refactor(gateway): split data-plane files into egress/supervisor/git_gate services

Group the gateway's data-plane modules into three service sub-packages
mirroring the host-side trio (bot_bottle.egress / .supervisor / .git_gate):

  gateway/egress/     addon_core, addon, dlp_config, dlp_detectors
  gateway/supervisor/ server            (was supervise_server)
  gateway/git_gate/   render, http_backend

Prefix-stripped filenames now that the package namespaces them; each
sub-package has a thin docstring __init__ (no eager imports, cheap leaf
loads). The two cross-cutting files stay at the gateway root:
policy_resolver (shared per-client lookup) and gateway_init, renamed to
bootstrap now that gateway/ already namespaces it.

Updated all importers (bot_bottle + tests), the in-VM/container `-m`
launch strings, the Dockerfile.gateway addon shim + ENTRYPOINT, and the
five gateway entries in scripts/critical-modules.txt. Full unit suite
green (2243).

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

bot_bottle/gateway/git_gate/__init__.py

@@ -0,0 +1,7 @@
+"""Gateway-side (data-plane) git-gate service: pure host-side hook rendering
+(PRD 0008) and the smart-HTTP backend that fronts git-gate repos.
+
+The host-side git-gate service (provisioning, preflight) lives in
+`bot_bottle.git_gate`; this is the data-plane counterpart. Import the concrete
+modules directly (`from bot_bottle.gateway.git_gate.render import ...`).
+"""

bot_bottle/gateway/git_gate/http_backend.py

@@ -0,0 +1,287 @@
+"""Tiny smart-HTTP wrapper for git-gate repos.
+
+Used where `git://` push traffic over a host-published Docker port can
+hang before receive-pack reaches hooks (e.g. the firecracker backend,
+where the guest reaches the gateway over the point-to-point TAP). The
+wrapper serves the same `/git/*.git` bare repos through
+`git http-backend`, so pre-receive and upstream forwarding remain the
+git-gate enforcement point.
+
+One shared gateway serves every bottle (PRD 0070): each request is served
+from the calling bottle's repo namespace (`<root>/<bottle_id>`), attributed
+from the unspoofable source IP via the orchestrator. Per-repo credentials +
+hooks scope by repo directory, so isolating the *root* per bottle isolates
+its creds too. Unattributed clients — and a missing/unreachable orchestrator
+— fail closed (404). `BOT_BOTTLE_ORCHESTRATOR_URL` is mandatory: there is no
+single-tenant flat-root fallback.
+"""
+
+from __future__ import annotations
+
+import os
+import subprocess
+import sys
+import typing
+from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
+from pathlib import Path
+from urllib.parse import urlsplit
+
+from bot_bottle.constants import GIT_GATE_TIMEOUT_SECS, IDENTITY_HEADER
+from bot_bottle.gateway.policy_resolver import PolicyResolveError, PolicyResolver
+
+
+DEFAULT_PORT = 9420
+
+# The per-host orchestrator control plane the backend attributes each request
+# to, serving from the *calling* bottle's repo namespace selected by source IP.
+# Mandatory — the same env the egress addon requires; there is no single flat
+# repo-root fallback.
+ORCHESTRATOR_URL_ENV = "BOT_BOTTLE_ORCHESTRATOR_URL"
+
+# The base under which each bottle's `<bottle_id>` repo namespace is nested.
+DEFAULT_REPO_ROOT = "/git"
+
+
+class ResolverLike(typing.Protocol):
+    """Structural type for the resolver `resolve_sandbox_root` needs — just
+    `resolve_bottle_id`. A Protocol so tests can pass a fake without
+    importing PolicyResolver (mirrors egress_addon_core.PolicyResolverLike)."""
+
+    def resolve_bottle_id(
+        self, source_ip: str, identity_token: str = ...,
+    ) -> "str | None": ...
+
+
+def resolve_sandbox_root(
+    resolver: "ResolverLike",
+    base_root: Path,
+    source_ip: str,
+    identity_token: str = "",
+) -> Path | None:
+    """The per-sandbox repo root to serve this request from — `base_root/
+    <bottle_id>`, where the sandbox is attributed from the source IP via the
+    orchestrator — or None to deny (404). Fail-closed: an unattributed client, a
+    resolver error, or a namespace that would escape `base_root` all deny, so one
+    sandbox can never reach another's repos."""
+    try:
+        bottle_id = resolver.resolve_bottle_id(source_ip, identity_token)
+    except PolicyResolveError:
+        return None  # orchestrator unreachable/errored → deny
+    if not bottle_id:
+        return None  # unattributed → deny
+    base = base_root.resolve()
+    namespace = (base / bottle_id).resolve()
+    if base not in namespace.parents:
+        return None  # bottle_id tried to escape the root → deny
+    return namespace
+
+# Bound memory use while still allowing ordinary git push packfiles.
