
screen's getch() raises StopIteration after the key list is exhausted, and
the loop is expected to return before that via Ctrl-D.
"""
def _run(self, keys: list[int], items: list[str], initial: list[str]) -> Optional[list[str]]:
"""Run _multiselect_loop with a synthetic screen feeding `keys`."""
key_iter = iter(keys)
class FakeScreen:
def erase(self) -> None: pass
def getmaxyx(self) -> tuple[int, int]: return (40, 80)
def refresh(self) -> None: pass
def getch(self) -> int: return next(key_iter)
def addstr(self, *a: Any) -> None: pass
def keypad(self, *a: Any) -> None: pass
return _multiselect_loop(FakeScreen(), items, title="", initial=initial) # type: ignore[arg-type]
def test_ctrl_d_confirms_initial_selection(self):
result = self._run([_KEY_CTRL_D], ["a", "b", "c"], ["a", "b"])
self.assertEqual(["a", "b"], result)
def test_esc_cancels(self):
result = self._run([_KEY_ESC], ["a", "b"], ["a"])
self.assertIsNone(result)
def test_tab_then_K_moves_item_up(self):
# Start: selected = ["a", "b", "c"]
# Tab → order mode (order_cursor=0 on "a")
# ↓ → order_cursor=1 (on "b")
# K → swap b and a → ["b", "a", "c"], order_cursor=0
# Ctrl-D → confirm
DOWN = ord("j")
result = self._run(
[ord("\t"), DOWN, ord("K"), _KEY_CTRL_D],
["a", "b", "c"],
["a", "b", "c"],
)
self.assertEqual(["b", "a", "c"], result)
def test_tab_then_J_moves_item_down(self):
# selected = ["a", "b", "c"], focus order, cursor=0
# J → swap a and b → ["b", "a", "c"], cursor=1
# Ctrl-D → confirm
result = self._run(
[ord("\t"), ord("J"), _KEY_CTRL_D],
["a", "b", "c"],
["a", "b", "c"],
)
self.assertEqual(["b", "a", "c"], result)
def test_K_at_top_is_no_op(self):
# cursor already at 0, K should not change order
result = self._run(
[ord("\t"), ord("K"), _KEY_CTRL_D],
["a", "b"],
["a", "b"],
)
self.assertEqual(["a", "b"], result)
def test_J_at_bottom_is_no_op(self):
DOWN = ord("j")
result = self._run(
[ord("\t"), DOWN, ord("J"), _KEY_CTRL_D],
["a", "b"],
["a", "b"],
)
self.assertEqual(["a", "b"], result)
def test_tab_back_to_filter_then_confirm(self):
# Tab → order, Tab → filter, Ctrl-D confirms unchanged
result = self._run(
[ord("\t"), ord("\t"), _KEY_CTRL_D],
["a", "b"],
["a", "b"],
)
self.assertEqual(["a", "b"], result)
def test_space_toggles_item_on(self):
# Space on an unselected item selects it; Ctrl-D confirms.
result = self._run([_KEY_SPACE, _KEY_CTRL_D], ["a", "b"], [])
self.assertEqual(["a"], result)
def test_space_toggles_item_off(self):
# Space on a selected item deselects it; Ctrl-D confirms empty.
result = self._run([_KEY_SPACE, _KEY_CTRL_D], ["a", "b"], ["a"])
self.assertEqual([], result)
def test_enter_confirms_without_toggle(self):
# Enter immediately confirms the current selection without toggling.
result = self._run([_KEY_ENTER], ["a", "b"], ["a"])
self.assertEqual(["a"], result)
def test_enter_confirms_empty_selection(self):
result = self._run([_KEY_ENTER], ["a", "b"], [])
self.assertEqual([], result)
def test_space_then_enter_confirms(self):
# Space selects "a", Enter confirms.
result = self._run([_KEY_SPACE, _KEY_ENTER], ["a", "b"], [])
self.assertEqual(["a"], result)
if __name__ == "__main__":
unittest.main()
+26 -26
View File
@@ -80,11 +80,7 @@ def _git_gate_plan(upstreams: tuple[GitGateUpstream, ...] = ()) -> GitGatePlan:
)
def _egress_plan(
routes: tuple[EgressRoute, ...] = (),
*,
canary: bool = False,
) -> EgressPlan:
def _egress_plan(routes: tuple[EgressRoute, ...] = ()) -> EgressPlan:
token_env_map = {
r.token_env: r.token_ref
for r in routes
@@ -99,8 +95,6 @@ def _egress_plan(
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 "",
)
@@ -108,6 +102,7 @@ def _supervise_plan() -> SupervisePlan:
return SupervisePlan(
slug=SLUG,
queue_dir=STATE / "supervise" / "queue",
current_config_dir=STATE / "supervise" / "current-config",
internal_network=f"bot-bottle-net-{SLUG}",
)
@@ -117,7 +112,6 @@ 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."""
@@ -156,7 +150,7 @@ def _plan(
slug=SLUG,
forwarded_env={"CLAUDE_CODE_OAUTH_TOKEN": "x"},
git_gate_plan=_git_gate_plan(upstreams),
egress_plan=_egress_plan(routes, canary=canary),
egress_plan=_egress_plan(routes),
supervise_plan=_supervise_plan() if supervise else None,
use_runsc=False,
agent_provision=AgentProvisionPlan(
@@ -270,11 +264,18 @@ class TestAgentAlwaysPresent(unittest.TestCase):
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):
def test_agent_current_config_mount_only_with_supervise(self):
with_sv = bottle_plan_to_compose(_plan(supervise=True))["services"]["agent"]
self.assertNotIn("volumes", with_sv)
self.assertTrue(any(
v["target"] == "/etc/bot-bottle/current-config"
for v in with_sv.get("volumes", [])
))
without_sv = bottle_plan_to_compose(_plan(supervise=False))["services"]["agent"]
self.assertNotIn("volumes", without_sv)
# Either no volumes key at all, or no current-config target.
self.assertFalse(any(
v["target"] == "/etc/bot-bottle/current-config"
for v in without_sv.get("volumes", [])
))
class TestSidecarBundleShape(unittest.TestCase):
@@ -300,6 +301,19 @@ class TestSidecarBundleShape(unittest.TestCase):
self.assertEqual("bot-bottle-sidecars:latest", sc["image"])
self.assertEqual("Dockerfile.sidecars", sc["build"]["dockerfile"])
def test_bundle_uses_packaged_dockerfile_when_root_missing(self):
from bot_bottle.backend.docker import compose as compose_mod
original = compose_mod._REPO_DIR
try:
compose_mod._REPO_DIR = "/tmp/does-not-exist"
self.assertEqual(
"bot_bottle/Dockerfile.sidecars",
compose_mod._sidecar_bundle_dockerfile(),
)
finally:
compose_mod._REPO_DIR = original
def test_bundle_container_name_uses_sidecars_prefix(self):
sc = self._render()["services"]["sidecars"]
self.assertEqual(f"bot-bottle-sidecars-{SLUG}", sc["container_name"])
@@ -374,20 +388,6 @@ class TestSidecarBundleShape(unittest.TestCase):
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"]
@@ -75,6 +75,7 @@ def _plan(
supervise_plan = SupervisePlan(
slug="demo-abc12",
queue_dir=Path("/tmp/queue"),
current_config_dir=Path("/tmp/current-config"),
)
return DockerBottlePlan(
spec=spec,
+1 -9
View File
@@ -29,9 +29,6 @@ from bot_bottle.supervise import SupervisePlan
_URL = "http://supervise:9100/"
_CODEX_DOCKERFILE = (
Path(__file__).resolve().parents[2] / "bot_bottle/contrib/codex/Dockerfile"
)
def _make_bottle(exec_result: ExecResult | None = None) -> MagicMock:
@@ -78,6 +75,7 @@ def _plan(
supervise_plan = SupervisePlan(
slug="demo-abc12",
queue_dir=Path("/tmp/queue"),
current_config_dir=Path("/tmp/current-config"),
)
return DockerBottlePlan(
spec=spec,
@@ -278,12 +276,6 @@ class TestCodexProvision(unittest.TestCase):
)
class TestCodexDockerfile(unittest.TestCase):
def test_installs_procps_for_remote_control_pid_management(self):
dockerfile = _CODEX_DOCKERFILE.read_text()
self.assertIn("procps", dockerfile)
class TestCodexSuperviseMcp(unittest.TestCase):
def test_noop_when_supervise_disabled(self):
bottle = _make_bottle()
@@ -10,11 +10,8 @@ from unittest.mock import MagicMock, patch
from bot_bottle.contrib.gitea.deploy_key_provisioner import (
GiteaDeployKeyProvisioner,
_API_TIMEOUT_SECS,
_KEYGEN_TIMEOUT_SECS,
_split_owner_repo,
)
from bot_bottle.deploy_key_provisioner import DeployKeyCollisionError
def _provisioner() -> GiteaDeployKeyProvisioner:
@@ -85,25 +82,6 @@ class TestCreate(unittest.TestCase):
self.assertEqual(str(fake_key_id), key_id)
self.assertEqual(fake_private, private_bytes)
def test_create_passes_timeout_to_ssh_keygen_and_urlopen(self):
provisioner = _provisioner()
with patch(
"bot_bottle.contrib.gitea.deploy_key_provisioner.subprocess.run"
) as mock_run, patch(
"bot_bottle.contrib.gitea.deploy_key_provisioner.urllib.request.urlopen"
) as mock_urlopen, patch(
"bot_bottle.contrib.gitea.deploy_key_provisioner.Path.read_bytes",
return_value=b"PRIVATE",
), patch(
"bot_bottle.contrib.gitea.deploy_key_provisioner.Path.read_text",
return_value="ssh-ed25519 AAAA\n",
):
mock_urlopen.return_value = _urlopen_response({"id": 1})
provisioner.create("owner/repo", "title")
self.assertEqual(_KEYGEN_TIMEOUT_SECS, mock_run.call_args.kwargs.get("timeout"))
self.assertEqual(_API_TIMEOUT_SECS, mock_urlopen.call_args.kwargs.get("timeout"))
def test_create_raises_on_http_error(self):
provisioner = _provisioner()
with patch(
@@ -122,30 +100,6 @@ class TestCreate(unittest.TestCase):
provisioner.create("owner/repo", "title")
self.assertIn("403", str(ctx.exception))
def test_create_raises_collision_error_on_422(self):
provisioner = _provisioner()
collision_body = json.dumps({
"errors": ["Key content already exists on this repository"],
"message": "422 Unprocessable Entity",
})
with patch(
"bot_bottle.contrib.gitea.deploy_key_provisioner.subprocess.run"
), patch(
"bot_bottle.contrib.gitea.deploy_key_provisioner.urllib.request.urlopen",
side_effect=_http_error(422, collision_body),
), patch(
"bot_bottle.contrib.gitea.deploy_key_provisioner.Path.read_bytes",
return_value=b"pk",
), patch(
"bot_bottle.contrib.gitea.deploy_key_provisioner.Path.read_text",
return_value="ssh-ed25519 AAAA\n",
):
with self.assertRaises(DeployKeyCollisionError) as ctx:
provisioner.create("owner/repo", "my-title")
msg = str(ctx.exception)
self.assertIn("owner/repo", msg)
self.assertIn("my-title", msg)
class TestDelete(unittest.TestCase):
def test_delete_calls_correct_endpoint(self):
@@ -160,16 +114,6 @@ class TestDelete(unittest.TestCase):
self.assertIn("/api/v1/repos/didericis/bot-bottle/keys/99", req.full_url)
self.assertEqual("DELETE", req.get_method())
def test_delete_passes_timeout_to_urlopen(self):
provisioner = _provisioner()
with patch(
"bot_bottle.contrib.gitea.deploy_key_provisioner.urllib.request.urlopen"
) as mock_urlopen:
mock_urlopen.return_value = _urlopen_response({})
provisioner.delete("owner/repo", "7")
self.assertEqual(_API_TIMEOUT_SECS, mock_urlopen.call_args.kwargs.get("timeout"))
def test_delete_tolerates_404(self):
provisioner = _provisioner()
with patch(
+2 -250
View File
@@ -1,23 +1,18 @@
"""Unit: DLP detectors (PRD 0053).
Tests for token pattern scanning, known secret detection, fragmentation-
resistant matching, entropy scoring, and naive prompt injection detection."""
Tests for token pattern scanning, known secret detection, and
naive prompt injection detection."""
import base64
import gzip
import unittest
from bot_bottle.dlp_detectors import (
ENTROPY_BLOCK_THRESHOLD,
PARTIAL_MATCH_MIN_LEN,
REDACT,
_alnum_projection,
_encoded_variants,
_normalize_text,
_shannon_entropy,
redact_tokens,
scan_crlf_injection,
scan_entropy,
scan_known_secrets,
scan_naive_injection,
scan_token_patterns,
@@ -450,248 +445,5 @@ class TestKnownSecretsNewVariants(unittest.TestCase):
self.assertIsNotNone(result)
class TestMatchedAndSafeTokens(unittest.TestCase):
"""PRD 0062: detectors carry the raw matched value, and a safelisted
value is skipped so the supervisor can approve a specific token."""
def test_token_pattern_sets_matched(self):
token = "ghp_" + "A" * 36
result = scan_token_patterns(f"token: {token}")
assert result is not None
self.assertEqual(token, result.matched)
def test_safe_token_is_skipped(self):
token = "ghp_" + "A" * 36
self.assertIsNone(
scan_token_patterns(f"token: {token}", safe_tokens={token})
)
def test_safe_token_does_not_mask_other_token(self):
safe = "ghp_" + "A" * 36
other = "AKIAIOSFODNN7EXAMPLE"
result = scan_token_patterns(
f"a={safe} b={other}", safe_tokens={safe},
)
assert result is not None
self.assertEqual(other, result.matched)
self.assertIn("AWS", result.reason)
def test_known_secret_sets_matched_and_safelist_skips(self):
secret = "supersecretvalue123"
env = {"EGRESS_TOKEN_FOO": secret}
result = scan_known_secrets(f"x={secret}", env=env)
assert result is not None
self.assertEqual(secret, result.matched)
self.assertIsNone(
scan_known_secrets(f"x={secret}", env=env, safe_tokens={secret})
)
def test_crlf_block_has_no_matched_value(self):
result = scan_crlf_injection("path%0d%0aHost: evil")
assert result is not None
self.assertEqual("", result.matched)
class TestStripCrlf(unittest.TestCase):
def test_removes_url_encoded_crlf(self):
from bot_bottle.dlp_detectors import strip_crlf
out = strip_crlf("next=%0d%0aX-Injected: evil")
self.assertNotRegex(out, r"%0[dD]%0[aA]")
def test_removes_literal_header_injection(self):
from bot_bottle.dlp_detectors import strip_crlf
out = strip_crlf("value\r\nX-Injected: evil")
self.assertIsNone(scan_crlf_injection(out))
def test_leaves_clean_text_unchanged(self):
from bot_bottle.dlp_detectors import strip_crlf
self.assertEqual("/api/v1/data?q=hello", strip_crlf("/api/v1/data?q=hello"))
class TestAlnumProjection(unittest.TestCase):
def test_alphanumeric_unchanged(self):
self.assertEqual("abc123XYZ", _alnum_projection("abc123XYZ"))
def test_strips_hyphens(self):
self.assertEqual("mysecretvalue", _alnum_projection("my-secret-value"))
def test_strips_spaces(self):
self.assertEqual("mysecretvalue", _alnum_projection("my secret value"))
def test_strips_dots_and_underscores(self):
self.assertEqual("mysecretvalue", _alnum_projection("my.secret_value"))
def test_empty_string(self):
self.assertEqual("", _alnum_projection(""))
def test_all_special_chars(self):
self.assertEqual("", _alnum_projection("!@#$%^&*()"))
class TestFragmentationResistantMatching(unittest.TestCase):
"""scan_known_secrets catches separator-injection and partial-substring evasion."""
