Merge branch 'main' into bb/gui

This commit is contained in:
emozilla 2026-05-09 00:27:42 -04:00
commit cc0bd10420
319 changed files with 10598 additions and 2078 deletions

View file

@ -10,48 +10,59 @@ on:
- 'Dockerfile'
- 'docker/**'
- '.github/workflows/docker-publish.yml'
- '.github/actions/hermes-smoke-test/**'
pull_request:
branches: [main]
paths:
- '**/*.py'
- 'pyproject.toml'
- 'uv.lock'
- 'Dockerfile'
- 'docker/**'
- '.github/workflows/docker-publish.yml'
- '.github/actions/hermes-smoke-test/**'
release:
types: [published]
permissions:
contents: read
# Top-level concurrency: do NOT cancel in-flight builds when a new push lands.
# Every commit deserves its own SHA-tagged image in the registry, and we guard
# the :latest tag in a separate job below (with its own concurrency group) so
# a slow run can't clobber :latest with older bits.
# Concurrency: push/release runs are NEVER cancelled so every merge gets its
# own SHA-tagged image; :latest is guarded separately by the move-latest job.
# PR runs reuse a PR-scoped group with cancel-in-progress: true so rapid
# pushes to the same PR collapse to the latest commit.
concurrency:
group: docker-${{ github.ref }}
cancel-in-progress: false
group: docker-${{ github.event.pull_request.number || github.ref }}
cancel-in-progress: ${{ github.event_name == 'pull_request' }}
env:
IMAGE_NAME: nousresearch/hermes-agent
jobs:
build-and-push:
# ---------------------------------------------------------------------------
# Build amd64 natively. This job also runs the smoke tests (basic --help
# and the dashboard subcommand regression guard from #9153), because amd64
# is the only arch we can `load` into the local daemon on an amd64 runner.
# ---------------------------------------------------------------------------
build-amd64:
# Only run on the upstream repository, not on forks
if: github.repository == 'NousResearch/hermes-agent'
runs-on: ubuntu-latest
timeout-minutes: 60
timeout-minutes: 45
outputs:
pushed_sha_tag: ${{ steps.mark_pushed.outputs.pushed }}
digest: ${{ steps.push.outputs.digest }}
steps:
- name: Checkout code
uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
with:
submodules: recursive
# Fetch enough history to run `git merge-base --is-ancestor` in the
# move-latest job. That job reuses this checkout via its own
# actions/checkout call, but commits reachable from main up to ~1000
# back are plenty for any realistic race window.
fetch-depth: 1000
- name: Set up QEMU
uses: docker/setup-qemu-action@c7c53464625b32c7a7e944ae62b3e17d2b600130 # v3
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # v3
# Build amd64 only so we can `load` the image for smoke testing.
# `load: true` cannot export a multi-arch manifest to the local daemon.
# The multi-arch build follows on push to main / release.
# Build once, load into the local daemon for smoke testing. Cached
# to gha with a per-arch scope; the push step below reuses every
# layer from this build.
- name: Build image (amd64, smoke test)
uses: docker/build-push-action@10e90e3645eae34f1e60eeb005ba3a3d33f178e8 # v6
with:
@ -59,36 +70,14 @@ jobs:
