After a repository moves to another owner, images publish under the new owner while existing deployments still pull the old namespace. The merge job now copies each published tag to LEGACY_GHCR_OWNER when that variable and the LEGACY_GHCR_TOKEN secret are set, using GHCR cross-repo blob mounts. It stays off while the legacy owner matches the publishing owner, and never fails the build.
* 🛰️ ci: Publish Every Image Through One Native-ARM Workflow
#15441 removed QEMU from the dev-branch image build and #15444 fixed the
prefix-glob bug it shipped with. Both changes lived in one of five workflows
that build images the same way; the other four still emulate arm64 with no
layer cache and take 20-40 minutes.
Rather than paste the pattern four more times, the build/merge logic moves to a
reusable `docker-publish.yml` that every image workflow calls. #15444 is the
argument for this: one wrong artifact-name expression would otherwise have
needed correcting in five files, and the same prefix hazard exists in all of
them (`librechat`/`librechat-api`, `librechat-dev`/`librechat-dev-api`,
`lc-dev-staging`/`lc-dev-staging-api`). The shared implementation is the
dev-branch one that already ran green, generalised only where callers differ.
Callers pass what actually varies:
- `images` — the target/file/image_name triples
- `tag_suffixes` — newline-separated tags applied in both registries
- `checkout_ref` / `build_branch` — main-image-workflow builds `main`, not the
dispatch ref
`main-image-workflow` and `tag-images` resolve their tags from git history, so
each grew a small `resolve-tag(s)` job whose output feeds the publish. That also
removes a duplicated `git fetch --tags` that previously ran once per matrix leg.
Two details worth noting:
- The digest-count assertion now derives its expected value from the `arches`
input rather than a hard-coded 2, so the architecture list has a single
source of truth shared by the build matrix and the merge guard.
- Nothing is interpolated into a `run:` block any more; `build_branch` and the
build digest arrive through `env`, so a ref name cannot reach a shell.
Net 135 lines lighter, and QEMU no longer appears anywhere in .github/workflows.
Workflow names are unchanged, so retry-docker-builds.yml still matches all five.
* 🔗 fix: Pin Release Builds to One Commit and Survive Full Re-runs
Review findings on the reusable publish workflow.
**P1 — every build leg could resolve `main` separately.** `main-image-workflow`
passed the symbolic ref `main` as `checkout_ref`, so the four build jobs each
resolved it at whatever moment they were scheduled. If `main` advanced in
between, the amd64 and arm64 halves of a release — or the API and application
images — could be built from different commits and published under the same
release and `latest` tags. `resolve-tag` now exports the commit it resolved the
tag from, and the publish pins to that SHA. The single-job workflow this
replaced checked out once, so this was a regression introduced by the split.
`docker-publish` likewise now falls back to `github.sha` rather than passing an
empty `ref` to `actions/checkout`, so callers that omit `checkout_ref` also get
an immutable commit instead of relying on checkout's empty-ref handling.
**P2 — digest artifacts on a full re-run.** `upload-artifact@v4` will not
upload over an existing artifact name, and a full re-run keeps the run id, so a
retry would fail before the merge could run. The suggested fix was to qualify
the artifact name with `run_attempt`, but `retry-docker-builds` picks its
endpoint by conclusion: `rerun` only when a job was cancelled, and
`rerun-failed-jobs` otherwise. Under the latter the merge re-runs alone and must
still find digests uploaded by the *previous* attempt's build legs, which a
run_attempt-qualified name would hide — precisely the shape of the #15444
failure, where the builds passed and only the merge failed. `overwrite: true`
resolves the conflict while keeping names stable across attempts.
**Unreachable error branch.** `LATEST_TAG=$(git tag ... | grep ... | head -1)`
under `set -euo pipefail` exits on grep's non-match, so the "No stable v<semver>
tag found" message could never print. Added `|| true`, matching what
`tag-images` already does. Pre-existing, carried over verbatim in the split.