+MAX_BODY_BYTES = 100 * 1024 * 1024
+
+
+class GitHttpHandler(BaseHTTPRequestHandler):
+    server_version = "bot-bottle-git-http/1"
+
+    def do_GET(self) -> None:
+        self._run_backend()
+
+    def do_POST(self) -> None:
+        self._run_backend()
+
+    def _sandbox_root(self) -> Path | None:
+        """This request's per-sandbox repo root (the calling bottle's source-IP-
+        selected `<base>/<bottle_id>` namespace), or None to deny. `GIT_PROJECT_
+        ROOT` keeps git's own env-var name."""
+        base = Path(os.environ.get("GIT_PROJECT_ROOT", DEFAULT_REPO_ROOT))
+        resolver = getattr(self.server, "policy_resolver", None)
+        if resolver is None:
+            return None  # server started without a resolver (misconfig) → deny
+        token = self.headers.get(IDENTITY_HEADER, "")
+        return resolve_sandbox_root(resolver, base, self.client_address[0], token)
+
+    def _run_backend(self) -> None:
+        sandbox_root = self._sandbox_root()
+        if sandbox_root is None:
+            # Unattributed / resolver error: deny before touching any repo.
+            self.send_error(404)
+            return
+        parsed = urlsplit(self.path)
+        if self._is_upload_pack(parsed.path, parsed.query):
+            repo_dir = self._repo_dir(sandbox_root, parsed.path)
+            if repo_dir is None:
+                self.send_error(404)
+                return
+            hook_path = os.environ.get(
+                "GIT_GATE_ACCESS_HOOK", "/etc/git-gate/access-hook",
+            )
+            peer = self.client_address[0]
+            try:
+                hook = subprocess.run(
+                    [hook_path, "upload-pack", str(repo_dir), peer, peer],
+                    capture_output=True,
+                    check=False,
+                    timeout=GIT_GATE_TIMEOUT_SECS,
+                )
+            except (OSError, subprocess.SubprocessError) as exc:
+                # The access-hook couldn't be run (missing, not executable,
+                # timed out, …). Fail closed with a real HTTP error rather
+                # than letting the exception kill the handler thread — an
+                # unhandled exception closes the socket with no response, which
+                # the client sees as an opaque "empty reply from server".
+                self.log_message(
+                    "access-hook could not run for %s: %s", parsed.path, exc,
+                )
+                self.send_error(503, "git-gate access-hook unavailable")
+                return
+            if hook.returncode != 0:
+                detail = (hook.stderr or hook.stdout).decode(
+                    "utf-8", errors="replace",
+                ).rstrip()
+                if detail:
+                    for line in detail.splitlines():
+                        self.log_message("access-hook denied %s: %s",
+                                         parsed.path, line)
+                else:
+                    self.log_message(
+                        "access-hook denied %s: exit=%d (no output)",
+                        parsed.path, hook.returncode,
+                    )
+                self.send_response(403)
+                self.send_header("Content-Type", "text/plain; charset=utf-8")
+                self.end_headers()
+                self.wfile.write(hook.stderr or hook.stdout)
+                return
+        env = os.environ.copy()
+        env.update({
+            "GIT_PROJECT_ROOT": str(sandbox_root),
+            "GIT_HTTP_EXPORT_ALL": "1",
+            "REQUEST_METHOD": self.command,
+            "PATH_INFO": parsed.path,
+            "QUERY_STRING": parsed.query,
+            "CONTENT_TYPE": self.headers.get("content-type", ""),
+            "CONTENT_LENGTH": self.headers.get("content-length", "0"),
+            "REMOTE_ADDR": self.client_address[0],
+            "REMOTE_PORT": str(self.client_address[1]),
+            "REMOTE_USER": "",
+            "SERVER_NAME": self.server.server_name,  # type: ignore
+            "SERVER_PORT": str(self.server.server_port),  # type: ignore
+            "SERVER_PROTOCOL": self.request_version,
+        })
+        # Attribute the gitleaks-allow supervise proposal (queued by
+        # receive-pack's pre-receive hook, a child of the CGI we spawn below) to
+        # the calling bottle. The hook queues over the control-plane RPC (PRD
+        # 0070 / issue #469), which re-resolves the bottle from these — the same
+        # (source_ip, identity_token) pair that selected the namespaced root
+        # above — so it can only ever queue its own proposals.
