fix(gateway)!: replace token cookies with revocable sessions and harden abuse controls (#40)

- Replace user:token cookies with opaque server-side sessions, revocable on logout, delete, recreate and expiry; bind every credential to the path user and add cross-user regression tests.
- Rate-limit /users and /login, add optional signup invite codes and form same-origin checks, and unify login failures to 401.
- Require explicit ALLOW_INSECURE_COOKIES for plain HTTP, use __Host-dsh_gw_session when secure, and fix secure cookie deletion.
- Strip client-supplied forwarding/SSO headers, add an optional upstream allowlist, per-user in-flight and WebSocket message caps, credential-free handshake errors, and sweep-time state pruning.
- Digest-pin base images, hash-pin gateway dependencies, verify DSH_COMMIT in the build, and run the gateway image as non-root with a pinned Python base.
- Update manifests, production checklist, architecture/security docs and add an SSO preflight script.

BREAKING CHANGE: existing dsh_gw_session=<user>:<token> cookies are invalid; users must sign in again. Unknown users on POST /login now return 401 instead of 404, and the gateway refuses COOKIE_SECURE=false unless ALLOW_INSECURE_COOKIES=1.

Co-authored-by: SREDevOpsAgents <agents@sredevops.org>

.env.sample

@@ -23,6 +23,9 @@ CEREBRAS_API_KEY=
 AI_GATEWAY_API_KEY=
 HF_TOKEN=
 DSH_VERSION=dsh-v0.2.1-rc.5
+# Full upstream commit SHA that DSH_VERSION resolves to; the main image build
+# fails if the clone's HEAD differs (guards against a moved tag).
+DSH_COMMIT=b830ec950faba0a46dda564be3e2d854afed94f1
 RELEASE_REVISION=
 PNPM_VERSION=11.28.5
 # Container port, and the host port published by "make run".

.github/workflows/build-main.yaml

@@ -29,6 +29,7 @@ jobs:
     outputs:
       identity: ${{ steps.meta.outputs.identity }}
       dsh_version: ${{ steps.meta.outputs.dsh_version }}
+      dsh_commit: ${{ steps.meta.outputs.dsh_commit }}
       pnpm_version: ${{ steps.meta.outputs.pnpm_version }}
       release_revision: ${{ steps.meta.outputs.release_revision }}
       ghcr_image: ${{ steps.meta.outputs.ghcr_image }}
@@ -53,6 +54,7 @@ jobs:
           {
             echo "identity=$identity"
             echo "dsh_version=$DSH_VERSION"
+            echo "dsh_commit=$DSH_COMMIT"
             echo "pnpm_version=$PNPM_VERSION"
             echo "release_revision=$RELEASE_REVISION"
             echo "ghcr_image=$GHCR_IMAGE"
@@ -75,6 +77,7 @@ jobs:
       dockerfile: Dockerfile
       build-args: |
         DSH_VERSION=${{ needs.meta.outputs.dsh_version }}
+        DSH_COMMIT=${{ needs.meta.outputs.dsh_commit }}
         RELEASE_REVISION=${{ needs.meta.outputs.release_revision }}
         PNPM_VERSION=${{ needs.meta.outputs.pnpm_version }}
         VCS_REF=${{ github.sha }}

.github/workflows/ci-image.yaml

@@ -48,6 +48,7 @@ jobs:
           {
             echo "identity=$identity"
             echo "dsh_version=$DSH_VERSION"
+            echo "dsh_commit=$DSH_COMMIT"
             echo "pnpm_version=$PNPM_VERSION"
             echo "release_revision=${RELEASE_REVISION:-}"
           } >> "$GITHUB_OUTPUT"
@@ -66,6 +67,7 @@ jobs:
           tags: dsh-web:ci
           build-args: |
             DSH_VERSION=${{ steps.meta.outputs.dsh_version }}
+            DSH_COMMIT=${{ steps.meta.outputs.dsh_commit }}
             RELEASE_REVISION=${{ steps.meta.outputs.release_revision }}
             PNPM_VERSION=${{ steps.meta.outputs.pnpm_version }}
             VCS_REF=${{ github.sha }}

.github/workflows/ci-python.yaml

@@ -43,7 +43,9 @@ jobs:
         run: |
           set -euo pipefail
           python -m pip install --upgrade pip
-          pip install -r requirements.txt -r requirements-dev.txt
+          # Both files are fully hash-pinned (uv pip compile --generate-hashes);
+          # pip refuses to install anything not listed with a matching hash.
+          pip install --require-hashes -r requirements.txt -r requirements-dev.txt
       - name: Lint
         run: |
           set -euo pipefail

.github/workflows/release.yaml

@@ -34,6 +34,7 @@ jobs:
     outputs:
       identity: ${{ steps.meta.outputs.identity }}
       dsh_version: ${{ steps.meta.outputs.dsh_version }}
+      dsh_commit: ${{ steps.meta.outputs.dsh_commit }}
       pnpm_version: ${{ steps.meta.outputs.pnpm_version }}
       release_revision: ${{ steps.meta.outputs.release_revision }}
       ghcr_image: ${{ steps.meta.outputs.ghcr_image }}
@@ -91,13 +92,28 @@ jobs:
             echo "tag '$tag' does not exist in this repository" >&2
             exit 1
           fi
-          if ! git ls-remote --tags --exit-code "$DSH_REPO" "$DSH_VERSION" >/dev/null; then
+          if ! upstream="$(git ls-remote --tags --exit-code "$DSH_REPO" \
+                "refs/tags/$DSH_VERSION^{}" "refs/tags/$DSH_VERSION")"; then
             echo "upstream ref '$DSH_VERSION' not found in $DSH_REPO" >&2
             exit 1
           fi
+          # Never release a ref that no longer resolves to the pinned commit: an
+          # annotated tag has a peeled ^{} line, a lightweight tag only the ref.
+          resolved="$(printf '%s\n' "$upstream" \
+            | awk -v t="refs/tags/$DSH_VERSION^{}" '$2 == t {print $1}' | head -n1)"
+          if [ -z "$resolved" ]; then
+            resolved="$(printf '%s\n' "$upstream" \
+              | awk -v t="refs/tags/$DSH_VERSION" '$2 == t {print $1}' | head -n1)"
+          fi
+          if [ "$resolved" != "$DSH_COMMIT" ]; then
+            echo "upstream $DSH_REPO@$DSH_VERSION resolved to '$resolved'," \
+              "versions.env pins DSH_COMMIT=$DSH_COMMIT" >&2
+            exit 1
+          fi
           {
             echo "identity=$identity"
             echo "dsh_version=$DSH_VERSION"
+            echo "dsh_commit=$DSH_COMMIT"
             echo "pnpm_version=$PNPM_VERSION"
             echo "release_revision=$RELEASE_REVISION"
             echo "ghcr_image=$GHCR_IMAGE"
@@ -139,7 +155,7 @@ jobs:
         run: |
           set -euo pipefail
           python -m pip install --upgrade pip
-          pip install -r requirements.txt -r requirements-dev.txt
+          pip install --require-hashes -r requirements.txt -r requirements-dev.txt
       - name: Lint
         if: needs.meta.outputs.run_tests == 'true'
         run: |
@@ -166,6 +182,7 @@ jobs:
       dockerfile: Dockerfile
       build-args: |
         DSH_VERSION=${{ needs.meta.outputs.dsh_version }}
+        DSH_COMMIT=${{ needs.meta.outputs.dsh_commit }}
         RELEASE_REVISION=${{ needs.meta.outputs.release_revision }}
         PNPM_VERSION=${{ needs.meta.outputs.pnpm_version }}
         VCS_REF=${{ github.sha }}

AGENTS.md

@@ -117,17 +117,33 @@ needs kind plus the agent-sandbox CRDs (see the example README).
 
 - AUTH_PROXY_HEADER is opt-in. Only enable it when the gateway Service is
   reachable exclusively through the authenticating proxy; otherwise any client
-  can spoof X-Forwarded-User.
+  can spoof X-Forwarded-User. The SSO variant's NetworkPolicy is required for
+  production, and `examples/dsh-agents-as-a-service/scripts/preflight-sso.sh`
+  verifies the setup (Secrets, gateway env, TLS reference, placeholders, second
+  paths).
 - The example gateway reads the DSH launch token from pod logs. Treat pod logs
   as sensitive and keep its RBAC namespace-scoped.
+- Browser sessions are opaque server-side ids held in gateway memory: they are
+  revocable (logout/delete/recreate/expiry) but a gateway restart logs everyone
+  out and horizontal scaling needs a shared store. Session cookies are never
+  accepted as bearer tokens.
+- AUTH_RATE_LIMIT, SIGNUP_INVITE_CODE, MAX_IN_FLIGHT_PER_USER and
+  WS_MAX_MESSAGE_BYTES are in-process abuse guards, not ingress rate limits,
+  quotas or an audit log. Add those for an internet-facing deployment.
 - The example shares provider keys (dsh-provider-keys plus the optional
   dsh-provider-keys-extra) across sandboxes; do not describe it as
   tenant-isolated.
-- gVisor, nodeSelector, the NetworkPolicies, extra provider keys and failed-Pod
+- gVisor, nodeSelector, the shipped sandbox/exposure NetworkPolicies and the
-  recovery are opt-in and are not active in the base manifests; do not describe
+  documented gateway egress policy, extra provider keys and failed-Pod recovery
-  the base example as hardened.
+  are opt-in and are not active in the base manifests; do not describe the base
-- TLS terminates outside the gateway; set COOKIE_SECURE=true for HTTPS and keep
+  example as hardened.
-  the base manifest safe for local HTTP.
+  The sandbox and gateway-egress policies are required production steps; an
+  exposure without its NetworkPolicy is demo-only. See the example's
+  production checklist.
+- TLS terminates outside the gateway. Set COOKIE_SECURE=true for HTTPS and drop
+  ALLOW_INSECURE_COOKIES; the gateway refuses COOKIE_SECURE=false unless
+  ALLOW_INSECURE_COOKIES=1, which is only for the plain-HTTP local demo. Never
+  expose that combination.
 
 ## Ask before
 

Dockerfile

@@ -6,13 +6,14 @@
 # Build args (all pinned in versions.env, verified by scripts/check-versions.sh):
 #   DSH_REPO              upstream git remote to package
 #   DSH_VERSION           upstream git ref to build (tag or branch)
+#   DSH_COMMIT            full commit SHA DSH_VERSION must resolve to
 #   RELEASE_REVISION      optional repository revision label (r2, r3, ...)
 #   PNPM_VERSION          pnpm used to build DSH
 #   VCS_REF               this repository's commit, recorded in OCI labels
-#   NODE_BUILD_IMAGE      node image used to build DSH
+#   NODE_BUILD_IMAGE      node image used to build DSH (pinned by digest)
-#   NODE_RUNTIME_IMAGE    node image used at runtime
+#   NODE_RUNTIME_IMAGE    node image used at runtime (pinned by digest)
-ARG NODE_BUILD_IMAGE=docker.io/node:24-trixie
+ARG NODE_BUILD_IMAGE=docker.io/node:24-trixie@sha256:8c761eca2bf7eec965f946cf47b8090143cb41f45f2f8699af0cc0298d2d2d19
-ARG NODE_RUNTIME_IMAGE=docker.io/node:24-trixie-slim
+ARG NODE_RUNTIME_IMAGE=docker.io/node:24-trixie-slim@sha256:54f84b4cf8432b21aaffd5d3ce8d41e12cea0d10d33c09d2f3c9879d49d6b446
 
 # ---------------------------------------------------------------------------
 # Build stage: clone DSH at the pinned ref, build, and package the CLI.
@@ -21,6 +22,7 @@ FROM $NODE_BUILD_IMAGE AS build
 
 ARG DSH_REPO=https://github.com/deepseek-ai/deepseek-harness.git
 ARG DSH_VERSION=dsh-v0.2.1-rc.5
+ARG DSH_COMMIT=b830ec950faba0a46dda564be3e2d854afed94f1
 ARG PNPM_VERSION=11.28.5
 
 ENV CI=true \
@@ -31,7 +33,15 @@ RUN corepack enable \
 
 WORKDIR /src
 
-RUN git clone --depth 1 --branch "$DSH_VERSION" "$DSH_REPO" .
+# Clone the pinned ref and fail closed unless it resolves to DSH_COMMIT. A moved
+# tag would otherwise silently change what the image packages.
+RUN git clone --depth 1 --branch "$DSH_VERSION" "$DSH_REPO" . \
+ && actual="$(git -C /src rev-parse HEAD)" \
+ && if [ "$actual" != "$DSH_COMMIT" ]; then \
+      echo "error: $DSH_REPO $DSH_VERSION resolved to $actual, expected DSH_COMMIT $DSH_COMMIT" >&2; \
+      echo "error: update DSH_VERSION/DSH_COMMIT in versions.env with scripts/set-version.sh" >&2; \
+      exit 1; \
+    fi
 
 RUN pnpm install --frozen-lockfile
 

Makefile

@@ -27,6 +27,7 @@ help: ## Show available targets
 image: ## Build the main DSH Web image (no push)
 	docker build \
 		--build-arg DSH_VERSION=$(DSH_VERSION) \
+		--build-arg DSH_COMMIT=$(DSH_COMMIT) \
 		--build-arg RELEASE_REVISION=$(RELEASE_REVISION) \
 		--build-arg PNPM_VERSION=$(PNPM_VERSION) \
 		--build-arg VCS_REF=$(VCS_REF) \

SECURITY.md

@@ -22,22 +22,40 @@ disclosure once a fix is available.
   tenant. Keep the gateway's RBAC namespace-scoped and treat pod logs as
   sensitive. Replacing log scraping with an upstream token API is tracked in
   the [example architecture document](examples/dsh-agents-as-a-service/docs/architecture.md#upstream-feature-request-remove-log-scraping).
+- **Browser sessions are server-side.** The gateway session cookie holds an
+  opaque session id, not a user name or token; it is not accepted as a bearer
+  token. Sessions are revoked on logout, user delete, `/recreate` and expiry,
+  but they live in gateway memory, so a gateway restart logs every browser out
+  and scaling beyond one replica requires a shared store. Do not treat the
+  cookie as durable or cross-replica state.
 - **SSO header trust boundary.** AUTH_PROXY_HEADER makes the gateway trust an
   identity header (for example X-Forwarded-User). Enable it only when the
-  gateway Service is reachable exclusively through the authenticating proxy;
+  gateway Service is reachable exclusively through the authenticating proxy
-  otherwise any client can spoof the header. The SSO exposure variant ships a
+  and its NetworkPolicy; otherwise any client can spoof the header. The SSO
-  NetworkPolicy that restricts gateway access to oauth2-proxy pods; a custom
+  exposure variant's policy is required, not optional: an exposure without it
-  exposure needs an equivalent.
+  is demo-only. Run `examples/dsh-agents-as-a-service/scripts/preflight-sso.sh`
+  after applying the variant; it checks the Secrets, gateway env, TLS
+  reference, leftover placeholders and accidental second paths.
+- **Insecure-cookie guard.** TLS terminates outside the gateway. Set
+  COOKIE_SECURE=true for HTTPS and remove ALLOW_INSECURE_COOKIES; the gateway
+  refuses to start with COOKIE_SECURE=false unless ALLOW_INSECURE_COOKIES=1 is
+  explicitly set, which exists only for the plain-HTTP local demo. Never expose
+  that combination outside localhost.
+- **Abuse controls are in-process.** AUTH_RATE_LIMIT/AUTH_RATE_WINDOW,
+  SIGNUP_INVITE_CODE, MAX_IN_FLIGHT_PER_USER and WS_MAX_MESSAGE_BYTES bound
+  casual abuse and resource exhaustion on the single gateway replica. They
+  reset on restart and are not an ingress rate limiter, WAF, quota system or
+  audit log; add those for an internet-facing deployment.
 - **Shared provider keys.** The example injects DEEPSEEK_API_KEY and any keys in
   the optional dsh-provider-keys-extra Secret into every tenant sandbox (a
   warm-pool constraint). Treat tenants as mutually trusting until per-tenant
   credentials or an egress proxy exist.
-- **Optional isolation is opt-in.** gVisor, nodeSelector, the sandbox/exposure
+- **The base example is demo-only, not hardened.** gVisor, nodeSelector, the
-  NetworkPolicies and extra provider keys are opt-in. Without a
+  sandbox/exposure NetworkPolicies, the gateway egress policy and extra provider
-  NetworkPolicy-capable CNI or a gVisor runtime, the base example is not
+  keys are opt-in. Without gVisor and the network policies there is no
-  tenant-isolated; see examples/dsh-agents-as-a-service/docs/optional-hardening.md.
+  tenant-to-tenant isolation; the sandboxes share the host kernel and can reach
-- **TLS is external.** Terminate TLS at an Ingress or Gateway and set
+  cluster-internal endpoints. Production requirements are enumerated in the
-  COOKIE_SECURE=true. Plain HTTP outside localhost exposes session cookies.
+  [production checklist](examples/dsh-agents-as-a-service/docs/optional-hardening.md#6-production-checklist).
 - **No secrets in the repository.** The repository only ships empty Secret
   manifests and *.yaml.example files.
 

docs/main-image.md

@@ -11,12 +11,16 @@ The image is image-first: it is the product, and the examples under
 
 ## What the build does
 
-The Dockerfile is a two-stage build:
+The Dockerfile is a two-stage build. Both stages use the `node` images pinned by
+digest in [versions.env](../versions.env): a mutable tag alone is not trusted, and
+`./scripts/check-versions.sh` rejects an image reference without a `@sha256:` digest.
 
-1. **Build stage** (`node:24-trixie`) clones DSH at the pinned git ref, installs
+1. **Build stage** (`NODE_BUILD_IMAGE`) clones DSH at the pinned git ref, verifies
+   that the clone's `HEAD` is exactly `DSH_COMMIT` (the build fails otherwise, so a
+   moved upstream tag cannot silently change what the image packages), installs
    dependencies with pnpm, runs the production build, packages the `@deepseek-ai/dsh`
    CLI with `pnpm pack`, and installs its production dependencies with npm.
-2. **Runtime stage** (`node:24-trixie-slim`) copies `/opt/dsh` to `/app`, adds the
+2. **Runtime stage** (`NODE_RUNTIME_IMAGE`) copies `/opt/dsh` to `/app`, adds the
    CLI tools DSH agents commonly use (`git`, `ripgrep`, `jq`, `yq`, `curl`, `wget`,
    `gh`, `tini`, `uv`), installs `bubblewrap` as DSH's preferred command-sandbox
    runner, and starts `dsh web` through a small entrypoint.
@@ -36,6 +40,7 @@ To reproduce the equivalent by hand:
 ```bash
 docker build \
   --build-arg DSH_VERSION=dsh-v0.2.1-rc.5 \
+  --build-arg DSH_COMMIT=b830ec950faba0a46dda564be3e2d854afed94f1 \
   --build-arg RELEASE_REVISION= \
   --build-arg PNPM_VERSION=11.28.5 \
   --build-arg VCS_REF="$(git rev-parse --short HEAD)" \
@@ -48,11 +53,17 @@ docker build \
 | --- | --- | --- |
 | `DSH_REPO` | `https://github.com/deepseek-ai/deepseek-harness.git` | Upstream DSH repository to clone. |
 | `DSH_VERSION` | `DSH_VERSION` in [versions.env](../versions.env) | Upstream DSH git tag/ref to package. The Dockerfile records it as `io.sredevopsorg.dsh.version` and (for local builds) `org.opencontainers.image.version`; published builds set the version label to the full release identity. |
+| `DSH_COMMIT` | `DSH_COMMIT` in [versions.env](../versions.env) | Full commit SHA `DSH_VERSION` must resolve to upstream. The build stage fails unless `git rev-parse HEAD` in the clone equals this value, which pins the source independently of a movable tag. |
 | `RELEASE_REVISION` | `RELEASE_REVISION` in [versions.env](../versions.env) | Repository revision suffix (`rN`), recorded in `io.sredevopsorg.release.revision`. The release identity is `DSH_VERSION` plus `-RELEASE_REVISION` when set. See [versioning](versioning.md). |
 | `PNPM_VERSION` | `PNPM_VERSION` in [versions.env](../versions.env) | pnpm version activated with corepack in both stages. |
 | `VCS_REF` | `git rev-parse --short HEAD` (via `make image`) | Source revision recorded for traceability. |
-| `NODE_BUILD_IMAGE` | `docker.io/node:24-trixie` | Build-stage base image. |
+| `NODE_BUILD_IMAGE` | `docker.io/node:24-trixie@sha256:8c761eca2bf7eec965f946cf47b8090143cb41f45f2f8699af0cc0298d2d2d19` | Build-stage base image, pinned to the multi-arch index digest. |
-| `NODE_RUNTIME_IMAGE` | `docker.io/node:24-trixie-slim` | Runtime-stage base image. |
+| `NODE_RUNTIME_IMAGE` | `docker.io/node:24-trixie-slim@sha256:54f84b4cf8432b21aaffd5d3ce8d41e12cea0d10d33c09d2f3c9879d49d6b446` | Runtime-stage base image, pinned to the multi-arch index digest. |
+
+Base images are pinned by digest because tags are mutable: `node:24-trixie` can be
+re-pointed at a new build at any time. Bumping the tag and its digest is a
+deliberate, reviewable change in [versions.env](../versions.env); environments that
+mirror the image should also mirror the `node` digest they build from.
 
 Never hard-code a version outside [versions.env](../versions.env):
 `./scripts/check-versions.sh` (and `make check`) fails when a pin drifts.

docs/versioning.md

@@ -61,14 +61,27 @@ Values from [versions.env](../versions.env) at the current identity:
 | --- | --- | --- |
 | Upstream DSH source | `DSH_REPO` | [versions.env](../versions.env) |
 | DSH ref | `dsh-v0.2.1-rc.5` | `DSH_VERSION` |
+| DSH commit | `b830ec950faba0a46dda564be3e2d854afed94f1` | `DSH_COMMIT`; the main image build fails unless the clone's `HEAD` matches |
 | Repository revision | `(empty)` | `RELEASE_REVISION` |
 | pnpm | `11.28.5` | `PNPM_VERSION` |
+| Node build image | `docker.io/node:24-trixie@sha256:8c761eca2bf7eec965f946cf47b8090143cb41f45f2f8699af0cc0298d2d2d19` | `NODE_BUILD_IMAGE`, digest-pinned |
+| Node runtime image | `docker.io/node:24-trixie-slim@sha256:54f84b4cf8432b21aaffd5d3ce8d41e12cea0d10d33c09d2f3c9879d49d6b446` | `NODE_RUNTIME_IMAGE`, digest-pinned |
+| Gateway Python image | `docker.io/python:3.12-slim@sha256:aa943ce411423c7582288f18707ff66eddcbaeb510502d747a72aeb34f30d159` | `GATEWAY_PYTHON_IMAGE`, digest-pinned |
 | agent-sandbox (CRDs) | `v1.0.9` | `AGENT_SANDBOX_VERSION`, used by the examples and CI dry-run |
 | Kubernetes Gateway API | `v1.2.1` | `GATEWAY_API_VERSION`, used by the SSO exposure variant |
-| oauth2-proxy | `quay.io/oauth2-proxy/oauth2-proxy:v7.15.5` | `OAUTH2_PROXY_IMAGE` |
+| oauth2-proxy | `quay.io/oauth2-proxy/oauth2-proxy:v7.15.5@sha256:8498b0d0ef0a7b29686414000a08aee467f02d0299c9ed1e006a8f33fc017916` | `OAUTH2_PROXY_IMAGE`, digest-pinned and used by the SSO exposure variant |
 | Main image | `ghcr.io/sredevopsorg/deepseek-kubernetes-sandbox` | `GHCR_IMAGE` |
 | Gateway image | `ghcr.io/sredevopsorg/deepseek-kubernetes-sandbox/dsh-agents-as-a-service/gateway` | `GATEWAY_IMAGE`, nested below `GHCR_IMAGE` |
 
+Every container base image is referenced as `name:tag@sha256:<index digest>`, not
+by tag alone: `check-versions.sh` rejects a pin without a digest, so a re-pushed
+tag cannot change what we build from. The example gateway's Python dependencies
+are fully hash-pinned in
+[requirements.txt](../examples/dsh-agents-as-a-service/gateway/requirements.txt)
+and
+[requirements-dev.txt](../examples/dsh-agents-as-a-service/gateway/requirements-dev.txt)
+and installed with `pip install --require-hashes`.
+
 Example component images are always nested below the main package:
 `<GHCR_IMAGE>/<example>/<component>`. `check-versions.sh` rejects an unrelated
 top-level package.
@@ -86,8 +99,15 @@ file to derive from it. Never edit the Dockerfile, manifests, Makefile or
 workflows with a literal version.
 
 - New upstream DSH ref: change `DSH_VERSION` and clear `RELEASE_REVISION`.
-- Repository-only change at the same DSH ref: keep `DSH_VERSION`, set
+  `set-version` resolves the new ref's commit with `git ls-remote` (peeled `^{}`
-  `RELEASE_REVISION=r(N+1)`.
+  commit first, tag ref as fallback) and rewrites `DSH_COMMIT` in `versions.env`,
+  the Dockerfile ARG default and `.env.sample`; the build then verifies it.
+- Repository-only change at the same DSH ref: keep `DSH_VERSION` and `DSH_COMMIT`,
+  set `RELEASE_REVISION=r(N+1)`.
+- Base images (Node and Python) are bumped by hand: change the tag *and* the
+  `@sha256:` digest in `versions.env` together, then run `make check` and a build.
+  There is deliberately no automated digest refresh, because a silent base-image
+  change is exactly what digest pinning exists to prevent.
 
 ## Release checklist
 
@@ -98,7 +118,8 @@ workflows with a literal version.
    the tag does not already exist, and previews the generated notes.
 5. Create and push the annotated `dsh-*` release tag (or dispatch
    `release.yaml` with an existing tag). The workflow validates that the tag
-   matches [versions.env](../versions.env).
+   matches [versions.env](../versions.env) and that the upstream ref still
+   resolves to `DSH_COMMIT` before building anything.
 6. The workflow builds and pushes multi-arch images for the main image and the
    example components (the identity tag plus `latest`), creates the GitHub
    Release from the git-cliff notes, and opens a `chore(changelog)` PR that
@@ -142,8 +163,17 @@ make changelog   # regenerate CHANGELOG.md locally
 
 ## Digest pinning
 
-Release identities are mutable only in theory; deployments should still pin the
+Supply-chain inputs are pinned to immutable content, not to mutable tags:
-resolved digest for reproducibility and supply-chain safety:
+
+- **Build inputs**: every container base image is referenced by multi-arch index
+  digest in [versions.env](../versions.env), and the example gateway's Python
+  dependencies are hash-pinned (`--require-hashes`).
+- **Upstream source**: the Dockerfile clones `DSH_VERSION` and fails unless the
+  clone's `HEAD` equals `DSH_COMMIT`, so a moved upstream tag cannot change what
+  a rebuild packages.
+
+Release identities are immutable in theory; deployments should still pin the
+_resolved_ digest for reproducibility and supply-chain safety:
 
 ```bash
 docker buildx imagetools inspect ghcr.io/sredevopsorg/deepseek-kubernetes-sandbox:dsh-v0.2.1-rc.5

examples/dsh-agents-as-a-service/README.md

@@ -16,8 +16,9 @@ It ships in three layers:
 1. **The resource layer** (steps 1–7): pure manifests + kubectl, so every
    mechanism is visible.
 2. **The service layer** (step 8): a small included **gateway** (`gateway/`) that
-   makes the platform browser-usable — a signup page/API, `HttpOnly` cookie
+   makes the platform browser-usable — a signup page/API, revocable server-side
-   sessions, a `/u/{user}/**` proxy for HTTP **and WebSocket** that transparently
+   **opaque-cookie sessions**, auth rate limiting and an optional signup invite
+   code, a `/u/{user}/**` proxy for HTTP **and WebSocket** that transparently
    **wakes suspended instances on connect**, and an idle sweeper that suspends
    them again. The gateway performs the DSH launch-token handshake server-side,
    so the browser never sees the token.
@@ -65,12 +66,13 @@ What it demonstrates, feature by feature:
   upstream instead of splitting `/v1/*` (API) from the dashboard.
 - **Shared provider keys**: `DEEPSEEK_API_KEY` plus any keys in the optional
   `dsh-provider-keys-extra` Secret are injected via `envFrom` into every
-  sandbox. There is no per-tenant key, dashboard basic-auth, session-cookie
+  sandbox. There is no per-tenant key, dashboard basic-auth, signed-session
-  secret, or API-server key.
+  secret (sessions are opaque server-side ids), or API-server key.
 - **Launch-token handshake**: DSH gates `/` behind a token it prints only in its
   logs. The gateway reads it, performs the handshake, and keeps the resulting
   auth cookie server-side; the browser authenticates to the gateway with its own
-  cookie. See [How the DSH handshake works](#how-the-dsh-handshake-works).
+  opaque session cookie, never the token. See
+  [How the DSH handshake works](#how-the-dsh-handshake-works).
 - **Host allow-list**: DSH rejects unknown `Host` headers. The gateway forwards
   the browser's `Host`, so the public hostname must be added to
   `DSH_TRUSTED_HOSTS` in the template.
@@ -285,6 +287,15 @@ kubectl -n dsh-demo port-forward svc/dsh-gateway 18080:8080
 
 > The gateway binds `8080`; the local port-forward uses `18080` and never `3080`.
 >
+> **Cookie/TLS guard.** The base manifest serves plain HTTP through port-forward,
+> so it sets `COOKIE_SECURE=false` **and** `ALLOW_INSECURE_COOKIES=1`. The gateway
+> refuses to start when `COOKIE_SECURE=false` unless
+> `ALLOW_INSECURE_COOKIES=1` explicitly acknowledges that the session cookie
+> travels in clear text; that prevents an HTTPS deployment from silently serving
+> an insecure cookie. Before exposing the gateway over TLS, set
+> `COOKIE_SECURE=true` and remove the acknowledgement:
+> `kubectl -n dsh-demo set env deploy/dsh-gateway COOKIE_SECURE=true ALLOW_INSECURE_COOKIES-`.
+>
 > **Image pull policy.** `manifests/50-gateway.yaml` uses
 > `imagePullPolicy: IfNotPresent` with the release identity, so a locally built
 > image must be loaded into the cluster under exactly that name (kind:
@@ -317,25 +328,40 @@ kubectl -n dsh-demo port-forward svc/dsh-gateway 18080:8080
 
 ### Browser flow
 
-Open <http://localhost:18080>. The landing page has a one-field signup form.
+Open <http://localhost:18080>. The landing page has a one-field signup form (plus
-Enter `bob`, and the gateway:
+an invite-code field when `SIGNUP_INVITE_CODE` is configured). Enter `bob`, and
+the gateway:
 
-1. creates the `SandboxClaim` over the warm pool,
+1. enforces the auth rate limit and, if configured, the signup invite code,
-2. waits for it to become `Ready`,
+2. creates the `SandboxClaim` over the warm pool,
-3. sets an `HttpOnly`, `SameSite=Lax` cookie `dsh_gw_session=<user>:<token>` on
+3. waits for it to become `Ready`,
-   the browser,
+4. mints a random, server-side session (the cookie value is an opaque `sid`, not
-4. redirects to `/u/bob/`, where the DSH Web UI loads through the gateway.
+   a user name and not a token), stores `sid -> (user, expiry)` in memory, and
+   sets the `HttpOnly`, `SameSite=Lax` cookie `dsh_gw_session=<sid>` on the
+   browser (`__Host-dsh_gw_session` when `COOKIE_SECURE=true`),
+5. redirects to `/u/bob/`, where the DSH Web UI loads through the gateway.
 
