From 65e79880c81e8bbefac5d47b03cc29455437d0b5 Mon Sep 17 00:00:00 2001
From: teknium1 <127238744+teknium1@users.noreply.github.com>
Date: Wed, 23 Sep 2026 07:11:02 -0700
Subject: [PATCH] ci(e2e): build the Ink TUI for the terminal suite; run the
 upgrade suite in its own job

tests/e2e/core/terminal drives the real `hermes --tui` over a PTY, so the e2e
job now installs the Node workspaces and builds ui-tui, and
HERMES_E2E_REQUIRE_TUI=1 makes a missing build fail instead of skip.

tests/e2e/core/upgrade runs a real N-1 -> HEAD `hermes update`: it needs full
history + tags, bubblewrap (every updater runs sandboxed so it can never reach
a real gateway or systemd), the warm uv cache, and up to ~15 min for one file.
It gets its own 60-minute job instead of stretching the e2e job.
---
 .github/workflows/tests.yml | 112 +++++++++++++++++++++++++++++++++++-
 1 file changed, 111 insertions(+), 1 deletion(-)

diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.yml
index 191bf29d02..a7ca83ed6c 100644
--- a/.github/workflows/tests.yml
+++ b/.github/workflows/tests.yml
@@ -182,6 +182,13 @@ jobs:
         with:
           node-version: 26
 