+        env["SUPERVISE_SOURCE_IP"] = self.client_address[0]
+        env["SUPERVISE_IDENTITY_TOKEN"] = self.headers.get(IDENTITY_HEADER, "")
+        for header, variable in (
+            ("accept", "HTTP_ACCEPT"),
+            ("content-encoding", "HTTP_CONTENT_ENCODING"),
+            ("git-protocol", "HTTP_GIT_PROTOCOL"),
+            ("user-agent", "HTTP_USER_AGENT"),
+        ):
+            value = self.headers.get(header)
+            if value:
+                env[variable] = value
+        raw_length = self.headers.get("content-length", "0") or "0"
+        try:
+            length = int(raw_length)
+        except ValueError:
+            self.send_error(400, "Bad Content-Length")
+            return
+        if length < 0:
+            self.send_error(400, "Negative Content-Length")
+            return
+        if length > MAX_BODY_BYTES:
+            self.send_error(413, "Request body too large")
+            return
+        body = self.rfile.read(length) if length else b""
+        proc = subprocess.run(
+            ["git", "http-backend"],
+            input=body,
+            env=env,
+            capture_output=True,
+            check=False,
+            timeout=GIT_GATE_TIMEOUT_SECS,
+        )
+        self._write_cgi_response(proc.stdout)
+
+    def _repo_dir(self, sandbox_root: Path, path: str) -> Path | None:
+        root = sandbox_root.resolve()
+        relative = path.lstrip("/").split(".git", 1)[0] + ".git"
+        candidate = (root / relative).resolve()
+        if root not in (candidate, *candidate.parents):
+            return None
+        if not candidate.is_dir():
+            return None
+        return candidate
+
+    @staticmethod
+    def _is_upload_pack(path: str, query: str) -> bool:
+        if path.endswith("/git-upload-pack"):
+            return True
+        if path.endswith("/info/refs"):
+            return any(
+                pair == "service=git-upload-pack"
+                for pair in query.split("&")
+            )
+        return False
+
+    def _write_cgi_response(self, raw: bytes) -> None:
+        head, sep, body = raw.partition(b"\r\n\r\n")
+        line_sep = b"\r\n"
+        if not sep:
+            head, sep, body = raw.partition(b"\n\n")
+            line_sep = b"\n"
+        status = 200
+        headers: list[tuple[str, str]] = []
+        for line in head.split(line_sep):
+            if not line:
+                continue
+            key, _, value = line.decode("latin1").partition(":")
+            value = value.strip()
+            if key.lower() == "status":
+                try:
+                    status = int(value.split()[0])
+                except (ValueError, IndexError):
+                    self.log_message(
+                        "malformed CGI Status header %r; using 500", value,
+                    )
+                    status = 500
+            else:
+                headers.append((key, value))
+        self.send_response(status)
+        for key, value in headers:
+            self.send_header(key, value)
+        self.end_headers()
+        self.wfile.write(body)
+
+    def log_message(self, format: str, *args: object) -> None:  # type: ignore  # noqa: A002
+        sys.stdout.write(format % args + "\n")
+        sys.stdout.flush()
+
+
+def main() -> int:
+    port = int(os.environ.get("GIT_HTTP_PORT", str(DEFAULT_PORT)))
+    orch_url = os.environ.get(ORCHESTRATOR_URL_ENV, "").strip()
+    if not orch_url:
+        # Resolver-only: without an orchestrator the backend can't attribute a
+        # request to a bottle namespace, so it must not serve (fail-closed).
+        sys.stderr.write(
+            f"git-http: {ORCHESTRATOR_URL_ENV} is required "
+            "(no single-tenant flat-root fallback)\n"
+        )
+        return 1
+    server = ThreadingHTTPServer(("0.0.0.0", port), GitHttpHandler)
+    # Resolve each request's sandbox namespace by source IP against the
+    # orchestrator control plane.
+    server.policy_resolver = PolicyResolver(orch_url)  # type: ignore[attr-defined]
+    sys.stdout.write(f"git-http listening on 0.0.0.0:{port} (multi-tenant)\n")
+    sys.stdout.flush()
+    server.serve_forever()
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

bot_bottle/gateway/git_gate/render.py

@@ -0,0 +1,562 @@
+"""Pure host-side rendering for the per-agent git-gate (PRD 0008).
+
+Builds the agent's `.gitconfig` insteadOf rewrites, the known_hosts
+line, and the entrypoint / pre-receive / access-hook scripts the gateway
+runs. No docker or forge calls — exposed for tests and reuse across
+backends. The host-side service (`git_gate.GitGate`) and the deploy-key
+lifecycle (`git_gate.provision`) each read on their own; `git_gate`
+re-exports these names for API stability."""
+
+from __future__ import annotations
+
+import re
+import shlex
+from dataclasses import dataclass
+from pathlib import Path
+
+from ...constants import GIT_GATE_TIMEOUT_SECS, IDENTITY_HEADER
+from ...manifest import ManifestBottle, ManifestGitEntry
+
+# Short network alias for git-gate inside the gateway. The
+# agent's `.gitconfig` insteadOf rewrites resolve through this name.
+GIT_GATE_HOSTNAME = "git-gate"
+
+
+@dataclass(frozen=True)
+class GitGateUpstream:
+    """One bare repo on the gate. `name` drives the bare-repo path
+    (`/git/<name>.git`), the agent's URL after insteadOf rewrite
+    (`git://<gate>/<name>.git`), and the per-upstream credential
+    paths inside the gate (`/git-gate/creds/<name>-key` and
+    `/git-gate/creds/<name>-known_hosts`).