 From then on every request under `/u/bob/` (assets, API calls, SSE, WebSocket) is
 proxied to bob's sandbox. The DSH launch token and DSH's own auth cookie stay in
-the gateway; the browser only holds the gateway cookie.
+the gateway; the browser only holds the opaque gateway session id. The cookie is
+useless as a bearer token.
+
+**Sessions are revocable and mostly short-lived in practice.** `POST /logout`,
+deleting the user, `POST /recreate` and cookie expiry (default 7 days,
+`COOKIE_MAX_AGE`) invalidate the server-side session. The session table lives in
+gateway memory, so **restarting the gateway logs every browser out** — expected
+for this single-replica demo; a production deployment needs a shared session
+store and sticky routing or per-request re-authentication. With SSO enabled, the
+gateway mints a session for the identity oauth2-proxy asserts instead of asking
+for a token.
 
 The same flow with `curl`, no JavaScript (the session cookie is the only
 credential):
 
 ```bash
 JAR=$(mktemp)
-# signup (form POST, exactly what the landing page sends)
+# signup (form POST, exactly what the landing page sends); add -d 'invite=...'
+# when SIGNUP_INVITE_CODE is configured, or send X-Signup-Invite
 curl -s -i -c "$JAR" -H 'Origin: http://localhost:18080' \
   -d 'user=bob' http://localhost:18080/users
 # proxy: bob's DSH Web through the gateway
@@ -344,13 +370,38 @@ curl -s -b "$JAR" http://localhost:18080/u/bob/ | head -5
 curl -s -o /dev/null -w '%{http_code}\n' http://localhost:18080/u/bob/   # 401
 # derived state: Ready / Waking / Suspended / ...
 curl -s -b "$JAR" http://localhost:18080/users/bob
-# delete bob (cascades sandbox + PVC)
+# sign out (revokes the server-side session)
+curl -s -b "$JAR" -H 'Origin: http://localhost:18080' -X POST http://localhost:18080/logout
+# delete bob (cascades sandbox + PVC and revokes every session for bob)
 curl -s -b "$JAR" -H 'Origin: http://localhost:18080' -X DELETE http://localhost:18080/users/bob
 ```
 
 API clients that prefer bearer tokens can use `POST /users` with a JSON body
 (`{"user":"bob"}`) and the returned one-time token, `POST /login` to exchange a
-token for a cookie, and `Authorization: Bearer <token>` on subsequent calls.
+token for a cookie, and `Authorization: Bearer <token>` on subsequent calls. A
+cookie/session value is never accepted as a bearer token, and a token for one
+user cannot read another user's path.
+
+### Auth abuse controls and proxy limits
+
+The gateway is a single process, so these limits are per replica. They stop
+casual abuse and one tenant monopolizing the service; an internet-facing
+deployment still needs ingress-level rate limiting and an audit trail.
+
+| Setting | Default | Behavior |
+| --- | --- | --- |
+| `AUTH_RATE_LIMIT` / `AUTH_RATE_WINDOW` | `30` per `60` s | Throttles `/users` and `/login` per client (rightmost `X-Forwarded-For` when behind a proxy, else the TCP peer) and answers `429` + `Retry-After` before reading the body or touching the cluster. `0` disables it. The base manifest sets it explicitly. |
+| `SIGNUP_INVITE_CODE` | unset | When set, `POST /users` requires the code as form field `invite` or header `X-Signup-Invite` (constant-time compare, `403` before user lookup). Put it in a Secret and restart the gateway to rotate. |
+| `MAX_IN_FLIGHT_PER_USER` | `32` | Caps concurrent proxied requests + WebSockets per user; excess HTTP gets `503` + `Retry-After`, excess WebSocket upgrades close with `1011`. |
+| `WS_MAX_MESSAGE_BYTES` | `16 MiB` | Largest WebSocket message received from DSH; oversized frames close the connection. Browser-to-DSH frames are bounded by uvicorn's own limit. HTTP/SSE streaming is not capped by this. |
+| `MAX_BODY_MB` | `32` | Largest proxied HTTP request body (`413`). |
+
+The gateway also strips client-supplied `Forwarded`, `X-Forwarded-User` and
+`X-Auth-Request-*` headers (and `x-forwarded-*` / `x-auth-request-*` prefixes)
+before proxying, so a tenant cannot inject identity or spoof hop headers into
+DSH. `UPSTREAM_HEADER_ALLOWLIST` can replace that denylist with an explicit
+comma-separated allowlist. See the [gateway README](gateway/README.md) for the
+full configuration.
 
 ### Gateway routes
 
@@ -395,8 +446,11 @@ not cut off.
 The upstream upgrade dials the sandbox **pod IP**, forwards no `Host`/`Origin`,
 and performs the launch-token handshake under the same `pod-IP:3080` authority.
 Missing or cross-origin auth closes with `4401`; upstream bridging failures close
-with `1011`. See the [gateway README](gateway/README.md#proxy-failure-semantics)
+with `1011`, as does exceeding `MAX_IN_FLIGHT_PER_USER` (per-user socket cap).
-for the full matrix.
+Messages received from DSH larger than `WS_MAX_MESSAGE_BYTES` (16 MiB by
+default) close the connection instead of being buffered; browser-to-DSH frames
+are bounded by uvicorn's own limit. See the
+[gateway README](gateway/README.md#proxy-failure-semantics) for the full matrix.
 
 ### Path routing
 
@@ -420,17 +474,20 @@ not a stack. Details, commands and the switch procedure are in the
 Both variants also ship NetworkPolicies: `ingress/61-networkpolicy.yaml` limits
 gateway ingress to Traefik pods, and `gateway-api-sso/75-networkpolicies.yaml`
 limits the gateway to oauth2-proxy and oauth2-proxy egress to DNS, public HTTPS
-and the gateway. They are part of the variant; see the
+and the gateway. They are part of the variant **and required for production**:
-[exposure README](manifests/exposure/README.md) and
+an exposure applied without its policy is demo-only. The sandbox side needs a
-[optional hardening](docs/optional-hardening.md).
+separate policy, and the gateway needs an egress policy; both are covered in
+[optional hardening](docs/optional-hardening.md) (see the production checklist)
+and summarized in the [exposure README](manifests/exposure/README.md).
 
 ### Option A — plain Ingress (gateway's own session auth)
 
 1. Set the Ingress host/TLS (or drop the `tls:` block), and set
    `DSH_TRUSTED_HOSTS` in `manifests/10-sandboxtemplate.yaml` to the same public
    host; re-apply the template.
-2. Set `COOKIE_SECURE=true` once the Ingress serves HTTPS:
+2. Set `COOKIE_SECURE=true` and drop the plain-HTTP acknowledgement once the
-   `kubectl -n dsh-demo set env deploy/dsh-gateway COOKIE_SECURE=true`.
+   Ingress serves HTTPS:
+   `kubectl -n dsh-demo set env deploy/dsh-gateway COOKIE_SECURE=true ALLOW_INSECURE_COOKIES-`.
 3. `kubectl apply -f manifests/exposure/ingress/`; verify
    `curl -sI https://<host>/healthz` returns `200`.
 
@@ -453,21 +510,37 @@ front of **oauth2-proxy**, which authenticates the browser against GitHub
 2. Create a GitHub OAuth App whose homepage/callback match the public FQDN, and
    create the oauth2-proxy and TLS Secrets from
    `73-oauth2-proxy-secret.yaml.example` and `74-tls-secret.yaml.example`.
-3. Replace `dsh-demo.example.com` and `your-github-org`, set
+3. Replace `dsh-demo.example.com` and `your-github-org` in the variant
-   `DSH_TRUSTED_HOSTS` in the template, and enable SSO:
+   manifests, set `DSH_TRUSTED_HOSTS` in the template, and enable SSO:
-   `kubectl -n dsh-demo set env deploy/dsh-gateway AUTH_PROXY_HEADER=X-Forwarded-User COOKIE_SECURE=true`.
+   `kubectl -n dsh-demo set env deploy/dsh-gateway AUTH_PROXY_HEADER=X-Forwarded-User COOKIE_SECURE=true ALLOW_INSECURE_COOKIES-`.
-4. `kubectl apply -f manifests/exposure/gateway-api-sso/`; verify the Gateway,
+4. `kubectl apply -f manifests/exposure/gateway-api-sso/`; then run
-   HTTPRoute, oauth2-proxy Deployment and endpoints as shown in the
+   [`scripts/preflight-sso.sh`](scripts/preflight-sso.sh) and fix everything it
+   reports **before** pointing real traffic at the Gateway. It verifies the
+   Secrets (including a valid oauth2-proxy cookie secret length), the gateway's
+   `AUTH_PROXY_HEADER`/`COOKIE_SECURE`, that the Gateway's TLS certificate
+   reference resolves, and that no `your-github-org`/`dsh-demo.example.com`
+   placeholder was left applied. Full verification steps are in the
    [exposure README](manifests/exposure/README.md).
 
+> **Exposure without the variant NetworkPolicy is demo-only.** The SSO
+> variant's `75-networkpolicies.yaml` is not optional in practice: it is the
+> only thing that makes oauth2-proxy the sole path to the gateway. Applying
+> only the Gateway/HTTPRoute/oauth2-proxy objects leaves the trust boundary
+> unenforced, so anyone who can reach `dsh-gateway:8080` can send
+> `X-Forwarded-User` and impersonate the user they claim to be.
+>
 > **SSO trust boundary — read this before enabling it.** After SSO is on, the
 > `dsh-gateway` Service must be reachable **only** through oauth2-proxy (it is
 > ClusterIP). The variant's `75-networkpolicies.yaml` restricts pod traffic
 > accordingly: the gateway accepts traffic only from oauth2-proxy pods,
 > oauth2-proxy only from the Gateway implementation, and its egress only to DNS,
-> public HTTPS and the gateway. Anyone who can reach `dsh-gateway:8080` directly
+> public HTTPS and the gateway. The gateway's own egress (Kubernetes API,
-> can send `X-Forwarded-User: <victim>`, so never add a second path. To turn SSO
+> sandbox pods) is not restricted by that file because the API-server endpoint is
-> off, remove the variable
+> cluster-specific; add the
+> [gateway egress policy](docs/optional-hardening.md#gateway-egress-required-for-production)
+> for production. Anyone who can reach `dsh-gateway:8080` directly can send
+> `X-Forwarded-User: <victim>`, so never add a second path. To turn SSO off,
+> remove the variable
 > (`kubectl -n dsh-demo set env deploy/dsh-gateway AUTH_PROXY_HEADER-`) and
 > delete the SSO variant.
 
@@ -481,25 +554,36 @@ gateway remains. Full commands and verification are in the
 
 ## Optional hardening
 
-The base walkthrough is deliberately portable. Five opt-in settings are
+The base walkthrough is deliberately portable, which means it is **not
-documented in [optional hardening](docs/optional-hardening.md):
+hardened**: without the policies and gVisor it is demo-only, not a safe
+multi-tenant platform. [Optional hardening](docs/optional-hardening.md) has the
+settings and a production checklist. In short:
 
 - **gVisor** — uncomment `runtimeClassName: gvisor` before applying, or patch an
   existing install. Requires a `gvisor` RuntimeClass and capable nodes.
   `kubectl port-forward` does not work under gVisor; the gateway path does.
+  Required for untrusted agents in production.
 - **nodeSelector** — uncomment and replace the placeholder node label to pin
   sandboxes and the gateway to a dedicated pool; add a toleration for tainted
   pools.
 - **Sandbox NetworkPolicy** —
   `kubectl apply -f manifests/optional/network-policy/` allows only
-  gateway→sandbox on `3080` and sandbox→DNS/public `443`.
+  gateway→sandbox on `3080` and sandbox→DNS/public `443`. Required for
+  production; exposure without it is demo-only.
+- **Gateway egress policy** — the gateway needs DNS, the Kubernetes API and
+  `3080` to sandbox pods. It is not shipped because the API-server endpoint is
+  cluster-specific; use the
+  [recipe](docs/optional-hardening.md#gateway-egress-required-for-production).
+  Required for production.
 - **Provider keys** — create `dsh-provider-keys-extra` as shown in step 1.
 - **Failed-Pod recovery** — uncomment `failedPodPolicy: Recreate` so the
   controller replaces a `Failed` sandbox Pod (node eviction) instead of parking
   the sandbox at `Finished=True`. Requires agent-sandbox v1.0.8+.
 
-Apply each independently and re-run the walkthrough. `kubectl apply -f manifests/`
+The **exposure variants' NetworkPolicies** are not optional in production
-is non-recursive, so the optional manifests are not applied by the base step.
+either; see step 9. Apply each setting independently and re-run the walkthrough.
+`kubectl apply -f manifests/` is non-recursive, so the optional manifests are not
+applied by the base step.
 
 ## Troubleshooting
 
@@ -508,9 +592,16 @@ is non-recursive, so the optional manifests are not applied by the base step.
 | Pod `CrashLoopBackOff`, probes failing with `401` | Probe path is `/`; change readiness/liveness to `/favicon.svg` |
 | Browser shows `401` from DSH through the gateway | Gateway handshake failed — check `kubectl -n dsh-demo logs deploy/dsh-gateway` and that RBAC grants `pods/log` |
 | `502` / `upstream unavailable` | Sandbox pod is not Ready (wake timed out) or the Service DNS is stale; check `kubectl get sandbox`, `WAKE_TIMEOUT` |
-| `503` with `Retry-After` | The launch token was not found in the pod logs yet; the gateway retries after a short delay. Check the pod logs and `DSH_LOG_TAIL_LINES` |
+| `503` with `Retry-After` | Either the launch token was not found in the pod logs yet (the gateway retries after a short delay; check the pod logs and `DSH_LOG_TAIL_LINES`) or the user hit `MAX_IN_FLIGHT_PER_USER` (default 32 concurrent requests/WebSockets); reduce client concurrency or raise the limit deliberately |
+| `429` with `Retry-After` on signup/login | The per-client auth rate limit (`AUTH_RATE_LIMIT`, default explicitly `30` per `AUTH_RATE_WINDOW=60` s) rejected the attempt before reading the body. Wait for the window, or raise the limit; behind a proxy make sure the real client IP is the rightmost `X-Forwarded-For` entry, not a shared NAT address |
+| `403` on signup: invite required/invalid | `SIGNUP_INVITE_CODE` is configured. Send the code as form field `invite` or header `X-Signup-Invite`; the landing page shows the field when enabled. A wrong code is rejected before the user lookup |
+| Gateway pod `CrashLoopBackOff` with `refusing to start with an insecure session cookie` | Intentional guard: plain HTTP is only allowed when explicitly acknowledged. For the local demo set `ALLOW_INSECURE_COOKIES=1` (the base manifest does); for HTTPS set `COOKIE_SECURE=true` and remove `ALLOW_INSECURE_COOKIES` |
+| Every browser is logged out after a gateway rollout/restart | Expected: sessions are opaque ids in gateway memory and a restart drops them. Sign in again; a production deployment needs shared session state or per-request re-authentication. The DSH sandboxes and their data are unaffected |
+| WebSocket closes with `1011` for a busy client | `MAX_IN_FLIGHT_PER_USER` (per-user connection cap) or an upstream/handshake failure closed the socket; check the gateway logs to tell them apart |
+| WebSocket closes after a very large message from DSH | A message received from DSH exceeded `WS_MAX_MESSAGE_BYTES` (16 MiB), so the relay closed it instead of buffering; raise the limit only if DSH legitimately sends larger frames. Browser-to-DSH frames are bounded by uvicorn's own limit |
+| `scripts/preflight-sso.sh` exits non-zero | It names the failing item: a missing Secret/key, a bad oauth2-proxy cookie-secret length, missing `AUTH_PROXY_HEADER`/`COOKIE_SECURE`, a dangling Gateway TLS reference, a leftover `your-github-org`/`dsh-demo.example.com` placeholder, or a second path to the gateway (an Ingress). Fix all items before exposing the SSO variant |
 | `409` on signup | User already has a claim; use `POST /login` with the existing token or delete the user first |
-| Cookie set but browser keeps getting `401` | `COOKIE_SECURE=true` while serving over plain HTTP (secure cookies are not sent); use HTTPS or set `false` for local demos |
+| Cookie set but browser keeps getting `401` | `COOKIE_SECURE=true` while serving over plain HTTP (secure cookies are not sent); use HTTPS or set `false` **and** `ALLOW_INSECURE_COOKIES=1` for local demos |
 | WebSocket closes immediately (`4401`) | Missing/expired gateway cookie, or the upgrade's `Origin` does not match `Host` (CSWSH check); DSH rejecting `Host` instead surfaces as close `1011` — add the host to `DSH_TRUSTED_HOSTS` |
 | Console spams `[connection] connection lost, retry #N` | The upstream WS upgrade is being rejected, surfaced as close `1011`. The gateway dials the sandbox **pod IP**, forwards no `Host`/`Origin`, and handshakes under the same `pod-IP:3080` authority DSH binds its cookie to; an older gateway image, or a sandbox with an empty `status.podIPs`, hits this loop |
 | `manifest.webmanifest` returns `401` in the console | Browsers fetch the Web App Manifest without credentials, so the gateway's session cookie is absent and the request fails closed. The UI is unaffected; only the PWA install prompt is lost |
@@ -539,9 +630,19 @@ is non-recursive, so the optional manifests are not applied by the base step.
 
 Deliberately **not** production code:
 
-- **Single replica.** Idle clocks, in-flight tracking, and the handshake cache
+- **Single replica.** Idle clocks, in-flight tracking, the handshake cache and
-  are in memory. Running two gateway replicas would double-suspend or lose wake
+  the browser session table are in memory. Running two gateway replicas would
-  tracking; scale up only after moving that state to a shared store.
+  double-suspend or lose wake tracking, and sessions would land on the wrong
+  replica; scale up only after moving that state to a shared store.
+- **Sessions die with the process.** Browser sessions are opaque ids held in
+  gateway memory (revocable on logout/delete/recreate, but not durable). A
+  gateway restart logs every browser out. There is no SSO refresh-token or
+  password store; identity is re-established by oauth2-proxy on the next
+  request.
+- **Abuse controls are per-process and coarse.** `AUTH_RATE_LIMIT`, the signup
+  invite code, `MAX_IN_FLIGHT_PER_USER` and `WS_MAX_MESSAGE_BYTES` limit casual
+  abuse, but they are not a substitute for ingress rate limiting, WAF/quota, or
+  an audit log, and the in-memory rate buckets reset on restart.
 - **Log scraping.** The launch token is recovered from pod logs. Log rotation, a
   restarted pod, or a changed DSH log format can break the handshake until the
   next `401` refresh.
@@ -551,12 +652,13 @@ Deliberately **not** production code:
   but the platform does not manage that. Real multi-tenancy needs per-tenant
   credentials or an egress proxy.
 - **No TLS in the gateway.** Terminate TLS at an Ingress or Gateway and set
-  `COOKIE_SECURE=true`.
+  `COOKIE_SECURE=true`, then remove `ALLOW_INSECURE_COOKIES`. The base manifest
+  runs plain HTTP for the port-forward demo and is demo-only.
 - **SSO trust is hop-based.** `AUTH_PROXY_HEADER` trusts whoever sets the header.
   The SSO variant ships `75-networkpolicies.yaml`, which restricts the gateway
   to oauth2-proxy and oauth2-proxy egress to the gateway/DNS/public HTTPS; a
   custom exposure without that policy has no signature, mTLS or network
-  enforcement.
+  enforcement. Exposure without the policy is demo-only.
 - **DSH's inner file sandbox is off here.** The template sets
   `DSH_PERMISSION_MODE=danger-full-access` because neither backend of DSH's own
   command sandbox is usable in this pod: `bubblewrap` is installed in the image
@@ -567,21 +669,24 @@ Deliberately **not** production code:
   pod remains the boundary — non-root,
   capabilities dropped, `seccompProfile: RuntimeDefault`, its own PVC and Service
   — but an agent command can now read its own `DSH_HOME` (including
-  `.credentials.yaml`) and write anywhere in the container. On hosts where a
+  `.credentials.yaml`) and write anywhere in the container. Run sandboxes under
-  backend works, set `workspace-write` (or `read-only`) and verify before relying
+  gVisor in production. On hosts where a backend works, set `workspace-write`
-  on the inner policy.
+  (or `read-only`) and verify before relying on the inner policy.
-- **Isolation is opt-in.** gVisor, the sandbox NetworkPolicy and the exposure
+- **Isolation is opt-in.** gVisor, the sandbox NetworkPolicy, the gateway egress
-  policies are opt-in; without them, sandboxes share the host kernel and can
+  policy and the exposure policies are opt-in; without them, sandboxes share the
-  reach the cluster network. The base example is a demo, not a hardened
+  host kernel and can reach the cluster network. The base example is a demo, not
-  multi-tenant platform.
+  a hardened multi-tenant platform. See the
+  [production checklist](docs/optional-hardening.md#6-production-checklist).
 - **OAuth org is the only authorization.** Any GitHub user in the configured
   organization gets an auto-provisioned sandbox; there is no per-user allow-list,
-  quota, or admin API.
+  quota, or admin API. `SIGNUP_INVITE_CODE` gates the gateway's own signup form,
+  not SSO auto-provisioning.
 - **In-memory user directory.** Users are claims + annotations; there is no
   database, password reset, or admin API. Tokens are stored only as SHA-256
   hashes in claim annotations.
 - **Bearer tokens in URLs.** Avoid putting the signup token in a URL/log; the
-  browser flow uses the `HttpOnly` cookie instead.
+  browser flow uses the `HttpOnly` cookie instead. The cookie no longer contains
+  the token, and a cookie value is never accepted as a bearer token.
 
 ## Cleanup
 
@@ -603,6 +708,8 @@ delete the Secrets with the namespace and revoke the OAuth App in GitHub.
 - [Architecture](docs/architecture.md) — container/sequence diagrams, ADRs,
   security and RBAC, failure modes, evolution path.
 - [Exposure README](manifests/exposure/README.md) — the two variants in detail.
+- [SSO preflight](scripts/preflight-sso.sh) — read-only checks for the SSO
+  variant (Secrets, gateway env, TLS reference, placeholders, second paths).
 - [Optional hardening](docs/optional-hardening.md) — gVisor, nodeSelector,
-  NetworkPolicy, extra provider keys and failed-Pod recovery, with verification
+  NetworkPolicy, extra provider keys and failed-Pod recovery, with verification,
-  and rollback.
+  the production checklist and rollback.

examples/dsh-agents-as-a-service/docs/architecture.md

@@ -72,8 +72,10 @@ Each variant also ships a NetworkPolicy: `ingress/61-networkpolicy.yaml` limits
 to Traefik pods, and `gateway-api-sso/75-networkpolicies.yaml` limits the gateway to
 oauth2-proxy, oauth2-proxy ingress to the Gateway implementation, and oauth2-proxy egress to
 DNS/public HTTPS/the gateway. The SSO policy turns the trust boundary into pod-traffic
-enforcement; the caveats (Traefik label, `hostNetwork`, kubelet probes) are in
+enforcement. These policies are **required for production**: exposing the gateway by applying
-[optional hardening](optional-hardening.md).
+only the Gateway/HTTPRoute/Ingress objects is demo-only. The sandbox-side policy and the
+gateway's own egress policy are separate (the API-server endpoint is cluster-specific); see
+[optional hardening](optional-hardening.md#gateway-egress-required-for-production).
 