file: Dockerfile
load: true
platforms: linux/amd64
tags: nousresearch/hermes-agent:test
cache-from: type=gha
cache-to: type=gha,mode=max
tags: ${{ env.IMAGE_NAME }}:test
cache-from: type=gha,scope=docker-amd64
cache-to: type=gha,mode=max,scope=docker-amd64
- name: Test image starts
run: |
mkdir -p /tmp/hermes-test
sudo chown -R 10000:10000 /tmp/hermes-test
# The image runs as the hermes user (UID 10000). GitHub Actions
# creates /tmp/hermes-test root-owned by default, which hermes
# can't write to — chown it to match the in-container UID before
# bind-mounting. Real users doing `docker run -v ~/.hermes:...`
# with their own UID hit the same issue and have their own
# remediations (HERMES_UID env var, or chown locally).
docker run --rm \
-v /tmp/hermes-test:/opt/data \
--entrypoint /opt/hermes/docker/entrypoint.sh \
nousresearch/hermes-agent:test --help
- name: Test dashboard subcommand
run: |
mkdir -p /tmp/hermes-test
sudo chown -R 10000:10000 /tmp/hermes-test
# Verify the dashboard subcommand is included in the Docker image.
# This prevents regressions like #9153 where the dashboard command
# was present in source but missing from the published image.
docker run --rm \
-v /tmp/hermes-test:/opt/data \
--entrypoint /opt/hermes/docker/entrypoint.sh \
nousresearch/hermes-agent:test dashboard --help
- name: Smoke test image
uses: ./.github/actions/hermes-smoke-test
with:
image: ${{ env.IMAGE_NAME }}:test
- name: Log in to Docker Hub
if: github.event_name == 'push' && github.ref == 'refs/heads/main' || github.event_name == 'release'
@ -97,61 +86,229 @@ jobs:
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_TOKEN }}
# Always push a per-commit SHA tag on main. This is race-free because
# every commit has a unique SHA — concurrent runs can't clobber each
# other here. We also embed the git SHA as an OCI label so the
# move-latest job (below) can read it back off the registry's `:latest`.
- name: Push multi-arch image with SHA tag (main branch)
id: push_sha
if: github.event_name == 'push' && github.ref == 'refs/heads/main'
# Push amd64 by digest only (no tag). The merge job assembles the
# tagged manifest list. `push-by-digest=true` is docker's recommended
# pattern for multi-runner multi-platform builds.
#
# We apply the OCI revision label here (and again on arm64) because
# the move-latest job reads it off the linux/amd64 sub-manifest config
# of `:latest` to decide whether it's safe to advance. The label must
# be on each per-arch image — manifest lists themselves don't carry
# image config labels.
- name: Push amd64 by digest
id: push
if: github.event_name == 'push' && github.ref == 'refs/heads/main' || github.event_name == 'release'
uses: docker/build-push-action@10e90e3645eae34f1e60eeb005ba3a3d33f178e8 # v6
with:
context: .
file: Dockerfile
push: true
platforms: linux/amd64,linux/arm64
tags: nousresearch/hermes-agent:sha-${{ github.sha }}
platforms: linux/amd64
labels: |
org.opencontainers.image.revision=${{ github.sha }}
cache-from: type=gha
cache-to: type=gha,mode=max
outputs: type=image,name=${{ env.IMAGE_NAME }},push-by-digest=true,name-canonical=true,push=true
cache-from: type=gha,scope=docker-amd64
cache-to: type=gha,mode=max,scope=docker-amd64
# Write the digest to a file and upload it as an artifact so the
# merge job can stitch both per-arch digests into a manifest list.
- name: Export digest
if: github.event_name == 'push' && github.ref == 'refs/heads/main' || github.event_name == 'release'
run: |
mkdir -p /tmp/digests
digest="${{ steps.push.outputs.digest }}"
touch "/tmp/digests/${digest#sha256:}"
- name: Upload digest artifact
if: github.event_name == 'push' && github.ref == 'refs/heads/main' || github.event_name == 'release'
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4
with:
name: digest-amd64
path: /tmp/digests/*
if-no-files-found: error
retention-days: 1
# ---------------------------------------------------------------------------
# Build arm64 natively on GitHub's free arm64 runner. This replaces the
# previous QEMU-emulated arm64 build, which was ~5-10x slower and shared
# a cache scope with amd64. Matches the amd64 job's shape: build+load,
# smoke test, then on push/release push by digest.
# ---------------------------------------------------------------------------
build-arm64:
if: github.repository == 'NousResearch/hermes-agent'
runs-on: ubuntu-24.04-arm
timeout-minutes: 45
outputs:
digest: ${{ steps.push.outputs.digest }}
steps:
- name: Checkout code
uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
with:
submodules: recursive
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # v3
# Build once, load into the local daemon for smoke testing. Cached
# to gha with a per-arch scope; the push step below reuses every
# layer from this build.
- name: Build image (arm64, smoke test)
uses: docker/build-push-action@10e90e3645eae34f1e60eeb005ba3a3d33f178e8 # v6
with:
context: .
file: Dockerfile
load: true
platforms: linux/arm64
tags: ${{ env.IMAGE_NAME }}:test
cache-from: type=gha,scope=docker-arm64
cache-to: type=gha,mode=max,scope=docker-arm64
- name: Smoke test image
uses: ./.github/actions/hermes-smoke-test
with:
image: ${{ env.IMAGE_NAME }}:test
- name: Log in to Docker Hub
if: github.event_name == 'push' && github.ref == 'refs/heads/main' || github.event_name == 'release'
uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # v3
with:
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_TOKEN }}
- name: Push arm64 by digest
id: push
if: github.event_name == 'push' && github.ref == 'refs/heads/main' || github.event_name == 'release'
uses: docker/build-push-action@10e90e3645eae34f1e60eeb005ba3a3d33f178e8 # v6
with:
context: .
