fix(plugins): isolate profile runtime state

.github/actions/detect-changes/action.yml

@@ -15,6 +15,9 @@ outputs:
   python:
     description: Run Python tests / ruff / ty / windows-footguns.
     value: ${{ steps.classify.outputs.python }}
+  python_prod:
+    description: Python changes outside tests/ — gates product jobs (Desktop E2E, Docker).
+    value: ${{ steps.classify.outputs.python_prod }}
   frontend:
     description: Run the TypeScript testing matrix + desktop build.
     value: ${{ steps.classify.outputs.frontend }}

.github/workflows/ci.yml

@@ -42,6 +42,7 @@ jobs:
     timeout-minutes: 10
     outputs:
       python: ${{ steps.classify.outputs.python }}
+      python_prod: ${{ steps.classify.outputs.python_prod }}
       frontend: ${{ steps.classify.outputs.frontend }}
       site: ${{ steps.classify.outputs.site }}
       scan: ${{ steps.classify.outputs.scan }}
@@ -89,7 +90,19 @@ jobs:
   e2e-desktop:
     name: Desktop E2E
     needs: detect
-    if: needs.detect.outputs.python == 'true' || needs.detect.outputs.frontend == 'true'
+    # python_prod (not python): the Playwright suite exercises the built app
+    # + `hermes serve` backend, which never import anything under tests/.
+    # Tests-only PRs (~17% of commits) skip this 5-minute job — the longest
+    # single job in the workflow — while still running the full pytest lanes.
+    #
+    # ⛔ TEMPORARILY DISABLED (Aug 2, 2026, Teknium) — the suite is red on
+    # every PR and on main itself since the Aug 1 night engines/npm churn
+    # (#76499 → #76562 → #76575): the mock-backend Electron window never
+    # gets a title, so boot/chat/setup/interim specs all fail identically
+    # regardless of the PR's diff (verified on #76573 and the docs-only
+    # #76582). Tracking issue: #76627 (assigned: Ari). To re-enable,
+    # delete the `false &&` below — nothing else changed.
+    if: ${{ false && (needs.detect.outputs.python_prod == 'true' || needs.detect.outputs.frontend == 'true') }}
     uses: ./.github/workflows/e2e-desktop.yml
 
   docs-site:
@@ -137,8 +150,10 @@ jobs:
     needs: detect
     # Trusted main pushes run docker.yml directly so its container-publish
     # environment secrets never cross this reusable-workflow call. PR runs
-    # remain build/test-only and secret-free.
-    if: needs.detect.outputs.event_name == 'pull_request' && (needs.detect.outputs.python == 'true' || needs.detect.outputs.frontend == 'true' || needs.detect.outputs.docker_meta == 'true')
+    # remain build/test-only and secret-free. Gated on python_prod (not
+    # python): the image copies installed code, never tests/ — tests-only
+    # PRs skip the build.
+    if: needs.detect.outputs.event_name == 'pull_request' && (needs.detect.outputs.python_prod == 'true' || needs.detect.outputs.frontend == 'true' || needs.detect.outputs.docker_meta == 'true')
     uses: ./.github/workflows/docker.yml
 
   supply-chain:

.github/workflows/deploy-site.yml

@@ -65,10 +65,14 @@ jobs:
 
       - uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020  # v4
         with:
-          node-version: 22
+          node-version: 26
           cache: npm
           cache-dependency-path: website/package-lock.json
 
+      - name: grab npm 12
+        run: |
+          npm i -g npm@12
+
       - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405  # v6.2.0
         with:
           python-version: '3.11'

.github/workflows/docs-site-checks.yml

@@ -15,10 +15,14 @@ jobs:
 
       - uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4
         with:
-          node-version: 22
+          node-version: 26
           cache: npm
           cache-dependency-path: website/package-lock.json
 
+      - name: grab npm 12
+        run: |
+          npm i -g npm@12
+
       - name: Install website dependencies
         uses: ./.github/actions/retry
         with:

.github/workflows/e2e-desktop.yml

@@ -39,8 +39,13 @@ jobs:
       # ── Node ───────────────────────────────────────────────────────────
       - uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4
         with:
-          node-version: 22
+          node-version: 26
           cache: npm
+
+      - name: grab npm 12
+        run: |
+          npm i -g npm@12
+
       # Full npm ci (not --ignore-scripts): electron's postinstall
       # downloads the binary we launch, and node-pty's native build is
       # needed for the terminal pane.
@@ -56,7 +61,7 @@ jobs:
           # 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.
-          version: "0.9.28"
+          version: '0.9.28'
           enable-cache: true
           cache-dependency-glob: |
             pyproject.toml
@@ -106,11 +111,11 @@ jobs:
               npx playwright test --reporter=list
           fi
         env:
-          CI: "true"
+          CI: 'true'
           # Ensure no real API keys leak into the test env.
-          OPENROUTER_API_KEY: ""
-          OPENAI_API_KEY: ""
-          NOUS_API_KEY: ""
+          OPENROUTER_API_KEY: ''
+          OPENAI_API_KEY: ''
+          NOUS_API_KEY: ''
 