 ## Flows
 
@@ -87,20 +89,22 @@ sequenceDiagram
     participant K as Kubernetes API
     participant C as agent-sandbox controller
 
-    B->>G: POST /users (form: user=bob, Origin)
+    B->>G: POST /users (form: user=bob, invite, Origin)
-    G->>G: validate user name and body size
+    G->>G: rate limit, invite check, validate user name and body size
     G->>K: create SandboxClaim dsh-bob (warmPoolRef)
     K->>C: reconcile claim
     C-->>K: adopt spare, Ready, status.sandbox.name = dsh-pool-xxxx
     G->>K: read claim (status) + sandbox + pod
-    G-->>B: 303 Location /u/bob/ + Set-Cookie dsh_gw_session
+    G->>G: mint opaque sid, store sid -> (user, expiry)
+    G-->>B: 303 Location /u/bob/ + Set-Cookie dsh_gw_session=<sid>
     Note over G: JSON clients instead get 201 (Ready),<br/>202 (accepted, still waking), or 409 (conflict)
 ```
 
 Form signup waits up to `WAKE_TIMEOUT` for the claim to become `Ready`, then redirects; the
 first proxied request also waits for `Ready` and performs the DSH handshake (below). A `409`
 means the user already has a claim, in which case `POST /login` (bearer token) or the existing
-cookie is the right path.
+cookie is the right path. The cookie value is an opaque session id: it is meaningless outside
+this gateway process and is never accepted as a bearer token.
 
 ### First request / proxy (with handshake)
 
@@ -112,8 +116,8 @@ sequenceDiagram
     participant K as Kubernetes API
     participant D as DSH Web pod
 
-    B->>G: GET /u/bob/ (Cookie dsh_gw_session)
+    B->>G: GET /u/bob/ (Cookie dsh_gw_session=<sid>)
-    G->>G: authenticate cookie, user = bob
+    G->>G: look up sid -> session (valid, not expired), user = bob
     G->>K: resolve claim -> sandbox -> pod
     alt sandbox Suspended
         G->>K: patch operatingMode=Running (wake)
@@ -140,6 +144,32 @@ Inside `proxy_http` the order is auth, in-flight slot, sandbox resolution/wake,
 body read, upstream send. An upload aborted mid-body may therefore already have paid for a wake
 and a handshake, but it never reaches DSH.
 
+### Browser sessions
+
+The browser never holds a DSH credential. On signup/login the gateway mints a random session id
+(`secrets.token_urlsafe(32)`), stores `sid -> Session(user, expires_at)` in memory, and sets it
+as the `HttpOnly`, `SameSite=Lax` cookie `dsh_gw_session` (`__Host-dsh_gw_session` when
+`COOKIE_SECURE=true`). Every browser request is resolved through that table; the cookie value is
+not a bearer token and cannot be replayed against another user's path.
+
+Sessions end on explicit logout, user delete, `/recreate` (all sessions for that user) and
+expiry (`COOKIE_MAX_AGE`, default 7 days). Because the table is process memory, a gateway
+restart logs every browser out; scaling beyond one replica therefore requires a shared session
+store (or re-authentication on every request). The sweeper prunes expired entries and sessions
+for users whose claim no longer exists.
+
+### Auth abuse controls and proxy limits
+
+Unauthenticated endpoints are throttled before the body is read: `AUTH_RATE_LIMIT` attempts per
+client per `AUTH_RATE_WINDOW` (defaults 30/60s; keyed on the rightmost `X-Forwarded-For` entry
+when present, else the peer address), answered with `429` + `Retry-After`. When
+`SIGNUP_INVITE_CODE` is set, signup additionally requires a constant-time-matched code (form
+field or `X-Signup-Invite`) and answers `403` otherwise. Proxied traffic is capped per user
+(`MAX_IN_FLIGHT_PER_USER`, default 32 concurrent HTTP requests + WebSockets: `503` for HTTP,
+close `1011` for WebSocket) and per WebSocket message received from DSH
+(`WS_MAX_MESSAGE_BYTES`, 16 MiB). These are in-process guards for a single replica, not an ingress
+rate limiter or quota system.
+
 ### Wake-on-connect and idle suspend
 
 ```mermaid
@@ -220,6 +250,14 @@ sequenceDiagram
     end
 ```
 
+An upgrade with a missing/expired session, or one that would exceed
+`MAX_IN_FLIGHT_PER_USER`, is accepted and then closed: `4401` for authentication, `1011` for
+the per-user socket cap. Messages received from DSH above `WS_MAX_MESSAGE_BYTES` (16 MiB) close
+the connection instead of being buffered; browser-to-DSH frames are bounded by uvicorn's own
+limit. Client-supplied `Forwarded`, `X-Forwarded-User`,
+`X-Auth-Request-*` and `x-forwarded-*`/`x-auth-request-*` headers are stripped on the HTTP and
+WebSocket paths; `UPSTREAM_HEADER_ALLOWLIST` replaces that denylist with an explicit allowlist.
+
 ## Decisions and trade-offs
 
 ### ADR-1: Starlette ASGI instead of a sync Flask proxy
@@ -279,14 +317,21 @@ sequenceDiagram
   (`kubectl annotate sandboxclaim ...`) to keep being swept. Fine for a reference pattern, not
   for a product.
 
-### ADR-6: Gateway cookie session instead of bearer tokens in the browser
+### ADR-6: Opaque server-side session cookie instead of bearer tokens in the browser
 
-- **Decision:** browsers get `dsh_gw_session=<user>:<token>`, `HttpOnly`, `SameSite=Lax`
+- **Decision:** browsers get `dsh_gw_session=<sid>`, `HttpOnly`, `SameSite=Lax` (`Secure` when
-  (`Secure` when enabled); API clients may still use `Authorization: Bearer`.
+  enabled); the sid maps to `Session(user, expires_at)` in gateway memory. API clients may still
-- **Why:** tokens never appear in URLs or JS-readable storage, and `SameSite=Lax` plus a strict
+  use `Authorization: Bearer`. The cookie name is `__Host-dsh_gw_session` when the Secure flag
-  `Origin`/`Referer` check on cookie-authenticated mutations blocks basic CSRF.
+  is on and no explicit `COOKIE_NAME` is set.
-- **Cost:** cookie-based auth needs TLS and correct `COOKIE_SECURE`; there is no signed-cookie
+- **Why:** tokens never appear in URLs or JS-readable storage, the cookie value is useless if
-  layer, so the gateway trusts the token hash comparison for validation.
+  leaked outside the gateway session table, sessions can be revoked server-side (logout,
+  user delete, recreate, expiry), and a cookie cannot be reused as a bearer token for another
+  user's path. `SameSite=Lax` plus a strict `Origin`/`Referer` check on cookie-authenticated
+  mutations blocks basic CSRF.
+- **Cost:** stateful auth in a single process: a restart logs everyone out and horizontal
+  scaling needs a shared session store. Cookie-based auth also needs TLS and the correct
+  `COOKIE_SECURE` setting; the gateway refuses to start with `COOKIE_SECURE=false` unless
+  `ALLOW_INSECURE_COOKIES=1` is set for a local HTTP demo.
 
 ## Security and RBAC
 
@@ -305,33 +350,52 @@ Notes and limits:
   permission is scoped to one namespace, but anyone who can read gateway memory or logs can
   impersonate users. Prefer the upstream token API when available.
 - **No cluster-wide access, no secret reads.** The gateway does not read `dsh-provider-keys`.
-- **Browser-facing hardening:** `HttpOnly`/`SameSite=Lax`/optional `Secure` cookies,
+  (It does read the optional signup invite code if it is mounted as an env var.)
-  timing-safe SHA-256 token comparison, strict same-origin check on cookie-auth mutations,
+- **Browser-facing hardening:** opaque server-side sessions instead of token-bearing cookies,
-  request-body limit (`MAX_BODY_MB`), hop-by-hop header stripping, upstream `Set-Cookie`
+  `HttpOnly`/`SameSite=Lax`/optional `Secure` (+ `__Host-` prefix when secure),
-  dropped, DSH `Location` headers rewritten under `/u/<user>/`.
+  timing-safe SHA-256 bearer-token comparison, timing-safe invite-code comparison, strict
+  same-origin check on cookie-auth mutations, request-body limit (`MAX_BODY_MB`), hop-by-hop
+  header stripping, client identity/hop headers (`Forwarded`, `X-Forwarded-User`,
+  `X-Auth-Request-*`, `x-forwarded-*`/`x-auth-request-*`) stripped on HTTP and WebSocket,
+  upstream `Set-Cookie` dropped, DSH `Location` headers rewritten under `/u/<user>/`.
+- **Session lifecycle:** login/signup mint an opaque sid; logout and user delete revoke it;
+  `/recreate` revokes every session for that user; expiry (`COOKIE_MAX_AGE`, default 7 days) is
+  enforced on lookup. The table is in memory, so a restart logs browsers out and a second
+  replica needs shared state.
+- **Abuse controls (per replica):** `AUTH_RATE_LIMIT`/`AUTH_RATE_WINDOW` throttle
+  unauthenticated signup/login per client with `429` + `Retry-After`; `SIGNUP_INVITE_CODE`
+  gates signup; `MAX_IN_FLIGHT_PER_USER` caps concurrent proxied requests + WebSockets per user;
+  `WS_MAX_MESSAGE_BYTES` caps messages received from DSH; browser-to-DSH frames are bounded by
+  uvicorn. These are in-process guards, not an ingress rate limiter or audit log.
 - **Host allow-list:** DSH rejects unknown `Host` headers. The gateway forwards the browser's
   `Host`, so every public hostname must be in `DSH_TRUSTED_HOSTS`; `localhost`/`127.0.0.1` are
   always trusted.
 - **TLS is external.** The gateway serves plain HTTP; terminate TLS at the Ingress and set
-  `COOKIE_SECURE=true`. Without TLS, session cookies are replayable on the network.
+  `COOKIE_SECURE=true`. The base demo sets `COOKIE_SECURE=false` with
+  `ALLOW_INSECURE_COOKIES=1` for the port-forward walkthrough; without TLS, session cookies are
+  replayable on the network and that combination must never be exposed.
 - **Tenant isolation** is pod + PVC separation; all tenants share one namespace, one DSH binary,
   and the shared provider keys (`dsh-provider-keys` plus the optional
-  `dsh-provider-keys-extra`). `manifests/optional/network-policy/` adds an opt-in sandbox
+  `dsh-provider-keys-extra`). The base example is demo-only: production requires gVisor for the
-  NetworkPolicy, and gVisor/`nodeSelector` are opt-in PodSpec fields. Add per-tenant
+  sandboxes, the sandbox NetworkPolicy, the gateway egress policy and the exposure NetworkPolicy,
-  credentials before calling it multi-tenant-grade.
+  plus per-tenant credentials or an egress proxy. See the
+  [production checklist](optional-hardening.md#6-production-checklist).
 - **DSH's inner file sandbox is disabled by deployment override.** The template sets
   `DSH_PERMISSION_MODE=danger-full-access` because the in-container backends are unusable here:
   `bubblewrap` ships in the image but is unsetuid and cannot create an unprivileged user namespace
   under the pod's seccomp/capability surface, and no Landlock runner is available; the confined
   executor would otherwise fail closed on every command. The pod remains the boundary, so an
-  agent can read its own `DSH_HOME`. Hosts with a working backend can keep a confined mode.
+  agent can read its own `DSH_HOME`. Hosts with a working backend can keep a confined mode;
+  multi-tenant deployments must put the pod in gVisor and a NetworkPolicy.
 - **Optional hardening is opt-in.** gVisor, node selection, the sandbox/exposure NetworkPolicies,
   extra provider keys and failed-Pod recovery are documented in
   [optional hardening](optional-hardening.md). The base manifests stay portable (no gVisor
   RuntimeClass, no active node labels, no NetworkPolicy, no extra Secret required, and the
   controller's default `failedPodPolicy: Retain`).
-- **No gateway rate limiting.** Signup can create claims until the cluster or warm pool is
+- **SSO is trust-on-hop.** `AUTH_PROXY_HEADER` makes the gateway trust the proxy-asserted
-  exhausted; put limits at the ingress for real deployments.
+  identity; the SSO variant must remain the only path to the Service, and its NetworkPolicy is
+  required, not optional. Run [`scripts/preflight-sso.sh`](../scripts/preflight-sso.sh) after
+  applying it.
 
 ## Failure modes
 
@@ -340,7 +404,14 @@ Notes and limits:
 | DSH log line changed or rotated away | Proxy returns `503` (missing launch token) | Fix the parser or restart the pod so the token line is re-emitted |
 | Probe on `/` | Pod `CrashLoopBackOff`, `401` in probe logs | Use `/favicon.svg` for readiness/liveness (shipped templates do) |
 | Warm pool exhausted | JSON signup returns `202` (state `Waking`); form signup is slow | Increase `replicas` in the warm pool |
-| Gateway restart | Idle sandboxes stop suspending; handshake cache lost | Rebuilt lazily on next request; consider a shared store for production |
+| Gateway restart | Idle sandboxes stop suspending; handshake cache and browser sessions lost | Idle clocks and handshake cache rebuild lazily; sessions do not, so browsers must sign in again after a rollout. Use a shared session store for production |
+| Gateway configured `COOKIE_SECURE=false` without `ALLOW_INSECURE_COOKIES=1` | Gateway pod exits at startup / `CrashLoopBackOff` | Intentional guard against an insecure cookie on an HTTPS deployment; set `ALLOW_INSECURE_COOKIES=1` only for the local plain-HTTP demo, or set `COOKIE_SECURE=true` |
+| Auth rate limit hit | `429` + `Retry-After` on signup/login | Per-client in-memory bucket (`AUTH_RATE_LIMIT`/`AUTH_RATE_WINDOW`); wait for the window or tune it. Behind a proxy, keying uses the rightmost `X-Forwarded-For` entry |
+| Signup invite missing/wrong | `403` before the claim is created | `SIGNUP_INVITE_CODE` is set; send the `invite` form field or `X-Signup-Invite` header |
+| Per-user concurrency cap hit | HTTP `503` + `Retry-After`, or WebSocket close `1011` | `MAX_IN_FLIGHT_PER_USER` protects the single gateway from one busy tenant; reduce concurrency or raise the cap deliberately. These are per replica |
+| Oversized WebSocket message from DSH | Connection closes | `WS_MAX_MESSAGE_BYTES` (16 MiB) is enforced on upstream messages; raise it only if DSH legitimately needs larger frames |
+| Session expiry / revocation | `401` (HTTP) or close `4401` (WebSocket) | Expected after logout, user delete, `/recreate`, `COOKIE_MAX_AGE` expiry or a gateway restart; sign in again |
+| SSO variant applied without its NetworkPolicy (or with an Ingress) | Gateway accepts spoofed `X-Forwarded-User` | Demo-only configuration; keep `75-networkpolicies.yaml`, remove the second path, and run `scripts/preflight-sso.sh` |
 | Browser aborts a request (tab reload, back navigation) during a slow wake or handshake | No response reaches the client; nothing appears in the access log | If the abort lands before the response starts, the body read raises `ClientDisconnect` and the app answers `499` (`CLIENT_CLOSED_REQUEST`), which cannot reach the departed peer. Nothing reached DSH, no ERROR traceback is logged, and the in-flight slot is released. A request already streaming ends with its upstream status. |
 | DSH auth cookie expired mid-session | Proxy `401` once, then recovers | Gateway refreshes the handshake once |
 | Upstream pod name changed after resume | Cached cookie keyed by old pod UID is useless | Cache is invalidated on suspend; next request re-handshakes |
@@ -372,10 +443,11 @@ single-retry refresh are the supported workaround.
 ## Evolution path
 
 1. Replace log scraping with the upstream token API (above), deleting the `pods/log` permission.
-2. Move idle clocks, in-flight tracking, and handshake cache to a shared store; then scale the
+2. Move idle clocks, in-flight tracking, handshake cache **and sessions** to a shared store; then
-   gateway horizontally (sticky routing not required if state is shared).
+   scale the gateway horizontally (sticky routing not required if state is shared).
 3. Add per-tenant API keys or an egress proxy so a single key is not shared by all sandboxes.
-4. Add NetworkPolicies (gateway → sandboxes only), TLS everywhere, rate limits, and audit
+4. Add NetworkPolicies (gateway → sandboxes only, plus the documented gateway egress policy),
-   logging at the ingress.
+   gVisor for sandbox pods, TLS everywhere, ingress-level rate limits/quota and audit logging.
+   The gateway's in-process limits are not a substitute.
 5. If DSH grows absolute URLs or per-user cookies that cannot be rewritten, switch to
    per-user subdomains with wildcard DNS/TLS.

examples/dsh-agents-as-a-service/docs/optional-hardening.md

@@ -2,14 +2,26 @@
 
 The base example is deliberately portable: it runs on kind and GKE without a
 gVisor runtime, a tainted node pool or a NetworkPolicy-capable CNI, and it
-boots with only the required `dsh-provider-keys` Secret. This document covers
+boots with only the required `dsh-provider-keys` Secret. That portability is
-four **opt-in** controls plus failed-Pod recovery:
+exactly why the base manifests are **demo-only**. This document covers the
+controls you add for production and the steps to enable or roll them back.
+
+**Production is not the base walkthrough.** At minimum, a production deployment
+needs: gVisor for the sandbox pods (or another kernel-isolation boundary), the
+sandbox NetworkPolicy, the gateway egress policy, the exposure variant's
+NetworkPolicy, TLS with `COOKIE_SECURE=true` (and no
+`ALLOW_INSECURE_COOKIES`), SSO (or an equivalent authenticating proxy) as the
+only path to the gateway, and per-tenant provider credentials/egress. The
+checklist at the end summarizes this; without the network and kernel layers the
+example is not tenant-isolated.
+
+This document covers four **opt-in** controls plus failed-Pod recovery:
 
 | Setting | Where it lives | What it changes |
 | --- | --- | --- |
-| gVisor | commented `runtimeClassName` in the SandboxTemplates and Deployments | puts DSH and/or the gateway in a userspace kernel |
+| gVisor | commented `runtimeClassName` in the SandboxTemplates and Deployments | puts DSH and/or the gateway in a userspace kernel; required for untrusted agents in production |
 | nodeSelector | commented `nodeSelector` in the same files | pins pods to a chosen node pool |
-| NetworkPolicy | `manifests/optional/network-policy/`, `manifests/exposure/*/` | limits sandbox, gateway and proxy connectivity |
+| NetworkPolicy | `manifests/optional/network-policy/`, `manifests/exposure/*/`, plus the gateway egress recipe | limits sandbox, gateway and proxy connectivity; the sandbox and gateway-egress policies are required for production |
 | Provider keys | optional `dsh-provider-keys-extra` Secret | injects extra provider API keys into every sandbox |
 | Failed-Pod recovery | commented `failedPodPolicy` in the SandboxTemplates | replaces a Failed sandbox Pod instead of parking the sandbox |
 
@@ -234,10 +246,17 @@ kubectl -n dsh-demo patch sandboxtemplate dsh-web --type merge \
 
 The base example does **not** manage NetworkPolicy: the SandboxTemplate is
 `networkPolicyManagement: Unmanaged`, and the gateway has no policy. That keeps
-the walkthrough portable and independent of the sandbox-router; the opt-in
+the walkthrough portable and independent of the sandbox-router. **For
-policies below are standard Kubernetes `NetworkPolicy` objects.
+production this is not optional**: without the sandbox policy every tenant can
+reach every other tenant and cluster-internal endpoints, and without a gateway
+egress policy the gateway can talk to anything the cluster network allows.
+Apply both. The policies below are standard Kubernetes `NetworkPolicy` objects.
 
-### Optional sandbox policy
+> **Demo vs production.** An installation that skips the sandbox NetworkPolicy
+> and the gateway egress policy is a demo. Exposure (Ingress/Gateway API) adds
+> ingress protection only; it does not isolate tenants from each other.
+
+### Sandbox policy (required for production)
 
 [`manifests/optional/network-policy/10-sandbox-networkpolicy.yaml`](../manifests/optional/network-policy/10-sandbox-networkpolicy.yaml)
 selects every Sandbox pod through the agent-sandbox tracking label
@@ -301,10 +320,10 @@ Caveats:
 - `kubectl port-forward` still works for debugging (the connection is local to
   the pod), except under gVisor.
 
-### Exposure-variant policies
+### Exposure-variant policies (required, part of the variant)
 
-Each exposure variant ships its own policy. They are part of the variant, not a
+Each exposure variant ships its own policy. They are part of the variant and
-separate opt-in step:
+**required for production**; an exposure without its policy is demo-only:
 
 - [`manifests/exposure/ingress/61-networkpolicy.yaml`](../manifests/exposure/ingress/61-networkpolicy.yaml)
   allows only Traefik pods (`app.kubernetes.io/name: traefik`) to reach the
@@ -317,7 +336,10 @@ separate opt-in step:
 The SSO policy is what turns the trust boundary in the
 [exposure README](../manifests/exposure/README.md) into network enforcement.
 The `dsh-gateway` Service must still stay ClusterIP; do not apply both exposure
-variants.
+variants. After applying the SSO variant, run
+[`scripts/preflight-sso.sh`](../scripts/preflight-sso.sh): it checks the
+gateway's SSO env, the Secrets, the TLS reference, leftover placeholders and
+accidental second paths (such as an Ingress).
 
 Verify the negative case from a sandbox pod (it is not the proxy):
 
@@ -332,11 +354,12 @@ different pod label, replace the `podSelector` with the correct selector or an
 `ipBlock`. As with the sandbox policy, kubelet probes can be affected on some
 CNIs.
 
-### Gateway egress (documented, not shipped)
+### Gateway egress (required for production)
 
-The gateway needs DNS, the Kubernetes API, and TCP `3080` to sandbox pods. The
+The gateway needs DNS, the Kubernetes API, and TCP `3080` to sandbox pods. An
-API server endpoint is cluster-specific (Service CIDR or node IP/port), so an
+egress policy is **required for production** but is not shipped, because the API
-egress policy is **not** shipped. If your cluster has a stable API-server CIDR
+server endpoint is cluster-specific (Service CIDR or node IP/port) and a wrong
+value silently breaks signup/proxy. If your cluster has a stable API-server CIDR
 and port, add an egress policy like this (replace the placeholders; verify the
 port, commonly `443` or `6443`):
 
@@ -597,7 +620,63 @@ done
 Warm-pool spares pick the default up as they are claimed and replenished, or
 delete them as in step 2 above.
 
-## 6. Verification summary
+## 6. Production checklist
+
+The base walkthrough is a demo. A production install must satisfy every item
+below; the sections above give the commands and caveats.
+
+**Isolation and network**
+
+- [ ] Sandbox pods run under gVisor (or an equivalent kernel-isolation
+      boundary) because DSH runs with `DSH_PERMISSION_MODE=danger-full-access`
+      in this image; the pod is the boundary. (Section 1.)
+- [ ] The sandbox NetworkPolicy is applied and verified: no tenant→tenant,
+      no tenant→cluster-Service/API, DNS + public HTTPS only. (Section 3.)
+- [ ] The gateway egress policy is applied with the cluster's real API-server
+      CIDR/port, scoped to DNS, the API server and sandbox pods on `3080`.
+      (Section 3, "Gateway egress".)
+- [ ] The exposure variant's NetworkPolicy is applied. An exposure without it is
+      demo-only. For SSO, the gateway is reachable **only** through
+      oauth2-proxy; there is no second Ingress/Gateway/port-forward path.
+- [ ] Nodes/CNI enforce NetworkPolicy (verify the negative cases, not just the
+      positive path).
+- [ ] The gateway and (optionally) oauth2-proxy run with `runAsNonRoot`,
+      dropped capabilities, `RuntimeDefault` seccomp and a read-only root
+      filesystem, as shipped.
+
+**Authentication, TLS and abuse controls**
+
+- [ ] TLS terminates in front of the gateway, `COOKIE_SECURE=true`, and
+      `ALLOW_INSECURE_COOKIES` is **not** set. The gateway refuses to start with
+      an insecure cookie unless explicitly acknowledged.
+- [ ] SSO (or an equivalent authenticating proxy) is enabled with
+      `AUTH_PROXY_HEADER=X-Forwarded-User`, and
+      [`scripts/preflight-sso.sh`](../scripts/preflight-sso.sh) exits `0`.
+- [ ] No `your-github-org` / `dsh-demo.example.com` placeholder remains.
+- [ ] `SIGNUP_INVITE_CODE` is set from a Secret if the gateway's own signup form
+      is reachable, and `AUTH_RATE_LIMIT` is set deliberately (`30`/60s shipped).
+      Add ingress-level rate limiting/quota too; the gateway's buckets are
+      in-process and reset on restart.
+- [ ] Session lifetime (`COOKIE_MAX_AGE`) and the logout/delete revocation
+      behavior are acceptable; account for gateway restarts logging users out.
+- [ ] `MAX_IN_FLIGHT_PER_USER` and `WS_MAX_MESSAGE_BYTES` fit the workload.
+
+**Credentials, platform and operations**
+
+- [ ] Provider keys are per-tenant (or routed through an egress proxy) instead
+      of the shared `dsh-provider-keys` Secrets; any shared key is treated as
+      visible to every tenant.
+- [ ] RBAC stays namespace-scoped; `pods/log` is treated as sensitive because
+      it contains launch tokens and model output. Plan the upstream token API
+      migration.
+- [ ] Images are digest-pinned and dependency installs are hash-locked.
+- [ ] Gateway replicas stay at `1` (in-memory sessions/idle state) or the state
+      is externalized.
+- [ ] `failedPodPolicy: Recreate` is set if node eviction/spot reclaim is
+      expected.
+- [ ] Audit logging, alerting and backups of the PVCs are in place.
+
+## 7. Verification summary
 
 Required locally for any change to this example:
 
@@ -605,6 +684,7 @@ Required locally for any change to this example:
 make check          # versions, example layout, manifest YAML shape
 yamllint .
 make test           # only when the gateway code changed
+shellcheck examples/dsh-agents-as-a-service/scripts/*.sh
 ```
 
 CI additionally parses every manifest and runs `kubectl apply
@@ -618,17 +698,25 @@ Manual checks, on a cluster with the relevant CNI/runtime:
   gateway proxy works, port-forward limitation acknowledged.
 - nodeSelector: pods land on the intended nodes; no `Pending` events.
 - Sandbox policy: the allow/deny matrix above.
+- Gateway egress policy: signup and proxy still work; the gateway cannot reach
+  an arbitrary cluster Service or the metadata server.
 - Exposure policies: browser path works; a non-proxy pod cannot reach the
-  gateway; probes stay healthy.
+  gateway; probes stay healthy. `scripts/preflight-sso.sh` exits `0`.
+- Cookie/TLS guard: with `COOKIE_SECURE=false` and no
+  `ALLOW_INSECURE_COOKIES` the gateway refuses to start; with TLS it starts and
+  the cookie is `Secure` (`__Host-` prefixed).
+- Auth abuse controls: `429` + `Retry-After` after the configured limit, `403`
+  on a wrong invite code, and revocations on logout/delete/recreate.
 - Provider keys: set/unset output (never the values) and the refresh procedure.
 - Failed-Pod recovery: `spec.failedPodPolicy` on the Sandbox, and the drill
   above replaces a `Failed` Pod while keeping the claim and PVC.
 