+
+    `identity_file` is the host-side absolute path the gate's start
+    step will docker-cp into the container. `known_host_key` is the
+    KnownHostKey string from the manifest; the gate's start step
+    materialises it into a known_hosts file if non-empty.
+
+    the gate credential paths inside the running gateway."""
+
+    name: str
+    upstream_url: str
+    upstream_host: str
+    upstream_port: str
+    identity_file: str
+    known_host_key: str
+    known_hosts_file: Path = Path()
+
+def git_gate_upstreams_for_bottle(bottle: ManifestBottle) -> tuple[GitGateUpstream, ...]:
+    """Lift each `bottle.git` entry into a GitGateUpstream. Unique-Name
+    validation already ran in `manifest.ManifestBottle.from_dict`."""
+    return tuple(
+        GitGateUpstream(
+            name=e.Name,
+            upstream_url=e.Upstream,
+            upstream_host=e.UpstreamHost,
+            upstream_port=e.UpstreamPort,
+            identity_file=e.IdentityFile,
+            known_host_key=e.KnownHostKey,
+        )
+        for e in bottle.git
+    )
+
+
+def _gitconfig_validate_value(field: str, value: str) -> None:
+    """Raise ValueError if value contains characters that break gitconfig line syntax."""
+    if "\n" in value or "\r" in value:
+        raise ValueError(
+            f"git-gate: {field} contains a newline, which would inject "
+            f"arbitrary gitconfig keys; rejecting manifest entry"
+        )
+
+
+def git_gate_render_gitconfig(
+    entries: tuple[ManifestGitEntry, ...], gate_host: str, *, scheme: str = "git",
+    identity_token: str = "",
+) -> str:
+    """Render the agent's ~/.gitconfig content for git-gate
+    `insteadOf` rewrites. Pure host-side, no docker / VM;
+    exposed for tests + reuse across backends.
+
+    `gate_host` is the part of the URL between `<scheme>://` and the
+    repo path — backends differ here:
+      - docker:        `git-gate` (the short network alias)
+      - firecracker:   `<bundle_ip>:<port>` (no DNS on the
+                       point-to-point TAP link)
+
+    Empty `entries` returns an empty string so callers can no-op
+    cleanly without conditional formatting at the call site."""
+    if not entries:
+        return ""
+    out = [
+        "# bot-bottle git-gate (PRD 0008): every git operation against\n",
+        "# a declared upstream routes through the gate, which mirrors\n",
+        "# the upstream bidirectionally (gitleaks-scanned push;\n",
+        "# fetch-from-upstream-before-every-upload-pack via access-hook).\n",
+    ]
+    # Over the smart-HTTP transport (VM backends), attach the per-bottle
+    # identity token as a request header on requests to the gate, scoped to
+    # its URL so it never goes to any other remote. git-http requires it (the
+    # gateway's mandatory (source_ip, token) attribution). git:// (single-tenant
+    # docker) carries no header — attribution there is the network alias.
+    if identity_token and scheme == "http":
+        _gitconfig_validate_value("identity_token", identity_token)
+        out.append(f'[http "http://{gate_host}/"]\n')
+        out.append(f"\textraHeader = {IDENTITY_HEADER}: {identity_token}\n")
+    for entry in entries:
+        _gitconfig_validate_value(f"repos[{entry.Name!r}].url", entry.Upstream)
+        out.append(f'[url "{scheme}://{gate_host}/{entry.Name}.git"]\n')
+        out.append(f"\tinsteadOf = {entry.Upstream}\n")
+        if entry.RemoteKey and entry.RemoteKey != entry.UpstreamHost:
+            port = (
+                f":{entry.UpstreamPort}"
+                if entry.UpstreamPort and entry.UpstreamPort != "22"
+                else ""
+            )
+            alias = (
+                f"ssh://{entry.UpstreamUser}@{entry.RemoteKey}{port}/"
+                f"{entry.UpstreamPath}"
+            )
+            _gitconfig_validate_value(f"repos[{entry.Name!r}].url (resolved alias)", alias)
+            out.append(f"\tinsteadOf = {alias}\n")
+    return "".join(out)
+
+
+def git_gate_known_hosts_line(host: str, port: str, key: str) -> str:
+    """Format `host[:port] key` for OpenSSH's known_hosts. Non-default
+    ports use the bracketed `[host]:port` form (the form OpenSSH writes
+    on disk for hosts reached via a non-22 port)."""
+    if port and port != "22":
+        target = f"[{host}]:{port}"
+    else:
+        target = host
+    return f"{target} {key}\n"
+
+
+def _git_gate_init_repo_fn(repo_root: str, creds_dir: str) -> list[str]:
+    """The `init_repo` shell function, parameterized by the bare-repo root
+    and the per-bottle creds dir. Single source of the credential-wiring
+    logic, shared by the single-tenant daemon entrypoint (`/git`,
+    `/git-gate/creds`) and the consolidated per-bottle provisioning
+    (`/git/<bottle_id>`, `/git-gate/creds/<bottle_id>`)."""