# Secrets long enough that their alnum projections are ≥ 8 chars.
SECRET = "supersecrettoken99"
ENV = {"EGRESS_TOKEN_0": SECRET}
def test_exact_match_still_works(self):
result = scan_known_secrets(f"key={self.SECRET}", env=self.ENV)
self.assertIsNotNone(result)
assert result is not None
self.assertEqual("block", result.severity)
def test_separator_injection_blocked(self):
# Hyphens inserted between chars of the secret.
fragmented = "-".join(self.SECRET)
result = scan_known_secrets(f"data={fragmented}", env=self.ENV)
self.assertIsNotNone(result)
assert result is not None
self.assertEqual("block", result.severity)
self.assertIn("separator injection", result.reason)
def test_space_separator_blocked(self):
fragmented = " ".join(self.SECRET)
result = scan_known_secrets(f"body: {fragmented}", env=self.ENV)
self.assertIsNotNone(result)
assert result is not None
self.assertIn("separator injection", result.reason)
def test_partial_substring_blocked(self):
# First PARTIAL_MATCH_MIN_LEN alnum chars of the secret, no separators.
partial = _alnum_projection(self.SECRET)[:PARTIAL_MATCH_MIN_LEN]
result = scan_known_secrets(f"x={partial}&y=other", env=self.ENV)
self.assertIsNotNone(result)
assert result is not None
self.assertEqual("block", result.severity)
self.assertIn("partial match", result.reason)
def test_short_secret_skips_projection(self):
# Secrets shorter than _ALNUM_MIN_LEN in alnum projection are not
# fragmentation-checked (too many false positives).
short_env = {"EGRESS_TOKEN_0": "abc"}
# "a b c" has alnum projection "abc" (3 chars, < 8); should not block.
self.assertIsNone(scan_known_secrets("a b c", env=short_env))
def test_clean_text_not_blocked(self):
self.assertIsNone(scan_known_secrets("nothing to see here", env=self.ENV))
def test_sensitive_prefixes_param_extra_prefix(self):
env = {"MY_CRED_0": self.SECRET, "IGNORED": "other"}
result = scan_known_secrets(
f"key={self.SECRET}",
env=env,
sensitive_prefixes=("MY_CRED_",),
)
self.assertIsNotNone(result)
assert result is not None
self.assertIn("MY_CRED_0", result.reason)
def test_sensitive_prefixes_default_only_egress_token(self):
# A value under a non-EGRESS_TOKEN_ key is ignored with default prefixes.
env = {"MY_CRED_0": self.SECRET}
self.assertIsNone(scan_known_secrets(f"key={self.SECRET}", env=env))
def test_canary_prefix_detected(self):
canary_value = "canary-fake-secret-value-xyz"
env = {"CANON_ALPHA_SECRET": canary_value}
result = scan_known_secrets(
f"x={canary_value}",
env=env,
sensitive_prefixes=("CANON_ALPHA_SECRET",),
)
self.assertIsNotNone(result)
assert result is not None
self.assertIn("CANON_ALPHA_SECRET", result.reason)
class TestRedactTokensBroadenedPrefixes(unittest.TestCase):
SECRET = "my-provisioned-secret"
def test_default_redacts_egress_token(self):
env = {"EGRESS_TOKEN_0": self.SECRET}
out = redact_tokens(f"val={self.SECRET}", env=env)
self.assertNotIn(self.SECRET, out)
self.assertIn(REDACT, out)
def test_extra_prefix_redacted(self):
env = {"MY_SECRET_KEY": self.SECRET}
out = redact_tokens(
f"val={self.SECRET}",
env=env,
sensitive_prefixes=("MY_SECRET_",),
)
self.assertNotIn(self.SECRET, out)
self.assertIn(REDACT, out)
def test_non_matching_prefix_not_redacted(self):
env = {"MY_SECRET_KEY": self.SECRET}
out = redact_tokens(f"val={self.SECRET}", env=env)
# Default prefixes only include EGRESS_TOKEN_ → secret not redacted
self.assertIn(self.SECRET, out)
class TestShannonEntropy(unittest.TestCase):
def test_empty_string_zero(self):
self.assertEqual(0.0, _shannon_entropy(""))
def test_single_char_zero(self):
self.assertEqual(0.0, _shannon_entropy("aaaaaa"))
def test_two_equal_chars_one_bit(self):
self.assertAlmostEqual(1.0, _shannon_entropy("abababab"), places=10)
def test_high_entropy_random_like(self):
# Uniform 64-char string over 64 distinct symbols has entropy 6 bits.
import string
alphabet = (string.ascii_letters + string.digits + "+/")[:64]
text = alphabet # each char appears exactly once
self.assertAlmostEqual(6.0, _shannon_entropy(text), places=10)
class TestScanEntropy(unittest.TestCase):
def test_empty_returns_none(self):
self.assertIsNone(scan_entropy(""))
def test_low_entropy_returns_none(self):
# Highly repetitive text has low entropy.
self.assertIsNone(scan_entropy("a" * 200))
def test_high_entropy_warns(self):
# Build a 64-char string with entropy > ENTROPY_BLOCK_THRESHOLD.
# Use all 64 distinct printable chars to maximise entropy (~6 bits).
import string
alphabet = (string.ascii_letters + string.digits + "+/")[:64]
result = scan_entropy(alphabet, threshold=ENTROPY_BLOCK_THRESHOLD)
self.assertIsNotNone(result)
assert result is not None
self.assertEqual("warn", result.severity)
self.assertIn("high-entropy", result.reason)
def test_never_blocks(self):
import string
alphabet = (string.ascii_letters + string.digits + "+/")[:64]
result = scan_entropy(alphabet)
# scan_entropy is warn-only; it must never return severity="block".
if result is not None:
self.assertNotEqual("block", result.severity)
def test_location_in_result(self):
import string
alphabet = (string.ascii_letters + string.digits + "+/")[:64]
result = scan_entropy(alphabet, location="authorization header")
if result is not None:
self.assertIn("authorization header", result.location)
def test_structured_json_no_warn(self):
# Typical JSON has low entropy and should not be flagged.
json_body = '{"status": "ok", "message": "hello world", "count": 42}'
self.assertIsNone(scan_entropy(json_body))
def test_short_text_below_window(self):
# Text shorter than the window: checked as one chunk.
# Use a uniform string to ensure it won't be flagged.
self.assertIsNone(scan_entropy("abcde", threshold=ENTROPY_BLOCK_THRESHOLD))
if __name__ == "__main__":
unittest.main()
-10
View File
@@ -136,16 +136,6 @@ class TestClaudeArgv(unittest.TestCase):
argv,
)
def test_codex_remote_control_startup_arg_does_not_receive_initial_prompt(self):
argv = _codex_bottle("/home/node/.bot-bottle-prompt.txt").agent_argv(
["--dangerously-bypass-approvals-and-sandbox", "remote-control"],
)
self.assertEqual(
["docker", "exec", "-it", "bot-bottle-dev-abc", "codex",
"--dangerously-bypass-approvals-and-sandbox", "remote-control"],
argv,
)
def test_codex_resume_does_not_append_initial_prompt(self):
argv = _codex_bottle("/home/node/.bot-bottle-prompt.txt").agent_argv(
["--dangerously-bypass-approvals-and-sandbox", "resume", "--last"],
+2 -2
View File
@@ -65,8 +65,8 @@ class TestOrphanStateDirs(_FakeHomeMixin, unittest.TestCase):
)
def test_preserve_marker_skips_dir(self):
# Preserve marker means the user explicitly wanted this dir
# kept for `resume`.
# Preserve marker = capability-block or crash auto-preserve;
# the user explicitly wanted this dir kept for `resume`.
bottle_state.write_per_bottle_dockerfile("kept-ccc", "FROM x\n")
bottle_state.mark_preserved("kept-ccc")
self.assertEqual(
@@ -31,6 +31,7 @@ class _Provider(AgentProvider):
return AgentProviderRuntime(
template="test", command="test", image="",
prompt_mode="append_file", bypass_args=(), resume_args=(),
remote_control_args=(),
)
def provision_plan(self, **kwargs): # type: ignore[override]
raise NotImplementedError
+6 -231
View File
@@ -1,22 +1,15 @@
"""Unit: Egress route lift + routes.yaml render + token
resolution (PRD 0017, PRD 0053)."""
import tempfile
import unittest
from pathlib import Path
from bot_bottle.egress import (
CODEX_HOST_CREDENTIAL_TOKEN_REF,
Egress,
EgressPlan,
EgressRoute,
_yaml_str_escape,
egress_agent_env_entries,
egress_manifest_routes,
egress_render_routes,
egress_resolve_token_values,
egress_routes_for_bottle,
egress_sidecar_env_entries,
egress_token_env_map,
)
from bot_bottle.log import Die
@@ -209,23 +202,6 @@ class TestProviderRouteMerge(unittest.TestCase):
self.assertEqual((), routes[0].matches)
self.assertEqual({}, egress_token_env_map(routes))
def test_provider_route_defaults_to_redact_on_match(self):
b = _bottle([])
pr = EgressRoute(host="api.anthropic.com")
routes = egress_routes_for_bottle(b, (pr,))
self.assertEqual("redact", routes[0].outbound_on_match)
def test_provider_route_explicit_on_match_preserved(self):
b = _bottle([])
pr = EgressRoute(host="api.anthropic.com", outbound_on_match="supervise")
routes = egress_routes_for_bottle(b, (pr,))
self.assertEqual("supervise", routes[0].outbound_on_match)
def test_manifest_route_does_not_get_redact_default(self):
b = _bottle([{"host": "api.example.com"}])
routes = egress_routes_for_bottle(b)
self.assertEqual("", routes[0].outbound_on_match)
def test_two_provider_routes_with_same_token_ref_share_slot(self):
b = _bottle([])
routes = egress_routes_for_bottle(b, (
@@ -323,7 +299,7 @@ class TestRenderRoutes(unittest.TestCase):
self.assertEqual([], parse_yaml_subset(rendered)["routes"])
def test_round_trip_through_addon_core(self):
from bot_bottle.egress_addon_core import load_config
from bot_bottle.egress_addon_core import load_routes
b = _bottle([
{"host": "api.github.com",
"auth": {"scheme": "Bearer", "token_ref": "GH_PAT"},
@@ -334,7 +310,7 @@ class TestRenderRoutes(unittest.TestCase):
{"host": "api.anthropic.com"},
])
routes = egress_routes_for_bottle(b)
addon_routes = load_config(egress_render_routes(routes)).routes
addon_routes = load_routes(egress_render_routes(routes))
self.assertEqual(3, len(addon_routes))
self.assertEqual("Bearer", addon_routes[0].auth_scheme)
self.assertEqual("EGRESS_TOKEN_0", addon_routes[0].token_env)
@@ -342,41 +318,24 @@ class TestRenderRoutes(unittest.TestCase):
self.assertEqual("", addon_routes[2].auth_scheme)
def test_dlp_round_trips(self):
from bot_bottle.egress_addon_core import load_config
from bot_bottle.egress_addon_core import load_routes
b = _bottle([{"host": "x.example", "dlp": {
"outbound_detectors": ["token_patterns"],
"inbound_detectors": False,
}}])
routes = egress_routes_for_bottle(b)
rendered = egress_render_routes(routes)
addon_routes = load_config(rendered).routes
addon_routes = load_routes(rendered)
self.assertEqual(("token_patterns",), addon_routes[0].outbound_detectors)
self.assertEqual((), addon_routes[0].inbound_detectors)
def test_outbound_on_match_round_trips(self):
from bot_bottle.egress_addon_core import load_config
b = _bottle([{"host": "logs.example", "dlp": {
"outbound_on_match": "redact",
}}])
routes = egress_routes_for_bottle(b)
rendered = egress_render_routes(routes)
self.assertIn('outbound_on_match: "redact"', rendered)
addon_routes = load_config(rendered).routes
self.assertEqual("redact", addon_routes[0].outbound_on_match)
def test_outbound_on_match_default_omitted_from_render(self):
b = _bottle([{"host": "x.example"}])
routes = egress_routes_for_bottle(b)
rendered = egress_render_routes(routes)
self.assertNotIn("outbound_on_match", rendered)
def test_git_fetch_policy_round_trips(self):
from bot_bottle.egress_addon_core import load_config
from bot_bottle.egress_addon_core import load_routes
b = _bottle([{"host": "github.com", "git": {"fetch": True}}])
routes = egress_routes_for_bottle(b)
rendered = egress_render_routes(routes)
self.assertEqual({"fetch": True}, self._parsed(routes)[0]["git"])
addon_routes = load_config(rendered).routes
addon_routes = load_routes(rendered)
self.assertTrue(addon_routes[0].git_fetch)
def test_log_zero_omitted_from_render(self):
@@ -420,76 +379,6 @@ class TestRenderRoutes(unittest.TestCase):
self.assertEqual(LOG_BLOCKS, cfg.log)
class TestYamlStrEscape(unittest.TestCase):
"""_yaml_str_escape produces safe YAML double-quoted scalar content."""
def test_plain_string_unchanged(self):
self.assertEqual("api.example.com", _yaml_str_escape("api.example.com"))
def test_double_quote_escaped(self):
self.assertEqual('\\"', _yaml_str_escape('"'))
def test_backslash_escaped(self):
self.assertEqual("\\\\", _yaml_str_escape("\\"))
def test_newline_escaped(self):
self.assertEqual("\\n", _yaml_str_escape("\n"))
def test_carriage_return_escaped(self):
self.assertEqual("\\r", _yaml_str_escape("\r"))
def test_tab_escaped(self):
self.assertEqual("\\t", _yaml_str_escape("\t"))
def test_combined(self):
self.assertEqual('\\"\\n\\\\', _yaml_str_escape('"\n\\'))
class TestRenderRoutesEscaping(unittest.TestCase):
"""Stray quotes/newlines in manifest strings do not corrupt routes.yaml."""
@staticmethod
def _parsed(routes) -> list[dict]: # type: ignore
return parse_yaml_subset(egress_render_routes(routes))["routes"] # type: ignore
def test_host_with_double_quote_round_trips(self):
routes = (EgressRoute(host='bad"host.example'),)
parsed = self._parsed(routes)
self.assertEqual('bad"host.example', parsed[0]["host"])
def test_host_with_newline_round_trips(self):
routes = (EgressRoute(host="host\nextra.example"),)
parsed = self._parsed(routes)
self.assertEqual("host\nextra.example", parsed[0]["host"])
def test_auth_scheme_with_double_quote_round_trips(self):
routes = (EgressRoute(
host="api.example",
auth_scheme='Bear"er',
token_env="EGRESS_TOKEN_0",
),)
parsed = self._parsed(routes)
self.assertEqual('Bear"er', parsed[0]["auth_scheme"])
def test_path_value_with_double_quote_round_trips(self):
from bot_bottle.egress_addon_core import PathMatch, MatchEntry
routes = (EgressRoute(
host="api.example",
matches=(MatchEntry(paths=(PathMatch(type="prefix", value='/v1/"quoted"/'),)),),
),)
parsed = self._parsed(routes)
self.assertEqual('/v1/"quoted"/', parsed[0]["matches"][0]["paths"][0]["value"])
def test_header_value_with_double_quote_round_trips(self):
from bot_bottle.egress_addon_core import HeaderMatch, MatchEntry
routes = (EgressRoute(
host="api.example",
matches=(MatchEntry(headers=(HeaderMatch(name="x-h", value='val"ue'),)),),
),)
parsed = self._parsed(routes)
self.assertEqual('val"ue', parsed[0]["matches"][0]["headers"][0]["value"])
class TestResolveTokenValues(unittest.TestCase):
def test_reads_host_env(self):
out = egress_resolve_token_values(
@@ -520,119 +409,5 @@ class TestResolveTokenValues(unittest.TestCase):
self.assertEqual({"EGRESS_TOKEN_0": "codex-access-token"}, out)
class TestCanaryGeneration(unittest.TestCase):
"""Egress.prepare() generates a unique canary token per session."""