-## 7. Rollback summary
+## 8. Rollback summary
 
 | Layer | Rollback |
 | --- | --- |
 | Sandbox policy | `kubectl delete -f manifests/optional/network-policy/` |
+| Gateway egress policy | `kubectl delete networkpolicy dsh-gateway-egress -n dsh-demo` (do not leave it half-configured) |
 | Exposure policy | delete the exposure variant directory |
 | gVisor | patch `runtimeClassName: null`, recreate pods |
 | nodeSelector | patch `nodeSelector: null`, recreate pods |

examples/dsh-agents-as-a-service/gateway/Dockerfile

@@ -1,16 +1,73 @@
-FROM python:3.12-slim
+# syntax=docker/dockerfile:1.7
+#
+# Example gateway image: the tenant-facing proxy in front of DSH sandboxes.
+# The base image is digest-pinned in versions.env (GATEWAY_PYTHON_IMAGE) and
+# scripts/check-versions.sh verifies the ARG default below.
+#
+# Two stages on that base:
+#   build    installs the fully hash-pinned runtime dependencies into /venv as
+#            a dedicated non-root UID, so the runtime stage copies a venv that
+#            contains no root-owned files.
+#   runtime  copies /venv and the app, runs as UID 10000 with HOME=/tmp and no
+#            writable location of its own: usable with readOnlyRootFilesystem.
+ARG GATEWAY_PYTHON_IMAGE=docker.io/python:3.12-slim@sha256:aa943ce411423c7582288f18707ff66eddcbaeb510502d747a72aeb34f30d159
 
-# Read-only-rootfs friendly: no .pyc writes, no home directory writes.
+# ---------------------------------------------------------------------------
+# Build stage: hash-pinned virtualenv owned by the runtime identity.
+# ---------------------------------------------------------------------------
+FROM $GATEWAY_PYTHON_IMAGE AS build
+
+ARG APP_UID=10000
+ARG APP_GID=10000
+
+# No .pyc writes and no user cache dirs: the runtime image stays read-only.
 ENV PYTHONDONTWRITEBYTECODE=1 \
     PYTHONUNBUFFERED=1 \
+    PIP_NO_CACHE_DIR=1 \
     HOME=/tmp
 
-WORKDIR /app
+RUN groupadd --gid "$APP_GID" app \
+ && useradd --uid "$APP_UID" --gid "$APP_GID" --no-create-home \
+      --home-dir /tmp --shell /usr/sbin/nologin app \
+ && python -m venv /venv \
+ && chown -R "$APP_UID:$APP_GID" /venv
+
+WORKDIR /build
 COPY requirements.txt .
-RUN pip install --no-cache-dir -r requirements.txt
+
-COPY gateway.py .
+# Install as the unprivileged user so every file in /venv is owned by UID 10000.
+# --require-hashes makes pip reject any requirement without a matching hash:
+# the dependency set in requirements.txt is fully pinned and verified. Use the
+# venv's own pip: the system pip would user-install into $HOME instead.
+USER $APP_UID:$APP_GID
+RUN /venv/bin/pip install --no-cache-dir --require-hashes -r requirements.txt
+
+# ---------------------------------------------------------------------------
+# Runtime stage
+# ---------------------------------------------------------------------------
+FROM $GATEWAY_PYTHON_IMAGE AS runtime
+
+ARG APP_UID=10000
+ARG APP_GID=10000
+
+ENV PYTHONDONTWRITEBYTECODE=1 \
+    PYTHONUNBUFFERED=1 \
+    HOME=/tmp \
+    PATH="/venv/bin:$PATH"
+
+RUN groupadd --gid "$APP_GID" app \
+ && useradd --uid "$APP_UID" --gid "$APP_GID" --no-create-home \
+      --home-dir /tmp --shell /usr/sbin/nologin app
+
+WORKDIR /app
+
+# Dependencies come from the build stage: same interpreter, no build tools left
+# in the runtime image and nothing owned by root inside /venv.
+COPY --from=build --chown=$APP_UID:$APP_GID /venv /venv
+COPY --chown=$APP_UID:$APP_GID gateway.py .
 
 EXPOSE 8080
+
 # Run as a fixed non-root UID; HOME=/tmp keeps caches out of the image.
 USER 10000
 

examples/dsh-agents-as-a-service/gateway/README.md

@@ -10,11 +10,13 @@ It does four things:
    (only its SHA-256 is stored as a claim annotation), reports derived state,
    and deletes the claim (cascading the sandbox and PVC).
 2. **Browser sessions** — exchanges a user token for an HttpOnly session
-   cookie so the DSH UI works in a browser at `/u/<user>/`. Automation can
+   cookie whose value is only an opaque, server-side session id (user and
-   still use `Authorization: Bearer <token>`.
+   expiry stay in the gateway's memory) so the DSH UI works in a browser at
+   `/u/<user>/`. Automation can still use
+   `Authorization: Bearer <token>`, which never comes from the cookie.
 3. **Reverse proxy** — proxies HTTP (including SSE) and WebSocket traffic to
    the sandbox's DSH Web server on `:3080`, including DSH's own cookie
-   handshake.
+   handshake. Client-supplied forwarding/identity headers are stripped.
 4. **Optional SSO** — when `AUTH_PROXY_HEADER` is set, trusts the identity
    header an authenticating reverse proxy (for example oauth2-proxy) forwards,
    auto-provisions that user, and exposes `POST /recreate` for a clean restart.
@@ -63,10 +65,10 @@ token. A failed handshake returns `503` with `Retry-After: 10`.
 | Method | Path | Auth | Purpose |
 | --- | --- | --- | --- |
 | `GET` | `/healthz` | none | Liveness/readiness. Never touches the cluster. |
-| `GET` | `/` | none | Landing page with signup + token login forms. With SSO it auto-provisions the proxy-identified user and redirects to their workspace. |
+| `GET` | `/` | none | Landing page with signup + token login forms (plus an invite-code input when `SIGNUP_INVITE_CODE` is set). With SSO it auto-provisions the proxy-identified user and redirects to their workspace. |
-| `POST` | `/users` | none | Signup. JSON body `{"user": "<dns-1123 label>"}` or form field `user`. JSON returns `201` when Ready, `202` when accepted but still Waking; form returns `303` to `/u/<user>/`. Both set the session cookie. `409` if the user exists, `400` if invalid, `413` if the body is too large. |
+| `POST` | `/users` | none | Signup. JSON body `{"user": "<dns-1123 label>"}` or form field `user`; when `SIGNUP_INVITE_CODE` is set, an `invite` form field or `X-Signup-Invite` header must match it (`403` otherwise, checked before the user lookup). JSON returns `201` when Ready, `202` when accepted but still Waking; form returns `303` to `/u/<user>/`. Both set the session cookie. `409` if the user exists, `400` if invalid, `413` if the body is too large, `429` when the auth rate limit is hit. |
-| `POST` | `/login` | none | Form (`user`, `token`) returns `303` to `/u/<user>/`; JSON returns `200`. Sets the session cookie. `401` on a bad token, `404` for an unknown user. |
+| `POST` | `/login` | none | Form (`user`, `token`) returns `303` to `/u/<user>/`; JSON returns `200`. Sets the session cookie. `401` on a bad token **and** for an unknown user (no username enumeration). `429` when the auth rate limit is hit. Both auth routes reject a form post whose `Origin`/`Referer` contradicts `Host` (`403`) when the browser sent one. |
-| `POST` | `/logout` | none | Clears the session cookie and `303`s to `/`. |
+| `POST` | `/logout` | none | Revokes the server-side session, clears the cookie and `303`s to `/`. |
 | `POST` | `/recreate` | trusted proxy header | **SSO only.** Deletes the authenticated user's claim (cascading sandbox + PVC, so workspace data is wiped), waits out finalizers, provisions a fresh claim and `303`s to `/u/<user>/`. `401` without a valid identity header; cookie-authenticated calls must be same-origin. |
 | `GET` | `/users/{user}` | bearer or cookie | Derived state: `Provisioning`, `Waking`, `Ready`, `Suspending`, `Suspended`. |
 | `DELETE` | `/users/{user}` | bearer or cookie | Delete the claim (sandbox + PVC cascade). Cookie-auth mutations require a same-origin `Origin`/`Referer`. |
@@ -78,19 +80,49 @@ token. A failed handshake returns `503` with `Retry-After: 10`.
 
 * `Authorization: Bearer <token>` is checked with a timing-safe SHA-256
   comparison against the `aaas.example.com/token-sha256` claim annotation.
-* The browser session cookie is
+* The browser session cookie is **opaque**: its value is a random
-  `dsh_gw_session=<user>:<token>` (HttpOnly, SameSite=Lax, Path=/, optional
+  server-side session id; the user and expiry live in gateway memory
-  Secure). A session for user A never authorizes user B.
+  (`GatewayState.sessions`). A cookie can never be edited into another user's
+  credentials, a session id is not accepted as a bearer token, and a bearer
+  token never authorizes a different user. The cookie name defaults to
+  `__Host-dsh_gw_session` when `COOKIE_SECURE=true` (HTTPS) and to
+  `dsh_gw_session` for plain HTTP; attributes are HttpOnly, SameSite=Lax,
+  Path=/ and (with `COOKIE_SECURE`) Secure.
+* Sessions are revoked on `POST /logout`, on `DELETE /users/{user}`, on
+  `POST /recreate`, and when they expire (looked up on every request; the
+  sweeper also drops expired entries). `from_env()` refuses to start without
+  `COOKIE_SECURE=true` or the explicit `ALLOW_INSECURE_COOKIES=1` opt-out for
+  local HTTP.
 * Cookie-authenticated **mutations** (`POST`, `PUT`, `PATCH`, `DELETE`) and
   cookie-authenticated **WebSocket upgrades** require the request `Origin`
   (or `Referer` fallback) to match the `Host` header. Missing or mismatched
   cross-origin metadata is rejected (`403` HTTP, close code `4401` for WS).
+  Form signup/login additionally reject a cross-origin `Origin`/`Referer`
+  when the browser sent one, before the body is read.
+* `POST /users` and `POST /login` are rate limited per client:
+  `AUTH_RATE_LIMIT` attempts per `AUTH_RATE_WINDOW` seconds (default 30/60,
+  `0` disables). The client key is the rightmost `X-Forwarded-For` entry when
+  present (the address the last trusted proxy saw, not a spoofable leftmost
+  value), else the socket peer. Over-limit requests get `429` +
+  `Retry-After` before the body is read.
+* Proxy requests strip client-supplied forwarding/identity headers in both
+  HTTP and WebSocket paths: `Forwarded`, every `X-Forwarded-*`
+  (including `X-Forwarded-User`), every `X-Auth-Request-*`, and `X-Real-IP`.
+  The gateway sets its own `X-Forwarded-For/Host/Proto/Port` values from the
+  connection. `UPSTREAM_HEADER_ALLOWLIST` optionally narrows the forwarded
+  client headers further (comma-separated, case-insensitive); unset keeps the
+  denylist behavior, and the gateway's own values are always added.
 * The gateway's bearer token, the browser `Cookie` header and any `?token=`
   query parameter are never forwarded upstream. Only the cached `dsh-auth-*`
   cookie is injected.
 * Upstream `Set-Cookie` headers are dropped. `Location` headers that are
   absolute paths are rewritten under `/u/<user>/`, and any `token` query
   parameter is stripped.
+* Concurrency is capped per user: `MAX_IN_FLIGHT_PER_USER` proxied requests
+  (default 32) before the gateway answers `503` + `Retry-After` (HTTP) or
+  closes the WebSocket with `1011`. Messages received from DSH are limited to
+  `WS_MAX_MESSAGE_BYTES` (default 16 MiB); browser-to-DSH frames are bounded by
+  uvicorn's own WebSocket size limit.
 
 ### SSO (opt-in)
 
@@ -106,7 +138,8 @@ kubectl -n dsh-demo set env deploy/dsh-gateway AUTH_PROXY_HEADER=X-Forwarded-Use
 When set, the gateway treats a request carrying that header as authenticated as
 that user, provided the value is a valid DNS-1123 label; the header is never
 trusted when the variable is unset. The landing page then auto-provisions the
-user (creates their claim idempotently, mints a rotated session token) and
+user (creates their claim idempotently, rotates the claim token when a new
+session is needed and mints an opaque session cookie) and
 redirects to `/u/<user>/`, and `POST /recreate` becomes available for a clean
 restart. The base manifests leave it unset on purpose; the
 [SSO exposure variant](../manifests/exposure/gateway-api-sso/) documents how to
@@ -133,14 +166,19 @@ oauth2-proxy's egress to the gateway, DNS and public HTTPS.
 | --- | --- |
 | Unknown user / claim | `404` |
 | Missing or invalid credentials | `401` |
-| Cross-origin cookie mutation | `403` |
+| Unknown user on `/login` | `401` (same as a bad token; no username enumeration) |
+| Cross-origin cookie mutation / cross-origin form signup or login | `403` |
+| Auth route over `AUTH_RATE_LIMIT` | `429` + `Retry-After`, before the body is read |
 | Request body over `MAX_BODY_MB` | `413` |
 | Client aborts mid-body, before the response starts | `499` (`CLIENT_CLOSED_REQUEST`). Nothing is forwarded to DSH and nothing can be delivered; it is not an error, so no traceback is logged. Covers the body-reading control routes (`POST /users`, `POST /login`) as well as the proxy. |
 | Client aborts mid-stream (SSE, long response) | The response already started, so its upstream status stands (typically `200`); the stream simply ends. No traceback, and the in-flight slot is released as the relay unwinds. |
-| Sandbox not provisioned, wake timeout, handshake failure | `503` + `Retry-After: 10` |
+| Sandbox not provisioned, wake timeout, handshake failure | `503` + `Retry-After: 10`. The handshake error body is a fixed message: it never contains the launch token, the handshake URL or pod/credential details. |
+| User over `MAX_IN_FLIGHT_PER_USER` | `503` + `Retry-After` (HTTP); the existing in-flight requests are untouched |
 | Upstream connection/protocol failure | `502` |
 | WS auth failure (unknown user, bad token, cross-origin) | accept, then close `4401` |
+| WS per-user concurrency cap | accept, then close `1011` |
 | WS upstream/handshake failure | accept, then close `1011` |
+| WS message from DSH over `WS_MAX_MESSAGE_BYTES` | the upstream/relay closes the connection (websockets' message-too-big path) |
 
 A close code can only be delivered after the WebSocket upgrade is accepted;
 Starlette would turn an early close into an HTTP 403, which is why WS auth
@@ -166,17 +204,27 @@ can also be injected into `create_app` for tests.
 | `DSH_PORT` | `3080` | Upstream DSH port. |
 | `DSH_CONTAINER` | `dsh-web` | Container whose logs carry the launch token. |
 | `DSH_LOG_TAIL_LINES` | `2000` | How many log lines to scan for the launch token. |
-| `COOKIE_NAME` | `dsh_gw_session` | Browser session cookie name. |
+| `COOKIE_NAME` | `__Host-dsh_gw_session` when secure, else `dsh_gw_session` | Browser session cookie name. Only an opaque session id is stored in it. |
-| `COOKIE_SECURE` | `false` | Add `Secure` to the session cookie when served over TLS. |
+| `COOKIE_SECURE` | `false` | Add `Secure` to the session cookie. Required unless `ALLOW_INSECURE_COOKIES=1` is set for local HTTP. |
-| `COOKIE_MAX_AGE` | `604800` | Session cookie lifetime in seconds. |
+| `ALLOW_INSECURE_COOKIES` | `0` | Explicit opt-out for plain-HTTP demos. Without it, `Settings.from_env()` refuses to start unless `COOKIE_SECURE=true`. |
+| `COOKIE_MAX_AGE` | `604800` | Session lifetime in seconds (server-side expiry and cookie `Max-Age`). |
 | `MAX_BODY_MB` | `32` | Maximum buffered request body (and `413` threshold). |
 | `HTTP_TIMEOUT` | `300` | Upstream connect/read timeout in seconds. Proxied streams (SSE, long responses) keep the connect/write budget but have **no read timeout**, so an idle event stream is not cut every five minutes. |
-| `SWEEP_INTERVAL` | `15` | Seconds between idle sweeps. |
+| `SWEEP_INTERVAL` | `15` | Seconds between idle sweeps. Sweeps also prune expired sessions and rate buckets and orphaned per-user state. |
+| `SIGNUP_INVITE_CODE` | unset | When set, `POST /users` requires the matching `invite` form field or `X-Signup-Invite` header (timing-safe compare); the landing page then shows an invite input. Unset leaves signup open. |
+| `AUTH_RATE_LIMIT` | `30` | Attempts allowed per client per `AUTH_RATE_WINDOW` on `POST /users` and `POST /login`; `0` disables the limit. |
+| `AUTH_RATE_WINDOW` | `60` | Rate-limit window in seconds. |
+| `UPSTREAM_HEADER_ALLOWLIST` | unset | Comma-separated, case-insensitive allowlist of client headers to forward upstream. Unset keeps the denylist behavior; forwarding/identity headers are stripped in both modes. |
+| `MAX_IN_FLIGHT_PER_USER` | `32` | Concurrent proxied requests per user before `503`/WS `1011`. `0` disables the cap. |
+| `WS_MAX_MESSAGE_BYTES` | `16777216` | Largest WebSocket message (16 MiB) accepted from DSH. Browser-to-DSH frames are bounded by uvicorn's own limit. |
 | `AUTH_PROXY_HEADER` | unset | Opt-in SSO: name of the trusted identity header set by an authenticating reverse proxy (e.g. `X-Forwarded-User`). Unset disables SSO and the header is never trusted. Enable only when the Service is reachable exclusively through that proxy (see [SSO](#sso-opt-in)). |
 
 The shipped `manifests/50-gateway.yaml` sets `IDLE_TIMEOUT=360` and
 `WAKE_TIMEOUT=240` for the demo; the e2e script overrides them to 60/120 so the
-smoke test does not wait minutes for the sweeper.
+smoke test does not wait minutes for the sweeper. It also sets
+`COOKIE_SECURE=false` together with the explicit `ALLOW_INSECURE_COOKIES=1`
+acknowledgement because the demo is reached over plain HTTP (a `Secure` cookie
+would never be sent). HTTPS deployments must set `COOKIE_SECURE=true`.
 
 ### Required RBAC
 
@@ -197,8 +245,10 @@ python -m pip install -r requirements-dev.txt
 python -m pytest -q
 python -m ruff check .
 