+    return [
+        "init_repo() {",
+        "  name=$1",
+        "  upstream_url=$2",
+        f"  keyfile={creds_dir}/${{name}}-key",
+        f"  hostsfile={creds_dir}/${{name}}-known_hosts",
+        "",
+        # `|| true`: PRD 0018 chunk 3+ bind-mounts these RO from the
+        # host, so chmod-syscalls fail with EROFS. The files already
+        # have the right perms on the host (SSH requires 0600 to load
+        # the key in the first place), so the chmod is best-effort
+        # cleanup for the legacy docker-cp path where the file
+        # landed at the host's umask perms.
+        "  chmod 600 \"$keyfile\" 2>/dev/null || true",
+        "  if [ -f \"$hostsfile\" ]; then",
+        "    chmod 600 \"$hostsfile\" 2>/dev/null || true",
+        "  fi",
+        "",
+        f"  repo={repo_root}/${{name}}.git",
+        "  if [ ! -d \"$repo\" ]; then",
+        "    git init --bare \"$repo\" >/dev/null",
+        # --mirror=fetch sets remote.origin.fetch = +refs/*:refs/* so a later
+        # `git fetch origin` mirrors the upstream's full ref graph (heads,
+        # tags, notes) into the bare repo at canonical paths. It does NOT set
+        # remote.origin.mirror=true, so an explicit `git push origin
+        # <ref>:<ref>` still pushes one ref.
+        "    git -C \"$repo\" remote add --mirror=fetch origin \"$upstream_url\"",
+        "  fi",
+        "  git -C \"$repo\" config git-gate.identityFile \"$keyfile\"",
+        "  git -C \"$repo\" config git-gate.knownHosts \"$hostsfile\"",
+        "  git -C \"$repo\" config receive.denyCurrentBranch ignore",
+        "  git -C \"$repo\" config receive.advertisePushOptions true",
+        "  git -C \"$repo\" config http.receivepack true",
+        "  install -m 755 /etc/git-gate/pre-receive \"$repo/hooks/pre-receive\"",
+        "}",
+    ]
+
+
+def git_gate_render_entrypoint(upstreams: tuple[GitGateUpstream, ...]) -> str:
+    """Posix-sh entrypoint. One `init_repo` call per upstream, then
+    `exec git daemon`. The function reads
+    `/git-gate/creds/<name>-{key,known_hosts}` (bind-mounted into
+    the bundle by the renderer) and wires them into each bare repo's
+    config; the access-hook + pre-receive hook pick those paths up
+    at fetch / push time."""
+    lines = ["#!/bin/sh", "set -eu", ""]
+    lines += _git_gate_init_repo_fn("/git", "/git-gate/creds")
+    lines += ["", "mkdir -p /git"]
+    for u in upstreams:
+        lines.append(f"init_repo {shlex.quote(u.name)} {shlex.quote(u.upstream_url)}")
+    lines.extend([
+        "",
+        "exec git daemon \\",
+        "  --reuseaddr \\",
+        f"  --timeout={GIT_GATE_TIMEOUT_SECS} \\",
+        f"  --init-timeout={GIT_GATE_TIMEOUT_SECS} \\",
+        "  --base-path=/git \\",
+        "  --export-all \\",
+        "  --enable=receive-pack \\",
+        "  --access-hook=/etc/git-gate/access-hook \\",
+        "  --verbose",
+    ])
+    return "\n".join(lines) + "\n"
+
+
+# A bottle id namespaces the consolidated gateway's repo + creds dirs; it is
+# embedded unquoted in the provisioning script, so restrict it to a shell- and
+# path-safe alphabet (registry ids are token_hex — this is defense in depth).
+_SAFE_BOTTLE_ID = re.compile(r"[A-Za-z0-9_-]+")
+
+
+def git_gate_render_provision(
+    bottle_id: str, upstreams: tuple[GitGateUpstream, ...],
+) -> str:
+    """Posix-sh script that provisions ONE bottle's bare repos into the
+    consolidated gateway (PRD 0070), under `/git/<bottle_id>/` with creds
+    read from `/git-gate/creds/<bottle_id>/`. Init-only — no `git daemon`,
+    since the shared gateway already serves every bottle; run inside the
+    running gateway when the bottle is registered.
+
+    Isolating each bottle's repo root and creds dir by id is what keeps one
+    bottle's push credentials out of another's repos on the shared gateway."""
