docs(prd): tighten audit ordering and chain guarantees

Per review: bot-bottle has no separate policy artifact — a bottled agent's
egress routes etc. are declared in its manifest (manifest/egress.py), so
manifest_digest already pins the policy in force. Remove the redundant
policy_version. Given a fixed manifest, the only other axis that changes an
outcome is the enforcing code, so add 'engine' (bot-bottle version + git
SHA) as a trusted field. Runtime operator overrides (supervise egress-allow)
are themselves audit events, so effective policy = manifest_digest + logged
deltas, reconstructable from the chain. Note the build must stamp the git
SHA (only version=0.1.0 exists today).

Refs #487

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

.gitea/workflows/canaries.yml

@@ -2,7 +2,7 @@
 # digest, etc.) without coupling every dev push to upstream registry
 # availability.
 #
-# Opt-in via BOT_BOTTLE_RUN_CANARIES=1 so the same files can be run
+# Opt-in via CLAUDE_BOTTLE_RUN_CANARIES=1 so the same files can be run
 # locally with the same gating.
 
 name: canaries
@@ -17,7 +17,7 @@ jobs:
   canaries:
     runs-on: ubuntu-latest
     env:
-      BOT_BOTTLE_RUN_CANARIES: "1"
+      CLAUDE_BOTTLE_RUN_CANARIES: "1"
     steps:
       - name: Checkout
         uses: actions/checkout@v4
@@ -25,7 +25,4 @@ jobs:
       # No actions/setup-python: canaries are stdlib unittest on the image's
       # system Python 3.12 (older act_runner mishandles setup-python's PATH).
       - name: Run canaries
-        run: |
-          python3 -m scripts.unittest_gate \
-            -t . -s tests/canaries -v \
-            --minimum-executed 1 --fail-on-skip
+        run: python3 -m unittest discover -t . -s tests/canaries -v

.gitea/workflows/prd-number-check.yml

@@ -3,7 +3,6 @@ name: prd-number-check
 on:
   pull_request:
     types: [opened, reopened, synchronize]
-    branches: [main]
 
 jobs:
   require-numbered-prds:

.gitea/workflows/pre-release-test.yml

@@ -60,9 +60,6 @@ jobs:
 
   integration-docker:
     runs-on: ubuntu-latest
-    concurrency:
-      group: integration-docker-infra
-      cancel-in-progress: false
     steps:
       - name: Checkout
         uses: actions/checkout@v4
@@ -87,30 +84,7 @@ jobs:
         env:
           BOT_BOTTLE_BACKEND: docker
           COVERAGE_FILE: ${{ github.workspace }}/.coverage.docker
-        run: |
-          set -euo pipefail
-          DOCKER_CLIENT_NETWORK=$(
-            docker inspect "$(hostname)" |
-              python3 -c 'import json,sys; n=json.load(sys.stdin)[0]["NetworkSettings"]["Networks"]; print(next(iter(n)))'
-          )
-          test -n "$DOCKER_CLIENT_NETWORK"
-          RUN_KEY="${GITHUB_RUN_ID:-${GITHUB_RUN_NUMBER:-0}}"
-          export NO_PROXY="*"
-          export no_proxy="*"
-          export BOT_BOTTLE_DOCKER_CLIENT_NETWORK="$DOCKER_CLIENT_NETWORK"
-          export BOT_BOTTLE_DOCKER_ROOT_MOUNT="bot-bottle-ci-root-$RUN_KEY"
-          export BOT_BOTTLE_DOCKER_CA_MOUNT="bot-bottle-ci-ca-$RUN_KEY"
-          python3 -m coverage run -m scripts.unittest_gate \
-            -t . -s tests/integration -v \
-            --minimum-executed 22 --fail-on-skip
-
-      - name: Clean Docker integration volumes
-        if: always()
-        run: |
-          RUN_KEY="${GITHUB_RUN_ID:-${GITHUB_RUN_NUMBER:-0}}"
-          docker volume rm --force \
-            "bot-bottle-ci-root-$RUN_KEY" \
-            "bot-bottle-ci-ca-$RUN_KEY" 2>/dev/null || true
+        run: python3 -m coverage run -m unittest discover -t . -s tests/integration -v
 
       # Non-dot name so upload-artifact's dotfile-skipping glob picks it up.
       - name: Stage docker coverage for upload

.gitea/workflows/test.yml

@@ -12,14 +12,10 @@ on:
       - 'bot_bottle/**'
       - 'tests/**/*.py'
       - 'cli.py'
-      - 'install.sh'
-      - 'setup.py'
-      - 'MANIFEST.in'
-      - 'flake.nix'
-      - 'nix/firecracker-netpool.nix'
       - 'scripts/coverage.sh'
       - 'scripts/critical-modules.txt'
-      - 'scripts/**/*.py'
+      - 'scripts/diff_coverage.py'
+      - 'scripts/tracker_policy.py'
       - 'scripts/firecracker-netpool.sh'
       - 'Dockerfile*'
       - 'pyproject.toml'
@@ -27,20 +23,15 @@ on:
       - '.coveragerc'
       - '.dockerignore'
       - '.gitea/workflows/test.yml'
-      - '.gitea/workflows/pre-release-test.yml'
   pull_request:
     paths:
       - 'bot_bottle/**'
       - 'tests/**/*.py'
       - 'cli.py'
-      - 'install.sh'
-      - 'setup.py'
-      - 'MANIFEST.in'
-      - 'flake.nix'
-      - 'nix/firecracker-netpool.nix'
       - 'scripts/coverage.sh'
       - 'scripts/critical-modules.txt'
-      - 'scripts/**/*.py'
+      - 'scripts/diff_coverage.py'
+      - 'scripts/tracker_policy.py'
       - 'scripts/firecracker-netpool.sh'
       - 'Dockerfile*'
       - 'pyproject.toml'
@@ -48,7 +39,6 @@ on:
       - '.coveragerc'
       - '.dockerignore'
       - '.gitea/workflows/test.yml'
-      - '.gitea/workflows/pre-release-test.yml'
 
 jobs:
   unit:
@@ -81,9 +71,6 @@ jobs:
 
   integration-docker:
     runs-on: ubuntu-latest
-    concurrency:
-      group: integration-docker-infra
-      cancel-in-progress: false
     steps:
       - name: Checkout
         uses: actions/checkout@v4
@@ -100,33 +87,7 @@ jobs:
         env:
           BOT_BOTTLE_BACKEND: docker
           COVERAGE_FILE: ${{ github.workspace }}/.coverage.docker
-        run: |
-          set -euo pipefail
-          # act_runner executes this job in a container while sharing the host
-          # Docker socket. Attach control-plane siblings to the job's network,
-          # and use named volumes for state the host daemon must mount.
-          DOCKER_CLIENT_NETWORK=$(
-            docker inspect "$(hostname)" |
-              python3 -c 'import json,sys; n=json.load(sys.stdin)[0]["NetworkSettings"]["Networks"]; print(next(iter(n)))'
-          )
-          test -n "$DOCKER_CLIENT_NETWORK"
-          RUN_KEY="${GITHUB_RUN_ID:-${GITHUB_RUN_NUMBER:-0}}"
-          export NO_PROXY="*"
-          export no_proxy="*"
-          export BOT_BOTTLE_DOCKER_CLIENT_NETWORK="$DOCKER_CLIENT_NETWORK"
-          export BOT_BOTTLE_DOCKER_ROOT_MOUNT="bot-bottle-ci-root-$RUN_KEY"
-          export BOT_BOTTLE_DOCKER_CA_MOUNT="bot-bottle-ci-ca-$RUN_KEY"
-          python3 -m coverage run -m scripts.unittest_gate \
-            -t . -s tests/integration -v \
-            --minimum-executed 22 --fail-on-skip
-
-      - name: Clean Docker integration volumes
-        if: always()
-        run: |
-          RUN_KEY="${GITHUB_RUN_ID:-${GITHUB_RUN_NUMBER:-0}}"
-          docker volume rm --force \
-            "bot-bottle-ci-root-$RUN_KEY" \
-            "bot-bottle-ci-ca-$RUN_KEY" 2>/dev/null || true
+        run: python3 -m coverage run -m unittest discover -t . -s tests/integration -v
 
       - name: Stage docker coverage for upload
         run: cp .coverage.docker coverage-docker.dat

.gitea/workflows/update-badges.yml

@@ -33,28 +33,19 @@ jobs:
       - name: Run coverage and extract percentage
         id: coverage
         run: |
-          set -euo pipefail
-          # Never publish a badge from a failed or partial test run.
-          python3 -m coverage run -m unittest discover -t . -s tests/unit
-          REPORT=$(python3 -m coverage report)
-          printf '%s\n' "$REPORT"
-          PERCENT=$(printf '%s\n' "$REPORT" | awk '$1 == "TOTAL" {gsub("%", "", $NF); print $NF}')
-          test -n "$PERCENT"
+          python3 -m coverage run -m unittest discover -t . -s tests/unit > /dev/null 2>&1 || true
+          PERCENT=$(python3 -m coverage report 2>/dev/null | grep '^TOTAL' | grep -oP '\d+(?=%)' | tail -1)
           echo "percent=$PERCENT" >> $GITHUB_OUTPUT
           echo "Coverage: $PERCENT%"
 
       - name: Extract core (critical-module) coverage percentage
         id: core_coverage
         run: |
-          set -euo pipefail
           # Reuses the .coverage data from the previous step. The core list is
-          # validated single source of truth. Fail if a listed path disappeared
-          # or if the measured core falls below ADR 0004's 90% minimum.
-          INCLUDE=$(python3 scripts/critical_modules.py)
-          REPORT=$(python3 -m coverage report --include="$INCLUDE" --fail-under=90)
-          printf '%s\n' "$REPORT"
-          PERCENT=$(printf '%s\n' "$REPORT" | awk '$1 == "TOTAL" {gsub("%", "", $NF); print $NF}')
-          test -n "$PERCENT"
+          # the single source of truth in scripts/critical-modules.txt; every
+          # core module is unit-tested, so the unit-only run is accurate for it.
+          INCLUDE=$(grep -vE '^[[:space:]]*(#|$)' scripts/critical-modules.txt | paste -sd, -)
+          PERCENT=$(python3 -m coverage report --include="$INCLUDE" 2>/dev/null | grep '^TOTAL' | grep -oP '\d+(?=%)' | tail -1)
           echo "percent=$PERCENT" >> $GITHUB_OUTPUT
           echo "Core coverage: $PERCENT%"
 

README.md

@@ -5,7 +5,7 @@
 # bot-bottle
 
 [![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)
-[![coverage](https://img.shields.io/badge/coverage-84%25-brightgreen)](https://coverage.readthedocs.io/)
+[![coverage](https://img.shields.io/badge/coverage-83%25-brightgreen)](https://coverage.readthedocs.io/)
 [![core coverage](https://img.shields.io/badge/core%20coverage-94%25-brightgreen)](https://gitea.dideric.is/didericis/bot-bottle/src/branch/main/docs/decisions/0004-coverage-policy.md)
 
 **Problem:** Developer wants to run a coding agent without supervision, but they don't want a prompt injected or misbehaving agent wrecking their environment or exfiltrating sensitive data.
@@ -75,7 +75,7 @@ On compatible macOS hosts, the default backend requires Apple's `container` CLI
 
 Use `BOT_BOTTLE_BACKEND=docker ./cli.py start <agent>` on hosts where neither Apple Container nor KVM is available and Docker is the desired backend.
 
-> **CI (macOS Apple Container):** the advisory `integration-macos` job in `.gitea/workflows/pre-release-test.yml` runs only on manual dispatch. It targets a self-hosted host-mode runner labelled `macos`; Apple Container cannot run inside the Linux pull-request runner. Provision an Apple Silicon host with the `container` CLI running and Python ≥ 3.11 plus `coverage` on the launchd service's explicit `PATH`. The infra container is a singleton (`bot-bottle-mac-infra`), so keep runner concurrency at 1. Its coverage is reported separately and never feeds the required pull-request gate.
+> **CI (macOS Apple Container):** the `integration-macos` job (`.gitea/workflows/test.yml`) runs the integration suite against `BOT_BOTTLE_BACKEND=macos-container` on a self-hosted macOS runner labelled `macos`, because Apple Container needs the host virtualization framework and cannot run in a Linux container (so it can't reuse the `kvm` runner). Provision an Apple Silicon host with the `container` CLI on `PATH` and `container system status` running, then register the runner in **host mode** (not docker mode) with the `macos` label — `brew install gitea-runner` (the `act_runner` rename). Give it a Python ≥ 3.11 with `coverage` importable on the launchd service's `PATH` (a launchd service doesn't inherit your shell profile, so pin `node` and the Python env explicitly). The job is **advisory** — `workflow_dispatch` (manual) only, never triggered by push or PR — since a single laptop that sleeps/roams must not block merges or churn on every push to main; its coverage doesn't feed the gate. The infra container is a singleton (`bot-bottle-mac-infra`), so keep runner concurrency at 1.
 
 ### Containers inside a bottle
 
@@ -174,7 +174,7 @@ BOT_BOTTLE_BACKEND=firecracker ./cli.py start <agent>
 
 > **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. For the network pool, consume the flake module — `imports = [ inputs.bot-bottle.nixosModules.firecracker-netpool ]; services.bot-bottle-firecracker = { enable = true; owner = "you"; };` — then `nixos-rebuild switch` (imperative nft/TAP rules don't survive a rebuild; channel users can `imports = [ <bot-bottle>/nix/firecracker-netpool.nix ]`). `firecracker` isn't in nixpkgs by default as a user binary — install the release binary (pin the version) and put it on `PATH`.
 