-# Uvicorn factory (loads in-cluster credentials only on the first claim call)
+# Uvicorn factory (loads in-cluster credentials only on the first claim call).
-uvicorn gateway:create_app --factory --host 0.0.0.0 --port 8080
+# from_env() insists on an explicit acknowledgement for plain HTTP; behind TLS
+# set COOKIE_SECURE=true instead.
+ALLOW_INSECURE_COOKIES=1 uvicorn gateway:create_app --factory --host 0.0.0.0 --port 8080
 ```
 
 Container image, from the repository root:
@@ -226,18 +276,27 @@ uvicorn's access log so bearer tokens in URLs are not logged.
   Log rotation, a very chatty container, or DSH changing its startup message
   breaks the handshake. Prefer a first-class token/credential API when DSH
   offers one.
-* **Single replica, in-memory state.** The handshake cookie cache, idle
+* **Single replica, in-memory state.** The handshake cookie cache, the opaque
-  activity clocks and in-flight counters live in one process. Running more
+  session table, idle activity clocks, in-flight counters and rate-limit
-  than one replica would need shared state (or sticky routing), otherwise each
+  buckets live in one process. Running more than one replica would need shared
-  replica handshakes independently and the sweeper may race another replica.
+  state (or sticky routing), otherwise each replica handshakes independently,
+  the sweeper may race another replica, and a session/rate budget is only seen
+  by the replica that created it.
+* **Sessions die with the process.** An opaque session id is valid only in the
+  process that minted it and expires after `COOKIE_MAX_AGE`; a restart logs
+  every browser out (tokens are unaffected).
 * **In-memory token cache has no TTL.** It is keyed by pod UID, so pod
   restarts invalidate it naturally; otherwise entries survive until the pod or
   claim is deleted.
-* **No TLS termination.** Run behind an ingress/load balancer; set
+* **No TLS termination.** Run behind an ingress/load balancer and set
-  `COOKIE_SECURE=true` there.
+  `COOKIE_SECURE=true`. `Settings.from_env()` refuses to start without it
+  unless `ALLOW_INSECURE_COOKIES=1` explicitly acknowledges plain-HTTP
+  sessions.
 * **Origin-based CSRF protection only.** Cookie-auth mutations require a
-  same-origin `Origin`/`Referer`; there is no per-form CSRF token, rate
+  same-origin `Origin`/`Referer`, and form signup/login reject a contradicting
-  limiting or login throttling.
+  origin when the browser sends one; there is no per-form CSRF token. Auth
+  routes have per-client rate limiting and login throttling, but the budget is
+  in-process (per replica) and keyed by the rightmost `X-Forwarded-For` value.
 * **HTTP request bodies are buffered** up to `MAX_BODY_MB`; uploads are not
   streamed. Responses (including SSE) are streamed.
 * **Upstream cookies are not forwarded.** DSH cannot rotate its own

examples/dsh-agents-as-a-service/gateway/gateway.py

@@ -7,9 +7,12 @@ single teaching-friendly module with three jobs:
   (only its SHA-256 is stored, as a claim annotation), report derived state,
   and delete the claim (which cascades the sandbox and its PVC).
 * **Browser sessions** -- exchange a user token for an HttpOnly session cookie
-  so the DSH UI can be opened in a browser at ``/u/<user>/``.  Browser requests
+  whose value is an opaque, server-side session id (the user and expiry live in
-  authenticate with that cookie; automation can keep using
+  memory) so the DSH UI can be opened in a browser at ``/u/<user>/``.  Browser
-  ``Authorization: Bearer <token>``.
+  requests authenticate with that cookie; automation can keep using
+  ``Authorization: Bearer <token>``.  Sessions are revoked on logout, user
+  deletion, recreate and expiry, and a cookie is never accepted as a bearer
+  token (nor the other way around).
 * **Reverse proxy** -- HTTP (including SSE) and WebSocket proxying to the
   sandbox's DSH Web server on ``:3080``.  DSH itself is cookie-gated: the
   gateway scrapes the launch token from the pod logs, performs the ``?token=``
@@ -38,6 +41,7 @@ import contextlib
 import hashlib
 import html
 import json
+import math
 import os
 import re
 import secrets
@@ -121,6 +125,19 @@ OWNED_REQUEST_HEADERS = HOP_BY_HOP | {
     "x-real-ip",
 }
 
+# Default session cookie names.  ``__Host-`` is only legal over HTTPS and pins
+# the cookie to Path=/ with no Domain attribute; the insecure default keeps the
+# example usable over plain HTTP behind a port-forward.
+DEFAULT_COOKIE_NAME = "dsh_gw_session"
+SECURE_COOKIE_NAME = "__Host-dsh_gw_session"
+
+# Header prefixes a client must never be able to smuggle upstream.  The gateway
+# derives its own X-Forwarded-* values from the connection; anything the browser
+# sends with these names is attacker-controlled and is dropped in both the HTTP
+# and WebSocket proxy paths.
+FORWARDING_HEADER_PREFIXES = ("x-forwarded-", "x-auth-request-")
+FORWARDING_HEADERS = frozenset({"forwarded"})
+
 _DSH_WEB_LINE = re.compile(r"dsh web:\s+(?P<url>https?://\S+)")
 
 
@@ -249,6 +266,33 @@ def same_origin(headers) -> bool:
     return False
 
 
+def strip_forwarding_header(name: str) -> bool:
+    """True for client-supplied identity/forwarding headers we never forward.
+
+    ``X-Forwarded-User`` and ``X-Auth-Request-*`` carry identities an
+    authenticating proxy or the gateway itself owns; ``Forwarded`` /
+    ``X-Forwarded-*`` describe the hop chain.  Forwarding any of them lets a
+    browser spoof its origin or a trusted SSO user upstream.
+    """
+    lowered = name.lower()
+    return lowered in FORWARDING_HEADERS or lowered.startswith(FORWARDING_HEADER_PREFIXES)
+
+
+def client_identity(headers, client) -> str:
+    """The rate-limit bucket for a request.
+
+    The rightmost ``X-Forwarded-For`` entry is the address the last trusted
+    proxy saw (each proxy appends), so it cannot be spoofed by prepending
+    arbitrary values.  Without the header fall back to the socket peer.
+    """
+    forwarded = (headers.get("x-forwarded-for") or "").strip()
+    if forwarded:
+        parts = [part.strip() for part in forwarded.split(",") if part.strip()]
+        if parts:
+            return parts[-1]
+    return getattr(client, "host", None) or "unknown"
+
+
 def rewrite_location(location: str, user: str) -> str:
     """Prefix absolute-path redirects so the browser stays under ``/u/<user>/``."""
     if not location.startswith("/") or location.startswith("//"):
@@ -306,6 +350,14 @@ def _env_float(name: str, default: float) -> float:
         return default
 
 
+def _env_allowlist(name: str) -> frozenset[str] | None:
+    """Parse a comma-separated header allowlist; unset means "denylist mode"."""
+    raw = os.environ.get(name)
+    if raw is None:
+        return None
+    return frozenset(part.strip().lower() for part in raw.split(",") if part.strip())
+
+
 # --- Settings --------------------------------------------------------------
 
 
@@ -325,7 +377,7 @@ class Settings:
     dsh_port: int = 3080
     dsh_container: str = "dsh-web"
     dsh_log_tail_lines: int = 2000
-    cookie_name: str = "dsh_gw_session"
+    cookie_name: str = DEFAULT_COOKIE_NAME
     cookie_secure: bool = False
     cookie_max_age: int = 7 * 24 * 60 * 60
     max_body_bytes: int = 32 * 1024 * 1024
@@ -339,9 +391,36 @@ class Settings:
     # valid user in this header are treated as authenticated (SSO); unset (None)
     # disables SSO entirely and the header is never trusted.
     auth_proxy_header: str | None = None
+    # Abuse controls. AUTH_RATE_LIMIT applies to the unauthenticated auth routes
+    # (POST /users and POST /login) per client and window; 0 disables it.
+    auth_rate_limit: int = 30
+    auth_rate_window: int = 60
+    # When set, signup requires this invite code (form field ``invite`` or the
+    # ``X-Signup-Invite`` header). None keeps signup open, as in the demo.
+    signup_invite_code: str | None = None
+    # Optional allowlist of client request headers to forward upstream. None
+    # keeps the default denylist behavior; a set (possibly empty) forwards only
+    # the named headers (plus the gateway's own X-Forwarded-* values).
+    upstream_header_allowlist: frozenset[str] | None = None
+    # Concurrent proxied requests per user before 503/1011 is returned.
+    max_in_flight_per_user: int = 32
+    # Largest WebSocket message accepted from DSH, in bytes. Browser-to-DSH
+    # frames are bounded by the ASGI server's own WebSocket limit.
+    ws_max_message_bytes: int = 16 * 1024 * 1024
 
     @classmethod
     def from_env(cls) -> Settings:
+        cookie_secure = _env_bool("COOKIE_SECURE", False)
+        allow_insecure = _env_bool("ALLOW_INSECURE_COOKIES", False)
+        if not cookie_secure and not allow_insecure:
+            raise RuntimeError(
+                "refusing to start with an insecure session cookie: set "
+                "COOKIE_SECURE=true behind TLS, or ALLOW_INSECURE_COOKIES=1 "
+                "for a local plain-HTTP demo"
+            )
+        cookie_name = os.environ.get("COOKIE_NAME") or (
+            SECURE_COOKIE_NAME if cookie_secure else DEFAULT_COOKIE_NAME
+        )
         return cls(
             namespace=os.environ.get("NAMESPACE", "dsh-demo"),
             pool=os.environ.get("POOL", "dsh-pool"),
@@ -350,13 +429,19 @@ class Settings:
             dsh_port=_env_int("DSH_PORT", 3080),
             dsh_container=os.environ.get("DSH_CONTAINER", "dsh-web"),
             dsh_log_tail_lines=_env_int("DSH_LOG_TAIL_LINES", 2000),
-            cookie_name=os.environ.get("COOKIE_NAME", "dsh_gw_session"),
+            cookie_name=cookie_name,
-            cookie_secure=_env_bool("COOKIE_SECURE", False),
+            cookie_secure=cookie_secure,
             cookie_max_age=_env_int("COOKIE_MAX_AGE", 7 * 24 * 60 * 60),
             max_body_bytes=_env_int("MAX_BODY_MB", 32) * 1024 * 1024,
             http_timeout=_env_float("HTTP_TIMEOUT", 300.0),
             sweep_interval=_env_float("SWEEP_INTERVAL", 15.0),
             auth_proxy_header=os.environ.get("AUTH_PROXY_HEADER") or None,
+            auth_rate_limit=_env_int("AUTH_RATE_LIMIT", 30),
+            auth_rate_window=_env_int("AUTH_RATE_WINDOW", 60),
+            signup_invite_code=os.environ.get("SIGNUP_INVITE_CODE") or None,
+            upstream_header_allowlist=_env_allowlist("UPSTREAM_HEADER_ALLOWLIST"),
+            max_in_flight_per_user=_env_int("MAX_IN_FLIGHT_PER_USER", 32),
+            ws_max_message_bytes=_env_int("WS_MAX_MESSAGE_BYTES", 16 * 1024 * 1024),
         )
 
 
@@ -546,6 +631,19 @@ class Kubernetes:
 # --- Gateway ---------------------------------------------------------------
 
 
+@dataclass(frozen=True)
+class Session:
+    """A browser session stored server-side, keyed by an opaque random id.
+
+    The cookie only carries the id; the user and the expiry stay in memory, so
+    a cookie can never be edited into another user's credentials and a stolen
+    token is not recoverable from the browser.
+    """
+
+    user: str
+    expires_at: float
+
+
 @dataclass
 class GatewayState:
     """In-memory, per-process state (single replica by design)."""
@@ -555,6 +653,10 @@ class GatewayState:
     maintenance: dict[str, bool] = field(default_factory=dict)
     # (user, pod UID, browser Host) -> "dsh-auth-a=...; dsh-auth-b=..."
     handshake: dict[tuple[str, str, str], str] = field(default_factory=dict)
+    # Opaque session id -> server-side session (user + expiry).
+    sessions: dict[str, Session] = field(default_factory=dict)
+    # Auth rate limiting: client -> (window start, attempts in window).
+    auth_rate: dict[str, tuple[float, int]] = field(default_factory=dict)
     lock: asyncio.Lock = field(default_factory=asyncio.Lock)
 
 
@@ -576,17 +678,40 @@ class Gateway:
 
     # -- credentials -------------------------------------------------------
 
+    def session_for(self, sid: str | None) -> Session | None:
+        """Look up a live session, dropping it when it has expired."""
+        if not sid:
+            return None
+        session = self.state.sessions.get(sid)
+        if session is None:
+            return None
+        if session.expires_at <= time.time():
+            self.state.sessions.pop(sid, None)
+            return None
+        return session
+
+    def revoke_session(self, sid: str | None) -> None:
+        if sid:
+            self.state.sessions.pop(sid, None)
+
+    def revoke_sessions(self, user: str) -> None:
+        for sid in [key for key, session in self.state.sessions.items() if session.user == user]:
+            self.state.sessions.pop(sid, None)
+
     def credentials(self, headers, cookies) -> tuple[str | None, str | None]:
-        """Return ``(token, cookie_user)``; bearer wins over the session cookie."""
+        """Return ``(token, session_user)``; bearer wins over the session cookie.
+
+        A bearer token is never resolved from a cookie and a session id is never
+        accepted as a bearer token.  An unknown or expired session is treated as
+        anonymous (and the expired entry is dropped).
+        """
         auth = headers.get("authorization", "")
         if auth.lower().startswith("bearer "):
             return auth[7:].strip(), None
-        raw = cookies.get(self.settings.cookie_name)
+        session = self.session_for(cookies.get(self.settings.cookie_name))
-        if raw:
+        if session is None:
-            user, sep, token = raw.partition(":")
-            if sep and user and token:
-                return token, user
             return None, None
+        return None, session.user
 
     def remote_user(self, headers) -> str | None:
         """The user asserted by a trusted reverse proxy, when SSO is enabled.
@@ -605,30 +730,36 @@ class Gateway:
         self,
         claim: dict,
         token: str | None,
-        cookie_user: str | None,
+        session_user: str | None,
         user: str,
         remote: str | None = None,
     ) -> bool:
         if remote == user:
             return True  # identity asserted by the authenticating proxy
-        if cookie_user is not None and cookie_user != user:
+        if session_user is not None:
-            return False  # a session for another user never authorizes this one
+            return session_user == user  # server-side session bound to this user
         return token_matches(claim, token)
 
     async def _sso_session(self, remote: str, headers, cookies, response: Response) -> dict | None:
-        """Provision ``remote`` idempotently and mint/refresh a session token.
+        """Provision ``remote`` idempotently and mint/refresh a session.
 
         The authenticating proxy has already verified ``remote``, so it is
         trusted. A brand-new user is provisioned (claim created, token minted);
-        an existing user whose session cookie is missing or no longer matches
+        an existing user whose session cookie is missing, foreign or no longer
-        gets a rotated token so a fresh cookie can be issued. A still-valid
+        matches gets a rotated token so a fresh cookie can be issued. A still-valid
-        session is reused untouched. Provisioning is non-blocking: the sandbox
+        session for the same user is reused untouched. Provisioning is
-        is awaited by the proxy path (``_resolve_sandbox``), so the landing page
+        non-blocking: the sandbox is awaited by the proxy path
-        can report "Provisioning" instead of stalling for ``WAKE_TIMEOUT``.
+        (``_resolve_sandbox``), so the landing page can report "Provisioning"
+        instead of stalling for ``WAKE_TIMEOUT``.
         """
         claim = await self.k8s.get_claim(remote)
-        token, cookie_user = self.credentials(headers, cookies)
+        sid = cookies.get(self.settings.cookie_name)
-        if claim is not None and cookie_user == remote and token_matches(claim, token):
+        session = self.session_for(sid)
+        if session is not None:
+            if session.user != remote:
+                # A session for another identity never authorizes this user.
+                self.revoke_session(sid)
+            elif claim is not None:
                 return claim
         token = secrets.token_urlsafe(32)
         token_hash = hashlib.sha256(token.encode()).hexdigest()
@@ -645,7 +776,7 @@ class Gateway:
         else:
             await self.k8s.patch_token(remote, token_hash)
             await self._touch(remote)
-        self.set_session(response, remote, token)
+        self.set_session(response, remote)
         return await self.k8s.get_claim(remote) if is_new else claim
 
     @staticmethod
@@ -656,16 +787,73 @@ class Gateway:
             and not same_origin(headers)
         )
 
-    def set_session(self, response: Response, user: str, token: str) -> None:
+    def set_session(self, response: Response, user: str) -> str:
+        """Mint an opaque server-side session and set the browser cookie."""
+        sid = secrets.token_urlsafe(32)
+        self.state.sessions[sid] = Session(
+            user=user,
+            expires_at=time.time() + self.settings.cookie_max_age,
+        )
         response.set_cookie(
             self.settings.cookie_name,
-            f"{user}:{token}",
+            sid,
             max_age=self.settings.cookie_max_age,
             path="/",
             httponly=True,
             samesite="lax",
             secure=self.settings.cookie_secure,
         )
+        return sid
+
+    # -- abuse controls ----------------------------------------------------
+
+    def _rate_limit(self, request: Request) -> Response | None:
+        """Return a 429 response when this client is over the auth budget."""
+        limit = self.settings.auth_rate_limit
+        if limit <= 0:
+            return None
+        window = max(1, self.settings.auth_rate_window)
+        key = client_identity(request.headers, request.client)
+        now = time.time()
+        bucket = self.state.auth_rate.get(key)
+        if bucket is None or now - bucket[0] >= window:
+            self.state.auth_rate[key] = (now, 1)
+            return None
+        start, count = bucket
+        if count >= limit:
+            retry_after = max(1, math.ceil(start + window - now))
+            return self._error(
+                429,
+                "too many authentication attempts, retry shortly",
+                {"Retry-After": str(retry_after)},
+            )
+        self.state.auth_rate[key] = (start, count + 1)
+        return None
+
+    def _invite_allowed(self, request: Request, payload: dict) -> bool:
+        """Check the signup invite code, when one is configured."""
+        expected = self.settings.signup_invite_code
+        if expected is None:
+            return True
+        provided = payload.get("invite")
+        if not isinstance(provided, str) or not provided:
+            provided = request.headers.get("x-signup-invite", "")
+        if not isinstance(provided, str) or not provided:
+            return False
+        return secrets.compare_digest(provided.encode("utf-8"), expected.encode("utf-8"))
+
+    def _form_cross_origin(self, request: Request) -> bool:
+        """Reject a form signup/login whose Origin/Referer contradicts Host.
+
+        Only checked when the browser actually sent one: non-browser clients
+        (automation, tests) commonly omit both headers and must keep working.
+        """
+        if not self._wants_form(request):
+            return False
+        headers = request.headers
+        if not (headers.get("origin") or headers.get("referer")):
+            return False
+        return not same_origin(headers)
 
     # -- activity / maintenance -------------------------------------------
 
@@ -674,12 +862,21 @@ class Gateway:
             self.state.last_activity[user] = time.time()
 
     async def _acquire(self, user: str) -> bool:
-        """Reserve an in-flight slot, waiting out a concurrent suspend."""
+        """Reserve an in-flight slot, waiting out a concurrent suspend.
+
+        Returns False when the user already has ``MAX_IN_FLIGHT_PER_USER``
+        requests in flight (an abuse guard, not a transient error) or when a
+        suspend does not finish within ``WAKE_TIMEOUT``.
+        """
         deadline = time.monotonic() + self.settings.wake_timeout
+        cap = self.settings.max_in_flight_per_user
         while True:
             async with self.state.lock:
                 if not self.state.maintenance.get(user):
-                    self.state.in_flight[user] = self.state.in_flight.get(user, 0) + 1
+                    current = self.state.in_flight.get(user, 0)
+                    if cap > 0 and current >= cap:
+                        return False
+                    self.state.in_flight[user] = current + 1
                     self.state.last_activity[user] = time.time()
                     return True
             if time.monotonic() > deadline:
@@ -759,14 +956,19 @@ class Gateway:
         host: str,
         force: bool = False,
     ) -> tuple[str, tuple[str, str, str], bool]:
-        """Return ``(cookie, cache_key, was_cached)``, handshaking on a miss."""
+        """Return ``(cookie, cache_key, was_cached)``, handshaking on a miss.
+
+        Every failure raises ``HandshakeError`` with a fixed, credential-free
+        message: the exception reaches the browser in the 503 body, so it must
+        never carry the launch token, the handshake URL or pod details.
+        """
         pod_name = self._pod_name(sandbox)
         try:
             pod = await self.k8s.get_pod(pod_name)
         except ApiException as exc:
-            raise HandshakeError(f"could not read pod {pod_name}: {exc}") from exc
+            raise HandshakeError("could not read the DSH handshake pod") from exc
         if pod is None:
-            raise HandshakeError(f"pod {pod_name} not found")
+            raise HandshakeError("the DSH handshake pod is not available")
         uid = (pod.get("metadata") or {}).get("uid") or pod_name
         key = (user, uid, host)
         if not force:
@@ -780,7 +982,7 @@ class Gateway:
                 self.settings.dsh_log_tail_lines,
             )
         except ApiException as exc:
-            raise HandshakeError(f"could not read logs for {pod_name}: {exc}") from exc
+            raise HandshakeError("could not read the pod logs for the handshake") from exc
         launch_token = parse_dsh_launch_token(logs)
         if not launch_token:
             raise HandshakeError("DSH launch token not found in pod logs")
@@ -798,12 +1000,12 @@ class Gateway:
                 timeout=self.settings.http_timeout,
             )
         except httpx.HTTPError as exc:
-            raise HandshakeError(f"DSH handshake failed: {exc}") from exc
+            raise HandshakeError("the DSH handshake request failed") from exc
         if response.status_code >= 400:
-            raise HandshakeError(f"DSH handshake returned {response.status_code}")
+            raise HandshakeError("the DSH handshake returned an error status")
         cookie = extract_dsh_cookies(response.headers.get_list("set-cookie"))
         if not cookie:
-            raise HandshakeError("DSH handshake set no dsh-auth cookie")
+            raise HandshakeError("the DSH handshake set no auth cookie")
         self.state.handshake[key] = cookie
         return cookie, key, False
 
@@ -879,9 +1081,9 @@ class Gateway:
             if "set-cookie" in response.headers:
                 page.headers["set-cookie"] = response.headers["set-cookie"]
             return page
-        token, user = self.credentials(request.headers, request.cookies)
+        _token, user = self.credentials(request.headers, request.cookies)
         session = ""
-        if user and token:
+        if user:
             safe_user = html.escape(user)
             session = (
                 f'<p class="session">Signed in as <strong>{safe_user}</strong>. '
@@ -889,6 +1091,11 @@ class Gateway:
                 '<form method="post" action="/logout">'
                 '<button type="submit">Sign out</button></form>'
             )
+        invite_input = (
+            '<input name="invite" type="password" placeholder="invite code" required>'
+            if self.settings.signup_invite_code is not None
+            else ""
+        )
         body = f"""<!doctype html>
 <html lang="en">
 <head>
@@ -911,6 +1118,7 @@ class Gateway:
 <h2>Create a sandbox</h2>
 <form method="post" action="/users">
   <input name="user" placeholder="username (dns-1123 label)" required>
+  {invite_input}
   <button type="submit">Create</button>
 </form>
 </section>
@@ -970,11 +1178,18 @@ against the JSON API. The browser session is an HttpOnly cookie.</p>
     # -- users -------------------------------------------------------------
 
     async def signup(self, request: Request) -> Response:
+        limited = self._rate_limit(request)
+        if limited is not None:
+            return limited
+        if self._form_cross_origin(request):
+            return self._error(403, "cross-origin request rejected")
         wants_form = self._wants_form(request)
         try:
             payload = await self._read_payload(request)
         except BodyTooLarge:
             return self._error(413, "request body too large")
+        if not self._invite_allowed(request, payload):
+            return self._error(403, "invalid or missing invite code")
         user = payload.get("user", "")
         if not valid_user(user):
             return self._error(400, "body must be {'user': '<dns-1123 label>'}")
@@ -992,16 +1207,21 @@ against the JSON API. The browser session is an HttpOnly cookie.</p>
         sandbox_name = (sandbox or {}).get("metadata", {}).get("name")
         if wants_form:
             response = RedirectResponse(f"/u/{user}/", status_code=303)
-            self.set_session(response, user, token)
+            self.set_session(response, user)
             return response
         response = JSONResponse(
             {"user": user, "token": token, "state": state, "sandbox": sandbox_name},
             status_code=201 if state == "Ready" else 202,
         )
-        self.set_session(response, user, token)
+        self.set_session(response, user)
         return response
 
     async def login(self, request: Request) -> Response:
+        limited = self._rate_limit(request)
+        if limited is not None:
+            return limited
+        if self._form_cross_origin(request):
+            return self._error(403, "cross-origin request rejected")
         wants_form = self._wants_form(request)
         try:
             payload = await self._read_payload(request)
@@ -1012,21 +1232,29 @@ against the JSON API. The browser session is an HttpOnly cookie.</p>
         if not isinstance(user, str) or not isinstance(token, str):
             return self._error(400, "user and token are required")
         claim = await self.k8s.get_claim(user)
-        if claim is None:
+        # An unknown user is indistinguishable from a bad token to the client:
-            return self._error(404, "not found")
+        # never reveal which usernames exist.
-        if not token_matches(claim, token):
+        if claim is None or not token_matches(claim, token):
             return self._error(401, "unauthorized")
         await self._touch(user)
         if wants_form:
             response = RedirectResponse(f"/u/{user}/", status_code=303)
         else:
             response = JSONResponse({"user": user, "state": "ok"})
-        self.set_session(response, user, token)
+        self.set_session(response, user)
         return response
 
     async def logout(self, request: Request) -> Response:
+        self.revoke_session(request.cookies.get(self.settings.cookie_name))
         response = RedirectResponse("/", status_code=303)
-        response.delete_cookie(self.settings.cookie_name, path="/")
+        # Match the attributes the cookie was set with: a __Host- cookie
+        # deletion that lacks Secure is rejected by browsers, leaving a stale
+        # (though already revoked) cookie behind.
+        response.delete_cookie(
+            self.settings.cookie_name,
+            path="/",
+            secure=self.settings.cookie_secure,
+        )
         return response
 
     async def get_user(self, request: Request) -> Response:
@@ -1061,6 +1289,7 @@ against the JSON API. The browser session is an HttpOnly cookie.</p>
         if self._mutation_from_cookie(request.headers, "DELETE", cookie_user):
             return self._error(403, "cross-origin request rejected")
         await self.k8s.delete_claim(user)
+        self.revoke_sessions(user)
         self._clear_handshake(user)
         async with self.state.lock:
             self.state.last_activity.pop(user, None)
@@ -1084,6 +1313,7 @@ against the JSON API. The browser session is an HttpOnly cookie.</p>
         if self._mutation_from_cookie(request.headers, "POST", cookie_user):
             return self._error(403, "cross-origin request rejected")
         await self.k8s.delete_claim(remote)
+        self.revoke_sessions(remote)
         self._clear_handshake(remote)
         async with self.state.lock:
             self.state.last_activity.pop(remote, None)
@@ -1111,7 +1341,7 @@ against the JSON API. The browser session is an HttpOnly cookie.</p>
                 return RedirectResponse("/", status_code=303)
             return self._error(404, "unknown user")
         token, cookie_user = self.credentials(request.headers, request.cookies)
-        if remote == user and not (cookie_user == user and token_matches(claim, token)):
+        if remote == user and cookie_user != user:
             # SSO user without a valid session cookie: bootstrap, then continue.
             return RedirectResponse("/", status_code=303)
         if not self._authorized(claim, token, cookie_user, user, remote):
@@ -1171,11 +1401,17 @@ against the JSON API. The browser session is an HttpOnly cookie.</p>
         if query:
             url = f"{url}?{query}"
 
-        headers = {
+        headers = {}
-            key: value
+        allowlist = self.settings.upstream_header_allowlist
-            for key, value in request.headers.items()
+        for key, value in request.headers.items():
-            if key.lower() not in OWNED_REQUEST_HEADERS and key.lower() != "content-length"
+            lowered = key.lower()
-        }
+            if lowered in OWNED_REQUEST_HEADERS or lowered == "content-length":
+                continue
+            if strip_forwarding_header(lowered):
+                continue  # client-supplied identity/hop-chain headers are spoofable
+            if allowlist is not None and lowered not in allowlist:
+                continue
+            headers[key] = value
         host = request.headers.get("host", "")
         headers["host"] = host
         headers["cookie"] = cookie  # only the cached DSH auth cookie
@@ -1309,13 +1545,19 @@ against the JSON API. The browser session is an HttpOnly cookie.</p>
                 query = filtered_query(websocket.url.query)
                 if query:
                     url = f"{url}?{query}"
-                headers = {
+                headers = {}
-                    key: value
+                allowlist = self.settings.upstream_header_allowlist
-                    for key, value in websocket.headers.items()
+                for key, value in websocket.headers.items():
-                    if key.lower() not in OWNED_REQUEST_HEADERS
+                    lowered = key.lower()
-                    and key.lower() != "origin"
+                    if lowered in OWNED_REQUEST_HEADERS or lowered == "origin":
-                    and not key.lower().startswith("sec-websocket-")
+                        continue
-                }
+                    if lowered.startswith("sec-websocket-"):
+                        continue
+                    if strip_forwarding_header(lowered):
+                        continue  # client-supplied identity/hop-chain headers
+                    if allowlist is not None and lowered not in allowlist:
+                        continue
+                    headers[key] = value
                 headers["cookie"] = cookie
                 headers["x-forwarded-host"] = host
                 headers["x-forwarded-proto"] = websocket.url.scheme
@@ -1331,7 +1573,7 @@ against the JSON API. The browser session is an HttpOnly cookie.</p>
                     additional_headers=headers,
                     subprotocols=subprotocols or None,
                     open_timeout=self.settings.wake_timeout,
-                    max_size=None,
+                    max_size=self.settings.ws_max_message_bytes,
                     proxy=None,
                 )
                 upstream = await upstream_cm.__aenter__()
@@ -1391,8 +1633,41 @@ against the JSON API. The browser session is an HttpOnly cookie.</p>
 
     # -- idle sweeper ------------------------------------------------------
 
+    def _prune_state(self, claims: list[dict]) -> None:
+        """Drop state that can no longer be reached.
+
+        Sessions and activity clocks for a user whose claim is gone, expired
+        sessions and expired rate-limit buckets would otherwise accumulate for
+        the lifetime of the process.  In-flight counters are only pruned at
+        zero, and a user with work in flight is always preserved.
+        """
+        now = time.time()
+        present = set()
+        for claim in claims:
+            name = (claim.get("metadata") or {}).get("name") or ""
+            if name.startswith("dsh-"):
+                present.add(name[len("dsh-") :])
+        for user in [user for user in self.state.last_activity if user not in present]:
+            self.state.last_activity.pop(user, None)
+        for user, count in list(self.state.in_flight.items()):
+            if user not in present and count == 0:
+                self.state.in_flight.pop(user, None)
+        for user, flag in list(self.state.maintenance.items()):
+            if user not in present and not flag:
+                self.state.maintenance.pop(user, None)
+        for key in [key for key in self.state.handshake if key[0] not in present]:
+            self.state.handshake.pop(key, None)
+        for sid, session in list(self.state.sessions.items()):
+            if session.user not in present or session.expires_at <= now:
+                self.state.sessions.pop(sid, None)
+        window = max(1, self.settings.auth_rate_window)
+        for key, (start, _count) in list(self.state.auth_rate.items()):
+            if now - start >= window:
+                self.state.auth_rate.pop(key, None)
+
     async def sweep_once(self) -> None:
         claims = await self.k8s.list_claims()
+        self._prune_state(claims)
         for claim in claims:
             # Only suspend claims this gateway created.  Everything else in
             # the namespace (resource-layer claims from the README walkthrough,

examples/dsh-agents-as-a-service/gateway/test_gateway.py

@@ -18,10 +18,12 @@ from types import SimpleNamespace
 import httpx
 import pytest
 from kubernetes.client.exceptions import ApiException
+from starlette.responses import Response
 from starlette.testclient import TestClient
 from starlette.websockets import WebSocketDisconnect
 
 from gateway import (
+    Session,
     Settings,
     UserExists,
     claim_name,
@@ -219,6 +221,39 @@ def add_user(k8s, user="alice", token=TOKEN, ready=True, pod_name=None, suffix="
     return sandbox_name, pod_name
 
 
+# --- browser sessions ------------------------------------------------------
+#
+# A browser session is an opaque server-side id.  Tests must never forge a
+# cookie (or a bearer token); they mint a real session through the gateway so
+# the production lookup path is exercised.
+
+
+def mint_session(env, user="alice") -> tuple[str, str]:
+    """Mint a server-side session for ``user``; returns ``(cookie_name, sid)``."""
+    response = Response()
+    sid = env.gateway.set_session(response, user)
+    return env.gateway.settings.cookie_name, sid
+
+
+def session_dict(env, user="alice") -> dict:
+    name, sid = mint_session(env, user)
+    return {name: sid}
+
+
+def session_cookie(env, user="alice") -> str:
+    name, sid = mint_session(env, user)
+    return f"{name}={sid}"
+
+
+def response_session_user(env, response) -> str:
+    """The user of the server-side session a response just set."""
+    cookie = response.headers["set-cookie"]
+    value = cookie.split(";", 1)[0].split("=", 1)[1]
+    session = env.gateway.state.sessions.get(value)
+    assert session is not None, "response did not set a server-side session"
+    return session.user
+
+
 @pytest.fixture
 def env():
     settings = Settings(
@@ -463,6 +498,12 @@ def test_settings_from_env(monkeypatch):
     monkeypatch.setenv("MAX_BODY_MB", "2")
     monkeypatch.setenv("HTTP_TIMEOUT", "12.5")
     monkeypatch.setenv("AUTH_PROXY_HEADER", "X-Forwarded-User")
+    monkeypatch.setenv("AUTH_RATE_LIMIT", "5")
+    monkeypatch.setenv("AUTH_RATE_WINDOW", "30")
+    monkeypatch.setenv("SIGNUP_INVITE_CODE", "invite-x")
+    monkeypatch.setenv("UPSTREAM_HEADER_ALLOWLIST", "X-Custom, Accept")
+    monkeypatch.setenv("MAX_IN_FLIGHT_PER_USER", "4")
+    monkeypatch.setenv("WS_MAX_MESSAGE_BYTES", "1024")
     settings = Settings.from_env()
     assert settings.namespace == "ns-x"
     assert settings.pool == "pool-x"
@@ -476,13 +517,56 @@ def test_settings_from_env(monkeypatch):
     assert settings.max_body_bytes == 2 * 1024 * 1024
     assert settings.http_timeout == 12.5
     assert settings.auth_proxy_header == "X-Forwarded-User"
+    assert settings.auth_rate_limit == 5
+    assert settings.auth_rate_window == 30
+    assert settings.signup_invite_code == "invite-x"
+    assert settings.upstream_header_allowlist == frozenset({"x-custom", "accept"})
+    assert settings.max_in_flight_per_user == 4
+    assert settings.ws_max_message_bytes == 1024
 
 
 def test_settings_auth_proxy_header_defaults_to_none(monkeypatch):
     monkeypatch.delenv("AUTH_PROXY_HEADER", raising=False)
+    monkeypatch.setenv("ALLOW_INSECURE_COOKIES", "1")
     assert Settings.from_env().auth_proxy_header is None
 
 
+def test_settings_from_env_rejects_insecure_cookies_by_default(monkeypatch):
+    monkeypatch.delenv("COOKIE_SECURE", raising=False)
+    monkeypatch.delenv("ALLOW_INSECURE_COOKIES", raising=False)
+    with pytest.raises(RuntimeError, match="insecure session cookie"):
+        Settings.from_env()
+
+
+def test_settings_from_env_allows_insecure_cookies_with_the_explicit_flag(monkeypatch):
+    monkeypatch.delenv("COOKIE_SECURE", raising=False)
+    monkeypatch.setenv("ALLOW_INSECURE_COOKIES", "1")
+    monkeypatch.delenv("COOKIE_NAME", raising=False)
+    settings = Settings.from_env()
+    assert settings.cookie_secure is False
+    assert settings.cookie_name == "dsh_gw_session"
+
+
+def test_settings_default_cookie_name_is_host_prefixed_when_secure(monkeypatch):
+    monkeypatch.setenv("COOKIE_SECURE", "true")
+    monkeypatch.delenv("COOKIE_NAME", raising=False)
+    assert Settings.from_env().cookie_name == "__Host-dsh_gw_session"
+
+
+def test_settings_explicit_cookie_name_wins(monkeypatch):
+    monkeypatch.setenv("COOKIE_SECURE", "true")
+    monkeypatch.setenv("COOKIE_NAME", "sid")
+    assert Settings.from_env().cookie_name == "sid"
+
+
+def test_settings_upstream_header_allowlist_unset_means_denylist_mode(monkeypatch):
+    monkeypatch.setenv("ALLOW_INSECURE_COOKIES", "1")
+    monkeypatch.delenv("UPSTREAM_HEADER_ALLOWLIST", raising=False)
+    assert Settings.from_env().upstream_header_allowlist is None
+    monkeypatch.setenv("UPSTREAM_HEADER_ALLOWLIST", "")
+    assert Settings.from_env().upstream_header_allowlist == frozenset()
+
+
 # --- Kubernetes adapter ----------------------------------------------------
 
 
@@ -635,11 +719,22 @@ async def test_landing_page_has_signup_and_login_forms(env):
     assert "text/html" in response.headers["content-type"]
     assert 'action="/users"' in response.text
     assert 'action="/login"' in response.text
+    # No invite code configured => no invite input on the landing page.
+    assert 'name="invite"' not in response.text
+
+
+@pytest.mark.asyncio
+async def test_landing_page_shows_invite_input_only_when_configured(env):
+    configure(env, signup_invite_code="let-me-in")
+    async with asgi_client(env) as client:
+        response = await client.get("/")
+    assert response.status_code == 200
+    assert 'name="invite"' in response.text
 
 
 @pytest.mark.asyncio
 async def test_landing_page_shows_session_when_cookie_present(env):
-    async with asgi_client(env, cookies={"dsh_gw_session": f"alice:{TOKEN}"}) as client:
+    async with asgi_client(env, cookies=session_dict(env)) as client:
         response = await client.get("/")
     assert "Signed in as" in response.text
     assert "/u/alice/" in response.text
@@ -708,11 +803,14 @@ async def test_signup_json_stores_only_hash_and_returns_token(env, monkeypatch):
     assert pool == "test-pool"
     assert token_hash == hashlib.sha256(body["token"].encode()).hexdigest()
     assert token_hash != body["token"]
-    # The JSON API also gets a browser session cookie (HttpOnly, SameSite=Lax).
+    # The JSON API also gets a browser session cookie (HttpOnly, SameSite=Lax)
+    # carrying only an opaque server-side session id, never the user/token.
     cookie = response.headers["set-cookie"]
-    assert "dsh_gw_session=alice:" in cookie
+    assert "dsh_gw_session=" in cookie
+    assert f"dsh_gw_session={TOKEN}" not in cookie
     assert "HttpOnly" in cookie
     assert "SameSite=lax" in cookie
+    assert response_session_user(env, response) == "alice"
 
 
 @pytest.mark.asyncio
@@ -741,13 +839,7 @@ async def test_signup_form_redirects_and_sets_session_cookie(env, monkeypatch):
         )
     assert response.status_code == 303
     assert response.headers["location"] == "/u/bob/"
-    cookie = response.headers["set-cookie"]
+    assert response_session_user(env, response) == "bob"
-    assert re_cookie_user(cookie) == "bob"
-
-
-def re_cookie_user(set_cookie: str) -> str:
-    value = set_cookie.split(";", 1)[0].split("=", 1)[1]
-    return value.split(":", 1)[0]
 
 
 @pytest.mark.asyncio
@@ -774,7 +866,29 @@ async def test_login_form_sets_cookie_and_redirects(env):
         )
     assert response.status_code == 303
     assert response.headers["location"] == "/u/alice/"
-    assert re_cookie_user(response.headers["set-cookie"]) == "alice"
+    assert response_session_user(env, response) == "alice"
+
+
+@pytest.mark.asyncio
+async def test_secure_session_cookie_uses_the_host_prefix_and_flags(env):
+    configure(env, cookie_secure=True, cookie_name="__Host-dsh_gw_session")
+    add_user(env.k8s)
+    async with asgi_client(env) as client:
+        response = await client.post(
+            "/login",
+            data={"user": "alice", "token": TOKEN},
+            headers={"content-type": "application/x-www-form-urlencoded"},
+        )
+    cookie = response.headers["set-cookie"]
+    assert cookie.startswith("__Host-dsh_gw_session=")
+    assert "Secure" in cookie
+    assert "HttpOnly" in cookie
+    assert "Path=/" in cookie
+    assert "SameSite=lax" in cookie
+    assert "Domain=" not in cookie
+    # The value is an opaque session id, not <user>:<token>.
+    assert "alice" not in cookie.split(";", 1)[0]
+    assert TOKEN not in cookie
 
 
 @pytest.mark.asyncio
@@ -786,17 +900,197 @@ async def test_login_json_and_failures(env):
         missing = await client.post("/login", json={"user": "ghost", "token": TOKEN})
     assert ok.status_code == 200
     assert bad.status_code == 401
-    assert missing.status_code == 404
+    # An unknown user is a 401 too: login must not reveal which users exist.
+    assert missing.status_code == 401
 
 
 @pytest.mark.asyncio
-async def test_logout_clears_cookie(env):
+async def test_logout_clears_cookie_and_revokes_the_session(env):
-    async with asgi_client(env, cookies={"dsh_gw_session": f"alice:{TOKEN}"}) as client:
+    add_user(env.k8s)
+    name, sid = mint_session(env)
+    assert env.gateway.session_for(sid) is not None