+    if not _SAFE_BOTTLE_ID.fullmatch(bottle_id):
+        raise ValueError(f"git-gate: unsafe bottle id {bottle_id!r}")
+    repo_root = f"/git/{bottle_id}"
+    creds_dir = f"/git-gate/creds/{bottle_id}"
+    lines = ["#!/bin/sh", "set -eu", ""]
+    lines += _git_gate_init_repo_fn(repo_root, creds_dir)
+    lines += ["", f"mkdir -p {shlex.quote(repo_root)}"]
+    for u in upstreams:
+        lines.append(f"init_repo {shlex.quote(u.name)} {shlex.quote(u.upstream_url)}")
+    return "\n".join(lines) + "\n"
+
+
+def git_gate_render_hook() -> str:
+    """The shared pre-receive hook: gitleaks-scan all incoming refs,
+    then forward each accepted ref to the real upstream (`origin`)
+    using the per-repo credential. Failure in either phase aborts
+    the push so the agent sees a real rejection. POSIX sh.
+
+    Two phases (scan all, then push all) keeps a hit on ref N from
+    half-pushing refs 1..N-1; both phases re-read stdin from a temp
+    file because pre-receive's stdin is a one-shot stream."""
+    return r"""#!/bin/sh
+# git-gate pre-receive (PRD 0008). Stdin: <old> <new> <ref> per line.
+set -u
+
+refs_file=$(mktemp)
+trap 'rm -f "$refs_file"' EXIT
+cat > "$refs_file"
+
+zero=0000000000000000000000000000000000000000
+
+supervise_gitleaks_allow() {
+  log_opts=$1
+  ref=$2
+  report_file=$(mktemp)
+  if ! gitleaks git \
+      --log-opts="$log_opts" \
+      --no-banner \
+      --redact \
+      --ignore-gitleaks-allow \
+      --report-format=json \
+      --report-path="$report_file" \
+      --exit-code 0 \
+      1>&2; then
+    rm -f "$report_file"
+    echo "git-gate: gitleaks inline-suppression scan failed for $ref" >&2
+    return 1
+  fi
+
+  proposal_id=$(
+    PYTHONPATH="/app${PYTHONPATH:+:$PYTHONPATH}" GITLEAKS_ALLOW_REF="$ref" python3 - "$report_file" <<'PY'
+import json
+import os
+import sys
+from pathlib import Path
+
+# Queue over the control-plane RPC — the git-gate data plane no longer opens
+# bot-bottle.db (PRD 0070 / issue #469). Attribution is by (source_ip,
+# identity_token), resolved server-side, so the proposal lands under the
+# calling bottle exactly as a direct write once did.
+try:
+    from bot_bottle.gateway.policy_resolver import PolicyResolver, PolicyResolveError
+    from bot_bottle.supervisor.types import TOOL_GITLEAKS_ALLOW
+except ImportError:
+    from policy_resolver import PolicyResolver, PolicyResolveError
+    from supervisor.types import TOOL_GITLEAKS_ALLOW
+
+report_path = Path(sys.argv[1])
+source_ip = os.environ.get("SUPERVISE_SOURCE_IP", "")
+token = os.environ.get("SUPERVISE_IDENTITY_TOKEN", "")
+orch_url = os.environ.get("BOT_BOTTLE_ORCHESTRATOR_URL", "")
+if not source_ip or not orch_url:
+    sys.exit(2)
+
+try:
+    raw = json.loads(report_path.read_text() or "[]")
+except json.JSONDecodeError:
+    sys.exit(3)
+if not isinstance(raw, list):
+    sys.exit(3)
+if not raw:
+    sys.exit(0)
+
+ref = os.environ.get("GITLEAKS_ALLOW_REF", "")
+lines = [
+    "gitleaks inline suppression requires supervisor approval",
+    f"ref: {ref}",
+    "",
+]
+for i, finding in enumerate(raw, 1):
+    if not isinstance(finding, dict):
+        continue
+    file_path = finding.get("File", "")
+    line_no = finding.get("StartLine", finding.get("Line", ""))
+    rule_id = finding.get("RuleID", "")
+    commit = finding.get("Commit", "")
+    line = finding.get("Line", "")
+    lines.extend([
+        f"finding {i}:",
+        f"  file: {file_path}",
+        f"  line: {line_no}",
+        f"  rule: {rule_id}",
+        f"  commit: {commit}",
+        f"  code: {line}",
+        "",
+    ])
+
+payload = "\n".join(lines).rstrip() + "\n"
+try:
+    proposal_id = PolicyResolver(orch_url).propose_supervise(
+        source_ip, token,
+        tool=TOOL_GITLEAKS_ALLOW,
+        proposed_file=payload,
+        justification=(
+            "git-gate found gitleaks findings hidden by # gitleaks:allow; "
+            "approve only for dummy test fixtures or confirmed false positives"
+        ),
+    )
+except PolicyResolveError:
+    sys.exit(4)
+if not proposal_id:
+    sys.exit(2)
+print(proposal_id)
+PY
+  )
+  rc=$?