-> **CI:** Firecracker integration runs in the manually dispatched `.gitea/workflows/pre-release-test.yml` on a self-hosted runner labelled `kvm`; privileged KVM hosts never execute unreviewed PR code automatically. Provision it like a normal Firecracker host: `firecracker` on `PATH`, `/dev/kvm`, the cached guest kernel and static dropbear, and the persistent TAP/nft pool. The required pull-request workflow runs unit plus the complete Docker integration suite on `ubuntu-latest`; see `docs/ci.md`.
+> **CI:** the coverage gate (`.gitea/workflows/test.yml` → `coverage` job) runs on a self-hosted runner labelled `kvm`, because the Firecracker backend's VM/SSH orchestration is exercised only by the integration suite, which needs `/dev/kvm` + the provisioned pool (a container runner would skip it and read as uncovered). Provision that runner exactly like a normal Firecracker host — `firecracker` on `PATH`, `/dev/kvm`, the cached guest kernel + static dropbear, and the pool installed as the persistent systemd unit — then register it with the `kvm` label. A Docker-capable hosted job builds the candidate once; KVM tests boot those exact bytes, and a successful main run publishes them. The unit/lint jobs still run on `ubuntu-latest`.
 
 ```sh
 ./cli.py start <agent>   # builds the image on first run, drops you into claude

bot_bottle/backend/base.py

@@ -23,14 +23,14 @@ from dataclasses import dataclass
 from pathlib import Path
 from typing import Generator, Generic, Sequence, TypeVar
 
-from ..agent_provider import AgentProvisionPlan, get_provider
+from ..agent_provider import AgentProvisionPlan, get_provider, build_agent_provision_plan
 from ..egress import EgressPlan
 from ..git_gate import GitGatePlan
 from ..log import die, info
 from ..util import expand_tilde
 from ..manifest import Manifest, ManifestIndex
 from ..supervisor.plan import SupervisePlan
-from ..env import ResolvedEnv
+from ..env import resolve_env, ResolvedEnv
 from ..workspace import WorkspacePlan, workspace_plan
 from .print_util import print_multi, visible_agent_env_names
 from .util import host_skill_dir
@@ -296,18 +296,82 @@ class BottleBackend(ABC, Generic[PlanT, CleanupT]):
         backend-specific resolution (names, scratch files, etc.). The
         validation step is enforced here so a future backend cannot
         accidentally skip it. No remote/runtime resources are created."""
-        from .preparation import BottlePreparationPlanner
-        prepared = BottlePreparationPlanner(self).prepare(spec)
+        from .resolve_common import (
+            merge_provision_env_vars,
+            mint_slug,
+            prepare_agent_state_dir,
+            prepare_egress,
+            prepare_git_gate,
+            prepare_supervise,
+            reject_nested_containers,
+            resolve_manifest_dockerfile,
+            write_launch_metadata,
+        )
+
+        manifest = self._validate(spec)
+
+        if not self.supports_nested_containers:
+            reject_nested_containers(self.name, manifest)
+
+        self._preflight()
+
+        from ..git_gate import GitGate
+        manifest = GitGate().preflight_host_keys(
+            manifest,
+            headless=spec.headless,
+            home_md=spec.manifest.home_md,
+        )
+
+        manifest_bottle = manifest.bottle
+        manifest_agent_provider = manifest_bottle.agent_provider
+        agent_provider = get_provider(manifest_agent_provider.template)
+        resolved_env = resolve_env(manifest)
+        workspace = workspace_plan(spec, guest_home=agent_provider.guest_home)
+
+        slug = mint_slug(spec)
+        write_launch_metadata(slug, spec, compose_project="", backend=self.name)
+
+        # Manifest may override the Dockerfile per-bottle; otherwise fall
+        # back to the provider plugin's bundled Dockerfile (next to its
+        # agent_provider.py module).
+        if manifest_agent_provider.dockerfile:
+            agent_dockerfile_path = resolve_manifest_dockerfile(
+                manifest_agent_provider.dockerfile, spec,
+            )
+        else:
+            agent_dockerfile_path = str(agent_provider.dockerfile)
+
+        agent_dir, prompt_file = prepare_agent_state_dir(slug, manifest)
+
+        agent_provision_plan = build_agent_provision_plan(
+            template=manifest_agent_provider.template,
+            dockerfile=agent_dockerfile_path,
+            state_dir=agent_dir,
+            instance_name=f"bot-bottle-{slug}",
+            prompt_file=prompt_file,
+            guest_env=self._build_guest_env(resolved_env),
+            forward_host_credentials=manifest_agent_provider.forward_host_credentials,
+            auth_token=manifest_agent_provider.auth_token,
+            host_env=dict(os.environ),
+            trusted_project_path=workspace.workdir,
+            label=spec.label,
+            color=spec.color,
+            provider_settings=manifest_agent_provider.settings,
+        )
+        agent_provision_plan = merge_provision_env_vars(agent_provision_plan)
+        egress_plan = prepare_egress(manifest_bottle, slug, agent_provision_plan)
+        supervise_plan = prepare_supervise(manifest_bottle, slug)
+        git_gate_plan = prepare_git_gate(manifest_bottle, slug)
 
         return self._resolve_plan(
             spec,
-            manifest=prepared.manifest,
-            slug=prepared.slug,
-            resolved_env=prepared.resolved_env,
-            agent_provision_plan=prepared.agent_provision_plan,
-            egress_plan=prepared.egress_plan,
-            supervise_plan=prepared.supervise_plan,
-            git_gate_plan=prepared.git_gate_plan,
+            manifest=manifest,
+            slug=slug,
+            resolved_env=resolved_env,
+            agent_provision_plan=agent_provision_plan,
+            egress_plan=egress_plan,
+            supervise_plan=supervise_plan,
+            git_gate_plan=git_gate_plan,
             stage_dir=stage_dir,
         )
 

bot_bottle/backend/docker/gateway.py

@@ -17,10 +17,6 @@ from ...gateway import (
   DEFAULT_CA_TIMEOUT_SECONDS, CA_POLL_SECONDS, GATEWAY_CA_CERT, GatewayError
 )
 
-DEFAULT_GATEWAY_SUBNET = "10.242.255.0/24"
-_GATEWAY_SUBNET_LABEL = "bot-bottle.gateway-subnet"
-
-
 class DockerGateway(Gateway):
     """The consolidated gateway as a single, fixed-name Docker container.
 
@@ -39,8 +35,6 @@ class DockerGateway(Gateway):
         build_context: Path | None = None,
         dockerfile: str | None = GATEWAY_DOCKERFILE,
         host_port_bindings: tuple[int, ...] = (),
-        ca_mount_source: str | Path | None = None,
-        subnet: str | None = None,
     ) -> None:
         self.image_ref = image_ref
         self.name = name
@@ -65,15 +59,6 @@ class DockerGateway(Gateway):
         # backend's dev-harness gateway so VMs can reach it via their TAP link;
         # Docker's DNAT + the nft `ct status dnat accept` rule handle the rest.
         self._host_port_bindings = host_port_bindings
-        self._subnet = (
-            subnet
-            or os.environ.get("BOT_BOTTLE_DOCKER_GATEWAY_SUBNET", "").strip()
-            or DEFAULT_GATEWAY_SUBNET
-        )
-        configured_ca = os.environ.get("BOT_BOTTLE_DOCKER_CA_MOUNT", "").strip()
-        self._ca_mount_source = str(
-            ca_mount_source or configured_ca or host_gateway_ca_dir()
-        )
 
     def image_exists(self) -> bool:
         return run_docker(["docker", "image", "inspect", self.image_ref]).returncode == 0
@@ -124,34 +109,10 @@ class DockerGateway(Gateway):
     def _ensure_network(self) -> None:
         """Create the shared gateway network if it doesn't exist. Idempotent —
         a concurrent create loses harmlessly (the loser sees 'already exists').
-        The explicit subnet is required because bottle attribution pins source
-        IPs; Docker rejects static endpoint addresses on an auto-IPAM network."""
-        inspected = run_docker([
-            "docker", "network", "inspect",
-            "--format", f'{{{{index .Labels "{_GATEWAY_SUBNET_LABEL}"}}}}',
-            self.network,
-        ])
-        if inspected.returncode == 0:
-            marker = inspected.stdout.strip()
-            if marker in {"", self._subnet}:
-                return
-        if inspected.returncode == 0:
-            # Migrate the stale auto-IPAM network created by older releases.
-            # Removing the fixed gateway is safe here: this launch recreates it.
-            run_docker(["docker", "rm", "--force", self.name])
-            removed = run_docker(["docker", "network", "rm", self.network])
-            if removed.returncode != 0:
-                raise GatewayError(
-                    f"gateway network {self.network} needs explicit subnet "
-                    f"{self._subnet} but could not be replaced: "
-                    f"{removed.stderr.strip()}"
-                )
-        proc = run_docker([
-            "docker", "network", "create",
-            "--subnet", self._subnet,
-            "--label", f"{_GATEWAY_SUBNET_LABEL}={self._subnet}",
-            self.network,
-        ])
+        Docker picks the subnet; the launcher reads it back to allocate IPs."""
+        if run_docker(["docker", "network", "inspect", self.network]).returncode == 0:
+            return
+        proc = run_docker(["docker", "network", "create", self.network])
         if proc.returncode != 0 and "already exists" not in proc.stderr:
             raise GatewayError(
                 f"gateway network {self.network} failed to create: {proc.stderr.strip()}"
@@ -182,9 +143,9 @@ class DockerGateway(Gateway):
         # Recreate when the running container's image is stale (a rebuild),
         # so source changes to the gateway's flat daemons take effect — not
         # just when the container is absent.
-        self._ensure_network()
         if self.is_running() and self._running_image_is_current():
             return
+        self._ensure_network()
         # Clear any stale (stopped OR outdated-image) container holding the
         # fixed name, then start fresh. `rm --force` on an absent name is a
         # tolerated no-op.
@@ -197,7 +158,7 @@ class DockerGateway(Gateway):
             # Persist the self-generated CA on the host so it survives both
             # container recreation AND docker volume pruning (agents trust it)
             # — see host_gateway_ca_dir / issue #450.
-            "--volume", f"{self._ca_mount_source}:{MITMPROXY_HOME}",
+            "--volume", f"{host_gateway_ca_dir()}:{MITMPROXY_HOME}",
             # No DB mount: the data plane (egress / supervise / git-gate) reaches
             # the supervise queue over the control-plane RPC and never opens
             # bot-bottle.db, so the gateway container gets no file handle on it
@@ -292,4 +253,4 @@ class DockerGateway(Gateway):
     def provisioning_transport(self) -> GatewayTransport:
         """The exec/cp transport git-gate provisioning stages per-bottle repos +
         deploy keys through (over the docker socket)."""
-        return DockerGatewayTransport(self.name)
+        return DockerGatewayTransport(self.name)

bot_bottle/backend/docker/infra.py

@@ -33,6 +33,7 @@ from .orchestrator import (
     ORCHESTRATOR_NAME,
     ORCHESTRATOR_NETWORK,
 )
+from ...paths import bot_bottle_root
 from ... import resources
 from ...gateway import (
     GATEWAY_IMAGE,
@@ -68,8 +69,6 @@ class DockerInfraService(InfraService):
         gateway_image: str = GATEWAY_IMAGE,
         repo_root: Path | None = None,
         host_root: Path | None = None,
-        root_mount_source: str | Path | None = None,
-        gateway_ca_mount_source: str | Path | None = None,
         orchestrator_name: str = ORCHESTRATOR_NAME,
         orchestrator_label: str = ORCHESTRATOR_LABEL,
         gateway_name: str = GATEWAY_NAME,
@@ -79,14 +78,10 @@ class DockerInfraService(InfraService):
         self.control_network = control_network
         self.orchestrator_image = orchestrator_image
         self.gateway_image = gateway_image
-        # Build context: the repo root in a checkout, a staged copy from the
-        # installed wheel otherwise (bot_bottle.resources).
+        # Build context / bind-mount source: the repo root in a checkout, a
+        # staged copy from the installed wheel otherwise (bot_bottle.resources).
         self._repo_root = repo_root if repo_root is not None else resources.build_root()
-        if host_root is not None and root_mount_source is not None:
-            raise ValueError("pass host_root or root_mount_source, not both")
-        self._host_root = host_root
-        self._root_mount_source = root_mount_source
-        self._gateway_ca_mount_source = gateway_ca_mount_source
+        self._host_root = host_root or bot_bottle_root()
         self._orchestrator_name = orchestrator_name
         self._orchestrator_label = orchestrator_label
         self._gateway_name = gateway_name
@@ -103,7 +98,6 @@ class DockerInfraService(InfraService):
             control_network=self.control_network,
             repo_root=self._repo_root,
             host_root=self._host_root,
-            root_mount_source=self._root_mount_source,
         )
 
     def gateway(self) -> DockerGateway:
@@ -118,7 +112,6 @@ class DockerInfraService(InfraService):
             network=self.network,
             control_network=self.control_network,
             build_context=self._repo_root,
-            ca_mount_source=self._gateway_ca_mount_source,
         )
 
     def ensure_running(

bot_bottle/backend/docker/orchestrator.py

@@ -42,9 +42,13 @@ ORCHESTRATOR_IMAGE = os.environ.get(
 )
 ORCHESTRATOR_DOCKERFILE = "Dockerfile.orchestrator"
 # Baked as a container label so `ensure_running` can detect whether the running
-# orchestrator image was built from the current source.
+# orchestrator is executing the current bind-mounted source.
 ORCHESTRATOR_SOURCE_HASH_LABEL = "bot-bottle-orchestrator-source-hash"
 
+# The bind-mount path for the live control-plane source inside the container.
+# PYTHONPATH points here so a code change takes effect on the next launch
+# without an image rebuild.
+_SRC_IN_CONTAINER = "/bot-bottle-src"
 # Bot-bottle host-root bind-mount (DB + state) inside the orchestrator. The
 # control plane opens bot-bottle.db under here (via BOT_BOTTLE_ROOT ->
 # host_db_path()); it is the ONLY container with a handle on it (issue #469).
@@ -68,51 +72,23 @@ class DockerOrchestrator(Orchestrator):
         control_network: str = ORCHESTRATOR_NETWORK,
         repo_root: Path | None = None,
         host_root: Path | None = None,
-        root_mount_source: str | Path | None = None,
-        client_host: str | None = None,
-        client_network: str | None = None,
-        bind_host: str | None = None,
         dockerfile: str | None = ORCHESTRATOR_DOCKERFILE,
     ) -> None:
-        if host_root is not None and root_mount_source is not None:
-            raise ValueError("pass host_root or root_mount_source, not both")
         self.image_ref = image_ref
         self.name = name
         self.label = label
         self.port = port
         self.control_network = control_network
-        # Build context: the repo root in a checkout, a staged copy from the
-        # installed wheel otherwise (bot_bottle.resources).
+        # Build context / bind-mount source: the repo root in a checkout, a
+        # staged copy from the installed wheel otherwise (bot_bottle.resources).
         self._repo_root = repo_root if repo_root is not None else resources.build_root()
-        configured_root = os.environ.get("BOT_BOTTLE_DOCKER_ROOT_MOUNT", "").strip()
-        self._root_mount_source = str(
-            root_mount_source or configured_root or host_root or bot_bottle_root()
-        )
-        configured_network = os.environ.get(
-            "BOT_BOTTLE_DOCKER_CLIENT_NETWORK", ""
-        ).strip()
-        self._client_network = client_network or configured_network or None
-        configured_host = os.environ.get(
-            "BOT_BOTTLE_DOCKER_HOST_ADDRESS", ""
-        ).strip()
-        self._client_host = (
-            client_host or configured_host
-            or (self.name if self._client_network else "127.0.0.1")
-        )
-        # A socket-shared CI runner reaches published ports through its Docker
-        # network rather than its own loopback. Production stays bound to host
-        # loopback unless a caller explicitly selects another client.
-        self._bind_host = bind_host or (
-            "0.0.0.0"
-            if not self._client_network and self._client_host != "127.0.0.1"
-            else "127.0.0.1"
-        )
+        self._host_root = host_root or bot_bottle_root()
         self._dockerfile = dockerfile
 
     def url(self) -> str:
-        """Control-plane URL reachable by this Docker client."""
-        port = DEFAULT_PORT if self._client_network else self.port
-        return f"http://{self._client_host}:{port}"
+        """Host-side control-plane URL — the orchestrator's published loopback,
+        which the CLI reaches."""
+        return f"http://127.0.0.1:{self.port}"
 
     def gateway_url(self) -> str:
         """The URL the gateway's data plane resolves policy against — the
@@ -143,7 +119,8 @@ class DockerOrchestrator(Orchestrator):
         return self.name in proc.stdout.split()
 
     def _source_current(self, current_hash: str) -> bool:
-        """True iff the running orchestrator image matches current source."""
+        """True iff the running orchestrator was started from the current
+        bind-mounted source."""
         if not self.is_running():
             return False
         proc = run_docker([
@@ -205,19 +182,15 @@ class DockerOrchestrator(Orchestrator):
             # Control network only — agents are never on it, so they have no
             # route to the control plane (the L3 block, not just the JWT).
             "--network", self.control_network,
-            # Host CLI reaches the control plane here (loopback by default).
-            # Socket-shared CI joins the container directly to the job network;
-            # the host-side mapping remains loopback-only in that topology. The
+            # Host CLI reaches the control plane here (loopback only). The
             # orchestrator listens on the fixed DEFAULT_PORT inside the
             # container; self.port is the host-side published port.
-            "--publish", f"{self._bind_host}:{self.port}:{DEFAULT_PORT}",
-            # The image was rebuilt from `_repo_root` immediately before this
-            # launch. Running its baked package avoids a host-path bind mount,
-            # which is both more production-like and works with socket-shared
-            # CI where the daemon cannot see the job container's workspace.
+            "--publish", f"127.0.0.1:{self.port}:{DEFAULT_PORT}",
+            # Live control-plane source (code changes without an image rebuild).
+            "--volume", f"{self._repo_root}:{_SRC_IN_CONTAINER}:ro",
+            "--env", f"PYTHONPATH={_SRC_IN_CONTAINER}",
             # Orchestrator registry DB on the host (sole writer: control plane).
-            # `root_mount_source` may be a host path or a named Docker volume.
-            "--volume", f"{self._root_mount_source}:{_ROOT_IN_CONTAINER}",
+            "--volume", f"{self._host_root}:{_ROOT_IN_CONTAINER}",
             "--env", f"BOT_BOTTLE_ROOT={_ROOT_IN_CONTAINER}",
             # The signing key — held ONLY by the orchestrator (it verifies
             # tokens); the gateway gets the pre-minted `gateway` JWT, never the
@@ -232,15 +205,6 @@ class DockerOrchestrator(Orchestrator):
             raise OrchestratorStartError(
                 f"orchestrator container failed to start: {proc.stderr.strip()}"
             )
-        if self._client_network:
-            proc = run_docker([
-                "docker", "network", "connect", self._client_network, self.name,
-            ])
-            if proc.returncode != 0:
-                raise OrchestratorStartError(
-                    f"orchestrator container failed to join client network "
-                    f"{self._client_network}: {proc.stderr.strip()}"
-                )
 
     def stop(self) -> None:
         """Remove the control-plane container (idempotent)."""

bot_bottle/backend/docker/util.py

@@ -6,17 +6,12 @@ from __future__ import annotations
 
 import os
 from datetime import datetime, timezone
+import re
 import shutil
 import subprocess
 from typing import Iterator
 
 from ...log import die, info
-from ...util import slugify as _slugify
-
-
-def slugify(name: str) -> str:
-    """Compatibility wrapper; new generic callers import ``bot_bottle.util``."""
-    return _slugify(name)
 
 
 def run_docker(
@@ -119,6 +114,19 @@ def docker_cp(src: str, dest: str) -> None:
             f"{(result.stderr or '').strip() or '<no stderr>'}")
 
 
+_SLUG_RE = re.compile(r"[^a-z0-9]+")
+
+
+def slugify(name: str) -> str:
+    """Lowercase, non-alnum runs → '-', trimmed. Dies on empty result."""
+    if not name:
+        die("slugify: missing name")
+    slug = _SLUG_RE.sub("-", name.lower()).strip("-")
+    if not slug:
+        die(f"name '{name}' produced an empty slug; use alphanumeric characters")
+    return slug
+
+
 def build_image(ref: str, context: str, *, dockerfile: str = "") -> None:
     """Invokes `docker build` every call. Layer cache makes no-change
     rebuilds cheap; running every time means Dockerfile edits land

bot_bottle/backend/egress_apply.py

@@ -11,8 +11,7 @@ from pathlib import Path
 
 from ..bottle_state import egress_state_dir
 from ..egress import EGRESS_ROUTES_FILENAME
-from ..gateway.egress.schema import load_config
-from ..gateway.egress.types import LOG_OFF
+from ..gateway.egress.addon_core import LOG_OFF, load_config
 
 
 class EgressApplyError(RuntimeError):

bot_bottle/backend/preparation.py

@@ -1,124 +0,0 @@
-"""Backend-neutral preparation planner.
-
-This module owns the shared transformation from a CLI ``BottleSpec`` to the
-typed inputs consumed by a concrete backend's ``_resolve_plan``. Backend
-classes retain only their validation/preflight/env hooks and their
-backend-specific final resolution.
-"""
-
-from __future__ import annotations
-
-import os
-from dataclasses import dataclass
-from typing import TYPE_CHECKING, Protocol
-
-from ..agent_provider import AgentProvisionPlan, build_agent_provision_plan, get_provider
-from ..egress import EgressPlan
-from ..env import ResolvedEnv, resolve_env
-from ..git_gate import GitGate, GitGatePlan
-from ..manifest import Manifest
-from ..supervisor.plan import SupervisePlan
-from ..workspace import workspace_plan
-from .resolve_common import (
-    merge_provision_env_vars,
-    mint_slug,
-    prepare_agent_state_dir,
-    prepare_egress,
-    prepare_git_gate,
-    prepare_supervise,
-    reject_nested_containers,
-    resolve_manifest_dockerfile,
-    write_launch_metadata,
-)
-
-if TYPE_CHECKING:
-    from .base import BottleSpec
-
-
-class PreparationBackend(Protocol):
-    """Backend hooks needed by the shared planner."""
-
-    name: str
-    supports_nested_containers: bool
-
-    def _validate(self, spec: BottleSpec) -> Manifest: ...
-    def _preflight(self) -> None: ...
-    def _build_guest_env(self, resolved_env: ResolvedEnv) -> dict[str, str]: ...
-
-
-@dataclass(frozen=True)
-class PreparedBottle:
-    """Typed, backend-neutral result of shared launch preparation."""
-
-    manifest: Manifest
-    slug: str
-    resolved_env: ResolvedEnv
-    agent_provision_plan: AgentProvisionPlan
-    egress_plan: EgressPlan
-    git_gate_plan: GitGatePlan
-    supervise_plan: SupervisePlan | None
-
-
-class BottlePreparationPlanner:
-    """Run the common, side-effect-limited part of bottle preparation."""
-
-    def __init__(self, backend: PreparationBackend) -> None:
-        self._backend = backend
-
-    def prepare(self, spec: BottleSpec) -> PreparedBottle:
-        backend = self._backend
-        # These are deliberately protected backend hooks: only this shared
-        # planner orchestrates them, while concrete backends provide the
-        # implementation.
-        manifest = backend._validate(spec)  # pylint: disable=protected-access
-        if not backend.supports_nested_containers:
-            reject_nested_containers(backend.name, manifest)
-
-        backend._preflight()  # pylint: disable=protected-access
-        manifest = GitGate().preflight_host_keys(
-            manifest,
-            headless=spec.headless,
-            home_md=spec.manifest.home_md,
-        )
-
-        bottle = manifest.bottle
-        provider_config = bottle.agent_provider
-        provider = get_provider(provider_config.template)
-        resolved_env = resolve_env(manifest)
-        workspace = workspace_plan(spec, guest_home=provider.guest_home)
-        slug = mint_slug(spec)
-        write_launch_metadata(slug, spec, compose_project="", backend=backend.name)
-
-        dockerfile = (
-            resolve_manifest_dockerfile(provider_config.dockerfile, spec)
-            if provider_config.dockerfile
-            else str(provider.dockerfile)
-        )
-        agent_dir, prompt_file = prepare_agent_state_dir(slug, manifest)
-        provision = build_agent_provision_plan(
-            template=provider_config.template,
-            dockerfile=dockerfile,
-            state_dir=agent_dir,
-            instance_name=f"bot-bottle-{slug}",
-            prompt_file=prompt_file,
-            guest_env=backend._build_guest_env(  # pylint: disable=protected-access
-                resolved_env
-            ),
-            forward_host_credentials=provider_config.forward_host_credentials,
-            auth_token=provider_config.auth_token,
-            host_env=dict(os.environ),
-            trusted_project_path=workspace.workdir,
-            label=spec.label,
-            color=spec.color,
-            provider_settings=provider_config.settings,
-        )
-        provision = merge_provision_env_vars(provision)
-        return PreparedBottle(
-            manifest=manifest,
-            slug=slug,
-            resolved_env=resolved_env,
-            agent_provision_plan=provision,
-            egress_plan=prepare_egress(bottle, slug, provision),
-            git_gate_plan=prepare_git_gate(bottle, slug),
-            supervise_plan=prepare_supervise(bottle, slug),
-        )

bot_bottle/backend/resolve_common.py

@@ -30,7 +30,6 @@ from ..log import die
 from ..manifest import Manifest, ManifestBottle
 from ..supervisor.plan import SupervisePlan
 from ..orchestrator.supervisor import Supervisor
-from ..util import slugify
 from . import BottleSpec
 
 
@@ -45,7 +44,8 @@ def mint_slug(spec: BottleSpec) -> str:
     if spec.identity:
         return spec.identity
     if spec.label:
-        return slugify(spec.label)
+        from .docker import util as docker_mod
+        return docker_mod.slugify(spec.label)
     return bottle_identity(spec.agent_name)
 
 

bot_bottle/cli/commands/start.py

@@ -25,11 +25,12 @@ from typing import Callable
 from ...agent_provider import get_provider, runtime_for
 from ...backend import (
     Bottle,
-    BottlePlan,
     BottleSpec,
     enumerate_active_agents,
     get_bottle_backend,
 )
+from ...backend.docker import util as docker_mod
+from ...backend.docker.bottle_plan import DockerBottlePlan
 from ...bottle_state import (
     cleanup_state,
     is_preserved,
@@ -39,7 +40,7 @@ from ...image_cache import StaleImageError
 from ...log import info, die
 from ...manifest import Manifest, ManifestIndex
 from ..constants import PROG
-from ...util import read_tty_line, slugify
+from ...util import read_tty_line
 from .. import tui
 
 
@@ -256,10 +257,10 @@ def _uniquify_label_headless(label: str) -> str:
     logging the chosen label. Orchestrators fire-and-forget many bottles,
     so silently picking a free name beats erroring on every collision."""
     active_slugs = {a.slug for a in enumerate_active_agents()}
-    if slugify(label) not in active_slugs:
+    if docker_mod.slugify(label) not in active_slugs:
         return label
     n = 2
-    while slugify(f"{label}-{n}") in active_slugs:
+    while docker_mod.slugify(f"{label}-{n}") in active_slugs:
         n += 1
     chosen = f"{label}-{n}"
     info(f"label '{label}' already in use; using '{chosen}'")
@@ -273,11 +274,11 @@ def prepare_with_preflight(
     spec: BottleSpec,
     *,
     stage_dir: Path,
-    render_preflight: Callable[[BottlePlan, str], None],
+    render_preflight: Callable[[DockerBottlePlan, str], None],
     prompt_yes: Callable[[], bool],
     dry_run: bool = False,
     backend_name: str | None = None,
-) -> tuple[BottlePlan | None, str]:
+) -> tuple[DockerBottlePlan | None, str]:
     """Run `backend.prepare`, render the preflight summary via the
     injected callable, prompt y/N via the injected callable.
 
@@ -404,7 +405,7 @@ def _resolve_unique_label(label: str, color: str) -> tuple[str, str]:
     in use among running bottles.  Passes through unchanged when no
     collision is found on the first check."""
     while True:
-        slug_candidate = slugify(label)
+        slug_candidate = docker_mod.slugify(label)
         active_slugs = {a.slug for a in enumerate_active_agents()}
         if slug_candidate not in active_slugs:
             return label, color
@@ -431,7 +432,7 @@ def _select_image_policy() -> str | None:
 
 
 def _text_render_preflight():
-    def _render(plan: BottlePlan, backend_name: str) -> None:
+    def _render(plan: DockerBottlePlan, backend_name: str) -> None:
         print(file=sys.stderr)
         print(f"backend: {backend_name}", file=sys.stderr)
         print(_manifest_to_yaml(plan.manifest), file=sys.stderr)

bot_bottle/cli/commands/supervise.py

@@ -368,7 +368,7 @@ def _main_loop(stdscr: "curses._CursesWindow") -> None:  # type: ignore  # pragm
         elif key in (curses.KEY_UP, ord("k")):
             selected = max(selected - 1, 0)
         elif key in (curses.KEY_ENTER, 10, 13):
-            status_line = _detail_view(stdscr, qp, green_attr=green_attr)
+            _detail_view(stdscr, qp, green_attr=green_attr)
         elif key == ord("a"):
             try:
                 status_line = _approve_from_tui(stdscr, qp)
@@ -456,7 +456,7 @@ def _detail_view(
     qp: QueuedProposal,
     *,
     green_attr: int = 0,
-) -> str:  # pragma: no cover
+) -> None:  # pragma: no cover
     """Render the full proposal. Scrollable. Press q to return."""
     lines = _detail_lines(qp, green_attr=green_attr)
     offset = 0
@@ -473,7 +473,7 @@ def _detail_view(
         stdscr.refresh()
         key = stdscr.getch()
         if key in (ord("q"), 27):
-            return ""
+            return
         if key in (curses.KEY_DOWN, ord("j")):
             offset = min(offset + 1, max(0, len(lines) - 1))
         elif key in (curses.KEY_UP, ord("k")):
@@ -484,34 +484,31 @@ def _detail_view(
             offset = max(0, len(lines) - 1)
         elif key == ord("a"):
             try:
-                return _approve_from_tui(stdscr, qp)
-            except ApplyError as exc:
-                return f"apply failed: {exc}"
+                _approve_from_tui(stdscr, qp)
+            except ApplyError:
+                pass
+            return
         elif key == ord("m"):
             if qp.proposal.tool in _REPORT_ONLY_TOOLS:
-                return f"modify unavailable for {qp.proposal.tool}"
+                return
             edited = _modify(stdscr, qp)
-            if edited is None:
-                return "modify aborted (no change)"
-            try:
-                return _approve_from_tui(
-                    stdscr, qp, final_file=edited,
-                    notes="operator modified before approving",
-                )
-            except ApplyError as exc:
-                return f"apply failed: {exc}"
+            if edited is not None:
+                try:
+                    _approve_from_tui(
+                        stdscr, qp, final_file=edited,
+                        notes="operator modified before approving",
+                    )
+                except ApplyError:
+                    pass
+            return
         elif key == ord("r"):
             reason = _prompt(stdscr, "reject reason: ")
             if reason:
                 reject(qp, reason=reason)
-                return f"rejected {qp.proposal.tool} for [{qp.label}]"
-            return "reject aborted (empty reason)"
+            return
 
 
-def _modify(
-    stdscr: "curses._CursesWindow",  # type: ignore
-    qp: QueuedProposal,
-) -> str | None:  # pragma: no cover
+def _modify(stdscr: "curses._CursesWindow", qp: QueuedProposal) -> str | None:  # type: ignore  # pragma: no cover
     """Suspend curses, open $EDITOR on the proposed file, return edited content."""
     suffix = _suffix_for_tool(qp.proposal.tool)
     curses.endwin()

bot_bottle/cli/tui.py

@@ -16,8 +16,6 @@ import os
 import sys
 from typing import Any, Optional
 
-from ..log import debug
-
 
 def filter_multiselect(
     items: list[str],
@@ -44,11 +42,7 @@ def filter_multiselect(
 
     try:
         tty_fd = open(tty_path, "r+b", buffering=0)
-    except OSError as exc:
-        debug(
-            "multi-select unavailable; treating it as cancellation",
-            context={"error_type": type(exc).__name__, "tty": tty_path},
-        )
+    except OSError:
         return None
 
     try:
@@ -79,11 +73,7 @@ def filter_select(
 
     try:
         tty_fd = open(tty_path, "r+b", buffering=0)
-    except OSError as exc:
-        debug(
-            "filter-select unavailable; treating it as cancellation",
-            context={"error_type": type(exc).__name__, "tty": tty_path},
-        )
+    except OSError:
         return None
 
     try:
@@ -139,11 +129,7 @@ def _run_picker(items: list[str], *, title: str, tty_fd: int) -> Optional[str]:
             curses.nocbreak()
             curses.echo()
             curses.endwin()
-    except Exception as exc:  # noqa: W0718 — curses can raise many error types
-        debug(
-            "filter-select display failed; treating it as cancellation",
-            context={"error_type": type(exc).__name__},
-        )
+    except Exception:  # noqa: W0718 — curses can raise many error types
         return None
     finally:
         sys.__stdin__ = orig_stdin    # type: ignore[assignment]
@@ -306,11 +292,7 @@ def _run_multiselect(
             curses.nocbreak()
             curses.echo()
             curses.endwin()
-    except Exception as exc:  # noqa: W0718
-        debug(
-            "multi-select display failed; treating it as cancellation",
-            context={"error_type": type(exc).__name__},
-        )
+    except Exception:  # noqa: W0718
         return None
     finally:
         sys.__stdin__ = orig_stdin    # type: ignore[assignment]
@@ -576,21 +558,13 @@ def name_color_modal(
     """
     try:
         tty_fd = open(tty_path, "r+b", buffering=0)  # pylint: disable=consider-using-with
-    except OSError as exc:
-        debug(
-            "name/color picker unavailable; using defaults",
-            context={"error_type": type(exc).__name__, "tty": tty_path},
-        )
+    except OSError:
         return default_label, ""
 
     try:
         fd_dup = os.dup(tty_fd.fileno())
         return _run_name_color(default_label, tty_fd=fd_dup, disclaimer=disclaimer)
-    except Exception as exc:  # noqa: BLE001  # pylint: disable=broad-exception-caught
-        debug(
-            "name/color picker failed; using defaults",
-            context={"error_type": type(exc).__name__},
-        )
+    except Exception:  # noqa: BLE001  # pylint: disable=broad-exception-caught
         return default_label, ""
     finally:
         tty_fd.close()

bot_bottle/egress/plan.py

@@ -11,7 +11,7 @@ from __future__ import annotations
 from dataclasses import dataclass
 from pathlib import Path
 
-from ..gateway.egress.types import Route
+from ..gateway.egress.addon_core import Route
 
 
 @dataclass(frozen=True)
@@ -19,7 +19,7 @@ class EgressRoute(Route):
     """Host-side extension of the addon's `Route`.
 
     Inherits `host`, `matches`, `auth_scheme`, and `token_env`
-    from the gateway's wire `Route` — those are the fields that cross the
+    from `egress_addon_core.Route` — those are the fields that cross the
     YAML wire into the gateway. The fields below are host-only and
     are never serialised to the addon.
 

bot_bottle/egress/service.py

@@ -14,8 +14,8 @@ import secrets
 from pathlib import Path
 from typing import TYPE_CHECKING
 
-from ..gateway.egress.dlp_config import ON_MATCH_REDACT
-from ..gateway.egress.types import (
+from ..gateway.egress.addon_core import (
+    ON_MATCH_REDACT,
     HeaderMatch as CoreHeaderMatch,
     MatchEntry as CoreMatchEntry,
     PathMatch as CorePathMatch,

bot_bottle/gateway/egress/addon.py

@@ -17,34 +17,28 @@ from mitmproxy import http  # type: ignore[import-not-found]  # pylint: disable=
 
 from bot_bottle.constants import IDENTITY_HEADER
 from bot_bottle.gateway.egress.dlp_detectors import redact_tokens, strip_crlf
-from bot_bottle.gateway.egress.dlp_config import (
+from bot_bottle.gateway.egress.addon_core import (
+    LOG_BLOCKS,
+    LOG_FULL,
     DEFAULT_OUTBOUND_ON_MATCH,
     ON_MATCH_BLOCK,
     ON_MATCH_REDACT,
-)
-from bot_bottle.gateway.egress.context import resolve_client_context
-from bot_bottle.gateway.egress.dlp import (
+    Config,
+    Route,
+    ScanResult,
     build_inbound_scan_text,
     build_outbound_scan_text,
     build_token_allow_payload,
-    outbound_scan_headers,
-    scan_inbound,
-    scan_outbound,
-)
-from bot_bottle.gateway.egress.matching import (
     decide,
     decide_git_fetch,
     is_git_fetch_request,
     is_git_push_request,
     match_route,
-)
-from bot_bottle.gateway.egress.schema import route_to_yaml_dict
-from bot_bottle.gateway.egress.types import (
-    LOG_BLOCKS,
-    LOG_FULL,
-    Config,
-    Route,
-    ScanResult,
+    resolve_client_context,
+    outbound_scan_headers,
+    route_to_yaml_dict,
+    scan_inbound,
+    scan_outbound,
 )
 from bot_bottle.gateway.policy_resolver import PolicyResolveError, PolicyResolver
 from bot_bottle.supervisor.types import (

bot_bottle/gateway/egress/context.py

@@ -1,77 +0,0 @@
-"""Fail-closed resolution of a client's policy and egress credentials."""
-
-from __future__ import annotations
-
-import typing
-
-from ...log import debug
-from .types import Config
-
-
-DENY_UNATTRIBUTED = (
-    "egress: this request was not attributed to any bottle, so no egress policy "
-    "applies and every host is denied. Either the bottle's registry row is "
-    "missing/ambiguous (torn down, or another bottle claimed its source IP), or "
-    "the request carried no matching identity token — check that the caller's "
-    "proxy URL includes it. This is not an allowlist problem."
-)
-DENY_UNPARSEABLE = (
-    "egress: this bottle's egress policy could not be parsed, so it is being "
-    "treated as deny-all. Fix the bottle's egress.routes; every host is denied "
-    "until it loads."
-)
-DENY_RESOLVER_ERROR = (
-    "egress: the orchestrator could not be reached to resolve this bottle's "
-    "egress policy, so every host is denied (fail-closed). Check that the "
-    "control plane is up; this is not an allowlist problem."
-)
-
-
-class PolicyResolverLike(typing.Protocol):
-    def resolve(self, source_ip: str, identity_token: str = ...) -> str | None: ...
-
-
-class ContextResolverLike(typing.Protocol):
-    def resolve_policy_and_bottle_id(
-        self, source_ip: str, identity_token: str = ...,
-    ) -> tuple[str | None, str | None, dict[str, str]]: ...
-
-
-def _config_from_policy(policy: str | None) -> Config:
-    # Local import keeps schema parsing independent of resolver protocols.
-    from .schema import load_config
-    if not policy:
-        return Config(routes=(), deny_reason=DENY_UNATTRIBUTED)
-    try:
-        return load_config(policy)
-    except ValueError:
-        return Config(routes=(), deny_reason=DENY_UNPARSEABLE)
-
-
-def resolve_client_config(
-    resolver: PolicyResolverLike, client_ip: str, identity_token: str = "",
-) -> Config:
-    try:
-        policy = resolver.resolve(client_ip, identity_token)
-    except Exception as exc:  # noqa: BLE001 - a policy lookup failure must deny
-        debug(
-            "egress policy resolution failed; applying deny-all",
-            context={"error_type": type(exc).__name__},
-        )
-        return Config(routes=(), deny_reason=DENY_RESOLVER_ERROR)
-    return _config_from_policy(policy)
-
-
-def resolve_client_context(
-    resolver: ContextResolverLike, client_ip: str, identity_token: str = "",
-) -> tuple[Config, str, dict[str, str]]:
-    try:
-        policy, bottle_id, tokens = resolver.resolve_policy_and_bottle_id(
-            client_ip, identity_token)
-    except Exception as exc:  # noqa: BLE001 - a policy lookup failure must deny
-        debug(
-            "egress context resolution failed; applying deny-all",
-            context={"error_type": type(exc).__name__},
-        )
-        return Config(routes=(), deny_reason=DENY_RESOLVER_ERROR), "", {}
-    return _config_from_policy(policy), (bottle_id or ""), tokens

bot_bottle/gateway/egress/dlp.py

@@ -1,99 +0,0 @@
-"""DLP scan dispatch and safe proposal rendering for egress requests."""
-
-from __future__ import annotations
-
-import typing
-
-from .types import Route, ScanResult
-
-
-def build_outbound_scan_text(host: str, path: str, query: str,
-                             headers: typing.Mapping[str, str], body: str) -> str:
-    parts = [host, path]
-    if query:
-        parts.append(query)
-    parts.extend(f"{name}: {value}" for name, value in headers.items())
-    if body:
-        parts.append(body)
-    return "\n".join(parts)
-
-
-def outbound_scan_headers(route: Route, headers: typing.Mapping[str, str]) -> dict[str, str]:
-    """Drop agent Authorization when the route injects gateway-owned auth."""
-    skip_auth = bool(route.auth_scheme and route.token_env)
-    return {name: value for name, value in headers.items()
-            if not (skip_auth and name.lower() == "authorization")}
-
-
-def build_inbound_scan_text(headers: typing.Mapping[str, str], body: str) -> str:
-    parts = [f"{name}: {value}" for name, value in headers.items()]
-    if body:
-        parts.append(body)
-    return "\n".join(parts)
-
-
-def _enabled(configured: tuple[str, ...] | None, name: str) -> bool:
-    return configured is None or name in configured
-
-
-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:
-    if not route.inspect:
-        return None
-    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 - gateway's flat module path
-        from .dlp_detectors import (
-            scan_crlf_injection, scan_entropy, scan_known_secrets, scan_token_patterns)
-    if isinstance(body, bytes):
-        try:
-            text = body.decode("utf-8")
-        except UnicodeDecodeError:
-            text = body.decode("latin-1")
-    else:
-        text = body
-    result = scan_crlf_injection(text if crlf_text is None else crlf_text)
-    if result is not None:
-        return result
-    if _enabled(route.outbound_detectors, "token_patterns"):
-        result = scan_token_patterns(text, location="body", safe_tokens=safe_tokens)
-        if result is not None:
-            return result
-    if _enabled(route.outbound_detectors, "known_secrets"):
-        extra = tuple(prefix for prefix in environ.get(
-            "BOT_BOTTLE_SENSITIVE_PREFIXES", "").split(",") if prefix)
-        result = scan_known_secrets(text, location="body", env=environ,
-                                    sensitive_prefixes=("EGRESS_TOKEN_",) + extra,
-                                    safe_tokens=safe_tokens)
-        if result is not None:
-            return result
-    if route.outbound_detectors is not None and "entropy" in route.outbound_detectors:
-        return scan_entropy(text, location="body")
-    return None
-
-
-def build_token_allow_payload(host: str, method: str, path: str, result: ScanResult) -> str:
-    """Render redacted operator context; the raw matched secret is excluded."""
-    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) -> ScanResult | None:
-    if not route.inspect:
-        return None
-    try:
-        from dlp_detectors import scan_naive_injection  # type: ignore[import-not-found]
-    except ImportError:  # pragma: no cover - gateway's flat module path
-        from .dlp_detectors import scan_naive_injection
-    text = body if isinstance(body, str) else body.decode("utf-8", errors="replace")
-    if _enabled(route.inbound_detectors, "naive_injection_detection"):
-        return scan_naive_injection(text)
-    return None

bot_bottle/gateway/egress/dlp_detectors.py

@@ -19,7 +19,7 @@ from math import log2
 from collections import Counter
 from urllib.parse import quote as url_quote
 
-from .types import ScanResult
+from .addon_core import ScanResult
 
 
 # ---------------------------------------------------------------------------

bot_bottle/gateway/egress/matching.py

@@ -1,112 +0,0 @@
-"""Route matching and request-policy decisions for the egress gateway."""
-
-from __future__ import annotations
-
-import typing
-
-from .types import Decision, MatchEntry, PathMatch, Route
-
-
-def _path_matches(pm: PathMatch, request_path: str) -> bool:
-    if pm.type == "exact":
-        return request_path == pm.value
-    if pm.type == "prefix":
-        if request_path == pm.value:
-            return True
-        if not pm.value.endswith("/"):
-            return request_path.startswith(pm.value + "/")
-        return request_path.startswith(pm.value)
-    return (
-        pm.type == "regex"
-        and pm.compiled is not None
-        and pm.compiled.search(request_path) is not None
-    )
-
-
-def _entry_matches(
-    entry: MatchEntry, request_path: str, request_method: str,
-    request_headers: typing.Mapping[str, str],
-) -> bool:
-    if entry.paths and not any(_path_matches(pm, request_path) for pm in entry.paths):
-        return False
-    if entry.methods and request_method.upper() not in entry.methods:
-        return False
-    for match in entry.headers:
-        value = request_headers.get(match.name.lower())
-        if value is None:
-            return False
-        if match.type == "exact" and value != match.value:
-            return False
-        if match.type == "regex" and (
-            match.compiled is None or match.compiled.search(value) is None
-        ):
-            return False
-    return True
-
-
-def evaluate_matches(
-    route: Route, request_path: str, request_method: str = "GET",