file: Dockerfile
platforms: linux/arm64
labels: |
org.opencontainers.image.revision=${{ github.sha }}
outputs: type=image,name=${{ env.IMAGE_NAME }},push-by-digest=true,name-canonical=true,push=true
cache-from: type=gha,scope=docker-arm64
cache-to: type=gha,mode=max,scope=docker-arm64
- name: Export digest
if: github.event_name == 'push' && github.ref == 'refs/heads/main' || github.event_name == 'release'
run: |
mkdir -p /tmp/digests
digest="${{ steps.push.outputs.digest }}"
touch "/tmp/digests/${digest#sha256:}"
- name: Upload digest artifact
if: github.event_name == 'push' && github.ref == 'refs/heads/main' || github.event_name == 'release'
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4
with:
name: digest-arm64
path: /tmp/digests/*
if-no-files-found: error
retention-days: 1
# ---------------------------------------------------------------------------
# Stitch both per-arch digests into a single tagged multi-arch manifest.
# This is a registry-side operation — no building, no layer re-push —
# so it runs in ~30 seconds. On main pushes it produces :sha-<sha>.
# On releases it produces :<release_tag_name>.
# ---------------------------------------------------------------------------
merge:
if: github.repository == 'NousResearch/hermes-agent' && (github.event_name == 'push' && github.ref == 'refs/heads/main' || github.event_name == 'release')
runs-on: ubuntu-latest
needs: [build-amd64, build-arm64]
timeout-minutes: 10
outputs:
pushed_sha_tag: ${{ steps.mark_pushed.outputs.pushed }}
steps:
- name: Download digests
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4
with:
path: /tmp/digests
pattern: digest-*
merge-multiple: true
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # v3
- name: Log in to Docker Hub
uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # v3
with:
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_TOKEN }}
# Compute the tag for this run. Main pushes use sha-<sha> (so every
# commit gets its own immutable tag); releases use the release tag name.
- name: Compute tag
id: tag
run: |
if [ "${{ github.event_name }}" = "release" ]; then
echo "tag=${{ github.event.release.tag_name }}" >> "$GITHUB_OUTPUT"
else
echo "tag=sha-${{ github.sha }}" >> "$GITHUB_OUTPUT"
fi
- name: Create manifest list and push
working-directory: /tmp/digests
run: |
set -euo pipefail
# Build the arg array from each digest file (filename = the digest
# hex, with no sha256: prefix; empty file content, only the name
# matters). Using an array avoids shellcheck SC2046 and keeps
# every digest a single argv token even under pathological names.
args=()
for digest_file in *; do
args+=("${IMAGE_NAME}@sha256:${digest_file}")
done
docker buildx imagetools create \
-t "${IMAGE_NAME}:${TAG}" \
"${args[@]}"
env:
IMAGE_NAME: ${{ env.IMAGE_NAME }}
TAG: ${{ steps.tag.outputs.tag }}
- name: Inspect image
run: |
docker buildx imagetools inspect "${IMAGE_NAME}:${TAG}"
env:
IMAGE_NAME: ${{ env.IMAGE_NAME }}
TAG: ${{ steps.tag.outputs.tag }}
# Signal to move-latest that the SHA tag is live. Only on main pushes;
# releases don't trigger move-latest (they use their own release tag).
- name: Mark SHA tag pushed
id: mark_pushed
if: github.event_name == 'push' && github.ref == 'refs/heads/main'
run: echo "pushed=true" >> "$GITHUB_OUTPUT"
- name: Push multi-arch image (release)
if: github.event_name == 'release'
uses: docker/build-push-action@10e90e3645eae34f1e60eeb005ba3a3d33f178e8 # v6
with:
context: .