def _bottle_obj(self):
return ManifestIndex.from_json_obj({
"bottles": {"dev": {"egress": {"routes": []}}},
"agents": {"demo": {"skills": [], "prompt": "", "bottle": "dev"}},
}).bottles["dev"]
def _make_plan(self) -> EgressPlan:
# Use a concrete no-op subclass so we can call prepare() without
# a real backend.
class _TestEgress(Egress):
pass
e = _TestEgress()
with tempfile.TemporaryDirectory() as td:
return e.prepare(self._bottle_obj(), "test-slug", Path(td))
def test_canary_is_non_empty(self):
plan = self._make_plan()
self.assertIsInstance(plan.canary, str)
self.assertGreater(len(plan.canary), 0)
self.assertRegex(plan.canary_env, r"^[A-Z]+_[A-Z]+_SECRET$")
def test_canary_is_unique_per_session(self):
with tempfile.TemporaryDirectory() as td:
bottle = self._bottle_obj()
class _TestEgress(Egress):
pass
e = _TestEgress()
plan_a = e.prepare(bottle, "slug-a", Path(td))
plan_b = e.prepare(bottle, "slug-b", Path(td))
self.assertNotEqual(plan_a.canary, plan_b.canary)
def test_canary_detected_by_scan_known_secrets(self):
from bot_bottle.dlp_detectors import scan_known_secrets
plan = self._make_plan()
env = {plan.canary_env: plan.canary}
result = scan_known_secrets(
f"exfil={plan.canary}",
env=env,
sensitive_prefixes=(plan.canary_env,),
)
self.assertIsNotNone(result)
assert result is not None
self.assertEqual("block", result.severity)
self.assertIn(plan.canary_env, result.reason)
def test_egress_plan_canary_field_default_empty(self):
# Verify EgressPlan can be constructed with an empty canary (backward compat).
from pathlib import Path
plan = EgressPlan(
slug="s",
routes_path=Path("/tmp/r.yaml"),
routes=(),
token_env_map={},
)
self.assertEqual("", plan.canary)
self.assertEqual("", plan.canary_env)
class TestEgressEnvEntries(unittest.TestCase):
def test_sidecar_entries_include_route_tokens_and_canary_scan_prefix(self):
plan = EgressPlan(
slug="s",
routes_path=Path("/tmp/r.yaml"),
routes=(EgressRoute(host="api.example"),),
token_env_map={"EGRESS_TOKEN_1": "T1", "EGRESS_TOKEN_0": "T0"},
canary="fake-canary-value",
canary_env="CANON_ALPHA_SECRET",
)
self.assertEqual(
(
"EGRESS_TOKEN_0",
"EGRESS_TOKEN_1",
"CANON_ALPHA_SECRET=fake-canary-value",
"BOT_BOTTLE_SENSITIVE_PREFIXES=CANON_ALPHA_SECRET",
),
egress_sidecar_env_entries(plan),
)
def test_agent_entries_include_only_canary_bait(self):
plan = EgressPlan(
slug="s",
routes_path=Path("/tmp/r.yaml"),
routes=(),
token_env_map={},
canary="fake-canary-value",
canary_env="CANON_ALPHA_SECRET",
)
self.assertEqual(
("CANON_ALPHA_SECRET=fake-canary-value",),
egress_agent_env_entries(plan),
)
def test_canary_entries_omitted_when_name_missing(self):
plan = EgressPlan(
slug="s",
routes_path=Path("/tmp/r.yaml"),
routes=(),
token_env_map={},
canary="fake-canary-value",
)
self.assertEqual((), egress_sidecar_env_entries(plan))
self.assertEqual((), egress_agent_env_entries(plan))
if __name__ == "__main__":
unittest.main()
+38 -234
View File
@@ -22,16 +22,15 @@ from bot_bottle.egress_addon_core import (
MatchEntry,
PathMatch,
Route,
ScanResult,
build_inbound_scan_text,
build_outbound_scan_text,
build_token_allow_payload,
decide,
decide_git_fetch,
evaluate_matches,
is_git_fetch_request,
is_git_push_request,
load_config,
load_routes,
match_route,
outbound_scan_headers,
parse_config,
@@ -268,24 +267,46 @@ class TestParseDlp(unittest.TestCase):
"dlp": {"wat": True},
}]})
def test_outbound_on_match_default_empty(self):
routes = parse_routes({"routes": [{"host": "x.example"}]})
self.assertEqual("", routes[0].outbound_on_match)
def test_outbound_on_match_parsed(self):
for policy in ("block", "redact", "supervise"):
routes = parse_routes({"routes": [{
"host": "x.example",
"dlp": {"outbound_on_match": policy},
}]})
self.assertEqual(policy, routes[0].outbound_on_match)
# --- load_routes ---------------------------------------------------------
def test_outbound_on_match_invalid_rejected(self):
class TestLoadRoutes(unittest.TestCase):
def test_yaml_text_round_trip(self):
routes = load_routes(
'routes:\n'
' - host: "api.example"\n'
)
self.assertEqual(1, len(routes))
self.assertEqual("api.example", routes[0].host)
def test_full_route_shape_parses(self):
routes = load_routes(
'routes:\n'
' - host: "api.example"\n'
' auth_scheme: "Bearer"\n'
' token_env: "EGRESS_TOKEN_0"\n'
' matches:\n'
' - paths:\n'
' - value: "/v1/"\n'
' - type: "exact"\n'
' value: "/messages"\n'
)
self.assertEqual(1, len(routes))
r = routes[0]
self.assertEqual("api.example", r.host)
self.assertEqual("Bearer", r.auth_scheme)
self.assertEqual("EGRESS_TOKEN_0", r.token_env)
self.assertEqual(1, len(r.matches))
self.assertEqual(2, len(r.matches[0].paths))
def test_empty_routes_list(self):
routes = load_routes("routes: []\n")
self.assertEqual((), routes)
def test_invalid_yaml_raises_value_error(self):
with self.assertRaises(ValueError):
parse_routes({"routes": [{
"host": "x.example",
"dlp": {"outbound_on_match": "nope"},
}]})
load_routes("routes:\n\t- host: x\n")
# --- load_config / parse_config ------------------------------------------
@@ -336,33 +357,6 @@ class TestLoadConfig(unittest.TestCase):
with self.assertRaises(ValueError):
parse_config("not a dict")
def test_empty_routes_list(self):
cfg = load_config("routes: []\n")
self.assertEqual((), cfg.routes)
def test_full_route_shape_parses(self):
cfg = load_config(
'routes:\n'
' - host: "api.example"\n'
' auth_scheme: "Bearer"\n'
' token_env: "EGRESS_TOKEN_0"\n'
' matches:\n'
' - paths:\n'
' - value: "/v1/"\n'
' - type: "exact"\n'
' value: "/messages"\n'
)
r = cfg.routes[0]
self.assertEqual("api.example", r.host)
self.assertEqual("Bearer", r.auth_scheme)
self.assertEqual("EGRESS_TOKEN_0", r.token_env)
self.assertEqual(1, len(r.matches))
self.assertEqual(2, len(r.matches[0].paths))
def test_invalid_yaml_raises_value_error(self):
with self.assertRaises(ValueError):
load_config("routes:\n\t- host: x\n")
# --- evaluate_matches ---------------------------------------------------
@@ -1173,195 +1167,5 @@ class TestScanInbound(unittest.TestCase):
self.assertEqual("block", result.severity)
class TestScanOutboundSafeTokens(unittest.TestCase):
"""PRD 0062: scan_outbound threads the supervisor-approved safe-tokens
set into the token detectors."""
def test_safe_token_allows_request(self):
text = build_outbound_scan_text(
host="api.example.com", path="/v1/data", query="",
headers={}, body=f"key={_AWS_KEY}",
)
self.assertIsNone(
scan_outbound(_ROUTE, text, {}, safe_tokens={_AWS_KEY})
)
def test_unrelated_safe_token_still_blocks(self):
text = build_outbound_scan_text(
host="api.example.com", path="/v1/data", query="",
headers={}, body=f"key={_AWS_KEY}",
)
result = scan_outbound(_ROUTE, text, {}, safe_tokens={"ghp_" + "A" * 36})
self.assertIsNotNone(result)
assert result is not None
self.assertEqual(_AWS_KEY, result.matched)
class TestScanOutboundCrlfText(unittest.TestCase):
"""PRD 0062: CRLF is scanned only over the request line + headers
(crlf_text), never the body a body is not an injection vector."""
def test_body_crlf_not_flagged_when_crlf_text_excludes_body(self):
# A form-encoded multi-line body legitimately contains %0d%0a.
body = "comment=line1%0d%0aline2"
full = build_outbound_scan_text(
host="api.example.com", path="/submit", query="",
headers={}, body=body,
)
crlf_text = build_outbound_scan_text(
host="api.example.com", path="/submit", query="",
headers={}, body="",
)
self.assertIsNone(scan_outbound(_ROUTE, full, {}, crlf_text=crlf_text))
def test_request_line_crlf_still_flagged(self):
full = build_outbound_scan_text(
host="api.example.com", path="/p", query="next=%0d%0aX:evil",
headers={}, body="",
)
crlf_text = full
result = scan_outbound(_ROUTE, full, {}, crlf_text=crlf_text)
self.assertIsNotNone(result)
assert result is not None
self.assertEqual("block", result.severity)
def test_default_crlf_text_scans_full_blob(self):
# Backward compatibility: crlf_text=None scans everything (body too).
full = build_outbound_scan_text(
host="api.example.com", path="/submit", query="",
headers={}, body="x=%0d%0aX:evil",
)
self.assertIsNotNone(scan_outbound(_ROUTE, full, {}))
class TestBuildTokenAllowPayload(unittest.TestCase):
def test_payload_includes_context_and_no_raw_token(self):
result = ScanResult(
severity="block",
reason="AWS access key found in body",
location="body",
context="key=******** tail",
matched=_AWS_KEY,
)
payload = build_token_allow_payload(
"api.example.com", "POST", "/v1/ingest", result,
)
self.assertIn("host: api.example.com", payload)
self.assertIn("method: POST", payload)
self.assertIn("path: /v1/ingest", payload)
self.assertIn("AWS access key found in body", payload)
self.assertIn("key=******** tail", payload)
# The raw matched value must never appear in the proposal file.
self.assertNotIn(_AWS_KEY, payload)
def test_payload_omits_context_line_when_empty(self):
result = ScanResult(severity="block", reason="r", matched="x")
payload = build_token_allow_payload("h", "GET", "/", result)
self.assertNotIn("context:", payload)
class TestScanOutboundEnhanced(unittest.TestCase):
"""scan_outbound changes: binary decode, entropy detector,
broadened known-value prefixes, fragmentation resistance."""
_ROUTE = Route(host="api.example.com")
_ROUTE_ENTROPY = Route(
host="api.example.com",
outbound_detectors=("entropy",),
)
def test_binary_body_latin1_decode_finds_ascii_secret(self):
# Body contains valid ASCII secret surrounded by non-UTF-8 bytes.
secret = "supersecrettoken99"
env = {"EGRESS_TOKEN_0": secret}
# Wrap the secret in bytes that are invalid UTF-8.
body = b"\x80\x81" + secret.encode("ascii") + b"\xff"
result = scan_outbound(self._ROUTE, body, env)
self.assertIsNotNone(result)
assert result is not None
self.assertEqual("block", result.severity)
def test_binary_body_valid_utf8_decoded_correctly(self):
env = {"EGRESS_TOKEN_0": "mysecret"}
# Valid UTF-8 body — should be decoded as UTF-8, not latin-1.
body = "clean body with mysecret".encode("utf-8")
result = scan_outbound(self._ROUTE, body, env)
self.assertIsNotNone(result)
def test_entropy_detector_off_by_default(self):
import string
# High-entropy content should NOT warn if the route has no entropy detector.
alphabet = (string.ascii_letters + string.digits + "+/")[:64]
result = scan_outbound(self._ROUTE, alphabet, {})
self.assertIsNone(result)
def test_entropy_detector_warns_when_enabled(self):
import string
alphabet = (string.ascii_letters + string.digits + "+/")[:64]
result = scan_outbound(self._ROUTE_ENTROPY, alphabet, {})
self.assertIsNotNone(result)
assert result is not None
self.assertEqual("warn", result.severity)
def test_bot_bottle_sensitive_prefixes_env_var(self):
# When the sidecar env contains BOT_BOTTLE_SENSITIVE_PREFIXES,
# scan_outbound should scan those additional prefixes.
secret = "extra-sensitive-value-abc"
env = {
"MY_CRED_KEY": secret,
"BOT_BOTTLE_SENSITIVE_PREFIXES": "MY_CRED_",
}
result = scan_outbound(self._ROUTE, f"x={secret}", env)
self.assertIsNotNone(result)
assert result is not None
self.assertEqual("block", result.severity)
def test_bot_bottle_sensitive_prefixes_multiple(self):
secret = "my-api-key-value-xyz"
env = {
"ANTHROPIC_API_0": secret,
"BOT_BOTTLE_SENSITIVE_PREFIXES": "ANTHROPIC_API_,OTHER_",
}
result = scan_outbound(self._ROUTE, f"auth={secret}", env)
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
# as sensitive through BOT_BOTTLE_SENSITIVE_PREFIXES.
canary = "canaryvalue12345abcdef"
env = {
"CANON_ALPHA_SECRET": canary,
"BOT_BOTTLE_SENSITIVE_PREFIXES": "CANON_ALPHA_SECRET",
}
result = scan_outbound(self._ROUTE, f"data={canary}", env)
self.assertIsNotNone(result)
assert result is not None
self.assertEqual("block", result.severity)
self.assertIn("CANON_ALPHA_SECRET", result.reason)
def test_fragmented_canary_blocked(self):
# Canary with separators injected is still caught.
canary = "supersecretcanary99"
env = {
"CANON_ALPHA_SECRET": canary,
"BOT_BOTTLE_SENSITIVE_PREFIXES": "CANON_ALPHA_SECRET",
}
fragmented = "-".join(canary)
result = scan_outbound(self._ROUTE, f"x={fragmented}", env)
self.assertIsNotNone(result)
class TestOutboundDetectorNames(unittest.TestCase):
def test_entropy_in_outbound_detector_names(self):
from bot_bottle.egress_addon_core import OUTBOUND_DETECTOR_NAMES
self.assertIn("entropy", OUTBOUND_DETECTOR_NAMES)
def test_known_secrets_in_outbound_detector_names(self):
from bot_bottle.egress_addon_core import OUTBOUND_DETECTOR_NAMES
self.assertIn("known_secrets", OUTBOUND_DETECTOR_NAMES)
def test_token_patterns_in_outbound_detector_names(self):
from bot_bottle.egress_addon_core import OUTBOUND_DETECTOR_NAMES
self.assertIn("token_patterns", OUTBOUND_DETECTOR_NAMES)
if __name__ == "__main__":
unittest.main()
@@ -1,274 +0,0 @@
"""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
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."""