-    request_headers: typing.Mapping[str, str] | None = None,
-) -> bool:
-    """Return whether a request satisfies a route's optional match entries."""
-    if not route.matches:
-        return True
-    return any(_entry_matches(entry, request_path, request_method, request_headers or {})
-               for entry in route.matches)
-
-
-def is_git_push_request(path: str, query: str) -> bool:
-    return path.endswith("/git-receive-pack") or (
-        path.endswith("/info/refs") and any(
-            pair.partition("=") == ("service", "=", "git-receive-pack")
-            for pair in query.split("&")
-        )
-    )
-
-
-def is_git_fetch_request(path: str, query: str) -> bool:
-    return path.endswith("/git-upload-pack") or (
-        path.endswith("/info/refs") and any(
-            pair.partition("=") == ("service", "=", "git-upload-pack")
-            for pair in query.split("&")
-        )
-    )
-
-
-def match_route(routes: typing.Sequence[Route], request_host: str) -> Route | None:
-    target = request_host.lower()
-    return next((route for route in routes if route.host.lower() == target), None)
-
-
-def decide(
-    routes: typing.Sequence[Route], request_host: str, request_path: str,
-    environ: typing.Mapping[str, str], *, request_method: str = "GET",
-    request_headers: typing.Mapping[str, str] | None = None, deny_reason: str = "",
-) -> Decision:
-    route = match_route(routes, request_host)
-    if route is None:
-        return Decision("block", deny_reason or (
-            f"egress: host {request_host!r} is not in the bottle's egress.routes "
-            "allowlist. Declare a route for it or remove the request."))
-    if not evaluate_matches(route, request_path, request_method, request_headers):
-        return Decision("block", (
-            f"egress: request {request_method} {request_path!r} does not match any "
-            f"entry in matches for {route.host!r}"))
-    if route.auth_scheme and route.token_env:
-        token = environ.get(route.token_env, "")
-        if not token:
-            return Decision("block", (
-                f"egress: route for {route.host!r} declared auth but env var "
-                f"{route.token_env!r} is unset"))
-        return Decision("forward", inject_authorization=f"{route.auth_scheme} {token}")
-    return Decision("forward")
-
-
-def decide_git_fetch(routes: typing.Sequence[Route], request_host: str) -> Decision:
-    route = match_route(routes, request_host)
-    if route is not None and route.git_fetch:
-        return Decision("forward")
-    return Decision("block", (
-        "egress: git fetch/clone over HTTPS is not allowed by default; use git-gate "
-        "for declared repos or set egress.routes[].git.fetch=true for explicit "
-        "read-only HTTPS Git access."))

bot_bottle/gateway/egress/schema.py

@@ -1,349 +0,0 @@
-"""Egress policy schema parsing and serialization (PRD 0017 / 0053)."""
-
-from __future__ import annotations
-
-import re
-import typing
-
-from ...yaml_subset import YamlSubsetError, parse_yaml_subset
-from .dlp_config import parse_inspect_block
-from .types import (
-    HEADER_MATCH_TYPES,
-    LOG_BLOCKS,
-    LOG_FULL,
-    LOG_OFF,
-    PATH_MATCH_TYPES,
-    VALID_METHODS,
-    Config,
-    HeaderMatch,
-    MatchEntry,
-    PathMatch,
-    Route,
-)
-
-# Parsing
-# ---------------------------------------------------------------------------
-
-def _parse_path_match(idx: int, j: int, raw: object) -> PathMatch:
-    label = f"route[{idx}] matches paths[{j}]"
-    if not isinstance(raw, dict):
-        raise ValueError(f"{label}: must be an object")
-    raw_dict: dict[str, object] = typing.cast(dict[str, object], raw)
-    ptype = raw_dict.get("type", "prefix")
-    if not isinstance(ptype, str) or ptype not in PATH_MATCH_TYPES:
-        raise ValueError(
-            f"{label}: 'type' must be one of {', '.join(PATH_MATCH_TYPES)} "
-            f"(got {ptype!r})"
-        )
-    value = raw_dict.get("value")
-    if not isinstance(value, str) or not value:
-        raise ValueError(f"{label}: 'value' must be a non-empty string")
-    if ptype in ("exact", "prefix") and not value.startswith("/"):
-        raise ValueError(
-            f"{label}: value {value!r} must start with '/' for "
-            f"type {ptype!r}"
-        )
-    compiled: re.Pattern[str] | None = None
-    if ptype == "regex":
-        try:
-            compiled = re.compile(value)
-        except re.error as e:
-            raise ValueError(
-                f"{label}: regex {value!r} failed to compile: {e}"
-            ) from e
-    for k in raw_dict:
-        if k not in ("type", "value"):
-            raise ValueError(f"{label}: unknown key {k!r}")
-    return PathMatch(type=ptype, value=value, compiled=compiled)
-
-
-def _parse_header_match(idx: int, j: int, raw: object) -> HeaderMatch:
-    label = f"route[{idx}] matches headers[{j}]"
-    if not isinstance(raw, dict):
-        raise ValueError(f"{label}: must be an object")
-    raw_dict: dict[str, object] = typing.cast(dict[str, object], raw)
-    name = raw_dict.get("name")
-    if not isinstance(name, str) or not name:
-        raise ValueError(f"{label}: 'name' must be a non-empty string")
-    value = raw_dict.get("value")
-    if not isinstance(value, str):
-        raise ValueError(f"{label}: 'value' must be a string")
-    htype = raw_dict.get("type", "exact")
-    if not isinstance(htype, str) or htype not in HEADER_MATCH_TYPES:
-        raise ValueError(
-            f"{label}: 'type' must be one of {', '.join(HEADER_MATCH_TYPES)} "
-            f"(got {htype!r})"
-        )
-    compiled: re.Pattern[str] | None = None
-    if htype == "regex":
-        try:
-            compiled = re.compile(value)
-        except re.error as e:
-            raise ValueError(
-                f"{label}: regex {value!r} failed to compile: {e}"
-            ) from e
-    for k in raw_dict:
-        if k not in ("name", "value", "type"):
-            raise ValueError(f"{label}: unknown key {k!r}")
-    return HeaderMatch(name=name, value=value, type=htype, compiled=compiled)
-
-
-def _parse_match_entry(idx: int, k: int, raw: object) -> MatchEntry:
-    label = f"route[{idx}] matches[{k}]"
-    if not isinstance(raw, dict):
-        raise ValueError(f"{label}: must be an object")
-    raw_dict: dict[str, object] = typing.cast(dict[str, object], raw)
-
-    paths: tuple[PathMatch, ...] = ()
-    paths_raw = raw_dict.get("paths")
-    if paths_raw is not None:
-        if not isinstance(paths_raw, list):
-            raise ValueError(f"{label}: 'paths' must be a list")
-        paths_list = typing.cast(list[object], paths_raw)
-        paths = tuple(_parse_path_match(idx, j, p) for j, p in enumerate(paths_list))
-
-    methods: tuple[str, ...] = ()
-    methods_raw = raw_dict.get("methods")
-    if methods_raw is not None:
-        if not isinstance(methods_raw, list):
-            raise ValueError(f"{label}: 'methods' must be a list")
-        methods_list = typing.cast(list[object], methods_raw)
-        normalised: list[str] = []
-        for j, m in enumerate(methods_list):
-            if not isinstance(m, str):
-                raise ValueError(f"{label}: methods[{j}] must be a string")
-            upper = m.upper()
-            if upper not in VALID_METHODS:
-                raise ValueError(
-                    f"{label}: methods[{j}] {m!r} is not a valid HTTP method"
-                )
-            normalised.append(upper)
-        methods = tuple(normalised)
-
-    headers: tuple[HeaderMatch, ...] = ()
-    headers_raw = raw_dict.get("headers")
-    if headers_raw is not None:
-        if not isinstance(headers_raw, list):
-            raise ValueError(f"{label}: 'headers' must be a list")
-        headers_list = typing.cast(list[object], headers_raw)
-        headers = tuple(
-            _parse_header_match(idx, j, h) for j, h in enumerate(headers_list)
-        )
-
-    for key in raw_dict:
-        if key not in ("paths", "methods", "headers"):
-            raise ValueError(f"{label}: unknown key {key!r}")
-
-    return MatchEntry(paths=paths, methods=methods, headers=headers)
-
-
-def parse_routes(payload: object) -> tuple[Route, ...]:
-    if not isinstance(payload, dict):
-        raise ValueError("routes payload: top-level must be an object")
-    payload_dict: dict[str, object] = typing.cast(dict[str, object], payload)
-    raw: object = payload_dict.get("routes")
-    if not isinstance(raw, list):
-        raise ValueError("routes payload: 'routes' must be a list")
-    raw_list: list[object] = typing.cast(list[object], raw)
-    out: list[Route] = []
-    for i, r in enumerate(raw_list):
-        out.append(_parse_one(i, r))
-    return tuple(out)
-
-
-def _parse_one(idx: int, raw: object) -> Route:
-    label = f"route[{idx}]"
-    if not isinstance(raw, dict):
-        raise ValueError(f"{label}: must be an object (got {type(raw).__name__})")
-    raw_dict: dict[str, object] = typing.cast(dict[str, object], raw)
-    host: object = raw_dict.get("host")
-    if not isinstance(host, str) or not host:
-        raise ValueError(f"{label}: 'host' must be a non-empty string")
-    legacy_flat = "inspect" not in raw_dict
-    inspect_raw = raw_dict.get("inspect", {})
-    if inspect_raw is False:
-        inspect = False
-        settings: dict[str, object] = {}
-    elif isinstance(inspect_raw, dict):
-        inspect = True
-        settings = (
-            {k: v for k, v in raw_dict.items() if k != "host"}
-            if legacy_flat
-            else typing.cast(dict[str, object], inspect_raw)
-        )
-        legacy_dlp = settings.pop("dlp", None)
-        if isinstance(legacy_dlp, dict):
-            settings.update(typing.cast(dict[str, object], legacy_dlp))
-        elif legacy_dlp is not None:
-            raise ValueError(
-                f"{label} ({host}): legacy 'dlp' must be an object"
-            )
-    else:
-        raise ValueError(f"{label} ({host}): 'inspect' must be false or an object")
-
-    # matches
-    matches: tuple[MatchEntry, ...] = ()
-    matches_raw = settings.get("matches")
-    if matches_raw is not None:
-        if not isinstance(matches_raw, list):
-            raise ValueError(f"{label} ({host}): 'matches' must be a list")
-        matches_list = typing.cast(list[object], matches_raw)
-        matches = tuple(
-            _parse_match_entry(idx, k, m) for k, m in enumerate(matches_list)
-        )
-
-    # auth (unchanged wire format)
-    auth_scheme: object = settings.get("auth_scheme", "")
-    token_env: object = settings.get("token_env", "")
-    if not isinstance(auth_scheme, str):
-        raise ValueError(f"{label} ({host}): 'auth_scheme' must be a string")
-    if not isinstance(token_env, str):
-        raise ValueError(f"{label} ({host}): 'token_env' must be a string")
-    if bool(auth_scheme) != bool(token_env):
-        raise ValueError(
-            f"{label} ({host}): 'auth_scheme' and 'token_env' must be both "
-            f"set or both empty (got auth_scheme={auth_scheme!r}, "
-            f"token_env={token_env!r})"
-        )
-
-    # git-over-HTTPS policy
-    git_fetch = False
-    git_raw = settings.get("git")
-    if git_raw is not None:
-        if not isinstance(git_raw, dict):
-            raise ValueError(f"{label} ({host}): 'git' must be an object")
-        git_dict: dict[str, object] = typing.cast(dict[str, object], git_raw)
-        fetch_raw = git_dict.get("fetch", False)
-        if fetch_raw is True or fetch_raw is False:
-            git_fetch = fetch_raw
-        else:
-            raise ValueError(f"{label} ({host}): 'git.fetch' must be a boolean")
-        for k in git_dict:
-            if k != "fetch":
-                raise ValueError(
-                    f"{label} ({host}): git has unknown key {k!r}; "
-                    "accepted key is 'fetch'"
-                )
-
-    # dlp detectors
-    outbound_detectors, inbound_detectors, outbound_on_match = parse_inspect_block(
-        idx, host, settings,
-    )
-
-    preserve_auth_raw = settings.get("preserve_auth", False)
-    if preserve_auth_raw is not True and preserve_auth_raw is not False:
-        raise ValueError(
-            f"{label} ({host}): 'preserve_auth' must be a boolean"
-        )
-    preserve_auth: bool = preserve_auth_raw
-
-    for k in settings:
-        if k not in (
-            "matches", "auth_scheme", "token_env", "git", "preserve_auth",
-            "outbound_detectors", "inbound_detectors", "outbound_on_match",
-        ):
-            raise ValueError(
-                f"{label} ({host}): inspect has unknown key {k!r}"
-            )
-    for k in raw_dict:
-        if not legacy_flat and k not in ("host", "inspect"):
-            raise ValueError(
-                f"{label} ({host}): unknown key {k!r}; accepted keys "
-                f"are 'host' and 'inspect'"
-            )
-
-    return Route(
-        host=host,
-        matches=matches,
-        auth_scheme=auth_scheme,
-        token_env=token_env,
-        git_fetch=git_fetch,
-        outbound_detectors=outbound_detectors,
-        inbound_detectors=inbound_detectors,
-        outbound_on_match=outbound_on_match,
-        preserve_auth=preserve_auth,
-        inspect=inspect,
-    )
-
-
-def _path_match_to_dict(pm: PathMatch) -> dict[str, object]:
-    d: dict[str, object] = {"value": pm.value}
-    if pm.type != "prefix":
-        d["type"] = pm.type
-    return d
-
-
-def _header_match_to_dict(hm: HeaderMatch) -> dict[str, object]:
-    d: dict[str, object] = {"name": hm.name, "value": hm.value}
-    if hm.type != "exact":
-        d["type"] = hm.type
-    return d
-
-
-def _match_entry_to_dict(me: MatchEntry) -> dict[str, object]:
-    d: dict[str, object] = {}
-    if me.paths:
-        d["paths"] = [_path_match_to_dict(p) for p in me.paths]
-    if me.methods:
-        d["methods"] = list(me.methods)
-    if me.headers:
-        d["headers"] = [_header_match_to_dict(h) for h in me.headers]
-    return d
-
-
-def route_to_yaml_dict(r: Route) -> dict[str, object]:
-    """Serialize a Route to YAML-schema-compatible dict.
-
-    Uses the same field names the YAML parser accepts, so the output
-    can be round-tripped directly into an `allow` or `egress-block`
-    proposal without translation. Fields that are empty/default are
-    omitted so the agent doesn't copy irrelevant keys."""
-    d: dict[str, object] = {"host": r.host}
-    if not r.inspect:
-        d["inspect"] = False
-        return d
-    inspected: dict[str, object] = {}
-    if r.auth_scheme:
-        inspected["auth_scheme"] = r.auth_scheme
-        inspected["token_env"] = r.token_env
-    if r.matches:
-        inspected["matches"] = [_match_entry_to_dict(m) for m in r.matches]
-    if r.git_fetch:
-        inspected["git"] = {"fetch": True}
-    if r.outbound_detectors is not None:
-        inspected["outbound_detectors"] = list(r.outbound_detectors)
-    if r.inbound_detectors is not None:
-        inspected["inbound_detectors"] = list(r.inbound_detectors)
-    if r.outbound_on_match:
-        inspected["outbound_on_match"] = r.outbound_on_match
-    if r.preserve_auth:
-        inspected["preserve_auth"] = True
-    if inspected:
-        d["inspect"] = inspected
-    return d
-
-
-def parse_config(payload: object) -> "Config":
-    """Parse a full egress config payload (top-level log level + routes)."""
-    if not isinstance(payload, dict):
-        raise ValueError("routes payload: top-level must be an object")
-    payload_dict: dict[str, object] = typing.cast(dict[str, object], payload)
-
-    log_raw: object = payload_dict.get("log", LOG_OFF)
-    if log_raw is True or log_raw is False or not isinstance(log_raw, int) \
-            or log_raw not in (LOG_OFF, LOG_BLOCKS, LOG_FULL):
-        raise ValueError(
-            f"routes payload: 'log' must be {LOG_OFF}, {LOG_BLOCKS}, or {LOG_FULL}"
-        )
-
-    routes = parse_routes(payload)
-    return Config(routes=routes, log=log_raw)
-
-
-def load_config(text: str) -> "Config":
-    """Parse YAML text → Config (routes + log flag)."""
-    try:
-        payload = parse_yaml_subset(text)
-    except YamlSubsetError as e:
-        raise ValueError(f"routes payload: invalid YAML: {e}") from e
-    return parse_config(payload)

bot_bottle/gateway/egress/types.py

@@ -1,81 +0,0 @@
-"""Shared egress policy value objects.
-
-Kept dependency-free so the schema parser, matcher, DLP scanner, and addon
-adapter can use the same immutable public shapes without importing each other.
-"""
-
-from __future__ import annotations
-
-import re
-from dataclasses import dataclass
-
-
-PATH_MATCH_TYPES = ("exact", "prefix", "regex")
-HEADER_MATCH_TYPES = ("exact", "regex")
-VALID_METHODS = frozenset({
-    "GET", "HEAD", "POST", "PUT", "DELETE", "PATCH", "OPTIONS", "TRACE",
-    "CONNECT",
-})
-
-LOG_OFF = 0
-LOG_BLOCKS = 1
-LOG_FULL = 2
-
-
-@dataclass(frozen=True)
-class PathMatch:
-    type: str
-    value: str
-    compiled: re.Pattern[str] | None = None
-
-
-@dataclass(frozen=True)
-class HeaderMatch:
-    name: str
-    value: str
-    type: str = "exact"
-    compiled: re.Pattern[str] | None = None
-
-
-@dataclass(frozen=True)
-class MatchEntry:
-    paths: tuple[PathMatch, ...] = ()
-    methods: tuple[str, ...] = ()
-    headers: tuple[HeaderMatch, ...] = ()
-
-
-@dataclass(frozen=True)
-class Route:
-    host: str
-    matches: tuple[MatchEntry, ...] = ()
-    auth_scheme: str = ""
-    token_env: str = ""
-    git_fetch: bool = False
-    outbound_detectors: tuple[str, ...] | None = None
-    inbound_detectors: tuple[str, ...] | None = None
-    outbound_on_match: str = ""
-    preserve_auth: bool = False
-    inspect: bool = True
-
-
-@dataclass(frozen=True)
-class Config:
-    routes: tuple[Route, ...]
-    log: int = LOG_OFF
-    deny_reason: str = ""
-
-
-@dataclass(frozen=True)
-class Decision:
-    action: str
-    reason: str = ""
-    inject_authorization: str | None = None
-
-
-@dataclass(frozen=True)
-class ScanResult:
-    severity: str
-    reason: str
-    location: str = ""
-    context: str = ""
-    matched: str = ""

bot_bottle/gateway/supervisor/server.py

@@ -58,9 +58,9 @@ import typing
 from dataclasses import dataclass
 
 from bot_bottle.constants import IDENTITY_HEADER
-from bot_bottle.gateway.egress.context import resolve_client_context
-from bot_bottle.gateway.egress.schema import load_config, route_to_yaml_dict
-from bot_bottle.gateway.egress.types import LOG_OFF
+from bot_bottle.gateway.egress.addon_core import (
+    LOG_OFF, load_config, resolve_client_context, route_to_yaml_dict,
+)
 from bot_bottle.gateway.policy_resolver import PolicyResolveError, PolicyResolver
 from bot_bottle.supervisor import types as _sv
 

bot_bottle/orchestrator/__main__.py

@@ -17,10 +17,7 @@ from pathlib import Path
 
 from .. import log
 from .store.store_manager import StoreManager
-from ..paths import LAUNCH_BROKER_KEY_ENV
-from .broker import StubBroker, SubmitBroker
-from .broker_client import BrokerClient
-from .host_server import DEFAULT_PORT, broker_secret
+from .broker import LaunchBroker, StubBroker
 from .server import make_server
 from .docker_broker import DockerBroker
 from .store.registry_store import RegistryStore, default_db_path
@@ -37,13 +34,8 @@ def main(argv: list[str] | None = None) -> int:
         help=f"registry DB path (default: {default_db_path()})",
     )
     parser.add_argument(
-        "--broker", choices=("stub", "docker", "http"), default="stub",
-        help="launch broker: 'stub' records requests; 'docker' runs containers "
-             "in-process; 'http' relays signed requests to a host control server",
-    )
-    parser.add_argument(
-        "--host-controller-url", default=f"http://127.0.0.1:{DEFAULT_PORT}",
-        help="host control server URL (used only with --broker http)",
+        "--broker", choices=("stub", "docker"), default="stub",
+        help="launch broker: 'stub' records requests; 'docker' runs containers",
     )
     args = parser.parse_args(argv)
 
@@ -55,27 +47,11 @@ def main(argv: list[str] | None = None) -> int:
     # operator reaches it over HTTP (never a second, disconnected DB).
     StoreManager(registry.db_path).migrate()
 
-    # A signing secret ties the orchestrator (signer) to its broker (verifier).
-    # 'stub' records launches instead of starting anything; 'docker' runs real
-    # containers in-process; 'http' relays signed requests to a separate host
-    # control server, which verifies and launches. For 'stub'/'docker' the secret
-    # is ephemeral (signer and verifier share this process). For 'http' it must be
-    # the SAME key the host controller holds — and this process is the *guest*
-    # (signer), so it must be given that key by injection, NOT mint its own
-    # process-local one (which would diverge from the host's and 401 every launch).
-    broker: SubmitBroker
-    if args.broker == "http":
-        secret = broker_secret()  # env-injected only; no host-file fallback here
-        if secret is None:
-            parser.error(
-                f"--broker http requires the launch-broker key injected as "
-                f"${LAUNCH_BROKER_KEY_ENV} (the host controller owns/mints it); the "
-                "orchestrator must not mint its own or it would diverge from the host's"
-            )
-        broker = BrokerClient(args.host_controller_url)
-    else:
-        secret = secrets.token_bytes(32)
-        broker = DockerBroker(secret) if args.broker == "docker" else StubBroker(secret)
+    # An ephemeral signing secret ties the orchestrator (signer) to its
+    # broker (verifier). 'stub' records launches instead of starting
+    # anything; 'docker' runs real containers (firecracker drops in later).
+    secret = secrets.token_bytes(32)
+    broker: LaunchBroker = DockerBroker(secret) if args.broker == "docker" else StubBroker(secret)
     orchestrator = OrchestratorCore(registry, broker, secret)
 
     server = make_server(orchestrator, host=args.host, port=args.port)

bot_bottle/orchestrator/broker.py

@@ -29,7 +29,6 @@ import json
 import secrets
 import time
 from dataclasses import dataclass
-from typing import Protocol
 
 _JWT_HEADER = {"alg": "HS256", "typ": "JWT"}
 _ALLOWED_OPS = ("launch", "teardown")
@@ -38,21 +37,7 @@ _ALLOWED_OPS = ("launch", "teardown")
 class BrokerAuthError(Exception):
     """A broker request failed provenance or schema verification —
     bad/absent signature, malformed token, or a payload that doesn't match
-    the fixed launch-request shape. Fail-closed: the broker must not act.
-
-    A **definite** negative: nothing was launched, so a caller may safely roll
-    back as if the op never happened."""
-
-
-class BrokerUnavailableError(Exception):
-    """A brokered request could not be carried to a verdict: the broker (or the
-    wire to it) was unreachable, timed out, or dropped the response.
-
-    Crucially **ambiguous** — unlike `BrokerAuthError`, the op MAY already have
-    taken effect on the backend before the response was lost, so a caller must
-    NOT assume it did nothing (e.g. must not roll a registry row back as if no
-    launch happened, which would orphan a running container). Only the in-process
-    brokers never raise this; the out-of-process `BrokerClient` does."""
+    the fixed launch-request shape. Fail-closed: the broker must not act."""
 
 
 @dataclass(frozen=True)
@@ -138,16 +123,6 @@ def verify_request(token: str, secret: bytes) -> LaunchRequest:
 
 # --- the broker itself ------------------------------------------------------
 
-class SubmitBroker(Protocol):
-    """The single method `OrchestratorCore` depends on: verify a signed token and
-    perform its op, returning the verified request. Both the in-process
-    `LaunchBroker` and the out-of-process `BrokerClient` (which relays the token
-    to the host control server) satisfy it structurally, so the core is unchanged
-    whether the backend is local or a real host service."""
-
-    def submit(self, token: str) -> LaunchRequest: ...
-
-
 class LaunchBroker(abc.ABC):
     """Verifies a signed request came from the orchestrator, then performs
     the backend-native launch/teardown. Subclasses implement `_launch` /
@@ -193,9 +168,7 @@ class StubBroker(LaunchBroker):
 
 __all__ = [
     "BrokerAuthError",
-    "BrokerUnavailableError",
     "LaunchRequest",
-    "SubmitBroker",
     "LaunchBroker",
     "StubBroker",
     "sign_request",

bot_bottle/orchestrator/broker_client.py

@@ -1,126 +0,0 @@
-"""Orchestrator-side broker transport (issue #468, chunk 1).
-
-The signer's half of the launch-broker transport gap. `BrokerClient` satisfies
-the exact `submit(token)` contract `OrchestratorCore` already depends on (see
-`broker.SubmitBroker`), but instead of verifying and launching in-process it POSTs
-the signed token to the host control server over HTTP (stdlib `urllib`, like
-`orchestrator/client.py`). Because it is drop-in for that interface, wiring a real
-out-of-process backend does not change the core: it still signs a request and
-calls `submit()`; only the wire is new.
-
-A provenance/schema rejection from the host controller (HTTP 401) is re-raised as
-the same `BrokerAuthError` the in-process broker raises, so the launch path's
-rollback-on-failure (`OrchestratorCore.launch_bottle`) behaves identically whether
-the broker is local or remote.
-"""
-
-from __future__ import annotations
-
-import json
-import urllib.error
-import urllib.request
-
-from .broker import BrokerAuthError, BrokerUnavailableError, LaunchRequest
-
-DEFAULT_TIMEOUT_SECONDS = 5.0
-
-
-class BrokerClientError(RuntimeError):
-    """The host control server *responded*, but with an unexpected status other
-    than the fail-closed 401 (which surfaces as `BrokerAuthError`) — e.g. a 502
-    backend failure or a malformed body. A definite negative: the host processed
-    the request and it did not launch. (A *no-response* failure — unreachable /
-    timeout / dropped — is the ambiguous `BrokerUnavailableError` instead.)"""
-
-
-class BrokerClient:
-    """Drop-in `submit(token)` that relays a signed request to the host control
-    server. Holds no secret — provenance rides entirely in the signed token, so a
-    caller that can reach this client still cannot forge a launch."""
-
-    def __init__(self, base_url: str, *, timeout: float = DEFAULT_TIMEOUT_SECONDS) -> None:
-        self._base = base_url.rstrip("/")
-        self._timeout = timeout
-
-    def submit(self, token: str) -> LaunchRequest:
-        """POST the signed token to the host controller and return the request it
-        verified and acted on.
-
-        Raises `BrokerAuthError` on a fail-closed 401 (bad provenance/schema —
-        the same exception the in-process broker raises); `BrokerClientError` if
-        the host *responds* with any other non-success status or a malformed
-        body (a definite negative); or `BrokerUnavailableError` if no response is
-        obtained (unreachable / timeout / dropped) — the **ambiguous** case, where
-        the host may already have acted, so the caller must not roll back."""
-        data = json.dumps({"token": token}).encode()
-        req = urllib.request.Request(
-            f"{self._base}/broker", data=data, method="POST",
-            headers={"Content-Type": "application/json"},
-        )
-        try:
-            with urllib.request.urlopen(req, timeout=self._timeout) as resp:
-                return _request_from(_json_object(resp.read()))
-        except urllib.error.HTTPError as e:
-            detail = _error_detail(e)
-            if e.code == 401:
-                raise BrokerAuthError(
-                    detail or "host controller rejected the request"
-                ) from e
-            raise BrokerClientError(
-                f"POST /broker: HTTP {e.code} {detail}".rstrip()
-            ) from e
-        except (urllib.error.URLError, TimeoutError, OSError) as e:
-            # No usable response — unreachable, timed out, or the connection
-            # dropped mid-exchange. Ambiguous: the request may already have
-            # launched the bottle, so this is NOT a definite failure.
-            raise BrokerUnavailableError(f"POST /broker: {e}") from e
-
-
-def _json_object(raw: bytes) -> dict[str, object]:
-    """Parse a JSON object, tolerating an empty or malformed body (→ {}), like
-    the orchestrator client — a bad body becomes a clean 'missing field' error
-    downstream rather than an opaque JSON crash."""
-    if not raw:
-        return {}
-    try:
-        obj = json.loads(raw)
-    except ValueError:
-        return {}
-    return obj if isinstance(obj, dict) else {}
-
-
-def _error_detail(e: urllib.error.HTTPError) -> str:
-    """The `error` string from a structured error response, best-effort — an
-    error body may be absent or unreadable, in which case there is no detail."""
-    try:
-        detail = _json_object(e.read()).get("error", "")
-    except Exception:  # noqa: BLE001 — the error body is advisory only
-        return ""
-    return detail if isinstance(detail, str) else ""
-
-
-def _request_from(payload: dict[str, object]) -> LaunchRequest:
-    """Reconstruct the verified `LaunchRequest` the controller echoed, so the
-    returned value matches the in-process broker's (which returns the request it
-    acted on). A missing op/bottle_id means a malformed response."""
-    op = payload.get("op")
-    bottle_id = payload.get("bottle_id")
-    if not isinstance(op, str) or not isinstance(bottle_id, str) or not bottle_id:
-        raise BrokerClientError("host controller response missing op/bottle_id")
-    source_ip = payload.get("source_ip")
-    image_ref = payload.get("image_ref")
-    slot = payload.get("slot")
-    return LaunchRequest(
-        op=op,
-        bottle_id=bottle_id,
-        source_ip=source_ip if isinstance(source_ip, str) else "",
-        image_ref=image_ref if isinstance(image_ref, str) else "",
-        slot=slot if isinstance(slot, int) and not isinstance(slot, bool) else None,
-    )
-
-
-__all__ = [
-    "BrokerClient",
-    "BrokerClientError",
-    "DEFAULT_TIMEOUT_SECONDS",
-]

bot_bottle/orchestrator/client.py

@@ -18,7 +18,6 @@ import urllib.request
 from collections.abc import Iterable
 from dataclasses import dataclass
 
-from ..log import debug
 from ..orchestrator_auth import ROLE_CLI
 from ..trust_domain import CONTROL_PLANE
 from .server import ORCHESTRATOR_AUTH_HEADER
@@ -54,23 +53,6 @@ class RegisteredBottle:
     env_var_secret: str = ""
 
 
-@dataclass(frozen=True)
-class BackendProbeFailure:
-    """Safe diagnostic for an optional backend discovery probe."""
-
-    backend: str
-    error_type: str
-
-
-def _probe_failure(backend: str, exc: BaseException) -> BackendProbeFailure:
-    failure = BackendProbeFailure(backend, type(exc).__name__)
-    debug(
-        "orchestrator discovery probe unavailable",
-        context={"backend": failure.backend, "error_type": failure.error_type},
-    )
-    return failure
-
-
 class OrchestratorClient:
     """Trusted host-side client for the orchestrator control plane.
 
@@ -263,41 +245,32 @@ def discover_orchestrator_url(*, timeout: float = 2.0) -> str:
     orchestrator TAP. Returns the first that answers `/health`; raises if none
     do (no orchestrator up — launch a bottle first)."""
     candidates: list[str] = []
-    failures: list[BackendProbeFailure] = []
     try:  # docker: loopback-published control plane
         from .lifecycle import DEFAULT_PORT as _DOCKER_PORT
         candidates.append(f"http://127.0.0.1:{_DOCKER_PORT}")
-    except Exception as exc:  # noqa: BLE001 — backend optional
-        failures.append(_probe_failure("docker", exc))
+    except Exception:  # noqa: BLE001 — backend optional
         candidates.append("http://127.0.0.1:8099")
     try:  # firecracker: infra VM control plane on the orchestrator TAP
         from ..backend.firecracker import netpool
         from ..backend.firecracker.infra_vm import ORCHESTRATOR_PORT
         candidates.append(
             f"http://{netpool.orch_slot().guest_ip}:{ORCHESTRATOR_PORT}")
-    except Exception as exc:  # noqa: BLE001 — backend optional / not firecracker
-        failures.append(_probe_failure("firecracker", exc))
+    except Exception:  # noqa: BLE001 — backend optional / not firecracker
+        pass
     try:  # macOS: orchestrator container on its host-only address
         from ..backend.macos_container.infra import probe_orchestrator_url
         url = probe_orchestrator_url()
         if url:
             candidates.append(url)
-    except Exception as exc:  # noqa: BLE001 — backend optional / not macOS
-        failures.append(_probe_failure("macos-container", exc))
+    except Exception:  # noqa: BLE001 — backend optional / not macOS
+        pass
     for url in candidates:
         if OrchestratorClient(url, timeout=timeout).health():
             return url
-    detail = ""
-    if failures:
-        detail = "; optional probes unavailable: " + ", ".join(
-            f"{failure.backend} ({failure.error_type})" for failure in failures
-        )
     raise OrchestratorClientError(
         "no running orchestrator control plane found (tried "
         + ", ".join(candidates)
-        + ")"
-        + detail
-        + "; launch a bottle first"
+        + "); launch a bottle first"
     )
 
 

bot_bottle/orchestrator/host_server.py

@@ -1,287 +0,0 @@
-"""Host control server (issue #468) — the launch broker as a real host service.
-
-Chunk 1 of the host-control-server stack closes the **transport** gap the PRD
-opens with: today `LaunchBroker.submit(token)` is an in-process method call from
-`OrchestratorCore`, and a real host service needs it reachable over the wire.
-This module is that service — the single privileged host component — reached over
-**HTTP** (the universal transport 0070 chose), mirroring the orchestrator control
-plane's shape (`orchestrator/server.py`): a pure `dispatch()` for socket-free
-testing, wrapped by a thin stdlib `http.server` adapter.
-
-    GET  /health  -> 200 {"status": "ok"}
-    POST /broker  -> 200 {"op", "bottle_id", "source_ip", "image_ref", "slot"}
-                     400 (bad body) | 401 (bad provenance/schema) | 502 (backend)
-                     body: {"token": "<signed launch/teardown JWT>"}
-
-Only the **signed token** crosses the wire; the server holds the shared HS256
-secret and a real `LaunchBroker` (e.g. `DockerBroker`) and runs the existing
-`verify_request` + `_launch`/`_teardown` path behind the endpoint, so nothing
-free-form ever reaches it. Provenance/schema failures are fail-closed 401s that
-never touch the backend (`LaunchBroker.submit` verifies before acting), and a
-backend launch failure is a 502 the caller must surface — neither takes the
-controller down.
-
-The signed launch token *is* the endpoint's authentication (its provenance is the
-whole point of the JWS), so `/broker` needs no separate caller credential; the
-host controller's own lifecycle endpoints, which do, arrive with the `host`-role
-tokens of the separate `HOST_CONTROLLER` trust domain in a later chunk.
-
-The shared signing secret is the durable **launch-broker `TrustDomain` key**
-(#468/#476): a host-canonical key file minted 0600 on first use, provisioned to
-the orchestrator (signer) and this server (verifier). A backend launcher injects
-it via `$BOT_BOTTLE_LAUNCH_BROKER_KEY`; a host-side dev-harness process reads the
-key file directly. Durability is the point — a restarted orchestrator re-verifies
-against the same key, so re-adoption works.
-"""
-
-from __future__ import annotations
-
-import argparse
-import http.server
-import json
-import os
-import socketserver
-import sys
-import typing
-from urllib.parse import urlsplit
-
-from .. import log
-from ..paths import LAUNCH_BROKER_KEY_ENV
-from ..trust_domain import LAUNCH_BROKER
-from .broker import BrokerAuthError, LaunchBroker
-from .docker_broker import DockerBroker
-
-# JSON body payload type (parsed request / rendered response).
-Json = dict[str, object]
-
-# Default host-controller port. Distinct from the orchestrator control plane
-# (8099) — a separate privileged component listening on its own socket.
-DEFAULT_PORT = 8091
-
-# Cap on the request body. A signed broker request is tiny, so rejecting anything
-# larger *before reading it* keeps a caller that can merely reach the socket (no
-# signed token needed) from exhausting memory or a handler thread with a huge
-# Content-Length — the signed token, not mere reachability, is the authority.
-MAX_BODY_BYTES = 64 * 1024
-
-# Per-request socket timeout, bounding how long a stalled / slow-loris caller can
-# hold a handler thread on this privileged listener.
-REQUEST_TIMEOUT_SECONDS = 15
-
-
-def _parse_json_object(body: bytes) -> Json:
-    """Parse a JSON object body. Raises ValueError for non-objects / bad JSON."""
-    if not body:
-        return {}
-    obj = json.loads(body)  # raises json.JSONDecodeError (a ValueError)
-    if not isinstance(obj, dict):
-        raise ValueError("request body must be a JSON object")
-    return obj
-
-
-def broker_secret(
-    environ: typing.Mapping[str, str] | None = None, *, allow_host_file: bool = False,
-) -> bytes | None:
-    """The shared launch-broker HS256 secret, as this process should use it.
-
-    Always prefers the key injected into this process's env
-    (`$BOT_BOTTLE_LAUNCH_BROKER_KEY`). `allow_host_file` decides the fallback when
-    it is absent, and the distinction is a security boundary:
-
-    - **Host-side** processes — the host controller and the host dev-harness — pass
-      ``allow_host_file=True`` to read (minting on first use) the durable host key
-      file (``bot_bottle_root()/launch-broker-key``) they legitimately own.
-    - The **guest orchestrator** (``--broker http``) keeps the default ``False``.
-      It runs inside a container/VM whose ``bot_bottle_root()`` is process-local,
-      so minting a file there would silently create a key UNRELATED to the host
-      controller's — startup would succeed but every launch would be rejected 401.
-      It must instead be *given* the key by its launcher, and fail closed (None)
-      if it wasn't, rather than diverge.
-
-    None when no key is available (a guest with no injection, or an unwritable
-    host root)."""
-    key = LAUNCH_BROKER.key_from_env(environ)
-    if not key and allow_host_file:
-        try:
-            key = LAUNCH_BROKER.signing_key()  # host-canonical, minted on first use
-        except OSError:
-            return None
-    return key.encode("utf-8") if key else None
-
-
-def dispatch(  # pylint: disable=too-many-return-statements
-    broker: LaunchBroker, method: str, path: str, body: bytes,
-) -> tuple[int, Json]:
-    """Route one host-control request to a (status, payload) pair. Pure — the
-    only side effect is the broker's own backend launch — so routing is testable
-    without a socket.
-
-    Total by design: a provenance/schema failure becomes 401 and a backend launch
-    failure becomes 502 rather than raising, so one bad request can neither act
-    on the backend nor take the controller down for the next caller."""
-    route = urlsplit(path).path.rstrip("/") or "/"
-
-    if method == "GET" and route == "/health":
-        return 200, {"status": "ok"}
-
-    if method == "POST" and route == "/broker":
-        try:
-            data = _parse_json_object(body)
-        except ValueError as e:
-            return 400, {"error": f"invalid JSON: {e}"}
-        token = data.get("token")
-        if not isinstance(token, str) or not token:
-            return 400, {"error": "token (string) is required"}
-        try:
-            req = broker.submit(token)
-        except BrokerAuthError as e:
-            # Fail-closed: bad signature, malformed token, or off-schema payload.
-            # `submit` verifies before acting, so nothing was launched.
-            return 401, {"error": f"broker auth failed: {e}"}
-        except Exception as e:  # noqa: BLE001 — a backend launch failure (docker
-            # down, image gone) is operational, not a control-plane bug; the
-            # caller must see it as a distinct 502, and the server must stay up.
-            return 502, {"error": f"backend launch failed: {e}"}
-        return 200, {
-            "op": req.op,
-            "bottle_id": req.bottle_id,
-            "source_ip": req.source_ip,
-            "image_ref": req.image_ref,
-            "slot": req.slot,
-        }
-
-    return 404, {"error": "not found"}
-
-
-class Handler(http.server.BaseHTTPRequestHandler):
-    """Thin stdlib adapter: read the body, call `dispatch`, write JSON."""
-
-    # Socket timeout per request (applied by StreamRequestHandler.setup) so a
-    # stalled caller can't pin a handler thread on this privileged listener.
-    timeout = REQUEST_TIMEOUT_SECONDS
-
-    # Quiet by default; opt back into stdlib access logging with
-    # BOT_BOTTLE_HOST_CONTROLLER_DEBUG (the controller has its own logging).
-    def log_message(self, format: str, *args: typing.Any) -> None:  # noqa: A002
-        if os.environ.get("BOT_BOTTLE_HOST_CONTROLLER_DEBUG"):
-            super().log_message(format, *args)
-
-    def _serve(self, method: str) -> None:
-        """Read the request body (bounded), dispatch it, and write the JSON
-        reply. A dispatch that raises (it shouldn't — dispatch is total) still
-        returns a 500 rather than dropping the connection."""
-        server = self.server
-        assert isinstance(server, HostControlServer)
-        try:
-            length = int(self.headers.get("Content-Length") or 0)
-        except ValueError:
-            self._reply(400, {"error": "invalid Content-Length"})
-            return
-        if length < 0 or length > MAX_BODY_BYTES:
-            # Reject before reading: nothing legitimate is this big, so an
-            # oversized declared length is a bug or a resource-exhaustion attempt.
-            self._reply(413, {"error": "request body too large"})
-            return
-        body = self.rfile.read(length) if length > 0 else b""
-        try:
-            status, payload = dispatch(server.broker, method, self.path, body)
-        except Exception as e:  # noqa: BLE001 — the controller must stay up
-            sys.stderr.write(f"host controller: {method} {self.path} failed: {e!r}\n")
-            sys.stderr.flush()
-            status, payload = 500, {"error": f"internal error: {e}"}
-        self._reply(status, payload)
-
-    def _reply(self, status: int, payload: typing.Mapping[str, object]) -> None:
-        """Write one JSON response with an explicit Content-Length."""
-        data = json.dumps(payload).encode()
-        self.send_response(status)
-        self.send_header("Content-Type", "application/json")
-        self.send_header("Content-Length", str(len(data)))
-        self.end_headers()
-        self.wfile.write(data)
-
-    def do_GET(self) -> None:
-        self._serve("GET")
-
-    def do_POST(self) -> None:
-        self._serve("POST")
-
-
-class HostControlServer(socketserver.ThreadingMixIn, http.server.HTTPServer):
-    """Threading HTTP server that carries the launch broker for its handlers.
-
-    The broker holds the shared signing secret and performs the backend-native
-    launch/teardown; the server itself keeps no secret of its own — provenance
-    rides entirely in each request's signed token."""
-
-    daemon_threads = True
-    allow_reuse_address = True
-
-    def __init__(self, address: tuple[str, int], broker: LaunchBroker) -> None:
-        self.broker = broker
-        super().__init__(address, Handler)
-
-
-def make_host_server(
-    broker: LaunchBroker, host: str = "127.0.0.1", port: int = DEFAULT_PORT
-) -> HostControlServer:
-    """Build (but do not start) a host control server. `port=0` binds an
-    ephemeral port — read `server.server_address` for the actual one."""
-    return HostControlServer((host, port), broker)
-
-
-def main(argv: list[str] | None = None) -> int:
-    """Run the host control server as a plain process (dev-harness).
-
-        python -m bot_bottle.orchestrator.host_server [--host H] [--port P]
-
-    Fail-closed: without the launch-broker key the server can verify no request's
-    provenance, so it refuses to start rather than run a launcher that accepts
-    unsigned input. As the host-side owner of the key, it may mint/read the host
-    key file (`allow_host_file=True`)."""
-    parser = argparse.ArgumentParser(prog="bot_bottle.orchestrator.host_server")
-    parser.add_argument("--host", default="127.0.0.1", help="bind address")
-    parser.add_argument("--port", type=int, default=DEFAULT_PORT, help="bind port (0 = ephemeral)")
-    args = parser.parse_args(argv)
-
-    secret = broker_secret(allow_host_file=True)
-    if secret is None:
-        sys.stderr.write(
-            f"host controller: refusing to start without the launch-broker key "
-            f"(${LAUNCH_BROKER_KEY_ENV}, or a writable host root to mint it) — it "
-            "could verify no request's provenance and would relay unsigned "
-            "launches to the backend\n"
-        )
-        sys.stderr.flush()
-        return 2
-
-    broker = DockerBroker(secret)
-    server = make_host_server(broker, host=args.host, port=args.port)
-    bound_host, bound_port = server.server_address[0], server.server_address[1]
-    log.info(
-        "host control server listening",
-        context={"host": bound_host, "port": bound_port},
-    )
-    try:
-        server.serve_forever()
-    except KeyboardInterrupt:
-        log.info("host controller shutting down")
-    finally:
-        server.server_close()
-    return 0
-
-
-__all__ = [
-    "dispatch",
-    "Handler",
-    "HostControlServer",
-    "make_host_server",
-    "broker_secret",
-    "main",
-    "Json",
-    "DEFAULT_PORT",
-]
-
-
-if __name__ == "__main__":
-    raise SystemExit(main())

bot_bottle/orchestrator/reprovision.py

@@ -2,7 +2,6 @@
 
 from __future__ import annotations
 
-from ..log import debug
 from .client import OrchestratorClient, OrchestratorClientError
 
 
@@ -28,14 +27,7 @@ def reprovision_bottles(
         try:
             if client.reprovision_gateway(bottle_id, secret):
                 restored += 1
-        except OrchestratorClientError as exc:
-            debug(
-                "gateway secret reprovision failed; continuing with other bottles",
-                context={
-                    "bottle_id": bottle_id,
-                    "error_type": type(exc).__name__,
-                },
-            )
+        except OrchestratorClientError:
             continue
     return restored
 

bot_bottle/orchestrator/server.py

@@ -57,7 +57,6 @@ from __future__ import annotations
 
 import http.server
 import json
-import math
 import os
 import socketserver
 import sys
@@ -218,18 +217,13 @@ def dispatch(  # pylint: disable=too-many-return-statements,too-many-branches
         raw_ips = data.get("live_source_ips")
         if not isinstance(raw_ips, list):
             return 400, {"error": "live_source_ips (list of strings) is required"}
-        if any(not isinstance(ip, str) or not ip for ip in raw_ips):
-            return 400, {"error": "live_source_ips must contain non-empty strings"}
-        live = raw_ips
+        live = [ip for ip in raw_ips if isinstance(ip, str) and ip]
         grace = data.get("grace_seconds")
-        kwargs: dict[str, float] = {}
-        if grace is not None:
-            if isinstance(grace, bool) or not isinstance(grace, (int, float)):
-                return 400, {"error": "grace_seconds must be a non-negative finite number"}
-            parsed_grace = float(grace)
-            if not math.isfinite(parsed_grace) or parsed_grace < 0:
-                return 400, {"error": "grace_seconds must be a non-negative finite number"}
-            kwargs["grace_seconds"] = parsed_grace
+        kwargs = (
+            {"grace_seconds": float(grace)}
+            if isinstance(grace, (int, float)) and not isinstance(grace, bool)
+            else {}
+        )
         return 200, {"reaped": orch.reconcile(live, **kwargs)}
 
     if method == "POST" and route == "/attribute":
@@ -379,15 +373,9 @@ class Handler(http.server.BaseHTTPRequestHandler):
             status, payload = dispatch(
                 server.orchestrator, method, self.path, body, role=role)
         except Exception as e:  # noqa: BLE001 — the control plane must stay up
-            # Do not echo exception messages to the caller or logs: broker and
-            # persistence exceptions can contain request data. The operation,
-            # route, and exception type are enough to correlate a traceback.
-            sys.stderr.write(
-                f"orchestrator: {method} {self.path} failed "
-                f"[error_type={type(e).__name__}]\n"
-            )
+            sys.stderr.write(f"orchestrator: {method} {self.path} failed: {e!r}\n")
             sys.stderr.flush()
-            status, payload = 500, {"error": "internal error"}
+            status, payload = 500, {"error": f"internal error: {e}"}
         data = json.dumps(payload).encode()
         self.send_response(status)
         self.send_header("Content-Type", "application/json")

bot_bottle/orchestrator/service.py

@@ -25,7 +25,7 @@ import json
 from collections.abc import Iterable
 from datetime import datetime, timezone
 
-from .broker import BrokerUnavailableError, LaunchRequest, SubmitBroker, sign_request
+from .broker import LaunchBroker, LaunchRequest, sign_request
 from .store.registry_store import DEFAULT_REAP_GRACE_SECONDS, BottleRecord, RegistryStore
 from .supervisor import (
     AuditEntry,
@@ -62,7 +62,7 @@ class OrchestratorCore:
     def __init__(
         self,
         registry: RegistryStore,
-        broker: SubmitBroker,
+        broker: LaunchBroker,
         sign_secret: bytes,
         supervisor: Supervisor | None = None,
     ) -> None:
@@ -111,23 +111,14 @@ class OrchestratorCore:
             image_ref=image_ref,
             slot=slot,
         )
+        launched = False
         try:
             self._broker.submit(sign_request(req, self._secret))
-        except BrokerUnavailableError:
-            # Ambiguous delivery failure (timeout / dropped response): the broker
-            # may already have launched the bottle before the response was lost.
-            # Do NOT deregister — that would orphan a running container with no
-            # registry row (reconcile reaps rows, never containers). Keep the row
-            # so reconcile reaps it iff the bottle is not actually live; surface
-            # the error so the caller knows the launch is unconfirmed.
-            raise
-        except Exception:
-            # A definite failure — a fail-closed rejection, a backend launch
-            # error, or the host reporting it did not launch: nothing is running,
-            # so roll the registry entry back to leave no orphan.
-            self.registry.deregister(rec.bottle_id)
-            self._tokens.pop(rec.bottle_id, None)
-            raise
+            launched = True
+        finally:
+            if not launched:
+                self.registry.deregister(rec.bottle_id)
+                self._tokens.pop(rec.bottle_id, None)
         return rec
 
     def teardown_bottle(self, bottle_id: str) -> bool:

bot_bottle/orchestrator/store/secret_store.py

@@ -12,22 +12,12 @@ reattachment path reads ENV_VAR_SECRET from the running agent container via
 ``POST /bottles/<id>/reprovision_gateway``; the orchestrator decrypts the
 stored rows and re-populates ``_tokens``.
 
-Encryption scheme: HMAC-SHA256 used as a PRF in CTR mode, **authenticated**
-encrypt-then-MAC (stdlib-only, no external deps). Each value is encrypted
-independently. The output blob is ``nonce (16 bytes) || ciphertext || tag
-(32 bytes)`` encoded as URL-safe base64 (no padding).
+Encryption scheme: HMAC-SHA256 used as a PRF in CTR mode (stdlib-only,
+no external deps). Each value is encrypted independently. The output blob is
+``nonce (16 bytes) || ciphertext`` encoded as URL-safe base64 (no padding).
 
     keystream_block_i = HMAC-SHA256(key, nonce || i.to_bytes(4, "big"))
     ciphertext_i      = plaintext_i XOR keystream_block_i[:len(plaintext_i)]
-    mac_key           = HMAC-SHA256(key, "bottled-secret-mac-v1")
-    tag               = HMAC-SHA256(mac_key, nonce || ciphertext)
-
-The tag is what makes a **wrong key deterministically detectable**: without it,
-CTR decryption with the wrong key yields garbage that only fails when it isn't
-valid UTF-8 (so ``reprovision`` would sometimes "succeed" with a wrong
-ENV_VAR_SECRET and inject garbage egress tokens). The MAC key is derived from
-the ENV_VAR_SECRET by a domain-separated HMAC so the same key never both
-generates the keystream and signs the tag with the same message shape.
 """
 
 from __future__ import annotations
@@ -39,7 +29,6 @@ import secrets
 
 _KEY_BYTES = 32    # 256-bit key from ENV_VAR_SECRET
 _NONCE_BYTES = 16  # 128-bit random nonce per encrypt call
-_TAG_BYTES = 32    # HMAC-SHA256 authentication tag
 _BLOCK = 32        # HMAC-SHA256 output width == one keystream block
 
 # Env-var name the agent container receives at startup.
@@ -61,58 +50,45 @@ def _keystream(key: bytes, nonce: bytes, block_index: int) -> bytes:
     ).digest()
 
 
-def _tag(key: bytes, nonce: bytes, ciphertext: bytes) -> bytes:
-    """The authentication tag over ``nonce || ciphertext``, keyed by a MAC
-    subkey domain-separated from the keystream key."""
-    mac_key = hmac.new(key, b"bottled-secret-mac-v1", hashlib.sha256).digest()
-    return hmac.new(mac_key, nonce + ciphertext, hashlib.sha256).digest()
-
-
-def _ctr(key: bytes, nonce: bytes, data: bytes) -> bytes:
-    """CTR keystream XOR — its own inverse, so it both encrypts and decrypts."""
-    out = bytearray()
-    for i in range(0, len(data), _BLOCK):
-        chunk = data[i : i + _BLOCK]
-        ks = _keystream(key, nonce, i)[: len(chunk)]
-        out.extend(b ^ k for b, k in zip(chunk, ks))
-    return bytes(out)
-
-
 def encrypt_value(secret_b64: str, plaintext: str) -> str:
     """Encrypt a single string value with *secret_b64* (the ENV_VAR_SECRET).
 
-    Returns a URL-safe base64 blob ``nonce || ciphertext || tag`` suitable for
+    Returns a URL-safe base64 blob ``nonce || ciphertext`` suitable for
     the ``bottled_agent_secrets.value`` column."""
     key = _b64dec(secret_b64)
+    pt = plaintext.encode()
     nonce = secrets.token_bytes(_NONCE_BYTES)
-    ct = _ctr(key, nonce, plaintext.encode())
-    tag = _tag(key, nonce, ct)
-    return base64.urlsafe_b64encode(nonce + ct + tag).rstrip(b"=").decode()
+    ct = bytearray()
+    for i in range(0, len(pt), _BLOCK):
+        chunk = pt[i : i + _BLOCK]
+        ks = _keystream(key, nonce, i)[: len(chunk)]
+        ct.extend(p ^ k for p, k in zip(chunk, ks))
+    return base64.urlsafe_b64encode(nonce + bytes(ct)).rstrip(b"=").decode()
 
 
 def decrypt_value(secret_b64: str, blob_b64: str) -> str:
     """Decrypt a blob produced by :func:`encrypt_value`.
 
     Returns the original plaintext string. Raises ``ValueError`` for malformed
-    input, a **wrong key**, or a tampered ciphertext — all caught by the
-    authentication tag before any plaintext is returned, so a wrong
-    ENV_VAR_SECRET is rejected deterministically (never a garbage token)."""
+    input or a key mismatch (wrong key produces garbage, not an error, unless
+    the plaintext is non-UTF-8 — treat all such failures as wrong key)."""
     key = _b64dec(secret_b64)
     try:
         blob = _b64dec(blob_b64)
     except Exception as exc:
         raise ValueError(f"invalid ciphertext blob: {exc}") from exc
-    if len(blob) < _NONCE_BYTES + _TAG_BYTES:
+    if len(blob) < _NONCE_BYTES:
         raise ValueError("ciphertext blob too short")
-    nonce = blob[:_NONCE_BYTES]
-    tag = blob[-_TAG_BYTES:]
-    ciphertext = blob[_NONCE_BYTES:-_TAG_BYTES]
-    if not hmac.compare_digest(tag, _tag(key, nonce, ciphertext)):
-        raise ValueError("ciphertext failed authentication (wrong key or tampered)")
+    nonce, ciphertext = blob[:_NONCE_BYTES], blob[_NONCE_BYTES:]
+    pt = bytearray()
+    for i in range(0, len(ciphertext), _BLOCK):
+        chunk = ciphertext[i : i + _BLOCK]
+        ks = _keystream(key, nonce, i)[: len(chunk)]
+        pt.extend(c ^ k for c, k in zip(chunk, ks))
     try:
-        return _ctr(key, nonce, ciphertext).decode()
-    except UnicodeDecodeError as exc:  # pragma: no cover - authenticated, so unreachable
-        raise ValueError(f"decryption produced non-UTF-8 output: {exc}") from exc
+        return bytes(pt).decode()
+    except UnicodeDecodeError as exc:
+        raise ValueError(f"decryption produced non-UTF-8 output (wrong key?): {exc}") from exc
 
 
 __all__ = ["ENV_VAR_SECRET_NAME", "new_env_var_secret", "encrypt_value", "decrypt_value"]

bot_bottle/orchestrator_auth.py

@@ -36,13 +36,6 @@ ROLE_GATEWAY = "gateway"
 ROLE_CLI = "cli"
 ROLES: frozenset[str] = frozenset({ROLE_GATEWAY, ROLE_CLI})
 
-# The host controller's own lifecycle role (#468). Deliberately OUTSIDE `ROLES`:
-# it belongs to a separate trust domain (`HOST_CONTROLLER`) signed by a key the
-# orchestrator never holds, so the orchestrator's control-plane key can neither
-# mint nor accept it — the orchestrator must not be able to forge the credential
-# used to start and stop it.
-ROLE_HOST = "host"
-
 _ALG = "HS256"
 
 
@@ -110,4 +103,4 @@ def verify(token: str, secret: str, *, roles: frozenset[str] = ROLES) -> str | N
     return role if isinstance(role, str) and role in roles else None
 
 
-__all__ = ["ROLE_GATEWAY", "ROLE_CLI", "ROLE_HOST", "ROLES", "mint", "verify"]
+__all__ = ["ROLE_GATEWAY", "ROLE_CLI", "ROLES", "mint", "verify"]

bot_bottle/paths.py

@@ -47,22 +47,6 @@ ORCHESTRATOR_TOKEN_ENV = "BOT_BOTTLE_ORCHESTRATOR_TOKEN"
 # cannot forge a higher-privilege `cli` token (issue #469 review).
 ORCHESTRATOR_AUTH_JWT_ENV = "BOT_BOTTLE_ORCHESTRATOR_AUTH_JWT"
 
-# The durable launch-broker signing key: the HS256 secret the orchestrator
-# (signer) and the host control server (verifier) share to sign/verify launch
-# requests (#468). A host-canonical key file (minted 0600 on first use) so it
-# survives orchestrator restarts — re-adoption re-verifies against the same key —
-# instead of the ephemeral per-process secret of the in-process broker.
-LAUNCH_BROKER_KEY_FILENAME = "launch-broker-key"
-LAUNCH_BROKER_KEY_ENV = "BOT_BOTTLE_LAUNCH_BROKER_KEY"
-# The host controller's OWN key, for its lifecycle endpoints (the direct
-# cli -> host controller path that starts/stops the orchestrator). Separate from
-# the launch-broker key and never held by the orchestrator: the controller starts
-# and stops the orchestrator, so the orchestrator must not be able to mint the
-# credentials used to drive it (#468/#476).
-HOST_CONTROLLER_KEY_FILENAME = "host-controller-key"
-HOST_CONTROLLER_KEY_ENV = "BOT_BOTTLE_HOST_CONTROLLER_KEY"
-HOST_CONTROLLER_AUTH_JWT_ENV = "BOT_BOTTLE_HOST_CONTROLLER_AUTH_JWT"
-
 # The host directory holding the gateway's persistent mitmproxy CA. Bind-mounted
 # into the infra/gateway container at mitmproxy's confdir so the self-generated
 # CA survives container recreation — every agent installs this one CA to trust
@@ -158,11 +142,6 @@ __all__ = [
     "ORCHESTRATOR_TOKEN_FILENAME",
     "ORCHESTRATOR_TOKEN_ENV",
     "ORCHESTRATOR_AUTH_JWT_ENV",
-    "LAUNCH_BROKER_KEY_FILENAME",
-    "LAUNCH_BROKER_KEY_ENV",
-    "HOST_CONTROLLER_KEY_FILENAME",
-    "HOST_CONTROLLER_KEY_ENV",
-    "HOST_CONTROLLER_AUTH_JWT_ENV",
     "GATEWAY_CA_DIRNAME",
     "bot_bottle_root",
     "host_db_path",

bot_bottle/trust_domain.py

@@ -29,13 +29,8 @@ from collections.abc import Mapping
 from dataclasses import dataclass
 
 from . import orchestrator_auth
-from .orchestrator_auth import ROLE_GATEWAY, ROLE_HOST
+from .orchestrator_auth import ROLE_GATEWAY
 from .paths import (
-    HOST_CONTROLLER_AUTH_JWT_ENV,
-    HOST_CONTROLLER_KEY_ENV,
-    HOST_CONTROLLER_KEY_FILENAME,
-    LAUNCH_BROKER_KEY_ENV,
-    LAUNCH_BROKER_KEY_FILENAME,
     ORCHESTRATOR_AUTH_JWT_ENV,
     ORCHESTRATOR_TOKEN_ENV,
     ORCHESTRATOR_TOKEN_FILENAME,
@@ -104,40 +99,6 @@ CONTROL_PLANE = TrustDomain(
 )
 
 
-# The launch-broker domain (#468): durable key material for the broker's own
-# signed launch requests (`broker.py`'s HS256 launch JWT), shared by the
-# orchestrator (signer) and the host control server (verifier). Unlike
-# `CONTROL_PLANE` it mints no role tokens — the broker's provenance is the launch
-# JWT, not a role token — so its `roles` set is empty and it is used only as a
-# provider of durable, host-canonical key material (`signing_key` / `key_from_env`).
-# The durability is the point: the key survives orchestrator restarts, so a
-# restarted orchestrator re-verifies against the same key instead of the
-# ephemeral per-process secret the in-process broker used.
-LAUNCH_BROKER = TrustDomain(
-    name="launch-broker",
-    key_filename=LAUNCH_BROKER_KEY_FILENAME,
-    roles=frozenset(),
-    key_env=LAUNCH_BROKER_KEY_ENV,
-    token_env="",
-)
-
-# The host controller's own domain (#468) — the SECOND domain #476 reserves. Its
-# key, which the orchestrator never holds, signs the `host`-role tokens the CLI
-# presents on the host controller's lifecycle endpoints (start / restart / status
-# of the orchestrator itself). Keeping it separate from `CONTROL_PLANE` is the
-# whole point: the host controller starts and stops the orchestrator, so the
-# orchestrator must not be able to mint the credentials used to drive it. (The
-# lifecycle endpoints themselves arrive in a later chunk; the domain is
-# established here alongside the durable launch-broker key.)
-HOST_CONTROLLER = TrustDomain(
-    name="host-controller",
-    key_filename=HOST_CONTROLLER_KEY_FILENAME,
-    roles=frozenset({ROLE_HOST}),
-    key_env=HOST_CONTROLLER_KEY_ENV,
-    token_env=HOST_CONTROLLER_AUTH_JWT_ENV,
-)
-
-
 @dataclass(frozen=True)
 class ControlPlaneProvisioning:
     """The one seam every backend launcher uses to provision control-plane auth,
@@ -171,56 +132,9 @@ class ControlPlaneProvisioning:
         return self.domain.mint(ROLE_GATEWAY)
 
 
-@dataclass(frozen=True)
-class LaunchBrokerProvisioning:
-    """The seam that provisions the host-side launch broker's durable keys (#468),
-    the counterpart to `ControlPlaneProvisioning`. Both the orchestrator (signer)
-    and the host control server (verifier) receive the SAME launch-broker key
-    (carry it in `broker_domain.key_env`); the host controller ALSO receives its
-    own lifecycle key (`controller_domain.key_env`) the orchestrator never holds.
-
-    Fail-closed like the control-plane seam: minting returns "" only if the host
-    root is unwritable, and an empty launch-broker key would leave the verifier
-    unable to authenticate any launch — so we raise rather than hand back a key
-    that would make the host controller reject (or, if a caller defaulted it,
-    accept) unsigned input."""
-
-    broker_domain: TrustDomain = LAUNCH_BROKER
-    controller_domain: TrustDomain = HOST_CONTROLLER
-
-    def broker_key(self) -> str:
-        """The durable launch-broker key both the orchestrator and the host
-        control server must receive (in `broker_domain.key_env`). Raises rather
-        than return ""."""
-        key = self.broker_domain.signing_key()
-        if not key:
-            raise ProvisioningError(
-                f"refusing to provision the {self.broker_domain.name} broker "
-                "without a signing key: the host controller could then verify no "
-                "launch request's provenance"
-            )
-        return key
-
-    def controller_key(self) -> str:
-        """The host controller's own lifecycle key — provisioned ONLY to the host
-        controller (in `controller_domain.key_env`), never to the orchestrator, so
-        the orchestrator cannot mint the `host`-role tokens that start and stop
-        it. Raises rather than return ""."""
-        key = self.controller_domain.signing_key()
-        if not key:
-            raise ProvisioningError(
-                f"refusing to provision the {self.controller_domain.name} without "
-                "a signing key: its lifecycle endpoints would authenticate no one"
-            )
-        return key
-
-
 __all__ = [
     "ProvisioningError",
     "TrustDomain",
     "CONTROL_PLANE",
-    "LAUNCH_BROKER",
-    "HOST_CONTROLLER",
     "ControlPlaneProvisioning",
-    "LaunchBrokerProvisioning",
 ]

bot_bottle/util.py

@@ -9,11 +9,8 @@ import difflib
 import hashlib
 import ipaddress
 import os
-import re
 import sys
 
-from .log import die
-
 
 def sha256_hex(content: str) -> str:
     """Hex SHA-256 of a UTF-8 string."""
@@ -70,20 +67,3 @@ def expand_tilde(path: str) -> str:
         home = os.environ.get("HOME", "")
         return home + path[1:]
     return path
-
-
-_SLUG_RE = re.compile(r"[^a-z0-9]+")
-
-
-def slugify(name: str) -> str:
-    """Return a portable bottle identifier from a human-readable name.
-
-    This is deliberately a root utility: names are part of the generic CLI
-    and state model, not a Docker container concern.
-    """
-    if not name:
-        die("slugify: missing name")
-    slug = _SLUG_RE.sub("-", name.lower()).strip("-")
-    if not slug:
-        die(f"name '{name}' produced an empty slug; use alphanumeric characters")
-    return slug

docs/ci.md

@@ -1,53 +1,50 @@
 # CI
 
-## Required pull-request gate
+The test workflow lives at [`.gitea/workflows/test.yml`](../.gitea/workflows/test.yml).
+It runs the unit suite plus one integration job per backend
+(`integration-docker`, `integration-firecracker`, `integration-macos`) on:
 
-[`.gitea/workflows/test.yml`](../.gitea/workflows/test.yml) runs the unit
-suite, Docker integration suite, combined coverage report, and diff-coverage
-gate when tested package/build inputs change on a pull request or on `main`.
+- every push to a branch with an open pull request, and
+- every push to `main`.
 
-The Docker job preflights the backend before discovery. Gitea's `act_runner`
-runs the job in a container with the host Docker socket, so the test process
-reaches control-plane siblings through the job's Docker network and uses named
-Docker volumes for orchestrator/CA state the host daemon must mount. The
-orchestrator runs the package baked into the image built from the checkout; it
-does not bind the job container's invisible workspace into a sibling container.
-Docker integration jobs share fixed singleton names, so required and manual
-runs use one non-cancelling concurrency group. The shared agent/gateway network
-has an explicit subnet, which Docker requires for the pinned source IPs used as
-the isolation/attribution key.
+`integration-macos` is the exception: it is **advisory**, running only on
+`workflow_dispatch` (manual dispatch), never on push or pull requests. It targets the
+Apple Container backend on a self-hosted macOS runner (label `macos`,
+registered in host mode — Apple Container can't run in a Linux container, so it
+can't reuse the `kvm` runner). A single non-redundant laptop must not be able
+to block a PR merge, so the job stays out of the `coverage` job's `needs` and
+its coverage never feeds the diff-coverage gate. Because the infra container is
+a singleton (`bot-bottle-mac-infra`), the job declares a `concurrency` group
+and tears the container down on exit; keep runner concurrency at 1. See the
+README "macOS Apple Container" CI note for runner provisioning.
 
-`scripts.unittest_gate` enforces the Docker job's contract: all 22 integration
-tests must execute and none may skip. This includes the real gateway-image,
-control-plane authentication, multitenant policy/token isolation,
-sandbox-escape, and orphan-network tests. Backend skip decorators remain useful
-for local runs, but the CI preflight plus execution-count gate prevents a
-missing backend or runner-topology regression from becoming a green job.
+Each integration job selects its backend via `BOT_BOTTLE_BACKEND` and
+runs a **preflight** (`./cli.py backend status --backend=<name>`) that
+prints a clear per-check readiness summary and fails the job when the
+backend is missing — so absent infrastructure is visible at the job level
+rather than hidden among per-test `unittest.skip` lines. The skip guards in
+[`tests/_backend.py`](../tests/_backend.py) gate on the same readiness
+check (`bot_bottle.backend.has_backend`): backend-agnostic tests use
+`skip_unless_selected_backend_available()` and run through whichever
+backend is selected (checking, e.g., Linux + `/dev/kvm` for Firecracker
+rather than unrelated Docker availability); Docker-implementation tests use
+`skip_unless_backend("docker")` and no-op under a non-Docker run.
 
-Combined unit + Docker coverage is informational globally. Two focused gates
-are enforced:
+A small subset of integration tests skip when running specifically
+under Gitea Actions (`GITEA_ACTIONS=true`), because `act_runner` runs
+the job inside a container with the host's `/var/run/docker.sock`
+mounted in. That topology breaks two assumptions those tests make:
 
-- changed executable Python lines must be at least 90% covered; and
-- the validated critical security/logic core must remain at least 90% covered.
+- networks created via the host daemon aren't always visible to a
+  same-process `docker network ls` call from inside the job container,
+  and
+- ports published by sibling containers land on the host's loopback,
+  not on the job container's `127.0.0.1` — so HTTP probes against
+  `http://127.0.0.1:<host_port>` from inside the job time out.
 
-## Privileged pre-release matrix
-
-[`.gitea/workflows/pre-release-test.yml`](../.gitea/workflows/pre-release-test.yml)
-is manually dispatched before a release. It repeats unit and Docker integration
-coverage, then runs:
-
-- Firecracker integration on the self-hosted `kvm` runner; and
-- advisory Apple Container integration on the self-hosted `macos` runner.
-
-These privileged host-mode runners never execute unreviewed pull-request code
-automatically. Firecracker coverage is combined in the manual pre-release
-report; macOS reports advisory coverage in its own job. The macOS infra
-container is a singleton, so its job uses a concurrency group and always tears
-the service down.
-
-## Scheduled canary
-
-[`.gitea/workflows/canaries.yml`](../.gitea/workflows/canaries.yml) runs weekly
-and on manual dispatch. It verifies the pinned gitleaks release URL, checksum,
-archive shape, and executable. The same unittest execution gate requires at
-least one executed canary and rejects skips.
+The affected tests (`test_orphan_cleanup.test_create_and_remove`,
+`test_gateway_image.TestGatewayImage`) still run
+locally where the test process and Docker daemon share a host.
+Making them work in CI is a follow-up: either re-write them to
+discover container IPs via `docker inspect`, or reconfigure the
+runner with host networking.

docs/decisions/0004-coverage-policy.md

@@ -34,13 +34,12 @@ a regression (Goodhart's law).
 Coverage is **risk-weighted**, measured over the **combined unit +
 integration** suites, with three rules:
 
-1. **Critical modules must remain ≥ 90%.** The curated security/logic core
-   covers the host and gateway egress policy, manifest trust boundary,
-   git-gate enforcement, supervise protocol/server, YAML parser, and bottle
-   state. The concrete module list lives in `scripts/critical-modules.txt`;
-   `scripts/critical_modules.py` rejects stale or ambiguous entries before
-   Coverage.py can silently ignore them. These modules are unit-testable, so
-   CI enforces the aggregate minimum independently of diff coverage.
+1. **Critical modules target ≥ 90%.** The security/logic core —
+   `egress_addon{,_core}.py`, `dlp_detectors.py`, `egress.py`,
+   `manifest*.py`, `git_gate.py`, `git_http_backend.py`, `supervise.py`,
+   `yaml_subset.py`, `bottle_state.py` — is Docker-independent and
+   unit-testable, so it carries the high bar. We ratchet toward 90% as
+   these modules are touched; new gaps in them are not acceptable.
 
 2. **Subprocess/backend orchestration is covered by the integration
    suite, not omitted.** `scripts/coverage.sh` runs unit + integration
@@ -83,9 +82,6 @@ omit list.
   (critical-module standard + diff coverage) are Docker-independent.
 - "We're at N%" is now a curated figure; outsiders should read the
   policy, not just the badge.
-- A rename or removal in the curated list fails CI. Updating the list is an
-  explicit review of where the security-critical behavior moved, not a way to
-  improve the percentage by omission.
 
 ## Links
 

docs/prds/prd-new-audit-event-schema.md

@@ -0,0 +1,732 @@
+# PRD prd-new: Canonical tamper-evident audit-event schema and local query contract
+
+- **Status:** Draft
+- **Author:** didericis-claude
+- **Created:** 2026-07-26
+- **Issue:** #487
+
+## Summary
+
+bot-bottle already emits security- and provenance-relevant events from
+several producers — supervise operator decisions (PRD 0013's
+`AuditStore`), egress allow/block enforcement, git-gate push decisions,
+control-plane token minting, and (next) host-controller lifecycle
+transitions — but each writes its own shape to its own sink. There is no
+shared envelope, no tamper-evidence, and no single place to search. Local
+incident reconstruction means grepping several stores that don't agree on
+field names, timestamps, or how a bottled agent is identified.
+
+This PRD defines **one canonical audit-event contract** every producer
+emits into:
+
+1. A **versioned envelope** — schema version, event id, event/observed
+   timestamps, host-attributed identity (`bottle`/`bottled_agent`/
+   `activation`), provenance (`manifest_digest` — the manifest is the
+   policy — and `engine` = bot-bottle version/SHA),
+   host-observed `actor`/`action`/`resource`/`outcome`, correlation/
+   causation ids, a sensitivity class, a typed payload, and an explicit
+   **trust boundary** between host-supplied and agent-claimed fields.
+2. **Canonical JSON serialization + a per-writer hash chain** (with
+   normative test vectors), so any deletion, edit, or reorder of a past
+   record breaks the chain and is detectable offline.
+3. An **append-only JSONL journal as the source of truth**, with a
+   **rebuildable SQLite index** and a local `audit query`/`verify` surface
+   — no paid platform, no network dependency.
+4. An **initial event registry** covering lifecycle, host-controller,
+   supervise decision, egress (request/decision/cutoff/anomaly), git-gate
+   and signed-commit (#480), auth/authz, and audit self-events — each with
+   its trusted-vs-claimed fields and redaction rules.
+5. A **stable export projection** (CloudEvents / OpenTelemetry Logs) and
+   the **#324 delivery contract** (payload, per-chain
+   `(host, epoch, seq)` cursor, dedup,
+   backpressure, retention ordering).
+
+It is explicitly scheduled to land **immediately after the host
+controller (#468)** so the host controller's lifecycle transitions are the
+first producer wired onto the new contract (per the directive on #487).
+
+## Problem
+
+Audit infrastructure is fragmented across #468, #324, and #480 with no
+shared schema. Concretely:
+
+- **No shared envelope.** `supervise_audit_entries` (PRD 0013) has
+  `timestamp, bottle_slug, component, operator_action, ...`. The egress
+  proxy and git-gate log their own ad-hoc lines. There is no common
+  `event_id`, `event_type`, or version, so cross-producer correlation
+  ("what did bottled agent X do between its start and this rejected push?") is
+  manual and lossy.
+- **No tamper-evidence.** The audit store is a plain SQLite table. Anyone
+  who can write the DB can delete or rewrite a row and leave no trace.
+  Audit that an attacker (or a buggy agent) can silently rewrite is not
+  audit.
+- **Trusted and untrusted data are mixed.** A bottled agent is attributed by
+  **source IP → slug** at the gateway (host-supplied, trustworthy). An
+  agent can also *claim* things about itself in a tool call
+  (agent-claimed, adversarial). Today nothing in the record marks which is
+  which, so a reader can be misled by an agent-supplied field that looks
+  authoritative.
+- **No local search.** Reconstructing an incident means reading multiple
+  sinks with different schemas. There is no query contract and no promise
+  that the index can be rebuilt from the journal if it drifts or is lost.
+- **No redaction rule.** Nothing prohibits a producer from writing a raw
+  token or secret into an audit record, which would turn the audit log
+  itself into a credential store.
+
+## Goals / Success Criteria
+
+- A single `AuditEvent` envelope type, versioned, that every producer
+  emits. The trust boundary is **one `untrusted` region**: everything
+  outside it is host-established and trusted (source-IP → bottled-agent
+  attribution, host wall-clock, producer identity, chain metadata);
+  `untrusted` is the sole place anything an agent or a remote claimed may
+  go. The boundary is structural, not a convention.
+- **Canonical serialization** (`sort_keys`, `(",", ":")` separators,
+  UTF-8, `ensure_ascii=False`) is defined once and reused, so the same
+  logical event always hashes identically across producers and hosts.
+- Each writer maintains a **hash chain**: `hash = sha256(prev_hash ||
+  canonical(event))`. Deleting or editing any past record breaks every
+  subsequent link; a standalone verifier detects the break offline with no
+  secret material.
+- The **JSONL journal is the source of truth**; the **SQLite index is
+  fully rebuildable** from it (`audit rebuild` reconstructs the DB and
+  re-verifies the chain).
+- **Local query** works with no paid platform and no egress: filter by
+  bottled agent, event type, time range, and producer, and follow a bottled
+  agent's events in order.
+- A **redaction rule** is enforced at the envelope boundary: known
+  credential-shaped fields are rejected/redacted before a record is
+  written; the writer refuses raw secrets rather than storing them.
+- The envelope **projects onto the OpenTelemetry Logs data model and a
+  CloudEvents JSON envelope** by field re-mapping alone (no reformat),
+  preserving the trust boundary and carrying the integrity fields — per
+  #487's export/interop requirement. (The export adapters are follow-up;
+  the *schema* must make them a re-map.)
+- The **host controller (#468)** emits `lifecycle.*` events through this
+  contract as the first consumer; existing supervise/egress producers are
+  migrated behind the same envelope without changing operator-facing
+  behavior.
+
+## Non-goals
+
+- **Cross-host aggregation / shipping.** This PRD makes each host's journal
+  canonical and correlatable *by construction* (stable ids, hash chain),
+  but the transport that merges multiple hosts into one timeline is a
+  follow-up (#324). The schema is designed so that merge is a later append,
+  not a reformat.
+- **Cryptographic signing / external anchoring.** Hash-chaining gives
+  tamper-**evidence** (you can detect edits), not tamper-**resistance**
+  against an attacker who can rewrite the whole chain. Per-writer signing
+  keys and periodic external anchoring are a follow-up; the chain-head hash
+  is the seam they attach to.
+- **Real-time alerting / SIEM rules.** Query is local and pull-based here.
+- **Retention / rotation policy.** Journal rotation and TTL are operator
+  policy, tracked separately; the format must survive rotation (chain head
+  carried across segments) but this PRD does not set the schedule.
+- **Replacing PRD 0013's operator queue.** The supervise proposal/response
+  queue is unchanged; only its terminal *audit* record is re-emitted onto
+  the new envelope.
+
+## Design
+
+### The envelope
+
+One dataclass, `AuditEvent`, serialized to a JSON object with a small,
+stable top level:
+
+```
+{
+  // ---- schema + integrity (host-owned) ----
+  "v": 1,                          // schema version — bumped only on a breaking change
+  "id": "<uuid4>",                 // globally unique event id; stable across export/replay (dedup key)
+  "type": "egress.decision",       // dotted event type from the registry
+  "epoch": 7,                      // writer-boot counter, bumped once per host-controller (writer) start
+  "seq": 1287,                     // monotonic sequence within this epoch (gap-detectable)
+  "segment": "20260726T000000Z",   // journal segment id (rotation boundary); chain continues across segments
+  "prev": "<hex>",                 // prior record hash ("" only for the first record of a new chain)
+  "hash": "<hex>",                 // sha256(prev + canonical(this event with hash=""))
+
+  // ---- timestamps (host-owned) ----
+  "ts_event": "2026-07-26T18:22:04.061Z",    // when the underlying event occurred at the boundary
+  "ts_recorded": "2026-07-26T18:22:04.113Z", // when the single writer appended it (authoritative)
+  "ts_mono": 90142.55,             // monotonic secs since this epoch's boot (intra-epoch ordering only)
+
+  // ---- attribution + provenance (host-established) ----
+  "producer": "egress",            // host component that emitted the event
+  "host": "mac-studio-1",
+  "engine": "bot-bottle/0.1.0+abc1234",  // bot-bottle version + git SHA of the enforcing host code
+  "bottle": "amber-fox",           // bottle (container/VM) identity
+  "bottled_agent": "amber-fox-12", // bottled-agent slug from source-IP attribution (null for host-level events)
+  "activation": "01J8Z...",        // activation id: one run/session of the bottled agent (null if n/a)
+  "manifest_digest": "sha256:9f2…", // digest of the manifest — which IS the policy (egress routes etc.); null if n/a
+
+  // ---- semantics: host-observed facts of what happened ----
+  "actor": "bottled-agent:amber-fox-12", // who acted, as a host-attributed identity
+  "action": "egress.connect",      // what was attempted / done
+  "resource": "registry.npmjs.org:443",  // what it acted on, as observed at the boundary
+  "outcome": "blocked",            // host-decided result: allowed|blocked|deferred|success|failure
+  "sensitivity": "security",       // classification: normal|security|restricted (drives redaction + export)
+
+  // ---- correlation (host-assigned) ----
+  "correlation_id": "flow-9c2a…",  // groups a related flow (request → decision → cutoff)
+  "causation_id": "<event id>",    // the event that directly caused this one ("" if root)
+
+  // ---- typed, trusted, event-specific payload (shape fixed per type in the registry) ----
+  "payload": {
+    "route_id": 4,
+    "detector": "token_patterns"
+  },
+
+  // ---- the ONLY untrusted region: agent- or remote-claimed data ----
+  "untrusted": {
+    "reason": "npm install needs registry.npmjs.org"  // the agent's stated justification
+  }
+}
+```
+
+The **trust boundary is a single region, not a split.** Everything outside
+`untrusted` is trusted by construction — the host established it: schema and
+chain metadata, both timestamps, the attribution/provenance fields
+(source-IP → `bottled_agent`/`bottle`/`activation`, `manifest_digest`,
+`engine`), the host-observed semantics
+(`actor`/`action`/`resource`/`outcome`), the host-assigned correlation ids,
+and the typed `payload`. `untrusted` is the **one** place anything an agent
+or a remote claimed may go (e.g. the agent's free-text `reason`). A reader
+(or a future policy engine) trusts every field outside `untrusted` for
+attribution and treats `untrusted.*` — and only `untrusted.*` — as
+adversarial claims.
+
+Framing it as "one untrusted region, everything else trusted" removes the
+mistake where a producer forgets to mark a claimed field: a field is
+trusted unless it is deliberately placed inside `untrusted`. The
+construction API enforces this — producers pass trusted fields explicitly
+and hand all agent/remote-claimed data as the single `untrusted` mapping,
+so there is no way to emit a top-level field that *looks* authoritative but
+isn't.
+
+**Two timestamps** because they answer different questions and can diverge
+under backpressure: `ts_event` is when the thing happened at the boundary
+(the proxy saw the connect, the gate saw the push); `ts_recorded` is when
+the single writer durably appended it. Ordering and the chain use
+`(epoch, seq)`, never either wall clock. Both are host-set — a bottled
+agent never supplies a timestamp.
+
+**The manifest *is* the policy.** bot-bottle has no separate policy
+artifact — a bottled agent's egress routes and other constraints are
+declared in its manifest (`bot_bottle/manifest/egress.py`), so
+`manifest_digest` already pins the ruleset in force; there is no distinct
+`policy_version`. Given a fixed manifest, the only other thing that can
+change a decision's outcome is the enforcing code — captured by `engine`
+(bot-bottle version + git SHA). So two `egress.decision` records with the
+same `resource` but different `outcome` are explained by exactly one of:
+different `manifest_digest` (the rules changed) or different `engine` (the
+enforcer changed). Runtime operator overrides (a supervise `egress-allow`)
+are themselves audit events, so the effective ruleset at any instant is
+`manifest_digest` plus the logged, approved deltas — reconstructable from
+the chain, not from a version stamp.
+
+**Optionality.** `bottle`/`bottled_agent`/`activation`, `manifest_digest`,
+and `payload`/`untrusted` are `null`/absent for events that have no such
+subject (a host-level `hostctl.*` or `audit.*` event has no bottled agent).
+Absent ≠ empty: a reader distinguishes "no subject" from "unknown". `id`,
+`type`, the chain fields, both timestamps, `producer`, `host`, `engine`,
+`actor`, `action`, `outcome`, and `sensitivity` are always present.
+
+#### Trust provenance of every common field
+
+| Field | Trust | Set by |
+|---|---|---|
+| `v` `id` `type` `epoch` `seq` `segment` `prev` `hash` | trusted | the single writer |
+| `ts_event` | trusted | emitting host component (boundary) |
+| `ts_recorded` `ts_mono` | trusted | the single writer |
+| `producer` `host` `engine` | trusted | the single writer |
+| `bottle` `bottled_agent` `activation` | trusted | gateway source-IP → slug attribution |
+| `manifest_digest` | trusted | control plane (the manifest = the policy in force) |
+| `actor` `action` `resource` `outcome` | trusted | host component that observed/decided it |
+| `sensitivity` | trusted | registry default for `type`, overridable up (never down) by the producer |
+| `correlation_id` `causation_id` | trusted | the single writer (assigned as it threads the flow) |
+| `payload.*` | trusted | emitting host component (shape fixed per `type`) |
+| `untrusted.*` | **claimed** | copied verbatim from a bottle / gateway / forge / remote |
+
+Every registry entry (below) restates, per event type, which `payload`
+keys are required and names any `untrusted` keys it carries — so "trusted
+vs claimed" is explicit for every event-specific attribute, not just the
+common ones.
+
+### Canonical serialization + hash chain
+
+Serialization is defined once (extends the existing `sha256_hex` /
+`util.py` helpers):
+
+```
+def canonical(event: dict) -> str:
+    return json.dumps(event, sort_keys=True, separators=(",", ":"),
+                      ensure_ascii=False)
+```
+
+The `hash` field is computed over the canonical form of the event **with
+`hash` set to `""`**, prefixed by the previous record's hash:
+
+```
+digest = sha256_hex(prev_hash + canonical({**event, "hash": ""}))
+```
+
+`prev` is the prior record's `hash`; only the first record of a brand-new
+chain uses `prev = ""`. The first record of a rotated segment carries the
+preceding segment's head, as specified under *Rotation* below.
+Two exact rules pin the bytes so the chain is reproducible anywhere:
+
+1. **Serialize the record with its own `hash` field set to `""`** (present,
+   empty), never omitted — the key set is identical before and after
+   hashing.
+2. **Digest = `sha256_hex(prev + canonical(record_with_empty_hash))`**,
+   where `prev` is the previous record's `hash` string (`""` at genesis),
+   `+` is string concatenation, and `canonical` is the function above.
+   `ts_mono`, being a float, is serialized by Python's shortest-round-trip
+   `repr` via `json.dumps`; producers therefore emit it as a JSON number
+   they do not post-process. (All other fields are strings/ints/objects,
+   which serialize unambiguously.)
+
+Editing or deleting record *n* changes its hash, so record *n+1*'s `prev`
+no longer matches — the break is local and names the tampered record.
+Verification needs only the journal itself (no keys), so it runs offline
+and in CI.
+
+#### Test vectors (normative)
+
+Two records, reduced to the chain-relevant fields, demonstrate the exact
+serialization and linkage. An implementation is conformant iff it
+reproduces these bytes and hashes.
+
+```
+# Record 0 — brand-new chain genesis (prev = "")
+canonical(record0, hash=""):
+{"hash":"","id":"11111111-1111-4111-8111-111111111111","prev":"","seq":0,"type":"audit.segment_open"}
+hash0 = sha256(""  + canonical) =
+  942ea5729bcac6efdbdea942396bfa574ab0d6ebf5615402595359422f2aeb83
+
+# Record 1 — chains onto record 0 (prev = hash0)
+canonical(record1, hash=""):
+{"hash":"","id":"22222222-2222-4222-8222-222222222222","prev":"942ea5729bcac6efdbdea942396bfa574ab0d6ebf5615402595359422f2aeb83","seq":1,"type":"lifecycle.bottled_agent_start"}
+hash1 = sha256(hash0 + canonical) =
+  bc082347680405fee50b60a9c304611aa026950b15d869b7e3ae56e1c451b856
+
+# Tamper check: flip record0.type → recompute →
+#   4553eda647f33f0c608cfea44be28efbbaca45ed30b873fcbd4405fa5ce737ed
+# which no longer equals record1.prev (942ea5…) — the break is detected at record1.
+```
+
+The implementation PR ships these plus full-envelope vectors (every field
+populated, and a redaction case) as committed fixtures, so a schema-version
+bump that changes the bytes fails a golden test loudly.
+
+### Ordering, idempotency, and duplicate handling
+
+- **Ordering.** `(epoch, seq)` is a strict total order within one host's
+  native chain and, because
+  the writer is single, a strict order per bottle/activation within that
+  host — satisfying "at least strict causal order per activation/bottle".
+  `causation_id` records the explicit cause edges (a DAG) on top of the
+  total order, so a consumer can reconstruct request → decision → cutoff
+  even if unrelated events interleave between them. There is deliberately
+  no invented total order across imported host chains; a cross-host key is
+  `(host, epoch, seq)`, and consumers use correlation/causation edges where
+  causal ordering across hosts is known.
+- **Idempotency.** `id` is the idempotency key. A producer that retries an
+  emit (e.g. after a writer restart mid-handoff) **reuses the same `id`**;
+  before appending, the writer checks a durable, host-wide id ledger that
+  spans every segment and survives restart/retention, and drops an id
+  already present. The ledger is operational metadata, not an audit source
+  of truth: after a crash it is reconciled from the journal before appends
+  resume, and retention preserves id tombstones after journal segments are
+  pruned. An in-memory set may cache the ledger but is never the authority.
+  The index additionally has a unique key on `id`; its `UPSERT` is
+  defensive and does not substitute for the pre-append check. Thus a
+  duplicate never enters the source-of-truth journal, double-counts, or
+  forks the chain.
+- **Deduplication downstream.** Because `id` is stable across export and
+  replay, #324's cursor replay and any cross-host merge dedup on `id` — no
+  consumer needs to invent a second identity.
+
+### Behavior across rotation, restart, import, truncation
+
+- **Rotation.** At a segment boundary the writer opens a new segment file,
+  sets its `segment` id, and carries the rotated-out segment's head as the
+  new segment's first `prev` — so the chain is continuous *across* segments
+  (`prev = ""` is reserved for the first record of a brand-new chain) while
+  each file stays independently openable. `verify` walks segments in order
+  and checks the preceding-head-to-first-record link at each seam.
+- **Restart.** Covered above: read last line → adopt its `hash` as `prev`,
+  bump `epoch`, reset `seq`. The chain never restarts even though the
+  counters do.
+- **Import.** `audit import <segment>` appends an externally supplied
+  segment (e.g. recovered from another host or a backup). Import verifies
+  the incoming chain in isolation first. A continuation whose first `prev`
+  matches a known head extends that chain. A foreign chain is registered as
+  a separate immutable chain namespace rather than rewriting or grafting
+  its records (which would invalidate their hashes). Imported records keep
+  their original `host`, `id`, `epoch`, and `seq`; the index keys their
+  native order by `(host, epoch, seq)` so attribution is not laundered and
+  tuples from different hosts cannot collide.
+- **Truncation.** A crash can leave a partial final line; `verify` reports
+  it as `truncated-tail` (recoverable — replay resumes from the last intact