+    async with asgi_client(env, cookies={name: sid}) as client:
         response = await client.post("/logout")
     assert response.status_code == 303
     assert response.headers["location"] == "/"
     assert "dsh_gw_session=" in response.headers["set-cookie"]
     assert "Max-Age=0" in response.headers["set-cookie"]
+    # The old sid is dead server-side, not just deleted from the browser.
+    assert env.gateway.session_for(sid) is None
+    async with asgi_client(env, cookies={name: sid}) as client:
+        replay = await client.get("/users/alice")
+    assert replay.status_code == 401
+
+
+@pytest.mark.asyncio
+async def test_logout_deletion_cookie_is_secure_for_the_host_prefix(env):
+    """A __Host- cookie can only be cleared by a Secure deletion Set-Cookie."""
+    configure(env, cookie_secure=True, cookie_name="__Host-dsh_gw_session")
+    add_user(env.k8s)
+    name, sid = mint_session(env)
+    assert name == "__Host-dsh_gw_session"
+    async with asgi_client(env, cookies={name: sid}) as client:
+        response = await client.post("/logout")
+    assert response.status_code == 303
+    cookie = response.headers["set-cookie"]
+    assert cookie.startswith("__Host-dsh_gw_session=")
+    assert "Max-Age=0" in cookie
+    assert "Path=/" in cookie
+    assert "Secure" in cookie
+    assert "Domain=" not in cookie
+
+
+# --- signup invite / auth abuse controls -----------------------------------
+
+
+def configure(env, **overrides):
+    """Return a copy of the fixture settings with overrides applied."""
+    env.settings = Settings(**{**env.settings.__dict__, **overrides})
+    env.gateway.settings = env.settings
+    return env
+
+
+@pytest.mark.asyncio
+async def test_signup_requires_invite_when_configured(env, monkeypatch):
+    configure(env, signup_invite_code="invite-code")
+
+    async def not_ready(user, timeout):
+        return None
+
+    monkeypatch.setattr(env.gateway, "wait_ready", not_ready)
+    async with asgi_client(env) as client:
+        missing = await client.post("/users", json={"user": "alice"})
+        wrong = await client.post("/users", json={"user": "alice", "invite": "nope"})
+        good = await client.post("/users", json={"user": "alice", "invite": "invite-code"})
+    assert missing.status_code == 403
+    assert wrong.status_code == 403
+    assert good.status_code == 202
+    assert [created[0] for created in env.k8s.created] == ["alice"]
+
+
+@pytest.mark.asyncio
+async def test_invite_is_checked_before_the_user_lookup(env):
+    configure(env, signup_invite_code="invite-code")
+    add_user(env.k8s)
+    async with asgi_client(env) as client:
+        response = await client.post("/users", json={"user": "alice"})
+    # 403, not 409: an unauthenticated caller cannot probe for existing users.
+    assert response.status_code == 403
+
+
+@pytest.mark.asyncio
+async def test_invite_accepts_the_header_and_the_form_field(env, monkeypatch):
+    configure(env, signup_invite_code="invite-code")
+
+    async def not_ready(user, timeout):
+        return None
+
+    monkeypatch.setattr(env.gateway, "wait_ready", not_ready)
+    async with asgi_client(env) as client:
+        via_header = await client.post(
+            "/users",
+            json={"user": "alice"},
+            headers={"X-Signup-Invite": "invite-code"},
+        )
+        via_form = await client.post(
+            "/users",
+            data={"user": "bob", "invite": "invite-code"},
+            headers={"content-type": "application/x-www-form-urlencoded"},
+        )
+    assert via_header.status_code == 202
+    assert via_form.status_code == 303
+
+
+@pytest.mark.asyncio
+async def test_form_auth_rejects_cross_origin_requests(env):
+    add_user(env.k8s)
+    form = {"content-type": "application/x-www-form-urlencoded"}
+    async with asgi_client(env) as client:
+        signup = await client.post(
+            "/users", data={"user": "bob"}, headers={**form, "Origin": "http://evil.test"}
+        )
+        login = await client.post(
+            "/login",
+            data={"user": "alice", "token": TOKEN},
+            headers={**form, "Origin": "http://evil.test"},
+        )
+        referer = await client.post(
+            "/login",
+            data={"user": "alice", "token": TOKEN},
+            headers={**form, "Referer": "http://evil.test/login"},
+        )
+        same_origin = await client.post(
+            "/login",
+            data={"user": "alice", "token": TOKEN},
+            headers={**form, "Origin": "http://gateway.test"},
+        )
+    assert signup.status_code == 403
+    assert login.status_code == 403
+    assert referer.status_code == 403
+    assert same_origin.status_code == 303
+
+
+@pytest.mark.asyncio
+async def test_auth_rate_limit_returns_429_with_retry_after(env):
+    configure(env, auth_rate_limit=2, auth_rate_window=60)
+    add_user(env.k8s)
+    async with asgi_client(env) as client:
+        first = await client.post("/login", json={"user": "alice", "token": "nope"})
+        second = await client.post("/login", json={"user": "alice", "token": "nope"})
+        third = await client.post("/login", json={"user": "alice", "token": "nope"})
+    assert first.status_code == 401
+    assert second.status_code == 401
+    assert third.status_code == 429
+    assert int(third.headers["retry-after"]) >= 1
+
+
+@pytest.mark.asyncio
+async def test_auth_rate_limit_is_per_client_via_rightmost_forwarded_for(env):
+    configure(env, auth_rate_limit=1, auth_rate_window=60)
+    add_user(env.k8s)
+    async with asgi_client(env) as client:
+        first = await client.post(
+            "/login",
+            json={"user": "alice", "token": "nope"},
+            headers={"X-Forwarded-For": "1.1.1.1, 10.0.0.1"},
+        )
+        # A spoofed leftmost entry cannot escape the same rightmost-client bucket.
+        same_client = await client.post(
+            "/login",
+            json={"user": "alice", "token": "nope"},
+            headers={"X-Forwarded-For": "9.9.9.9, 10.0.0.1"},
+        )
+        other_client = await client.post(
+            "/login",
+            json={"user": "alice", "token": "nope"},
+            headers={"X-Forwarded-For": "10.0.0.2"},
+        )
+    assert first.status_code == 401
+    assert same_client.status_code == 429
+    assert other_client.status_code == 401
+
+
+@pytest.mark.asyncio
+async def test_auth_rate_limit_zero_disables_it(env):
+    configure(env, auth_rate_limit=0)
+    add_user(env.k8s)
+    async with asgi_client(env) as client:
+        responses = [
+            await client.post("/login", json={"user": "alice", "token": "nope"}) for _ in range(40)
+        ]
+    assert {response.status_code for response in responses} == {401}
+
+
+@pytest.mark.asyncio
+async def test_signup_is_rate_limited_before_the_body_is_read(env):
+    """429 wins over parsing: an abusive client cannot even submit a body."""
+    configure(env, auth_rate_limit=1, auth_rate_window=60)
+    async with asgi_client(env) as client:
+        # Spend the single allowed auth attempt on a login, then hit signup.
+        await client.post("/login", json={"user": "alice", "token": "nope"})
+        limited = await client.post("/users", content=b"not json at all")
+    assert limited.status_code == 429
+    assert env.k8s.created == []
 
 
 # --- auth ------------------------------------------------------------------
@@ -810,11 +1104,11 @@ async def test_get_user_requires_valid_bearer_or_cookie(env):
         bearer = await client.get("/users/alice", headers={"Authorization": f"Bearer {TOKEN}"})
         cookie = await client.get(
             "/users/alice",
-            headers={"Cookie": f"dsh_gw_session=alice:{TOKEN}"},
+            headers={"Cookie": session_cookie(env)},
         )
         wrong_user_cookie = await client.get(
             "/users/alice",
-            headers={"Cookie": f"dsh_gw_session=bob:{TOKEN}"},
+            headers={"Cookie": session_cookie(env, "bob")},
         )
     assert forbidden.status_code == 401
     assert bearer.status_code == 200
@@ -852,7 +1146,7 @@ async def test_delete_user_requires_auth(env):
 async def test_delete_with_cookie_requires_same_origin(env):
     add_user(env.k8s)
     env.gateway.state.handshake[("alice", POD_UID, "gateway.test")] = "dsh-auth-a=x"
-    cookies = {"dsh_gw_session": f"alice:{TOKEN}"}
+    cookies = session_dict(env)
     async with asgi_client(env, cookies=cookies) as client:
         missing = await client.delete("/users/alice")
         cross = await client.delete("/users/alice", headers={"Origin": "http://evil.test"})
@@ -890,13 +1184,78 @@ async def test_unexpected_api_error_propagates(env):
             await client.get("/users/alice")
 
 
+@pytest.mark.asyncio
+async def test_bearer_token_never_authorizes_another_user(env):
+    add_user(env.k8s, "alice", token=TOKEN)
+    add_user(env.k8s, "bob", token="bob-token")
+    async with asgi_client(env) as client:
+        alice_on_bob = await client.get("/users/bob", headers={"Authorization": f"Bearer {TOKEN}"})
+        bob_on_alice = await client.get(
+            "/users/alice", headers={"Authorization": "Bearer bob-token"}
+        )
+        alice_on_alice = await client.get(
+            "/users/alice", headers={"Authorization": f"Bearer {TOKEN}"}
+        )
+    assert alice_on_bob.status_code == 401
+    assert bob_on_alice.status_code == 401
+    assert alice_on_alice.status_code == 200
+
+
+@pytest.mark.asyncio
+async def test_session_cookie_never_authorizes_another_user(env):
+    add_user(env.k8s, "alice", token=TOKEN)
+    add_user(env.k8s, "bob", token="bob-token")
+    bob_cookie = session_cookie(env, "bob")
+    async with asgi_client(env) as client:
+        user = await client.get("/users/alice", headers={"Cookie": bob_cookie})
+        proxy = await client.get("/u/alice/api/state", headers={"Cookie": bob_cookie})
+    assert user.status_code == 401
+    assert proxy.status_code == 401
+
+
+@pytest.mark.asyncio
+async def test_opaque_session_cookie_is_not_a_bearer_token(env):
+    add_user(env.k8s)
+    _name, sid = mint_session(env)
+    async with asgi_client(env) as client:
+        response = await client.get("/users/alice", headers={"Authorization": f"Bearer {sid}"})
+    assert response.status_code == 401
+
+
+@pytest.mark.asyncio
+async def test_expired_session_is_revoked_and_treated_as_anonymous(env):
+    add_user(env.k8s)
+    name, sid = mint_session(env)
+    env.gateway.state.sessions[sid] = Session(user="alice", expires_at=time.time() - 1)
+    async with asgi_client(env, cookies={name: sid}) as client:
+        user = await client.get("/users/alice")
+        landing = await client.get("/")
+    assert user.status_code == 401
+    assert "Signed in as" not in landing.text
+    assert sid not in env.gateway.state.sessions
+
+
+@pytest.mark.asyncio
+async def test_delete_user_revokes_all_its_sessions(env):
+    add_user(env.k8s)
+    cookie = session_dict(env)
+    other = session_dict(env)  # a second browser session for the same user
+    async with asgi_client(env, cookies=cookie) as client:
+        response = await client.delete("/users/alice", headers={"Origin": "http://gateway.test"})
+    assert response.status_code == 200
+    assert env.gateway.state.sessions == {}
+    async with asgi_client(env, cookies=other) as client:
+        landing = await client.get("/")
+    assert "Signed in as" not in landing.text
+
+
 # --- DSH handshake ---------------------------------------------------------
 
 
 @pytest.mark.asyncio
 async def test_proxy_handshakes_and_uses_browser_host(env):
     add_user(env.k8s)
-    async with asgi_client(env, cookies={"dsh_gw_session": f"alice:{TOKEN}"}) as client:
+    async with asgi_client(env, cookies=session_dict(env)) as client:
         response = await client.get("/u/alice/api/state")
     assert response.status_code == 200
     assert response.text == "hello from DSH"
@@ -912,7 +1271,7 @@ async def test_proxy_handshakes_and_uses_browser_host(env):
 @pytest.mark.asyncio
 async def test_dsh_cookie_is_cached_per_pod_uid_and_host(env):
     add_user(env.k8s)
-    async with asgi_client(env, cookies={"dsh_gw_session": f"alice:{TOKEN}"}) as client:
+    async with asgi_client(env, cookies=session_dict(env)) as client:
         first = await client.get("/u/alice/api/one")
         second = await client.get("/u/alice/api/two")
     assert first.status_code == second.status_code == 200
@@ -924,7 +1283,7 @@ async def test_dsh_cookie_is_cached_per_pod_uid_and_host(env):
 async def test_missing_launch_token_returns_503_with_retry_after(env):
     _sandbox_name, pod_name = add_user(env.k8s)
     env.k8s.logs[pod_name] = "no token printed yet\n"
-    async with asgi_client(env, cookies={"dsh_gw_session": f"alice:{TOKEN}"}) as client:
+    async with asgi_client(env, cookies=session_dict(env)) as client:
         response = await client.get("/u/alice/api/state")
     assert response.status_code == 503
     assert response.headers["retry-after"] == "10"
@@ -935,7 +1294,7 @@ async def test_missing_launch_token_returns_503_with_retry_after(env):
 async def test_handshake_4xx_is_503(env):
     add_user(env.k8s)
     env.upstream.handshake_status = 401
-    async with asgi_client(env, cookies={"dsh_gw_session": f"alice:{TOKEN}"}) as client:
+    async with asgi_client(env, cookies=session_dict(env)) as client:
         response = await client.get("/u/alice/api/state")
     assert response.status_code == 503
 
@@ -944,11 +1303,27 @@ async def test_handshake_4xx_is_503(env):
 async def test_missing_cookie_in_handshake_is_503(env):
     add_user(env.k8s)
     env.upstream.handshake_cookies = ["other=1; Path=/"]
-    async with asgi_client(env, cookies={"dsh_gw_session": f"alice:{TOKEN}"}) as client:
+    async with asgi_client(env, cookies=session_dict(env)) as client:
         response = await client.get("/u/alice/api/state")
     assert response.status_code == 503
 
 
+@pytest.mark.asyncio
+async def test_handshake_error_never_leaks_the_launch_token_or_url(env):
+    _sandbox_name, pod_name = add_user(env.k8s)
+    secret = "super-secret-launch-token"
+    env.k8s.logs[pod_name] = f"dsh web: http://10.0.0.7:3080/?token={secret}\n"
+    env.upstream.handshake_status = 500
+    async with asgi_client(env, cookies=session_dict(env)) as client:
+        response = await client.get("/u/alice/api/state")
+    assert response.status_code == 503
+    body = response.text
+    assert secret not in body
+    assert FQDN not in body
+    assert "10.0.0.7" not in body
+    assert "dsh-auth" not in body
+
+
 @pytest.mark.asyncio
 async def test_pod_annotation_overrides_sandbox_name(env):
     sandbox_name, pod_name = add_user(env.k8s)
@@ -957,7 +1332,7 @@ async def test_pod_annotation_overrides_sandbox_name(env):
     )
     env.k8s.pods["custom-pod"] = {"metadata": {"uid": "other-uid"}}
     env.k8s.logs["custom-pod"] = env.k8s.logs[pod_name]
-    async with asgi_client(env, cookies={"dsh_gw_session": f"alice:{TOKEN}"}) as client:
+    async with asgi_client(env, cookies=session_dict(env)) as client:
         response = await client.get("/u/alice/api/state")
     assert response.status_code == 200
     assert ("alice", "other-uid", "gateway.test") in env.gateway.state.handshake
@@ -984,7 +1359,7 @@ async def test_proxy_strips_gateway_auth_cookie_and_hop_headers(env):
     env.upstream.proxy_handler = handler
     headers = {
         "Authorization": f"Bearer {TOKEN}",
-        "Cookie": "dsh_gw_session=alice:x; browser=1",
+        "Cookie": session_cookie(env) + "; browser=1",
         "X-Forwarded-For": "1.2.3.4",
         "X-Forwarded-Proto": "https",
         "Host": "gateway.test",
@@ -1009,6 +1384,83 @@ async def test_proxy_strips_gateway_auth_cookie_and_hop_headers(env):
     assert "connection" not in response.headers
 
 
+@pytest.mark.asyncio
+async def test_proxy_strips_client_supplied_forwarding_and_sso_headers(env):
+    add_user(env.k8s)
+    headers = {
+        "Authorization": f"Bearer {TOKEN}",
+        "Forwarded": "for=evil.test;proto=https",
+        "X-Forwarded-User": "bob",
+        "X-Forwarded-Host": "evil.test",
+        "X-Auth-Request-User": "bob",
+        "X-Auth-Request-Email": "bob@evil.test",
+        "X-Real-IP": "6.6.6.6",
+        "Origin": "http://gateway.test",
+    }
+    async with asgi_client(env) as client:
+        response = await client.get("/u/alice/api/state", headers=headers)
+    assert response.status_code == 200
+    proxy = env.upstream.proxy_requests[0]
+    for name in (
+        "forwarded",
+        "x-forwarded-user",
+        "x-auth-request-user",
+        "x-auth-request-email",
+        "x-real-ip",
+    ):
+        assert name not in proxy.headers
+    # The gateway's own hop metadata comes from the real connection instead.
+    assert proxy.headers["x-forwarded-for"] == "127.0.0.1"
+    assert proxy.headers["x-forwarded-host"] == "gateway.test"
+
+
+@pytest.mark.asyncio
+async def test_proxy_upstream_header_allowlist_drops_unlisted_headers(env):
+    configure(env, upstream_header_allowlist=frozenset({"x-custom-ok"}))
+    add_user(env.k8s)
+    headers = {
+        "Authorization": f"Bearer {TOKEN}",
+        "X-Custom-Ok": "keep",
+        "X-Custom-Drop": "drop",
+        "X-Forwarded-User": "bob",
+        "Origin": "http://gateway.test",
+    }
+    async with asgi_client(env) as client:
+        response = await client.get("/u/alice/api/state", headers=headers)
+    assert response.status_code == 200
+    proxy = env.upstream.proxy_requests[0]
+    assert proxy.headers["x-custom-ok"] == "keep"
+    assert "x-custom-drop" not in proxy.headers
+    # Allowlisting never re-enables gateway-owned or spoofable headers.
+    assert "authorization" not in proxy.headers
+    assert "x-forwarded-user" not in proxy.headers
+    assert "cookie" not in proxy.headers or proxy.headers["cookie"] == "dsh-auth-a=one"
+
+
+@pytest.mark.asyncio
+async def test_proxy_rejects_requests_over_the_per_user_in_flight_cap(env):
+    configure(env, max_in_flight_per_user=1)
+    add_user(env.k8s)
+    env.gateway.state.in_flight["alice"] = 1
+    async with asgi_client(env, cookies=session_dict(env)) as client:
+        response = await client.get("/u/alice/api/state")
+    assert response.status_code == 503
+    assert "retry-after" in response.headers
+    assert env.gateway.state.in_flight["alice"] == 1
+    assert env.upstream.proxy_requests == []
+
+
+@pytest.mark.asyncio
+async def test_proxy_accepts_requests_below_the_per_user_in_flight_cap(env):
+    configure(env, max_in_flight_per_user=2)
+    add_user(env.k8s)
+    env.gateway.state.in_flight["alice"] = 1
+    async with asgi_client(env, cookies=session_dict(env)) as client:
+        response = await client.get("/u/alice/api/state")
+    assert response.status_code == 200
+    assert env.gateway.state.in_flight["alice"] == 1  # the slot was released again
+
+
 @pytest.mark.asyncio
 async def test_proxy_rewrites_absolute_path_location(env):
     add_user(env.k8s)
@@ -1019,7 +1471,7 @@ async def test_proxy_rewrites_absolute_path_location(env):
             ("set-cookie", "upstream=leak; Path=/"),
         ],
     )
-    async with asgi_client(env, cookies={"dsh_gw_session": f"alice:{TOKEN}"}) as client:
+    async with asgi_client(env, cookies=session_dict(env)) as client:
         response = await client.get("/u/alice/api/redirect", follow_redirects=False)
     assert response.status_code == 303
     assert response.headers["location"] == "/u/alice/?next=1"
@@ -1040,7 +1492,7 @@ async def test_proxy_refreshes_cookie_once_on_upstream_401(env):
         return dsh_response(200, b"fresh")
 
     env.upstream.proxy_handler = handler
-    async with asgi_client(env, cookies={"dsh_gw_session": f"alice:{TOKEN}"}) as client:
+    async with asgi_client(env, cookies=session_dict(env)) as client:
         response = await client.get("/u/alice/api/state")
     assert response.status_code == 200
     assert response.text == "fresh"
@@ -1053,7 +1505,7 @@ async def test_proxy_refreshes_cookie_once_on_upstream_401(env):
 async def test_proxy_does_not_refresh_401_without_cached_cookie(env):
     add_user(env.k8s)
     env.upstream.proxy_handler = lambda request: dsh_response(401, b"no")
-    async with asgi_client(env, cookies={"dsh_gw_session": f"alice:{TOKEN}"}) as client:
+    async with asgi_client(env, cookies=session_dict(env)) as client:
         response = await client.get("/u/alice/api/state")
     assert response.status_code == 401
     assert len(env.upstream.proxy_requests) == 1
@@ -1067,7 +1519,7 @@ async def test_proxy_upstream_connection_error_is_502(env):
         raise httpx.ConnectError("boom", request=request)
 
     env.upstream.proxy_handler = handler
-    async with asgi_client(env, cookies={"dsh_gw_session": f"alice:{TOKEN}"}) as client:
+    async with asgi_client(env, cookies=session_dict(env)) as client:
         response = await client.get("/u/alice/api/state")
     assert response.status_code == 502
     assert env.gateway.state.in_flight["alice"] == 0
@@ -1106,7 +1558,7 @@ async def test_proxy_client_disconnect_mid_body_returns_499(env):
             "/u/alice/api/echo",
             headers=[
                 (b"origin", b"http://gateway.test"),
-                (b"cookie", f"dsh_gw_session=alice:{TOKEN}".encode()),
+                (b"cookie", session_cookie(env).encode()),
                 (b"content-type", b"application/json"),
             ],
         ),
@@ -1167,7 +1619,7 @@ async def test_proxy_client_disconnect_mid_stream_frees_slot(env):
         raw_scope(
             "GET",
             "/u/alice/api/stream",
-            headers=[(b"cookie", f"dsh_gw_session=alice:{TOKEN}".encode())],
+            headers=[(b"cookie", session_cookie(env).encode())],
         ),
         receive,
     )
@@ -1234,7 +1686,7 @@ async def test_proxy_client_disconnect_survives_cancelled_upstream_close(env):
         raw_scope(
             "GET",
             "/u/alice/api/stream",
-            headers=[(b"cookie", f"dsh_gw_session=alice:{TOKEN}".encode())],
+            headers=[(b"cookie", session_cookie(env).encode())],
         ),
         receive,
     )
@@ -1258,7 +1710,7 @@ async def test_proxy_wakes_suspended_sandbox(env, monkeypatch):
         return env.k8s.sandboxes[sandbox_name]
 
     monkeypatch.setattr(env.gateway, "wait_ready", ready)
-    async with asgi_client(env, cookies={"dsh_gw_session": f"alice:{TOKEN}"}) as client:
+    async with asgi_client(env, cookies=session_dict(env)) as client:
         response = await client.get("/u/alice/api/state")
     assert response.status_code == 200
     assert ("dsh-alice-sbx", "Running") in env.k8s.patches
@@ -1273,7 +1725,7 @@ async def test_proxy_wake_timeout_returns_503(env, monkeypatch):
         return None
 
     monkeypatch.setattr(env.gateway, "wait_ready", never)
-    async with asgi_client(env, cookies={"dsh_gw_session": f"alice:{TOKEN}"}) as client:
+    async with asgi_client(env, cookies=session_dict(env)) as client:
         response = await client.get("/u/alice/api/state")
     assert response.status_code == 503
     assert response.headers["retry-after"] == "10"
@@ -1297,7 +1749,7 @@ async def test_proxy_requires_auth(env):
 @pytest.mark.asyncio
 async def test_proxy_cookie_mutation_requires_same_origin(env):
     add_user(env.k8s)
-    cookies = {"dsh_gw_session": f"alice:{TOKEN}"}
+    cookies = session_dict(env)
     async with asgi_client(env, cookies=cookies) as client:
         cross = await client.post(
             "/u/alice/api/mutate", headers={"Origin": "http://evil.test"}, content=b"{}"
@@ -1385,7 +1837,7 @@ def test_ws_cookie_cross_origin_closes_4401(env):
         with client.websocket_connect(
             "/u/alice/api/remote.mux",
             headers={
-                "cookie": f"dsh_gw_session=alice:{TOKEN}",
+                "cookie": session_cookie(env),
                 "origin": "http://evil.test",
             },
         ) as ws:
@@ -1425,7 +1877,7 @@ def test_ws_cookie_same_origin_bridges_frames(env):
         with client.websocket_connect(
             "/u/alice/api/remote.mux",
             headers={
-                "cookie": f"dsh_gw_session=alice:{TOKEN}",
+                "cookie": session_cookie(env),
                 "origin": "http://testserver",
             },
         ) as ws:
@@ -1464,6 +1916,70 @@ def test_ws_upstream_connect_failure_closes_1011(env):
     assert exc.value.code == 1011
 
 
+def test_ws_strips_client_supplied_forwarding_and_sso_headers(env):
+    add_user(env.k8s)
+    with TestClient(env.app) as client:
+        with client.websocket_connect(
+            "/u/alice/api/remote.mux",
+            headers={
+                "Authorization": f"Bearer {TOKEN}",
+                "Forwarded": "for=evil.test",
+                "X-Forwarded-User": "bob",
+                "X-Auth-Request-User": "bob",
+            },
+        ) as ws:
+            ws.send_text("hello")
+            assert ws.receive_text() == "welcome"
+            assert ws.receive_text() == "pong"
+    headers = env.ws_connect.calls[0][1]["additional_headers"]
+    assert "forwarded" not in headers
+    assert "x-forwarded-user" not in headers
+    assert "x-auth-request-user" not in headers
+    assert headers["cookie"] == "dsh-auth-a=one"
+
+
+def test_ws_per_user_in_flight_cap_closes_1011(env):
+    configure(env, max_in_flight_per_user=1)
+    add_user(env.k8s)
+    env.gateway.state.in_flight["alice"] = 1
+    with TestClient(env.app) as client:
+        with client.websocket_connect(
+            "/u/alice/api/remote.mux",
+            headers={"Authorization": f"Bearer {TOKEN}"},
+        ) as ws:
+            with pytest.raises(WebSocketDisconnect) as exc:
+                ws.receive_text()
+    assert exc.value.code == 1011
+    assert env.ws_connect.calls == []
+
+
+def test_ws_passes_the_default_max_message_size(env):
+    add_user(env.k8s)
+    with TestClient(env.app) as client:
+        with client.websocket_connect(
+            "/u/alice/api/remote.mux",
+            headers={"Authorization": f"Bearer {TOKEN}"},
+        ) as ws:
+            ws.send_text("hello")
+            assert ws.receive_text() == "welcome"
+            assert ws.receive_text() == "pong"
+    assert env.ws_connect.calls[0][1]["max_size"] == 16 * 1024 * 1024
+
+
+def test_ws_max_message_size_is_configurable(env):
+    configure(env, ws_max_message_bytes=2048)
+    add_user(env.k8s)
+    with TestClient(env.app) as client:
+        with client.websocket_connect(
+            "/u/alice/api/remote.mux",
+            headers={"Authorization": f"Bearer {TOKEN}"},
+        ) as ws:
+            ws.send_text("hello")
+            assert ws.receive_text() == "welcome"
+            assert ws.receive_text() == "pong"
+    assert env.ws_connect.calls[0][1]["max_size"] == 2048
+
+
 # --- idle sweeper ----------------------------------------------------------
 
 
@@ -1576,14 +2092,46 @@ async def test_sweeper_survives_transient_api_error(env):
     assert env.gateway.state.maintenance["alice"] is False
 
 
+@pytest.mark.asyncio
+async def test_sweeper_prunes_orphan_and_expired_state(env):
+    now = time.time()
+    # No claim for "ghost": every per-user entry is orphaned.
+    env.gateway.state.last_activity["ghost"] = now
+    env.gateway.state.in_flight["ghost"] = 0
+    env.gateway.state.maintenance["ghost"] = False
+    env.gateway.state.handshake[("ghost", POD_UID, "gateway.test")] = "dsh-auth-a=x"
+    _ghost_name, ghost_sid = mint_session(env, "ghost")
+    env.gateway.state.auth_rate["1.2.3.4"] = (now - 3600, 5)
+    # A user with requests still in flight is preserved even without a claim.
+    env.gateway.state.in_flight["busy"] = 2
+    # A live claim keeps its user's current session...
+    env.k8s.claims["alice"] = ready_claim()
+    env.k8s.sandboxes["dsh-alice-sbx"] = ready_sandbox()
+    env.gateway.state.last_activity["alice"] = now
+    _alice_name, alice_sid = mint_session(env, "alice")
+    # ...but an expired session is pruned even for a live user.
+    _old_name, expired_sid = mint_session(env, "alice")
+    env.gateway.state.sessions[expired_sid] = Session(user="alice", expires_at=now - 1)
+
+    await env.gateway.sweep_once()
+
+    assert "ghost" not in env.gateway.state.last_activity
+    assert "ghost" not in env.gateway.state.in_flight
+    assert "ghost" not in env.gateway.state.maintenance
+    assert ("ghost", POD_UID, "gateway.test") not in env.gateway.state.handshake
+    assert ghost_sid not in env.gateway.state.sessions
+    assert env.gateway.state.auth_rate == {}
+    assert env.gateway.state.in_flight["busy"] == 2
+    assert alice_sid in env.gateway.state.sessions
+    assert expired_sid not in env.gateway.state.sessions
+
+
 # --- SSO (reverse-proxy identity) ------------------------------------------
 
 
 def enable_sso(env, header="X-Forwarded-User"):
     """Flip an env into SSO mode: the gateway trusts the named identity header."""
-    env.settings = Settings(**{**env.settings.__dict__, "auth_proxy_header": header})
+    return configure(env, auth_proxy_header=header)
-    env.gateway.settings = env.settings
-    return env
 
 
 def test_remote_user_none_when_sso_disabled(env):
@@ -1611,7 +2159,7 @@ async def test_sso_landing_new_user_shows_provisioning(env):
     assert "Signed in as <strong>alice</strong>" in response.text
     assert "Provisioning" in response.text
     assert "Recreate sandbox" not in response.text
-    assert re_cookie_user(response.headers["set-cookie"]) == "alice"
+    assert response_session_user(env, response) == "alice"
     assert [c[0] for c in env.k8s.created] == ["alice"]
     assert env.k8s.token_patches == []
 
@@ -1620,7 +2168,7 @@ async def test_sso_landing_new_user_shows_provisioning(env):
 async def test_sso_landing_ready_connects_and_offers_recreate_only(env):
     enable_sso(env)
     add_user(env.k8s)
-    async with asgi_client(env, cookies={"dsh_gw_session": f"alice:{TOKEN}"}) as client:
+    async with asgi_client(env, cookies=session_dict(env)) as client:
         response = await client.get("/", headers={"X-Forwarded-User": "alice"})
     assert response.status_code == 200
     assert "Signed in as <strong>alice</strong>" in response.text
@@ -1642,11 +2190,55 @@ async def test_sso_landing_rotates_token_when_session_missing(env):
         response = await client.get("/", headers={"X-Forwarded-User": "alice"})
     assert response.status_code == 200
     assert "Recreate sandbox" in response.text
-    assert re_cookie_user(response.headers["set-cookie"]) == "alice"
+    assert response_session_user(env, response) == "alice"
     assert [p[0] for p in env.k8s.token_patches] == ["alice"]
     assert env.k8s.created == []
 
 
+@pytest.mark.asyncio
+async def test_sso_landing_reuses_a_valid_session_for_the_remote_user(env):
+    enable_sso(env)
+    add_user(env.k8s)
+    name, sid = mint_session(env)
+    async with asgi_client(env, cookies={name: sid}) as client:
+        response = await client.get("/", headers={"X-Forwarded-User": "alice"})
+    assert response.status_code == 200
+    assert "Recreate sandbox" in response.text
+    # Untouched: no cookie is re-issued and no token is rotated.
+    assert "set-cookie" not in response.headers
+    assert [p[0] for p in env.k8s.token_patches] == []
+    assert env.gateway.state.sessions[sid].user == "alice"
+
+
+@pytest.mark.asyncio
+async def test_sso_landing_revokes_a_foreign_session(env):
+    enable_sso(env)
+    add_user(env.k8s)
+    bob_name, bob_sid = mint_session(env, "bob")
+    async with asgi_client(env, cookies={bob_name: bob_sid}) as client:
+        response = await client.get("/", headers={"X-Forwarded-User": "alice"})
+    assert response.status_code == 200
+    # A session for another identity is never reused and is revoked server-side.
+    assert bob_sid not in env.gateway.state.sessions
+    assert response_session_user(env, response) == "alice"
+
+
+@pytest.mark.asyncio
+async def test_recreate_revokes_the_old_session_and_mints_a_new_one(env):
+    enable_sso(env)
+    add_user(env.k8s)
+    name, sid = mint_session(env)
+    async with asgi_client(env, cookies={name: sid}) as client:
+        response = await client.post(
+            "/recreate",
+            headers={"X-Forwarded-User": "alice", "Origin": "http://gateway.test"},
+        )
+    assert response.status_code == 303
+    assert sid not in env.gateway.state.sessions
+    new_sid = response.headers["set-cookie"].split(";", 1)[0].split("=", 1)[1]
+    assert env.gateway.state.sessions[new_sid].user == "alice"
+
+
 @pytest.mark.asyncio
 async def test_recreate_deletes_and_reprovisions(env):
     enable_sso(env)
@@ -1657,7 +2249,7 @@ async def test_recreate_deletes_and_reprovisions(env):
     assert response.headers["location"] == "/u/alice/"
     assert env.k8s.deleted == ["alice"]
     assert [c[0] for c in env.k8s.created] == ["alice"]
-    assert re_cookie_user(response.headers["set-cookie"]) == "alice"
+    assert response_session_user(env, response) == "alice"
 
 
 @pytest.mark.asyncio
@@ -1673,7 +2265,7 @@ async def test_recreate_requires_sso(env):
 async def test_recreate_rejects_cross_origin(env):
     enable_sso(env)
     add_user(env.k8s)
-    async with asgi_client(env, cookies={"dsh_gw_session": f"alice:{TOKEN}"}) as client:
+    async with asgi_client(env, cookies=session_dict(env)) as client:
         response = await client.post(
             "/recreate",
             headers={"X-Forwarded-User": "alice", "Origin": "http://evil.test"},

examples/dsh-agents-as-a-service/manifests/10-sandboxtemplate.yaml

@@ -131,6 +131,24 @@ spec:
             # a private PVC), so trade DSH's inner file policy for a working
             # agent. Set this to workspace-write (or read-only) on hosts where a
             # backend is available; see the README troubleshooting row.
+            # SECURITY: the pod is the isolation boundary in this example.
+            # danger-full-access is set only because DSH's own command sandbox
+            # has no usable backend in this pod (see above), which means an
+            # agent command can read its own DSH_HOME (including
+            # .credentials.yaml) and write anywhere in the container. What
+            # still contains it is the pod itself: one pod per user, non-root,
+            # all capabilities dropped, RuntimeDefault seccomp, its own PVC and
+            # Service. That is NOT a hardened multi-tenant boundary on a shared
+            # kernel. For production/multi-tenant use, additionally run the
+            # sandbox under gVisor (`runtimeClassName: gvisor` above) so a
+            # container escape is trapped in a userspace kernel, and apply the
+            # sandbox NetworkPolicy (manifests/optional/network-policy/) so
+            # tenants cannot reach each other or cluster-internal endpoints.
+            # The base manifests without those two controls are a demo. Treat
+            # danger-full-access as a fallback, not a target: on hosts where
+            # DSH's command-sandbox backend works, prefer workspace-write (or
+            # read-only), and recreate the pod because the value is stamped at
+            # creation.
             - name: DSH_PERMISSION_MODE
               value: danger-full-access
           # Probes target /favicon.svg: DSH gates / behind its launch-token

examples/dsh-agents-as-a-service/manifests/50-gateway.yaml

@@ -134,14 +134,30 @@ spec:
             # the DSH launch token.
             - name: DSH_CONTAINER
               value: dsh-web
-            # Cookie dsh_gw_session is HttpOnly + SameSite=Lax. "false" keeps
+            # Browser session cookie: HttpOnly + SameSite=Lax, holds only an
-            # the plain-HTTP demo usable through port-forward: a Secure cookie
+            # opaque, server-side session id (sid) - never the user's DSH
-            # is never sent over HTTP, so login would silently fail.
+            # token. Sessions can be revoked server-side: POST /logout, user
-            # HTTPS deployments (the ingress/ variant with TLS, or
+            # delete, POST /recreate and expiry (COOKIE_MAX_AGE, default
-            # gateway-api-sso/, which terminates TLS at the Gateway) MUST set
+            # 7 days) all invalidate them. The session table is in process
-            # this to "true".
+            # memory, so restarting this Deployment logs every browser out.
+            # With COOKIE_SECURE=true the cookie is named
+            # __Host-dsh_gw_session; COOKIE_NAME overrides the name.
+            #
+            # "false" keeps the plain-HTTP demo usable through port-forward: a
+            # Secure cookie is never sent over HTTP, so login would silently
+            # fail. The gateway REFUSES TO START with COOKIE_SECURE=false
+            # unless ALLOW_INSECURE_COOKIES=1 acknowledges that the session
+            # travels in clear text, so the base demo sets both. HTTPS
+            # deployments (the ingress/ variant with TLS, or gateway-api-sso/,
+            # which terminates TLS at the Gateway) MUST set this to "true".
             - name: COOKIE_SECURE
               value: "false"
+            # Explicit acknowledgement that this base demo serves plain HTTP.
+            # Required when COOKIE_SECURE=false (the gateway exits at startup
+            # otherwise); ignored once COOKIE_SECURE=true, so HTTPS installs
+            # should drop it. Never set this on an internet-facing deployment.
+            - name: ALLOW_INSECURE_COOKIES
+              value: "1"
             # SSO IS OPT-IN AND DISABLED HERE. With AUTH_PROXY_HEADER unset the
             # gateway trusts only its own bearer/session auth and ignores every
             # identity header. Enable it ONLY behind
@@ -152,9 +168,49 @@ spec:
             # reach :8080 can impersonate any user by sending that header.
             # - name: AUTH_PROXY_HEADER
             #   value: X-Forwarded-User
+            # Brute-force / abuse throttle for the unauthenticated auth
+            # endpoints (/users and /login): at most N attempts per client per
+            # AUTH_RATE_WINDOW seconds (default 60). A client is the rightmost
+            # X-Forwarded-For entry (the one added by the trusted proxy) when
+            # present, otherwise the TCP peer. Over the limit the gateway
+            # answers 429 + Retry-After BEFORE reading the body or touching the
+            # cluster; 0 disables the limiter. This is a per-process bucket, so
+            # it is not a substitute for an ingress rate limit.
+            - name: AUTH_RATE_LIMIT
+              value: "30"
+            # Window in seconds for AUTH_RATE_LIMIT (default 60).
+            # - name: AUTH_RATE_WINDOW
+            #   value: "60"
+            # Optional signup gate. When set, POST /users requires the invite
+            # code - form field "invite" or header X-Signup-Invite - compared in
+            # constant time. A missing/wrong code is rejected with 403 before
+            # the user is looked up, so it also stops unauthenticated claim
+            # creation. The landing page shows the invite input only when this
+            # is set. Keep the value in a Secret, create it before rollout and
+            # restart the gateway to pick up a rotation:
+            #   kubectl -n dsh-demo create secret generic dsh-signup-invite \
+            #     --from-literal=code="$(openssl rand -hex 16)"
+            # - name: SIGNUP_INVITE_CODE
+            #   valueFrom:
+            #     secretKeyRef:
+            #       name: dsh-signup-invite
+            #       key: code
             # Reject proxied request bodies larger than this (413).
             - name: MAX_BODY_MB
               value: "32"
+            # Per-user concurrency guard (default 32): at most this many
+            # proxied HTTP requests and WebSocket connections per user.
+            # Excess HTTP requests get 503 + Retry-After and excess WebSocket
+            # upgrades close with 1011, so one tenant cannot exhaust the
+            # single-replica gateway for everyone else.
+            # - name: MAX_IN_FLIGHT_PER_USER
+            #   value: "32"
+            # Largest WebSocket message received from DSH, in bytes (default
+            # 16 MiB); oversized frames close the connection. Browser-to-DSH
+            # frames are bounded by uvicorn's own limit. HTTP/SSE responses are
+            # streamed without this cap.
+            # - name: WS_MAX_MESSAGE_BYTES
+            #   value: "16777216"
           # /healthz is unauthenticated and returns 200 without touching the
           # cluster, so it is safe for both readiness and liveness.
           readinessProbe:

examples/dsh-agents-as-a-service/manifests/exposure/README.md

@@ -16,6 +16,16 @@ Applying both gives the gateway two entry points, and the SSO variant is only
 safe when the gateway is reachable **exclusively** through oauth2-proxy. Do not
 mix them.
 
+> **Production requirement.** Each variant's NetworkPolicy is part of the
+> variant, and applying the variant without it is demo-only. The sandbox
+> NetworkPolicy and the gateway egress policy (the API server is cluster-specific)
+> are separate and equally required; see the
+> [production checklist](../../docs/optional-hardening.md#6-production-checklist)
+> and the
+> [gateway egress recipe](../../docs/optional-hardening.md#gateway-egress-required-for-production).
+> For SSO, run [`scripts/preflight-sso.sh`](../../scripts/preflight-sso.sh)
+> after applying the variant and before sending real traffic.
+
 Each variant also ships a NetworkPolicy, applied by the same directory apply:
 
 - `ingress/61-networkpolicy.yaml` allows only Traefik pods to reach the gateway
@@ -27,7 +37,8 @@ Each variant also ships a NetworkPolicy, applied by the same directory apply:
 The policies assume Traefik's `app.kubernetes.io/name: traefik` pod label.
 Adjust the selector for another implementation or a `hostNetwork` install; see
 [optional hardening](../../docs/optional-hardening.md) for the probe caveat and
-verification commands.
+verification commands. Keep the policies: an exposure without its NetworkPolicy
+is demo-only.
 
 ## Applying a variant
 
@@ -69,10 +80,13 @@ Secrets imperatively (commands below) before applying the directory.
 2. Set `DSH_TRUSTED_HOSTS` in the SandboxTemplate to the same public host:
    the gateway forwards the browser's `Host`, and DSH rejects unknown hosts on
    `/api` (see `../10-sandboxtemplate.yaml`).
-3. Set `COOKIE_SECURE=true` on the gateway once the Ingress serves HTTPS:
+3. Set `COOKIE_SECURE=true` and remove the plain-HTTP acknowledgement once the
-   `kubectl -n dsh-demo set env deploy/dsh-gateway COOKIE_SECURE=true`. The
+   Ingress serves HTTPS:
-   base manifest keeps `false` so the plain-HTTP port-forward demo works; a
+   `kubectl -n dsh-demo set env deploy/dsh-gateway COOKIE_SECURE=true ALLOW_INSECURE_COOKIES-`.
-   `Secure` cookie is never sent over HTTP, which silently breaks login.
+   The base manifest keeps `false` + `ALLOW_INSECURE_COOKIES=1` so the
+   plain-HTTP port-forward demo works; a `Secure` cookie is never sent over HTTP,
+   which silently breaks login, while the acknowledgement must not survive into
+   production.
 4. Do not attach buffering or compression middlewares to this router: they
    break WebSocket upgrades and streaming.
 5. `61-networkpolicy.yaml` is part of this variant: it allows only Traefik pods
@@ -116,14 +130,23 @@ kubectl -n dsh-demo create secret tls dsh-demo-tls --cert=tls.crt --key=tls.key
 
 # 3. Enable SSO on the gateway and trust the public host in the template.
 kubectl -n dsh-demo set env deploy/dsh-gateway \
-  AUTH_PROXY_HEADER=X-Forwarded-User COOKIE_SECURE=true
+  AUTH_PROXY_HEADER=X-Forwarded-User COOKIE_SECURE=true ALLOW_INSECURE_COOKIES-
 # then set DSH_TRUSTED_HOSTS=dsh-demo.example.com in the SandboxTemplate
 # (see ../10-sandboxtemplate.yaml) and re-apply it.
 
 # 4. Apply the variant.
 kubectl apply -f manifests/exposure/gateway-api-sso/
+
+# 5. Preflight: fails loudly on missing Secrets, a bad oauth2-proxy cookie
+#    secret, missing gateway SSO env, a dangling TLS reference, leftover
+#    placeholders, or a second path to the gateway.
+./scripts/preflight-sso.sh
 ```
 