from __future__ import annotations
import json
import sys
import types
import unittest
from io import StringIO
from typing import Any
from unittest.mock import patch
# ---------------------------------------------------------------------------
# Sidecar-import shims — must run before importing egress_addon
# ---------------------------------------------------------------------------
def _ensure_shims() -> None:
if "mitmproxy" not in sys.modules:
_mm = types.ModuleType("mitmproxy")
_mh = types.ModuleType("mitmproxy.http")
setattr(_mm, "http", _mh)
sys.modules["mitmproxy"] = _mm
sys.modules["mitmproxy.http"] = _mh
if "egress_addon_core" not in sys.modules:
import bot_bottle.egress_addon_core as _core
sys.modules["egress_addon_core"] = _core
_ensure_shims()
from bot_bottle.egress_addon import EgressAddon # noqa: E402 (import after shims)
from bot_bottle.egress_addon_core import Config, LOG_FULL # noqa: E402
# ---------------------------------------------------------------------------
# Helpers
# ---------------------------------------------------------------------------
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._supervise_queue_dir = ""
a._supervise_slug = ""
a._token_allow_timeout = 300.0
return a
class _Headers:
def __init__(self, d: dict[str, str]) -> None:
self._d = d
def items(self) -> list[tuple[str, str]]:
return list(self._d.items())
class _Request:
def __init__(
self,
host: str = "api.example.com",
method: str = "POST",
path: str = "/v1/messages",
headers: dict[str, str] | None = None,
body: str = "",
) -> None:
self.pretty_host = host
self.method = method
self.path = path
self.headers = _Headers(headers or {})
self._body = body
def get_text(self, *, strict: bool = True) -> str:
return self._body
class _Response:
def __init__(
self,
status_code: int = 200,
headers: dict[str, str] | None = None,
body: str = "",
) -> None:
self.status_code = status_code
self.headers = _Headers(headers or {})
self._body = body
def get_text(self, *, strict: bool = True) -> str:
return self._body
class _Flow:
def __init__(
self,
request: _Request | None = None,
response: _Response | None = None,
) -> None:
self.request = request or _Request()
self.response = response or _Response()
def _log_request(addon: EgressAddon, flow: _Flow) -> dict[str, Any]:
buf = StringIO()
with patch("sys.stderr", buf):
addon._log_request(flow) # type: ignore[arg-type]
return json.loads(buf.getvalue())
def _log_response(addon: EgressAddon, flow: _Flow) -> dict[str, Any]:
buf = StringIO()
with patch("sys.stderr", buf):
addon._log_response(flow) # type: ignore[arg-type]
return json.loads(buf.getvalue())
# ---------------------------------------------------------------------------
# _log_request — authorization header stripped
# ---------------------------------------------------------------------------
class TestLogRequestAuthorizationStripped(unittest.TestCase):
def test_lowercase_authorization_excluded(self) -> None:
addon = _addon()
flow = _Flow(request=_Request(headers={"authorization": "Bearer sk-real-secret"}))
entry = _log_request(addon, flow)
self.assertNotIn("authorization", entry["headers"])
def test_titlecase_authorization_excluded(self) -> None:
addon = _addon()
flow = _Flow(request=_Request(headers={"Authorization": "Bearer sk-real-secret"}))
entry = _log_request(addon, flow)
self.assertNotIn("Authorization", entry["headers"])
self.assertNotIn("authorization", entry["headers"])
def test_non_auth_headers_retained(self) -> None:
addon = _addon()
flow = _Flow(request=_Request(headers={
"authorization": "Bearer sk-real-secret",
"content-type": "application/json",
}))
entry = _log_request(addon, flow)
self.assertIn("content-type", entry["headers"])
self.assertEqual("application/json", entry["headers"]["content-type"])
def test_no_authorization_header_logs_all_others(self) -> None:
addon = _addon()
flow = _Flow(request=_Request(headers={"x-request-id": "abc"}))
entry = _log_request(addon, flow)
self.assertEqual({"x-request-id": "abc"}, entry["headers"])
# ---------------------------------------------------------------------------
# _log_request — body redaction
# ---------------------------------------------------------------------------
_OPENAI_KEY = "sk-" + "A" * 48
class TestLogRequestBodyRedacted(unittest.TestCase):
def test_token_pattern_in_body_scrubbed(self) -> None:
addon = _addon()
flow = _Flow(request=_Request(body=f"key={_OPENAI_KEY}"))
entry = _log_request(addon, flow)
self.assertNotIn(_OPENAI_KEY, entry["body"])
self.assertIn("********", entry["body"])
def test_provisioned_secret_in_body_scrubbed(self) -> None:
addon = _addon()
secret = "provisioned-egress-secret-xyz"
flow = _Flow(request=_Request(body=f"token={secret}"))
with patch.dict("os.environ", {"EGRESS_TOKEN_0": secret}):
entry = _log_request(addon, flow)
self.assertNotIn(secret, entry["body"])
self.assertIn("********", entry["body"])
def test_clean_body_preserved(self) -> None:
addon = _addon()
payload = '{"model": "claude-3", "max_tokens": 1024}'
flow = _Flow(request=_Request(body=payload))
entry = _log_request(addon, flow)
self.assertEqual(payload, entry["body"])
# ---------------------------------------------------------------------------
# _log_request — non-authorization header value redaction
# ---------------------------------------------------------------------------
class TestLogRequestHeaderValuesRedacted(unittest.TestCase):
def test_token_in_custom_header_scrubbed(self) -> None:
addon = _addon()
flow = _Flow(request=_Request(headers={"x-api-key": _OPENAI_KEY}))
entry = _log_request(addon, flow)
self.assertNotIn(_OPENAI_KEY, entry["headers"].get("x-api-key", ""))
self.assertIn("********", entry["headers"].get("x-api-key", ""))
def test_clean_header_value_preserved(self) -> None:
addon = _addon()
flow = _Flow(request=_Request(headers={"accept": "application/json"}))
entry = _log_request(addon, flow)
self.assertEqual("application/json", entry["headers"]["accept"])
# ---------------------------------------------------------------------------
# _log_response — body redaction
# ---------------------------------------------------------------------------
class TestLogResponseBodyRedacted(unittest.TestCase):
def test_token_pattern_in_response_body_scrubbed(self) -> None:
addon = _addon()
flow = _Flow(
request=_Request(),
response=_Response(body=f'{{"key": "{_OPENAI_KEY}"}}'),
)
entry = _log_response(addon, flow)
self.assertNotIn(_OPENAI_KEY, entry["body"])
self.assertIn("********", entry["body"])
def test_provisioned_secret_in_response_body_scrubbed(self) -> None:
addon = _addon()
secret = "provisioned-egress-secret-xyz"
flow = _Flow(
request=_Request(),
response=_Response(body=f'{{"token": "{secret}"}}'),
)
with patch.dict("os.environ", {"EGRESS_TOKEN_0": secret}):
entry = _log_response(addon, flow)
self.assertNotIn(secret, entry["body"])
self.assertIn("********", entry["body"])
def test_clean_response_body_preserved(self) -> None:
addon = _addon()
flow = _Flow(request=_Request(), response=_Response(body='{"result": "ok"}'))
entry = _log_response(addon, flow)
self.assertEqual('{"result": "ok"}', entry["body"])
# ---------------------------------------------------------------------------
# _log_response — response header value redaction
# ---------------------------------------------------------------------------
class TestLogResponseHeaderValuesRedacted(unittest.TestCase):
def test_token_in_response_header_scrubbed(self) -> None:
addon = _addon()
flow = _Flow(
request=_Request(),
response=_Response(headers={"set-cookie": f"token={_OPENAI_KEY}"}),
)
entry = _log_response(addon, flow)
cookie_val = entry["headers"].get("set-cookie", "")
self.assertNotIn(_OPENAI_KEY, cookie_val)
self.assertIn("********", cookie_val)
def test_clean_response_header_preserved(self) -> None:
addon = _addon()
flow = _Flow(
request=_Request(),
response=_Response(headers={"content-type": "application/json"}),
)
entry = _log_response(addon, flow)
self.assertEqual("application/json", entry["headers"]["content-type"])
if __name__ == "__main__":
unittest.main()
-9
View File
@@ -54,15 +54,6 @@ class TestValidateRoutesContent(unittest.TestCase):
' auth_scheme: "Bearer"\n'
)
def test_rejects_log_full(self):
with self.assertRaises(EgressApplyError) as cm:
applicator.validate_routes_content(
'log: 2\n'
'routes:\n'
' - host: "x.example"\n'
)
self.assertIn("must not change egress logging", str(cm.exception))
class TestApplyRoutesChange(unittest.TestCase):
def setUp(self):
-65
View File
@@ -4,7 +4,6 @@ import os
import tempfile
import unittest
from pathlib import Path
from unittest.mock import patch
from bot_bottle.git_gate import (
GitGate,
@@ -14,8 +13,6 @@ from bot_bottle.git_gate import (
git_gate_render_access_hook,
git_gate_render_entrypoint,
git_gate_render_hook,
revoke_git_gate_provisioned_keys,
_resolve_identity_file,
git_gate_upstreams_for_bottle,
)
from bot_bottle.manifest import ManifestIndex
@@ -331,68 +328,6 @@ class TestPrepare(unittest.TestCase):
self.assertIn("exec git daemon", content)
class TestDynamicKeyProvisioning(unittest.TestCase):
def setUp(self):
self.stage = Path(tempfile.mkdtemp())
def tearDown(self):
import shutil
shutil.rmtree(self.stage, ignore_errors=True)
def _gitea_manifest(self):
return ManifestIndex.from_json_obj({
"bottles": {
"dev": {
"git-gate": {
"repos": {
"repo": {
"url": "ssh://git@gitea.example.com/org/repo.git",
"key": {
"provider": "gitea",
"forge_token_env": "GITEA_TOKEN",
},
"host_key": "ssh-ed25519 AAAA...",
},
},
}
}
},
"agents": {"demo": {"skills": [], "prompt": "", "bottle": "dev"}},
})
def test_resolve_identity_file_static_uses_entry_path(self):
entry = fixture_with_git().bottles["dev"].git[0]
self.assertEqual(entry.IdentityFile, _resolve_identity_file(entry, "demo", self.stage))
def test_resolve_identity_file_gitea_provisions_key(self):
entry = self._gitea_manifest().bottles["dev"].git[0]
with patch("bot_bottle.git_gate._provision_dynamic_key", return_value="/tmp/provisioned-key") as mock_provision:
self.assertEqual("/tmp/provisioned-key", _resolve_identity_file(entry, "demo", self.stage))
mock_provision.assert_called_once()
def test_revoke_skips_non_gitea_and_missing_id_file(self):
revoke_git_gate_provisioned_keys(fixture_with_git().bottles["dev"], self.stage)
def test_revoke_calls_delete_for_gitea_entry(self):
bottle = self._gitea_manifest().bottles["dev"]
(self.stage / "repo-deploy-key-id").write_text("123\n")
with patch.dict("os.environ", {"GITEA_TOKEN": "token"}), patch(
"bot_bottle.deploy_key_provisioner.get_provisioner"
) as mock_get_provisioner:
provisioner = mock_get_provisioner.return_value
revoke_git_gate_provisioned_keys(bottle, self.stage)
mock_get_provisioner.assert_called_once()
provisioner.delete.assert_called_once_with("org/repo", "123")
def test_revoke_missing_token_raises(self):
bottle = self._gitea_manifest().bottles["dev"]
(self.stage / "repo-deploy-key-id").write_text("123\n")
with patch.dict("os.environ", {}, clear=True), self.assertRaises(RuntimeError) as cm:
revoke_git_gate_provisioned_keys(bottle, self.stage)
self.assertIn("env var is not set", str(cm.exception))
class TestShellEscaping(unittest.TestCase):
"""Regression tests: all three render functions must produce syntactically
valid sh code even when names and upstream URLs contain shell-special
-107
View File
@@ -9,7 +9,6 @@ import urllib.request
from pathlib import Path
from unittest import mock
from bot_bottle.git_gate import GIT_GATE_TIMEOUT_SECS
from bot_bottle.git_http_backend import GitHttpHandler, MAX_BODY_BYTES
@@ -151,61 +150,6 @@ class TestGitHttpBackend(unittest.TestCase):
)
self.assertEqual("git/test", env["HTTP_USER_AGENT"])
def test_subprocess_calls_include_timeout(self):
"""Both subprocess.run calls (access-hook and git http-backend) must
pass timeout= so a hung upstream cannot wedge the sidecar."""
from http.server import ThreadingHTTPServer
with tempfile.TemporaryDirectory() as tmp:
root = Path(tmp)
(root / "repo.git").mkdir()
old_root = os.environ.get("GIT_PROJECT_ROOT")
os.environ["GIT_PROJECT_ROOT"] = str(root)
self.addCleanup(self._restore_env, old_root)
old_hook = os.environ.get("GIT_GATE_ACCESS_HOOK")
hook = root / "access-hook"
hook.write_text("#!/bin/sh\nexit 0\n")
hook.chmod(0o700)
os.environ["GIT_GATE_ACCESS_HOOK"] = str(hook)
self.addCleanup(self._restore_hook, old_hook)
server = ThreadingHTTPServer(("127.0.0.1", 0), GitHttpHandler)
thread = threading.Thread(target=server.serve_forever, daemon=True)
thread.start()
self.addCleanup(server.shutdown)
self.addCleanup(server.server_close)
backend_response = (
b"Status: 200 OK\r\n"
b"Content-Type: application/x-git-upload-pack-result\r\n"
b"\r\n"
b"0000"
)
calls = [
subprocess.CompletedProcess(["hook"], 0, b"", b""),
subprocess.CompletedProcess(["git"], 0, backend_response, b""),
]
with mock.patch(
"bot_bottle.git_http_backend.subprocess.run",
side_effect=calls,
) as run:
req = urllib.request.Request(
f"http://127.0.0.1:{server.server_port}"
"/repo.git/git-upload-pack",
data=b"",
method="POST",
)
with urllib.request.urlopen(req, timeout=5):
pass
for call in run.call_args_list:
self.assertEqual(
GIT_GATE_TIMEOUT_SECS,
call.kwargs.get("timeout"),
f"subprocess.run call missing timeout: {call}",
)
def test_access_hook_denial_is_logged_to_stdout(self):
"""When the access-hook exits non-zero we still return 403 to the
client, but the hook's stderr must also appear on the handler's
@@ -312,57 +256,6 @@ class TestGitHttpBackend(unittest.TestCase):
os.environ["GIT_GATE_ACCESS_HOOK"] = value
class TestMalformedStatusHeader(unittest.TestCase):
"""Malformed CGI Status: headers must not propagate as unhandled exceptions;
the handler should fall back to HTTP 500."""
def setUp(self):
from http.server import ThreadingHTTPServer
import tempfile
self._tmp = tempfile.mkdtemp()
os.environ["GIT_PROJECT_ROOT"] = self._tmp
self._server = ThreadingHTTPServer(("127.0.0.1", 0), GitHttpHandler)
self._thread = threading.Thread(
target=self._server.serve_forever, daemon=True,
)
self._thread.start()
self._port = self._server.server_port
def tearDown(self):
self._server.shutdown()
self._server.server_close()
os.environ.pop("GIT_PROJECT_ROOT", None)
import shutil
shutil.rmtree(self._tmp, ignore_errors=True)
def _get_with_backend_response(self, cgi_response: bytes) -> int:
with mock.patch(
"bot_bottle.git_http_backend.subprocess.run",
return_value=mock.Mock(returncode=0, stdout=cgi_response),
):
req = urllib.request.Request(
f"http://127.0.0.1:{self._port}/repo.git/info/refs",
method="GET",
)
try:
with urllib.request.urlopen(req, timeout=3) as resp:
return resp.status
except urllib.error.HTTPError as e: # type: ignore
return e.code
def test_empty_status_value_returns_500(self):
status = self._get_with_backend_response(
b"Status: \r\nContent-Type: text/plain\r\n\r\n"
)
self.assertEqual(500, status)
def test_non_numeric_status_returns_500(self):
status = self._get_with_backend_response(
b"Status: bad\r\nContent-Type: text/plain\r\n\r\n"
)
self.assertEqual(500, status)
class TestContentLengthBounds(unittest.TestCase):
"""PRD 0041: malformed or oversized Content-Length is rejected before
git http-backend is invoked."""
+34
View File
@@ -0,0 +1,34 @@
"""Unit: install.sh static contract checks."""
from __future__ import annotations
import subprocess
import unittest
from pathlib import Path
ROOT = Path(__file__).resolve().parents[2]
class TestInstallScript(unittest.TestCase):
def test_shell_syntax(self):
result = subprocess.run(
["sh", "-n", str(ROOT / "install.sh")],
check=False,
capture_output=True,
text=True,
)
self.assertEqual("", result.stderr)
self.assertEqual(0, result.returncode)
def test_contract_phrases(self):
script = (ROOT / "install.sh").read_text(encoding="utf-8")
self.assertIn("python3", script)
self.assertIn("docker info", script)
self.assertIn("pipx install --force", script)
self.assertIn("pip install --user --upgrade", script)
self.assertIn('"${BOT_BOTTLE_BIN}" doctor', script)
if __name__ == "__main__":
unittest.main()
-127
View File
@@ -1,127 +0,0 @@
"""Unit: leveled + structured logging wrappers (issue #252).
Locks three properties of bot_bottle.log:
- backward compatibility default output is byte-identical to the
original bare wrappers, so the 100+ existing single-string call
sites are unaffected;
- context rendering an optional mapping becomes a parseable
` [k=v ...]` suffix;
- level gating BOT_BOTTLE_LOG_LEVEL filters by severity, debug is
silent by default, and error always surfaces.