+  record). A chain that ends before a persisted head, or a missing interior
+  `seq`, is reported as `gap`/`missing-suffix` (evidence of deletion, not a
+  clean crash). The two are distinguished so an operator can tell "power
+  loss" from "someone trimmed the log".
+
+### Single writer; ordering across restarts
+
+**Decided: one writer per host** (reviewed — the host controller owns it).
+Producers hand events to the host controller, which is the sole appender,
+so the chain has one well-defined total order and one `seq`/`epoch`
+counter. This ties audit availability to the host controller being up,
+which is acceptable because the host controller already gates every
+lifecycle transition; per-producer chains are noted only as a future
+scaling path, not built now.
+
+**Restarts** are handled by the chain, not the clock. `ts_mono` resets to
+~0 on every writer start, so it orders events only *within* one boot. On
+start the writer:
+
+1. reads the last line of the journal, adopts its `hash` as the next
+   record's `prev` (the chain is continuous across the restart), and
+2. bumps `epoch` (persisted alongside the chain head) and resets `seq` to
+   0 for the new boot.
+
+Total order within this host's native chain is therefore `(epoch, seq)` —
+monotonic across restarts by construction — with
+`ts_event`/`ts_recorded` for human reading and `ts_mono` for sub-second
+ordering inside an epoch. Imported chains retain their own
+`(host, epoch, seq)` order and do not acquire a fictional order relative to
+the local chain. A crash mid-append truncates at most the last (partial)
+line; the verifier flags it and replay resumes from the last intact record.
+
+### Journal (source of truth) + SQLite index (rebuildable)
+
+- **Journal:** one append-only JSONL file per host (path from `paths.py`,
+  alongside `host_db_path()`), one canonical event per line, opened
+  `O_APPEND`. This is authoritative.
+- **Index:** a new `audit_events` table via the existing `DbStore` /
+  `TableMigrations` machinery. It is a **derived cache, not a second source
+  of truth**: `audit rebuild` truncates and replays the journal,
+  re-verifying the chain as it goes, so a deleted or drifted DB is
+  regenerated from the journal with no data loss. On a `verify` failure
+  during rebuild it stops and reports rather than indexing past a break.
+  (This supersedes the free-standing `supervise_audit_entries` table, which
+  becomes a producer onto the new index.)
+
+**Indexable fields** (columns + indices): `ts_event`, `ts_recorded`,
+`type`, `host`, `bottle`, `bottled_agent`, `activation`, `actor`,
+`outcome`, `sensitivity`, `correlation_id`, `causation_id`, plus two
+event-specific projections promoted out of `payload` for query —
+`repository` and `commit_sha` (populated for `forge.*`/`commit.*`, null
+otherwise). The unique event id and native-order index are respectively
+`id` and `(host, epoch, seq)`; a local-only `ingest_seq` provides stable
+display order when a query intentionally mixes chains without pretending
+that it is causal order. The full canonical record is stored verbatim in a
+`raw` column so the index never loses fidelity to the journal.
+
+**Local query surface** — `audit query`, no egress, no paid platform:
+
+```
+audit query \
+  [--since T] [--until T] [--type egress.*] [--host H] [--bottle B] \
+  [--activation A] [--agent SLUG] [--actor ID] [--outcome blocked] \
+  [--repository R] [--correlation-id C] [--commit SHA] \
+  [--follow BOTTLE]        # one host chain's events in (epoch, seq) order
+  [--json | --table]
+audit verify [--segment S] # offline chain check; exit non-zero on any break
+audit rebuild              # drop + replay journal → index
+audit import <segment>     # graft an external segment (see above)
+```
+
+Type filters accept a `group.*` glob. A read-only local HTTP endpoint
+mirrors the same filters for the future review console; both are pure reads
+over the index and can never mutate the journal.
+
+### Event registry (initial)
+
+Dotted `type` names, grouped. The registry is a table mapping each type to
+its required `payload` keys, its `untrusted` keys (if any), a default
+`sensitivity`, and its correlation behavior — so producers and the verifier
+agree on shape and "trusted vs claimed" is pinned per type. Initial
+coverage (the issue's mandated set):
+
+| Group / type | Producer | Required `payload` (trusted) | `untrusted` | Default sensitivity |
+|---|---|---|---|---|
+| **lifecycle.*** — `bottled_agent_start` / `_stop` / `_crash` | host-controller (#468) | `manifest_digest`, `exit` (for stop/crash) | — | normal |
+| **hostctl.*** — `broker_launch`, `broker_teardown`, `broker_reject` | host-controller (#468) | `op`, `request_digest` | — | security |
+| **decision.*** — `proposed`, `resolved` | supervise | `tool`, `operator_action`, `justification`, `diff_digest` | `agent_rationale` | security |
+| **egress.*** — `request`, `decision`, `cutoff`, `anomaly` | egress proxy | `route_id`, `detector` (on match), `bytes` (cutoff) | `reason`, `target_claimed` | security |
+| **forge.*** — `push_accepted`, `push_rejected`, `pr_opened` | git-gate | `repository`, `ref`, `gitleaks_result` | `title`, `description` | security |
+| **commit.signed** (#480) | git-gate | `repository`, `commit_sha`, `activation_key_id`, `signature_ref` | `commit_message` | security |
+| **auth.*** — `token_minted`, `token_rejected`, `authz_denied` | control plane | `role`, `token_id`, `reason_code` | — | security |
+| **audit.*** — `segment_open`, `verify_failed`, `truncation_detected`, `export_failed` | audit writer/verifier | `segment`, `detail` | — | security |
+
+Notes:
+- **`egress.request` vs `egress.decision`** share a `correlation_id`; the
+  `decision`'s `causation_id` points at the `request`, and a later `cutoff`
+  chains onto the `decision` — so a flow is reconstructable.
+- **`audit.*` self-events** make the audit subsystem audit itself: a failed
+  verification, a detected truncation, or a dropped export is itself a
+  chained, tamper-evident record — you cannot silence the alarm without
+  breaking the chain that carries it.
+- **Free-text and remote-echoed fields are always `untrusted`** (`reason`,
+  `agent_rationale`, PR `title`/`description`, `target_claimed`), because
+  they originate in the bottle or a remote response; the host-observed
+  counterpart (`resource`, `outcome`, `gitleaks_result`) is the trusted
+  fact.
+
+**Sensitivity + redaction per type.** Every type's default `sensitivity`
+is listed above; a producer may raise it (never lower it). `restricted`
+events keep their `payload` in the journal but the export projection ships
+only the envelope + a payload digest unless the consumer is authorized —
+so a `security`/`restricted` record is still counted and correlated
+downstream without leaking its body. The credential-shape redaction rules
+(next) apply to **every** type regardless of sensitivity.
+
+**Schema evolution & backward-compatible readers.** The registry is
+append-only: **adding** a type, an optional `payload` key, or an
+`untrusted` key does **not** bump `v`; readers ignore unknown fields
+(forward-compatible) and treat absent optional fields as `null`.
+**Removing** or **re-typing** a field, or making an optional field
+required, bumps `v`. A reader declares the max `v` it understands and
+refuses to *interpret* a higher-`v` record, but the **verifier is
+version-agnostic** — the hash covers whatever fields exist, so chain
+integrity is checkable across versions without understanding semantics.
+Every `v` bump ships a migration note and updated golden vectors.
+
+### Redaction rule
+
+Redaction runs at the envelope boundary, before a record is written, in two
+layers:
+
+1. **Key deny-list (structural).** A field whose *key* matches a known
+   credential shape (`token`, `secret`, `password`, `authorization`,
+   `*_key`) is refused — the producer must pass a reference (a token *id*
+   or `sha256` fingerprint), never the raw value. `auth.token_minted`
+   therefore records the token id and role, not the JWT. This is the
+   primary guard: it is cheap, deterministic, and catches the intended
+   mistake (a producer stuffing a credential into a named field).
+
+2. **Value scan — reuse the egress DLP detectors.** Per review, the value
+   layer reuses the *same* deterministic credential-shape detectors the
+   egress proxy already ships:
+   `bot_bottle/gateway/egress/dlp_detectors.py` —
+   `scan_token_patterns` / `redact_tokens` (and `scan_known_secrets` for
+   host-known secret material). They are pure-Python, mitmproxy-free, and
+   already the project's source of truth for "what a leaked credential
+   looks like," so a single detector set governs both what may leave over
+   the wire and what may land in the journal — they can't drift apart.
+
+   **Scoped deliberately:** only the pattern/known-secret detectors are
+   reused, **not** `scan_entropy`. Entropy scoring is tuned for large
+   streamed request bodies; on the short, high-entropy structured values an
+   audit event legitimately carries (hashes, uuids, base64 ids) it would
+   false-positive and start redacting the very fingerprints the log needs.
+   So the shared layer is the deterministic detectors; entropy stays an
+   egress-only concern. (This is the "evaluate how reasonable that is" from
+   review: reuse the deterministic detectors — yes; share the entropy
+   heuristic — no.)
+
+On a value-layer match the default is **redact** (scrub to a placeholder
+and keep the event) rather than drop, so a producer bug can never make an
+audit event vanish; the key deny-list stays a hard refusal because a
+credential in a named field is always a producer bug worth surfacing.
+
+**No raw-payload capture by default.** The envelope carries *decisions and
+metadata*, not traffic. Prompts, model responses, request/response bodies,
+and file contents are **not** recorded unless a producer opts a specific,
+reviewed field in — and such a field is `untrusted` and subject to both
+redaction layers. This keeps the audit log from becoming a covert copy of
+the very data the sandbox exists to contain (the issue's "unsafe payload
+capture" non-goal).
+
+### Export / interoperability (CloudEvents, OpenTelemetry Logs)
+
+#487 requires the envelope to map onto the **OpenTelemetry Logs data
+model** and/or a **CloudEvents JSON** envelope *without losing integrity or
+attribution semantics*. The flattened shape (one `untrusted` region,
+everything else trusted at top level) does **not** conflict with either — it
+maps *more* cleanly than a nested `trusted`/`untrusted` pair would, because
+both target models expect a flat set of top-level fields plus one payload
+subtree.
+
+**CloudEvents.** Context attributes MUST be scalar simple types — a map
+cannot be a context attribute — so a nested `trusted` block would have had
+to be flattened for CloudEvents anyway. Our flat top level maps directly:
+`id`→`id`, `type`→`type`, `producer`+`host`→`source`,
+`bottled_agent`→`subject`, `ts_event`→`time` (`ts_recorded` as an extension); the integrity/chain fields
+(`epoch`, `seq`, `prev`, `hash`, `v`) ride as **extension attributes**
+(scalars — legal). The `untrusted` map goes in `data`. Only mechanical
+transform needed: extension attribute names must be lowercase-alphanumeric,
+so `bottled_agent`/`ts_mono`/etc. are renamed at export (e.g. a
+`botbottle`-prefixed form) — a naming rule, not a schema conflict.
+
+**OpenTelemetry Logs.** `ts_event`→`Timestamp`, `ts_recorded`→`ObservedTimestamp`; `type`→the `event.name`
+attribute; the flat trusted fields → `Attributes` under a `botbottle.*`
+namespace (`botbottle.bottled_agent`, `botbottle.producer`,
+`botbottle.chain.hash`, …); `untrusted.*` → `Attributes` under
+`botbottle.untrusted.*` (or `Body`). OTel attributes are a dotted map that
+happily carries the nested subtree.
+
+**Attribution is preserved** precisely because the boundary is now
+structural: on export, top-level fields become trusted context/attributes
+and the `untrusted` subtree stays a single, clearly-named region — so a
+downstream consumer still sees exactly which fields an agent claimed.
+Nothing agent-claimed is promoted to a trusted-looking position.
+
+**Integrity has one deliberate caveat.** CloudEvents/OTel are
+representation envelopes with their own (or no) canonicalization; `hash`
+and `prev` are computed over **our** canonical JSON, not over the exported
+form. So the chain fields travel *as data* for reference, but
+tamper-evidence is always verified against the **native journal** (the
+source of truth) — never re-derived from an exported CloudEvents/OTel
+record, whose key ordering / number formatting the exporter may change.
+Export is thus a lossless-for-attribution **projection** that carries the
+integrity fields along; verification stays on the canonical journal. This
+satisfies "without losing integrity or attribution semantics": both are
+carried, neither is *relied upon* in the foreign format.
+
+The export adapters themselves are follow-up implementation — this PRD
+fixes the *schema* so that projection is a field re-map, never a reformat.
+
+#### The #324 delivery contract (payload, cursor, backpressure)
+
+#324 transports events off-box; it must not invent a second envelope. This
+PRD fixes the contract it depends on:
+
+- **Payload.** #324 ships the **native canonical record verbatim** (the
+  exact bytes the hash covers), optionally wrapped in the CloudEvents
+  projection whose `data` *is* that record. Either way the integrity fields
+  travel intact and the receiver can verify against the same bytes.
+- **Cursor.** Export maintains one cursor per native host chain:
+  `(host, epoch, seq)` (equivalently that chain's last exported `hash`).
+  It advances **only on acknowledgement**, so delivery is at-least-once and
+  gap-free; a crash re-sends from the last acked cursor. Imported foreign
+  chains use independent cursors and never share a bare `(epoch, seq)`
+  namespace with the local chain.
+- **Idempotency / replay.** Dedup is on `id` (stable across replay), so
+  at-least-once delivery is safe — the receiver collapses re-sends.
+- **Backpressure.** The outbox is the journal itself plus a cursor; when
+  the endpoint is slow the cursor simply lags — the writer never blocks on
+  export, and audit never applies backpressure to the data plane it
+  records.
+- **Retention interaction.** Retention/rotation **must not** prune a
+  segment whose records are still behind the export cursor; the reaper
+  honors `min(cursor)` across all configured consumers. (The schedule
+  itself stays the retention follow-up; this is the *ordering* constraint
+  that follow-up must respect.)
+
+#### #480 signed-commit attribution maps in without weakening it
+
+#480 binds a commit's bytes to a per-activation signing key. It maps to the
+`commit.signed` event: `payload` carries `repository`, `commit_sha`,
+`activation_key_id`, and a `signature_ref` (the detached-signature
+location or its digest) — **not** the private key and not a re-derived
+signature. The audit event therefore *references and timestamps* #480's
+existing byte-to-activation-key proof inside the tamper-evident chain; it
+does not re-implement or replace it, so #480's guarantee is unweakened —
+the signature still verifies against the commit bytes independently, and
+the audit record adds only "this binding was observed at this point in the
+chain". The trusted `actor`/`activation` fields and the `commit_sha`
+payload are host-observed at the gate, so attribution cannot be forged by
+the committing agent.
+
+## Implementation chunks
+
+1. **(this PR — PRD only.)** The contract above. No code; scheduled to land
+   right after #468.
+2. **Envelope + canonical + chain core.** `AuditEvent` dataclass,
+   `canonical()`, chain hashing, and the single-writer journal appender in
+   `bot_bottle/store/` (reusing `sha256_hex`); redaction wired to the
+   existing `gateway/egress/dlp_detectors` (`scan_token_patterns` /
+   `redact_tokens`); embed the git SHA at build so `engine` is populated
+   (only `version = "0.1.0"` exists in `pyproject.toml` today — the build
+   must stamp the SHA); unit tests for determinism, chain-break detection,
+   `epoch`/`seq` continuity across a simulated restart, and redaction of
+   both a deny-listed key and a token-shaped value.
+3. **SQLite index + `audit` CLI.** New `audit_events` migration (indexable
+   fields above); replay-from-journal; offline chain verifier
+   (`truncated-tail` vs `gap`); `query` / `verify` / `rebuild` / `import`;
+   idempotent `UPSERT` by `id`.
+4. **Host controller as first producer (#468).** Wire
+   `lifecycle.bottled_agent_*` and `hostctl.*` emission into the host
+   controller; establish the `epoch` bump + chain-head carry + segment
+   rotation on writer restart here (it owns the single writer).
+5. **Migrate existing producers.** Re-emit supervise `decision.*` (retiring
+   the standalone `supervise_audit_entries` shape behind the index), egress
+   `egress.*`, git-gate `forge.*` + `commit.signed` (#480), control-plane
+   `auth.*`; add the `audit.*` self-events (verify/truncation/export
+   failure).
+6. **CloudEvents / OTel export adapters + #324 delivery.** Projection layer
+   (field re-map per *Export / interoperability*) plus the outbox cursor,
+   ack-driven advance, and retention-ordering guard the #324 contract
+   specifies.
+7. **(follow-up.)** Cross-host merge transport; per-writer signing +
+   external anchoring on the chain head; retention/rotation *schedule*.
+
+## Acceptance-criteria coverage (#487)
+
+The issue defines the contract; implementation is explicitly split into
+follow-up PRs. This PRD is the durable decision record; each acceptance box
+maps to a section:
+
+| #487 acceptance criterion | Where |
+|---|---|
+| Durable PRD defines versioned envelope + initial registry | *The envelope*, *Event registry* |
+| Canonical JSON + hash-chain rules, unambiguous, with test vectors | *Canonical serialization + hash chain* → *Test vectors* |
+| Trust provenance explicit for every common + event-specific field | *Trust provenance of every common field*; per-type `untrusted` in *Event registry* |
+| Redaction prohibits credentials / raw secrets / unsafe capture by default | *Redaction rule*; `untrusted`-only claims; sensitivity classes |
+| JSONL journal canonical; SQLite index fully rebuildable | *Journal + SQLite index* (`audit rebuild`) |
+| Minimum local search/query contract | *Journal + SQLite index* → *Local query surface* |
+| #324 can transport/replay without a second envelope | *The #324 delivery contract* |
+| #480 maps in without weakening its byte-to-activation-key guarantee | *#480 signed-commit attribution maps in…* |
+| Schema evolution + backward-compatible readers | *Schema evolution & backward-compatible readers* |
+| Integrity detects modification / deletion / reorder / bad continuation | *Test vectors* (tamper), *Behavior across rotation…truncation*, `audit verify` |
+
+Two acceptance items are **specified here, implemented later** by design
+(the issue permits this): the concrete test-vector *fixtures* and the
+`audit` CLI land in impl chunks 2–3; the #324 outbox lands in chunk 6.
+Nothing in the contract is left undefined — only its code is deferred.
+
+## Resolved in review (#495)
+
+- **Single writer per host — decided.** The host controller owns the sole
+  appender; per-producer chains are a future scaling path only. (Design →
+  *Single writer; ordering across restarts*.)
+- **Restarts — decided.** An `epoch` counter (bumped per writer boot) plus
+  carrying the last chain head as the next `prev` gives a total order of
+  `(epoch, seq)` that survives restarts; `ts_mono` orders only within an
+  epoch. (Design → *ordering across restarts*.)
+- **Flatten to one `untrusted` region — decided.** Everything outside
+  `untrusted` (chain metadata, `producer`/`host`, `bottled_agent`, `ts_*`)
+  is trusted by construction, so the separate `trusted` sub-block is
+  removed; a field is trusted unless deliberately placed under `untrusted`.
+  (Design → *The envelope*.)
+- **Subject term is `bottled_agent` everywhere** — the top-level field and
+  the `lifecycle.bottled_agent_*` leaf names. (Design → *The envelope* /
+  *Event registry*.)
+- **Retention head-carry — yes.** When a journal segment is rotated out,
+  the new segment's first record carries the rotated-out head as `prev`, so
+  the verifier still trusts the current head across a rotation. (Folds into the
+  retention follow-up.)
+- **Redaction reuses the egress detectors — yes, scoped.** Reuse the
+  deterministic `dlp_detectors` (`scan_token_patterns` / `redact_tokens` /
+  `scan_known_secrets`); exclude `scan_entropy` as brittle on the short,
+  high-entropy structured values audit records carry. (Design → *Redaction
+  rule*.)
+
+## Open questions
+
+- **Value-scan cost on the hot path.** The single writer runs the reused
+  detectors on every event's `untrusted` block inline. Is that cheap enough
+  at lifecycle-event volume, or should the value scan move to index-build
+  time (journal stays raw, index stores the redacted view)? Leaning inline
+  so the raw journal never contains a leaked value in the first place.
+- **`epoch` persistence location.** Store the per-writer `epoch` + chain
+  head in the SQLite index (rebuildable, but then the writer needs the DB
+  at boot) or in a tiny sidecar file next to the journal (independent of
+  the index)? Leaning sidecar, so the writer can start and append without
+  the index present.

docs/prds/prd-new-host-control-server.md

@@ -1,273 +0,0 @@
-# PRD prd-new: Host control server
-
-- **Status:** Draft
-- **Author:** Claude
-- **Created:** 2026-07-26
-- **Issue:** #468
-
-## Summary
-
-Promote the in-process launch broker into a standalone **host control
-server**: the single privileged component on the host. Both the CLI and the
-orchestrator drive it over HTTP; it brokers agent launches, owns the
-orchestrator's own lifecycle, and is the sole writer of host-durable state (the
-tamper-evident audit record). This closes the three gaps between today's
-well-formed broker *contract* ([`orchestrator/broker.py`](../../bot_bottle/orchestrator/broker.py))
-and a real out-of-process service — transport, durable provisioned secret,
-and a disciplined op vocabulary — and splits host state by
-owner and lifetime. The prize: **the CLI no longer needs the Docker socket**,
-which is what finally lets a dedicated Gitea runner user drop the
-root-equivalent `docker` group (PRD 0070, "Relationship to other work").
-
-## Problem
-
-Container launches run directly from a short-lived CLI process against the
-Docker socket. That socket is root-equivalent, so every host that launches
-bottles hands root to whoever invokes the CLI — including a CI runner user we
-want to keep unprivileged. PRD 0070 already argues for replacing the fat socket
-with a **thin, structured, auditable** launch broker, and the contract for that
-broker exists and is tested in-process. But it is *only* in-process:
-`LaunchBroker.submit(token)` is a method call from
-`OrchestratorCore.launch_bottle` ([`service.py:116`](../../bot_bottle/orchestrator/service.py)),
-and `DockerBroker` is on no production path — every backend starts the
-orchestrator with `--broker stub` ([`__main__.py:54`](../../bot_bottle/orchestrator/__main__.py)).
-
-Three gaps stand between that scaffold and a host service:
-
-1. **No transport.** `submit` is an in-process call. A real service needs a
-   `BrokerClient` that POSTs the signed token and a host-side HTTP server that
-   verifies and acts.
-2. **The signing secret is ephemeral and self-generated.**
-   [`__main__.py:53`](../../bot_bottle/orchestrator/__main__.py) does
-   `secrets.token_bytes(32)` and hands the *same value* to signer and verifier —
-   viable only because they share a process. A separate daemon needs the secret
-   provisioned out of band and durable across orchestrator restarts.
-3. **The op vocabulary is `launch` / `teardown` only.** Everything else
-   host-privileged still lives in the CLI, so the schema has to grow — carefully,
-   since PRD 0070's security argument rests on "structured requests only, static
-   flags + ids."
-
-Separately, host state has no clear owner. `OrchestratorCore.reconcile` takes
-`live_source_ips` as a parameter *only because the orchestrator cannot see the
-backend* ([`service.py:137`](../../bot_bottle/orchestrator/service.py)); the
-egress traffic log is written to the container's stderr; and there is no durable,
-tamper-evident home for the audit record that survives orchestrator destruction.
-
-## Goals / Success Criteria
-
-- A standalone host control server that the CLI and orchestrator reach over
-  **HTTP**, with three entry paths working end to end:
-  - `web console -(iroh)-> orchestrator -(http)-> host controller -> launch`
-  - `cli -(http)-> orchestrator -(http)-> host controller -> launch`
-  - `cli -(http)-> host controller` — start / restart / status of the
-    orchestrator **itself** (the bootstrap/recovery path #391 targets).
-- The launch op is expressed as a **signed JWT of static flags + ids only**,
-  verified against a closed schema.
-- The signing secret is **provisioned out of band and durable** across
-  orchestrator restarts (a `TrustDomain` per #476, with a key the orchestrator
-  never holds for the host controller's *own* endpoints).
-- Host-privileged operations move off the CLI to the control server; **the CLI
-  no longer opens the Docker socket** for bottle operations.
-- `Orchestrator.reconcile` no longer takes `live_source_ips` — live-bottle
-  enumeration becomes an internal control-server call.
-- Host-durable state lands as an **append-only, hash-chained JSONL** audit log
-  owned solely by the host controller; operational state stays SQLite owned
-  solely by the orchestrator.
-
-## Non-goals
-
-- **Removing standing privilege.** This converts on-demand privilege (a CLI the
-  user invokes) into standing privilege (a daemon under launchd/systemd). The
-  win is that the privilege is *narrower* (structured requests vs. a raw socket),
-  not that it disappears. "Always running" is an accepted new property.
-- **Asymmetric signing.** We stay HS256 — see Design / "Signing stays
-  symmetric."
-- **Integrity against a live compromised orchestrator.** Host-location of the
-  audit log does not buy this: the orchestrator makes the decisions being audited
-  and can forge or omit entries wherever the file lives. An off-box copy is the
-  answer, tracked separately.
-- **A single unified DB for all state.** Impossible over a guest-kernel share
-  (SQLite locking is not coherent); state is split by owner and lifetime instead.
-- **The generic `SecretProvider` (#355)** and **remote terminal design (#478)** —
-  both ride the same door but are their own work.
-
-## Design
-
-### Topology
-
-The host controller is the sole privileged component. The orchestrator becomes a
-client of it for launches, and the CLI becomes a client of it for *both* bottle
-operations (indirectly, through the orchestrator) and orchestrator lifecycle
-(directly, for bootstrap/recovery — startup can't route through the thing being
-started).
-
-```
-web console ─(iroh)─▶ orchestrator ─┐
-                                    ├─(http, signed JWT)─▶ host controller ─▶ launch
-cli ────────(http)──▶ orchestrator ─┘
-cli ────────(http, bearer)──────────────────────────────▶ host controller   (orchestrator lifecycle)
-```
-
-### Transport: `BrokerClient` + host server
-
-`LaunchBroker.submit(token)` keeps its exact signature and semantics; only the
-*wire* changes. A new `BrokerClient` implements the same submit contract by
-POSTing the signed token to the host controller (stdlib `urllib`, like the
-existing [`orchestrator/client.py`](../../bot_bottle/orchestrator/client.py)),
-and the host controller's launch handler is the existing `verify_request` +
-`_launch`/`_teardown` path, now reached over HTTP instead of a method call. The
-in-process `StubBroker` stays for the dev-harness and tests; `DockerBroker`'s
-`_launch`/`_teardown` bodies move behind the server unchanged. Because the client
-satisfies the same interface `OrchestratorCore` already depends on, the core does
-not change to gain a real backend.
-
-### Signing stays symmetric (HS256)
-
-PRD 0070 nominally specifies asymmetric; the code is HS256 and we keep it.
-Asymmetric matters when the verifier is *less* privileged than the signer — here
-it is the reverse: the host controller (verifier) is strictly more privileged
-than the orchestrator (signer), and a controller that could forge orchestrator
-requests gains nothing, since it is already the component that launches. Staying
-symmetric also honors the no-runtime-deps policy (stdlib has no Ed25519). This
-matches the reasoning already inlined in `broker.py`'s module docstring.
-
-### Replay protection is out of scope (tracked in #494)
-
-Once the launch token travels over a wire, a captured token could be replayed —
-`sign_request` already emits `jti`/`iat` but `verify_request` reads neither, so
-there is no expiry window or `jti` cache today. Enforcing that (an `iat` window +
-a self-trimming `jti` cache) is a pure in-process change that lands independently
-of this work, and it is deferred to **#494** rather than gating the MVP of the
-host control server. Nothing here depends on it; it can merge before or after.
-
-### Op vocabulary and the "ids + static flags" rule (gap 3)
-
-Each op moved off the CLI widens the privileged surface, so growth is governed by
-one explicit rule, enforced in `verify_request`'s schema check:
-
-> A broker op carries **only ids and enumerated static flags** — a bottle id, a
-> pool slot, a **content-addressed** image ref chosen from a fixed set, an op
-> name from a closed vocabulary. Never a free-form path, argv, command, or
-> caller-supplied filesystem location. If an operation cannot be expressed that
-> way, it does not become a broker op.
-
-Operations that fit and move off the CLI (all today in
-`backend/*/consolidated_launch.py`, driven by a short-lived CLI process):
-
-| Op | What it does | Fits the rule because |
-|---|---|---|
-| `launch` / `teardown` | existing | ids + slot + image ref |
-| `orchestrator.ensure_running` | start the infra container | no arguments |
-| `orchestrator.{start,restart,status}` | lifecycle (the #391 path) | no arguments |
-| `list_live` | enumerate running bottles for reconcile | no arguments; returns ids/IPs |
-| `allocate_ip` | `next_free_ip` over `_network_container_ips` | no arguments; returns an IP |
-| `provision_git_gate` | `cp`/`exec` a per-bottle deploy key into the gateway | bottle id + key handle, no path |
-| `reprovision` | `docker exec printenv <ENV_VAR_SECRET>` on a live agent | bottle id + secret *name* |
-
-Image **builds** stay with the orchestrator for v1 (PRD 0070 §Memory: builds run
-control-plane-side; a dedicated slim build unit is later, #468-adjacent), so no
-`build` broker op is added here.
-
-With `list_live` as an internal control-server call, `Orchestrator.reconcile`'s
-`live_source_ips` parameter goes away — the tell PRD 0070 called out that the
-orchestrator couldn't see the backend disappears with it.
-
-### Secret provisioning (gap 2)
-
-The shared HS256 secret becomes a durable, out-of-band artifact via the
-**`TrustDomain`** seam (#476,
-[`trust_domain.py`](../../bot_bottle/trust_domain.py)):
-
-- The **launch-broker secret** is a `TrustDomain` whose key
-  (`host_signing_key(<file>)`, minted 0600 on first use, durable under
-  `bot_bottle_root()`) is provisioned to the orchestrator (signer) and the host
-  controller (verifier). Durability across orchestrator restarts is what makes
-  re-adoption work — a restart re-verifies against the same key.
-- The **host controller's own lifecycle endpoints** (the direct `cli -> host
-  controller` path) get a **separate** `TrustDomain` key the orchestrator never
-  holds — exactly the second domain #476's PRD reserves. The orchestrator must
-  not be able to mint the credentials used to start and stop it.
-
-This reuses the seam #476 landed rather than re-deriving provisioning per
-backend (the PR #471 bug class).
-
-### One daemon, structurally separate handlers (open decision 1)
-
-The audit writer and the broker live in **one daemon** for install simplicity,
-but with **no shared parsing** and **different credentials per handler**:
-
-- the **launch** handler requires the signed launch **JWT** (provenance +
-  un-coercible schema);
-- the **audit-append** handler takes a plain **bearer token** and writes to the
-  JSONL log.
-
-This does not defend against orchestrator compromise (it holds both creds) — it
-stops a bug in the boring audit path from reaching the privileged launch path.
-The launcher stays small enough to audit line-by-line, per PRD 0070.
-
-### State ownership: split by owner and lifetime
-
-A single mounted DB is impossible — SQLite locking is not coherent across guest
-kernels over a share, which is why the macOS backend already uses a container-only
-volume (`INFRA_DB_VOLUME`). So state splits three ways (depends on #469, which
-gets `bot-bottle.db` off the data plane first):
-
-| Owner | State | Home | Shape |
-|---|---|---|---|
-| **Orchestrator** | `orchestrator_bottles` registry; `bottled_agent_secrets` (encrypted egress tokens); `supervise_proposals` / `supervise_responses` | volume nothing else mounts (generalizing the macOS design) | **SQLite** — mutable, transactional, queried |
-| **Host controller** | supervise audit entries; egress traffic log (today → container stderr); host-side config | host filesystem, survives orchestrator/volume destruction | **JSONL** — append-only |
-| **Gateway** | none | — | after #469 the data plane holds no DB state |
-
-The historical record is **JSONL, not SQLite**, because it is append-only, never
-updated, never transactionally queried: `O_APPEND` writes are atomic, there is no
-locking protocol to get wrong, hash-chaining for tamper-evidence is cheap, and it
-survives container-runtime volume pruning (the #450 lesson) and stays readable
-without the orchestrator running. Both halves of "the audit record" — supervise
-decisions and the egress traffic log — land in the one place.
-
-The orchestrator is **sole mounter and sole writer** of its SQLite volume; the
-host controller is **sole writer** of the JSONL log, over the authenticated
-audit-append channel.
-
-## Implementation chunks
-
-Ordered, each independently mergeable:
-
-1. **`BrokerClient` + host launch server** over HTTP, reusing `verify_request`
-   and the existing `DockerBroker` bodies. Wire `OrchestratorCore` to a
-   `BrokerClient` behind a flag; keep `StubBroker` for the dev-harness. Closes
-   gap 1.
-2. **Durable secret via `TrustDomain`** — provision the launch-broker key to
-   signer + verifier; add the host controller's own lifecycle `TrustDomain`.
-   Closes gap 2.
-3. **Grow the op vocabulary** one op at a time (`list_live` first — it also
-   removes `reconcile`'s `live_source_ips`), each behind the ids + static-flags
-   rule. Closes gap 3.
-4. **JSONL audit log** — the host-controller-owned, hash-chained historical
-   record with the plain-bearer audit-append handler; redirect the egress traffic
-   log into it.
-5. **Drop the Docker socket from the CLI** once every host-privileged op it used
-   is a broker op — the payoff that unblocks the unprivileged Gitea runner user.
-
-## Open questions
-
-1. **Schema-width rule enforcement.** The "ids + static flags" rule is stated;
-   should `verify_request` reject unknown claim keys outright (strict schema) to
-   keep the surface from drifting? Leaning yes.
-2. **Audit-append back-pressure.** What the audit handler does if the JSONL sink
-   is unavailable (fail-closed vs. buffer) — resolve before shipping chunk 5.
-
-## References
-
-- **PRD 0070** — the contract, the launch broker, and the state tiers this
-  implements.
-- **#469** — get `bot-bottle.db` off the data plane (lands underneath this).
-- **#476** ([`prd-new-control-plane-auth-provisioning`](prd-new-control-plane-auth-provisioning.md))
-  — the `TrustDomain` seam this plugs the host controller's key into.
-- **#391** — backend-agnostic orchestrator restart (the bootstrap path).
-- **#494** — enforce broker replay protection (`iat` window + `jti` cache); split
-  out of this PRD as an independent in-process change.
-- **#386** — prebuilt images from the Gitea OCI registry (the fixed image set the
-  broker validates against).
-- **#355** — generic `SecretProvider`.
-- **#478** — remote terminal design.

scripts/coverage.sh

@@ -20,10 +20,10 @@ cd "$(dirname "$0")/.."
 
 PY="${PYTHON:-python3}"
 
-# Critical security/logic core held to the high bar by ADR 0004. The helper
-# fails before coverage when a curated path was renamed or removed; Coverage.py
-# itself would silently ignore that stale include and inflate the score.
-CRITICAL=$("$PY" scripts/critical_modules.py)
+# Critical security/logic core held to the high bar by ADR 0004. The list
+# lives in one place (scripts/critical-modules.txt) so this report and the
+# README "core coverage" badge can't drift; comma-join it for --include.
+CRITICAL=$(grep -vE '^[[:space:]]*(#|$)' scripts/critical-modules.txt | paste -sd, -)
 
 if [ "${1:-}" = "aggregate" ]; then
     # Aggregate mode: combine .coverage.* artifacts already in the workspace.
@@ -34,8 +34,8 @@ if [ "${1:-}" = "aggregate" ]; then
     "$PY" -m coverage report -m
 
     if [ "${2:-}" = "critical" ]; then
-        echo "== critical modules (ADR 0004 minimum: 90%) ==" >&2
-        "$PY" -m coverage report --include="$CRITICAL" --fail-under=90
+        echo "== critical modules (ADR 0004 target: 90%) ==" >&2
+        "$PY" -m coverage report --include="$CRITICAL"
     fi
     exit 0
 fi
@@ -55,6 +55,6 @@ echo "== combined report ==" >&2
 "$PY" -m coverage report -m
 
 if [ "${1:-}" = "critical" ]; then
-    echo "== critical modules (ADR 0004 minimum: 90%) ==" >&2
-    "$PY" -m coverage report --include="$CRITICAL" --fail-under=90
+    echo "== critical modules (ADR 0004 target: 90%) ==" >&2
+    "$PY" -m coverage report --include="$CRITICAL"
 fi

scripts/critical-modules.txt

@@ -7,48 +7,19 @@
 # number that silently stops measuring a module is worse than no badge.
 #
 # One module path per line, relative to the repo root. Blank lines and
-# `#` comments are ignored. scripts/critical_modules.py rejects missing,
-# duplicate, non-Python, and out-of-repository entries before coverage runs.
-
-# Host-side egress planning and secret preparation.
-bot_bottle/egress/plan.py
-bot_bottle/egress/service.py
-
-# Gateway egress policy, matching, and DLP enforcement.
+# `#` comments are ignored.
 bot_bottle/gateway/egress/addon.py
 bot_bottle/gateway/egress/addon_core.py
-bot_bottle/gateway/egress/context.py
-bot_bottle/gateway/egress/dlp.py
-bot_bottle/gateway/egress/dlp_config.py
 bot_bottle/gateway/egress/dlp_detectors.py
-bot_bottle/gateway/egress/matching.py
-bot_bottle/gateway/egress/schema.py
-bot_bottle/gateway/egress/types.py
-
-# Manifest trust boundary and schema.
-bot_bottle/manifest/agent.py
-bot_bottle/manifest/bottle.py
-bot_bottle/manifest/egress.py
-bot_bottle/manifest/extends.py
-bot_bottle/manifest/git.py
-bot_bottle/manifest/index.py
-bot_bottle/manifest/loader.py
-bot_bottle/manifest/schema.py
-bot_bottle/manifest/util.py
-
-# Host-side and gateway-side git policy enforcement.
-bot_bottle/git_gate/host_key.py
-bot_bottle/git_gate/plan.py
-bot_bottle/git_gate/provision.py
-bot_bottle/git_gate/service.py
+bot_bottle/egress.py
+bot_bottle/manifest.py
+bot_bottle/manifest_egress.py
+bot_bottle/manifest_agent.py
+bot_bottle/manifest_schema.py
+bot_bottle/git_gate.py
 bot_bottle/gateway/git_gate/render.py
+bot_bottle/git_gate_provision.py
 bot_bottle/gateway/git_gate/http_backend.py
-
-# Supervise proposal protocol and data plane.
-bot_bottle/supervisor/plan.py
-bot_bottle/supervisor/types.py
-bot_bottle/gateway/supervisor/server.py
-
-# Shared parsers and state validation.
+bot_bottle/supervise.py
 bot_bottle/yaml_subset.py
 bot_bottle/bottle_state.py

scripts/critical_modules.py

@@ -1,101 +0,0 @@
-#!/usr/bin/env python3
-"""Validate and render the critical-module coverage manifest.
-
-Coverage.py silently ignores an ``--include`` path that does not exist.  That
-is useful for broad globs, but dangerous for bot-bottle's curated security
-core: a rename could otherwise improve the reported percentage by removing a
-module from the measurement.  Keep the validation in one small stdlib helper
-and make every coverage consumer call it.
-"""
-
-from __future__ import annotations
-
-import argparse
-import sys
-from pathlib import Path
-
-
-REPO_ROOT = Path(__file__).resolve().parents[1]
-DEFAULT_MANIFEST = REPO_ROOT / "scripts" / "critical-modules.txt"
-
-
-class CriticalModulesError(ValueError):
-    """The critical-module manifest is empty, ambiguous, or stale."""
-
-
-def load_critical_modules(manifest: Path, *, root: Path) -> list[str]:
-    """Return validated module paths relative to *root*.
-
-    Entries must be unique, concrete Python files inside the repository.
-    Globs are deliberately rejected by the file check: each rename must update
-    this explicit security review surface.
-    """
-
-    root = root.resolve()
-    try:
-        lines = manifest.read_text(encoding="utf-8").splitlines()
-    except OSError as exc:
-        raise CriticalModulesError(
-            f"cannot read critical-module manifest {manifest}: {exc}"
-        ) from exc
-
-    modules: list[str] = []
-    seen: set[str] = set()
-    errors: list[str] = []
-    for line_number, raw in enumerate(lines, start=1):
-        entry = raw.strip()
-        if not entry or entry.startswith("#"):
-            continue
-        path = Path(entry)
-        prefix = f"{manifest}:{line_number}: {entry!r}"
-        if path.is_absolute():
-            errors.append(f"{prefix} must be relative to the repository root")
-            continue
-        try:
-            resolved = (root / path).resolve()
-            resolved.relative_to(root)
-        except ValueError:
-            errors.append(f"{prefix} escapes the repository root")
-            continue
-        if entry in seen:
-            errors.append(f"{prefix} is duplicated")
-            continue
-        seen.add(entry)
-        if path.suffix != ".py":
-            errors.append(f"{prefix} is not a Python module")
-            continue
-        if not resolved.is_file():
-            errors.append(f"{prefix} does not exist")
-            continue
-        modules.append(path.as_posix())
-
-    if not modules and not errors:
-        errors.append(f"{manifest}: contains no critical modules")
-    if errors:
-        raise CriticalModulesError("\n".join(errors))
-    return modules
-
-
-def main(argv: list[str] | None = None) -> int:
-    parser = argparse.ArgumentParser(
-        description="validate and print the critical coverage include list"
-    )
-    parser.add_argument("--manifest", type=Path, default=DEFAULT_MANIFEST)
-    parser.add_argument("--root", type=Path, default=REPO_ROOT)
-    parser.add_argument(
-        "--check", action="store_true",
-        help="validate only; do not print the comma-separated include list",
-    )
-    args = parser.parse_args(argv)
-    try:
-        modules = load_critical_modules(args.manifest, root=args.root)
-    except CriticalModulesError as exc:
-        print(f"critical-modules: {exc}", file=sys.stderr)
-        return 1
-    if not args.check:
-        print(",".join(modules))
-    return 0
-
-
-if __name__ == "__main__":
-    raise SystemExit(main())

scripts/unittest_gate.py

@@ -1,67 +0,0 @@
-#!/usr/bin/env python3
-"""Run unittest discovery with explicit execution-count assurances.
-
-The standard unittest CLI exits successfully when a suite contains skipped
-tests. That is normally useful, but it let the Docker integration job stay
-green while its security-boundary classes were all skipped under act_runner.
-This wrapper keeps normal unittest output and adds opt-in minimum-executed and
-no-skip gates for jobs that promise a concrete integration surface.
-"""
-
-from __future__ import annotations
-
-import argparse
-import sys
-import unittest
-
-
-def assurance_errors(
-    *, tests_run: int, skipped: int, minimum_executed: int, fail_on_skip: bool
-) -> list[str]:
-    """Return human-readable assurance failures for a completed suite."""
-
-    executed = tests_run - skipped
-    errors: list[str] = []
-    if executed < minimum_executed:
-        errors.append(
-            f"executed {executed} test(s), below required minimum "
-            f"{minimum_executed} (discovered {tests_run}, skipped {skipped})"
-        )
-    if fail_on_skip and skipped:
-        errors.append(f"{skipped} test(s) skipped in a no-skip suite")
-    return errors
-
-
-def main(argv: list[str] | None = None) -> int:
-    parser = argparse.ArgumentParser(
-        description="unittest discovery with execution-count assurance"
-    )
-    parser.add_argument("-s", "--start-directory", default=".")
-    parser.add_argument("-t", "--top-level-directory", default=None)
-    parser.add_argument("-p", "--pattern", default="test*.py")
-    parser.add_argument("--minimum-executed", type=int, default=0)
-    parser.add_argument("--fail-on-skip", action="store_true")
-    parser.add_argument("-v", "--verbose", action="store_true")
-    args = parser.parse_args(argv)
-
-    suite = unittest.defaultTestLoader.discover(
-        args.start_directory,
-        pattern=args.pattern,
-        top_level_dir=args.top_level_directory,
-    )
-    result = unittest.TextTestRunner(
-        verbosity=2 if args.verbose else 1,
-    ).run(suite)
-    failures = assurance_errors(
-        tests_run=result.testsRun,
-        skipped=len(result.skipped),
-        minimum_executed=args.minimum_executed,
-        fail_on_skip=args.fail_on_skip,
-    )
-    for failure in failures:
-        print(f"unittest-gate: {failure}", file=sys.stderr)
-    return 0 if result.wasSuccessful() and not failures else 1
-
-
-if __name__ == "__main__":
-    raise SystemExit(main())

tests/README.md

@@ -20,11 +20,10 @@ tests/
     ...                             # many others; see unit/ directory
   integration/
     test_gateway_image.py
-    test_sandbox_escape.py
+    test_dry_run_plan.py
     test_orphan_cleanup.py
     ...
-  canaries/
-    test_gitleaks_release.py        # opt-in upstream artifact check
+  canaries/                         # opt-in; see below (currently empty)
 ```
 