+The preflight is read-only and exits non-zero on any failure, naming the exact
+fix. Run it again after rotating a Secret or changing the public host; it also
+verifies that the oauth2-proxy cookie secret decodes to 16, 24 or 32 bytes.
+
 ### SSO trust boundary
 
 `AUTH_PROXY_HEADER` is opt-in and deliberately unset in the base gateway
@@ -141,8 +164,14 @@ takes all of these:
    impersonate any user.
 3. Keep `75-networkpolicies.yaml` with the variant. It enforces the boundary in
    the network layer (gateway ← oauth2-proxy ← Traefik, and limited oauth2-proxy
-   egress). A custom exposure without an equivalent policy has no network
+   egress). This is required, not optional: an exposure without the policy is
+   demo-only, and a custom exposure without an equivalent policy has no network
    enforcement.
+4. Apply the gateway egress policy too: the gateway talks to the Kubernetes API
+   and to sandbox pods, and `75-networkpolicies.yaml` intentionally leaves that
+   direction unrestricted because the API-server endpoint is cluster-specific.
+   See
+   [gateway egress](../../docs/optional-hardening.md#gateway-egress-required-for-production).
 
 Also terminate TLS in front of the gateway (the Gateway listener does) and
 leave `COOKIE_SECURE=true` so the session cookie never travels in clear text.

examples/dsh-agents-as-a-service/manifests/exposure/gateway-api-sso/72-oauth2-proxy.yaml

@@ -25,8 +25,9 @@
 # TLS terminates at the Gateway listener (70-gateway.yaml); keep
 # --cookie-secure=true and COOKIE_SECURE=true on the gateway.
 #
-# The image is pinned to quay.io/oauth2-proxy/oauth2-proxy:v7.15.5
+# The image is digest-pinned: quay.io/oauth2-proxy/oauth2-proxy:v7.15.5@sha256:...
-# (versions.env: OAUTH2_PROXY_IMAGE). Credentials come from the
+# (versions.env: OAUTH2_PROXY_IMAGE). The digest is the immutable multi-arch
+# index, so the tag can never be moved under us. Credentials come from the
 # "oauth2-proxy" Secret (see 73-oauth2-proxy-secret.yaml.example); this
 # manifest never carries secrets.
 apiVersion: apps/v1
@@ -61,7 +62,7 @@ spec:
           type: RuntimeDefault
       containers:
         - name: oauth2-proxy
-          image: quay.io/oauth2-proxy/oauth2-proxy:v7.15.5
+          image: quay.io/oauth2-proxy/oauth2-proxy:v7.15.5@sha256:8498b0d0ef0a7b29686414000a08aee467f02d0299c9ed1e006a8f33fc017916
           imagePullPolicy: IfNotPresent
           securityContext:
             allowPrivilegeEscalation: false

examples/dsh-agents-as-a-service/manifests/exposure/gateway-api-sso/75-networkpolicies.yaml

@@ -1,5 +1,5 @@
-# OPTIONAL with the SSO exposure variant: enforce the trust boundary at the
+# REQUIRED with the SSO exposure variant: enforce the trust boundary at the
-# network layer.
+# network layer. Applying the SSO variant without this file is demo-only.
 #
 # The chain is Traefik (Gateway API) -> oauth2-proxy -> dsh-gateway. These
 # policies make it the ONLY chain:
@@ -8,8 +8,9 @@
 #   - oauth2-proxy egress is limited to DNS, public HTTPS (GitHub) and the
 #     gateway.
 # The gateway's own egress (Kubernetes API, sandbox pods) is intentionally not
-# restricted here: the API-server endpoint is cluster-specific. See
+# restricted here: the API-server endpoint is cluster-specific. Add it for
-# ../../../docs/optional-hardening.md for that recipe.
+# production. See
+# ../../../docs/optional-hardening.md#gateway-egress-required-for-production.
 #
 # This manifest assumes Traefik, matching gatewayClassName: traefik in
 # 70-gateway.yaml. Adjust the app.kubernetes.io/name selector for another

examples/dsh-agents-as-a-service/manifests/exposure/ingress/60-ingress.yaml

@@ -14,8 +14,13 @@
 #      DSH_TRUSTED_HOSTS to this host so DSH accepts the forwarded Host/Origin
 #      on /api.
 #   2. Gateway Deployment (manifests/50-gateway.yaml): set COOKIE_SECURE to
-#      "true" once this Ingress serves HTTPS, so the session cookie is Secure.
+#      "true" and remove ALLOW_INSECURE_COOKIES once this Ingress serves HTTPS,
-#      The base manifest sets "false" for the plain-HTTP port-forward demo.
+#      so the session cookie is Secure:
+#        kubectl -n dsh-demo set env deploy/dsh-gateway \
+#          COOKIE_SECURE=true ALLOW_INSECURE_COOKIES-
+#      The base manifest sets "false" + ALLOW_INSECURE_COOKIES=1 for the
+#      plain-HTTP port-forward demo; without the acknowledgement the gateway
+#      refuses to start.
 #
 # WebSocket support is REQUIRED: the browser talks to /u/<user>/... and DSH
 # uses WebSockets for live session traffic. Traefik upgrades WS/SSE
@@ -24,9 +29,11 @@
 # and upgrades. `path: /` Prefix covers the landing page and every per-user
 # proxy path, so no per-sandbox Ingress is needed.
 #
-# 61-networkpolicy.yaml is part of this variant: it restricts the gateway's
+# 61-networkpolicy.yaml is part of this variant and required for production:
-# ingress to Traefik pods. Adjust its selector if your ingress controller uses
+# it restricts the gateway's ingress to Traefik pods. Adjust its selector if
-# a different label or hostNetwork.
+# your ingress controller uses a different label or hostNetwork. The sandbox
+# and gateway-egress NetworkPolicies are separate requirements; see
+# ../../../docs/optional-hardening.md#6-production-checklist.
 apiVersion: networking.k8s.io/v1
 kind: Ingress
 metadata:

examples/dsh-agents-as-a-service/manifests/exposure/ingress/61-networkpolicy.yaml

@@ -1,11 +1,16 @@
-# OPTIONAL with the Ingress exposure variant: restrict the gateway's ingress
+# REQUIRED with the Ingress exposure variant for production: restrict the
-# to the ingress controller.
+# gateway's ingress to the ingress controller. Applying the variant without
+# this policy is demo-only.
 #
 # This manifest assumes Traefik, matching this variant's
 # `ingressClassName: traefik`. Traefik's Helm chart labels its pods
 # app.kubernetes.io/name=traefik; adjust the selector for another controller or
 # for a hostNetwork install (where the source is the node IP, not a pod IP).
 #
+# The sandbox NetworkPolicy and the gateway egress policy are separate and also
+# required for production; see
+# ../../../docs/optional-hardening.md#6-production-checklist.
+#
 # NetworkPolicy enforcement of kubelet probe traffic is CNI-dependent. If the
 # gateway starts failing its /healthz probes, allow the node CIDR on port 8080
 # or remove this policy. See ../../../docs/optional-hardening.md.

examples/dsh-agents-as-a-service/manifests/optional/README.md

@@ -23,6 +23,12 @@ It requires a CNI that enforces `NetworkPolicy`. The selector uses the
 agent-sandbox controller's pod tracking label, so the policy applies to
 existing warm-pool and claimed sandboxes without recreation.
 
