refactor: provision egress routes via AgentProvisionPlan
test / unit (pull_request) Failing after 31s
test / integration (pull_request) Failing after 18s

Remove provider-specific branching from egress.py and pipelock.py.
Previously, `egress_routes_for_bottle` and `pipelock_effective_tls_passthrough`
both contained `template == "codex"` checks — the same pattern the rest
of the PR moved out of the backends.

Root cause: `EgressRoute` had no `tls_passthrough` field, so pipelock
couldn't learn from the synthesised Codex routes that they needed
passthrough. Fix:

- Add `EgressRoute.tls_passthrough: bool`. `egress_manifest_routes` lifts
  the existing `pipelock.tls_passthrough` manifest flag here; provider
  routes set it directly.
- Add `AgentProvisionPlan.egress_routes`. `agent_provision_plan` populates
  it for Codex + `forward_host_credentials`, including `tls_passthrough=True`.
- Replace Codex-specific `egress_routes_for_bottle` logic with a generic
  `_merge_provider_route` helper. Backends call `egress_routes_for_bottle(bottle,
  plan.egress_routes)`; no provider type checks inside egress or pipelock.
- Rewrite `pipelock_effective_tls_passthrough` to read `route.tls_passthrough`
  from the merged route set instead of re-implementing the provider check.
- Both backends now call `agent_provision_plan` before `Egress.prepare` and
  `PipelockProxy.prepare`, threading `plan.egress_routes` to both. `has_provider_auth`
  is derived from `egress_manifest_routes` (manifest routes only — provider
  routes carry no auth roles, so the result is identical).