 Classification falls out of the directory — no hand-maintained list to
@@ -44,27 +43,24 @@ Discovery is invoked with `-t .` (top-level dir = repo root) so the
 
 ## What the integration tests cover
 
+- `test_dry_run_plan.py` — `cli.py start --dry-run --format=json` emits
+  a structured plan that contains the resolved egress allowlist and
+  the bottle's runtime, and creates zero Docker resources.
 - `test_orphan_cleanup.py` — `network_remove` is idempotent against
   missing resources, so the EXIT trap can call it unconditionally.
 - `test_gateway_image.py` — builds Dockerfile.gateway and
   probes that gitleaks / mitmdump / supervise are all reachable
   inside the gateway image.
-- `test_orchestrator_docker_auth.py` — drives the real control-plane
-  container and verifies role-scoped authentication.
-- `test_multitenant_isolation.py` and `test_sandbox_escape.py` — exercise
-  token/allowlist separation and end-to-end escape attempts.
 
 ## Canaries
 
 `tests/canaries/` holds upstream-regression checks gated on
 `BOT_BOTTLE_RUN_CANARIES=1` and not part of the per-push suite.
-They're invoked by the scheduled `canaries` workflow. The gitleaks canary
-downloads the exact release archive pinned by `Dockerfile.gateway`, verifies
-its architecture-specific checksum, and executes the binary.
+They're invoked by the scheduled `canaries` workflow. Currently
+no canaries are defined.
 
 ```bash
-BOT_BOTTLE_RUN_CANARIES=1 python -m scripts.unittest_gate \
-  -t . -s tests/canaries -v --minimum-executed 1 --fail-on-skip
+BOT_BOTTLE_RUN_CANARIES=1 python -m unittest discover -t . -s tests/canaries -v
 ```
 
 ## What's NOT covered

tests/canaries/test_gitleaks_release.py

@@ -1,85 +0,0 @@
-"""Canary: the pinned gitleaks release remains downloadable and executable.
-
-The gateway Dockerfile verifies this archive during an image build. Repeating
-the upstream check weekly keeps registry/release drift out of normal pull
-requests while proving that the pinned URL, architecture checksum, archive
-shape, and binary still agree.
-"""
-
-from __future__ import annotations
-
-import hashlib
-import os
-import platform
-import re
-import subprocess
-import tarfile
-import tempfile
-import unittest
-import urllib.request
-from pathlib import Path
-
-
-ROOT = Path(__file__).resolve().parents[2]
-DOCKERFILE = ROOT / "Dockerfile.gateway"
-
-
-def _docker_arg(text: str, name: str) -> str:
-    match = re.search(rf"^ARG {re.escape(name)}=(\S+)$", text, re.MULTILINE)
-    if match is None:
-        raise AssertionError(f"Dockerfile.gateway has no concrete ARG {name}")
-    return match.group(1)
-
-
-@unittest.skipUnless(
-    os.environ.get("BOT_BOTTLE_RUN_CANARIES") == "1",
-    "canary suite is opt-in; set BOT_BOTTLE_RUN_CANARIES=1 to run",
-)
-class TestGitleaksRelease(unittest.TestCase):
-    def test_pinned_archive_checksum_and_binary(self) -> None:
-        dockerfile = DOCKERFILE.read_text(encoding="utf-8")
-        version = _docker_arg(dockerfile, "GITLEAKS_VERSION")
-        machine = platform.machine().lower()
-        architectures = {
-            "x86_64": ("linux_x64", "GITLEAKS_SHA256_AMD64"),
-            "amd64": ("linux_x64", "GITLEAKS_SHA256_AMD64"),
-            "aarch64": ("linux_arm64", "GITLEAKS_SHA256_ARM64"),
-            "arm64": ("linux_arm64", "GITLEAKS_SHA256_ARM64"),
-        }
-        if machine not in architectures:
-            self.fail(f"unsupported canary runner architecture: {machine}")
-        asset, checksum_arg = architectures[machine]
-        expected_checksum = _docker_arg(dockerfile, checksum_arg)
-        url = (
-            "https://github.com/gitleaks/gitleaks/releases/download/"
-            f"v{version}/gitleaks_{version}_{asset}.tar.gz"
-        )
-
-        with tempfile.TemporaryDirectory(prefix="bot-bottle-gitleaks-canary.") as tmp:
-            archive = Path(tmp) / "gitleaks.tar.gz"
-            urllib.request.urlretrieve(url, archive)
-            self.assertEqual(
-                expected_checksum,
-                hashlib.sha256(archive.read_bytes()).hexdigest(),
-                "the pinned upstream archive no longer matches Dockerfile.gateway",
-            )
-            with tarfile.open(archive, "r:gz") as bundle:
-                member = bundle.getmember("gitleaks")
-                source = bundle.extractfile(member)
-                if source is None:
-                    self.fail("gitleaks archive member is not a regular file")
-                binary = Path(tmp) / "gitleaks"
-                binary.write_bytes(source.read())
-            binary.chmod(0o755)
-            result = subprocess.run(
-                [str(binary), "version"],
-                capture_output=True,
-                text=True,
-                check=False,
-            )
-            self.assertEqual(0, result.returncode, result.stderr)
-            self.assertIn(version, result.stdout + result.stderr)
-
-
-if __name__ == "__main__":
-    unittest.main()

tests/integration/test_gateway_image.py

@@ -14,7 +14,9 @@ the chunk-1 contract:
     expected "no daemons selected" line when the supervisor is
     pointed at an empty daemon set.
 
-Skips cleanly only when the selected Docker backend is unavailable.
+Skips cleanly when docker is unavailable, or under act_runner
+where the host bind-mount topology breaks multi-stage builds
+that pull large bases.
 """
 
 from __future__ import annotations
@@ -31,6 +33,12 @@ _DOCKERFILE = "Dockerfile.gateway"
 
 
 @skip_unless_backend("docker")
+@unittest.skipIf(
+    os.environ.get("GITEA_ACTIONS") == "true",
+    "skipped under act_runner: multi-stage build pulls a 200+MB "
+    "mitmproxy base + two upstream gateway images; runner storage "
+    "+ time budget make this an interactive-only test",
+)
 class TestGatewayImage(unittest.TestCase):
     """Builds the image once for the class, then runs a few
     `docker run` probes against it."""
@@ -43,11 +51,10 @@ class TestGatewayImage(unittest.TestCase):
              "-f", _DOCKERFILE, "."],
             cwd=repo_root,
             stdout=subprocess.PIPE, stderr=subprocess.STDOUT,
-            check=False,
         )
         if proc.returncode != 0:
-            raise AssertionError(
-                f"docker build failed; image probes cannot run.\n"
+            raise unittest.SkipTest(
+                f"docker build failed; skipping image probes.\n"
                 f"{proc.stdout.decode('utf-8', errors='replace')[-2000:]}"
             )
 
@@ -56,16 +63,14 @@ class TestGatewayImage(unittest.TestCase):
         subprocess.run(
             ["docker", "image", "rm", "-f", _IMAGE],
             stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL,
-            check=False,
         )
 
     def _run_in_image(self, *cmd: str, timeout: float = 30.0) -> tuple[int, str]:
         proc = subprocess.run(
             ["docker", "run", "--rm", "--entrypoint", cmd[0], _IMAGE,
-            *cmd[1:]],
+             *cmd[1:]],
             stdout=subprocess.PIPE, stderr=subprocess.STDOUT,
             timeout=timeout,
-            check=False,
         )
         return proc.returncode, proc.stdout.decode("utf-8", errors="replace")
 
@@ -86,9 +91,7 @@ class TestGatewayImage(unittest.TestCase):
         # Probe that the package imports resolve inside the image.
         rc, out = self._run_in_image(
             "python3", "-c",
-            "from bot_bottle.supervisor import types; "
-            "from bot_bottle.gateway.supervisor import server as supervise_server; "
-            "print('ok')",
+            "from bot_bottle.supervisor import types; from bot_bottle.gateway.supervisor import server as supervise_server; print('ok')",
         )
         self.assertEqual(0, rc, msg=out)
         self.assertIn("ok", out)
@@ -103,7 +106,6 @@ class TestGatewayImage(unittest.TestCase):
              _IMAGE],
             stdout=subprocess.PIPE, stderr=subprocess.STDOUT,
             timeout=10.0,
-            check=False,
         )
         out = proc.stdout.decode("utf-8", errors="replace")
         self.assertEqual(0, proc.returncode, msg=out)

tests/integration/test_multitenant_isolation.py

@@ -16,10 +16,11 @@ throwaway BOT_BOTTLE_ROOT for a clean registry and tears everything down.
 
 from __future__ import annotations
 
-import secrets
+import os
 import subprocess
-import time
+import tempfile
 import unittest
+from pathlib import Path
 
 from bot_bottle.backend.docker.consolidated_launch import (
     _network_cidr,
@@ -72,12 +73,19 @@ _PROBE_SRC = (
 
 
 @skip_unless_backend("docker")
+@unittest.skipIf(
+    os.environ.get("GITEA_ACTIONS") == "true",
+    "skipped under act_runner: the orchestrator container bind-mounts the repo "
+    "path into a container on the socket-shared host daemon, which can't see the "
+    "runner's /workspace — same host-bind-mount constraint as the other "
+    "bottle-bringup integration tests",
+)
 class TestMultitenantIsolation(unittest.TestCase):
     def setUp(self) -> None:
-        # Named volume → a clean registry DB that is also visible to a
-        # socket-shared host daemon when the test process runs in act_runner.
-        self._root_volume = "bot-bottle-mtitest-root-" + secrets.token_hex(4)
-        self.svc = DockerInfraService(root_mount_source=self._root_volume)
+        self._tmp = tempfile.TemporaryDirectory()
+        self.addCleanup(self._tmp.cleanup)
+        # Throwaway root → a clean registry DB, independent of the host's.
+        self.svc = DockerInfraService(host_root=Path(self._tmp.name))
         self.addCleanup(self._teardown_docker)
         # ensure_running builds the bundle image (slow on a cold cache) and
         # brings up the shared network + gateway + orchestrator.
@@ -92,8 +100,13 @@ class TestMultitenantIsolation(unittest.TestCase):
         self.svc.stop()
         subprocess.run(["docker", "network", "rm", GATEWAY_NETWORK],
                        stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False)
+        # The orchestrator container wrote the registry DB as root into the
+        # throwaway root; chown it back so the (non-root) tempdir cleanup can
+        # remove it.
         subprocess.run(
-            ["docker", "volume", "rm", "--force", self._root_volume],
+            ["docker", "run", "--rm", "-v", f"{self._tmp.name}:/r",
+             "--entrypoint", "chown", GATEWAY_IMAGE, "-R",
+             f"{os.getuid()}:{os.getgid()}", "/r"],
             stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False)
 
     @staticmethod
@@ -119,61 +132,29 @@ class TestMultitenantIsolation(unittest.TestCase):
         taken = _network_container_ips(GATEWAY_NETWORK) + extra_taken
         return next_free_ip(_network_cidr(GATEWAY_NETWORK), taken)
 