"""
from __future__ import annotations
import contextlib
import io
import unittest
from typing import Callable
from unittest import mock
from bot_bottle import log
def _capture(
fn: Callable[..., None],
*args: object,
env: dict[str, str] | None = None,
**kwargs: object,
) -> str:
buf = io.StringIO()
patched = mock.patch.dict("os.environ", env or {}, clear=False)
with patched, contextlib.redirect_stderr(buf):
fn(*args, **kwargs)
return buf.getvalue()
class TestBackwardCompat(unittest.TestCase):
"""No context + default level → exactly the legacy lines."""
def test_info(self):
self.assertEqual("bot-bottle: hello\n", _capture(log.info, "hello"))
def test_warn(self):
self.assertEqual(
"bot-bottle: warning: careful\n", _capture(log.warn, "careful")
)
def test_error(self):
self.assertEqual(
"bot-bottle: error: boom\n", _capture(log.error, "boom")
)
class TestContext(unittest.TestCase):
def test_appends_sorted_parseable_suffix(self):
out = _capture(
log.error, "rpc failed", context={"slug": "abc123", "code": "-32603"}
)
# keys sorted: code before slug
self.assertEqual(
"bot-bottle: error: rpc failed [code=-32603 slug=abc123]\n", out
)
def test_quotes_values_with_whitespace(self):
out = _capture(
log.info, "did thing", context={"path": "/a b/c", "ok": "yes"}
)
self.assertEqual(
'bot-bottle: did thing [ok=yes path="/a b/c"]\n', out
)
def test_empty_context_is_noop_suffix(self):
self.assertEqual(
"bot-bottle: x\n", _capture(log.info, "x", context={})
)
class TestLevels(unittest.TestCase):
def test_debug_silent_by_default(self):
self.assertEqual("", _capture(log.debug, "trace"))
def test_debug_emits_when_level_lowered(self):
out = _capture(log.debug, "trace", env={"BOT_BOTTLE_LOG_LEVEL": "debug"})
self.assertEqual("bot-bottle: debug: trace\n", out)
def test_error_level_suppresses_info_and_warn(self):
env = {"BOT_BOTTLE_LOG_LEVEL": "error"}
self.assertEqual("", _capture(log.info, "i", env=env))
self.assertEqual("", _capture(log.warn, "w", env=env))
# error still surfaces — nothing sits above it
self.assertEqual(
"bot-bottle: error: e\n", _capture(log.error, "e", env=env)
)
def test_unknown_level_falls_back_to_default(self):
# garbage value → default INFO threshold, so info still prints
out = _capture(log.info, "i", env={"BOT_BOTTLE_LOG_LEVEL": "loud"})
self.assertEqual("bot-bottle: i\n", out)
def test_warning_alias_accepted(self):
env = {"BOT_BOTTLE_LOG_LEVEL": "warning"}
self.assertEqual("", _capture(log.info, "i", env=env))
self.assertEqual(
"bot-bottle: warning: w\n", _capture(log.warn, "w", env=env)
)
class TestDie(unittest.TestCase):
def test_die_still_raises_and_prints_error(self):
buf = io.StringIO()
with contextlib.redirect_stderr(buf):
with self.assertRaises(log.Die) as cm:
log.die("fatal thing")
self.assertEqual("fatal thing", cm.exception.message)
self.assertIn("bot-bottle: error: fatal thing", buf.getvalue())
def test_die_surfaces_even_at_error_level(self):
buf = io.StringIO()
with mock.patch.dict("os.environ", {"BOT_BOTTLE_LOG_LEVEL": "error"}):
with contextlib.redirect_stderr(buf):
with self.assertRaises(log.Die):
log.die("still fatal")
self.assertIn("bot-bottle: error: still fatal", buf.getvalue())
if __name__ == "__main__":
unittest.main()
+1 -24
View File
@@ -30,7 +30,6 @@ def _plan(
supervise: bool = False,
agent_git_gate_url: str = "",
agent_supervise_url: str = "",
canary: bool = False,
) -> MacosContainerBottlePlan:
routes_path = stage_dir / "routes.yaml"
routes_path.write_text("routes: []\n", encoding="utf-8")
@@ -43,8 +42,6 @@ def _plan(
routes_path=routes_path,
routes=("route",),
token_env_map={"EGRESS_TOKEN_0": "HOST_TOKEN"},
canary="fake-canary-value" if canary else "",
canary_env="CANON_ALPHA_SECRET" if canary else "",
)
if git:
key_path = stage_dir / "origin-key"
@@ -141,26 +138,6 @@ class TestMacosContainerLaunchArgv(unittest.TestCase):
argv,
)
def test_sidecar_argv_registers_canary_env_as_sensitive(self):
plan = _plan(stage_dir=self.stage_dir, canary=True)
argv = launch._sidecar_run_argv(
plan,
"bot-bottle-sidecars-dev-abc",
"bot-bottle-net-dev-abc",
"bot-bottle-egress-dev-abc",
)
self.assertIn("CANON_ALPHA_SECRET=fake-canary-value", argv)
self.assertIn("BOT_BOTTLE_SENSITIVE_PREFIXES=CANON_ALPHA_SECRET", argv)
def test_agent_argv_receives_canary_env(self):
plan = _plan(stage_dir=self.stage_dir, canary=True)
argv = launch._agent_run_argv(
plan,
"bot-bottle-net-dev-abc",
"192.0.2.10",
)
self.assertIn("CANON_ALPHA_SECRET=fake-canary-value", argv)
def test_agent_env_points_proxy_at_sidecar_ip(self):
plan = _plan(
stage_dir=self.stage_dir,
@@ -294,7 +271,7 @@ def _build_plan(stage_dir: Path) -> MacosContainerBottlePlan:
manifest=_MANIFEST,
stage_dir=stage_dir,
git_gate_plan=cast(GitGatePlan, SimpleNamespace(upstreams=())),
egress_plan=cast(EgressPlan, SimpleNamespace(canary="")),
egress_plan=cast(EgressPlan, SimpleNamespace()),
supervise_plan=None,
agent_provision=AgentProvisionPlan(
template="claude",
-27
View File
@@ -73,33 +73,6 @@ resolver #2
)
self.assertTrue(run.call_args_list[-1].kwargs["check"])
def test_build_image_anchors_relative_dockerfile_to_context(self):
status = util.subprocess.CompletedProcess(
args=[],
returncode=0,
stdout=(
'[{"status":{"state":"running"},'
'"configuration":{"dns":{"nameservers":["9.9.9.9"]}}}]'
),
stderr="",
)
with patch.object(util.subprocess, "run", return_value=status) as run, \
patch.object(util.os, "environ", {
"BOT_BOTTLE_MACOS_CONTAINER_DNS": "9.9.9.9",
}):
util.build_image(
"bot-bottle-sidecars:latest",
"/repo",
dockerfile="Dockerfile.sidecars",
)
self.assertEqual(
[
"container", "build", "-t", "bot-bottle-sidecars:latest",
"--dns", "9.9.9.9", "-f", "/repo/Dockerfile.sidecars", "/repo",
],
run.call_args_list[-1].args[0],
)
def test_commit_container_execs_tar_and_builds_image(self):
# stderr is bytes because subprocess.run uses stderr=PIPE without text=True
completed = util.subprocess.CompletedProcess(
-200
View File
@@ -1,200 +0,0 @@
"""Unit: runtime bottle composition (issue #269).
Tests for merge_bottles_runtime and ManifestIndex.load_for_agent with
the new bottle_names parameter.
"""
from __future__ import annotations
import os
import shutil
import tempfile
import textwrap
import unittest
from pathlib import Path
from bot_bottle.manifest import ManifestBottle, ManifestError, ManifestIndex
from bot_bottle.manifest_extends import merge_bottles_runtime
def _index(bottles: dict[str, object], agents: dict[str, object]) -> ManifestIndex:
return ManifestIndex.from_json_obj({"bottles": bottles, "agents": agents})
def _bottle(**kwargs: object) -> ManifestBottle:
return ManifestBottle.from_dict("test", kwargs)
class TestMergeBottlesRuntime(unittest.TestCase):
def test_single_bottle_returns_as_is(self):
b = _bottle(env={"FOO": "1"})
result = merge_bottles_runtime([b])
self.assertEqual({"FOO": "1"}, dict(result.env))
def test_env_later_wins(self):
base = _bottle(env={"FOO": "base", "ONLY_BASE": "x"})
override = _bottle(env={"FOO": "override", "ONLY_OVERRIDE": "y"})
result = merge_bottles_runtime([base, override])
self.assertEqual("override", result.env["FOO"])
self.assertEqual("x", result.env["ONLY_BASE"])
self.assertEqual("y", result.env["ONLY_OVERRIDE"])
def test_egress_routes_concatenated(self):
from bot_bottle.manifest_egress import ManifestEgressConfig, ManifestEgressRoute
r1 = ManifestEgressRoute(Host="api.a.com")
r2 = ManifestEgressRoute(Host="api.b.com")
base = ManifestBottle(egress=ManifestEgressConfig(routes=(r1,)))
override = ManifestBottle(egress=ManifestEgressConfig(routes=(r2,)))
result = merge_bottles_runtime([base, override])
hosts = [r.Host for r in result.egress.routes]
self.assertIn("api.a.com", hosts)
self.assertIn("api.b.com", hosts)
def test_supervise_later_wins(self):
base = _bottle(supervise=True)
override = _bottle(supervise=False)
result = merge_bottles_runtime([base, override])
self.assertFalse(result.supervise)
def test_three_bottles_merged_left_to_right(self):
b1 = _bottle(env={"A": "1", "B": "1", "C": "1"})
b2 = _bottle(env={"B": "2", "C": "2"})
b3 = _bottle(env={"C": "3"})
result = merge_bottles_runtime([b1, b2, b3])
self.assertEqual("1", result.env["A"])
self.assertEqual("2", result.env["B"])
self.assertEqual("3", result.env["C"])
def test_empty_list_raises(self):
with self.assertRaises(ValueError):
merge_bottles_runtime([])
class TestLoadForAgentWithBottleNames(unittest.TestCase):
def test_bottle_names_override_agent_bottle(self):
idx = _index(
bottles={
"base": {"env": {"X": "base"}},
"override": {"env": {"X": "override"}},
},
agents={"impl": {"bottle": "base", "skills": [], "prompt": ""}},
)
m = idx.load_for_agent("impl", ("override",))
self.assertEqual("override", m.bottle.env["X"])
def test_bottle_names_merged_in_order(self):
idx = _index(
bottles={
"a": {"env": {"X": "a", "A": "only-a"}},
"b": {"env": {"X": "b", "B": "only-b"}},
},
agents={"impl": {"bottle": "a", "skills": [], "prompt": ""}},
)
m = idx.load_for_agent("impl", ("a", "b"))
self.assertEqual("b", m.bottle.env["X"])
self.assertEqual("only-a", m.bottle.env["A"])
self.assertEqual("only-b", m.bottle.env["B"])
def test_empty_bottle_names_uses_agent_bottle(self):
idx = _index(
bottles={"base": {"env": {"X": "base"}}},
agents={"impl": {"bottle": "base", "skills": [], "prompt": ""}},
)
m = idx.load_for_agent("impl", ())
self.assertEqual("base", m.bottle.env["X"])
def test_no_bottle_and_no_bottle_names_raises(self):
idx = _index(
bottles={"base": {}},
agents={"impl": {"skills": [], "prompt": ""}},
)
with self.assertRaises(ManifestError) as ctx:
idx.load_for_agent("impl", ())
self.assertIn("no 'bottle' field", str(ctx.exception))
def test_unknown_bottle_name_raises(self):
idx = _index(
bottles={"base": {}},
agents={"impl": {"bottle": "base", "skills": [], "prompt": ""}},
)
with self.assertRaises(ManifestError) as ctx:
idx.load_for_agent("impl", ("nonexistent",))
self.assertIn("nonexistent", str(ctx.exception))
def test_agent_without_bottle_works_with_bottle_names(self):
idx = _index(
bottles={"base": {"env": {"X": "base"}}},
agents={"impl": {"skills": [], "prompt": ""}},
)
m = idx.load_for_agent("impl", ("base",))
self.assertEqual("base", m.bottle.env["X"])
class TestAllBottleNames(unittest.TestCase):
def test_eager_mode_returns_bottle_names(self):
idx = _index(
bottles={"alpha": {}, "beta": {}, "gamma": {}},
agents={"impl": {"bottle": "alpha", "skills": [], "prompt": ""}},
)
self.assertEqual(["alpha", "beta", "gamma"], idx.all_bottle_names)
def test_lazy_mode_scans_files(self):
home = Path(tempfile.mkdtemp(prefix="cb-home-"))
orig_home = os.environ.get("HOME")
os.environ["HOME"] = str(home)
try:
bottles_dir = home / ".bot-bottle" / "bottles"
agents_dir = home / ".bot-bottle" / "agents"
bottles_dir.mkdir(parents=True)
agents_dir.mkdir(parents=True)
(bottles_dir / "claude.md").write_text("---\n---\n")
(bottles_dir / "dev.md").write_text("---\n---\n")
(agents_dir / "impl.md").write_text("---\nbottle: claude\n---\n")
idx = ManifestIndex.resolve(str(home))
self.assertEqual(["claude", "dev"], idx.all_bottle_names)
finally:
if orig_home is None:
os.environ.pop("HOME", None)
else:
os.environ["HOME"] = orig_home
shutil.rmtree(home, ignore_errors=True)
class TestAgentOptionalBottleMd(unittest.TestCase):
"""Agent file without bottle: works when bottle_names are provided at launch."""
def setUp(self) -> None:
self.home = Path(tempfile.mkdtemp(prefix="cb-home-"))
self._orig_home = os.environ.get("HOME")
os.environ["HOME"] = str(self.home)
def tearDown(self) -> None:
if self._orig_home is None:
os.environ.pop("HOME", None)
else:
os.environ["HOME"] = self._orig_home
shutil.rmtree(self.home, ignore_errors=True)
def _write(self, rel: str, text: str) -> None:
p = self.home / ".bot-bottle" / rel
p.parent.mkdir(parents=True, exist_ok=True)
p.write_text(textwrap.dedent(text).lstrip("\n"))
def test_agent_without_bottle_resolves_with_bottle_names(self):
self._write("bottles/dev.md", "---\nenv:\n X: dev\n---\n")
self._write("agents/impl.md", "---\n---\nimpl agent.\n")
idx = ManifestIndex.resolve(str(self.home))
m = idx.load_for_agent("impl", ("dev",))
self.assertEqual("dev", m.bottle.env["X"])
def test_agent_without_bottle_fails_without_bottle_names(self):
self._write("bottles/dev.md", "---\n---\n")
self._write("agents/impl.md", "---\n---\nimpl agent.\n")
idx = ManifestIndex.resolve(str(self.home))
with self.assertRaises(ManifestError) as ctx:
idx.load_for_agent("impl", ())
self.assertIn("no 'bottle' field", str(ctx.exception))
if __name__ == "__main__":
unittest.main()
+1 -46
View File
@@ -167,40 +167,13 @@ class TestAgentProviderHostCredentials(unittest.TestCase):
},
})
def test_startup_args_allowed_for_claude(self):
b = _provider_config_bottle({
"template": "claude",
"settings": {"startup_args": ["--model", "opus"]},
})
self.assertEqual(
{"startup_args": ["--model", "opus"]},
b.agent_provider.settings,
)
def test_startup_args_allowed_for_codex(self):
b = _provider_config_bottle({
"template": "codex",
"settings": {"startup_args": ["--model", "gpt-5-codex"]},
})
self.assertEqual(
{"startup_args": ["--model", "gpt-5-codex"]},
b.agent_provider.settings,
)
def test_provider_specific_settings_still_rejected_for_claude(self):
def test_settings_rejected_for_claude(self):
with self.assertRaises(ManifestError):
_provider_config_bottle({
"template": "claude",
"settings": {"models": ["qwen2.5-coder:7b"]},
})
def test_startup_args_must_be_string_array(self):
with self.assertRaises(ManifestError):
_provider_config_bottle({
"template": "codex",
"settings": {"startup_args": ["--model", 42]},
})
def test_settings_models_must_be_non_empty_string_array(self):
with self.assertRaises(ManifestError):
_provider_config_bottle({
@@ -329,24 +302,6 @@ class TestDlp(unittest.TestCase):
"bogus": True,
}}])
def test_outbound_on_match_omitted_is_empty(self):
b = _bottle([{"host": "x.example"}])
self.assertEqual("", b.egress.routes[0].OutboundOnMatch)
def test_outbound_on_match_accepts_policies(self):
for policy in ("block", "redact", "supervise"):
with self.subTest(policy=policy):
b = _bottle([{"host": "x.example", "dlp": {
"outbound_on_match": policy,
}}])
self.assertEqual(policy, b.egress.routes[0].OutboundOnMatch)
def test_outbound_on_match_rejects_unknown_value(self):
with self.assertRaises(ManifestError):
_bottle([{"host": "x.example", "dlp": {
"outbound_on_match": "allow",
}}])
class TestGitPolicy(unittest.TestCase):
def test_omitted_means_https_git_fetch_disabled(self):
+3 -176
View File
@@ -423,182 +423,9 @@ class TestExtendsErrors(unittest.TestCase):
)
self.assertIn("extends cycle", msg)
def test_non_string_non_list_extends_dies(self):
msg = _error_message(_build, child={"extends": 123})
self.assertIn("extends must be a string or list of strings", msg)
def test_list_entry_non_string_dies(self):
msg = _error_message(_build, child={"extends": [123]})
self.assertIn("extends[0] must be a string", msg)
class TestExtendsMultiParent(unittest.TestCase):
"""extends: [p1, p2, ...] — multi-parent composition (issue #268)."""
