mirror of
https://github.com/anthropics/claude-code.git
synced 2026-07-04 16:03:28 +00:00
f605f0b68d
- Update Vertex AI prose references to Agent Platform across the example (READMEs, script/terraform comments, config template). Functional identifiers are unchanged: the 'provider: vertex' config key, roles/aiplatform.user, aiplatform.googleapis.com, and the terraform resource label (renaming it would recreate the IAM binding in existing states). First mentions keep '(formerly Vertex AI)' for searchability. - Drop the README's self-referential public-mirror link.
157 lines
9.2 KiB
Plaintext
157 lines
9.2 KiB
Plaintext
# gateway.yaml.example — Claude Gateway config template, GCP-shaped (walkthrough §6).
|
|
#
|
|
# Google Workspace IdP + Agent Platform (formerly Vertex AI) upstream, following
|
|
# the walkthrough at https://code.claude.com/docs/en/claude-apps-gateway-on-gcp.
|
|
# The active sections
|
|
# below are a strict subset of the full configuration reference at
|
|
# https://code.claude.com/docs/en/claude-apps-gateway; optional keys are included
|
|
# commented-out.
|
|
#
|
|
# USAGE — this is the shippable TEMPLATE. Copy it to gateway.yaml and fill it in:
|
|
# cp gateway.yaml.example gateway.yaml
|
|
# setup.sh and terraform/ read gateway.yaml (your filled-in copy, which is
|
|
# gitignored). It is published as the Secret Manager secret `gateway-config`
|
|
# (§6) and mounted at /etc/claude/gateway.yaml — the container ENTRYPOINT runs
|
|
# `claude gateway --config /etc/claude/gateway.yaml`.
|
|
#
|
|
# Secret expansion: ${ENV_VAR} reads an env var; ${file:/path} reads a mounted file.
|
|
# On Cloud Run, setup.sh injects the JWT / OIDC / Postgres secrets as ENV VARS
|
|
# (Cloud Run can't mount multiple secrets into a single directory), and mounts
|
|
# only gateway.yaml itself as a file at /etc/claude. On GKE you may use file mounts.
|
|
#
|
|
# BEFORE DEPLOY — replace every REPLACE_ME placeholder below (setup.sh refuses to
|
|
# publish the config secret while any remain), and create the referenced secrets:
|
|
# gateway-jwt-secret (setup.sh generates this)
|
|
# gateway-oidc-client-secret (from the Google Cloud Console OAuth client)
|
|
# gateway-postgres-url (setup.sh generates this)
|
|
|
|
# ── Listener ─────────────────────────────────────────────────────────────────
|
|
listen:
|
|
host: 0.0.0.0
|
|
port: 8080 # Cloud Run sets PORT=8080; leave as-is
|
|
# Required. Fixes the IdP redirect_uri, the OIDC discovery doc, and the
|
|
# gateway-token issuer so none are derived from the client-controlled Host
|
|
# header (X-Forwarded-Host/-Proto are likewise never trusted). On Cloud Run
|
|
# the run.app URL is only assigned on the first deploy, so this starts as a
|
|
# placeholder for the provisioning-only first pass (login does NOT work until
|
|
# the real URL is set). After the first deploy, setup.sh prints the run.app
|
|
# URL: set it here (or your LB hostname) and re-run; setup.sh republishes the
|
|
# config and redeploys. Register the same host's /oauth/callback on the
|
|
# Google OAuth client.
|
|
public_url: https://set-after-first-deploy.invalid
|
|
# Register this exact redirect URI on the Google OAuth client:
|
|
# https://<public_url host>/oauth/callback
|
|
#
|
|
# On Cloud Run (or behind any L7 LB) every request arrives via Google's front
|
|
# end, so the gateway sees one peer IP for all developers — set trusted_proxies
|
|
# so X-Forwarded-For from those proxies is trusted and per-IP rate limiting /
|
|
# audit IPs record the real client. 169.254.0.0/16 is Cloud Run's fixed
|
|
# link-local serving range; the proxy-only subnet is the one your internal ALB
|
|
# uses in this VPC.
|
|
# trusted_proxies:
|
|
# - 169.254.0.0/16 # Cloud Run serving proxy (link-local peer)
|
|
# - <proxy-only-subnet-cidr> # add if fronted by your internal ALB (its proxy-only subnet)
|
|
#
|
|
# Alternative — terminate TLS in the gateway itself instead of at a proxy:
|
|
# tls:
|
|
# cert: /certs/gateway.crt
|
|
# key: /certs/gateway.key
|
|
|
|
# ── Identity provider — Google Workspace ─────────────────────────────────────
|
|
oidc:
|
|
issuer: https://accounts.google.com
|
|
client_id: REPLACE_ME # Google OAuth client ID (not secret; from Cloud Console)
|
|
client_secret: ${OIDC_CLIENT_SECRET}
|
|
allowed_email_domains: [REPLACE_ME] # e.g. [example.com] — reject id_tokens outside your org
|
|
# Google ignores the default offline_access scope; these two are what actually
|
|
# yield refresh tokens (silent renewal + the deprovision leash) from Google.
|
|
scopes: [openid, profile, email]