-    def _probe(self, source_ip: str, identity_token: str, host: str) -> str:
-        deadline = time.monotonic() + 30
-        last = subprocess.CompletedProcess([], 1, "", "probe not attempted")
-        while time.monotonic() < deadline:
-            last = subprocess.run(
-                [
-                    "docker", "run", "--rm",
-                    "--network", GATEWAY_NETWORK, "--ip", source_ip,
-                    "--entrypoint", "python3", GATEWAY_IMAGE, "-c", _PROBE_SRC,
-                    f"http://bottle:{identity_token}@{self.gw_ip}:{EGRESS_PORT}",
-                    host,
-                ],
-                stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True,
-                check=False, timeout=90,
-            )
-            output = last.stdout.strip()
-            if last.returncode == 0 and output:
-                return output
-            time.sleep(0.25)
-        self.fail(
-            f"gateway probe did not become ready: "
-            f"exit={last.returncode}, stderr={last.stderr.strip()!r}"
+    def _probe(self, source_ip: str, host: str) -> str:
+        proc = subprocess.run(
+            ["docker", "run", "--rm", "--network", GATEWAY_NETWORK, "--ip", source_ip,
+             "--entrypoint", "python3", GATEWAY_IMAGE, "-c", _PROBE_SRC,
+             f"http://{self.gw_ip}:{EGRESS_PORT}", host],
+            stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True, check=False, timeout=90,
         )
+        return proc.stdout.strip()
 
     def test_two_bottles_share_gateway_with_isolated_tokens_and_allowlists(self) -> None:
         ip_a = self._free_ip([])
         ip_b = self._free_ip([ip_a])
-        bottle_a = self.client.register_bottle(
-            ip_a, policy=_POLICY_A, tokens={"EGRESS_TOKEN_0": _TOKEN_A}
-        )
-        bottle_b = self.client.register_bottle(
-            ip_b, policy=_POLICY_B, tokens={"EGRESS_TOKEN_0": _TOKEN_B}
-        )
+        self.client.register_bottle(ip_a, policy=_POLICY_A, tokens={"EGRESS_TOKEN_0": _TOKEN_A})
+        self.client.register_bottle(ip_b, policy=_POLICY_B, tokens={"EGRESS_TOKEN_0": _TOKEN_B})
 
         # Each bottle gets its OWN token injected on the shared route — no bleed.
-        self.assertEqual(
-            f"200 AUTH=Bearer {_TOKEN_A}",
-            self._probe(ip_a, bottle_a.identity_token, "echo-shared"),
-        )
-        self.assertEqual(
-            f"200 AUTH=Bearer {_TOKEN_B}",
-            self._probe(ip_b, bottle_b.identity_token, "echo-shared"),
-        )
+        self.assertEqual(f"200 AUTH=Bearer {_TOKEN_A}", self._probe(ip_a, "echo-shared"))
+        self.assertEqual(f"200 AUTH=Bearer {_TOKEN_B}", self._probe(ip_b, "echo-shared"))
 
         # Allowlist is per-bottle: echo-bonly is only in B's policy.
-        self.assertTrue(
-            self._probe(
-                ip_a, bottle_a.identity_token, "echo-bonly"
-            ).startswith("403"),  # fail-closed for A
-            "A reached a host outside its allowlist",
-        )
-        self.assertEqual(
-            "200 AUTH=NONE",
-            self._probe(ip_b, bottle_b.identity_token, "echo-bonly"),
-        )  # allowed, unauthed for B
+        self.assertTrue(self._probe(ip_a, "echo-bonly").startswith("403"),  # fail-closed for A
+                        "A reached a host outside its allowlist")
+        self.assertEqual("200 AUTH=NONE", self._probe(ip_b, "echo-bonly"))  # allowed, unauthed for B
 
 
 if __name__ == "__main__":

tests/integration/test_orchestrator_docker_auth.py

@@ -23,6 +23,7 @@ import secrets
 import subprocess
 import tempfile
 import unittest
+from pathlib import Path
 
 from bot_bottle.orchestrator_auth import ROLE_CLI, ROLE_GATEWAY, mint
 from bot_bottle.orchestrator.client import OrchestratorClient
@@ -37,6 +38,13 @@ _TEST_GATEWAY_IMAGE = "bot-bottle-gateway:itest"
 
 
 @skip_unless_backend("docker")
+@unittest.skipIf(
+    os.environ.get("GITEA_ACTIONS") == "true",
+    "skipped under act_runner: the orchestrator container bind-mounts the repo "
+    "path into a container on the socket-shared host daemon, which can't see the "
+    "runner's /workspace — same host-bind-mount constraint as the other "
+    "bottle-bringup integration tests",
+)
 class TestDockerOrchestratorAuthIntegration(unittest.TestCase):
     @classmethod
     def setUpClass(cls) -> None:
@@ -66,10 +74,10 @@ class TestDockerOrchestratorAuthIntegration(unittest.TestCase):
         gateway_name = f"bot-bottle-gateway-itest-{suffix}"
         network = f"bot-bottle-net-itest-{suffix}"
         control_network = f"bot-bottle-ctrl-itest-{suffix}"
-        root_volume = f"bot-bottle-root-itest-{suffix}"
+        host_root = Path(cls._tmp.name)
         cls.addClassCleanup(
             cls._teardown_docker,
-            orchestrator_name, gateway_name, network, control_network, root_volume,
+            orchestrator_name, gateway_name, network, control_network, host_root,
         )
 
         cls.svc = DockerInfraService(
@@ -80,7 +88,7 @@ class TestDockerOrchestratorAuthIntegration(unittest.TestCase):
             orchestrator_image=_TEST_ORCHESTRATOR_IMAGE,
             gateway_image=_TEST_GATEWAY_IMAGE,
             port=20000 + secrets.randbelow(10000),
-            root_mount_source=root_volume,
+            host_root=host_root,
         )
         cls.svc.ensure_running()
         # The control plane now verifies role-scoped signed tokens, not the raw
@@ -92,7 +100,7 @@ class TestDockerOrchestratorAuthIntegration(unittest.TestCase):
     @staticmethod
     def _teardown_docker(
         orchestrator_name: str, gateway_name: str,
-        network: str, control_network: str, root_volume: str,
+        network: str, control_network: str, host_root: Path,
     ) -> None:
         for name in (gateway_name, orchestrator_name):
             subprocess.run(
@@ -104,8 +112,14 @@ class TestDockerOrchestratorAuthIntegration(unittest.TestCase):
                 ["docker", "network", "rm", net],
                 stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False,
             )
+        # The orchestrator container (no USER directive) wrote the registry
+        # DB as root into the throwaway host_root; chown it back so the
+        # (non-root) tempdir cleanup can remove it. Same workaround
+        # test_multitenant_isolation.py uses for the identical bind mount.
         subprocess.run(
-            ["docker", "volume", "rm", "--force", root_volume],
+            ["docker", "run", "--rm", "-v", f"{host_root}:/r",
+             "--entrypoint", "chown", _TEST_ORCHESTRATOR_IMAGE, "-R",
+             f"{os.getuid()}:{os.getgid()}", "/r"],
             stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False,
         )
 

tests/integration/test_orphan_cleanup.py

@@ -42,6 +42,11 @@ class TestOrphanCleanup(unittest.TestCase):
         # Returning True == idempotent success.
         self.assertTrue(network_remove(f"bot-bottle-net-{self.slug}-does-not-exist"))
 
+    @unittest.skipIf(
+        os.environ.get("GITEA_ACTIONS") == "true",
+        "skipped under act_runner: docker socket mount topology breaks "
+        "in-process visibility of networks created on the host daemon",
+    )
     def test_create_and_remove(self):
         self.internal_name = network_create_internal(self.slug)
         self.egress_name = network_create_egress(self.slug)

tests/integration/test_sandbox_escape.py

@@ -67,7 +67,26 @@ _DUMMY_HOST_KEY = (
 )
 
 
+# Backends whose CI runner is HOST-mode (self-hosted), so the test process
+# and the backend share a host. The containerized act_runner (docker on
+# ubuntu-latest) is the one that can't see the host bind mount egress_tls_init
+# uses and hides sibling-gateway network topology; host-mode runners
+# (firecracker/KVM, macos-container) don't have those constraints, so the test
+# runs there. Keep this in sync with the `runs-on` labels in
+# .gitea/workflows/test.yml.
+_HOST_MODE_CI_BACKENDS = frozenset({"firecracker", "macos-container"})
+
+
 @skip_unless_selected_backend_available()
+@unittest.skipIf(
+    os.environ.get("GITEA_ACTIONS") == "true"
+    and os.environ.get("BOT_BOTTLE_BACKEND") not in _HOST_MODE_CI_BACKENDS,
+    "skipped under the containerized act_runner (docker on ubuntu-latest): "
+    "egress_tls_init uses a host bind mount the runner container can't "
+    "see, and the network topology hides sibling-gateway visibility — "
+    "these constraints don't apply on the self-hosted host-mode runners "
+    "(firecracker/KVM, macos-container)",
+)
 class TestSandboxEscape(unittest.TestCase):
     """End-to-end attacks against a real bottle. The bottle stays
     up for the whole class — bringup is ~10-30s, so per-test
@@ -170,7 +189,7 @@ class TestSandboxEscape(unittest.TestCase):
                 missing.append(tool)
         if missing:
             cls._teardown_resources()
-            raise AssertionError(
+            raise unittest.SkipTest(
                 f"agent missing required tools: {', '.join(missing)} — "
                 f"add them to the backend's base image"
             )

tests/unit/test_architecture_guardrails.py

@@ -1,96 +0,0 @@
-"""Architecture rules that should fail before coupling becomes entrenched."""
-
-from __future__ import annotations
-
-import ast
-import unittest
-from pathlib import Path
-
-
-ROOT = Path(__file__).resolve().parents[2]
-
-
-class TestCliBackendBoundaries(unittest.TestCase):
-    def test_cli_does_not_import_a_concrete_backend(self) -> None:
-        forbidden = (
-            "backend.docker", "backend.firecracker", "backend.macos_container",
-            "bot_bottle.backend.docker", "bot_bottle.backend.firecracker",
-            "bot_bottle.backend.macos_container",
-        )
-        violations: list[str] = []
-        for path in (ROOT / "bot_bottle" / "cli").rglob("*.py"):
-            tree = ast.parse(path.read_text(), filename=str(path))
-            for node in ast.walk(tree):
-                if isinstance(node, ast.ImportFrom):
-                    module = node.module
-                    if module and module.startswith(forbidden):
-                        violations.append(
-                            f"{path.relative_to(ROOT)}:{node.lineno}: {module}"
-                        )
-                if isinstance(node, ast.Import):
-                    violations.extend(
-                        f"{path.relative_to(ROOT)}:{node.lineno}: {alias.name}"
-                        for alias in node.names if alias.name.startswith(forbidden)
-                    )
-        self.assertEqual([], violations, "generic CLI imports concrete backend internals:\n" +
-                         "\n".join(violations))
-
-
-class TestRuntimeModuleSizes(unittest.TestCase):
-    def test_no_runtime_module_grows_beyond_global_ceiling(self) -> None:
-        """A coarse ceiling catches new monoliths; focused caps stay tighter."""
-        ceiling = 850
-        oversized = [
-            f"{path.relative_to(ROOT)} ({len(path.read_text().splitlines())})"
-            for path in (ROOT / "bot_bottle").rglob("*.py")
-            if len(path.read_text().splitlines()) > ceiling
-        ]
-        self.assertEqual(
-            [], oversized,
-            f"runtime modules must stay at or below {ceiling} lines: "
-            + ", ".join(oversized),
-        )
-
-    def test_egress_modules_stay_focused(self) -> None:
-        caps = {
-            "addon_core.py": 100,
-            "schema.py": 400,
-            "types.py": 180,
-            "matching.py": 180,
-            "dlp.py": 180,
-            "context.py": 140,
-        }
-        directory = ROOT / "bot_bottle" / "gateway" / "egress"
-        oversized = [f"{name} ({len((directory / name).read_text().splitlines())}>{cap})"
-                     for name, cap in caps.items()
-                     if len((directory / name).read_text().splitlines()) > cap]
-        self.assertEqual([], oversized, "split a module rather than raising its cap: " +
-                         ", ".join(oversized))
-
-    def test_runtime_code_uses_focused_egress_modules(self) -> None:
-        """addon_core is compatibility-only, never an internal dependency."""
-        violations: list[str] = []
-        package = ROOT / "bot_bottle"
-        facade = package / "gateway" / "egress" / "addon_core.py"
-        package_init = package / "gateway" / "egress" / "__init__.py"
-        for path in package.rglob("*.py"):
-            if path in (facade, package_init):
-                continue
-            text = path.read_text()
-            if "gateway.egress.addon_core import" in text or \
-                    ".addon_core import" in text:
-                violations.append(str(path.relative_to(ROOT)))
-        self.assertEqual([], violations)
-
-    def test_backend_contract_does_not_absorb_preparation_logic(self) -> None:
-        caps = {
-            ROOT / "bot_bottle" / "backend" / "base.py": 580,
-            ROOT / "bot_bottle" / "backend" / "preparation.py": 160,
-        }
-        oversized = [
-            f"{path.relative_to(ROOT)} "
-            f"({len(path.read_text().splitlines())}>{cap})"
-            for path, cap in caps.items()
-            if len(path.read_text().splitlines()) > cap
-        ]
-        self.assertEqual([], oversized)

tests/unit/test_backend_secret_reprovision.py

@@ -48,13 +48,12 @@ class TestSharedReprovision(unittest.TestCase):
         client.reprovision_gateway.side_effect = [
             OrchestratorClientError("bad key"), True,
         ]
-        with patch("bot_bottle.orchestrator.reprovision.debug") as debug:
-            count = reprovision_bottles(
+        self.assertEqual(
+            1,
+            reprovision_bottles(
                 client, {"10.0.0.1": "key-1", "10.0.0.2": "key-2"},
-            )
-        self.assertEqual(1, count)
-        self.assertEqual("b1", debug.call_args.kwargs["context"]["bottle_id"])
-        self.assertNotIn("bad key", repr(debug.call_args))
+            ),
+        )
 
 
 class TestMacosReprovision(unittest.TestCase):

tests/unit/test_cli_tui.py

@@ -9,7 +9,6 @@ from __future__ import annotations
 
 import unittest
 from typing import Any, Optional
-from unittest.mock import patch
 
 from bot_bottle.cli.tui import _filter_items, _multiselect_loop, filter_multiselect, filter_select
 
@@ -50,10 +49,8 @@ class TestFilterSelectEmptyItems(unittest.TestCase):
 
     def test_returns_none_when_tty_unavailable(self):
         # /nonexistent is guaranteed to not open.
-        with patch("bot_bottle.cli.tui.debug") as debug:
-            result = filter_select(["a", "b"], tty_path="/nonexistent/tty")
+        result = filter_select(["a", "b"], tty_path="/nonexistent/tty")
         self.assertIsNone(result)
-        self.assertEqual("FileNotFoundError", debug.call_args.kwargs["context"]["error_type"])
 
 
 class TestFilterMultiselectEmptyItems(unittest.TestCase):
@@ -63,10 +60,8 @@ class TestFilterMultiselectEmptyItems(unittest.TestCase):
         self.assertEqual([], result)
 
     def test_returns_none_when_tty_unavailable(self):
-        with patch("bot_bottle.cli.tui.debug") as debug:
-            result = filter_multiselect(["a", "b"], tty_path="/nonexistent/tty")
+        result = filter_multiselect(["a", "b"], tty_path="/nonexistent/tty")
         self.assertIsNone(result)
-        self.assertEqual("FileNotFoundError", debug.call_args.kwargs["context"]["error_type"])
 
 
 class TestMultiselectLoopReordering(unittest.TestCase):

tests/unit/test_critical_modules.py

@@ -1,101 +0,0 @@
-"""Tests for the fail-closed critical coverage manifest."""
-
-from __future__ import annotations
-
-import tempfile
-import unittest
-from contextlib import redirect_stderr, redirect_stdout
-from io import StringIO
-from pathlib import Path
-
-from scripts.critical_modules import (
-    DEFAULT_MANIFEST,
-    REPO_ROOT,
-    CriticalModulesError,
-    load_critical_modules,
-    main,
-)
-
-
-class TestCriticalModules(unittest.TestCase):
-    def test_repository_manifest_is_valid(self) -> None:
-        modules = load_critical_modules(DEFAULT_MANIFEST, root=REPO_ROOT)
-        self.assertGreater(len(modules), 20)
-        self.assertEqual(len(modules), len(set(modules)))
-
-    def test_missing_module_fails(self) -> None:
-        with tempfile.TemporaryDirectory() as tmp:
-            root = Path(tmp)
-            manifest = root / "critical-modules.txt"
-            manifest.write_text("bot_bottle/renamed.py\n", encoding="utf-8")
-            with self.assertRaisesRegex(CriticalModulesError, "does not exist"):
-                load_critical_modules(manifest, root=root)
-
-    def test_duplicate_module_fails(self) -> None:
-        with tempfile.TemporaryDirectory() as tmp:
-            root = Path(tmp)
-            module = root / "bot_bottle" / "core.py"
-            module.parent.mkdir()
-            module.write_text("", encoding="utf-8")
-            manifest = root / "critical-modules.txt"
-            manifest.write_text(
-                "bot_bottle/core.py\nbot_bottle/core.py\n", encoding="utf-8"
-            )
-            with self.assertRaisesRegex(CriticalModulesError, "duplicated"):
-                load_critical_modules(manifest, root=root)
-
-    def test_entry_cannot_escape_repository(self) -> None:
-        with tempfile.TemporaryDirectory() as tmp:
-            root = Path(tmp)
-            manifest = root / "critical-modules.txt"
-            manifest.write_text("../outside.py\n", encoding="utf-8")
-            with self.assertRaisesRegex(CriticalModulesError, "escapes"):
-                load_critical_modules(manifest, root=root)
-
-    def test_invalid_entry_forms_are_reported_together(self) -> None:
-        with tempfile.TemporaryDirectory() as tmp:
-            root = Path(tmp)
-            manifest = root / "critical-modules.txt"
-            manifest.write_text(
-                f"{root / 'absolute.py'}\nREADME.md\n",
-                encoding="utf-8",
-            )
-            with self.assertRaises(CriticalModulesError) as raised:
-                load_critical_modules(manifest, root=root)
-            self.assertIn("must be relative", str(raised.exception))
-            self.assertIn("is not a Python module", str(raised.exception))
-
-    def test_empty_manifest_fails(self) -> None:
-        with tempfile.TemporaryDirectory() as tmp:
-            root = Path(tmp)
-            manifest = root / "critical-modules.txt"
-            manifest.write_text("# comments do not define modules\n", encoding="utf-8")
-            with self.assertRaisesRegex(CriticalModulesError, "contains no"):
-                load_critical_modules(manifest, root=root)
-
-    def test_unreadable_manifest_fails(self) -> None:
-        with tempfile.TemporaryDirectory() as tmp:
-            missing = Path(tmp) / "missing.txt"
-            with self.assertRaisesRegex(CriticalModulesError, "cannot read"):
-                load_critical_modules(missing, root=Path(tmp))
-
-    def test_main_prints_include_list_or_checks_silently(self) -> None:
-        output = StringIO()
-        with redirect_stdout(output):
-            self.assertEqual(0, main([]))
-        self.assertIn("bot_bottle/manifest/egress.py", output.getvalue())
-
-        output = StringIO()
-        with redirect_stdout(output):
-            self.assertEqual(0, main(["--check"]))
-        self.assertEqual("", output.getvalue())
-
-    def test_main_reports_manifest_error(self) -> None:
-        error = StringIO()
-        with redirect_stderr(error):
-            self.assertEqual(1, main(["--manifest", "/definitely/missing"]))
-        self.assertIn("critical-modules:", error.getvalue())
-
-
-if __name__ == "__main__":
-    unittest.main()

tests/unit/test_docker_infra.py

@@ -9,7 +9,6 @@ a freshly minted token."""
 from __future__ import annotations
 
 import unittest
-from pathlib import Path
 from unittest.mock import MagicMock, patch
 
 from bot_bottle.backend.docker.infra import (
@@ -68,21 +67,6 @@ class TestDockerInfraService(unittest.TestCase):
         self.assertTrue(any(GATEWAY_NAME in a for a in rms))
         self.assertTrue(any(ORCHESTRATOR_NAME in a for a in rms))
 
-    def test_named_mounts_propagate_to_both_planes(self) -> None:
-        svc = DockerInfraService(
-            root_mount_source="registry-volume",
-            gateway_ca_mount_source="ca-volume",
-        )
-        self.assertEqual("registry-volume", svc.orchestrator()._root_mount_source)
-        self.assertEqual("ca-volume", svc.gateway()._ca_mount_source)
-
-    def test_host_path_and_named_root_mount_are_mutually_exclusive(self) -> None:
-        with self.assertRaisesRegex(ValueError, "host_root or root_mount_source"):
-            DockerInfraService(
-                host_root=Path("/host/path"),
-                root_mount_source="registry-volume",
-            )
-
 
 if __name__ == "__main__":
     unittest.main()

tests/unit/test_docker_orchestrator.py

@@ -4,7 +4,6 @@ from __future__ import annotations
 
 import unittest
 import urllib.error
-from pathlib import Path
 from unittest.mock import MagicMock, Mock, patch
 
 from bot_bottle.backend.docker.orchestrator import (
@@ -48,55 +47,6 @@ class TestDockerOrchestrator(unittest.TestCase):
     def test_url_is_host_loopback(self) -> None:
         self.assertEqual("http://127.0.0.1:8099", self.orch.url())
 
-    def test_socket_shared_client_uses_explicit_host_and_open_bind(self) -> None:
-        orch = DockerOrchestrator(
-            port=8099, client_host="172.17.0.1", root_mount_source="state-volume"
-        )
-        with patch(_TOKEN, return_value="k"), \
-                patch(_URLOPEN, side_effect=[urllib.error.URLError("down"), _health(200)]), \
-                patch(_RUN, return_value=_proc()) as run, patch(_SLEEP):
-            orch.ensure_running()
-        self.assertEqual("http://172.17.0.1:8099", orch.url())
-        argv = next(c.args[0] for c in run.call_args_list
-                    if c.args[0][:2] == ["docker", "run"])
-        self.assertEqual("0.0.0.0:8099:8099", argv[argv.index("--publish") + 1])
-        self.assertIn("state-volume:/bot-bottle-root", argv)
-
-    def test_host_path_and_named_root_mount_are_mutually_exclusive(self) -> None:
-        with self.assertRaisesRegex(ValueError, "host_root or root_mount_source"):
-            DockerOrchestrator(
-                host_root=Path("/host/path"),
-                root_mount_source="state-volume",
-            )
-
-    def test_socket_shared_job_network_uses_container_dns(self) -> None:
-        orch = DockerOrchestrator(
-            name="orchestrator-itest",
-            port=22001,
-            client_network="runner-job-network",
-            root_mount_source="state-volume",
-        )
-        with patch(_TOKEN, return_value="k"), \
-                patch(
-                    _URLOPEN,
-                    side_effect=[urllib.error.URLError("down"), _health(200)],
-                ), patch(_RUN, return_value=_proc()) as run, patch(_SLEEP):
-            orch.ensure_running()
-        self.assertEqual("http://orchestrator-itest:8099", orch.url())
-        calls = [call.args[0] for call in run.call_args_list]
-        self.assertIn(
-            [
-                "docker", "network", "connect",
-                "runner-job-network", "orchestrator-itest",
-            ],
-            calls,
-        )
-        argv = next(call for call in calls if call[:2] == ["docker", "run"])
-        self.assertEqual(
-            "127.0.0.1:22001:8099",
-            argv[argv.index("--publish") + 1],
-        )
-
     def test_gateway_url_is_the_container_dns_name(self) -> None:
         # The gateway reaches the orchestrator by name on the control network.
         self.assertEqual(f"http://{ORCHESTRATOR_NAME}:8099", self.orch.gateway_url())
@@ -160,8 +110,6 @@ class TestDockerOrchestrator(unittest.TestCase):
         # The lean control plane: no mitmproxy CA mount, no gateway daemons.
         self.assertFalse([a for a in argv if a.endswith(":/home/mitmproxy/.mitmproxy")])
         self.assertNotIn("BOT_BOTTLE_GATEWAY_DAEMONS", " ".join(argv))
-        self.assertNotIn("/bot-bottle-src", " ".join(argv))
-        self.assertNotIn("PYTHONPATH", " ".join(argv))
         # Orchestrator entrypoint args (image ENTRYPOINT is `-m bot_bottle.orchestrator`).
         self.assertIn("--broker", argv)
         self.assertIn("stub", argv)

tests/unit/test_egress_core_parsing.py

@@ -8,18 +8,16 @@ from __future__ import annotations
 
 import unittest
 
-from bot_bottle.gateway.egress.matching import evaluate_matches
-from bot_bottle.gateway.egress.schema import (
-    load_config,
-    parse_config,
-    parse_routes,
-    route_to_yaml_dict,
-)
-from bot_bottle.gateway.egress.types import (
+from bot_bottle.gateway.egress.addon_core import (
     HeaderMatch,
     MatchEntry,
     PathMatch,
     Route,
+    evaluate_matches,
+    load_config,
+    parse_config,
+    parse_routes,
+    route_to_yaml_dict,
 )
 
 

tests/unit/test_egress_multitenant.py

@@ -3,16 +3,15 @@
 from __future__ import annotations
 
 import unittest
-from unittest.mock import patch
 
-from bot_bottle.gateway.egress.context import (
+from bot_bottle.gateway.egress.addon_core import (
     DENY_RESOLVER_ERROR,
     DENY_UNATTRIBUTED,
     DENY_UNPARSEABLE,
+    decide,
     resolve_client_config,
     resolve_client_context,
 )
-from bot_bottle.gateway.egress.matching import decide
 from bot_bottle.gateway.policy_resolver import PolicyResolveError
 
 
@@ -45,13 +44,7 @@ class TestResolveClientConfig(unittest.TestCase):
 
     def test_resolver_error_denies_all(self) -> None:
         # Orchestrator unreachable/errored must never widen egress.
-        with patch("bot_bottle.gateway.egress.context.debug") as debug:
-            config = resolve_client_config(_FakeResolver(raises=True), "10.243.0.1")
-        self.assertEqual((), config.routes)
-        self.assertEqual(
-            "PolicyResolveError", debug.call_args.kwargs["context"]["error_type"],
-        )
-        self.assertNotIn("orchestrator down", repr(debug.call_args))
+        self.assertEqual((), resolve_client_config(_FakeResolver(raises=True), "10.243.0.1").routes)
 
     def test_unparseable_policy_denies_all(self) -> None:
         cfg = resolve_client_config(_FakeResolver(result="routes: notalist\n"), "10.243.0.1")

tests/unit/test_orchestrator_broker_client.py

@@ -1,117 +0,0 @@
-"""Unit: orchestrator-side broker client (issue #468, chunk 1). HTTP mocked."""
-
-from __future__ import annotations
-
-import io
-import json
-import unittest
-import urllib.error
-from unittest.mock import MagicMock, patch
-
-from bot_bottle.orchestrator.broker import (
-    BrokerAuthError,
-    BrokerUnavailableError,
-    LaunchRequest,
-)
-from bot_bottle.orchestrator.broker_client import BrokerClient, BrokerClientError
-
-_URLOPEN = "bot_bottle.orchestrator.broker_client.urllib.request.urlopen"
-
-
-def _resp(payload: object) -> MagicMock:
-    m = MagicMock()
-    m.__enter__.return_value.read.return_value = json.dumps(payload).encode()
-    return m
-
-
-def _http_error(code: int, payload: object = None) -> urllib.error.HTTPError:
-    body = json.dumps(payload).encode() if payload is not None else b""
-    return urllib.error.HTTPError(
-        "http://host/broker", code, "err", {}, io.BytesIO(body))  # type: ignore[arg-type]
-
-
-class TestSubmit(unittest.TestCase):
-    def setUp(self) -> None:
-        self.c = BrokerClient("http://host:8091")
-
-    def test_returns_the_verified_request(self) -> None:
-        echo = {
-            "op": "launch", "bottle_id": "b1", "source_ip": "10.0.0.1",
-            "image_ref": "img", "slot": 3,
-        }
-        with patch(_URLOPEN, return_value=_resp(echo)):
-            got = self.c.submit("tok")
-        self.assertEqual(
-            LaunchRequest(op="launch", bottle_id="b1", source_ip="10.0.0.1",
-                          image_ref="img", slot=3),
-            got,
-        )
-
-    def test_posts_token_to_broker_endpoint(self) -> None:
-        with patch(_URLOPEN, return_value=_resp({"op": "teardown", "bottle_id": "b1"})) as m:
-            self.c.submit("signed-token")
-        request = m.call_args.args[0]
-        self.assertEqual("POST", request.get_method())
-        self.assertTrue(request.full_url.endswith("/broker"))
-        self.assertEqual({"token": "signed-token"}, json.loads(request.data))
-
-    def test_401_raises_broker_auth_error(self) -> None:
-        # A fail-closed provenance/schema rejection surfaces as the SAME exception
-        # the in-process broker raises, so the launch path's rollback is identical.
-        with patch(_URLOPEN, side_effect=_http_error(401, {"error": "bad signature"})):
-            with self.assertRaises(BrokerAuthError):
-                self.c.submit("forged")
-
-    def test_502_is_a_definite_client_error(self) -> None:
-        # The host responded — it processed the request and did not launch, so a
-        # definite BrokerClientError (the caller may safely roll back).
-        with patch(_URLOPEN, side_effect=_http_error(502, {"error": "docker down"})):
-            with self.assertRaises(BrokerClientError):
-                self.c.submit("tok")
-
-    def test_unreachable_is_ambiguous_unavailable(self) -> None:
-        # No response at all — the request may already have launched, so the
-        # AMBIGUOUS BrokerUnavailableError (the caller must NOT roll back).
-        with patch(_URLOPEN, side_effect=urllib.error.URLError("refused")):
-            with self.assertRaises(BrokerUnavailableError):
-                self.c.submit("tok")
-
-    def test_timeout_is_ambiguous_unavailable(self) -> None:
-        # A dropped/late response after the request was sent is the exact orphan
-        # risk: the host may have launched. Must be ambiguous, not a definite fail.
-        with patch(_URLOPEN, side_effect=TimeoutError("read timed out")):
-            with self.assertRaises(BrokerUnavailableError):
-                self.c.submit("tok")
-
-    def test_malformed_success_body_raises(self) -> None:
-        with patch(_URLOPEN, return_value=_resp({"op": "launch"})):  # missing bottle_id
-            with self.assertRaises(BrokerClientError):
-                self.c.submit("tok")
-
-    def test_empty_error_body_is_tolerated(self) -> None:
-        # An error with no readable JSON body still classifies by status code.
-        with patch(_URLOPEN, side_effect=_http_error(401)):
-            with self.assertRaises(BrokerAuthError):
-                self.c.submit("forged")
-
-    def test_non_json_success_body_raises(self) -> None:
-        # A 200 whose body isn't JSON is tolerated into {} then fails the
-        # missing-field check — a definite client error, not a crash.
-        m = MagicMock()
-        m.__enter__.return_value.read.return_value = b"not json at all"
-        with patch(_URLOPEN, return_value=m):
-            with self.assertRaises(BrokerClientError):
-                self.c.submit("tok")
-
-    def test_unreadable_error_body_is_tolerated(self) -> None:
-        # An HTTPError whose body can't be read (fp=None) still classifies by
-        # status — the error detail is best-effort.
-        err = urllib.error.HTTPError(
-            "http://host/broker", 502, "err", {}, None)  # type: ignore[arg-type]
-        with patch(_URLOPEN, side_effect=err):
-            with self.assertRaises(BrokerClientError):
-                self.c.submit("tok")
-
-
-if __name__ == "__main__":
-    unittest.main()

tests/unit/test_orchestrator_client.py

@@ -12,9 +12,7 @@ from bot_bottle.orchestrator.client import (
     OrchestratorClient,
     OrchestratorClientError,
     RegisteredBottle,
-    BackendProbeFailure,
     _host_auth_token,
-    _probe_failure,
 )
 
 _URLOPEN = "bot_bottle.orchestrator.client.urllib.request.urlopen"
@@ -35,15 +33,6 @@ class TestHostAuthToken(unittest.TestCase):
             self.assertEqual("", _host_auth_token())
 
 
-class TestBackendProbeFailure(unittest.TestCase):
-    def test_records_safe_typed_diagnostic(self) -> None:
-        with patch("bot_bottle.orchestrator.client.debug") as debug:
-            result = _probe_failure("firecracker", RuntimeError("secret detail"))
-        self.assertEqual(BackendProbeFailure("firecracker", "RuntimeError"), result)
-        rendered = repr(debug.call_args)
-        self.assertNotIn("secret detail", rendered)
-
-
 def _resp(status: int, payload: object) -> MagicMock:
     m = MagicMock()
     inner = m.__enter__.return_value

tests/unit/test_orchestrator_gateway.py

@@ -7,10 +7,7 @@ import unittest
 from pathlib import Path
 from unittest.mock import Mock, patch
 
-from bot_bottle.backend.docker.gateway import (
-    DEFAULT_GATEWAY_SUBNET,
-    DockerGateway,
-)
+from bot_bottle.backend.docker.gateway import DockerGateway
 from bot_bottle.gateway import (
     GATEWAY_CA_CERT,
     GATEWAY_NAME,
@@ -145,22 +142,6 @@ class TestDockerGateway(unittest.TestCase):
         # Data plane resolves policy against the orchestrator control plane.
         self.assertIn(f"BOT_BOTTLE_ORCHESTRATOR_URL={_ORCH_URL}", runs[0])
 