file: Dockerfile
push: true
platforms: linux/amd64,linux/arm64
tags: nousresearch/hermes-agent:${{ github.event.release.tag_name }}
cache-from: type=gha
cache-to: type=gha,mode=max
# Second job: moves `:latest` to point at the SHA tag the first job pushed.
# ---------------------------------------------------------------------------
# Move :latest to point at the SHA tag the merge job pushed.
#
# Has its own concurrency group with `cancel-in-progress: true`, which
# gives us the serialization we need: if a newer push arrives while an
# older run is mid-way through this job, the older run is cancelled
# before it can clobber `:latest`. Combined with the ancestor check
# below, this means `:latest` only ever moves forward in git history.
# The real serialization guarantee comes from the top-level concurrency
# group (`docker-${{ github.ref }}` with `cancel-in-progress: false`),
# which ensures at most one workflow run for this ref executes at a time.
# That means two move-latest steps for the same ref cannot overlap.
#
# This job has its own concurrency group as defense-in-depth: if the
# top-level group is ever loosened, queued move-latests will run serially
# in arrival order, each one running the ancestor check below and either
# advancing :latest or skipping. `cancel-in-progress: false` matches the
# top-level setting — we don't want rapid pushes to cancel a queued
# move-latest, because the ancestor check is the real safety mechanism
# and queueing is cheap (move-latest is a ~30s registry op).
#
# Combined with the ancestor check, this means :latest only ever moves
# forward in git history.
# ---------------------------------------------------------------------------
move-latest:
if: |
github.repository == 'NousResearch/hermes-agent'
&& github.event_name == 'push'
&& github.ref == 'refs/heads/main'
&& needs.build-and-push.outputs.pushed_sha_tag == 'true'
needs: build-and-push
&& needs.merge.outputs.pushed_sha_tag == 'true'
needs: merge
runs-on: ubuntu-latest
timeout-minutes: 10
concurrency:
group: docker-move-latest-${{ github.ref }}
cancel-in-progress: true
cancel-in-progress: false
steps:
- name: Checkout code
uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
@ -167,11 +324,11 @@ jobs:
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_TOKEN }}
# Read the git revision label off the current `:latest` manifest, then
# Read the git revision label off the current :latest manifest, then
# use `git merge-base --is-ancestor` to check whether our commit is a
# descendant of it. If `:latest` doesn't exist yet, or its label is
# descendant of it. If :latest doesn't exist yet, or its label is
# missing, we treat that as "safe to publish". If another run already
# advanced `:latest` past us (or diverged), we skip and leave it alone.
# advanced :latest past us (or diverged), we skip and leave it alone.
- name: Decide whether to move :latest
id: latest_check
run: |

View file

@ -1,9 +1,12 @@
name: Lint (ruff + ty)
# Surface ruff and ty diagnostics as a diff vs the target branch.
# This check is advisory only ATM it always exits zero and never blocks merge.
# It posts a Markdown summary to the workflow run and, for pull requests,
# comments the same summary on the PR.
# Two things here:
# 1. Advisory diff — ruff + ty diagnostics as a diff vs the target branch.
# Posts a Markdown summary and a PR comment. Exit zero always.
# 2. Blocking ``ruff check .`` — enforces the explicit rules in
# ``[tool.ruff.lint.select]`` (currently PLW1514). Failure blocks merge.
# Separate job so the advisory diff still runs and posts even when
# enforcement fails.
on:
push:
@ -149,3 +152,50 @@ jobs:
body: fullBody,
});
}
ruff-blocking:
# Enforce the rules in pyproject.toml [tool.ruff.lint.select]. Currently
# PLW1514 (unspecified-encoding) — catches bare ``open()`` /
# ``read_text()`` / ``write_text()`` calls that default to locale
# encoding on Windows. Failure here blocks merge; the advisory
# ``lint-diff`` job above runs independently so reviewers still get
# the diff comment even when enforcement fails.
name: ruff enforcement (blocking)
runs-on: ubuntu-latest
timeout-minutes: 5
steps:
- name: Checkout code
uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
- name: Install uv
uses: astral-sh/setup-uv@d4b2f3b6ecc6e67c4457f6d3e41ec42d3d0fcb86 # v5
- name: Install ruff
run: uv tool install ruff
- name: ruff check .
# No --exit-zero, no || true. Exit code propagates to the job,
# which propagates to the required-check gate.
run: |
ruff check .
windows-footguns:
# Static guardrails on Windows-unsafe Python primitives — os.kill(pid, 0),
# os.killpg, os.setsid, signal.SIGKILL without getattr fallback,
# shebang scripts via subprocess, bare open() without encoding=, etc.
# See scripts/check-windows-footguns.py for the full rule list.
name: Windows footguns (blocking)
runs-on: ubuntu-latest
timeout-minutes: 5
steps:
- name: Checkout code
uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
- name: Set up Python
uses: actions/setup-python@0b93645e9fea7318ecaed2b359559ac225c90a2b # v5
with:
python-version: "3.11"
- name: Run footgun checker
run: python scripts/check-windows-footguns.py --all

119
.github/workflows/uv-lockfile-check.yml vendored Normal file
View file

@ -0,0 +1,119 @@
name: uv.lock check
# Verify uv.lock is in sync with pyproject.toml. Blocking check — PRs
# that modify pyproject.toml without regenerating uv.lock (or vice versa)
# must not merge, because the Docker build's `uv sync --frozen` step will
# fail on a stale lockfile and we'd rather catch it here than in the
# docker-publish workflow on main.
#
# ─────────────────────────────────────────────────────────────────────────
# IMPORTANT: this check runs against the MERGED state, not just your branch
# ─────────────────────────────────────────────────────────────────────────
#
# For `pull_request` events, GitHub checks out `refs/pull/<N>/merge` by
# default — a synthetic commit that merges your PR branch into the CURRENT
# state of `main`. That means the pyproject.toml evaluated here is
# `main's pyproject.toml + your PR's changes to pyproject.toml`, not just
# what's on your branch.
#
# Failure mode this creates: if `main` has advanced since you branched
# (e.g. someone merged a PR that added a dep to pyproject.toml + its
# corresponding uv.lock entries), your branch's uv.lock is missing those
# new entries. `uv lock --check` resolves against the merged pyproject
# and sees a lockfile that doesn't cover all the current deps → fails
# with "The lockfile at uv.lock needs to be updated."
#
# This can be confusing: `uv lock --check` passes locally (your branch
# is internally consistent) but fails in CI (merged state isn't).
#
# Fix is to sync your branch with main and regenerate the lockfile:
#
# git fetch origin main
# git rebase origin/main # or merge, whatever the repo prefers
# uv lock # regenerates uv.lock against new pyproject.toml
# git add uv.lock
# git commit -m "chore: refresh uv.lock after rebase onto main"
# git push --force-with-lease # if you rebased
#
# If you also changed pyproject.toml in your PR, `uv lock` handles that
# at the same time — one regeneration covers both your changes and the
# drift from main.
#
# This is the correct behavior! The check is protecting main's Docker
# build: a post-merge build would see the same merged state and fail
# the same way. Better to catch it here than after merge.
on:
push:
branches: [main]
paths:
- 'pyproject.toml'
- 'uv.lock'
- '.github/workflows/uv-lockfile-check.yml'
pull_request:
branches: [main]
paths:
- 'pyproject.toml'
- 'uv.lock'
- '.github/workflows/uv-lockfile-check.yml'
permissions:
contents: read
concurrency:
group: uv-lockfile-check-${{ github.event.pull_request.number || github.ref }}
cancel-in-progress: ${{ github.event_name == 'pull_request' }}
jobs:
check:
name: uv lock --check
runs-on: ubuntu-latest
timeout-minutes: 5
steps:
- name: Checkout code
uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
- name: Install uv
uses: astral-sh/setup-uv@d4b2f3b6ecc6e67c4457f6d3e41ec42d3d0fcb86 # v5
# `uv lock --check` re-resolves the project from pyproject.toml and
# compares the result to uv.lock, exiting non-zero if they disagree.
# No network writes, no file modifications.
#
# On PRs this runs against the merge commit (see comment at the top
# of this file) — failures often mean "your branch is behind main,
# rebase and regenerate uv.lock."
- name: Verify uv.lock is up-to-date
run: |
if ! uv lock --check; then
cat <<'EOF' >> "$GITHUB_STEP_SUMMARY"
## ❌ uv.lock is out of sync with pyproject.toml
**If this is a PR:** this check runs against the merged state
(your branch + current `main`), not just your branch. If
`uv lock --check` passes locally, your branch is likely behind
`main` — recent changes to `pyproject.toml` on `main` aren't
reflected in your branch's `uv.lock` yet.
To fix, sync with main and regenerate the lockfile:
```bash
git fetch origin main
git rebase origin/main # or `git merge origin/main`
uv lock # regenerate against new pyproject.toml
git add uv.lock
git commit -m "chore: refresh uv.lock after syncing with main"
git push --force-with-lease # drop --force-with-lease if you merged
```
**If you only changed pyproject.toml:** run `uv lock` locally
and commit the result.
This check is blocking because the Docker image build uses
`uv sync --frozen --extra all`, which rejects stale lockfiles
— catching it here avoids a ~15 min failed docker-publish run
on `main` post-merge.
EOF
echo "::error title=uv.lock out of sync::Run \`uv lock\` locally and commit the result. If on a PR, sync with main first."
exit 1
fi