Assisted-by: Claude Code
This commit is contained in:
2026-06-01 23:27:27 +00:00
parent 1fceaae8e6
commit b79b49090f
8 changed files with 350 additions and 214 deletions
+33 -37
View File
@@ -21,11 +21,7 @@ from dataclasses import dataclass
from pathlib import Path
from typing import cast
from .egress import (
CODEX_HOST_CREDENTIAL_HOSTS,
EGRESS_HOSTNAME,
egress_routes_for_bottle,
)
from .egress import EGRESS_HOSTNAME, EgressRoute, egress_routes_for_bottle
from .supervise import SUPERVISE_HOSTNAME
from .manifest import Bottle
@@ -54,14 +50,17 @@ PIPELOCK_HOSTNAME = "pipelock"
# --- Allowlist resolution --------------------------------------------------
def pipelock_effective_allowlist(bottle: Bottle) -> list[str]:
def pipelock_effective_allowlist(
bottle: Bottle,
provider_routes: tuple[EgressRoute, ...] = (),
) -> list[str]:
"""Hostnames pipelock allows. Sorted for stability.
Always mirrors `egress_routes_for_bottle(bottle)` — egress is the
single allowlist surface, and pipelock's allowlist is the downstream
copy for defense-in-depth + DLP body scanning. For bottles without
any `egress.routes[]` declared, this is empty except for supervise
sidecar traffic when `supervise: true`.
Always mirrors `egress_routes_for_bottle(bottle, provider_routes)` —
egress is the single allowlist surface, and pipelock's allowlist is
the downstream copy for defense-in-depth + DLP body scanning. For
bottles without any `egress.routes[]` declared, this is empty except
for supervise sidecar traffic when `supervise: true`.
The supervise sidecar's hostname is auto-added when supervise
is enabled (sibling-sidecar traffic that flows through pipelock
@@ -69,7 +68,7 @@ def pipelock_effective_allowlist(bottle: Bottle) -> list[str]:
`bottle.git` do NOT contribute here — git traffic flows
through git-gate (PRD 0008), not pipelock."""
seen: dict[str, None] = {}
for r in egress_routes_for_bottle(bottle):
for r in egress_routes_for_bottle(bottle, provider_routes):
if r.host:
seen.setdefault(r.host, None)
if bottle.supervise:
@@ -102,32 +101,23 @@ def pipelock_seed_phrase_detection_enabled(bottle: Bottle) -> bool:
return False
def pipelock_effective_tls_passthrough(bottle: Bottle) -> list[str]:
def pipelock_effective_tls_passthrough(
bottle: Bottle,
provider_routes: tuple[EgressRoute, ...] = (),
) -> list[str]:
"""Hostnames pipelock should pass through (no TLS MITM).
A route opts in with `pipelock.tls_passthrough: true`. This is
useful for provider API routes where egress injects the
Authorization header after the agent boundary; pipelock still
enforces the host allowlist but does not decrypt and scan that
provider request.
A manifest route opts in with `pipelock.tls_passthrough: true`
(lifted into `EgressRoute.tls_passthrough` in `egress_manifest_routes`).
Provider routes that set `tls_passthrough=True` (e.g. Codex credential
routes where egress injects the host bearer after the agent boundary)
are also included. Both arrive via `egress_routes_for_bottle` — no
provider-specific branching needed here.
"""
seen: dict[str, None] = {host: None for host in DEFAULT_TLS_PASSTHROUGH}
for route in bottle.egress.routes:
if route.Pipelock.TlsPassthrough:
seen.setdefault(route.Host, None)
# forward_host_credentials makes egress inject the host ChatGPT bearer
# on the Codex API hosts AFTER the agent boundary. Pipelock sits
# downstream of egress and DLP-scans request headers; left to MITM
# these routes it flags the injected JWT as a leaked secret
# ("request header contains secret") and blocks. Pass them through so
# pipelock still enforces the host allowlist on CONNECT but does not
# decrypt + rescan egress-owned auth. The auto-added routes live in
# egress_routes_for_bottle, not bottle.egress.routes, so add the
# hosts explicitly here.
provider = bottle.agent_provider
if provider.forward_host_credentials and provider.template == "codex":
for host in CODEX_HOST_CREDENTIAL_HOSTS:
seen.setdefault(host, None)
for route in egress_routes_for_bottle(bottle, provider_routes):
if route.tls_passthrough:
seen.setdefault(route.host, None)
return sorted(seen.keys())
@@ -159,6 +149,7 @@ def pipelock_build_config(
ca_cert_path: str = "",
ca_key_path: str = "",
ssrf_ip_allowlist: tuple[str, ...] = (),
provider_routes: tuple[EgressRoute, ...] = (),
) -> dict[str, object]:
"""Build the structured pipelock config dict the sidecar will load.
@@ -188,7 +179,7 @@ def pipelock_build_config(
"version": 1,
"mode": "strict",
"enforce": True,
"api_allowlist": pipelock_effective_allowlist(bottle),
"api_allowlist": pipelock_effective_allowlist(bottle, provider_routes),
"forward_proxy": {"enabled": True},
}
if not pipelock_seed_phrase_detection_enabled(bottle):
@@ -222,7 +213,7 @@ def pipelock_build_config(
"enabled": True,
"ca_cert": ca_cert_path,
"ca_key": ca_key_path,
"passthrough_domains": pipelock_effective_tls_passthrough(bottle),
"passthrough_domains": pipelock_effective_tls_passthrough(bottle, provider_routes),
}
effective_ssrf_ip_allowlist = pipelock_effective_ssrf_ip_allowlist(
bottle, ssrf_ip_allowlist,
@@ -336,7 +327,11 @@ class PipelockProxy:
(`PIPELOCK_CA_CERT_IN_CONTAINER` / `PIPELOCK_CA_KEY_IN_CONTAINER`)."""
def prepare(
self, bottle: Bottle, slug: str, stage_dir: Path
self,
bottle: Bottle,
slug: str,
stage_dir: Path,
provider_routes: tuple[EgressRoute, ...] = (),
) -> PipelockProxyPlan:
"""Write the pipelock yaml config (mode 600) under `stage_dir`
and return the plan for launch. Pure host-side, no docker
@@ -359,6 +354,7 @@ class PipelockProxy:
bottle,
ca_cert_path=PIPELOCK_CA_CERT_IN_CONTAINER,
ca_key_path=PIPELOCK_CA_KEY_IN_CONTAINER,
provider_routes=provider_routes,
)
yaml_path.write_text(pipelock_render_yaml(cfg))
yaml_path.chmod(0o600)