+  rm -f "$report_file"
+  if [ "$rc" -eq 0 ] && [ -z "$proposal_id" ]; then
+    return 0
+  fi
+  if [ "$rc" -ne 0 ]; then
+    echo "git-gate: cannot route # gitleaks:allow finding to supervisor; refusing push" >&2
+    return 1
+  fi
+
+  timeout=${SUPERVISE_GITLEAKS_ALLOW_TIMEOUT_SECONDS:-300}
+  case "$timeout" in
+    ''|*[!0-9]*)
+      echo "git-gate: invalid SUPERVISE_GITLEAKS_ALLOW_TIMEOUT_SECONDS=$timeout" >&2
+      return 1
+      ;;
+  esac
+  echo "git-gate: queued # gitleaks:allow supervisor approval $proposal_id" >&2
+  echo "git-gate: approve with './cli.py supervise' to continue this push" >&2
+  waited=0
+  while [ "$waited" -lt "$timeout" ]; do
+    status=$(PYTHONPATH="/app${PYTHONPATH:+:$PYTHONPATH}" python3 - "$proposal_id" <<'PY'
+import os
+import sys
+
+# Non-blocking poll over the control plane. A decided proposal is archived
+# server-side on read, so no separate archive step is needed here.
+try:
+    from bot_bottle.gateway.policy_resolver import PolicyResolver, PolicyResolveError
+except ImportError:
+    from policy_resolver import PolicyResolver, PolicyResolveError
+
+source_ip = os.environ.get("SUPERVISE_SOURCE_IP", "")
+token = os.environ.get("SUPERVISE_IDENTITY_TOKEN", "")
+orch_url = os.environ.get("BOT_BOTTLE_ORCHESTRATOR_URL", "")
+try:
+    result = PolicyResolver(orch_url).poll_supervise(source_ip, token, sys.argv[1])
+except PolicyResolveError:
+    sys.exit(2)
+if result is None:
+    sys.exit(2)
+status = result.get("status", "")
+if status in ("pending", "unknown"):
+    sys.exit(2)
+print(status)
+PY
+    )
+    rc=$?
+    if [ "$rc" -eq 2 ]; then
+      status=""
+    elif [ "$rc" -ne 0 ]; then
+      status="invalid"
+    fi
+    if [ -n "$status" ]; then
+      case "$status" in
+        approved|modified)
+          echo "git-gate: supervisor approved # gitleaks:allow for $ref" >&2
+          return 0
+          ;;
+        rejected)
+          echo "git-gate: supervisor rejected # gitleaks:allow for $ref" >&2
+          return 1
+          ;;
+        *)
+          echo "git-gate: invalid supervisor response for # gitleaks:allow" >&2
+          return 1
+          ;;
+      esac
+    fi
+    sleep 1
+    waited=$((waited + 1))
+  done
+  echo "git-gate: supervisor approval timed out for # gitleaks:allow; refusing push" >&2
+  return 1
+}
+
+# Phase 1: gitleaks scan each ref's incoming commits.
+while IFS=' ' read -r old new ref; do
+  [ -z "$ref" ] && continue
+  [ "$new" = "$zero" ] && continue
+  # Scan only the commits this push introduces — those reachable from
+  # $new but not from any ref the gate already has. Everything already
+  # on the gate arrived via upstream mirror-fetch or a previously
+  # gitleaks-scanned push, so it's already-upstream or already-scanned;
+  # re-scanning it only resurfaces historical fixture findings.
+  #
+  # Applies to both new refs and updates. The old existing-branch range
+  # `$old..$new` walks commits reachable from the new tip but not the
+  # *old branch tip*: on a rebase/force-push onto a freshly-advanced
+  # main that pulls in all of main's new history (incl. the deliberate
+  # sandbox-escape gitleaks fixtures), blocking the push. `--not --all`
+  # excludes anything already on the gate regardless of ancestry, so it
+  # is also correct for non-fast-forward pushes (a rebase can skip
+  # commits off the direct path). Security-equivalent per PRD 0028's
+  # analysis: the bare repo's refs come only from trusted upstream
+  # mirror-fetch or gitleaks-gated pushes.
+  # See PRD 0028 (open question) / issues #106, #346.
+  log_opts="$new --not --all"
+  echo "git-gate: gitleaks scanning $ref ($log_opts)" >&2
+  if ! gitleaks git --log-opts="$log_opts" --no-banner --redact 1>&2; then
+    echo "git-gate: gitleaks rejected push to $ref" >&2
+    exit 1
+  fi
+  if ! supervise_gitleaks_allow "$log_opts" "$ref"; then
+    exit 1
+  fi
+done < "$refs_file"
+
+# Phase 2: forward each ref to the upstream (`origin`, configured
+# in the entrypoint via `git remote add --mirror=fetch`).