_GIT_A = {"url": "ssh://git@host-a/a.git", "key": {"provider": "static", "path": "/k"}}
_GIT_B = {"url": "ssh://git@host-b/b.git", "key": {"provider": "static", "path": "/k"}}
def test_single_element_list_same_as_string(self):
m = _build(
base={"env": {"X": "1"}},
child={"extends": ["base"]},
)
self.assertEqual({"X": "1"}, dict(m.bottles["child"].env))
def test_two_parents_env_union(self):
m = _build(
p1={"env": {"A": "1"}},
p2={"env": {"B": "2"}},
child={"extends": ["p1", "p2"]},
)
self.assertEqual({"A": "1", "B": "2"}, dict(m.bottles["child"].env))
def test_two_parents_env_last_wins_on_collision(self):
m = _build(
p1={"env": {"X": "from-p1"}},
p2={"env": {"X": "from-p2"}},
child={"extends": ["p1", "p2"]},
)
self.assertEqual("from-p2", m.bottles["child"].env["X"])
def test_child_wins_over_all_parents(self):
m = _build(
p1={"env": {"X": "from-p1"}},
p2={"env": {"X": "from-p2"}},
child={"extends": ["p1", "p2"], "env": {"X": "from-child"}},
)
self.assertEqual("from-child", m.bottles["child"].env["X"])
def test_two_parents_supervise_last_wins(self):
m = _build(
p1={"supervise": False},
p2={"supervise": True},
child={"extends": ["p1", "p2"]},
)
self.assertTrue(m.bottles["child"].supervise)
def test_child_supervise_overrides_all_parents(self):
m = _build(
p1={"supervise": True},
p2={"supervise": True},
child={"extends": ["p1", "p2"], "supervise": False},
)
self.assertFalse(m.bottles["child"].supervise)
def test_two_parents_egress_routes_concatenated(self):
m = _build(
p1={"egress": {"routes": [{"host": "a.example.com"}]}},
p2={"egress": {"routes": [{"host": "b.example.com"}]}},
child={"extends": ["p1", "p2"]},
)
hosts = [r.Host for r in m.bottles["child"].egress.routes]
self.assertEqual(["a.example.com", "b.example.com"], hosts)
def test_child_egress_appends_after_combined_parents(self):
m = _build(
p1={"egress": {"routes": [{"host": "a.example.com"}]}},
p2={"egress": {"routes": [{"host": "b.example.com"}]}},
child={
"extends": ["p1", "p2"],
"egress": {"routes": [{"host": "c.example.com"}]},
},
)
hosts = [r.Host for r in m.bottles["child"].egress.routes]
self.assertEqual(["a.example.com", "b.example.com", "c.example.com"], hosts)
def test_two_parents_git_repos_union(self):
m = _build(
p1={"git-gate": {"repos": {"a": self._GIT_A}}},
p2={"git-gate": {"repos": {"b": self._GIT_B}}},
child={"extends": ["p1", "p2"]},
)
names = {e.Name for e in m.bottles["child"].git}
self.assertEqual({"a", "b"}, names)
def test_two_parents_git_same_name_later_wins_per_field(self):
# Both parents declare the same repo name. p2's `key` wins; p1's
# `host_key` is preserved because p2 doesn't override it.
p1_entry = {
"url": "ssh://git@host-a/repo.git",
"host_key": "ecdsa AAAA",
"key": {"provider": "static", "path": "/k1"},
}
p2_entry = {
"url": "ssh://git@host-a/repo.git", # required, same url
"key": {"provider": "gitea", "forge_token_env": "TOK"},
}
m = _build(
p1={"git-gate": {"repos": {"repo": p1_entry}}},
p2={"git-gate": {"repos": {"repo": p2_entry}}},
child={"extends": ["p1", "p2"]},
)
entries = m.bottles["child"].git
self.assertEqual(1, len(entries))
e = entries[0]
self.assertEqual("ssh://git@host-a/repo.git", e.Upstream)
self.assertEqual("ecdsa AAAA", e.KnownHostKey)
self.assertEqual("gitea", e.Key.provider)
def test_p1_repos_preserved_when_p2_has_none(self):
m = _build(
p1={"git-gate": {"repos": {"a": self._GIT_A}}},
p2={"env": {"X": "1"}},
child={"extends": ["p1", "p2"]},
)
names = [e.Name for e in m.bottles["child"].git]
self.assertEqual(["a"], names)
def test_diamond_shared_ancestor_resolved_once(self):
# a <- b, a <- c; child extends [b, c]
# `a` must be resolved once and cached.
m = _build(
a={"env": {"FROM_A": "1"}, "supervise": False},
b={"extends": "a", "env": {"FROM_B": "1"}},
c={"extends": "a", "env": {"FROM_C": "1"}},
child={"extends": ["b", "c"]},
)
child = m.bottles["child"]
self.assertEqual("1", child.env["FROM_A"])
self.assertEqual("1", child.env["FROM_B"])
self.assertEqual("1", child.env["FROM_C"])
# supervise=False from `a` threads through both b and c; c is the
# later parent so its effective supervise (False) wins.
self.assertFalse(child.supervise)
def test_three_parents_env_fold_order(self):
m = _build(
p1={"env": {"X": "1", "A": "a"}},
p2={"env": {"X": "2", "B": "b"}},
p3={"env": {"X": "3", "C": "c"}},
child={"extends": ["p1", "p2", "p3"]},
)
env = dict(m.bottles["child"].env)
self.assertEqual("3", env["X"])
self.assertEqual("a", env["A"])
self.assertEqual("b", env["B"])
self.assertEqual("c", env["C"])
def test_undefined_bottle_in_list_dies(self):
msg = _error_message(
_build,
base={"env": {}},
child={"extends": ["base", "ghost"]},
)
self.assertIn("extends 'ghost'", msg)
self.assertIn("not defined", msg)
def test_self_reference_in_list_dies(self):
msg = _error_message(_build, child={"extends": ["child"]})
self.assertIn("extends itself", msg)
def test_cycle_through_multi_parent_edge_dies(self):
msg = _error_message(
_build,
a={"extends": ["b", "c"]},
b={},
c={"extends": "a"},
)
self.assertIn("extends cycle", msg)
def test_non_string_extends_dies(self):
msg = _error_message(_build, child={"extends": ["base"]})
self.assertIn("extends must be a string", msg)
class TestExtendsAvailableInBottleKeys(unittest.TestCase):
+1 -1
View File
@@ -130,7 +130,7 @@ def _capture_print(plan: DockerBottlePlan | SmolmachinesBottlePlan) -> list[str]
orig = sys.stderr
sys.stderr = buf
try:
plan.print()
plan.print(remote_control=False)
finally:
sys.stderr = orig
return buf.getvalue().splitlines()
-38
View File
@@ -8,7 +8,6 @@ import unittest
from bot_bottle.git_gate import (
GIT_GATE_HOSTNAME,
_gitconfig_validate_value,
git_gate_render_gitconfig,
)
from bot_bottle.manifest import ManifestIndex
@@ -91,42 +90,5 @@ class TestGitGateGitconfigRender(unittest.TestCase):
self.assertNotIn("gitea.dideric.is", out)
class TestGitconfigValidateValue(unittest.TestCase):
"""_gitconfig_validate_value rejects values that would inject gitconfig keys."""
def test_normal_url_passes(self):
_gitconfig_validate_value("url", "ssh://git@github.com/owner/repo.git")
def test_newline_in_url_raises(self):
with self.assertRaises(ValueError):
_gitconfig_validate_value("url", "ssh://git@github.com/owner/\nrepo.git")
def test_carriage_return_in_url_raises(self):
with self.assertRaises(ValueError):
_gitconfig_validate_value("url", "ssh://git@github.com/\rrepo.git")
def test_error_message_names_field(self):
with self.assertRaises(ValueError, msg="error should name the field") as ctx:
_gitconfig_validate_value("repos['bad'].url", "ssh://host/\npath")
self.assertIn("repos['bad'].url", str(ctx.exception))
class TestGitconfigRenderRejectsNewlineInUpstream(unittest.TestCase):
"""git_gate_render_gitconfig raises on Upstream values with newlines."""
def test_newline_in_upstream_raises(self):
m = ManifestIndex.from_json_obj({
"bottles": {"dev": {"git-gate": {"repos": {
"evil": {
"url": "ssh://git@github.com/owner/\nfake-key = injected\nrepo.git",
"key": {"provider": "static", "path": "/dev/null"},
},
}}}},
"agents": {"demo": {"skills": [], "prompt": "", "bottle": "dev"}},
})
with self.assertRaises(ValueError):
git_gate_render_gitconfig(m.bottles["dev"].git, GIT_GATE_HOSTNAME)
if __name__ == "__main__":
unittest.main()
+27
View File
@@ -0,0 +1,27 @@
"""Unit: Python package metadata for install script PRD."""
from __future__ import annotations
import tomllib
import unittest
from pathlib import Path
ROOT = Path(__file__).resolve().parents[2]
class TestPyproject(unittest.TestCase):
def test_console_script_and_no_runtime_dependencies(self):
data = tomllib.loads((ROOT / "pyproject.toml").read_text(encoding="utf-8"))
project = data["project"]
self.assertEqual("bot-bottle", project["name"])
self.assertEqual(">=3.11", project["requires-python"])
self.assertEqual([], project["dependencies"])
self.assertEqual(
"bot_bottle.cli:main",
project["scripts"]["bot-bottle"],
)
if __name__ == "__main__":
unittest.main()
+16 -119
View File
@@ -8,7 +8,6 @@ inspecting running bundle containers' port bindings."""
from __future__ import annotations
import json
import os
import sqlite3
import subprocess
import tempfile
@@ -113,16 +112,9 @@ class TestEnsurePool(unittest.TestCase):
class TestAllocate(unittest.TestCase):
def test_per_bottle_alias_on_linux(self):
# Linux gets the same per-bottle scoping as macOS (127/8 is
# already loopback, so no ifconfig is needed). A fresh host
# with no running bundles allocates the first pool entry.
with tempfile.TemporaryDirectory() as tmp:
lock_path = Path(tmp) / "smolmachines.lock"
with patch.object(loopback_alias, "_is_macos", return_value=False), \
patch.object(loopback_alias, "_ALLOC_LOCK_PATH", lock_path), \
patch.object(loopback_alias, "_aliases_in_use", return_value=set()):
self.assertEqual("127.0.0.16", loopback_alias.allocate("demo"))
def test_returns_loopback_on_linux(self):
with patch.object(loopback_alias, "_is_macos", return_value=False):
self.assertEqual("127.0.0.1", loopback_alias.allocate("demo"))
def test_picks_lowest_unused_on_macos(self):
# No bundles running -> first pool entry.
@@ -174,25 +166,12 @@ class TestAllocateLock(unittest.TestCase):
self.assertIn(fcntl_mod.LOCK_EX, flock_calls)
def test_acquires_exclusive_lock_on_linux(self):
# Linux allocates per-bottle too, so it must take the same
# lock to serialise concurrent launches.
import fcntl as fcntl_mod
flock_calls: list[int] = []
def record_flock(fd, op): # type: ignore
flock_calls.append(op)
with tempfile.TemporaryDirectory() as tmp:
lock_path = Path(tmp) / "smolmachines.lock"
with patch.object(loopback_alias, "_is_macos", return_value=False), \
patch.object(loopback_alias, "_ALLOC_LOCK_PATH", lock_path), \
patch.object(loopback_alias, "_aliases_in_use", return_value=set()), \
patch.object(loopback_alias.fcntl, "flock",
side_effect=record_flock):
loopback_alias.allocate("demo")
self.assertIn(fcntl_mod.LOCK_EX, flock_calls)
def test_no_lock_on_linux(self):
# Linux early-returns before touching the lock file.
with patch.object(loopback_alias, "_is_macos", return_value=False), \
patch.object(loopback_alias.fcntl, "flock") as flock:
loopback_alias.allocate("demo")
flock.assert_not_called()
def test_sequential_allocations_with_shared_lock_are_serialised(self):
# Two sequential calls share the same lock file. The second
@@ -262,12 +241,10 @@ class TestAliasInUseDetection(unittest.TestCase):
class TestForceAllowlist(unittest.TestCase):
"""Smolvm 0.8.0 silently drops `--allow-cidr` with `--from`, so
`force_allowlist` opens the state DB directly and sets the row's
`allowed_cidrs` field on both macOS and Linux. It is
fail-closed: it dies rather than launching a VM whose allowlist
it can't confirm. Round-trip tests against a real SQLite DB to
lock down the BLOB encoding."""
"""Smolvm 0.8.0 silently drops `--allow-cidr` with `--from`,
so `force_allowlist` opens the state DB directly and sets
the row's `allowed_cidrs` field. Round-trip tests against a
real SQLite DB to lock down the BLOB encoding."""
def setUp(self):
self._tmp = tempfile.TemporaryDirectory(prefix="smolvm-db.")
@@ -313,67 +290,17 @@ class TestForceAllowlist(unittest.TestCase):
self.assertEqual(4, cfg["cpus"])
self.assertTrue(cfg["network"])
def test_patches_on_linux_too(self):
# force_allowlist no longer no-ops on Linux — the TSI
# allowlist must be enforced there as well.
def test_noop_on_linux(self):
with patch.object(loopback_alias, "_is_macos", return_value=False), \
patch.object(loopback_alias, "_SMOLVM_DB_PATH", self.db):
loopback_alias.force_allowlist("demo-vm", ["127.0.0.16/32"])
# DB row should be untouched.
con = sqlite3.connect(str(self.db))
cfg = json.loads(con.execute(
"SELECT data FROM vms WHERE name='demo-vm'",
).fetchone()[0])
con.close()
self.assertEqual(["127.0.0.16/32"], cfg["allowed_cidrs"])
def test_skips_write_when_already_matching(self):
# A newer smolvm that honors --allow-cidr at create leaves the
# row already correct; force_allowlist must not rewrite it. We
# detect a no-write by comparing the raw BLOB byte-for-byte
# (a rewrite re-serialises the JSON, changing key order/bytes
# is not guaranteed, but mtime/identity isn't observable — so
# we assert the stored bytes are exactly what we pre-seeded).
seeded = json.dumps({
"name": "demo-vm", "cpus": 4, "mem": 8192,
"network": True, "allowed_cidrs": ["127.0.0.16/32"],
}).encode()
con = sqlite3.connect(str(self.db))
con.execute(
"UPDATE vms SET data=? WHERE name='demo-vm'",
(sqlite3.Binary(seeded),),
)
con.commit()
con.close()
with patch.object(loopback_alias, "_is_macos", return_value=True), \
patch.object(loopback_alias, "_SMOLVM_DB_PATH", self.db):
loopback_alias.force_allowlist("demo-vm", ["127.0.0.16/32"])
con = sqlite3.connect(str(self.db))
stored = con.execute(
"SELECT data FROM vms WHERE name='demo-vm'").fetchone()[0]
con.close()
self.assertEqual(seeded, bytes(stored))
def test_dies_when_patch_does_not_take(self):
# If the persisted allowlist still doesn't match after the
# patch (e.g. wrong schema / smolvm stores it elsewhere),
# force_allowlist must fail closed rather than boot the VM.
original = loopback_alias._read_machine_cfg
def stale_cfg(con, name):
# Always report the un-patched row so the post-write
# verification never sees the requested cidrs.
cfg = original(con, name)
cfg["allowed_cidrs"] = None
return cfg
with patch.object(loopback_alias, "_is_macos", return_value=True), \
patch.object(loopback_alias, "_SMOLVM_DB_PATH", self.db), \
patch.object(loopback_alias, "_read_machine_cfg", side_effect=stale_cfg), \
patch.object(loopback_alias, "die", side_effect=SystemExit("die")):
with self.assertRaises(SystemExit):
loopback_alias.force_allowlist("demo-vm", ["127.0.0.16/32"])
self.assertIsNone(cfg["allowed_cidrs"])
def test_dies_on_missing_db(self):
with patch.object(loopback_alias, "_is_macos", return_value=True), \
@@ -396,35 +323,5 @@ class TestForceAllowlist(unittest.TestCase):
loopback_alias.force_allowlist("not-in-db", ["127.0.0.16/32"])
class TestSmolvmDbPath(unittest.TestCase):
"""The smolvm state-DB path is platform-derived: Application
Support on macOS, XDG data dir on Linux."""