+**This is opt-in for the demo but required for production.** Without it every
+tenant can reach every other tenant and cluster-internal endpoints. Production
+also needs the gateway egress policy (cluster-specific API-server endpoint) and
+the exposure variant's policy; see the
+[production checklist](../../docs/optional-hardening.md#6-production-checklist).
+
 ## gVisor, nodeSelector and provider keys
 
 These are configured in the main manifests or with an extra Secret:

examples/dsh-agents-as-a-service/manifests/optional/network-policy/10-sandbox-networkpolicy.yaml

@@ -1,9 +1,15 @@
-# OPTIONAL, opt-in tenant network policy for the DSH sandboxes.
+# OPTIONAL for the base walkthrough, REQUIRED for production. Opt-in tenant
+# network policy for the DSH sandboxes: without it every tenant can reach every
+# other tenant and cluster-internal endpoints.
 #
 # It is NOT part of the top-level walkthrough. Apply and delete it explicitly:
 #   kubectl apply  -f manifests/optional/network-policy/
 #   kubectl delete -f manifests/optional/network-policy/
 #
+# Production also needs the gateway egress policy (cluster-specific API-server
+# endpoint) and the exposure variant's policy, plus gVisor
+# (docs/optional-hardening.md#6-production-checklist).
+#
 # The selector uses the agent-sandbox controller's pod tracking label, which is
 # present on every Sandbox pod (including warm-pool spares), so the policy
 # applies to existing sandboxes without recreating them. The SandboxTemplate

examples/dsh-agents-as-a-service/scripts/preflight-sso.sh

@@ -0,0 +1,234 @@
+#!/usr/bin/env bash
+# Preflight for the gateway-api-sso exposure variant.
+#
+# Run this AFTER creating the oauth2-proxy/TLS Secrets, setting the gateway
+# env and applying manifests/exposure/gateway-api-sso/, and BEFORE sending real
+# traffic. It checks the configuration that is easy to get wrong and whose
+# failure is either silent (login appears to work but the gateway still asks
+# for its own token) or dangerous (a spoofable identity header, a placeholder
+# host, a TLS Secret that does not exist).
+#
+# Checks:
+#   1. kubectl reaches the cluster and the SSO objects exist;
+#   2. the oauth2-proxy Secret has client-id, client-secret and a cookie-secret
+#      that decodes to 16, 24 or 32 bytes; the TLS Secret exists;
+#   3. deploy/dsh-gateway has AUTH_PROXY_HEADER=X-Forwarded-User and
+#      COOKIE_SECURE=true (both are opt-in and both are required for SSO over
+#      TLS);
+#   4. the Gateway's TLS certificate reference resolves to an existing Secret;
+#   5. no your-github-org / dsh-demo.example.com placeholder is left in the
+#      applied oauth2-proxy args, Gateway listeners or HTTPRoute hostnames;
+#   6. (warning) no Ingress in the namespace creates a second path to
+#      dsh-gateway. With SSO enabled the Service must be reachable only through
+#      oauth2-proxy.
+#
+# Exit status: 0 when every check passes (warnings allowed), 1 on any failure.
+# Every failure prints the fix. This script only reads cluster state.
+#
+# Usage:
+#   examples/dsh-agents-as-a-service/scripts/preflight-sso.sh
+#
+# Environment overrides:
+#   NAMESPACE        namespace (default: dsh-demo)
+#   GATEWAY_DEPLOY   gateway Deployment name (default: dsh-gateway)
+#   OAUTH_DEPLOY     oauth2-proxy Deployment name (default: oauth2-proxy)
+#   OAUTH_SECRET     oauth2-proxy Secret name (default: oauth2-proxy)
+#   TLS_SECRET       TLS Secret name the Gateway should reference (default:
+#                    dsh-demo-tls)
+set -euo pipefail
+cd "$(dirname "$0")/.."
+
+NS="${NAMESPACE:-dsh-demo}"
+GATEWAY_DEPLOY="${GATEWAY_DEPLOY:-dsh-gateway}"
+OAUTH_DEPLOY="${OAUTH_DEPLOY:-oauth2-proxy}"
+OAUTH_SECRET="${OAUTH_SECRET:-oauth2-proxy}"
+TLS_SECRET="${TLS_SECRET:-dsh-demo-tls}"
+
+FAILED=0
+pass() { printf 'PASS  %s\n' "$*"; }
+warn() { printf 'WARN  %s\n' "$*" >&2; }
+fail() { printf 'FAIL  %s\n' "$*" >&2; FAILED=1; }
+
+if ! command -v kubectl >/dev/null 2>&1; then
+  echo "FAIL  kubectl is not installed; install it and select the target context" >&2
+  exit 1
+fi
+
+if ! kubectl -n "$NS" get deployment "$GATEWAY_DEPLOY" >/dev/null 2>&1; then
+  echo "FAIL  deploy/$GATEWAY_DEPLOY not found in namespace $NS." >&2
+  echo "      Apply the base manifests first: kubectl apply -f manifests/" >&2
+  echo "      Then apply the variant: kubectl apply -f manifests/exposure/gateway-api-sso/" >&2
+  exit 1
+fi
+
+echo "== Secrets"
+# check_secret_key <secret> <key> <hint>
+check_secret_key() {
+  local secret=$1 key=$2 hint=$3 value escaped
+  # Kubernetes JSONPath treats "." as a path separator; escape it in keys such
+  # as tls.crt.
+  escaped=${key//./\\.}
+  value=$(kubectl -n "$NS" get secret "$secret" -o jsonpath="{.data.${escaped}}" 2>/dev/null || true)
+  if [ -n "$value" ]; then
+    pass "Secret $secret has non-empty key '$key'"
+  else
+    fail "Secret $secret is missing a non-empty '$key' key. $hint"
+  fi
+}
+
+check_secret_key "$OAUTH_SECRET" client-id \
+  "Create it from manifests/exposure/gateway-api-sso/73-oauth2-proxy-secret.yaml.example."
+check_secret_key "$OAUTH_SECRET" client-secret \
+  "Create it from manifests/exposure/gateway-api-sso/73-oauth2-proxy-secret.yaml.example."
+check_secret_key "$OAUTH_SECRET" cookie-secret \
+  "Create it from manifests/exposure/gateway-api-sso/73-oauth2-proxy-secret.yaml.example."
+
+# The cookie secret must be URL-safe unpadded base64 of 16, 24 or 32 bytes;
+# oauth2-proxy refuses anything else (the classic error is "44 bytes").
+if COOKIE_B64=$(kubectl -n "$NS" get secret "$OAUTH_SECRET" \
+  -o jsonpath='{.data.cookie-secret}' 2>/dev/null); then
+  if [ -n "$COOKIE_B64" ]; then
+    if ! COOKIE_LEN=$(printf '%s' "$COOKIE_B64" | base64 -d 2>/dev/null | wc -c); then
+      fail "Secret $OAUTH_SECRET key 'cookie-secret' is not valid base64. Generate it with: python3 -c 'import secrets; print(secrets.token_urlsafe(32))'"
+    else
+      case "$COOKIE_LEN" in
+        16 | 24 | 32) pass "oauth2-proxy cookie-secret decodes to $COOKIE_LEN bytes" ;;
+        *)
+          fail "oauth2-proxy cookie-secret decodes to $COOKIE_LEN bytes; it must be 16, 24 or 32. Generate a URL-safe unpadded value with: python3 -c 'import secrets; print(secrets.token_urlsafe(32))'"
+          ;;
+      esac
+    fi
+  fi
+fi
+
+check_secret_key "$TLS_SECRET" tls.crt \
+  "Create the TLS Secret with: kubectl -n $NS create secret tls $TLS_SECRET --cert=tls.crt --key=tls.key"
+check_secret_key "$TLS_SECRET" tls.key \
+  "Create the TLS Secret with: kubectl -n $NS create secret tls $TLS_SECRET --cert=tls.crt --key=tls.key"
+
+echo
+echo "== Gateway SSO configuration (deploy/$GATEWAY_DEPLOY)"
+GATEWAY_ENV=$(kubectl -n "$NS" get deployment "$GATEWAY_DEPLOY" \
+  -o jsonpath='{range .spec.template.spec.containers[*].env[*]}{.name}={.value}{"\n"}{end}')
+
+# env_value <NAME>: print the literal env value, or nothing when unset.
+env_value() {
+  printf '%s\n' "$GATEWAY_ENV" | awk -F= -v key="$1" '$1 == key { sub(/^[^=]*=/, ""); print }'
+}
+env_is_set() {
+  printf '%s\n' "$GATEWAY_ENV" | awk -F= -v key="$1" '$1 == key { found = 1 } END { exit found ? 0 : 1 }'
+}
+
+if ! env_is_set AUTH_PROXY_HEADER; then
+  fail "AUTH_PROXY_HEADER is not set on deploy/$GATEWAY_DEPLOY, so the gateway ignores oauth2-proxy's identity header and users are still asked for the gateway token. Fix: kubectl -n $NS set env deploy/$GATEWAY_DEPLOY AUTH_PROXY_HEADER=X-Forwarded-User"
+elif [ "$(env_value AUTH_PROXY_HEADER)" != "X-Forwarded-User" ]; then
+  fail "AUTH_PROXY_HEADER is '$(env_value AUTH_PROXY_HEADER)', expected 'X-Forwarded-User'. Fix: kubectl -n $NS set env deploy/$GATEWAY_DEPLOY AUTH_PROXY_HEADER=X-Forwarded-User"
+else
+  pass "AUTH_PROXY_HEADER=X-Forwarded-User"
+fi
+
+if ! env_is_set COOKIE_SECURE; then
+  fail "COOKIE_SECURE is not set on deploy/$GATEWAY_DEPLOY; the session cookie must be Secure behind TLS. Fix: kubectl -n $NS set env deploy/$GATEWAY_DEPLOY COOKIE_SECURE=true"
+elif [ "$(env_value COOKIE_SECURE | tr '[:upper:]' '[:lower:]')" != "true" ]; then
+  fail "COOKIE_SECURE is '$(env_value COOKIE_SECURE)', expected 'true' behind TLS. Fix: kubectl -n $NS set env deploy/$GATEWAY_DEPLOY COOKIE_SECURE=true"
+else
+  pass "COOKIE_SECURE=true"
+fi
+
+if env_is_set ALLOW_INSECURE_COOKIES; then
+  warn "ALLOW_INSECURE_COOKIES is still set on deploy/$GATEWAY_DEPLOY. It is ignored while COOKIE_SECURE=true but is a footgun: remove it with 'kubectl -n $NS set env deploy/$GATEWAY_DEPLOY ALLOW_INSECURE_COOKIES-'."
+fi
+
+echo
+echo "== SSO objects and placeholders"
+if kubectl -n "$NS" get deployment "$OAUTH_DEPLOY" >/dev/null 2>&1; then
+  pass "deploy/$OAUTH_DEPLOY exists"
+  OAUTH_ARGS=$(kubectl -n "$NS" get deployment "$OAUTH_DEPLOY" \
+    -o jsonpath='{range .spec.template.spec.containers[*].args[*]}{@}{"\n"}{end}')
+else
+  OAUTH_ARGS=""
+  fail "deploy/$OAUTH_DEPLOY not found. Apply the variant: kubectl apply -f manifests/exposure/gateway-api-sso/"
+fi
+
+# GitHub org restriction is the only authorization in the shipped variant.
+# --email-domain=* is acceptable only because --github-org narrows membership;
+# a missing or empty org value would accept any GitHub account.
+if [ -n "$OAUTH_ARGS" ]; then
+  if printf '%s\n' "$OAUTH_ARGS" | grep -q '^--provider=github$'; then
+    pass "oauth2-proxy uses --provider=github"
+  else
+    fail "oauth2-proxy is not configured with --provider=github. Fix: add --provider=github to deploy/$OAUTH_DEPLOY."
+  fi
+  if printf '%s\n' "$OAUTH_ARGS" | grep -Eq '^--github-org=.+$'; then
+    pass "oauth2-proxy restricts membership with --github-org"
+  else
+    fail "oauth2-proxy has no non-empty --github-org. Fix: set --github-org=<your-org> in deploy/$OAUTH_DEPLOY; otherwise --email-domain=* accepts any GitHub account."
+  fi
+fi
+
+if kubectl -n "$NS" get httproute dsh-gateway >/dev/null 2>&1; then
+  pass "HTTPRoute dsh-gateway exists"
+  ROUTE_STATE=$(kubectl -n "$NS" get httproute dsh-gateway \
+    -o jsonpath='{.spec.hostnames[*]}' 2>/dev/null || true)
+else
+  ROUTE_STATE=""
+  fail "HTTPRoute dsh-gateway not found. Apply the variant: kubectl apply -f manifests/exposure/gateway-api-sso/"
+fi
+
+if kubectl -n "$NS" get gateway dsh-gateway >/dev/null 2>&1; then
+  pass "Gateway dsh-gateway exists"
+  GATEWAY_STATE=$(kubectl -n "$NS" get gateway dsh-gateway \
+    -o jsonpath='{range .spec.listeners[*]}{.hostname}{"\n"}{end}' 2>/dev/null || true)
+  CERT_REFS=$(kubectl -n "$NS" get gateway dsh-gateway \
+    -o jsonpath='{range .spec.listeners[*].tls.certificateRefs[*]}{.namespace}{"/"}{.name}{"\n"}{end}' 2>/dev/null || true)
+else
+  GATEWAY_STATE=""
+  CERT_REFS=""
+  fail "Gateway dsh-gateway not found. Apply the variant: kubectl apply -f manifests/exposure/gateway-api-sso/"
+fi
+
+# Placeholders are the default values in the committed manifests. They reach
+# the cluster if the variant is applied before editing them.
+PLACEHOLDER_RE='your-github-org|dsh-demo\.example\.com'
+PLACEHOLDER_STATE=$(printf '%s\n%s\n%s\n' "$OAUTH_ARGS" "$ROUTE_STATE" "$GATEWAY_STATE")
+if printf '%s\n' "$PLACEHOLDER_STATE" | grep -En "$PLACEHOLDER_RE" >/dev/null 2>&1; then
+  fail "the applied SSO objects still contain a placeholder (your-github-org or dsh-demo.example.com):"
+  printf '%s\n' "$PLACEHOLDER_STATE" | grep -En "$PLACEHOLDER_RE" | sed 's/^/      /' >&2
+  echo "      Replace --github-org, --redirect-url, the Gateway listener host and the HTTPRoute hostname with the real public FQDN and organization, then re-apply and restart the proxy." >&2
+else
+  pass "no your-github-org / dsh-demo.example.com placeholder in the applied SSO objects"
+fi
+
+# The Gateway must reference an existing TLS Secret; the default name is
+# dsh-demo-tls, but 70-gateway.yaml can be edited to another name.
+if [ -n "$CERT_REFS" ]; then
+  while IFS= read -r ref; do
+    [ -n "$ref" ] || continue
+    ref_ns=${ref%%/*}
+    ref_name=${ref#*/}
+    ref_ns=${ref_ns:-$NS}
+    if kubectl -n "$ref_ns" get secret "$ref_name" >/dev/null 2>&1; then
+      pass "Gateway TLS certificate reference ${ref_ns}/${ref_name} exists"
+    else
+      fail "Gateway references TLS Secret ${ref_ns}/${ref_name} but it does not exist. Create it (see manifests/exposure/gateway-api-sso/74-tls-secret.yaml.example)."
+    fi
+  done <<<"$CERT_REFS"
+else
+  warn "the Gateway has no TLS certificateRefs; SSO over plain HTTP would expose the session cookie. Terminate TLS at the Gateway listener."
+fi
+
+# A second path to the gateway defeats SSO: anyone who can reach
+# dsh-gateway:8080 can spoof X-Forwarded-User. This is a best-effort check.
+if kubectl -n "$NS" get ingress >/dev/null 2>&1; then
+  INGRESS_STATE=$(kubectl -n "$NS" get ingress -o json 2>/dev/null || true)
+  if printf '%s' "$INGRESS_STATE" | grep -q '"name":"dsh-gateway"'; then
+    fail "an Ingress in namespace $NS also routes to dsh-gateway. With SSO enabled the gateway must be reachable only through oauth2-proxy: delete the Ingress variant (kubectl delete -f manifests/exposure/ingress/)."
+  fi
+fi
+
+echo
+if [ "$FAILED" -ne 0 ]; then
+  echo "preflight-sso: FAILED - fix the items above before exposing the gateway." >&2
+  exit 1
+fi
+echo "preflight-sso: ok - the SSO variant looks correctly configured."

scripts/check-versions.sh

@@ -22,14 +22,48 @@ expect() { # <file> <literal>
 
 # Main Dockerfile build args
 expect Dockerfile "ARG DSH_VERSION=$DSH_VERSION"
+expect Dockerfile "ARG DSH_COMMIT=$DSH_COMMIT"
 expect Dockerfile "ARG PNPM_VERSION=$PNPM_VERSION"
 expect Dockerfile "ARG RELEASE_REVISION=$RELEASE_REVISION"
+expect Dockerfile "ARG NODE_BUILD_IMAGE=$NODE_BUILD_IMAGE"
+expect Dockerfile "ARG NODE_RUNTIME_IMAGE=$NODE_RUNTIME_IMAGE"
+# The build stage must fail closed when the tag no longer resolves to DSH_COMMIT.
+expect Dockerfile "git -C /src rev-parse HEAD"
+
+# Example gateway build base image
+expect examples/dsh-agents-as-a-service/gateway/Dockerfile \
+  "ARG GATEWAY_PYTHON_IMAGE=$GATEWAY_PYTHON_IMAGE"
 
 # Local configuration mirrored for humans
 expect .env.sample "DSH_VERSION=$DSH_VERSION"
+expect .env.sample "DSH_COMMIT=$DSH_COMMIT"
 expect .env.sample "PNPM_VERSION=$PNPM_VERSION"
 expect .env.sample "RELEASE_REVISION=$RELEASE_REVISION"
 
+# Human-facing docs embed the resolved commit in the build example and table.
+expect docs/main-image.md "$DSH_COMMIT"
+expect docs/versioning.md "$DSH_COMMIT"
+
+# Every container image is pinned to an immutable multi-arch index digest, not
+# a mutable tag. This is a supply-chain invariant: don't "fix" a failing check
+# by dropping the digest.
+for image_var in NODE_BUILD_IMAGE NODE_RUNTIME_IMAGE GATEWAY_PYTHON_IMAGE OAUTH2_PROXY_IMAGE; do
+  image_value="${!image_var:-}"
+  if ! printf '%s' "$image_value" | grep -qE '@sha256:[0-9a-f]{64}$'; then
+    err "versions.env: $image_var must be digest-pinned (name:tag@sha256:<64 hex>), got: ${image_value:-<unset>}"
+  fi
+done
+
+if ! printf '%s' "${DSH_COMMIT:-}" | grep -qE '^[0-9a-f]{40}$'; then
+  err "versions.env: DSH_COMMIT must be a full 40-character commit SHA, got: ${DSH_COMMIT:-<unset>}"
+fi
+
+# Build entrypoints must pass DSH_COMMIT rather than trusting the tag alone.
+expect Makefile "--build-arg DSH_COMMIT=\$(DSH_COMMIT)"
+for wf in build-main.yaml release.yaml ci-image.yaml; do
+  expect ".github/workflows/$wf" "DSH_COMMIT="
+done
+
 # Image references in the example manifests
 for f in \
   examples/dsh-agents-as-a-service/manifests/10-sandboxtemplate.yaml \
@@ -38,6 +72,10 @@ for f in \
 done
 expect examples/dsh-agents-as-a-service/manifests/50-gateway.yaml "image: $GATEWAY_IMAGE:$IDENTITY"
 
+# The oauth2-proxy exposure variant pins the digest, not the mutable tag.
+expect examples/dsh-agents-as-a-service/manifests/exposure/gateway-api-sso/72-oauth2-proxy.yaml \
+  "image: $OAUTH2_PROXY_IMAGE"
+
 # The gateway image must live below the repository image (one package per
 # example component, no unrelated top-level packages).
 case "$GATEWAY_IMAGE" in

scripts/set-version.sh

@@ -4,6 +4,11 @@
 #
 #   ./scripts/set-version.sh dsh-v0.2.2-rc.1        # new DSH ref, no revision
 #   ./scripts/set-version.sh dsh-v0.2.1-rc.5 r3    # same ref, new repo revision
+#
+# For a new DSH ref the script resolves the tag's commit with "git ls-remote"
+# (peeled ^{} commit first, tag ref as fallback) and rewrites DSH_COMMIT in
+# versions.env, the Dockerfile ARG default and .env.sample. A revision-only bump
+# at the same ref keeps the existing commit and needs no network access.
 set -euo pipefail
 cd "$(dirname "$0")/.."
 
@@ -23,9 +28,11 @@ if [ -n "$new_revision" ]; then
 fi
 
 # shellcheck source=/dev/null
-old_version="$(. ./versions.env; printf '%s' "$DSH_VERSION")"
+. ./versions.env
-# shellcheck source=/dev/null
+
-old_revision="$(. ./versions.env; printf '%s' "${RELEASE_REVISION:-}")"
+old_version="$DSH_VERSION"
+old_revision="${RELEASE_REVISION:-}"
+old_commit="${DSH_COMMIT:-}"
 
 old_identity="$old_version"
 [ -z "$old_revision" ] || old_identity="$old_version-$old_revision"
@@ -37,6 +44,29 @@ if [ "$old_identity" = "$new_identity" ]; then
   exit 0
 fi
 
+# Resolve the commit the new upstream tag points at. Annotated tags expose a
+# peeled ^{} line (the commit) and a tag-object line; prefer the peeled commit
+# and fall back to the tag ref for lightweight tags. A repository-only revision
+# bump keeps the already pinned commit, so it needs no network.
+new_commit="$old_commit"
+if [ "$new_version" != "$old_version" ] || [ -z "$new_commit" ]; then
+  if ! refs="$(git ls-remote --tags --exit-code "$DSH_REPO" \
+        "refs/tags/$new_version^{}" "refs/tags/$new_version")"; then
+    echo "set-version: upstream tag '$new_version' not found in $DSH_REPO" >&2
+    exit 1
+  fi
+  new_commit="$(printf '%s\n' "$refs" \
+    | awk -v t="refs/tags/$new_version^{}" '$2 == t {print $1}' | head -n1)"
+  if [ -z "$new_commit" ]; then
+    new_commit="$(printf '%s\n' "$refs" \
+      | awk -v t="refs/tags/$new_version" '$2 == t {print $1}' | head -n1)"
+  fi
+  if ! printf '%s' "$new_commit" | grep -qE '^[0-9a-f]{40}$'; then
+    echo "set-version: could not resolve a commit for '$new_version' in $DSH_REPO" >&2
+    exit 1
+  fi
+fi
+
 # Replace the identity first (it contains the base version), then the base
 # version itself. CHANGELOG.md is generated from tags, so it is left alone.
 while IFS= read -r file; do
@@ -48,17 +78,30 @@ while IFS= read -r file; do
   sed -i "s/$old_identity/$new_identity/g; s/$old_version/$new_version/g" "$file"
 done < <(git ls-files)
 
-# versions.env is authoritative: write both keys explicitly so an empty
+# versions.env is authoritative: write these keys explicitly so an empty
 # revision is stored as an empty value.
 sed -i "s/^DSH_VERSION=.*/DSH_VERSION=$new_version/" versions.env
 sed -i "s/^RELEASE_REVISION=.*/RELEASE_REVISION=$new_revision/" versions.env
+sed -i "s/^DSH_COMMIT=.*/DSH_COMMIT=$new_commit/" versions.env
 
 # Values stored separately from the full identity: Dockerfile ARG defaults and
 # the human-facing sample cannot be reached by the identity replacement above.
 sed -i "s/^ARG DSH_VERSION=.*/ARG DSH_VERSION=$new_version/" Dockerfile
 sed -i "s/^ARG RELEASE_REVISION=.*/ARG RELEASE_REVISION=$new_revision/" Dockerfile
+sed -i "s/^ARG DSH_COMMIT=.*/ARG DSH_COMMIT=$new_commit/" Dockerfile
 sed -i "s/^DSH_VERSION=.*/DSH_VERSION=$new_version/" .env.sample
 sed -i "s/^RELEASE_REVISION=.*/RELEASE_REVISION=$new_revision/" .env.sample
+sed -i "s/^DSH_COMMIT=.*/DSH_COMMIT=$new_commit/" .env.sample
+
+# The human-facing build examples embed the full SHA, which the version
+# replacement above cannot see. Keep them in step; check-versions.sh verifies.
+if [ -n "$old_commit" ] && [ "$old_commit" != "$new_commit" ]; then
+  for doc in docs/main-image.md docs/versioning.md; do
+    [ -f "$doc" ] || continue
+    sed -i "s/$old_commit/$new_commit/g" "$doc"
+  done
+fi
 
 echo "set-version: $old_identity -> $new_identity"
+echo "set-version: DSH_COMMIT=$new_commit"
 echo "set-version: run 'make check' and review the diff"

versions.env

@@ -2,10 +2,17 @@
 # repository. Consumed by the Makefile, build.sh, scripts/*.sh and the GitHub
 # Actions workflows. Never hard-code these values elsewhere: run "make check"
 # (scripts/check-versions.sh) to verify every pin.
+#
+# Every container image below is pinned to an immutable multi-arch index digest
+# (name:tag@sha256:...), not just a mutable tag. Bump the tag and the digest
+# together; scripts/check-versions.sh requires the digest form.
 
 # Upstream DeepSeek Harness source, and the ref this repository packages.
+# DSH_COMMIT is the full commit SHA that DSH_VERSION resolves to upstream; the
+# Dockerfile verifies the clone's HEAD against it and fails the build on drift.
 DSH_REPO=https://github.com/deepseek-ai/deepseek-harness.git
 DSH_VERSION=dsh-v0.2.1-rc.5
+DSH_COMMIT=b830ec950faba0a46dda564be3e2d854afed94f1
 PNPM_VERSION=11.28.5
 
 # Release identity = DSH_VERSION plus an optional repository revision.
@@ -15,6 +22,13 @@ PNPM_VERSION=11.28.5
 # repository-only change at the same ref becomes -r2.
 RELEASE_REVISION=
 
+# Base images for the main DSH Web image (root Dockerfile), pinned by digest.
+NODE_BUILD_IMAGE=docker.io/node:24-trixie@sha256:8c761eca2bf7eec965f946cf47b8090143cb41f45f2f8699af0cc0298d2d2d19
+NODE_RUNTIME_IMAGE=docker.io/node:24-trixie-slim@sha256:54f84b4cf8432b21aaffd5d3ce8d41e12cea0d10d33c09d2f3c9879d49d6b446
+
+# Base image for the example gateway (examples/dsh-agents-as-a-service/gateway).
+GATEWAY_PYTHON_IMAGE=docker.io/python:3.12-slim@sha256:aa943ce411423c7582288f18707ff66eddcbaeb510502d747a72aeb34f30d159
+
 # Control-plane versions used by the examples and their manifests.
 # The matching SHA-256s pin the release manifests that CI downloads and
 # applies; update both the version and the digest when bumping either pin.
@@ -22,7 +36,7 @@ AGENT_SANDBOX_VERSION=v1.0.9
 AGENT_SANDBOX_MANIFEST_SHA256=4bf9ee5558e9a663f91cfa5963e96f2591bfaa1dcf79f03bfab65bc5d65cc699
 GATEWAY_API_VERSION=v1.2.1
 GATEWAY_API_MANIFEST_SHA256=97598bf6ab3b33b9b5c5432bdd24de091e4e9c3aa0575ebb0710a2a19cd64d64
-OAUTH2_PROXY_IMAGE=quay.io/oauth2-proxy/oauth2-proxy:v7.15.5
+OAUTH2_PROXY_IMAGE=quay.io/oauth2-proxy/oauth2-proxy:v7.15.5@sha256:8498b0d0ef0a7b29686414000a08aee467f02d0299c9ed1e006a8f33fc017916
 
 # Registry layout: the main image is the repository itself, and every example
 # component is a nested package below it (<registry>/<owner>/<repo>/<example>/<component>).