+keyfile=$(git config --get git-gate.identityFile)
+hostsfile=$(git config --get git-gate.knownHosts)
+if [ ! -f "$hostsfile" ]; then
+  echo "git-gate: no KnownHostKey configured for this upstream; refusing to push" >&2
+  echo "git-gate: add KnownHostKey to the bottle.git entry and restart the bottle" >&2
+  exit 1
+fi
+ssh_cmd="ssh -i $keyfile -o UserKnownHostsFile=$hostsfile -o StrictHostKeyChecking=yes -o IdentitiesOnly=yes -o BatchMode=yes -o ConnectTimeout=10"
+
+push_option_count=${GIT_PUSH_OPTION_COUNT:-0}
+case "$push_option_count" in
+  ''|*[!0-9]*)
+    echo "git-gate: invalid GIT_PUSH_OPTION_COUNT=$push_option_count" >&2
+    exit 1
+    ;;
+esac
+set --
+i=0
+while [ "$i" -lt "$push_option_count" ]; do
+  opt=$(printenv "GIT_PUSH_OPTION_$i" || :)
+  set -- "$@" --push-option="$opt"
+  i=$((i + 1))
+done
+
+while IFS=' ' read -r old new ref; do
+  [ -z "$ref" ] && continue
+  if [ "$new" = "$zero" ]; then
+    refspec=":$ref"
+  elif [ "$old" != "$zero" ] && ! git merge-base --is-ancestor "$old" "$new" 2>/dev/null; then
+    refspec="+$new:$ref"
+  else
+    refspec="$new:$ref"
+  fi
+  echo "git-gate: forwarding $ref to origin" >&2
+  if ! GIT_SSH_COMMAND="$ssh_cmd" git push "$@" origin "$refspec" 1>&2; then
+    echo "git-gate: upstream push failed for $ref" >&2
+    exit 1
+  fi
+done < "$refs_file"
+
+exit 0
+"""
+
+
+def git_gate_render_access_hook() -> str:
+    """`git daemon --access-hook` script. Runs before each protocol
+    service; for `upload-pack` (fetch / clone / ls-remote / pull) it
+    refreshes the bare repo from upstream first, so the response
+    reflects upstream's current state. For other services (notably
+    `receive-pack`) it returns 0 immediately and lets the existing
+    pre-receive hook gate the operation. POSIX sh.
+
+    The hook receives:
+      $1  service name (`upload-pack`, `receive-pack`, ...)
+      $2  absolute path to the resolved repo
+      $3  client hostname (unused)
+      $4  client tcp address (unused)
+
+    Fail-closed on upstream errors: the agent's fetch fails too,
+    so it never silently sees stale data — matches the PRD's
+    'equivalent to operations against the upstream' contract."""
+    return r"""#!/bin/sh
+# git-gate access-hook (PRD 0008). $1=service $2=repo $3=host $4=peer
+set -u
+service=$1
+repo_dir=$2
+
+# Push path keeps its own gating in pre-receive (gitleaks +
+# forward). Only refresh-from-upstream on fetch operations.
+if [ "$service" != "upload-pack" ]; then
+  exit 0
+fi
+
+keyfile=$(git -C "$repo_dir" config --get git-gate.identityFile 2>/dev/null || true)
+hostsfile=$(git -C "$repo_dir" config --get git-gate.knownHosts 2>/dev/null || true)
+if [ -z "$keyfile" ] || [ ! -f "$hostsfile" ]; then
+  echo "git-gate: missing credentials for $repo_dir; refusing fetch" >&2
+  exit 1
+fi
+ssh_cmd="ssh -i $keyfile -o UserKnownHostsFile=$hostsfile -o StrictHostKeyChecking=yes -o IdentitiesOnly=yes -o BatchMode=yes -o ConnectTimeout=10"
+
+echo "git-gate: refreshing $repo_dir from upstream" >&2
+if ! GIT_SSH_COMMAND="$ssh_cmd" git -C "$repo_dir" fetch origin --prune >&2; then
+  echo "git-gate: upstream fetch failed for $repo_dir; refusing to serve stale data" >&2
+  exit 1
+fi
+
+# Sync the bare repo's HEAD to upstream's HEAD on the first fetch
+# (when it still points at the `git init --bare` default of
+# refs/heads/master and upstream uses something else, the cloned
+# checkout would fail with "remote HEAD refers to nonexistent ref").
+# Costs one extra ls-remote on first fetch only; subsequent fetches
+# skip the branch. If upstream's default branch changes after the
+# gate has cached it, restart the bottle to resync.
+if ! git -C "$repo_dir" rev-parse --verify HEAD >/dev/null 2>&1; then
+  upstream_head=$(GIT_SSH_COMMAND="$ssh_cmd" git -C "$repo_dir" \
+    ls-remote --symref origin HEAD 2>/dev/null \
+    | awk '/^ref:/ {print $2; exit}')
+  if [ -n "$upstream_head" ]; then
+    git -C "$repo_dir" symbolic-ref HEAD "$upstream_head" || true
+  fi
+fi
+exit 0
+"""