* 🧩 ci: Close Workflow Path-Filter Gaps
Six trigger-filter gaps found by reading all workflows against the live
dependency graph (AI-1755, codegraph FINDINGS §6l):
- backend-review/frontend-review: root package.json/package-lock.json now
trigger unit tests — a lockfile-only dependency bump previously ran zero
backend or frontend unit tests while every test job installs from it
- agents-integration-tests: widen to the three package src trees it builds
and imports (was only src/agents/**)
- cache-integration-tests: same shape — verified live that
packages/api/src/flow/manager.ts (imported by mcp/oauth) matched neither
integration filter
- docker-smoke: plain Dockerfile had no PR-time validation despite shipping
via dev-images/tag-images; new node-image-smoke job builds it, gated by
paths-filter to Dockerfile/.dockerignore changes
- dev-images/dev-branch-images: add config/**, skill/**, .dockerignore —
the single-stage image COPYs the full build context
- static-checks: eslint.config.mjs now re-triggers the lint job (gap carried
over from eslint-ci.yml in the #14716 consolidation)
- delete generate_embeddings.yml: fired on docs/**, which no longer exists,
and its docs-root-path pointed at the same missing directory
* 🧩 ci: Address Codex Review Findings
- Build caches: all 26 build-* keys across 8 workflows now lead with
root package.json + package-lock.json so manifest-only bumps cannot
restore stale dists (data-provider embeds the root version); unifies
the split key families (playwright already hashed the lockfile)
- static-checks: config changes now gate on the ESLint config loading
and applying to representative files, plus a report-only full-tree
sweep (70 pre-existing errors at dev HEAD block a hard gate for now)
- docker-smoke: the workflow file itself triggers the plain-Dockerfile
build so job edits are validated
- dev-images/dev-branch-images: re-include skill/**/*.md after !**.md
so shipped deployment-skill Markdown rebuilds images
* 🧩 ci: Gate Config Lint Sweep on Regression vs Base Config
Second-round codex finding: the report-only sweep swallowed config-wide
breakage in scoped blocks the representative files don't exercise. The
sweep now lints the same tree under the PR's config and the base ref's
config and fails only when the PR's config produces more diagnostics for
some (file, rule) pair — pre-existing debt never fails the gate, and
fixes are never penalized. Base-config unavailability degrades to the
load gate with a notice. Outcome surfaced in the failure summary.
* 🧩 ci: Harden Config Lint Gate per External Review
- Coverage direction: fail when the PR config stops linting files the
base config covered (set difference on linted files) — a mis-scoped
ignores previously only removed diagnostics and passed both gates
- Severity-aware fingerprints: (file, rule, severity) so warn->error
escalations gate on a clean tree for that rule; downgrades still free
- Hard-fail when the base commit is missing so a future shallow-checkout
change cannot silently disable the gate; annotate fetch-depth: 0
- Tab-separated fingerprint keys (space-in-path proof), --config on
both sweeps, EXIT trap for the base config copy, comment on why it
must live at the repo root (flat-config pattern base paths)
- Narrow skill md re-include with !skill/README.md: top-level README is
documentation-only; runtime skill Markdown still rebuilds images
* ci: bump GitHub Actions to Node.js 24 runtimes
Clear Node 20 deprecation warnings on runners by moving workflow
actions to majors that declare node24 (checkout, cache, setup-node,
artifacts, Docker buildx/build-push/qemu/login, github-script,
setup-go, Azure login/helm, create-pull-request, axe-linter).
* fix: release leader lock via ioredis on Redis Cluster
@keyv/redis EVAL can surface unhandled MOVED redirects on cluster,
so resign() logged failure and left LeadingServerUUID set. Use ioredis
for leader election SET NX / GET / Lua (same pattern as principals and
concurrency locks) so cluster redirects are retried and resignation
clears the lock.
* 🏗️ refactor: Derive App Version from Root package.json + Add buildInfo Schema
The hardcoded `Constants.VERSION` in `data-provider` is now replaced at
rollup build time via `@rollup/plugin-replace`, sourcing from the root
`package.json` so version bumps are a single-file change.
Adds the shape needed by the rest of the series:
- `interface.buildInfo` boolean flag (default `true`) — lets self-hosters
opt out of exposing commit/branch/date.
- `buildInfo` on `TStartupConfig` — commit/commitShort/branch/buildDate.
- `SettingsTabValues.ABOUT` — new settings tab enum value.
Ref: https://github.com/danny-avila/LibreChat/issues/12406
* 🛠️ feat: Add Build Metadata Resolver and Expose via /api/config
Adds `resolveBuildInfo()` in `@librechat/api` that surfaces commit SHA,
branch, and build date from (in order) `BUILD_*` env vars, then local git
metadata. Result is cached per-process.
`/api/config` includes a `buildInfo` field on both authenticated and
anonymous responses when `interface.buildInfo !== false` and at least one
resolver field is populated. Omitted entirely otherwise.
Designed so pre-built Docker images carry metadata via build-arg while
source installs pick it up from `.git` — no manual version tracking.
Ref: https://github.com/danny-avila/LibreChat/issues/12406
* ℹ️ feat: Add Settings → About Panel with Diagnostics Copy
New Settings tab that renders the running build's version, commit (short
SHA), branch, and build date in a monospaced block alongside a "Copy
diagnostics" button that emits a preformatted text blob for pasting into
support issues.
Tab is hidden when `interface.buildInfo` is set to `false`. Reads from
`startupConfig.buildInfo` provided by `/api/config`.
Ref: https://github.com/danny-avila/LibreChat/issues/12406
* 🐳 ci: Inject BUILD_COMMIT/BRANCH/DATE into Docker Images
Adds optional `BUILD_COMMIT`, `BUILD_BRANCH`, `BUILD_DATE` ARGs to both
`Dockerfile` and `Dockerfile.multi`, wired as `ENV` vars in the runtime
stage so the backend's `resolveBuildInfo` picks them up.
All image-publishing workflows (`tag`, `main`, `dev`, `dev-branch`,
`dev-staging`) now compute `${github.sha}`, `${github.ref_name}`, and a
UTC timestamp, then pass them to `docker/build-push-action` as
`build-args`.
Defaults are empty — non-CI builds (local `docker build`) still work,
and the backend falls back to local `.git` metadata if ARGs aren't set.
Ref: https://github.com/danny-avila/LibreChat/issues/12406
* 📝 docs: Direct Bug Reporters to Settings → About for Version Info
The previous instructions (`docker images | grep librechat`,
`git rev-parse HEAD`) only worked for a subset of deployments and
rarely produced a commit SHA for users pulling pre-built images.
Point users to the new in-app Settings → About panel's
"Copy diagnostics" button, which captures version, commit, branch,
build date, and user agent in a single preformatted block. Fallback
instructions preserved for older installs.
Ref: https://github.com/danny-avila/LibreChat/issues/12406
* 🐳 fix: Move BUILD_* ENV to End of Docker Stages to Preserve Layer Cache
Per-commit BUILD_COMMIT/BUILD_DATE changes were being promoted to ENV
before `npm ci` / `npm run frontend` (single-stage) and before
`npm ci --omit=dev` (multi-stage api-build), which invalidated the cache
for every subsequent layer on every CI run.
Move the ARG/ENV block below the heavy install and build steps in both
Dockerfiles. Metadata is still available in the runtime image but no
longer busts layer reuse.
Addresses codex review on #12756.
* 🔧 fix: Propagate interface.buildInfo=false to Unauthenticated /api/config
The unauthenticated branch of `/api/config` was emitting an `interface`
object only when `privacyPolicy` or `termsOfService` was set, which
meant an admin's explicit `interface.buildInfo: false` opt-out was never
visible to anonymous/guest clients. `Settings.tsx` gates the About tab
on `startupConfig?.interface?.buildInfo !== false`, so a missing field
fell through as "enabled" for those clients.
Include `interface.buildInfo: false` in the unauth payload whenever it's
explicitly disabled. Keep the implicit default (true) absent to preserve
the minimal-unauth-payload convention.
Addresses codex review on #12756.
* 🔀 ci: Trigger Dev Image Workflows on Root package.json + Dockerfile Changes
The baked `Constants.VERSION` now reads from the root `package.json` via
rollup-plugin-replace, but the `dev-images.yml` and `dev-branch-images.yml`
path filters only matched `api/**`, `client/**`, `packages/**`. A release
commit that only bumps root `package.json` would not trigger a rebuild,
leaving `latest` dev images with stale Footer/About version metadata.
Include `package.json`, `package-lock.json`, and both Dockerfiles in the
path filters so dependency changes (lockfile rebuilds) and image build
tweaks also rebuild dev images.
Addresses codex review on #12756.
* 🧽 fix: Harden About Panel Lifecycle, A11y, and Loading Gate
Review follow-ups on #12756:
- #1 timer leak: stash the copy-state `setTimeout` in a ref and clear it
from a `useEffect` cleanup so unmounting the Settings dialog mid-toast
doesn't fire `setCopied(false)` on an unmounted component.
- #3 flash of About tab: gate `aboutEnabled` on `startupConfig != null`
so the tab stays hidden until `/api/config` returns. For admins who
disabled `interface.buildInfo`, the tab no longer briefly appears and
vanishes on page load.
- #6 aria-live placement: move the live region off the interactive
button onto a dedicated `<span role="status" aria-live="polite">` so
screen readers announce the copied state, not the full button content
on every re-render.
- #2 missing coverage: add `About.spec.tsx` exercising populated/empty
buildInfo rendering, invalid-date handling, diagnostics clipboard
payload, copy-state toggling, unmount cleanup, and the live region.
* ⚡ perf: Eagerly Resolve Build Info at Module Load
Review follow-up #4 on #12756: `resolveBuildInfo()` calls `execFileSync`
with a 2s timeout on source installs without `BUILD_*` env vars. Paying
this cost on the first HTTP request blocks the event loop mid-flight.
Call `resolveBuildInfo()` once at config route module load so the
resolver's cache is warm before any request arrives. Docker images with
the BUILD_* env vars set sidestep the git path entirely, so this only
affects the edge case of source installs.
* 📝 docs: Document rollup Version Placeholder Contract
Review follow-ups #5 / #8 on #12756. The `__LIBRECHAT_VERSION__`
placeholder relies on a substring replacement rule that only works
because the token appears inside a string literal, and the substitution
only runs during `npm run build:data-provider`.
- Expand the `Constants.VERSION` JSDoc to spell out that consumers read
the placeholder through the built dist bundle; source-level test
imports would see the raw placeholder.
- Add a NOTE above the rollup `replace` config warning future
contributors not to repurpose the token as a bare identifier without
switching to a quoted replacement value.
Non-functional; prevents future contributors from stepping on a subtle
constraint.
* 🪪 fix: Only Toast "Copied" When Clipboard Copy Actually Succeeds
Codex R5 on #12756. `copy-to-clipboard` returns a boolean indicating
whether the underlying `execCommand('copy')` / fallback prompt actually
wrote to the clipboard. The previous handler flipped to the "Copied"
state unconditionally, which in hardened browsers or when the
permission prompt is dismissed would mislead users into filing bug
reports without the diagnostics blob attached.
Gate the state/timer/live-region on the boolean return; silently no-op
on failure rather than showing a false positive. Adds a test asserting
the button label stays at "Copy diagnostics" when the clipboard call
fails.
* 🐳 fix: Derive main image metadata from checkout
* 🪪 fix: Keep About enabled until disabled
* ✅ test: Avoid literal Settings mock text
* 🧱 refactor: Rename Build Info Module
* chore: remove unused code in progressCallback, as well as handle reply.trim(), post `getCompletion`
* chore(Dockerfile): remove curl installation
* experimental: dev image parallelized with matrix strategy and building for amd64/arm64 support
* make platforms explicit
* nginx setup
* chore(dev-images.yml): update workflow trigger to push events on main branch
chore(dev-images.yml): remove building and pushing of librechat-dev-client image
chore(nginx.conf): comment out SSL configuration in nginx.conf
chore(deploy-compose.yml): uncomment api build configuration in deploy-compose.yml
chore(deploy-compose.yml): update client build configuration in deploy-compose.yml
* chore(deploy-compose.yml): update API and client image references to use latest versions from ghcr.io
feat(deploy-compose.yml): add NODE_ENV environment variable with value 'production' for API service
* chore(dev-images.yml): tag and push latest images to container registry
chore(dev-images.yml): tag and push latest client image to container registry
chore(dev-images.yml): tag and push latest dev image to container registry
fix(Dockerfile.multi): fix CMD command to properly set NODE_ENV variable
* feat: add Dockerfile.multi for building API, Client, and Data Provider
feat: add nginx.conf for client-side routing in Nginx
feat: add deploy-compose.yml for deploying the application with Docker Compose
chore: update version in deploy-compose.yml to 3.8
chore: remove unused configuration in docs/dev/deploy-compose.yml
* chore(Dockerfile.multi): Remove data-provider build stage
chore(deploy-compose.yml): Add NODE_ENV=production environment variable
* chore(Dockerfile.multi): add environment variable NODE_OPTIONS with value "--max-old-space-size=776"
feat(Dockerfile.multi): copy client build output to api build stage
* chore(Dockerfile.multi): update NODE_OPTIONS to increase max-old-space-size to 2048
chore(deploy-compose.yml): remove NODE_ENV=production environment variable
* feat(dev-images.yml): add GitHub Actions workflow for Docker multi-stage build on push to main branch