       # ── Save updated baselines to cache (main only) ───────────────────
       - name: Save updated baselines to cache

.github/workflows/js-autofix.yml

@@ -67,9 +67,13 @@ jobs:
 
       - uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4
         with:
-          node-version: 22
+          node-version: 26
           cache: npm
 
+      - name: grab npm 12
+        run: |
+          npm i -g npm@12
+
       # --ignore-scripts: eslint only needs TS sources + eslint packages.
       - uses: ./.github/actions/retry
         with:

.github/workflows/js-tests.yml

@@ -15,8 +15,13 @@ jobs:
       - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
       - uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4
         with:
-          node-version: 22
+          node-version: 26
           cache: npm
+
+      - name: grab npm 12
+        run: |
+          npm i -g npm@12
+
       - uses: ./.github/actions/retry
         with:
           command: npm ci --ignore-scripts
@@ -61,8 +66,13 @@ jobs:
       - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
       - uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4
         with:
-          node-version: 22
+          node-version: 26
           cache: npm
+
+      - name: grab npm 12
+        run: |
+          npm i -g npm@12
+
       - uses: ./.github/actions/retry
         with:
           command: npm ci

.github/workflows/osv-scanner.yml

@@ -43,11 +43,13 @@ jobs:
     uses: google/osv-scanner-action/.github/workflows/osv-scanner-reusable.yml@9a498708959aeaef5ef730655706c5a1df1edbc2 # v2.3.8
     with:
       # Scan explicit lockfiles rather than recursing, so we only look at
-      # the three sources of truth and skip vendored / test / worktree dirs.
+      # the five sources of truth and skip vendored / test / worktree dirs.
       scan-args: |-
         --lockfile=uv.lock
         --lockfile=package-lock.json
         --lockfile=website/package-lock.json
+        --lockfile=plugins/platforms/photon/sidecar/package-lock.json
+        --lockfile=scripts/whatsapp-bridge/package-lock.json
       # The upstream reusable workflow uploads this exact file under its
       # fixed artifact name, which the wrapper downloads below.
       results-file-name: osv-results.sarif

.npmrc

@@ -45,3 +45,7 @@ min-release-age-exclude[]=vite
 min-release-age-exclude[]=rolldown
 min-release-age-exclude[]=@rolldown/*
 min-release-age-exclude[]=@oxc-project/types
+
+# ink needs
+min-release-age-exclude[]=lightningcss
+min-release-age-exclude[]=postcss

.nvmrc

@@ -0,0 +1 @@
+26

.python-version

@@ -0,0 +1 @@
+3.11

Dockerfile

@@ -41,14 +41,14 @@ RUN apt-get -o Acquire::Retries=3 update && \
     make install
 
 FROM ghcr.io/astral-sh/uv:0.11.6-python3.13-trixie@sha256:b3c543b6c4f23a5f2df22866bd7857e5d304b67a564f4feab6ac22044dde719b AS uv_source
-# Node 22 LTS source stage. Debian trixie's bundled nodejs is pinned to 20.x
-# which reached EOL in April 2026 — we copy node + npm + corepack from the
-# upstream node:22 image instead so we can stay on a supported LTS without
-# waiting for Debian 14 (forky, ~mid-2027).  Bookworm-based slim image used
-# so the produced binary links against glibc 2.36, which runs cleanly on
-# our Debian 13 (trixie, glibc 2.41) runtime.  Bumping to a new Node major
-# is a one-line ARG change; see #4977.
-FROM node:22-bookworm-slim@sha256:7af03b14a13c8cdd38e45058fd957bf00a72bbe17feac43b1c15a689c029c732 AS node_source
+# Node 26 source stage. Debian trixie's bundled nodejs is pinned to 20.x
+# which reached EOL in April 2026 — we copy node + npm from the upstream
+# node:26 image instead (Hermes pins its toolchain to Node 26 everywhere).
+# Bookworm-based slim image used so the produced binary links
+# against glibc 2.36, which runs cleanly on our Debian 13 (trixie, glibc
+# 2.41) runtime.  Bumping to a new Node major is a one-line ARG change; see
+# #4977.
+FROM node:26-bookworm-slim@sha256:9e6f9357d371591e32ab6f2d8a26d63bdd0d17c29eee3f4f3e7e454d9634bf73 AS node_source
 FROM debian:13.4
 