-    def test_named_ca_volume_supports_socket_shared_runner(self) -> None:
-        sc = DockerGateway(
-            "bot-bottle-gateway:latest", ca_mount_source="ci-ca-volume"
-        )
-
-        def fake(argv: list[str], **_kw: object) -> Mock:
-            return _proc(stdout="") if argv[:2] == ["docker", "ps"] else _proc()
-
-        with patch(_RUN_DOCKER, side_effect=fake) as run:
-            sc.connect_to_orchestrator(_ORCH_URL, _TOKEN)
-        argv = next(c.args[0] for c in run.call_args_list
-                    if c.args[0][:2] == ["docker", "run"])
-        self.assertIn(
-            "ci-ca-volume:/home/mitmproxy/.mitmproxy", argv
-        )
-
     def test_connect_injects_the_pre_minted_gateway_token(self) -> None:
         # The gateway presents the token the orchestrator handed it — it never
         # mints (holds no signing key). The value rides the env (bare `--env
@@ -212,38 +193,7 @@ class TestDockerGateway(unittest.TestCase):
         with patch(_RUN_DOCKER, side_effect=fake):
             self.sc.connect_to_orchestrator(_ORCH_URL, _TOKEN)
         creates = [c for c in calls if c[:3] == ["docker", "network", "create"]]
-        self.assertEqual(
-            [[
-                "docker", "network", "create",
-                "--subnet", DEFAULT_GATEWAY_SUBNET,
-                "--label",
-                f"bot-bottle.gateway-subnet={DEFAULT_GATEWAY_SUBNET}",
-                self.sc.network,
-            ]],
-            creates,
-        )
-
-    def test_ensure_running_replaces_stale_auto_ipam_network(self) -> None:
-        calls: list[list[str]] = []
-
-        def fake(argv: list[str], **_kw: object) -> Mock:
-            calls.append(argv)
-            if argv[:2] == ["docker", "ps"]:
-                return _proc(stdout="")
-            if argv[:3] == ["docker", "network", "inspect"]:
-                return _proc(stdout="<no value>\n")
-            return _proc()
-
-        with patch(_RUN_DOCKER, side_effect=fake):
-            self.sc.connect_to_orchestrator(_ORCH_URL, _TOKEN)
-        self.assertIn(
-            ["docker", "rm", "--force", self.sc.name],
-            calls,
-        )
-        self.assertIn(
-            ["docker", "network", "rm", self.sc.network],
-            calls,
-        )
+        self.assertEqual([["docker", "network", "create", self.sc.network]], creates)
 
     def test_ca_cert_pem_reads_from_container(self) -> None:
         with patch(_RUN_DOCKER, return_value=_proc(stdout=_CA_PEM)) as m:

tests/unit/test_orchestrator_host_server.py

@@ -1,306 +0,0 @@
-"""Unit tests for the host control server (issue #468, chunk 1).
-
-Mostly exercises the pure `dispatch()` (socket-free, like the orchestrator
-server tests), plus a real-socket round-trip through `BrokerClient` that proves
-the full sign -> POST -> verify -> act seam over HTTP.
-"""
-
-from __future__ import annotations
-
-import http.client
-import io
-import json
-import os
-import secrets
-import tempfile
-import threading
-import typing
-import unittest
-from unittest.mock import MagicMock, patch
-
-from bot_bottle.orchestrator.broker import (
-    BrokerAuthError,
-    LaunchBroker,
-    LaunchRequest,
-    StubBroker,
-    sign_request,
-)
-from bot_bottle.orchestrator.broker_client import BrokerClient
-from bot_bottle.orchestrator.host_server import (
-    MAX_BODY_BYTES,
-    Handler,
-    HostControlServer,
-    broker_secret,
-    dispatch,
-    main,
-    make_host_server,
-)
-from bot_bottle.paths import LAUNCH_BROKER_KEY_ENV
-
-
-def _body(obj: object) -> bytes:
-    return json.dumps(obj).encode()
-
-
-class _RaisingBroker(LaunchBroker):
-    """A broker whose backend launch always fails — exercises the 502 path (an
-    operational backend failure, distinct from a fail-closed provenance 401)."""
-
-    def _launch(self, req: LaunchRequest) -> None:
-        raise RuntimeError("docker down")
-
-    def _teardown(self, req: LaunchRequest) -> None:
-        raise RuntimeError("docker down")
-
-
-class TestDispatch(unittest.TestCase):
-    def setUp(self) -> None:
-        self.secret = secrets.token_bytes(16)
-        self.broker = StubBroker(self.secret)
-
-    def _token(self, **kwargs: object) -> str:
-        return sign_request(LaunchRequest(**kwargs), self.secret)  # type: ignore[arg-type]
-
-    def test_health(self) -> None:
-        status, payload = dispatch(self.broker, "GET", "/health", b"")
-        self.assertEqual(200, status)
-        self.assertEqual("ok", payload["status"])
-
-    def test_broker_launch_verifies_and_acts(self) -> None:
-        token = self._token(
-            op="launch", bottle_id="b1", source_ip="10.243.0.1",
-            image_ref="img", slot=2,
-        )
-        status, payload = dispatch(self.broker, "POST", "/broker", _body({"token": token}))
-        self.assertEqual(200, status)
-        self.assertEqual("launch", payload["op"])
-        self.assertEqual("b1", payload["bottle_id"])
-        self.assertEqual("img", payload["image_ref"])
-        self.assertEqual(2, payload["slot"])
-        self.assertEqual(["b1"], [r.bottle_id for r in self.broker.launched])
-
-    def test_broker_teardown_acts(self) -> None:
-        token = self._token(op="teardown", bottle_id="b1")
-        status, _ = dispatch(self.broker, "POST", "/broker", _body({"token": token}))
-        self.assertEqual(200, status)
-        self.assertEqual(["b1"], [r.bottle_id for r in self.broker.torn_down])
-
-    def test_forged_token_is_401_and_nothing_acted(self) -> None:
-        forged = sign_request(
-            LaunchRequest(op="launch", bottle_id="b1"), secrets.token_bytes(16))
-        status, payload = dispatch(self.broker, "POST", "/broker", _body({"token": forged}))
-        self.assertEqual(401, status)
-        self.assertIn("broker auth failed", str(payload["error"]))
-        self.assertEqual([], self.broker.launched)  # fail-closed: never launched
-
-    def test_backend_failure_is_502(self) -> None:
-        broker = _RaisingBroker(self.secret)
-        token = self._token(op="launch", bottle_id="b1", image_ref="img")
-        status, payload = dispatch(broker, "POST", "/broker", _body({"token": token}))
-        self.assertEqual(502, status)
-        self.assertIn("backend launch failed", str(payload["error"]))
-
-    def test_missing_token_is_400(self) -> None:
-        status, _ = dispatch(self.broker, "POST", "/broker", _body({}))
-        self.assertEqual(400, status)
-
-    def test_bad_json_is_400(self) -> None:
-        status, _ = dispatch(self.broker, "POST", "/broker", b"{not json")
-        self.assertEqual(400, status)
-
-    def test_empty_body_is_missing_token_400(self) -> None:
-        # Empty body parses to {} (no token) → 400, never reaching the broker.
-        status, _ = dispatch(self.broker, "POST", "/broker", b"")
-        self.assertEqual(400, status)
-        self.assertEqual([], self.broker.launched)
-
-    def test_non_object_body_is_400(self) -> None:
-        status, _ = dispatch(self.broker, "POST", "/broker", b"[1, 2]")
-        self.assertEqual(400, status)
-
-    def test_unknown_route_404(self) -> None:
-        status, _ = dispatch(self.broker, "GET", "/nope", b"")
-        self.assertEqual(404, status)
-
-    def test_trailing_slash_normalized(self) -> None:
-        status, _ = dispatch(self.broker, "GET", "/health/", b"")
-        self.assertEqual(200, status)
-
-
-class TestBrokerSecret(unittest.TestCase):
-    """The durable launch-broker key (#468/#476): prefer the env-injected key,
-    else the durable host key file, so signer and verifier resolve the same one."""
-
-    def test_reads_injected_key_from_env(self) -> None:
-        # The injected key is honoured regardless of allow_host_file — both the
-        # host controller and the guest orchestrator take an injected key.
-        self.assertEqual(
-            b"injected-key", broker_secret({LAUNCH_BROKER_KEY_ENV: "injected-key"}))
-        self.assertEqual(
-            b"injected-key",
-            broker_secret({LAUNCH_BROKER_KEY_ENV: "injected-key"}, allow_host_file=True))
-
-    def test_guest_without_injection_fails_closed(self) -> None:
-        # The default (guest orchestrator): no env key and NO host-file fallback,
-        # so it returns None rather than mint a divergent process-local key.
-        self.assertIsNone(broker_secret({}))
-
-    def test_host_side_falls_back_to_the_durable_key_file(self) -> None:
-        # allow_host_file=True (host controller / dev-harness): mint/read the
-        # durable host key file, the same key on every call (restart re-adoption).
-        with tempfile.TemporaryDirectory() as root:
-            with patch.dict("os.environ", {"BOT_BOTTLE_ROOT": root}, clear=False):
-                os.environ.pop(LAUNCH_BROKER_KEY_ENV, None)
-                first = broker_secret(allow_host_file=True)
-                second = broker_secret(allow_host_file=True)
-        self.assertTrue(first)
-        self.assertEqual(first, second)
-
-
-class TestSeamRoundTrip(unittest.TestCase):
-    """The whole point of chunk 1: a request signed by the orchestrator side is
-    POSTed to a real host control server, verified there, and acted on — over
-    HTTP, not an in-process call."""
-
-    def _serve(self, broker: LaunchBroker) -> BrokerClient:
-        server = make_host_server(broker, "127.0.0.1", 0)
-        self.addCleanup(server.server_close)
-        threading.Thread(target=server.serve_forever, daemon=True).start()
-        self.addCleanup(server.shutdown)
-        host, port = server.server_address[0], server.server_address[1]
-        return BrokerClient(f"http://{host}:{port}")
-
-    def test_sign_post_verify_act_over_http(self) -> None:
-        secret = secrets.token_bytes(16)
-        broker = StubBroker(secret)
-        client = self._serve(broker)
-        req = LaunchRequest(
-            op="launch", bottle_id="b1", source_ip="10.0.0.1", image_ref="img", slot=1)
-        got = client.submit(sign_request(req, secret))
-        self.assertEqual(req, got)  # the controller echoes the verified request
-        self.assertEqual(["b1"], [r.bottle_id for r in broker.launched])
-
-    def test_forged_token_raises_broker_auth_error_over_http(self) -> None:
-        secret = secrets.token_bytes(16)
-        broker = StubBroker(secret)
-        client = self._serve(broker)
-        forged = sign_request(
-            LaunchRequest(op="launch", bottle_id="b1"), secrets.token_bytes(16))
-        with self.assertRaises(BrokerAuthError):
-            client.submit(forged)
-        self.assertEqual([], broker.launched)  # fail-closed across the wire
-
-
-class TestRequestLimits(unittest.TestCase):
-    """The privileged listener must not let a caller that can merely reach the
-    socket (no signed token) exhaust it via an oversized declared body — and it
-    rejects on the Content-Length *header*, before reading the body."""
-
-    def _addr(self) -> tuple[str, int]:
-        self.broker = StubBroker(secrets.token_bytes(16))
-        server = make_host_server(self.broker, "127.0.0.1", 0)
-        self.addCleanup(server.server_close)
-        threading.Thread(target=server.serve_forever, daemon=True).start()
-        self.addCleanup(server.shutdown)
-        host, port = server.server_address[:2]
-        return typing.cast(str, host), port
-
-    def test_oversized_content_length_is_rejected_before_reading(self) -> None:
-        host, port = self._addr()
-        conn = http.client.HTTPConnection(host, port, timeout=5)
-        self.addCleanup(conn.close)
-        # Declare an oversized body but send only a sliver: the server must reject
-        # on the header before reading, so the caller gets a clean, deterministic
-        # 413 (no large unread body to race a connection reset).
-        conn.putrequest("POST", "/broker", skip_accept_encoding=True)
-        conn.putheader("Content-Type", "application/json")
-        conn.putheader("Content-Length", str(MAX_BODY_BYTES + 1))
-        conn.endheaders()
-        conn.send(b"{}")  # far short of the declared length; never read
-        resp = conn.getresponse()
-        self.assertEqual(413, resp.status)
-        self.assertEqual([], self.broker.launched)  # never reached the broker
-
-
-class TestServeUnit(unittest.TestCase):
-    """Drive `Handler._serve` directly (no socket). The real per-request handler
-    runs in a daemon thread whose coverage/trace data is lost, so the
-    bounded-body and error paths are exercised here in the main thread instead."""
-
-    def _handler(self, broker: LaunchBroker, headers: dict[str, str],
-                 body: bytes = b"") -> tuple[Handler, MagicMock]:
-        server = HostControlServer.__new__(HostControlServer)
-        server.broker = broker
-        h = Handler.__new__(Handler)
-        h.server = server
-        h.headers = headers  # type: ignore[assignment] — dict is a valid .get() stand-in
-        h.path = "/broker"
-        h.rfile = io.BytesIO(body)
-        h.wfile = io.BytesIO()
-        send_response = MagicMock()
-        h.send_response = send_response  # type: ignore[method-assign]
-        h.send_header = MagicMock()  # type: ignore[method-assign]
-        h.end_headers = MagicMock()  # type: ignore[method-assign]
-        return h, send_response
-
-    def test_oversized_content_length_is_413(self) -> None:
-        broker = StubBroker(secrets.token_bytes(16))
-        h, send_response = self._handler(broker, {"Content-Length": str(MAX_BODY_BYTES + 1)})
-        h.do_POST()  # exercises do_POST -> _serve
-        send_response.assert_called_once_with(413)
-        self.assertEqual([], broker.launched)  # rejected before the broker
-
-    def test_invalid_content_length_is_400(self) -> None:
-        h, send_response = self._handler(StubBroker(secrets.token_bytes(16)),
-                                         {"Content-Length": "not-a-number"})
-        h._serve("POST")
-        send_response.assert_called_once_with(400)
-
-    def test_valid_request_dispatches_200(self) -> None:
-        secret = secrets.token_bytes(16)
-        broker = StubBroker(secret)
-        body = _body({"token": sign_request(
-            LaunchRequest(op="teardown", bottle_id="b1"), secret)})
-        h, send_response = self._handler(broker, {"Content-Length": str(len(body))}, body)
-        h._serve("POST")
-        send_response.assert_called_once_with(200)
-        self.assertEqual(["b1"], [r.bottle_id for r in broker.torn_down])
-
-    def test_dispatch_exception_becomes_500(self) -> None:
-        # dispatch is total, but the handler still guards it: a raised dispatch
-        # returns 500 rather than dropping the connection.
-        h, send_response = self._handler(
-            StubBroker(secrets.token_bytes(16)), {"Content-Length": "0"})
-        with patch("bot_bottle.orchestrator.host_server.dispatch",
-                   side_effect=RuntimeError("boom")):
-            h._serve("POST")
-        send_response.assert_called_once_with(500)
-
-    def test_health_over_do_get(self) -> None:
-        h, send_response = self._handler(StubBroker(secrets.token_bytes(16)), {})
-        h.path = "/health"
-        h.do_GET()
-        send_response.assert_called_once_with(200)
-
-
-class TestMain(unittest.TestCase):
-    def test_fail_closed_without_secret(self) -> None:
-        with patch("bot_bottle.orchestrator.host_server.broker_secret",
-                   return_value=None):
-            self.assertEqual(2, main(["--port", "0"]))
-
-    def test_serves_then_shuts_down_cleanly(self) -> None:
-        fake = MagicMock()
-        fake.server_address = ("127.0.0.1", 0)
-        fake.serve_forever.side_effect = KeyboardInterrupt
-        with patch("bot_bottle.orchestrator.host_server.broker_secret",
-                   return_value=b"k"), \
-             patch("bot_bottle.orchestrator.host_server.make_host_server",
-                   return_value=fake):
-            self.assertEqual(0, main(["--port", "0"]))
-        fake.serve_forever.assert_called_once()
-        fake.server_close.assert_called_once()
-
-
-if __name__ == "__main__":
-    unittest.main()

tests/unit/test_orchestrator_main.py

@@ -1,67 +0,0 @@
-"""Unit: the orchestrator dev-harness entrypoint (`python -m bot_bottle.orchestrator`).
-
-Exercises broker selection (stub / docker / http) and the fail-closed http path,
-patching `make_server` so the serve loop returns instead of blocking.
-"""
-
-from __future__ import annotations
-
-import os
-import secrets
-import tempfile
-import unittest
-from pathlib import Path
-from unittest.mock import MagicMock, patch
-
-from bot_bottle.orchestrator.__main__ import main
-from bot_bottle.paths import LAUNCH_BROKER_KEY_ENV
-
-
-def _fake_server() -> MagicMock:
-    fake = MagicMock()
-    fake.server_address = ("127.0.0.1", 0)
-    # Break out of serve_forever immediately, exercising the try/finally.
-    fake.serve_forever.side_effect = KeyboardInterrupt
-    return fake
-
-
-class TestMain(unittest.TestCase):
-    def _run(self, broker: str, env: dict[str, str] | None = None) -> tuple[int, MagicMock]:
-        fake = _fake_server()
-        with tempfile.TemporaryDirectory() as d:
-            argv = ["--db", str(Path(d) / "r.db"), "--port", "0", "--broker", broker]
-            with patch("bot_bottle.orchestrator.__main__.make_server", return_value=fake), \
-                    patch.dict("os.environ", env or {}, clear=False):
-                if env is None:
-                    os.environ.pop(LAUNCH_BROKER_KEY_ENV, None)
-                rc = main(argv)
-        return rc, fake
-
-    def test_stub_broker_serves_and_closes(self) -> None:
-        rc, fake = self._run("stub")
-        self.assertEqual(0, rc)
-        fake.serve_forever.assert_called_once()
-        fake.server_close.assert_called_once()
-
-    def test_docker_broker_serves(self) -> None:
-        rc, _ = self._run("docker")
-        self.assertEqual(0, rc)
-
-    def test_http_broker_with_injected_key_serves(self) -> None:
-        # The guest orchestrator takes the launch-broker key by injection.
-        rc, _ = self._run(
-            "http", env={LAUNCH_BROKER_KEY_ENV: secrets.token_urlsafe(16)})
-        self.assertEqual(0, rc)
-
-    def test_http_broker_without_injected_key_exits(self) -> None:
-        # Fail-closed: no host-file fallback for the guest, so a missing injected
-        # key is a usage error rather than a silently-minted divergent key.
-        with tempfile.TemporaryDirectory() as d:
-            with patch.dict("os.environ", {}, clear=False):
-                os.environ.pop(LAUNCH_BROKER_KEY_ENV, None)
-                with self.assertRaises(SystemExit):
-                    main(["--db", str(Path(d) / "r.db"), "--broker", "http"])
-
-
-if __name__ == "__main__":
-    unittest.main()

tests/unit/test_orchestrator_secret_store.py

@@ -2,12 +2,10 @@
 
 from __future__ import annotations
 
-import base64
 import unittest
 
 from bot_bottle.orchestrator.store.secret_store import (
     ENV_VAR_SECRET_NAME,
-    _NONCE_BYTES,
     decrypt_value,
     encrypt_value,
     new_env_var_secret,
@@ -67,27 +65,22 @@ class TestDecryptErrors(unittest.TestCase):
     def setUp(self) -> None:
         self.secret = new_env_var_secret()
 
-    def test_wrong_key_always_raises_value_error(self) -> None:
-        # Deterministic: the authentication tag rejects a wrong key every time,
-        # so reprovision can never inject a garbage token. Repeat across many
-        # random keys (the old unauthenticated scheme let ~5% through when the
-        # garbage happened to decode as valid UTF-8).
-        for _ in range(200):
-            ct = encrypt_value(self.secret, "secret-token")
-            with self.assertRaises(ValueError):
-                decrypt_value(new_env_var_secret(), ct)
-
-    def test_tampered_ciphertext_raises_value_error(self) -> None:
+    def test_wrong_key_raises_value_error(self) -> None:
         ct = encrypt_value(self.secret, "secret-token")
-        raw = bytearray(base64.urlsafe_b64decode(ct + "=" * (-len(ct) % 4)))
-        raw[_NONCE_BYTES] ^= 0x01  # flip a bit in the ciphertext body → tag mismatch
-        tampered = base64.urlsafe_b64encode(bytes(raw)).rstrip(b"=").decode()
-        with self.assertRaises(ValueError):
-            decrypt_value(self.secret, tampered)
+        other_key = new_env_var_secret()
+        # Wrong key produces garbage bytes; decrypt_value raises ValueError
+        # when the result is non-UTF-8 (which is very likely for 12-char data).
+        # We allow it to succeed only if garbage happens to be valid UTF-8, but
+        # the plaintext must not match.
+        try:
+            result = decrypt_value(other_key, ct)
+            self.assertNotEqual("secret-token", result)
+        except ValueError:
+            pass
 
     def test_truncated_blob_raises_value_error(self) -> None:
         with self.assertRaises(ValueError):
-            decrypt_value(self.secret, "dG9vc2hvcnQ")  # "tooshort" — under nonce+tag
+            decrypt_value(self.secret, "dG9vc2hvcnQ")  # "tooshort" — under 16 nonce bytes
 
     def test_invalid_base64_raises_value_error(self) -> None:
         with self.assertRaises(ValueError):

tests/unit/test_orchestrator_server.py

@@ -7,7 +7,6 @@ server tests), plus one real-socket round-trip to prove the handler wiring.
 from __future__ import annotations
 
 import base64
-import io
 import json
 import secrets
 import sqlite3
@@ -18,7 +17,7 @@ import urllib.error
 import urllib.request
 from contextlib import closing
 from pathlib import Path
-from unittest.mock import MagicMock, patch
+from unittest.mock import patch
 
 from bot_bottle.orchestrator_auth import ROLE_CLI, ROLE_GATEWAY, mint
 from bot_bottle.orchestrator.broker import StubBroker
@@ -284,25 +283,6 @@ class TestServerRoundTrip(unittest.TestCase):
         ))
         self.assertEqual(reg["bottle_id"], attr["bottle_id"])
 
-    def test_internal_failure_is_contextual_but_redacted(self) -> None:
-        orch = MagicMock()
-        orch.registry.all.side_effect = RuntimeError("SENSITIVE request value")
-        with patch("sys.stderr", io.StringIO()) as stderr:
-            server = make_server(orch, "127.0.0.1", 0)
-            self.addCleanup(server.server_close)
-            thread = threading.Thread(target=server.serve_forever, daemon=True)
-            thread.start()
-            self.addCleanup(server.shutdown)
-            host, port = server.server_address[0], server.server_address[1]
-            with self.assertRaises(urllib.error.HTTPError) as raised:
-                urllib.request.urlopen(f"http://{host}:{port}/bottles", timeout=5)
-            payload = json.loads(raised.exception.read())
-            output = stderr.getvalue()
-        self.assertEqual({"error": "internal error"}, payload)
-        self.assertIn("GET /bottles", output)
-        self.assertIn("RuntimeError", output)
-        self.assertNotIn("SENSITIVE", output)
-
 
 class TestOrchestratorAuth(unittest.TestCase):
     """Role-scoped control-plane tokens (issue #400 / #469 review): every route
@@ -667,24 +647,10 @@ class TestReconcileRoute(unittest.TestCase):
         self.assertEqual(200, status)
         self.assertEqual([], payload["reaped"])
 
-    def test_non_string_entries_are_rejected(self) -> None:
+    def test_non_string_entries_are_ignored(self) -> None:
+        dead = self._old("10.0.0.4")
         status, payload = dispatch(
             self.orch, "POST", "/reconcile",
             _body({"live_source_ips": [None, 7, "10.0.0.9"]}))
-        self.assertEqual(400, status)
-        self.assertIn("live_source_ips", str(payload["error"]))
-
-    def test_empty_live_source_ip_is_rejected(self) -> None:
-        status, payload = dispatch(
-            self.orch, "POST", "/reconcile", _body({"live_source_ips": [""]}))
-        self.assertEqual(400, status)
-        self.assertIn("live_source_ips", str(payload["error"]))
-
-    def test_invalid_grace_seconds_is_rejected(self) -> None:
-        for value in (True, "30", -1, float("inf"), float("nan")):
-            with self.subTest(value=value):
-                status, payload = dispatch(
-                    self.orch, "POST", "/reconcile",
-                    _body({"live_source_ips": [], "grace_seconds": value}))
-                self.assertEqual(400, status)
-                self.assertIn("grace_seconds", str(payload["error"]))
+        self.assertEqual(200, status)
+        self.assertEqual([dead], payload["reaped"])

tests/unit/test_orchestrator_service.py

@@ -11,12 +11,7 @@ from contextlib import closing
 from pathlib import Path
 from unittest.mock import patch
 
-from bot_bottle.orchestrator.broker import (
-    BrokerUnavailableError,
-    LaunchBroker,
-    LaunchRequest,
-    StubBroker,
-)
+from bot_bottle.orchestrator.broker import LaunchBroker, LaunchRequest, StubBroker
 from bot_bottle.orchestrator.store.registry_store import RegistryStore
 from bot_bottle.orchestrator.service import OrchestratorCore
 from bot_bottle.orchestrator.store.secret_store import new_env_var_secret
@@ -30,8 +25,8 @@ from bot_bottle.orchestrator.supervisor import (
 
 
 class _FailingBroker(LaunchBroker):
-    """Verifies the token like any broker, then fails the launch *definitely* —
-    to exercise the orchestrator's registry rollback."""
+    """Verifies the token like any broker, then fails the launch — to
+    exercise the orchestrator's registry rollback."""
 
     def _launch(self, req: LaunchRequest) -> None:
         raise RuntimeError("launch failed")
@@ -40,18 +35,6 @@ class _FailingBroker(LaunchBroker):
         pass
 
 
-class _UnavailableBroker(LaunchBroker):
-    """Verifies the token, then raises the *ambiguous* BrokerUnavailableError —
-    the host may already have launched — so the orchestrator must KEEP the
-    registry row rather than orphan a running container."""
-
-    def _launch(self, req: LaunchRequest) -> None:
-        raise BrokerUnavailableError("delivery dropped after send")
-
-    def _teardown(self, req: LaunchRequest) -> None:
-        pass
-
-
 class TestOrchestrator(unittest.TestCase):
     def setUp(self) -> None:
         self._tmp = tempfile.TemporaryDirectory()
@@ -122,19 +105,11 @@ class TestOrchestrator(unittest.TestCase):
 
     def test_reprovision_rejects_missing_rows_and_wrong_key(self) -> None:
         self.assertFalse(self.orch.reprovision_from_secret("missing", new_env_var_secret()))
-        key = "AQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQE"
-        wrong_key = "FBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQ"
-        # Pin the nonce so this is a deterministic wrong-key/decryption vector
-        # instead of a probabilistic assertion over random bytes.
-        with patch(
-            "bot_bottle.orchestrator.store.secret_store.secrets.token_bytes",
-            return_value=b"\0" * 16,
-        ):
-            rec = self.orch.launch_bottle(
-                "10.243.0.13", tokens={"K": "value"},
-                env_var_secret=key,
-            )
-        self.assertFalse(self.orch.reprovision_from_secret(rec.bottle_id, wrong_key))
+        rec = self.orch.launch_bottle(
+            "10.243.0.13", tokens={"K": "value"},
+            env_var_secret=new_env_var_secret(),
+        )
+        self.assertFalse(self.orch.reprovision_from_secret(rec.bottle_id, new_env_var_secret()))
 
     def test_set_policy_live_reload(self) -> None:
         rec = self.orch.launch_bottle("10.243.0.3")
@@ -161,20 +136,11 @@ class TestOrchestrator(unittest.TestCase):
         self.assertIsNotNone(self.orch.resolve("10.243.0.3", rec.identity_token))
         self.assertIsNone(self.orch.resolve("10.243.0.3", "wrong-token"))
 
-    def test_launch_rolls_back_registry_on_definite_broker_failure(self) -> None:
+    def test_launch_rolls_back_registry_on_broker_failure(self) -> None:
         orch = OrchestratorCore(self.store, _FailingBroker(self.secret), self.secret)
         with self.assertRaises(RuntimeError):
             orch.launch_bottle("10.243.0.9")
-        self.assertEqual([], self.store.all())  # no orphan row
-
-    def test_launch_keeps_registry_on_ambiguous_broker_failure(self) -> None:
-        # The host may already have launched the bottle before the response was
-        # lost, so deregistering would orphan a running container with no row.
-        # The row is kept for reconcile to reap iff the bottle is not live.
-        orch = OrchestratorCore(self.store, _UnavailableBroker(self.secret), self.secret)
-        with self.assertRaises(BrokerUnavailableError):
-            orch.launch_bottle("10.243.0.9")
-        self.assertEqual(1, len(self.store.all()))  # row survives — no orphan container
+        self.assertEqual([], self.store.all())  # no orphan
 
     def test_gateway_status_reports_unconfigured(self) -> None:
         # The orchestrator no longer owns a standalone gateway lifecycle; the

tests/unit/test_trust_domain.py

@@ -6,13 +6,10 @@ import unittest
 from unittest.mock import patch
 
 from bot_bottle import orchestrator_auth
-from bot_bottle.orchestrator_auth import ROLE_CLI, ROLE_GATEWAY, ROLE_HOST
+from bot_bottle.orchestrator_auth import ROLE_CLI, ROLE_GATEWAY
 from bot_bottle.trust_domain import (
     CONTROL_PLANE,
-    HOST_CONTROLLER,
-    LAUNCH_BROKER,
     ControlPlaneProvisioning,
-    LaunchBrokerProvisioning,
     ProvisioningError,
     TrustDomain,
 )
@@ -104,73 +101,5 @@ class TestControlPlaneProvisioning(unittest.TestCase):
         self.assertNotEqual(ROLE_CLI, CONTROL_PLANE.verify(tok, "k"))
 
 
-class TestLaunchBrokerAndHostControllerDomains(unittest.TestCase):
-    """The real #468 domains: the launch-broker key (shared by orchestrator +
-    host controller) and the host controller's own lifecycle key."""
-
-    def test_launch_broker_mints_no_role_tokens(self) -> None:
-        # Empty role set — it provides durable key material for the broker's own
-        # launch JWT, not orchestrator_auth role tokens.
-        self.assertEqual(frozenset(), LAUNCH_BROKER.roles)
-        with patch("bot_bottle.trust_domain.host_signing_key", return_value="k"):
-            with self.assertRaises(ValueError):
-                LAUNCH_BROKER.mint(ROLE_CLI)
-
-    def test_host_controller_signs_host_role_only(self) -> None:
-        with patch("bot_bottle.trust_domain.host_signing_key", return_value="k"):
-            tok = HOST_CONTROLLER.mint(ROLE_HOST)
-        self.assertEqual(ROLE_HOST, HOST_CONTROLLER.verify(tok, "k"))
-        # A control-plane `cli` token (the orchestrator's key) never verifies as a
-        # host-controller role — the orchestrator can't forge lifecycle creds.
-        cli_tok = orchestrator_auth.mint(ROLE_CLI, "k")
-        self.assertIsNone(HOST_CONTROLLER.verify(cli_tok, "k"))
-
-    def test_control_plane_cannot_mint_the_host_role(self) -> None:
-        # `host` is outside the control-plane role set on purpose.
-        with patch("bot_bottle.trust_domain.host_signing_key", return_value="k"):
-            with self.assertRaises(ValueError):
-                CONTROL_PLANE.mint(ROLE_HOST)
-
-    def test_the_three_domains_use_distinct_keys_and_env_vars(self) -> None:
-        self.assertEqual(3, len({
-            CONTROL_PLANE.key_filename,
-            LAUNCH_BROKER.key_filename,
-            HOST_CONTROLLER.key_filename,
-        }))
-        self.assertEqual(3, len({
-            CONTROL_PLANE.key_env, LAUNCH_BROKER.key_env, HOST_CONTROLLER.key_env,
-        }))
-
-
-class TestLaunchBrokerProvisioning(unittest.TestCase):
-    def test_broker_key_returns_the_durable_key(self) -> None:
-        prov = LaunchBrokerProvisioning()
-        with patch("bot_bottle.trust_domain.host_signing_key", return_value="bk"):
-            self.assertEqual("bk", prov.broker_key())
-
-    def test_broker_key_fail_closes_when_empty(self) -> None:
-        # An empty key would leave the host controller unable to verify any
-        # launch — fail-closed rather than hand back a useless/dangerous key.
-        prov = LaunchBrokerProvisioning()
-        with patch("bot_bottle.trust_domain.host_signing_key", return_value=""):
-            with self.assertRaises(ProvisioningError):
-                prov.broker_key()
-
-    def test_controller_key_is_distinct_from_the_broker_key(self) -> None:
-        # The orchestrator holds the broker key but NEVER the controller key.
-        prov = LaunchBrokerProvisioning()
-        keys = {"launch-broker-key": "bk", "host-controller-key": "ck"}
-        with patch("bot_bottle.trust_domain.host_signing_key",
-                   side_effect=keys.__getitem__):
-            self.assertEqual("bk", prov.broker_key())
-            self.assertEqual("ck", prov.controller_key())
-
-    def test_controller_key_fail_closes_when_empty(self) -> None:
-        prov = LaunchBrokerProvisioning()
-        with patch("bot_bottle.trust_domain.host_signing_key", return_value=""):
-            with self.assertRaises(ProvisioningError):
-                prov.controller_key()
-
-
 if __name__ == "__main__":
     unittest.main()

tests/unit/test_unittest_gate.py

@@ -1,91 +0,0 @@
-"""Unit tests for CI's unittest execution-count gate."""
-
-from __future__ import annotations
-
-import unittest
-from contextlib import redirect_stderr
-from io import StringIO
-from unittest.mock import Mock, patch
-
-from scripts.unittest_gate import assurance_errors, main
-
-
-class TestAssuranceErrors(unittest.TestCase):
-    def test_accepts_suite_that_meets_minimum_without_skips(self) -> None:
-        self.assertEqual(
-            [],
-            assurance_errors(
-                tests_run=22, skipped=0, minimum_executed=22, fail_on_skip=True
-            ),
-        )
-
-    def test_rejects_green_suite_below_execution_minimum(self) -> None:
-        errors = assurance_errors(
-            tests_run=22, skipped=18, minimum_executed=22, fail_on_skip=False
-        )
-        self.assertEqual(1, len(errors))
-        self.assertIn("executed 4", errors[0])
-
-    def test_rejects_any_skip_when_required(self) -> None:
-        errors = assurance_errors(
-            tests_run=23, skipped=1, minimum_executed=22, fail_on_skip=True
-        )
-        self.assertEqual(["1 test(s) skipped in a no-skip suite"], errors)
-
-    def test_main_accepts_successful_assured_suite(self) -> None:
-        result = Mock(
-            testsRun=22,
-            skipped=[],
-            wasSuccessful=Mock(return_value=True),
-        )
-        runner = Mock()
-        runner.run.return_value = result
-        with patch(
-            "scripts.unittest_gate.unittest.defaultTestLoader.discover",
-            return_value=Mock(),
-        ) as discover, patch(
-            "scripts.unittest_gate.unittest.TextTestRunner",
-            return_value=runner,
-        ) as runner_type:
-            self.assertEqual(
-                0,
-                main([
-                    "-s", "tests/integration",
-                    "-t", ".",
-                    "-p", "test_*.py",
-                    "--minimum-executed", "22",
-                    "--fail-on-skip",
-                    "-v",
-                ]),
-            )
-        discover.assert_called_once_with(
-            "tests/integration", pattern="test_*.py", top_level_dir="."
-        )
-        runner_type.assert_called_once_with(verbosity=2)
-
-    def test_main_rejects_unsuccessful_underfilled_suite(self) -> None:
-        result = Mock(
-            testsRun=1,
-            skipped=[(Mock(), "not available")],
-            wasSuccessful=Mock(return_value=False),
-        )
-        runner = Mock()
-        runner.run.return_value = result
-        error = StringIO()
-        with patch(
-            "scripts.unittest_gate.unittest.defaultTestLoader.discover",
-            return_value=Mock(),
-        ), patch(
-            "scripts.unittest_gate.unittest.TextTestRunner",
-            return_value=runner,
-        ), redirect_stderr(error):
-            self.assertEqual(
-                1,
-                main(["--minimum-executed", "2", "--fail-on-skip"]),
-            )
-        self.assertIn("below required minimum", error.getvalue())
-        self.assertIn("skipped in a no-skip suite", error.getvalue())
-
-
-if __name__ == "__main__":
-    unittest.main()