def test_macos_path(self):
with patch.object(loopback_alias.platform, "system", return_value="Darwin"):
p = loopback_alias._smolvm_db_path()
self.assertEqual(
("Library", "Application Support", "smolvm", "server", "smolvm.db"),
p.parts[-5:],
)
def test_linux_default_xdg_path(self):
env = {k: v for k, v in os.environ.items() if k != "XDG_DATA_HOME"}
with patch.object(loopback_alias.platform, "system", return_value="Linux"), \
patch.dict(loopback_alias.os.environ, env, clear=True):
p = loopback_alias._smolvm_db_path()
self.assertEqual(
(".local", "share", "smolvm", "server", "smolvm.db"),
p.parts[-5:],
)
def test_linux_respects_xdg_data_home(self):
with patch.object(loopback_alias.platform, "system", return_value="Linux"), \
patch.dict(loopback_alias.os.environ,
{"XDG_DATA_HOME": "/custom/data"}, clear=False):
p = loopback_alias._smolvm_db_path()
self.assertEqual(Path("/custom/data/smolvm/server/smolvm.db"), p)
if __name__ == "__main__":
unittest.main()
+5 -29
View File
@@ -26,7 +26,9 @@ from bot_bottle.backend.smolmachines.bottle import SmolmachinesBottle
from bot_bottle.backend.smolmachines.bottle_plan import (
SmolmachinesBottlePlan,
)
from bot_bottle.backend.smolmachines import launch as _launch
# from bot_bottle.backend.smolmachines.provision import (
# workspace as _workspace,
# )
from bot_bottle.backend.smolmachines.launch import _bundle_launch_spec
from bot_bottle.backend.util import AGENT_CA_PATH
from bot_bottle.egress import EgressPlan, EgressRoute
@@ -42,6 +44,7 @@ class _Provider(AgentProvider):
return AgentProviderRuntime(
template="test", command="test", image="",
prompt_mode="append_file", bypass_args=(), resume_args=(),
remote_control_args=(),
)
def provision_plan(self, **kwargs): # type: ignore[override]
raise NotImplementedError
@@ -83,7 +86,6 @@ def _plan(
stage_dir: Path | None = None,
egress_routes: tuple[EgressRoute, ...] = (),
egress_ca_path: Path = Path(),
canary: bool = False,
supervise: bool = False,
bundle_ip: str = "192.168.50.2",
agent_git_gate_host: str = "127.0.0.1:55555",
@@ -130,6 +132,7 @@ def _plan(
supervise_plan = SupervisePlan(
slug="demo-abc12",
queue_dir=Path("/tmp/queue"),
current_config_dir=Path("/tmp/current-config"),
)
return SmolmachinesBottlePlan(
spec=spec,
@@ -153,8 +156,6 @@ def _plan(
routes=egress_routes,
token_env_map={},
mitmproxy_ca_cert_only_host_path=egress_ca_path,
canary="fake-canary-value" if canary else "",
canary_env="CANON_ALPHA_SECRET" if canary else "",
),
supervise_plan=supervise_plan,
agent_git_gate_host=agent_git_gate_host,
@@ -410,31 +411,6 @@ class TestBundleLaunchSpec(unittest.TestCase):
self.assertIn(9420, spec.ports_to_publish)
self.assertNotIn(9418, spec.ports_to_publish)
def test_canary_env_registered_as_sensitive_in_bundle(self):
plan = _plan(canary=True)
spec = _bundle_launch_spec(plan, "net", "127.0.0.16")
self.assertIn("CANON_ALPHA_SECRET=fake-canary-value", spec.environment)
self.assertIn(
"BOT_BOTTLE_SENSITIVE_PREFIXES=CANON_ALPHA_SECRET",
spec.environment,
)
def test_canary_env_visible_to_smolvm_guest(self):
plan = _plan(canary=True)
with patch.object(
_launch._bundle,
"bundle_host_port",
return_value="65000",
):
stamped = _launch._discover_urls(plan, "127.0.0.16")
self.assertEqual(
"fake-canary-value",
stamped.guest_env["CANON_ALPHA_SECRET"],
)
class TestProvisionGitUser(unittest.TestCase):
"""`provision_git` runs `git config --global` inside the
-63
View File
@@ -56,14 +56,9 @@ class TestBundleSubnet(unittest.TestCase):
class TestPreflight(unittest.TestCase):
def test_smolvm_present_returns_none(self):
# Pin macOS so the Linux KVM gate doesn't fire on a CI runner
# (ubuntu, no /dev/kvm) — this test isolates the PATH check.
with patch(
"bot_bottle.backend.smolmachines.util.shutil.which",
return_value="/usr/local/bin/smolvm",
), patch(
"bot_bottle.backend.smolmachines.util.platform.system",
return_value="Darwin",
):
self.assertIsNone(smolmachines_preflight())
@@ -93,63 +88,5 @@ class TestPreflight(unittest.TestCase):
self.assertIn("BOT_BOTTLE_BACKEND=docker", msg)
class TestKvmPreflight(unittest.TestCase):
"""Linux-only KVM gate: smolvm needs /dev/kvm present and
accessible. macOS skips this entirely (Hypervisor.framework)."""
def _run(self, *, system, exists, access):
with patch(
"bot_bottle.backend.smolmachines.util.shutil.which",
return_value="/usr/bin/smolvm",
), patch(
"bot_bottle.backend.smolmachines.util.platform.system",
return_value=system,
), patch(
"bot_bottle.backend.smolmachines.util.os.path.exists",
return_value=exists,
), patch(
"bot_bottle.backend.smolmachines.util.os.access",
return_value=access,
):
return smolmachines_preflight()
def test_macos_skips_kvm_check(self):
# Even with /dev/kvm absent, macOS must not run the gate.
self.assertIsNone(self._run(system="Darwin", exists=False, access=False))
def test_linux_ok_returns_none(self):
self.assertIsNone(self._run(system="Linux", exists=True, access=True))
def test_linux_missing_device_dies(self):
with self.assertRaises(SystemExit):
self._run(system="Linux", exists=False, access=False)
def test_linux_no_access_dies(self):
with self.assertRaises(SystemExit):
self._run(system="Linux", exists=True, access=False)
def test_linux_missing_device_message(self):
import io
import sys
captured = io.StringIO()
with patch.object(sys, "stderr", captured):
with self.assertRaises(SystemExit):
self._run(system="Linux", exists=False, access=False)
msg = captured.getvalue()
self.assertIn("/dev/kvm", msg)
self.assertIn("kvm-intel", msg)
def test_linux_no_access_message(self):
import io
import sys
captured = io.StringIO()
with patch.object(sys, "stderr", captured):
with self.assertRaises(SystemExit):
self._run(system="Linux", exists=True, access=False)
msg = captured.getvalue()
self.assertIn("kvm", msg)
self.assertIn("group", msg)
if __name__ == "__main__":
unittest.main()
+20 -26
View File
@@ -16,7 +16,7 @@ from bot_bottle.supervise import (
STATUS_APPROVED,
STATUS_MODIFIED,
STATUS_REJECTED,
TOOL_EGRESS_ALLOW,
TOOL_CAPABILITY_BLOCK,
TOOL_GITLEAKS_ALLOW,
archive_proposal,
audit_log_path,
@@ -37,9 +37,9 @@ FIXED_TS = datetime(2026, 5, 25, 12, 0, 0, tzinfo=timezone.utc)
def _proposal(
tool: str = TOOL_EGRESS_ALLOW,
proposed: str = "routes:\n - host: example.com\n",
justification: str = "need egress",
tool: str = TOOL_CAPABILITY_BLOCK,
proposed: str = "FROM python:3.13\n",
justification: str = "need a capability",
) -> Proposal:
return Proposal.new(
bottle_slug="dev",
@@ -57,7 +57,7 @@ class TestProposalRoundtrip(unittest.TestCase):
self.assertTrue(p.id)
self.assertEqual("2026-05-25T12:00:00+00:00", p.arrival_timestamp)
self.assertEqual("dev", p.bottle_slug)
self.assertEqual(TOOL_EGRESS_ALLOW, p.tool)
self.assertEqual(TOOL_CAPABILITY_BLOCK, p.tool)
def test_to_from_dict_roundtrip(self):
p = _proposal()
@@ -142,14 +142,14 @@ class TestQueueIO(unittest.TestCase):
def test_list_pending_sorted_by_arrival(self):
# Fabricate two with explicit timestamps.
a = Proposal.new(
bottle_slug="dev", tool=TOOL_EGRESS_ALLOW,
proposed_file="routes:\n - host: early.example.com\n", justification="early",
bottle_slug="dev", tool=TOOL_CAPABILITY_BLOCK,
proposed_file="FROM python:3.13\n", justification="early",
current_file_hash="x",
now=datetime(2026, 5, 25, 10, 0, 0, tzinfo=timezone.utc),
)
b = Proposal.new(
bottle_slug="dev", tool=TOOL_EGRESS_ALLOW,
proposed_file="routes:\n - host: late.example.com\n", justification="late",
bottle_slug="dev", tool=TOOL_CAPABILITY_BLOCK,
proposed_file="FROM python:3.13\n", justification="late",
current_file_hash="x",
now=datetime(2026, 5, 25, 14, 0, 0, tzinfo=timezone.utc),
)
@@ -318,29 +318,19 @@ class TestToolConstants(unittest.TestCase):
def test_tools_tuple_matches_individual_constants(self):
self.assertEqual(
(
supervise.TOOL_EGRESS_ALLOW,
supervise.TOOL_ALLOW,
TOOL_CAPABILITY_BLOCK,
supervise.TOOL_EGRESS_BLOCK,
TOOL_GITLEAKS_ALLOW,
supervise.TOOL_EGRESS_TOKEN_ALLOW,
supervise.TOOL_LIST_EGRESS_ROUTES,
),
supervise.TOOLS,
)
def test_token_allow_proposal_roundtrips(self):
p = Proposal.new(
bottle_slug="dev",
tool=supervise.TOOL_EGRESS_TOKEN_ALLOW,
proposed_file="host: api.example.com\n",
justification="false positive",
current_file_hash="h",
)
self.assertEqual(p, Proposal.from_dict(p.to_dict()))
def test_component_map_has_egress_entries(self):
self.assertEqual(
{
supervise.TOOL_EGRESS_ALLOW: "egress",
supervise.TOOL_ALLOW: "egress",
supervise.TOOL_EGRESS_BLOCK: "egress",
},
supervise.COMPONENT_FOR_TOOL,
@@ -377,16 +367,20 @@ class TestSupervisePrepare(unittest.TestCase):
supervise.bot_bottle_root = fake_root # type: ignore[assignment]
return lambda: setattr(supervise, "bot_bottle_root", original)
def test_prepare_creates_queue(self):
def test_prepare_creates_queue_and_current_config(self):
plan = _StubSupervise().prepare("dev", self.stage_dir)
self.assertTrue(plan.queue_dir.is_dir())
self.assertTrue(plan.current_config_dir.is_dir())
self.assertEqual("dev", plan.slug)
self.assertEqual("", plan.internal_network)
def test_prepare_does_not_create_current_config_dir(self):
def test_prepare_writes_no_files_to_current_config(self):
# dockerfile_content is no longer accepted by prepare.
# routes.yaml + allowlist live behind the
# `list-egress-routes` MCP tool (PRD 0017 chunk 3).
plan = _StubSupervise().prepare("dev", self.stage_dir)
self.assertFalse((self.stage_dir / "current-config").exists())
self.assertFalse(hasattr(plan, "current_config_dir"))
files = sorted(p.name for p in plan.current_config_dir.iterdir())
self.assertEqual([], files)
if __name__ == "__main__":
+29 -58
View File
@@ -18,9 +18,8 @@ from bot_bottle.supervise import (
STATUS_APPROVED,
STATUS_MODIFIED,
STATUS_REJECTED,
TOOL_EGRESS_ALLOW,
TOOL_CAPABILITY_BLOCK,
TOOL_GITLEAKS_ALLOW,
TOOL_EGRESS_TOKEN_ALLOW,
read_audit_entries,
read_response,
sha256_hex,
@@ -30,12 +29,12 @@ from bot_bottle.supervise import (
FIXED = datetime(2026, 5, 25, 12, 0, 0, tzinfo=timezone.utc)
def _proposal(slug: str = "dev", tool: str = TOOL_EGRESS_ALLOW) -> Proposal:
def _proposal(slug: str = "dev", tool: str = TOOL_CAPABILITY_BLOCK) -> Proposal:
payloads = {
supervise.TOOL_EGRESS_ALLOW: "routes:\n - host: example.com\n",
TOOL_CAPABILITY_BLOCK: "FROM python:3.13\n",
supervise.TOOL_ALLOW: "routes:\n - host: example.com\n",
supervise.TOOL_EGRESS_BLOCK: "routes:\n - host: example.com\n",
TOOL_GITLEAKS_ALLOW: "file: tests/test_fixture.py\nline: 3\n",
TOOL_EGRESS_TOKEN_ALLOW: "host: api.example.com\ndetector: token\n",
}
payload = payloads.get(tool, "")
return Proposal.new(
@@ -85,14 +84,14 @@ class TestDiscoverPending(_FakeHomeMixin, unittest.TestCase):
def test_sorted_by_arrival_across_bottles(self):
early = Proposal.new(
bottle_slug="api", tool=TOOL_EGRESS_ALLOW,
proposed_file="routes:\n - host: early.example.com\n", justification="early",
bottle_slug="api", tool=TOOL_CAPABILITY_BLOCK,
proposed_file="FROM python:3.13\n", justification="early",
current_file_hash="h",
now=datetime(2026, 5, 25, 10, 0, 0, tzinfo=timezone.utc),
)
late = Proposal.new(
bottle_slug="dev", tool=TOOL_EGRESS_ALLOW,
proposed_file="routes:\n - host: late.example.com\n", justification="late",
bottle_slug="dev", tool=TOOL_CAPABILITY_BLOCK,
proposed_file="FROM python:3.13\n", justification="late",
current_file_hash="h",
now=datetime(2026, 5, 25, 14, 0, 0, tzinfo=timezone.utc),
)
@@ -121,7 +120,7 @@ class TestApproveReject(_FakeHomeMixin, unittest.TestCase):
def tearDown(self):
self._teardown_fake_home()
def _enqueue(self, tool: str = TOOL_EGRESS_ALLOW):
def _enqueue(self, tool: str = TOOL_CAPABILITY_BLOCK):
p = _proposal(tool=tool)
qdir = supervise.queue_dir_for_slug("dev")
qdir.mkdir(parents=True, exist_ok=True)
@@ -130,29 +129,19 @@ class TestApproveReject(_FakeHomeMixin, unittest.TestCase):
def test_approve_writes_response(self):
qp = self._enqueue()
with patch(
"bot_bottle.cli.supervise.apply_routes_change",
return_value=("routes: []\n", "routes:\n - host: example.com\n"),
):
supervise_cli.approve(qp)
resp = read_response(qp.queue_dir, qp.proposal.id)
supervise_cli.approve(qp)