 # Disable Python stdout buffering to ensure logs are printed immediately.
@@ -70,7 +70,7 @@ ENV PLAYWRIGHT_BROWSERS_PATH=/opt/hermes/.playwright
 # hermes process, the dashboard, and per-profile gateways.
 RUN apt-get -o Acquire::Retries=3 update && \
     apt-get -o Acquire::Retries=3 install -y --no-install-recommends \
-    ca-certificates curl iputils-ping python3 python-is-python3 ripgrep ffmpeg gcc g++ make cmake python3-dev python3-venv libffi-dev libolm-dev procps git openssh-client docker-cli xz-utils && \
+    ca-certificates curl iputils-ping python3 python-is-python3 ripgrep ffmpeg gcc g++ make cmake python3-dev python3-venv libffi-dev libolm-dev libatomic1 procps git openssh-client docker-cli xz-utils && \
     rm -rf /var/lib/apt/lists/*
 
 # Prefer the fixed SQLite over Debian's vulnerable libsqlite3.so.0. Keep the
@@ -151,17 +151,20 @@ RUN useradd -u 10000 -m -d /opt/data hermes
 
 COPY --chmod=0755 --from=uv_source /usr/local/bin/uv /usr/local/bin/uvx /usr/local/bin/
 
-# Node 22 LTS: copy the node binary plus the bundled npm + corepack JS
-# installs from the upstream image.  npm and npx are recreated as symlinks
-# because they're symlinks in the source image (and need to live on PATH).
+# Node 26: copy the node binary plus the bundled npm JS install from the
+# upstream image.  npm and npx are recreated as symlinks because they're
+# symlinks in the source image (and need to live on PATH).
+#
+# No corepack: Node unbundled it upstream, so node:26 ships only npm in
+# /usr/local/lib/node_modules.  Nothing here needs it — no package.json
+# declares a `packageManager`, and no build step shells out to yarn or pnpm.
+#
 # See node_source stage at the top of the file for the version-bump
 # rationale (#4977).
 COPY --chmod=0755 --from=node_source /usr/local/bin/node /usr/local/bin/
 COPY --from=node_source /usr/local/lib/node_modules/npm /usr/local/lib/node_modules/npm
-COPY --from=node_source /usr/local/lib/node_modules/corepack /usr/local/lib/node_modules/corepack
 RUN ln -sf /usr/local/lib/node_modules/npm/bin/npm-cli.js /usr/local/bin/npm && \
-    ln -sf /usr/local/lib/node_modules/npm/bin/npx-cli.js /usr/local/bin/npx && \
-    ln -sf /usr/local/lib/node_modules/corepack/dist/corepack.js /usr/local/bin/corepack
+    ln -sf /usr/local/lib/node_modules/npm/bin/npx-cli.js /usr/local/bin/npx
 
 WORKDIR /opt/hermes
 
@@ -400,6 +403,8 @@ ENV HERMES_LAZY_INSTALL_TARGET=/opt/data/lazy-packages
 # Recursion is impossible because the shim exec's the venv binary by
 # absolute path (/opt/hermes/.venv/bin/hermes). See the shim source for
 # the opt-out env var (HERMES_DOCKER_EXEC_AS_ROOT=1).
+COPY --chmod=0755 docker/hermes-exec-shim.sh /opt/hermes/bin/hermes
+COPY --chmod=0755 docker/entrypoint-dispatch.sh /opt/hermes/docker/entrypoint-dispatch.sh
 
 # Pre-s6 entrypoint.sh did `source .venv/bin/activate` which exported
 # the venv bin onto PATH; Architecture B's main-wrapper.sh does the
@@ -416,27 +421,37 @@ ENV PATH="/opt/hermes/bin:/opt/hermes/.venv/bin:/opt/data/.local/bin:${PATH}"
 RUN mkdir -p /opt/data
 VOLUME [ "/opt/data" ]
 