+      - name: Install Node deps and build the Ink TUI
+        # tests/e2e/core/terminal drives the real `hermes --tui` over a PTY;
+        # HERMES_E2E_REQUIRE_TUI=1 below turns a missing build into a failure.
+        uses: ./.github/actions/retry
+        with:
+          command: npm ci --ignore-scripts --no-audit --no-fund && npm run build --prefix ui-tui
+
       - name: Install ripgrep (prebuilt binary)
         run: |
           set -euo pipefail
@@ -253,9 +260,11 @@ jobs:
         # One subprocess per file, in parallel: the core suites spawn real
         # processes (serve, gateway, tui_gateway, MCP servers, SQLite writers)
         # and must not share interpreter state.
+        # tests/e2e/core/upgrade runs in its own job (e2e-upgrade) below.
         run: |
           source .venv/bin/activate
-          scripts/run_tests.sh --include-integration tests/e2e
+          mapfile -t files < <(find tests/e2e -name 'test_*.py' -not -path 'tests/e2e/core/upgrade/*' | sort)
+          scripts/run_tests.sh --include-integration "${files[@]}"
         env:
           # Multi-process episodes (torture chamber, compaction kill -9,
           # gateway liveness, delivery exactly-once through a real gateway,
@@ -265,6 +274,107 @@ jobs:
           # exactly-once/compaction suites are race detectors, and a rare
           # corruption that passes on retry is still a corruption.
           HERMES_TEST_FILE_RETRIES: "0"
+          HERMES_E2E_REQUIRE_TUI: "1"
+          OPENROUTER_API_KEY: ""
+          OPENAI_API_KEY: ""
+          NOUS_API_KEY: ""
+
+  e2e-upgrade:
+    # tests/e2e/core/upgrade: a real N-1 -> HEAD `hermes update` (clean,
+    # autostash, killed mid-pull / mid-deps, offline), fresh-process import and
+    # entrypoint smoke, and the config round-trip property matrix. Its own job:
+    # it needs full history + tags, bubblewrap, and one file runs ~5-15 min.
+    runs-on: ubuntu-latest-32-core
+    timeout-minutes: 60
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          # N-1 = `git describe --tags --abbrev=0 HEAD~1`.
+          fetch-depth: 0
+          fetch-tags: true
+
+      - name: Set up Node
+        # `hermes update` builds the web UI / TUI workspaces.
+        uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4
+        with:
+          node-version: 26
+
+      - name: Install ripgrep (prebuilt binary)
+        run: |
+          set -euo pipefail
+          RG_VERSION=15.1.0
+          RG_SHA256=1c9297be4a084eea7ecaedf93eb03d058d6faae29bbc57ecdaf5063921491599
+          RG_TARBALL=ripgrep-${RG_VERSION}-x86_64-unknown-linux-musl.tar.gz
+          curl -sSfL --retry 3 --retry-delay 5 -o "$RG_TARBALL" \
+            "https://github.com/BurntSushi/ripgrep/releases/download/${RG_VERSION}/${RG_TARBALL}"
+          echo "${RG_SHA256}  ${RG_TARBALL}" | sha256sum -c -
+          tar -xzf "$RG_TARBALL"
+          sudo mv "ripgrep-${RG_VERSION}-x86_64-unknown-linux-musl/rg" /usr/local/bin/rg
+          rm -rf "$RG_TARBALL" "ripgrep-${RG_VERSION}-x86_64-unknown-linux-musl"
+          rg --version
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@fac544c07dec837d0ccb6301d7b5580bf5edae39 # 8.2.0
+        with:
+          # Pin the uv version: unpinned, setup-uv resolves "latest" by
+          # fetching a manifest from raw.githubusercontent.com on EVERY job —
+          # a transient fetch failure fails the whole job (2026-07-28 slice-5
+          # incident). Pinned, the binary downloads directly; no manifest hop.
+          # Newer than the unit job's pin on purpose: 0.9.28 only knows CPython
+          # 3.11.14, whose bundled SQLite has the WAL-reset bug, so Hermes runs
+          # state.db in DELETE mode and the WAL torture chamber would skip.
+          version: "0.12.13"
+          # Persist uv's download/wheel cache (~/.cache/uv) across runs.
+          # Keyed on the dependency manifests, so the cache is reused until
+          # pyproject.toml or uv.lock changes. `uv sync` still runs every
+          # time, but resolves from the warm cache instead of re-downloading
+          # and re-building wheels.
+          enable-cache: true
+          cache-dependency-glob: |
+            pyproject.toml
+            uv.lock
+
+      - name: Set up Python 3.11
+        run: uv python install 3.11.15
+
+      - name: Install dependencies
+        # `uv sync --locked` installs the exact pinned set from uv.lock (and
+        # fails if the lock is out of sync with pyproject.toml), giving a
+        # reproducible env. It also creates .venv itself, so no separate
+        # `uv venv` step is needed.
+        #
+        # Same extras as the test job's sync above: the hermetic test env
+        # forbids mid-run pip installs (HERMES_DISABLE_LAZY_INSTALLS=1 in
+        # tests/conftest.py), so lazy-install SDKs exercised by tests must be
+        # in the venv up front.
+        uses: ./.github/actions/retry
+        with:
+          command: uv sync --locked --python 3.11.15 --extra all --extra dev --extra anthropic --extra mistral --extra fal --extra modal --extra daytona --extra parallel-web
+
+      - name: Install bubblewrap
+        # Every spawned updater runs in bwrap (own PID namespace, no user
+        # systemd bus, only the test tmp writable). Ubuntu 24.04 restricts
+        # unprivileged user namespaces, which bwrap needs.
+        run: |
+          sudo apt-get update -qq
+          sudo apt-get install -y -qq bubblewrap
+          sudo sysctl -w kernel.apparmor_restrict_unprivileged_userns=0 || true
+          bwrap --unshare-pid --dev-bind / / true && echo "bwrap ok"
+
+      - name: Require a WAL-capable SQLite
+        # The state.db suites skip on a WAL-reset-vulnerable SQLite; fail
+        # instead of reporting green over zero coverage.
+        run: |
+          source .venv/bin/activate
+          python -c "import sqlite3, hermes_state_wal as w; print('sqlite', sqlite3.sqlite_version); assert not w.is_sqlite_wal_reset_vulnerable()"
+
+      - name: Run upgrade e2e tests
+        run: |
+          source .venv/bin/activate
+          scripts/run_tests.sh --include-integration tests/e2e/core/upgrade
+        env:
+          HERMES_TEST_FILE_TIMEOUT: "3000"
           OPENROUTER_API_KEY: ""
           OPENAI_API_KEY: ""
           NOUS_API_KEY: ""