|
|
extra_auth_params: { access_type: offline, prompt: consent }
|
|
# NOTE: Google id_tokens carry NO groups claim. For group-based RBAC with
|
|
# Google as IdP, set `google_groups` (below) and the gateway fetches each
|
|
# user's Workspace groups at login via the Admin SDK Directory API.
|
|
# Otherwise, use email_domain matching (see managed.policies below).
|
|
# google_groups:
|
|
# service_account_json_path: /secrets/google-sa.json # SA with domain-wide delegation on admin.directory.group.readonly
|
|
# admin_email: admin@example.com # a Workspace admin the SA impersonates
|
|
# groups_claim: groups # Okta=groups, Entra app roles=roles — NOT Google
|
|
# ca_cert_pem: ${file:/secrets/idp-ca.pem} # only for an IdP behind a private CA
|
|
|
|
# ── Sessions ─────────────────────────────────────────────────────────────────
|
|
session:
|
|
jwt_secret: ${GATEWAY_JWT_SECRET} # >= 32 bytes; openssl rand -base64 32
|
|
# Google issues refresh tokens (above), so sessions renew silently and this
|
|
# mainly bounds deprovision latency. 8 is a sane default; lower toward 1 for
|
|
# tighter revocation. Array form rotates keys: [new, old] (index 0 signs, all verify).
|
|
ttl_hours: 8
|
|
|
|
# ── Store (REQUIRED — the gateway refuses to boot without it) ─────────────────
|
|
store:
|
|
postgres_url: ${GATEWAY_POSTGRES_URL} # private-IP Cloud SQL; built with ?sslmode=require by setup.sh
|
|
|
|
# ── Upstreams — Agent Platform ───────────────────────────────────────────────
|
|
upstreams:
|
|
- provider: vertex
|
|
region: us-east5 # a region where the Claude models you need are published in Model Garden
|
|
project_id: REPLACE_ME # your GCP project ID for Agent Platform access
|
|
auth: {} # ADC via Cloud Run SA / GKE Workload Identity (preferred — no static keys)
|
|
# base_url: https://us-east5-aiplatform.p.googleapis.com # Private Service Connect endpoint
|
|
# Add more upstreams for failover (tried top→bottom on 5xx/timeout/501): a
|
|
# second region, or an anthropic/bedrock fallback. See
|
|
# https://code.claude.com/docs/en/claude-apps-gateway.
|
|
|
|
# ── Telemetry fan-out (OPTIONAL) ─────────────────────────────────────────────
|
|
# The CLI sends OTLP/HTTP to the gateway; the gateway fans out, stamping
|
|
# user.id/user.email/user.groups server-side. On GCP, point at an OpenTelemetry
|
|
# Collector with the googlecloud exporter (-> Cloud Trace / Managed Prometheus).
|
|
# Takes effect after the second pass (once public_url is the real URL, not the
|
|
# placeholder): when forward_to and public_url are both configured the gateway pushes
|
|
# CLAUDE_CODE_ENABLE_TELEMETRY and the OTEL exporter selectors to every client
|
|
# automatically — no per-developer config needed.
|
|
# telemetry:
|
|
# forward_to:
|
|
# - url: https://otel-collector.internal.example.com:4318
|
|
# headers:
|
|
# Authorization: ${file:/secrets/otlp-token}
|
|
# metrics: true # safe aggregate counters (default)
|
|
# logs: false # carries bash commands / tool inputs — opt in deliberately
|
|
# traces: false
|
|
|
|
# ── RBAC + managed settings (OPTIONAL; first-match-wins, top -> bottom) ───────
|
|
# With Google as IdP, match on email_domain, or on group email addresses
|
|
# (e.g. eng@example.com) once oidc.google_groups is configured above.
|
|
# managed:
|
|
# policies:
|
|
# - match: { email_domain: example.com }
|
|
# cli:
|
|
# availableModels: [claude-opus-4-8, claude-sonnet-4-6, claude-haiku-4-5]
|
|
# permissions: { deny: ["Read(./.env)", "Read(./secrets/**)"] }
|
|
# - match: {} # catch-all floor — keep LAST
|
|
# cli:
|
|
# availableModels: [claude-sonnet-4-6, claude-haiku-4-5]
|
|
|
|
# ── Admin API (OPTIONAL — enables db-mode runtime config + spend caps) ───────
|
|
# admin_groups needs a groups claim — with Google as IdP, set
|
|
# oidc.google_groups (above) so Workspace group email addresses populate the
|
|
# claim, or use the bootstrap keys below instead. Named keys for
|
|
# attribution in the audit log; 32-char minimum on key values. On Cloud Run add
|
|
# these as env vars to --set-secrets (or terraform env value_source blocks),
|
|
# same as the JWT/OIDC/Postgres secrets above; on GKE you may use ${file:...}.
|
|
# admin:
|
|
# write_keys:
|
|
# - id: terraform
|
|
# key: ${GATEWAY_ADMIN_WRITE_KEY}
|
|
# read_keys:
|
|
# - id: reporting
|
|
# key: ${GATEWAY_ADMIN_READ_KEY}
|
|
# # admin_groups: [platform-finops@example.com] # group emails via oidc.google_groups, or any groups-capable IdP
|
|
|
|
# ── Model catalog (OPTIONAL) ─────────────────────────────────────────────────
|
|
# Default true: every built-in Claude model is exposed and auto-translated per
|
|
# upstream. Set false + a models: list to pin IDs (e.g. provisioned throughput).
|
|
# auto_include_builtin_models: true
|
|
# models:
|
|
# - id: claude-opus-4-8
|
|
# label: Claude Opus 4.8
|
|
# upstream_model: { vertex: claude-opus-4-8 }
|