-# s6-overlay's /init is PID 1. It sets up the supervision tree, runs
-# /etc/cont-init.d/* (our stage2 hook), starts s6-rc services
-# declared in /etc/s6-overlay/s6-rc.d/, then exec's its remaining
-# argv as the container's "main program" with stdin/stdout/stderr
-# inherited (this is what makes interactive --tui work). When the
-# main program exits, /init begins stage 3 shutdown and the container
-# exits with the program's exit code. Replaces tini — see Phase 2 of
-# docs/plans/2026-05-07-s6-overlay-dynamic-subagent-gateways.md.
+# The image ENTRYPOINT is a tiny dispatcher rather than `/init` directly.
+# When the image really owns PID 1 (normal Docker / Podman), the dispatcher
+# execs `/init` and preserves the full s6 supervision tree. When a platform
+# wraps the image entrypoint under its own PID-1 init (Fly Machines,
+# `docker run --init`, some schedulers), `/init` would abort with
+# `can only run as pid 1`; in that case the dispatcher falls back to
+# `stage2-hook.sh` + `main-wrapper.sh` directly so foreground commands still
+# work. See #38349.
+#
+# On the PID-1 path, s6-overlay's /init sets up the supervision tree, runs
+# /etc/cont-init.d/* (our stage2 hook), starts s6-rc services declared in
+# /etc/s6-overlay/s6-rc.d/, then exec's its remaining argv as the container's
+# "main program" with stdin/stdout/stderr inherited (this is what makes
+# interactive --tui work). When the main program exits, /init begins stage 3
+# shutdown and the container exits with the program's exit code. Replaces
+# tini — see Phase 2 of docs/plans/2026-05-07-s6-overlay-dynamic-subagent-gateways.md.
 #
 # We use the ENTRYPOINT+CMD split rather than CMD alone so the
 # wrapper is prepended to user-supplied args automatically:
 #
-#   docker run <image>                  → /init main-wrapper.sh   (CMD default)
-#   docker run <image> chat -q "hi"     → /init main-wrapper.sh chat -q hi
-#   docker run <image> sleep infinity   → /init main-wrapper.sh sleep infinity
-#   docker run <image> --tui            → /init main-wrapper.sh --tui
+#   docker run <image>                  → entrypoint-dispatch.sh   (CMD default)
+#   docker run <image> chat -q "hi"     → entrypoint-dispatch.sh chat -q hi
+#   docker run <image> sleep infinity   → entrypoint-dispatch.sh sleep infinity
+#   docker run <image> --tui            → entrypoint-dispatch.sh --tui
 #
 # main-wrapper.sh handles arg routing (bare-exec vs. hermes
 # subcommand vs. no-args), drops to the hermes user via s6-setuidgid,
 # and exec's the final program so its exit code becomes the container
-# exit code. Without the wrapper-as-ENTRYPOINT, leading-dash args
-# like `--version` would be intercepted by /init's POSIX shell.
-ENTRYPOINT [ "/init", "/opt/hermes/docker/main-wrapper.sh" ]
+# exit code. The dispatcher preserves that contract across both the
+# supervised PID-1 path and the non-PID-1 fallback path. Without the
+# wrapper-as-ENTRYPOINT, leading-dash args like `--version` would be
+# intercepted by /init's POSIX shell.
+ENTRYPOINT [ "/opt/hermes/docker/entrypoint-dispatch.sh" ]
 CMD [ ]

acp_adapter/entry.py

@@ -247,16 +247,22 @@ def main(argv: list[str] | None = None) -> None:
     import acp
     from .server import HermesACPAgent
 
-    # MCP tool discovery from config.yaml — run before asyncio.run() so
-    # it's safe to use blocking waits.  (ACP also registers per-session
-    # MCP servers dynamically via asyncio.to_thread inside the event
-    # loop; that path is unaffected.)  Moved from model_tools.py module
-    # scope to avoid freezing the gateway's loop on lazy import (#16856).
+    # MCP tool discovery from config.yaml — fire-and-forget in a
+    # background daemon thread so the ACP server becomes responsive
+    # immediately while MCP servers connect.  Previously this blocked
+    # asyncio.run() for 2-5 s.  (ACP also registers per-session MCP
+    # servers dynamically via asyncio.to_thread inside the event loop;
+    # that path is unaffected.)  Moved from model_tools.py module scope
+    # to avoid freezing the gateway's loop on lazy import (#16856).
     # Metadata-only hosts can opt out of unrelated global MCP startup.
     if os.environ.get("HERMES_ACP_SKIP_CONFIGURED_MCP", "").strip() != "1":
         try:
-            from tools.mcp_tool import discover_mcp_tools
-            discover_mcp_tools()
+            from hermes_cli.mcp_startup import start_background_mcp_discovery
+
+            start_background_mcp_discovery(
+                logger=logger,
+                thread_name="acp-mcp-discovery",
+            )
         except Exception:
             logger.debug("MCP tool discovery failed at ACP startup", exc_info=True)