# capability-block is archived on approve, so the response file
# moves to processed/ before the caller can read it.
resp = read_response(qp.queue_dir / "processed", qp.proposal.id)
self.assertEqual(STATUS_APPROVED, resp.status)
self.assertIsNone(resp.final_file)
def test_approve_with_final_file_marks_modified(self):
qp = self._enqueue()
with patch(
"bot_bottle.cli.supervise.apply_routes_change",
return_value=("routes: []\n", "routes:\n - host: edited.example.com\n"),
):
supervise_cli.approve(
qp,
final_file="routes:\n - host: edited.example.com\n",
notes="tweaked",
)
resp = read_response(qp.queue_dir, qp.proposal.id)
supervise_cli.approve(qp, final_file="FROM bookworm\n", notes="tweaked")
resp = read_response(qp.queue_dir / "processed", qp.proposal.id)
self.assertEqual(STATUS_MODIFIED, resp.status)
self.assertEqual("routes:\n - host: edited.example.com\n", resp.final_file)
self.assertEqual("FROM bookworm\n", resp.final_file)
self.assertEqual("tweaked", resp.notes)
def test_reject_writes_rejection(self):
@@ -162,6 +151,11 @@ class TestApproveReject(_FakeHomeMixin, unittest.TestCase):
self.assertEqual(STATUS_REJECTED, resp.status)
self.assertEqual("nope", resp.notes)
def test_no_audit_log_for_capability_block(self):
qp = self._enqueue(tool=TOOL_CAPABILITY_BLOCK)
supervise_cli.approve(qp)
self.assertEqual([], read_audit_entries("egress", "dev"))
def test_approve_egress_block_writes_audit_log(self):
qp = self._enqueue(tool=supervise.TOOL_EGRESS_BLOCK)
with patch(
@@ -202,38 +196,10 @@ class TestApproveReject(_FakeHomeMixin, unittest.TestCase):
resp = read_response(qp.queue_dir, qp.proposal.id)
self.assertEqual("test fixture", resp.notes)
def test_approve_token_allow_leaves_response_for_egress(self):
qp = self._enqueue(tool=TOOL_EGRESS_TOKEN_ALLOW)
supervise_cli.approve(qp, notes="false positive")
# The egress addon polls the queue dir for the response; the TUI must
# not archive it (the addon archives after reading).
resp = read_response(qp.queue_dir, qp.proposal.id)
self.assertEqual(STATUS_APPROVED, resp.status)
self.assertEqual("false positive", resp.notes)
self.assertFalse((qp.queue_dir / "processed").exists())
def test_token_allow_writes_no_audit_log(self):
qp = self._enqueue(tool=TOOL_EGRESS_TOKEN_ALLOW)
supervise_cli.approve(qp, notes="false positive")
self.assertEqual([], read_audit_entries("egress", "dev"))
def test_tui_token_allow_requires_reason(self):
qp = self._enqueue(tool=TOOL_EGRESS_TOKEN_ALLOW)
with patch.object(supervise_cli, "_prompt", return_value=""):
status = supervise_cli._approve_from_tui(None, qp) # type: ignore[arg-type]
self.assertEqual("approve aborted (empty reason)", status)
self.assertFalse((qp.queue_dir / "processed").exists())
def test_tui_token_allow_writes_reason(self):
qp = self._enqueue(tool=TOOL_EGRESS_TOKEN_ALLOW)
with patch.object(supervise_cli, "_prompt", return_value="legit"):
status = supervise_cli._approve_from_tui(None, qp) # type: ignore[arg-type]
self.assertIn("approved egress-token-allow", status)
resp = read_response(qp.queue_dir, qp.proposal.id)
self.assertEqual("legit", resp.notes)
def test_suffix_for_token_allow_is_txt(self):
self.assertEqual(".txt", supervise_cli._suffix_for_tool(TOOL_EGRESS_TOKEN_ALLOW))
# class TestCapabilityApplyWiring(_FakeHomeMixin, unittest.TestCase):
# # DISABLED — capability_apply functionality is currently commented out.
# pass
class TestEditInEditor(unittest.TestCase):
@@ -280,5 +246,10 @@ class TestEditInEditor(unittest.TestCase):
os.environ["EDITOR"] = original_editor
# class TestCapabilityBlockSmolmachinesGuard(_FakeHomeMixin, unittest.TestCase):
# # DISABLED — capability_apply functionality is currently commented out.
# pass
if __name__ == "__main__":
unittest.main()
+26 -180
View File
@@ -20,7 +20,6 @@ import supervise as _sv # noqa: E402 # type: ignore
from bot_bottle import supervise_server # noqa: E402
from bot_bottle.supervise_server import (
ERR_INTERNAL,
ERR_INVALID_PARAMS,
ERR_INVALID_REQUEST,
ERR_METHOD_NOT_FOUND,
@@ -30,9 +29,7 @@ from bot_bottle.supervise_server import (
PROPOSED_FILE_FIELD,
ServerConfig,
TOOL_DEFINITIONS,
_RpcClientError,
_RpcError,
_RpcInternalError,
_response_timeout_from_env,
format_response_text,
handle_initialize,
@@ -50,19 +47,19 @@ from bot_bottle.supervise_server import (
class TestValidation(unittest.TestCase):
def test_capability_block_accepts_anything_nonempty(self):
validate_proposed_file(
_sv.TOOL_CAPABILITY_BLOCK,
"FROM python:3.13\nRUN apk add git\n",
)
def test_empty_proposed_file_rejected_for_tools_with_file_field(self):
with self.assertRaises(_RpcError):
validate_proposed_file(_sv.TOOL_EGRESS_ALLOW, " \n\t")
def test_capability_block_rejected_as_unknown_tool(self):
with self.assertRaises(_RpcError) as cm:
validate_proposed_file("capability-block", "FROM python:3.13\n")
self.assertEqual(ERR_INVALID_PARAMS, cm.exception.code)
self.assertIn("unknown tool", cm.exception.message)
validate_proposed_file(_sv.TOOL_CAPABILITY_BLOCK, " \n\t")
def test_egress_routes_yaml_is_validated(self):
validate_proposed_file(
_sv.TOOL_EGRESS_ALLOW,
_sv.TOOL_ALLOW,
"routes:\n - host: example.com\n",
)
@@ -70,74 +67,6 @@ class TestValidation(unittest.TestCase):
with self.assertRaises(_RpcError):
validate_proposed_file(_sv.TOOL_EGRESS_BLOCK, "routes: nope\n")
def test_egress_routes_yaml_rejects_log_full(self):
with self.assertRaises(_RpcError) as cm:
validate_proposed_file(
_sv.TOOL_EGRESS_ALLOW,
"log: 2\nroutes:\n - host: example.com\n",
)
self.assertEqual(ERR_INVALID_PARAMS, cm.exception.code)
self.assertIn("must not change egress logging", cm.exception.message)
# --- Error taxonomy --------------------------------------------------------
class TestRpcErrorTaxonomy(unittest.TestCase):
def test_rpc_client_error_is_rpc_error(self):
e = _RpcClientError(ERR_INVALID_PARAMS, "bad param")
self.assertIsInstance(e, _RpcError)
self.assertEqual(ERR_INVALID_PARAMS, e.code)
self.assertEqual("bad param", e.message)
def test_rpc_internal_error_is_rpc_error(self):
e = _RpcInternalError("disk full")
self.assertIsInstance(e, _RpcError)
self.assertEqual(ERR_INTERNAL, e.code)
self.assertEqual("disk full", e.message)
def test_rpc_internal_error_preserves_cause(self):
cause = OSError("no space left on device")
try:
raise _RpcInternalError("failed to write") from cause
except _RpcInternalError as e:
self.assertIs(cause, e.__cause__)
def test_parse_error_is_client_error(self):
with self.assertRaises(_RpcClientError):
parse_jsonrpc(b"{bad json")
def test_validation_error_is_client_error(self):
with self.assertRaises(_RpcClientError):
validate_proposed_file(_sv.TOOL_EGRESS_ALLOW, "routes: nope\n")
def test_unknown_tool_in_tools_call_is_client_error(self):
config = ServerConfig(bottle_slug="dev", queue_dir=Path("/unused"))
with self.assertRaises(_RpcClientError) as cm:
handle_tools_call({"name": "no-such-tool", "arguments": {}}, config)
self.assertEqual(ERR_INVALID_PARAMS, cm.exception.code)
class TestRpcInternalErrorOnIoFailure(unittest.TestCase):
def test_write_proposal_os_error_raises_internal(self):
config = ServerConfig(
bottle_slug="dev",
queue_dir=Path("/dev/null/cannot-exist"),
)
with self.assertRaises(_RpcInternalError) as cm:
handle_tools_call(
{
"name": _sv.TOOL_EGRESS_ALLOW,
"arguments": {
"routes_yaml": "routes:\n - host: example.com\n",
"justification": "x",
},
},
config,
)
self.assertEqual(ERR_INTERNAL, cm.exception.code)
self.assertIsNotNone(cm.exception.__cause__)
# --- JSON-RPC parsing ------------------------------------------------------
@@ -218,7 +147,8 @@ class TestHandleToolsList(unittest.TestCase):
names = [t["name"] for t in result["tools"]] # type: ignore[index]
self.assertEqual(
sorted([
_sv.TOOL_EGRESS_ALLOW,
_sv.TOOL_ALLOW,
_sv.TOOL_CAPABILITY_BLOCK,
_sv.TOOL_EGRESS_BLOCK,
_sv.TOOL_LIST_EGRESS_ROUTES,
]),
@@ -251,7 +181,7 @@ class TestHandleToolsList(unittest.TestCase):
self.assertNotIn("required", schema) # type: ignore[operator]
def test_egress_tools_take_routes_yaml_and_justification(self):
for tool_name in (_sv.TOOL_EGRESS_ALLOW, _sv.TOOL_EGRESS_BLOCK):
for tool_name in (_sv.TOOL_ALLOW, _sv.TOOL_EGRESS_BLOCK):
with self.subTest(tool_name=tool_name):
tool = next(t for t in TOOL_DEFINITIONS if t["name"] == tool_name)
schema = tool["inputSchema"]
@@ -294,10 +224,10 @@ class TestHandleToolsCall(unittest.TestCase):
try:
result = handle_tools_call(
{
"name": _sv.TOOL_EGRESS_BLOCK,
"name": _sv.TOOL_CAPABILITY_BLOCK,
"arguments": {
"routes_yaml": "routes:\n - host: example.com\n",
"justification": "need example.com",
"dockerfile": "FROM python:3.13\n",
"justification": "need git",
},
},
self.config,
@@ -314,7 +244,7 @@ class TestHandleToolsCall(unittest.TestCase):
try:
result = handle_tools_call(
{
"name": _sv.TOOL_EGRESS_ALLOW,
"name": _sv.TOOL_ALLOW,
"arguments": {
"routes_yaml": "routes:\n - host: example.com\n",
"justification": "need example.com",
@@ -334,9 +264,9 @@ class TestHandleToolsCall(unittest.TestCase):
try:
result = handle_tools_call(
{
"name": _sv.TOOL_EGRESS_ALLOW,
"name": _sv.TOOL_CAPABILITY_BLOCK,
"arguments": {
"routes_yaml": "routes:\n - host: example.com\n",
"dockerfile": "FROM python:3.13\n",
"justification": "needed for tests",
},
},
@@ -358,52 +288,20 @@ class TestHandleToolsCall(unittest.TestCase):
with self.assertRaises(_RpcError):
handle_tools_call(
{
"name": _sv.TOOL_EGRESS_ALLOW,
"arguments": {"routes_yaml": "routes:\n - host: example.com\n"},
"name": _sv.TOOL_CAPABILITY_BLOCK,
"arguments": {"dockerfile": "FROM python:3.13\n"},
},
self.config,
)
def test_missing_name_raises(self):
with self.assertRaises(_RpcError) as cm:
handle_tools_call({"arguments": {}}, self.config)
self.assertEqual(ERR_INVALID_PARAMS, cm.exception.code)
def test_arguments_must_be_object(self):
with self.assertRaises(_RpcError) as cm:
handle_tools_call(
{
"name": _sv.TOOL_EGRESS_ALLOW,
"arguments": [],
},
self.config,
)
self.assertEqual(ERR_INVALID_PARAMS, cm.exception.code)
self.assertIn("must be an object", cm.exception.message)
def test_capability_block_call_raises_unknown_tool(self):
with self.assertRaises(_RpcError) as cm:
handle_tools_call(
{
"name": "capability-block",
"arguments": {
"dockerfile": "FROM python:3.13\n",
"justification": "need git",
},
},
self.config,
)
self.assertEqual(ERR_INVALID_PARAMS, cm.exception.code)
self.assertIn("unknown tool", cm.exception.message)
def test_archives_proposal_after_response(self):
responder = self._respond_when_proposal_appears(_sv.STATUS_APPROVED)
try:
handle_tools_call(
{
"name": _sv.TOOL_EGRESS_ALLOW,
"name": _sv.TOOL_CAPABILITY_BLOCK,
"arguments": {
"routes_yaml": "routes:\n - host: example.com\n",
"dockerfile": "FROM python:3.13\n",
"justification": "x",
},
},
@@ -425,10 +323,10 @@ class TestHandleToolsCall(unittest.TestCase):
)
result = handle_tools_call(
{
"name": _sv.TOOL_EGRESS_ALLOW,
"name": _sv.TOOL_CAPABILITY_BLOCK,
"arguments": {
"routes_yaml": "routes:\n - host: example.com\n",
"justification": "need egress",
"dockerfile": "FROM python:3.13\n",
"justification": "need a capability",
},
},
config,
@@ -443,31 +341,6 @@ class TestHandleToolsCall(unittest.TestCase):
class TestHandleListEgressRoutes(unittest.TestCase):
def test_success_returns_body_text(self):
class _Resp:
def __enter__(self):
return self
def __exit__(self, exc_type: type[BaseException] | None, exc: BaseException | None, tb: object) -> bool:
return False
def read(self):
return b"[{\"host\": \"example.com\"}]"
class _Opener:
def open(self, *args, **kwargs): # noqa: ANN001, ANN002, ANN003 # type: ignore
return _Resp()
with patch.object(supervise_server.urllib.request, "build_opener", return_value=_Opener()):
result = handle_list_egress_routes(
{},
ServerConfig(bottle_slug="dev", queue_dir=Path("/unused")),
)
self.assertFalse(result["isError"]) # type: ignore[index]
text = result["content"][0]["text"] # type: ignore[index]
self.assertIn("example.com", text)
def test_url_error_returns_tool_error(self):
class _Opener:
def open(self, *args, **kwargs): # noqa: ANN001, ANN002, ANN003 # type: ignore
@@ -527,13 +400,6 @@ class TestFormatResponseText(unittest.TestCase):
self.assertIn("the operator modified", text.lower())
class TestFormatPendingResponseText(unittest.TestCase):
def test_formats_timeout_message(self):
text = supervise_server.format_pending_response_text(12.5)
self.assertIn("status: pending", text)
self.assertIn("12.5s", text)
# --- End-to-end HTTP sanity ------------------------------------------------
@@ -584,8 +450,8 @@ class TestHttpEndToEnd(unittest.TestCase):
self.assertEqual("2.0", result["jsonrpc"])
self.assertEqual(1, result["id"])
names = [t["name"] for t in result["result"]["tools"]] # type: ignore[index]
self.assertNotIn("capability-block", names)
self.assertIn(_sv.TOOL_EGRESS_ALLOW, names)
self.assertIn(_sv.TOOL_CAPABILITY_BLOCK, names)
self.assertIn(_sv.TOOL_ALLOW, names)
self.assertIn(_sv.TOOL_EGRESS_BLOCK, names)
def test_unknown_method_returns_jsonrpc_error(self):
@@ -594,26 +460,6 @@ class TestHttpEndToEnd(unittest.TestCase):
)
self.assertEqual(ERR_METHOD_NOT_FOUND, result["error"]["code"]) # type: ignore[index]
def test_internal_error_returns_err_internal_over_http(self):
with patch.object(
supervise_server._sv, "write_proposal",
side_effect=OSError("disk full"),
):
result = self._post_jsonrpc({
"jsonrpc": "2.0",
"id": 99,
"method": "tools/call",
"params": {
"name": _sv.TOOL_EGRESS_ALLOW,
"arguments": {
"routes_yaml": "routes:\n - host: example.com\n",
"justification": "x",
},
},
})
self.assertIn("error", result)
self.assertEqual(ERR_INTERNAL, result["error"]["code"]) # type: ignore[index]
def test_health_endpoint(self):
conn = http.client.HTTPConnection("127.0.0.1", self.port, timeout=5)
try: