chore: ⬆️ Update mudler/parakeet.cpp to 30a307553f1965ceb38a1a922069a71e7dd67bf3 (#10092)

⬆️ Update mudler/parakeet.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>

.agents/building-and-testing.md

@@ -15,3 +15,32 @@ Let's say the user wants to build a particular backend for a given platform. For
 - Unless the user specifies that they want you to run the command, then just print it because not all agent frontends handle long running jobs well and the output may overflow your context
 - The user may say they want to build AMD or ROCM instead of hipblas, or Intel instead of SYCL or NVIDIA insted of l4t or cublas. Ask for confirmation if there is ambiguity.
 - Sometimes the user may need extra parameters to be added to `docker build` (e.g. `--platform` for cross-platform builds or `--progress` to view the full logs), in which case you can generate the `docker build` command directly.
+
+## Test coverage gate
+
+The core Go suites (`./pkg`, `./core`, plus the in-process integration suite `./tests/e2e`) are covered by a **strict, monotonic coverage ratchet**:
+
+- `make test-coverage` — runs the suites with `covermode=atomic` instrumentation and writes a merged profile to `coverage/coverage.out`. Uses the same prerequisites as `make test`.
+  - **`--coverpkg` (`COVERAGE_COVERPKG = core/...,pkg/...`):** coverage is attributed to the core+pkg packages, not just the package under test. This is what lets the in-process `tests/e2e` suite (which drives the real HTTP server over loopback via `application.New`) credit the `core/http/endpoints/...` handlers it exercises — folding it in roughly doubled endpoint coverage (e.g. `endpoints/openai` 13.6% → 52%). The denominator is therefore *all* of `core`+`pkg` (minus generated proto, dropped via `COVERAGE_EXCLUDE_RE`), so the number isn't comparable to a plain per-package figure.
+  - **Integration suites (`COVERAGE_E2E_ROOTS = ./tests/e2e`)** run non-recursively (excludes `tests/e2e/distributed`, which needs containers) with `--label-filter=!real-models` (those need a downloaded model) against the mock backend built by `prepare-test`. `tests/integration` is deliberately excluded — it needs `make backends/local-store`, which the coverage CI job doesn't build.
+  - **Flake note:** folding integration tests into a *strict* gate means a hard e2e failure (or a spec that silently stops running) can fail the coverage gate, not just the test. `--flake-attempts` absorbs transient retryable failures; covermode=atomic keeps line coverage deterministic otherwise.
+  - **Why one ginkgo run per root (`scripts/run-coverage.sh`):** passing several recursive roots to a *single* ginkgo invocation (e.g. `ginkgo -r ./pkg ./core`) only merges **one** root's coverprofile into `--output-dir`/`--coverprofile` — the others are silently dropped. Verified with ginkgo 2.29.0: `-r ./pkg ./core` yields only `./pkg` coverage, while `-r ./core` alone yields all 34 core packages. So the script runs each root separately and concatenates the (disjoint) profiles. Don't "simplify" it back to a single multi-root invocation — that's how `core/` (including all of `core/http`, ~7.4k statements) silently vanished from the number before.
+  - **Build tags (`COVERAGE_TAGS`, passed via `GINKGO_TAGS`):** defaults to `debug auth`. The `auth` tag is required to compile the real (sqlite-backed) auth implementation and its ~150 `//go:build auth` tests — without it those files aren't built, the tests don't run, and the gate scores auth against a stub (~3.7% instead of ~38%). If you add new tag-gated tests, extend `COVERAGE_TAGS` or they won't count (and likely won't run in CI at all).
+- `make test-coverage-check` — runs `test-coverage`, then `scripts/coverage-check.sh` fails the build if total coverage is **below** the committed baseline in `coverage-baseline.txt`. The Linux job in `.github/workflows/test.yml` runs this instead of `make test`.
+- `make test-coverage-baseline` — regenerates and overwrites `coverage-baseline.txt` from the current run.
+- `make install-hooks` — sets `core.hooksPath` to the versioned `.githooks/`, whose `pre-commit` runs checks scoped to what's staged: Go changes → `make lint` + `make test-coverage-check`; `core/http/react-ui/` changes → `make test-ui-coverage-check` (Playwright e2e + UI coverage gate). A commit touching neither is skipped; bypass with `git commit --no-verify`. The hook resolves golangci-lint's new-from base to `upstream/master` → `origin/master` → `master`, so it works from a fork clone where `origin/master` is stale (passed to `make lint` via `LINT_NEW_FROM`).
+
+### React UI coverage
+
+The React UI (`core/http/react-ui/`) has **no component/unit tests** — its only tests are the Playwright e2e specs in `e2e/`, which run against the real app served by `tests/e2e-ui/ui-test-server` (the dist is `//go:embed`ed, so the server is rebuilt per coverage run). Those specs do genuinely exercise the UI (clicks, `fill`, `setInputFiles`, `getByRole`/`getByText`, visibility/value assertions).
+
+- `make test-ui-coverage` — builds an istanbul-instrumented bundle (`COVERAGE=true`, via `vite-plugin-istanbul` with `forceBuildInstrument: true` — the plugin skips production builds otherwise), re-embeds it into `ui-test-server` (the dist is `//go:embed`ed), runs the Playwright specs, and writes an `nyc` report to `core/http/react-ui/coverage/`. The specs import `{ test, expect }` from `e2e/coverage-fixtures.js` (re-exports Playwright's, plus harvests `window.__coverage__` into `.nyc_output/` after each test). Instrumentation is off unless `COVERAGE=true`, so dev/prod builds and plain `make test-ui-e2e` are unaffected (the fixture no-ops when `window.__coverage__` is absent).
+- **Browser:** the flake dev shell ships `chromium` and exports `PLAYWRIGHT_CHROMIUM_PATH`; `playwright.config.js` uses it via `launchOptions.executablePath`, and the Makefile skips `playwright install` when it's set. This avoids Playwright's downloaded browser, which can't resolve system libs (`libglib-2.0`, …) on NixOS. In CI (no `PLAYWRIGHT_CHROMIUM_PATH`) the Makefile falls back to `playwright install --with-deps chromium`.
+- The app is a React SPA, so coverage accumulates across in-app navigation within a test; a full `page.goto`/reload resets it.
+- `.nycrc.json` uses `all: true`, so **every `src/**` file is in the report**, including 0%-coverage ones — that's how you spot features with no test at all (sort the HTML report or `coverage-summary.json` by line% ascending). 
+- **UI coverage gate:** `make test-ui-coverage-check` runs the suite then `scripts/ui-coverage-check.sh`, failing if total line coverage drops more than `UI_COVERAGE_TOLERANCE` (default **1.0pp**) below `core/http/react-ui/coverage-baseline.txt`. `make test-ui-coverage-baseline` regenerates the baseline. **Why a tolerance (unlike the strict Go gate):** UI e2e line coverage is *non-deterministic* — async/debounced paths (e.g. the VRAM estimate's 500ms debounce) make identical specs vary ~0.5pp run-to-run, so a zero-tolerance gate would flake. Keep the tolerance just above the observed jitter. Run in CI (`tests-ui-e2e.yml`) and pre-commit on `core/http/react-ui/` changes.
+
+Rules:
+- The gate is **strict — there is no tolerance**. Any decrease fails, regardless of how many lines a PR adds or deletes. `covermode=atomic` makes line coverage deterministic, so there's no run-to-run jitter to excuse.
+- When a change legitimately **raises** coverage, run `make test-coverage-baseline` and **commit** the updated `coverage-baseline.txt` so the ratchet moves up. Never lower the baseline by hand.
+- If you can't get coverage back to baseline, the fix is to **add tests**, not to edit the baseline.

.agents/coding-style.md

@@ -50,6 +50,17 @@ Do not mix styles within a package. If you are extending tests in a package that
 
 This is enforced by `golangci-lint` via the `forbidigo` linter (see `.golangci.yml`); calls like `t.Errorf` / `t.Fatalf` / `t.Run` / `t.Skip` / `t.Logf` are flagged. Run `make lint` locally before submitting; the same check runs in CI (`.github/workflows/lint.yml`).
 
+## Outbound HTTP
+
+All outbound HTTP must go through `github.com/mudler/LocalAI/pkg/httpclient` rather than the standard library's default client. Use `httpclient.New(...)` (no body deadline — safe for streaming/SSE) or `httpclient.NewWithTimeout(d, ...)` (simple request/response). Both **refuse redirects by default** and set a TLS 1.2 floor.
+
+The reason is GHSA-3mj3-57v2-4636: the std default client follows redirects, and on a *cross-host* redirect Go forwards custom credential headers (e.g. Anthropic's `x-api-key`) to the redirect target, leaking the secret. `httpclient` fails closed instead.
+
+- Need to follow redirects (download CDNs, registry blobs, GitHub asset URLs)? Pass `httpclient.WithFollowRedirects()` — it still strips credential headers on any cross-host hop.
+- Have a custom transport (IP-pinned dialer, HTTP/2 tuning, a credential-injecting `RoundTripper`)? Pass `httpclient.WithTransport(rt)`, basing the transport on `httpclient.HardenedTransport()` to keep the TLS floor. Handed a `*http.Client` by a library? `httpclient.Harden(c)` applies the policy in place.
+
+This is enforced by `forbidigo` (see `.golangci.yml`): `http.DefaultClient` and `http.Get`/`Post`/`PostForm`/`Head` are flagged. The `&http.Client{}` composite literal can't be matched precisely by forbidigo without also flagging legitimate `*http.Client` type references, so that form is caught by review — don't construct raw clients.
+
 ## Documentation
 
 The project documentation is located in `docs/content`. When adding new features or changing existing functionality, it is crucial to update the documentation to reflect these changes. This helps users understand how to use the new capabilities and ensures the documentation stays relevant.

.dockerignore

@@ -30,3 +30,19 @@ backend/python/**/source
 # up compiled against whatever (likely older) commit the host had.
 backend/cpp/llama-cpp/llama.cpp
 backend/cpp/llama-cpp-*-build
+
+# Rust backend build output (sources are tracked; target/ is generated)
+backend/rust/*/target
+
+# Local-only artifacts that bloat the build context but the image never needs.
+# Saved image tarballs, locally-installed backends, the host-built binary, and
+# assorted tool/scratch dirs. None of these are git-tracked.
+backend-images
+local-backends
+local-ai
+.crush
+protoc
+tests
+
+# Installed via npm inside the build stage; no need to ship the host copy.
+**/node_modules

.githooks/pre-commit

@@ -0,0 +1,60 @@
+#!/usr/bin/env sh
+#
+# LocalAI pre-commit hook. Install it (once per clone) with:
+#
+#     make install-hooks
+#
+# Runs only the checks relevant to what's staged:
+#   - Go files          -> make lint + make test-coverage-check
+#   - core/http/react-ui -> make test-ui-coverage-check (Playwright e2e + gate)
+# A commit touching neither is skipped entirely (docs/YAML/etc. can't change
+# lint findings, Go coverage, or the UI).
+#
+# To bypass for a single commit (e.g. a WIP checkpoint): git commit --no-verify
+set -eu
+
+repo_root="$(git rev-parse --show-toplevel)"
+cd "$repo_root"
+
+staged="$(git diff --cached --name-only --diff-filter=ACMRD)"
+
+go_changed=0
+ui_changed=0
+if echo "$staged" | grep -qE '\.go$'; then go_changed=1; fi
+if echo "$staged" | grep -qE '^core/http/react-ui/'; then ui_changed=1; fi
+
+if [ "$go_changed" -eq 0 ] && [ "$ui_changed" -eq 0 ]; then
+	echo "pre-commit: no Go or React UI changes staged — skipping."
+	exit 0
+fi
+
+if [ "$go_changed" -eq 1 ]; then
+	# Resolve the ref golangci-lint's new-from-merge-base should compare
+	# against. .golangci.yml pins origin/master, which is correct in CI
+	# (origin == the canonical repo) but wrong from a fork clone, where
+	# origin/master lags behind and lint would report the whole upstream
+	# backlog. Prefer upstream/master, then origin/master, then master.
+	lint_base=""
+	for ref in upstream/master origin/master master; do
+		if git rev-parse --verify --quiet "${ref}^{commit}" >/dev/null 2>&1; then
+			lint_base="$ref"
+			break
+		fi
+	done
+
+	echo "pre-commit ▶ golangci-lint (make lint${lint_base:+, new-from $lint_base})"
+	make lint LINT_NEW_FROM="$lint_base"
+
+	echo "pre-commit ▶ coverage gate (make test-coverage-check) — builds and runs the"
+	echo "             pkg/core suites plus tests/e2e; can take a few minutes."
+	make test-coverage-check
+fi
+
+if [ "$ui_changed" -eq 1 ]; then
+	echo "pre-commit ▶ React UI e2e + coverage gate (make test-ui-coverage-check) —"
+	echo "             rebuilds the UI + ui-test-server, runs the Playwright specs, and"
+	echo "             fails if line coverage regressed; can take a couple of minutes."
+	make test-ui-coverage-check
+fi
+
+echo "pre-commit ✓ all relevant checks passed"

.github/backend-matrix.yml

@@ -690,6 +690,19 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2404'
+  - build-type: 'cublas'
+    cuda-major-version: "12"
+    cuda-minor-version: "8"
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-nvidia-cuda-12-rfdetr-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "rfdetr-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
   - build-type: 'cublas'
     cuda-major-version: "12"
     cuda-minor-version: "8"
@@ -703,6 +716,19 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2404'
+  - build-type: 'cublas'
+    cuda-major-version: "12"
+    cuda-minor-version: "8"
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-nvidia-cuda-12-parakeet-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "parakeet-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
   - build-type: 'cublas'
     cuda-major-version: "12"
     cuda-minor-version: "8"
@@ -1491,6 +1517,19 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2404'
+  - build-type: 'cublas'
+    cuda-major-version: "13"
+    cuda-minor-version: "0"
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-nvidia-cuda-13-rfdetr-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "rfdetr-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
   - build-type: 'cublas'
     cuda-major-version: "13"
     cuda-minor-version: "0"
@@ -1504,6 +1543,19 @@ include:
     backend: "sam3-cpp"
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
+  - build-type: 'cublas'
+    cuda-major-version: "13"
+    cuda-minor-version: "0"
+    platforms: 'linux/arm64'
+    skip-drivers: 'false'
+    tag-latest: 'auto'
+    tag-suffix: '-nvidia-l4t-cuda-13-arm64-rfdetr-cpp'
+    base-image: "ubuntu:24.04"
+    ubuntu-version: '2404'
+    runs-on: 'ubuntu-24.04-arm'
+    backend: "rfdetr-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
   - build-type: 'cublas'
     cuda-major-version: "13"
     cuda-minor-version: "0"
@@ -1517,6 +1569,19 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2404'
+  - build-type: 'cublas'
+    cuda-major-version: "13"
+    cuda-minor-version: "0"
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-nvidia-cuda-13-parakeet-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "parakeet-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
   - build-type: 'cublas'
     cuda-major-version: "13"
     cuda-minor-version: "0"
@@ -1530,6 +1595,19 @@ include:
     backend: "whisper"
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
+  - build-type: 'cublas'
+    cuda-major-version: "13"
+    cuda-minor-version: "0"
+    platforms: 'linux/arm64'
+    skip-drivers: 'false'
+    tag-latest: 'auto'
+    tag-suffix: '-nvidia-l4t-cuda-13-arm64-parakeet-cpp'
+    base-image: "ubuntu:24.04"
+    ubuntu-version: '2404'
+    runs-on: 'ubuntu-24.04-arm'
+    backend: "parakeet-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
   - build-type: 'cublas'
     cuda-major-version: "13"
     cuda-minor-version: "0"
@@ -2635,6 +2713,74 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2404'
+  # rfdetr-cpp
+  - build-type: ''
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-cpu-rfdetr-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "rfdetr-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
+  - build-type: 'sycl_f32'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-intel-sycl-f32-rfdetr-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
+    skip-drivers: 'false'
+    backend: "rfdetr-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
+  - build-type: 'sycl_f16'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-intel-sycl-f16-rfdetr-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
+    skip-drivers: 'false'
+    backend: "rfdetr-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
+  - build-type: 'vulkan'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    platform-tag: 'amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-vulkan-rfdetr-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "rfdetr-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
+  - build-type: 'vulkan'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/arm64'
+    platform-tag: 'arm64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-vulkan-rfdetr-cpp'
+    runs-on: 'ubuntu-24.04-arm'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "rfdetr-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
   - build-type: 'sycl_f32'
     cuda-major-version: ""
     cuda-minor-version: ""
@@ -2715,6 +2861,19 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2204'
+  - build-type: 'cublas'
+    cuda-major-version: "12"
+    cuda-minor-version: "0"
+    platforms: 'linux/arm64'
+    skip-drivers: 'false'
+    tag-latest: 'auto'
+    tag-suffix: '-nvidia-l4t-arm64-rfdetr-cpp'
+    base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
+    runs-on: 'ubuntu-24.04-arm'
+    backend: "rfdetr-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2204'
   # whisper
   - build-type: ''
     cuda-major-version: ""
@@ -2824,6 +2983,115 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2404'
+  # parakeet-cpp
+  - build-type: ''
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    platform-tag: 'amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-cpu-parakeet-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "parakeet-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
+  - build-type: ''
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/arm64'
+    platform-tag: 'arm64'
+    tag-latest: 'auto'
+    tag-suffix: '-cpu-parakeet-cpp'
+    runs-on: 'ubuntu-24.04-arm'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "parakeet-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
+  - build-type: 'sycl_f32'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-intel-sycl-f32-parakeet-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
+    skip-drivers: 'false'
+    backend: "parakeet-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
+  - build-type: 'sycl_f16'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-intel-sycl-f16-parakeet-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
+    skip-drivers: 'false'
+    backend: "parakeet-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
+  - build-type: 'vulkan'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    platform-tag: 'amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-vulkan-parakeet-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "parakeet-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
+  - build-type: 'vulkan'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/arm64'
+    platform-tag: 'arm64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-vulkan-parakeet-cpp'
+    runs-on: 'ubuntu-24.04-arm'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "parakeet-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
+  - build-type: 'cublas'
+    cuda-major-version: "12"
+    cuda-minor-version: "0"
+    platforms: 'linux/arm64'
+    skip-drivers: 'false'
+    tag-latest: 'auto'
+    tag-suffix: '-nvidia-l4t-arm64-parakeet-cpp'
+    base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
+    runs-on: 'ubuntu-24.04-arm'
+    backend: "parakeet-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2204'
+  - build-type: 'hipblas'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-rocm-hipblas-parakeet-cpp'
+    base-image: "rocm/dev-ubuntu-24.04:7.2.1"
+    runs-on: 'ubuntu-latest'
+    skip-drivers: 'false'
+    backend: "parakeet-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
   # acestep-cpp
   - build-type: ''
     cuda-major-version: ""
@@ -3856,6 +4124,10 @@ includeDarwin:
     tag-suffix: "-metal-darwin-arm64-whisper"
     build-type: "metal"
     lang: "go"
+  - backend: "parakeet-cpp"
+    tag-suffix: "-metal-darwin-arm64-parakeet-cpp"
+    build-type: "metal"
+    lang: "go"
   - backend: "acestep-cpp"
     tag-suffix: "-metal-darwin-arm64-acestep-cpp"
     build-type: "metal"

.github/workflows/bump_deps.yaml

@@ -30,6 +30,10 @@ jobs:
             variable: "WHISPER_CPP_VERSION"
             branch: "master"
             file: "backend/go/whisper/Makefile"
+          - repository: "mudler/parakeet.cpp"
+            variable: "PARAKEET_VERSION"
+            branch: "master"
+            file: "backend/go/parakeet-cpp/Makefile"
           - repository: "leejet/stable-diffusion.cpp"
             variable: "STABLEDIFFUSION_GGML_VERSION"
             branch: "master"
@@ -50,6 +54,10 @@ jobs:
             variable: "SAM3_VERSION"
             branch: "main"
             file: "backend/go/sam3-cpp/Makefile"
+          - repository: "mudler/rf-detr.cpp"
+            variable: "RFDETR_VERSION"
+            branch: "main"
+            file: "backend/go/rfdetr-cpp/Makefile"
           - repository: "predict-woo/qwen3-tts.cpp"
             variable: "QWEN3TTS_CPP_VERSION"
             branch: "main"

.github/workflows/stalebot.yml

@@ -11,7 +11,7 @@ jobs:
     if: github.repository == 'mudler/LocalAI'
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/stale@b5d41d4e1d5dceea10e7104786b73624c18a190f # v9
+      - uses: actions/stale@eb5cf3af3ac0a1aa4c9c45633dd1ae542a27a899 # v9
         with:
           stale-issue-message: 'This issue is stale because it has been open 90 days with no activity. Remove stale label or comment or this will be closed in 5 days.'
           stale-pr-message: 'This PR is stale because it has been open 90 days with no activity. Remove stale label or comment or this will be closed in 10 days.'

.github/workflows/test-extra.yml

@@ -37,6 +37,7 @@ jobs:
       sglang: ${{ steps.detect.outputs.sglang }}
       acestep-cpp: ${{ steps.detect.outputs.acestep-cpp }}
       qwen3-tts-cpp: ${{ steps.detect.outputs.qwen3-tts-cpp }}
+      rfdetr-cpp: ${{ steps.detect.outputs.rfdetr-cpp }}
       vibevoice-cpp: ${{ steps.detect.outputs.vibevoice-cpp }}
       localvqe: ${{ steps.detect.outputs.localvqe }}
       voxtral: ${{ steps.detect.outputs.voxtral }}
@@ -45,6 +46,7 @@ jobs:
       speaker-recognition: ${{ steps.detect.outputs.speaker-recognition }}
       sherpa-onnx: ${{ steps.detect.outputs.sherpa-onnx }}
       whisper: ${{ steps.detect.outputs.whisper }}
+      parakeet-cpp: ${{ steps.detect.outputs.parakeet-cpp }}
     steps:
       - name: Checkout repository
         uses: actions/checkout@v6
@@ -632,6 +634,26 @@ jobs:
       - name: Build whisper backend image and run transcription gRPC e2e tests
         run: |
           make test-extra-backend-whisper-transcription
+  # Parakeet ASR via the parakeet-cpp backend (C++/ggml port of NeMo
+  # Parakeet). Drives AudioTranscription (offline, with word timestamps) on
+  # tdt_ctc-110m + the JFK 11s clip.
+  tests-parakeet-cpp-grpc-transcription:
+    needs: detect-changes
+    if: needs.detect-changes.outputs.parakeet-cpp == 'true' || needs.detect-changes.outputs.run-all == 'true'
+    runs-on: ubuntu-latest
+    timeout-minutes: 90
+    steps:
+      - name: Clone
+        uses: actions/checkout@v6
+        with:
+          submodules: true
+      - name: Setup Go
+        uses: actions/setup-go@v5
+        with:
+          go-version: '1.25.4'
+      - name: Build parakeet-cpp backend image and run transcription gRPC e2e tests
+        run: |
+          make test-extra-backend-parakeet-cpp-transcription
   # VITS TTS via the sherpa-onnx backend. Drives both TTS (file write) and
   # TTSStream (PCM chunks) on the e2e-backends harness.
   tests-sherpa-onnx-grpc-tts:
@@ -843,6 +865,42 @@ jobs:
       - name: Test qwen3-tts-cpp
         run: |
           make --jobs=5 --output-sync=target -C backend/go/qwen3-tts-cpp test
+  # Per-backend smoke for rfdetr-cpp: builds the .so + Go binary and runs
+  # `make -C backend/go/rfdetr-cpp test`. test.sh fetches the small (~20 MB)
+  # rfdetr-nano-q8_0 GGUF from the published mudler/rfdetr-cpp-nano HF repo
+  # via curl and synthesises a tiny PNG to exercise the wire protocol.
+  tests-rfdetr-cpp:
+    needs: detect-changes
+    if: needs.detect-changes.outputs.rfdetr-cpp == 'true' || needs.detect-changes.outputs.run-all == 'true'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Clone
+        uses: actions/checkout@v6
+        with:
+          submodules: true
+      - name: Dependencies
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y build-essential cmake curl libopenblas-dev
+      - name: Setup Go
+        uses: actions/setup-go@v5
+      - name: Display Go version
+        run: go version
+      - name: Proto Dependencies
+        run: |
+          # Install protoc
+          curl -L -s https://github.com/protocolbuffers/protobuf/releases/download/v26.1/protoc-26.1-linux-x86_64.zip -o protoc.zip && \
+          unzip -j -d /usr/local/bin protoc.zip bin/protoc && \
+          rm protoc.zip
+          go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.2
+          go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f11e97d44e567e945af
+          PATH="$PATH:$HOME/go/bin" make protogen-go
+      - name: Build rfdetr-cpp
+        run: |
+          make --jobs=5 --output-sync=target -C backend/go/rfdetr-cpp
+      - name: Test rfdetr-cpp
+        run: |
+          make --jobs=5 --output-sync=target -C backend/go/rfdetr-cpp test
   # Per-backend smoke for vibevoice-cpp: builds the .so + Go binary and
   # runs `make -C backend/go/vibevoice-cpp test`. test.sh auto-downloads
   # the published mudler/vibevoice.cpp-models bundle (TTS Q8_0 + ASR Q4_K

.github/workflows/test.yml

@@ -53,9 +53,22 @@ jobs:
           node-version: '22'
       - name: Build React UI
         run: make react-ui
-      - name: Test
+      # Runs the core suite with coverage and fails if total coverage dropped
+      # below the committed baseline (coverage-baseline.txt). The gate is
+      # strict — any decrease fails. Raise the baseline with
+      # `make test-coverage-baseline` and commit it when coverage rises.
+      - name: Test (with coverage gate)
         run: |
-          PATH="$PATH:/root/go/bin" make --jobs 5 --output-sync=target test
+          PATH="$PATH:/root/go/bin" make --jobs 5 --output-sync=target test-coverage-check
+      - name: Upload coverage report
+        if: ${{ always() }}
+        uses: actions/upload-artifact@v4
+        with:
+          name: coverage-linux
+          path: |
+            coverage/coverage.out
+            coverage/coverage.html
+          if-no-files-found: ignore
       - name: Setup tmate session if tests fail
         if: ${{ failure() }}
         uses: mxschmitt/action-tmate@v3.23

.github/workflows/tests-ui-e2e.yml

@@ -37,6 +37,10 @@ jobs:
         uses: actions/setup-node@v6
         with:
           node-version: '22'
+      - name: Setup Bun
+        uses: oven-sh/setup-bun@v2
+        with:
+          bun-version: '1.3.11'
       - name: Proto Dependencies
         run: |
           curl -L -s https://github.com/protocolbuffers/protobuf/releases/download/v26.1/protoc-26.1-linux-x86_64.zip -o protoc.zip && \
@@ -48,16 +52,12 @@ jobs:
         run: |
           sudo apt-get update
           sudo apt-get install -y build-essential libopus-dev
-      - name: Build UI test server
-        run: PATH="$PATH:$HOME/go/bin" make build-ui-test-server
-      - name: Install Playwright
-        working-directory: core/http/react-ui
-        run: |
-          npm install
-          npx playwright install --with-deps chromium
-      - name: Run Playwright tests
-        working-directory: core/http/react-ui
-        run: npx playwright test
+      # Builds an instrumented UI bundle, runs the Playwright specs, and fails
+      # if line coverage regressed beyond the jitter tolerance (the gate is
+      # in `make test-ui-coverage-check`). PLAYWRIGHT_CHROMIUM_PATH is unset
+      # here, so scripts/ensure-playwright-browser.sh installs Chromium via apt.
+      - name: Run UI e2e + coverage gate
+        run: PATH="$PATH:$HOME/go/bin" make test-ui-coverage-check
       - name: Upload Playwright report
         if: ${{ failure() }}
         uses: actions/upload-artifact@v7
@@ -65,6 +65,14 @@ jobs:
           name: playwright-report
           path: core/http/react-ui/playwright-report/
           retention-days: 7
+      - name: Upload UI coverage report
+        if: ${{ always() }}
+        uses: actions/upload-artifact@v7
+        with:
+          name: ui-coverage
+          path: core/http/react-ui/coverage/
+          if-no-files-found: ignore
+          retention-days: 7
       - name: Setup tmate session if tests fail
         if: ${{ failure() }}
         uses: mxschmitt/action-tmate@v3.23

.gitignore

@@ -70,10 +70,17 @@ docs/static/gallery.html
 # per-developer customization files for the development container
 .devcontainer/customization/*
 
+# Coverage profiles (the committed baseline is coverage-baseline.txt)
+/coverage/
+
 # React UI build artifacts (keep placeholder dist/index.html)
 core/http/react-ui/node_modules/
 core/http/react-ui/dist
 
+# React UI coverage (vite-plugin-istanbul + nyc, via `make test-ui-coverage`)
+core/http/react-ui/.nyc_output/
+core/http/react-ui/coverage/
+
 # Extracted backend binaries for container-based testing
 local-backends/
 

.golangci.yml

@@ -56,6 +56,20 @@ linters:
         # are exempt — see linters.exclusions.rules below.
         - pattern: '^os\.(Getenv|LookupEnv|Environ)$'
           msg: 'Plumb config through ApplicationConfig (or the relevant CLI struct) instead of reading env directly. CLI entry points (core/cli/) bind env vars via kong''s `env:` tag — that is the only sanctioned env→struct boundary. See .agents/coding-style.md.'
+        # Outbound HTTP must go through pkg/httpclient, which refuses redirects
+        # by default and sets a TLS floor. The std-library default client and
+        # the http.Get/Post/... convenience helpers follow redirects (up to 10)
+        # and, on a cross-host redirect, forward custom credential headers such
+        # as Anthropic's x-api-key to the redirect target — leaking the secret
+        # (GHSA-3mj3-57v2-4636). forbidigo can't precisely match the
+        # `&http.Client{}` composite literal without also flagging legitimate
+        # `*http.Client` type references, so that form is enforced by
+        # convention + review; these two patterns catch the implicit-default
+        # client, which is the common footgun.
+        - pattern: '^http\.DefaultClient$'
+          msg: 'Use pkg/httpclient (httpclient.New / NewWithTimeout) instead of http.DefaultClient — the std client follows redirects and leaks credential headers cross-host (GHSA-3mj3-57v2-4636). See .agents/coding-style.md.'
+        - pattern: '^http\.(Get|Post|PostForm|Head)$'
+          msg: 'Use pkg/httpclient (httpclient.New / NewWithTimeout) instead of http.Get/Post/PostForm/Head — these use http.DefaultClient, which follows redirects and leaks credential headers cross-host (GHSA-3mj3-57v2-4636). See .agents/coding-style.md.'
   exclusions:
     paths:
       # Upstream whisper.cpp source tree fetched by the whisper backend Makefile.
@@ -95,3 +109,18 @@ linters:
       - path: _test\.go$
         text: 'os\.(Getenv|LookupEnv|Environ)'
         linters: [forbidigo]
+      # pkg/httpclient is the sanctioned home for outbound HTTP clients; it
+      # necessarily references net/http directly.
+      - path: ^pkg/httpclient/
+        text: 'http\.(DefaultClient|Get|Post|PostForm|Head)'
+        linters: [forbidigo]
+      # Tests drive local httptest servers where redirect/TLS hardening is
+      # irrelevant; the std client is fine there.
+      - path: _test\.go$
+        text: 'http\.(DefaultClient|Get|Post|PostForm|Head)'
+        linters: [forbidigo]
+      # Vendored upstream whisper.cpp Go bindings are a separate module and
+      # cannot import pkg/httpclient.
+      - path: ^backend/go/whisper/sources/
+        text: 'http\.(DefaultClient|Get|Post|PostForm|Head)'
+        linters: [forbidigo]

CONTRIBUTING.md

@@ -198,6 +198,7 @@ For AI-assisted development, see [`AGENTS.md`](AGENTS.md) (or the equivalent [`C
 
 - Prefer modern Go idioms — for example, use `any` instead of `interface{}`.
 - Use [`golangci-lint`](https://golangci-lint.run) to catch common issues before submitting a PR.
+- Run `make install-hooks` once per clone to enable the pre-commit hook: Go changes run `make lint` + the coverage gate (`make test-coverage-check`); `core/http/react-ui/` changes run the Playwright e2e suite (`make test-ui`). Bypass a single commit with `git commit --no-verify`.
 - Use [`github.com/mudler/xlog`](https://github.com/mudler/xlog) for logging (same API as `slog`). Do not use `fmt.Println` or the standard `log` package for operational logging.
 - Use tab indentation for Go files (as defined in `.editorconfig`).
 

Makefile

@@ -1,5 +1,5 @@
 # Disable parallel execution for backend builds
-.NOTPARALLEL: backends/diffusers backends/llama-cpp backends/turboquant backends/outetts backends/piper backends/stablediffusion-ggml backends/whisper backends/faster-whisper backends/silero-vad backends/local-store backends/huggingface backends/rfdetr backends/insightface backends/speaker-recognition backends/kitten-tts backends/kokoro backends/chatterbox backends/llama-cpp-darwin backends/neutts build-darwin-python-backend build-darwin-go-backend backends/mlx backends/diffuser-darwin backends/mlx-vlm backends/mlx-audio backends/mlx-distributed backends/stablediffusion-ggml-darwin backends/vllm backends/vllm-omni backends/sglang backends/moonshine backends/pocket-tts backends/qwen-tts backends/faster-qwen3-tts backends/qwen-asr backends/nemo backends/voxcpm backends/whisperx backends/ace-step backends/acestep-cpp backends/fish-speech backends/voxtral backends/opus backends/trl backends/llama-cpp-quantization backends/kokoros backends/sam3-cpp backends/qwen3-tts-cpp backends/vibevoice-cpp backends/localvqe backends/tinygrad backends/sherpa-onnx backends/ds4 backends/ds4-darwin backends/liquid-audio
+.NOTPARALLEL: backends/diffusers backends/llama-cpp backends/turboquant backends/outetts backends/piper backends/stablediffusion-ggml backends/whisper backends/parakeet-cpp backends/faster-whisper backends/silero-vad backends/local-store backends/huggingface backends/rfdetr backends/rfdetr-cpp backends/insightface backends/speaker-recognition backends/kitten-tts backends/kokoro backends/chatterbox backends/llama-cpp-darwin backends/neutts build-darwin-python-backend build-darwin-go-backend backends/mlx backends/diffuser-darwin backends/mlx-vlm backends/mlx-audio backends/mlx-distributed backends/stablediffusion-ggml-darwin backends/vllm backends/vllm-omni backends/sglang backends/moonshine backends/pocket-tts backends/qwen-tts backends/faster-qwen3-tts backends/qwen-asr backends/nemo backends/voxcpm backends/whisperx backends/ace-step backends/acestep-cpp backends/fish-speech backends/voxtral backends/opus backends/trl backends/llama-cpp-quantization backends/kokoros backends/sam3-cpp backends/qwen3-tts-cpp backends/vibevoice-cpp backends/localvqe backends/tinygrad backends/sherpa-onnx backends/ds4 backends/ds4-darwin backends/liquid-audio
 
 GOCMD=go
 GOTEST=$(GOCMD) test
@@ -71,8 +71,39 @@ endif
 
 TEST_PATHS?=./api/... ./pkg/... ./core/... ./backend/go/cloud-proxy/... ./backend/go/local-store/...
 
+## Coverage output and the committed baseline that CI compares against.
+## The gate is strict: total coverage must never decrease (no tolerance).
+## covermode=atomic makes line coverage deterministic regardless of test
+## ordering or flake retries, so there is no run-to-run jitter to absorb.
+COVERAGE_DIR?=$(abspath ./coverage)
+COVERAGE_PROFILE?=$(COVERAGE_DIR)/coverage.out
+COVERAGE_BASELINE?=coverage-baseline.txt
+## Coverage is collected one recursive root at a time and merged (see
+## scripts/run-coverage.sh): passing several recursive roots to a single
+## ginkgo invocation only keeps one root's coverprofile. Mirrors TEST_PATHS
+## minus ./api (which doesn't exist).
+COVERAGE_ROOTS?=./pkg ./core
+## Build tags for the coverage build. `auth` is required to compile the real
+## auth implementation and its ~150 `//go:build auth` tests (otherwise they're
+## invisible and the gate scores auth against a stub). `debug` matches `test`.
+COVERAGE_TAGS?=debug auth
+## Coverage is attributed to these packages via --coverpkg, so the in-process
+## integration suites (COVERAGE_E2E_ROOTS) credit the core/http handlers they
+## drive over HTTP — not just their own test package.
+COVERAGE_COVERPKG?=github.com/mudler/LocalAI/core/...,github.com/mudler/LocalAI/pkg/...
+## In-process integration suites folded into coverage. Run non-recursively
+## (excludes tests/e2e/distributed, which needs containers) with the mock
+## backend built by prepare-test. real-models specs need a downloaded model,
+## so they're filtered out. NOTE: tests/integration is intentionally NOT here —
+## it needs the local-store backend built (`make backends/local-store`), which
+## the coverage CI job doesn't do.
+COVERAGE_E2E_ROOTS?=./tests/e2e
+COVERAGE_E2E_LABELS?=!real-models
+## Drop generated protobuf from the denominator (it has no tests by design).
+COVERAGE_EXCLUDE_RE?=grpc/proto/.*[.]pb[.]go
 
-.PHONY: all test build vendor lint lint-all
+
+.PHONY: all test test-coverage test-coverage-baseline test-coverage-check test-ui test-ui-coverage-baseline test-ui-coverage-check install-hooks build vendor lint lint-all
 
 all: help
 
@@ -170,6 +201,36 @@ test: prepare-test
 	OPUS_SHIM_LIBRARY=$(abspath ./pkg/opus/shim/libopusshim.so) \
 	$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --flake-attempts $(TEST_FLAKES) --fail-fast -v -r $(TEST_PATHS)
 
+## Runs the core suite ($(TEST_PATHS)) with statement-coverage instrumentation
+## and writes a merged profile to $(COVERAGE_PROFILE). Deliberately omits
+## --fail-fast so a single failure doesn't truncate the coverage number, and
+## uses covermode=atomic so the result is deterministic. Prints the total.
+test-coverage: prepare-test
+	@echo 'Running tests with coverage'
+	GINKGO_TAGS="$(COVERAGE_TAGS)" \
+	COVERAGE_COVERPKG="$(COVERAGE_COVERPKG)" \
+	COVERAGE_E2E_ROOTS="$(COVERAGE_E2E_ROOTS)" \
+	COVERAGE_E2E_LABELS="$(COVERAGE_E2E_LABELS)" \
+	COVERAGE_EXCLUDE_RE='$(COVERAGE_EXCLUDE_RE)' \
+	OPUS_SHIM_LIBRARY=$(abspath ./pkg/opus/shim/libopusshim.so) \
+	scripts/run-coverage.sh $(COVERAGE_DIR) $(COVERAGE_PROFILE) $(TEST_FLAKES) $(COVERAGE_ROOTS)
+	@$(GOCMD) tool cover -html=$(COVERAGE_PROFILE) -o $(COVERAGE_DIR)/coverage.html
+	@$(GOCMD) tool cover -func=$(COVERAGE_PROFILE) | tail -n1
+
+## Writes the current total coverage to $(COVERAGE_BASELINE). Run this (and
+## commit the result) whenever a change legitimately raises coverage so the
+## ratchet moves up. Never lower it by hand.
+test-coverage-baseline: test-coverage
+	@$(GOCMD) tool cover -func=$(COVERAGE_PROFILE) | awk '/^total:/{gsub(/%/,"",$$NF); print $$NF}' > $(COVERAGE_BASELINE)
+	@echo "Saved coverage baseline: $$(cat $(COVERAGE_BASELINE))%"
+
+## CI gate: fails if total coverage dropped more than COVERAGE_TOLERANCE
+## (default 0.5pp) below the committed baseline. A small tolerance absorbs the
+## run-to-run jitter from the in-process tests/e2e suite folded in via
+## --coverpkg (timing-dependent which handler lines execute).
+test-coverage-check: test-coverage
+	@scripts/coverage-check.sh $(COVERAGE_PROFILE) $(COVERAGE_BASELINE)
+
 ########################################################
 ## Lint
 ########################################################
@@ -185,12 +246,17 @@ test: prepare-test
 ## everything else automatically, so new packages are scanned by default.
 LINT_EXCLUDE_DIRS_RE=/(backend/go/(piper|silero-vad|llm)|cmd/launcher)(/|$$)
 
+## Set LINT_NEW_FROM to a git ref to override .golangci.yml's
+## new-from-merge-base (origin/master). Useful from a fork clone where
+## origin/master is stale relative to the canonical repo — the pre-commit
+## hook passes the resolved upstream ref here so local lint matches CI.
+LINT_NEW_FROM?=
 lint:
 	@command -v golangci-lint >/dev/null 2>&1 || { \
 		echo 'golangci-lint not installed. Install: go install github.com/golangci/golangci-lint/v2/cmd/golangci-lint@latest'; \
 		exit 1; \
 	}
-	golangci-lint run $$(go list -e -f '{{.Dir}}' ./... | grep -vE '$(LINT_EXCLUDE_DIRS_RE)')
+	golangci-lint run $(if $(LINT_NEW_FROM),--new-from-merge-base=$(LINT_NEW_FROM),) $$(go list -e -f '{{.Dir}}' ./... | grep -vE '$(LINT_EXCLUDE_DIRS_RE)')
 
 ## Like `lint` but reports every issue, including the pre-existing baseline
 ## that `lint` ignores via .golangci.yml's new-from-merge-base. Use this to
@@ -202,6 +268,17 @@ lint-all:
 	}
 	golangci-lint run --new=false --new-from-merge-base= --new-from-rev= $$(go list -e -f '{{.Dir}}' ./... | grep -vE '$(LINT_EXCLUDE_DIRS_RE)')
 
+########################################################
+## Git hooks
+########################################################
+## Points git at the versioned .githooks/ directory so the pre-commit hook
+## (lint + coverage gate) runs locally. Run once per clone. Undo with:
+## `git config --unset core.hooksPath`. Skip a single commit with
+## `git commit --no-verify`.
+install-hooks:
+	git config core.hooksPath .githooks
+	@echo 'Installed git hooks: core.hooksPath -> .githooks (pre-commit runs lint + test-coverage-check on Go changes)'
+
 ########################################################
 ## E2E AIO tests (uses standard image with pre-configured models)
 ########################################################
@@ -481,6 +558,7 @@ prepare-test-extra: protogen-python
 	$(MAKE) -C backend/python/insightface
 	$(MAKE) -C backend/python/speaker-recognition
 	$(MAKE) -C backend/rust/kokoros kokoros-grpc
+	$(MAKE) -C backend/go/rfdetr-cpp
 
 test-extra: prepare-test-extra
 	$(MAKE) -C backend/python/transformers test
@@ -507,6 +585,7 @@ test-extra: prepare-test-extra
 	$(MAKE) -C backend/python/insightface test
 	$(MAKE) -C backend/python/speaker-recognition test
 	$(MAKE) -C backend/rust/kokoros test
+	$(MAKE) -C backend/go/rfdetr-cpp test
 
 ##
 ## End-to-end gRPC tests that exercise a built backend container image.
@@ -912,6 +991,19 @@ test-extra-backend-whisper-transcription: docker-build-whisper
 	BACKEND_TEST_CAPS=health,load,transcription \
 	$(MAKE) test-extra-backend
 
+## Audio transcription wrapper for the parakeet-cpp (parakeet.cpp ggml port)
+## backend. Mirrors test-extra-backend-whisper-transcription: drives the
+## AudioTranscription / AudioTranscriptionStream RPCs against a published
+## Parakeet GGUF using the JFK 11s clip from whisper.cpp's CI samples. Not
+## part of the default test suite - run explicitly once the pinned model URL
+## is reachable.
+test-extra-backend-parakeet-cpp-transcription: docker-build-parakeet-cpp
+	BACKEND_IMAGE=local-ai-backend:parakeet-cpp \
+	BACKEND_TEST_MODEL_URL=https://huggingface.co/mudler/parakeet-cpp-gguf/resolve/main/tdt_ctc-110m-f16.gguf \
+	BACKEND_TEST_AUDIO_URL=https://github.com/ggml-org/whisper.cpp/raw/master/samples/jfk.wav \
+	BACKEND_TEST_CAPS=health,load,transcription \
+	$(MAKE) test-extra-backend
+
 ## LocalVQE audio transform (joint AEC + noise suppression + dereverb).
 ## Exercises the audio_transform capability end-to-end: batch transform
 ## of a real WAV fixture and bidi streaming of synthetic silent frames.
@@ -1070,6 +1162,7 @@ BACKEND_HUGGINGFACE = huggingface|golang|.|false|true
 BACKEND_SILERO_VAD = silero-vad|golang|.|false|true
 BACKEND_STABLEDIFFUSION_GGML = stablediffusion-ggml|golang|.|--progress=plain|true
 BACKEND_WHISPER = whisper|golang|.|false|true
+BACKEND_PARAKEET_CPP = parakeet-cpp|golang|.|false|true
 BACKEND_VOXTRAL = voxtral|golang|.|false|true
 BACKEND_ACESTEP_CPP = acestep-cpp|golang|.|false|true
 BACKEND_QWEN3_TTS_CPP = qwen3-tts-cpp|golang|.|false|true
@@ -1119,6 +1212,7 @@ BACKEND_KOKOROS = kokoros|rust|.|false|true
 
 # C++ backends (Go wrapper with purego)
 BACKEND_SAM3_CPP = sam3-cpp|golang|.|false|true
+BACKEND_RFDETR_CPP = rfdetr-cpp|golang|.|false|true
 
 # Helper function to build docker image for a backend
 # Usage: $(call docker-build-backend,BACKEND_NAME,DOCKERFILE_TYPE,BUILD_CONTEXT,PROGRESS_FLAG,NEEDS_BACKEND_ARG)
@@ -1156,6 +1250,7 @@ $(eval $(call generate-docker-build-target,$(BACKEND_HUGGINGFACE)))
 $(eval $(call generate-docker-build-target,$(BACKEND_SILERO_VAD)))
 $(eval $(call generate-docker-build-target,$(BACKEND_STABLEDIFFUSION_GGML)))
 $(eval $(call generate-docker-build-target,$(BACKEND_WHISPER)))
+$(eval $(call generate-docker-build-target,$(BACKEND_PARAKEET_CPP)))
 $(eval $(call generate-docker-build-target,$(BACKEND_VOXTRAL)))
 $(eval $(call generate-docker-build-target,$(BACKEND_OPUS)))
 $(eval $(call generate-docker-build-target,$(BACKEND_RERANKERS)))
@@ -1198,13 +1293,14 @@ $(eval $(call generate-docker-build-target,$(BACKEND_LLAMA_CPP_QUANTIZATION)))
 $(eval $(call generate-docker-build-target,$(BACKEND_TINYGRAD)))
 $(eval $(call generate-docker-build-target,$(BACKEND_KOKOROS)))
 $(eval $(call generate-docker-build-target,$(BACKEND_SAM3_CPP)))
+$(eval $(call generate-docker-build-target,$(BACKEND_RFDETR_CPP)))
 $(eval $(call generate-docker-build-target,$(BACKEND_SHERPA_ONNX)))
 
 # Pattern rule for docker-save targets
 docker-save-%: backend-images
 	docker save local-ai-backend:$* -o backend-images/$*.tar
 
-docker-build-backends: docker-build-llama-cpp docker-build-ik-llama-cpp docker-build-turboquant docker-build-ds4 docker-build-rerankers docker-build-vllm docker-build-vllm-omni docker-build-sglang docker-build-transformers docker-build-outetts docker-build-diffusers docker-build-kokoro docker-build-faster-whisper docker-build-coqui docker-build-chatterbox docker-build-vibevoice docker-build-liquid-audio docker-build-moonshine docker-build-pocket-tts docker-build-qwen-tts docker-build-fish-speech docker-build-faster-qwen3-tts docker-build-qwen-asr docker-build-nemo docker-build-voxcpm docker-build-whisperx docker-build-ace-step docker-build-acestep-cpp docker-build-voxtral docker-build-mlx-distributed docker-build-trl docker-build-llama-cpp-quantization docker-build-tinygrad docker-build-kokoros docker-build-sam3-cpp docker-build-qwen3-tts-cpp docker-build-vibevoice-cpp docker-build-localvqe docker-build-insightface docker-build-speaker-recognition docker-build-sherpa-onnx docker-build-cloud-proxy
+docker-build-backends: docker-build-llama-cpp docker-build-ik-llama-cpp docker-build-turboquant docker-build-ds4 docker-build-rerankers docker-build-vllm docker-build-vllm-omni docker-build-sglang docker-build-transformers docker-build-outetts docker-build-diffusers docker-build-kokoro docker-build-faster-whisper docker-build-coqui docker-build-chatterbox docker-build-vibevoice docker-build-liquid-audio docker-build-moonshine docker-build-pocket-tts docker-build-qwen-tts docker-build-fish-speech docker-build-faster-qwen3-tts docker-build-qwen-asr docker-build-nemo docker-build-voxcpm docker-build-whisperx docker-build-ace-step docker-build-acestep-cpp docker-build-voxtral docker-build-mlx-distributed docker-build-trl docker-build-llama-cpp-quantization docker-build-tinygrad docker-build-kokoros docker-build-sam3-cpp docker-build-rfdetr-cpp docker-build-qwen3-tts-cpp docker-build-vibevoice-cpp docker-build-localvqe docker-build-insightface docker-build-speaker-recognition docker-build-sherpa-onnx docker-build-cloud-proxy
 
 ########################################################
 ### Mock Backend for E2E Tests
@@ -1232,6 +1328,50 @@ build-ui-test-server: build-mock-backend react-ui protogen-go
 test-ui-e2e: build-ui-test-server
 	cd core/http/react-ui && npm install && npx playwright install --with-deps chromium && npx playwright test
 
+## Optional Playwright worker count for the UI e2e targets below. Pass
+## UI_TEST_WORKERS=N (e.g. `make test-ui-coverage UI_TEST_WORKERS=20`) to
+## override Playwright's default (cores/2). Empty by default so Playwright
+## picks its own worker count.
+UI_TEST_WORKERS ?=
+PLAYWRIGHT_WORKERS_FLAG = $(if $(UI_TEST_WORKERS),--workers=$(UI_TEST_WORKERS),)
+
+## Fast Playwright e2e run used by the pre-commit hook on React UI changes.
+## Force-rebuilds the (non-instrumented) dist so the suite tests the working
+## tree — not a stale dist the `react-ui` skip-guard would leave — re-embeds
+## it into ui-test-server, and runs the specs. Uses the nix-provided browser
+## when PLAYWRIGHT_CHROMIUM_PATH is set (flake dev shell), else falls back to
+## downloading it as `test-ui-e2e` does.
+test-ui: build-mock-backend protogen-go
+	cd core/http/react-ui && bun install && bun run build
+	$(GOCMD) build -o tests/e2e-ui/ui-test-server ./tests/e2e-ui
+	cd core/http/react-ui && sh $(CURDIR)/scripts/ensure-playwright-browser.sh && bunx playwright test $(PLAYWRIGHT_WORKERS_FLAG)
+
+## React UI code coverage from the Playwright e2e suite. Builds a
+## NON-instrumented bundle with source maps (COVERAGE_V8=true), re-embeds it
+## into the ui-test-server (the dist is //go:embed'ed at compile time), runs the
+## Playwright specs which collect native Chromium V8 coverage (PW_V8_COVERAGE=1)
+## — far cheaper than istanbul's build-time counters (~40% faster end-to-end) —
+## convert it to istanbul via v8-to-istanbul in the coverage fixture, and write
+## an nyc report to core/http/react-ui/coverage/. Removes the dist afterwards so
+## normal builds aren't served source-mapped assets. (The legacy istanbul path
+## still exists: `bun run build:coverage` + unset PW_V8_COVERAGE.)
+test-ui-coverage: build-mock-backend protogen-go
+	trap 'rm -rf "$(CURDIR)/core/http/react-ui/dist"' EXIT; \
+	( cd core/http/react-ui && bun install && bun run build:coverage-v8 ) && \
+	$(GOCMD) build -o tests/e2e-ui/ui-test-server ./tests/e2e-ui && \
+	( cd core/http/react-ui && rm -rf .nyc_output coverage && \
+	    sh $(CURDIR)/scripts/ensure-playwright-browser.sh && \
+	    PW_V8_COVERAGE=1 bunx playwright test $(PLAYWRIGHT_WORKERS_FLAG) && bun run coverage:report )
+
+## UI coverage baseline (committed) and the strict gate that compares against
+## it — the React mirror of test-coverage-baseline / test-coverage-check.
+test-ui-coverage-baseline: test-ui-coverage
+	@node -e 'const fs=require("fs");process.stdout.write(String(JSON.parse(fs.readFileSync("core/http/react-ui/coverage/coverage-summary.json")).total.lines.pct))' > core/http/react-ui/coverage-baseline.txt
+	@echo "Saved UI coverage baseline: $$(cat core/http/react-ui/coverage-baseline.txt)% lines"
+
+test-ui-coverage-check: test-ui-coverage
+	sh $(CURDIR)/scripts/ui-coverage-check.sh core/http/react-ui/coverage/coverage-summary.json core/http/react-ui/coverage-baseline.txt
+
 test-ui-e2e-docker:
 	docker build -t localai-ui-e2e -f tests/e2e-ui/Dockerfile .
 	docker run --rm localai-ui-e2e

README.md

@@ -149,8 +149,10 @@ For more details, see the [Getting Started guide](https://localai.io/basics/gett
 
 ## Latest News
 
-- **April 2026**: [Voice recognition](https://github.com/mudler/LocalAI/pull/9500), [Face recognition, identification & liveness detection](https://github.com/mudler/LocalAI/pull/9480), [Ollama API compatibility](https://github.com/mudler/LocalAI/pull/9284), [Video generation in stable-diffusion.ggml](https://github.com/mudler/LocalAI/pull/9420), [Backend versioning with auto-upgrade](https://github.com/mudler/LocalAI/pull/9315), [Pin models & load-on-demand toggle](https://github.com/mudler/LocalAI/pull/9309), [Universal model importer](https://github.com/mudler/LocalAI/pull/9466), new backends: [sglang](https://github.com/mudler/LocalAI/pull/9359), [ik-llama-cpp](https://github.com/mudler/LocalAI/pull/9326), [TurboQuant](https://github.com/mudler/LocalAI/pull/9355), [sam.cpp](https://github.com/mudler/LocalAI/pull/9288), [Kokoros](https://github.com/mudler/LocalAI/pull/9212), [qwen3tts.cpp](https://github.com/mudler/LocalAI/pull/9316), [tinygrad multimodal](https://github.com/mudler/LocalAI/pull/9364)
-- **March 2026**: [Agent management](https://github.com/mudler/LocalAI/pull/8820), [New React UI](https://github.com/mudler/LocalAI/pull/8772), [WebRTC](https://github.com/mudler/LocalAI/pull/8790), [MLX-distributed via P2P and RDMA](https://github.com/mudler/LocalAI/pull/8801), [MCP Apps, MCP Client-side](https://github.com/mudler/LocalAI/pull/8947)
+- **May 2026**: **LocalAI 4.3.0** - `llama.cpp` [prompt cache on by default](https://github.com/mudler/LocalAI/pull/9925) (repeated system prompts collapse from minutes to seconds), [keyless cosign signing of backend OCI images](https://github.com/mudler/LocalAI/pull/9823), [per-API-key + per-user usage attribution](https://github.com/mudler/LocalAI/pull/9920), Distributed v3 with [per-request replica routing](https://github.com/mudler/LocalAI/pull/9968). [Release notes](https://github.com/mudler/LocalAI/releases/tag/v4.3.0)
+- **May 2026**: **LocalAI 4.2.0** - LocalAI sees and hears: [voice recognition](https://github.com/mudler/LocalAI/pull/9500), [face recognition + antispoofing liveness](https://github.com/mudler/LocalAI/pull/9480), speaker diarization. Plus [drop-in Ollama API](https://github.com/mudler/LocalAI/pull/9284), [video generation](https://github.com/mudler/LocalAI/pull/9420), redesigned UI with i18n + admin-configurable branding, vLLM at feature parity with llama.cpp, and 11 new backends. [Release notes](https://github.com/mudler/LocalAI/releases/tag/v4.2.0)
+- **April 2026**: **LocalAI 4.1.0** - LocalAI becomes a control tower: distributed cluster mode with VRAM-aware smart routing + autoscaling, multi-user platform with OIDC and API keys, per-user quotas with predictive analytics, in-UI fine-tuning with TRL (auto-export to GGUF), on-the-fly quantization backend, visual pipeline editor. [Release notes](https://github.com/mudler/LocalAI/releases/tag/v4.1.0)
+- **March 2026**: **LocalAI 4.0.0** - native agentic orchestration with the new [Agenthub](https://agenthub.localai.io) community hub, full React UI rewrite with Canvas mode, [MCP Apps + client-side](https://github.com/mudler/LocalAI/pull/8947) with tool streaming, [WebRTC realtime audio](https://github.com/mudler/LocalAI/pull/8790), [MLX-distributed](https://github.com/mudler/LocalAI/pull/8801). [Release notes](https://github.com/mudler/LocalAI/releases/tag/v4.0.0)
 - **February 2026**: [Realtime API for audio-to-audio with tool calling](https://github.com/mudler/LocalAI/pull/6245), [ACE-Step 1.5 support](https://github.com/mudler/LocalAI/pull/8396)
 - **January 2026**: **LocalAI 3.10.0** — Anthropic API support, Open Responses API, video & image generation (LTX-2), unified GPU backends, tool streaming, Moonshine, Pocket-TTS. [Release notes](https://github.com/mudler/LocalAI/releases/tag/v3.10.0)
 - **December 2025**: [Dynamic Memory Resource reclaimer](https://github.com/mudler/LocalAI/pull/7583), [Automatic multi-GPU model fitting (llama.cpp)](https://github.com/mudler/LocalAI/pull/7584), [Vibevoice backend](https://github.com/mudler/LocalAI/pull/7494)
@@ -236,11 +238,22 @@ A huge thank you to our generous sponsors who support this project covering CI e
   <a href="https://www.spectrocloud.com/" target="blank">
     <img height="200" src="https://github.com/user-attachments/assets/72eab1dd-8b93-4fc0-9ade-84db49f24962">
   </a>
+</p>
+
+<details>
+
+<summary>
+Past sponsors
+</summary>
+
+<p align="center">
   <a href="https://www.premai.io/" target="blank">
     <img height="200" src="https://github.com/mudler/LocalAI/assets/2420543/42e4ca83-661e-4f79-8e46-ae43689683d6"> <br>
   </a>
 </p>
 
+</details>
+
 ### Individual sponsors
 
 A special thanks to individual sponsors, a full list is on [GitHub](https://github.com/sponsors/mudler) and [buymeacoffee](https://buymeacoffee.com/mudler). Special shout out to [drikster80](https://github.com/drikster80) for being generous. Thank you everyone!

backend/cpp/ds4/CMakeLists.txt

@@ -60,6 +60,11 @@ elseif(DS4_GPU STREQUAL "cpu")
     set(DS4_OBJS "${DS4_DIR}/ds4_cpu.o")
 endif()
 
+# ds4.c now references ds4_distributed.c (distributed inference was split into
+# its own translation unit upstream). It is a single GPU-agnostic object shared
+# by every GPU mode, so link it in regardless of DS4_GPU.
+list(APPEND DS4_OBJS "${DS4_DIR}/ds4_distributed.o")
+
 add_executable(${TARGET}
     grpc-server.cpp
     dsml_parser.cpp

backend/cpp/ds4/Makefile

@@ -1,10 +1,10 @@
 # ds4 backend Makefile.
 #
-# Upstream pin lives below as DS4_VERSION?=f91c12b50a1448527c435c028bfc70d1b00f6c33
+# Upstream pin lives below as DS4_VERSION?=e16ead1e29c81a67bbb64e5b001117679cf9ce6e
 # (.github/bump_deps.sh) can find and update it - matches the
 # llama-cpp / ik-llama-cpp / turboquant convention.
 
-DS4_VERSION?=f91c12b50a1448527c435c028bfc70d1b00f6c33
+DS4_VERSION?=e16ead1e29c81a67bbb64e5b001117679cf9ce6e
 DS4_REPO?=https://github.com/antirez/ds4
 
 CURRENT_MAKEFILE_DIR := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))
@@ -18,16 +18,19 @@ UNAME_S := $(shell uname -s)
 
 CMAKE_ARGS ?= -DCMAKE_BUILD_TYPE=Release
 
+# ds4_distributed.o is a GPU-agnostic translation unit that ds4.c/ds4_cpu.o now
+# reference (upstream split distributed inference into its own .c). The same
+# object is shared by every GPU mode, so it is appended unconditionally below.
 ifeq ($(BUILD_TYPE),cublas)
     CMAKE_ARGS += -DDS4_GPU=cuda
-    DS4_OBJ_TARGET := ds4.o ds4_cuda.o
+    DS4_OBJ_TARGET := ds4.o ds4_cuda.o ds4_distributed.o
 else ifeq ($(UNAME_S),Darwin)
     CMAKE_ARGS += -DDS4_GPU=metal
-    DS4_OBJ_TARGET := ds4.o ds4_metal.o
+    DS4_OBJ_TARGET := ds4.o ds4_metal.o ds4_distributed.o
 else
     # CPU reference path (Linux only - macOS CPU path is broken by VM bug per ds4 README).
     CMAKE_ARGS += -DDS4_GPU=cpu
-    DS4_OBJ_TARGET := ds4_cpu.o
+    DS4_OBJ_TARGET := ds4_cpu.o ds4_distributed.o
 endif
 
 ifneq ($(NATIVE),true)
@@ -52,11 +55,11 @@ ds4:
 # the right per-platform compile flags (Objective-C/Metal on Darwin, nvcc on Linux+CUDA).
 ds4/ds4.o: ds4
 ifeq ($(BUILD_TYPE),cublas)
-	+$(MAKE) -C ds4 ds4.o ds4_cuda.o
+	+$(MAKE) -C ds4 ds4.o ds4_cuda.o ds4_distributed.o
 else ifeq ($(UNAME_S),Darwin)
-	+$(MAKE) -C ds4 ds4.o ds4_metal.o
+	+$(MAKE) -C ds4 ds4.o ds4_metal.o ds4_distributed.o
 else
-	+$(MAKE) -C ds4 ds4_cpu.o
+	+$(MAKE) -C ds4 ds4_cpu.o ds4_distributed.o
 endif
 
 grpc-server: ds4/ds4.o

backend/cpp/ik-llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-IK_LLAMA_VERSION?=9f7ba245ab41e118f03aa8dd5134d18a81159d02
+IK_LLAMA_VERSION?=8960c5ba5ee9db30ba838304373aa4dbec9f7cbd
 LLAMA_REPO?=https://github.com/ikawrakow/ik_llama.cpp
 
 CMAKE_ARGS?=

backend/cpp/llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-LLAMA_VERSION?=549b9d84330c327e6791fa812a7d60c0cf63572e
+LLAMA_VERSION?=22d66b567eef11cf2e9832f04db64ee0323a0fd0
 LLAMA_REPO?=https://github.com/ggerganov/llama.cpp
 
 CMAKE_ARGS?=

backend/cpp/llama-cpp/grpc-server.cpp

@@ -573,8 +573,12 @@ static void params_parse(server_context& /*ctx_server*/, const backend::ModelOpt
     // checkpoint_min_step: minimum spacing between context checkpoints in
     // tokens (0 disables the minimum). Match upstream's default (256). This
     // field was renamed from `checkpoint_every_nt` in llama.cpp; the semantics
-    // also shifted from a fixed cadence to a minimum spacing.
+    // also shifted from a fixed cadence to a minimum spacing. The turboquant
+    // fork branched before the field existed, so skip it on the legacy path
+    // (LOCALAI_LEGACY_LLAMA_CPP_SPEC is injected by patch-grpc-server.sh).
+#ifndef LOCALAI_LEGACY_LLAMA_CPP_SPEC
     params.checkpoint_min_step = 256;
+#endif
 
      // decode options. Options are in form optname:optvale, or if booleans only optname.
     for (int i = 0; i < request->options_size(); i++) {
@@ -748,11 +752,18 @@ static void params_parse(server_context& /*ctx_server*/, const backend::ModelOpt
                 params.cache_idle_slots = false;
             }
 
+#ifndef LOCALAI_LEGACY_LLAMA_CPP_SPEC
         // --- minimum context-checkpoint spacing (upstream -cms / --checkpoint-min-step) ---
         // 0 disables the minimum-spacing gate. Old option names (`checkpoint_every_nt`,
         // `checkpoint_every_n_tokens`) are kept as aliases for backward compatibility
         // with existing user configs: upstream renamed the field and shifted its
         // semantics from a fixed cadence to a minimum spacing.
+        //
+        // Gated out for the turboquant fork, which lacks common_params::
+        // checkpoint_min_step. The leading `}` closing the cache_idle_slots
+        // branch is removed with this block; the next `} else if` (n_ubatch)
+        // then closes cache_idle_slots, so braces stay balanced under both
+        // preprocessor branches.
         } else if (!strcmp(optname, "checkpoint_min_step") || !strcmp(optname, "checkpoint_min_spacing") ||
                    !strcmp(optname, "checkpoint_every_nt") || !strcmp(optname, "checkpoint_every_n_tokens")) {
             if (optval != NULL) {
@@ -762,6 +773,7 @@ static void params_parse(server_context& /*ctx_server*/, const backend::ModelOpt
                     // If conversion fails, keep default value (256)
                 }
             }
+#endif
 
         // --- physical batch size (upstream -ub / --ubatch-size) ---
         // Note: line ~482 already aliases n_ubatch to n_batch as a default; this
@@ -1165,9 +1177,15 @@ static void params_parse(server_context& /*ctx_server*/, const backend::ModelOpt
             params.tensor_buft_overrides.push_back({nullptr, nullptr});
         }
     }
+    // The draft tensor_buft_overrides are only populated under the modern
+    // (post-#22838) layout, whose population code is itself gated by
+    // LOCALAI_LEGACY_LLAMA_CPP_SPEC above. The turboquant fork lacks
+    // common_params_speculative::draft entirely, so skip the sentinel there too.
+#ifndef LOCALAI_LEGACY_LLAMA_CPP_SPEC
     if (!params.speculative.draft.tensor_buft_overrides.empty()) {
         params.speculative.draft.tensor_buft_overrides.push_back({nullptr, nullptr});
     }
+#endif
 
     // TODO: Add yarn
 

backend/cpp/turboquant/patch-grpc-server.sh

@@ -124,8 +124,11 @@ fi
 # 5. Define LOCALAI_LEGACY_LLAMA_CPP_SPEC at the top of the file so the
 #    grpc-server option parser skips the new option-handler blocks (ngram_mod,
 #    ngram_map_k, ngram_map_k4v, ngram_cache, draft.cache_type_*, draft.cpuparams*,
-#    draft.tensor_buft_overrides) introduced for the post-#22838 layout. Those
-#    blocks reference struct fields that simply do not exist in the fork.
+#    draft.tensor_buft_overrides) introduced for the post-#22838 layout, the
+#    draft.tensor_buft_overrides sentinel termination, and the
+#    common_params::checkpoint_min_step default/option (added with the
+#    35c9b1f3 bump). Those blocks reference struct fields that simply do not
+#    exist in the fork.
 if grep -q '^#define LOCALAI_LEGACY_LLAMA_CPP_SPEC' "$SRC"; then
     echo "==> $SRC already defines LOCALAI_LEGACY_LLAMA_CPP_SPEC, skipping"
 else

backend/go/cloud-proxy/passthrough_edge_test.go

@@ -192,6 +192,61 @@ var _ = Describe("Forward", func() {
 		Expect(<-gotAuth).To(Equal("Bearer sk-real"), "caller-supplied Basic header must be replaced")
 	})
 
+	It("refuses to follow upstream redirects and never leaks the key to the redirect target", func() {
+		// A 3xx from the configured upstream means misconfiguration or a
+		// hijacked/spoofed host. Following it would replay the request —
+		// and the injected API key — to the Location host. Anthropic's
+		// x-api-key is NOT stripped by Go on cross-host redirects, so this
+		// would be a credential leak. The proxy must refuse the redirect.
+		sinkHit := make(chan string, 1)
+		sink := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+			sinkHit <- r.Header.Get("x-api-key")
+			w.WriteHeader(http.StatusOK)
+		}))
+		defer sink.Close()
+
+		redirector := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+			http.Redirect(w, r, sink.URL, http.StatusFound)
+		}))
+		defer redirector.Close()
+
+		GinkgoT().Setenv("CLOUD_PROXY_REDIRECT_KEY", "ant-secret")
+
+		cp := NewCloudProxy()
+		Expect(cp.Load(&pb.ModelOptions{
+			Proxy: &pb.ProxyOptions{
+				UpstreamUrl: redirector.URL,
+				Mode:        modePassthrough,
+				Provider:    providerAnthropic,
+				ApiKeyEnv:   "CLOUD_PROXY_REDIRECT_KEY",
+			},
+		})).To(Succeed())
+
+		addr := "test://forward-no-redirect"
+		grpc.Provide(addr, cp)
+		c := grpc.NewClient(addr, true, nil, false)
+		stream, err := c.Forward(context.Background())
+		Expect(err).NotTo(HaveOccurred())
+		Expect(stream.Send(&pb.ForwardRequest{
+			Path:   "/v1/messages",
+			Method: "POST",
+		})).To(Succeed())
+		Expect(stream.CloseSend()).To(Succeed())
+
+		// Drain the stream; a refused redirect surfaces as a non-EOF error.
+		var streamErr error
+		for {
+			if _, err := stream.Recv(); err != nil {
+				if !errors.Is(err, io.EOF) {
+					streamErr = err
+				}
+				break
+			}
+		}
+		Expect(streamErr).To(HaveOccurred(), "refused redirect must surface as an error")
+		Expect(sinkHit).NotTo(Receive(), "the redirect target must never be contacted")
+	})
+
 	It("handles concurrent calls without interference", func() {
 		// CloudProxy explicitly omits base.SingleThread — independent
 		// Forward streams must not block each other or leak state.

backend/go/cloud-proxy/proxy.go

@@ -11,9 +11,11 @@ import (
 	"strings"
 	"sync/atomic"
 
+	"github.com/mudler/xlog"
+
 	"github.com/mudler/LocalAI/pkg/grpc/base"
 	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
-	"github.com/mudler/xlog"
+	"github.com/mudler/LocalAI/pkg/httpclient"
 )
 
 // Mirror of core/config.Proxy{Mode,Provider}* — backends don't
@@ -48,10 +50,15 @@ type proxyConfig struct {
 }
 
 func NewCloudProxy() *CloudProxy {
-	// No Client-level Timeout — that would bound streaming SSE
-	// responses too, which can legitimately last minutes. Per-request
-	// deadlines come from the gRPC stream context.
-	return &CloudProxy{client: &http.Client{}}
+	// httpclient.New refuses redirects outright: the proxy talks to a
+	// single configured upstream API (OpenAI/Anthropic/...) that answers
+	// directly, so a 3xx means misconfiguration, a hijacked upstream, or
+	// DNS trickery — never normal operation. Following it would replay the
+	// request, including the operator's x-api-key (which Go does NOT strip
+	// on cross-host redirects), to an unvetted host and leak the key
+	// (GHSA-3mj3-57v2-4636). It also imposes no body deadline, so streaming
+	// SSE responses that legitimately last minutes are not truncated.
+	return &CloudProxy{client: httpclient.New()}
 }
 
 func (c *CloudProxy) Load(opts *pb.ModelOptions) error {
@@ -426,4 +433,3 @@ func isHopByHopHeader(name string) bool {
 	}
 	return false
 }
-

backend/go/parakeet-cpp/.gitignore

@@ -0,0 +1,11 @@
+.cache/
+sources/
+build/
+package/
+parakeet-cpp-grpc
+# build artifacts staged in-tree by the Makefile (cp from sources/) or
+# symlinked for local dev; the real sources live in parakeet.cpp upstream.
+*.so
+*.so.*
+parakeet_capi.h
+compile_commands.json

backend/go/parakeet-cpp/Makefile

@@ -0,0 +1,89 @@
+# parakeet-cpp backend Makefile.
+#
+# Upstream pin lives below as PARAKEET_VERSION?=30a307553f1965ceb38a1a922069a71e7dd67bf3
+# (.github/bump_deps.sh) can find and update it - matches the
+# whisper.cpp / ds4 / vibevoice-cpp convention.
+#
+# Local dev shortcut: if you already have an out-of-tree parakeet.cpp
+# build, you can symlink the .so + header into this directory and skip
+# the clone/cmake steps entirely, e.g.:
+#
+#   ln -sf /path/to/parakeet.cpp/build-shared/libparakeet.so .
+#   ln -sf /path/to/parakeet.cpp/include/parakeet_capi.h .
+#   go build -o parakeet-cpp-grpc .
+#
+# That's what the L0 smoke test uses. The default target below does the
+# proper clone-at-pin + cmake build so CI doesn't need a side-checkout.
+
+PARAKEET_VERSION?=30a307553f1965ceb38a1a922069a71e7dd67bf3
+PARAKEET_REPO?=https://github.com/mudler/parakeet.cpp
+
+GOCMD?=go
+GO_TAGS?=
+JOBS?=$(shell nproc 2>/dev/null || sysctl -n hw.ncpu 2>/dev/null || echo 4)
+
+BUILD_TYPE?=
+NATIVE?=false
+
+# Build ggml statically into libparakeet.so (PIC) so the shared lib is
+# self-contained: dlopen needs no libggml*.so alongside it, only system libs
+# (libstdc++/libgomp/libc) that the runtime image already provides.
+CMAKE_ARGS?=-DCMAKE_BUILD_TYPE=Release -DPARAKEET_SHARED=ON -DPARAKEET_BUILD_CLI=OFF -DBUILD_SHARED_LIBS=OFF -DCMAKE_POSITION_INDEPENDENT_CODE=ON
+
+ifeq ($(NATIVE),false)
+	CMAKE_ARGS+=-DGGML_NATIVE=OFF
+endif
+
+ifeq ($(BUILD_TYPE),cublas)
+	CMAKE_ARGS+=-DGGML_CUDA=ON
+else ifeq ($(BUILD_TYPE),openblas)
+	CMAKE_ARGS+=-DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS
+else ifeq ($(BUILD_TYPE),hipblas)
+	CMAKE_ARGS+=-DGGML_HIP=ON
+else ifeq ($(BUILD_TYPE),vulkan)
+	CMAKE_ARGS+=-DGGML_VULKAN=ON
+endif
+
+.PHONY: parakeet-cpp-grpc package build clean purge test all
+
+all: parakeet-cpp-grpc
+
+# Clone the upstream parakeet.cpp source at the pinned commit. Directory
+# acts as the target so make only re-clones when missing. After a
+# PARAKEET_VERSION bump, run 'make purge && make' to refetch.
+sources/parakeet.cpp:
+	mkdir -p sources/parakeet.cpp
+	cd sources/parakeet.cpp && \
+	git init -q && \
+	git remote add origin $(PARAKEET_REPO) && \
+	git fetch --depth 1 origin $(PARAKEET_VERSION) && \
+	git checkout FETCH_HEAD && \
+	git submodule update --init --recursive --depth 1 --single-branch
+
+# Build the shared lib + header out-of-tree, then stage them next to the
+# Go sources so purego.Dlopen("libparakeet.so") and the cgo-less build
+# both pick them up.
+libparakeet.so: sources/parakeet.cpp
+	cmake -B sources/parakeet.cpp/build-shared -S sources/parakeet.cpp $(CMAKE_ARGS)
+	cmake --build sources/parakeet.cpp/build-shared --config Release -j$(JOBS)
+	cp -fv sources/parakeet.cpp/build-shared/libparakeet.so* ./ 2>/dev/null || true
+	cp -fv sources/parakeet.cpp/include/parakeet_capi.h ./
+
+parakeet-cpp-grpc: libparakeet.so main.go goparakeetcpp.go
+	CGO_ENABLED=0 $(GOCMD) build -tags "$(GO_TAGS)" -o parakeet-cpp-grpc .
+
+package: parakeet-cpp-grpc
+	bash package.sh
+
+build: package
+
+# Test target. Smoke test is gated on PARAKEET_BACKEND_TEST_MODEL +
+# PARAKEET_BACKEND_TEST_WAV; without them the spec auto-skips.
+test:
+	LD_LIBRARY_PATH=$(CURDIR):$$LD_LIBRARY_PATH $(GOCMD) test ./... -count=1
+
+clean: purge
+	rm -rf libparakeet.so* parakeet_capi.h package parakeet-cpp-grpc
+
+purge:
+	rm -rf sources/parakeet.cpp

backend/go/parakeet-cpp/goparakeetcpp.go

@@ -0,0 +1,393 @@
+package main
+
+import (
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"os"
+	"path/filepath"
+	"strings"
+	"unsafe"
+
+	"github.com/go-audio/wav"
+	"github.com/mudler/LocalAI/pkg/grpc/base"
+	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	"github.com/mudler/LocalAI/pkg/utils"
+	"google.golang.org/grpc/codes"
+	"google.golang.org/grpc/status"
+)
+
+// purego-bound entry points from libparakeet.so. Names match
+// parakeet_capi.h exactly so a `nm libparakeet.so | grep parakeet_capi`
+// is enough to spot drift.
+//
+// Functions that return char* are declared as uintptr so we can call
+// parakeet_capi_free_string on the same pointer after copying, the
+// C-API contract is "caller owns and must free the returned buffer".
+var (
+	CppAbiVersion         func() int32
+	CppLoad               func(ggufPath string) uintptr
+	CppFree               func(ctx uintptr)
+	CppTranscribePath     func(ctx uintptr, wavPath string, decoder int32) uintptr
+	CppTranscribePathJSON func(ctx uintptr, wavPath string, decoder int32) uintptr
+	CppFreeString         func(s uintptr)
+	CppLastError          func(ctx uintptr) string
+
+	// Cache-aware streaming (RNN-T) entry points. stream_begin returns 0 for
+	// non-streaming models. feed/finalize return a malloc'd char* (uintptr,
+	// freed via CppFreeString); feed writes 1 to *eouOut on an <EOU>/<EOB>.
+	CppStreamBegin    func(ctx uintptr) uintptr
+	CppStreamFeed     func(s uintptr, pcm []float32, nSamples int32, eouOut unsafe.Pointer) uintptr
+	CppStreamFinalize func(s uintptr) uintptr
+	CppStreamFree     func(s uintptr)
+)
+
+// streamChunkSamples is how much 16 kHz mono PCM we hand to stream_feed per
+// call (1 s). The session buffers internally and decodes once a full
+// cache-aware encoder chunk is available, so this only bounds how often we
+// poll for newly-finalized text, not the model's actual chunk size.
+const streamChunkSamples = 16000
+
+// transcriptJSON mirrors the document returned by
+// parakeet_capi_transcribe_path_json (see parakeet_capi.h):
+//
+//	{"text":"...",
+//	 "words":[{"w":"...","start":0.480,"end":0.640,"conf":0.9100}, ...],
+//	 "tokens":[{"id":123,"t":0.480,"conf":0.9100}, ...]}
+//
+// "start"/"end"/"t" are seconds; "conf" is confidence in (0,1].
+type transcriptJSON struct {
+	Text   string            `json:"text"`
+	Words  []transcriptWord  `json:"words"`
+	Tokens []transcriptToken `json:"tokens"`
+}
+
+type transcriptWord struct {
+	W     string  `json:"w"`
+	Start float64 `json:"start"`
+	End   float64 `json:"end"`
+	Conf  float64 `json:"conf"`
+}
+
+type transcriptToken struct {
+	ID   int32   `json:"id"`
+	T    float64 `json:"t"`
+	Conf float64 `json:"conf"`
+}
+
+// ParakeetCpp owns a single loaded parakeet_ctx. The C engine is a
+// thread-unsafe singleton (mirrors whisper.cpp / vibevoice.cpp), so we
+// serialize calls through base.SingleThread.
+type ParakeetCpp struct {
+	base.SingleThread
+	ctxPtr uintptr
+}
+
+// Load is the LocalAI gRPC entry point for LoadModel: it calls
+// parakeet_capi_load with the GGUF path and stashes the resulting
+// opaque context pointer for AudioTranscription.
+func (p *ParakeetCpp) Load(opts *pb.ModelOptions) error {
+	if opts.ModelFile == "" {
+		return errors.New("parakeet-cpp: ModelFile is required")
+	}
+
+	ctx := CppLoad(opts.ModelFile)
+	if ctx == 0 {
+		// No ctx to ask for last_error (the C-API's last-error buffer
+		// lives on the ctx that was never returned). Surface the path
+		// so the operator at least knows which load failed.
+		return fmt.Errorf("parakeet-cpp: parakeet_capi_load failed for %q", opts.ModelFile)
+	}
+	p.ctxPtr = ctx
+	return nil
+}
+
+// AudioTranscription runs parakeet_capi_transcribe_path_json on the wav at
+// opts.Dst with the default decoder (decoder=0, which selects the right head
+// per architecture: transducer for tdt/rnnt/hybrid, CTC for ctc) and shapes
+// the per-word timestamps into a LocalAI TranscriptResult.
+//
+// Parakeet emits word- and token-level timestamps but no native segment
+// boundaries, so we synthesise a single whole-clip segment spanning the first
+// word start to the last word end. Word-level timings are attached only when
+// the caller opts in via timestamp_granularities=["word"] (matching the
+// OpenAI API, whose default is segment-level); token ids always populate
+// Segment.Tokens.
+//
+// translate/diarize/prompt/temperature/language/threads are not applicable to
+// parakeet and are ignored; streaming is handled by AudioTranscriptionStream
+// (L2).
+func (p *ParakeetCpp) AudioTranscription(_ context.Context, opts *pb.TranscriptRequest) (pb.TranscriptResult, error) {
+	if p.ctxPtr == 0 {
+		return pb.TranscriptResult{}, errors.New("parakeet-cpp: model not loaded")
+	}
+	if opts.Dst == "" {
+		return pb.TranscriptResult{}, errors.New("parakeet-cpp: TranscriptRequest.dst (audio path) is required")
+	}
+
+	cstr := CppTranscribePathJSON(p.ctxPtr, opts.Dst, 0)
+	if cstr == 0 {
+		msg := CppLastError(p.ctxPtr)
+		if msg == "" {
+			msg = "unknown error"
+		}
+		return pb.TranscriptResult{}, fmt.Errorf("parakeet-cpp: transcribe_path_json failed: %s", msg)
+	}
+
+	raw := goStringFromCPtr(cstr)
+	CppFreeString(cstr)
+
+	var doc transcriptJSON
+	if err := json.Unmarshal([]byte(raw), &doc); err != nil {
+		return pb.TranscriptResult{}, fmt.Errorf("parakeet-cpp: decode transcript json: %w", err)
+	}
+
+	text := strings.TrimSpace(doc.Text)
+
+	words := make([]*pb.TranscriptWord, 0, len(doc.Words))
+	for _, w := range doc.Words {
+		words = append(words, &pb.TranscriptWord{
+			Start: secondsToNanos(w.Start),
+			End:   secondsToNanos(w.End),
+			Text:  w.W,
+		})
+	}
+
+	tokens := make([]int32, 0, len(doc.Tokens))
+	for _, t := range doc.Tokens {
+		tokens = append(tokens, t.ID)
+	}
+
+	// Single whole-clip segment, spanning the first word start to the last
+	// word end (0/0 when the clip produced no words).
+	var segStart, segEnd int64
+	if len(words) > 0 {
+		segStart = words[0].Start
+		segEnd = words[len(words)-1].End
+	}
+	seg := &pb.TranscriptSegment{
+		Id:     0,
+		Start:  segStart,
+		End:    segEnd,
+		Text:   text,
+		Tokens: tokens,
+	}
+	if wordsRequested(opts.TimestampGranularities) {
+		seg.Words = words
+	}
+
+	return pb.TranscriptResult{
+		Text:     text,
+		Segments: []*pb.TranscriptSegment{seg},
+	}, nil
+}
+
+// wordsRequested reports whether the caller asked for word-level timestamps.
+// The OpenAI transcription API gates word timings behind
+// timestamp_granularities[] containing "word" and defaults to segment-level
+// otherwise; we follow that contract.
+func wordsRequested(granularities []string) bool {
+	for _, g := range granularities {
+		if strings.EqualFold(strings.TrimSpace(g), "word") {
+			return true
+		}
+	}
+	return false
+}
+
+// secondsToNanos converts the C-API's fractional-second timestamps into the
+// int64 nanoseconds LocalAI carries on TranscriptSegment/TranscriptWord, the
+// same nanosecond convention the whisper backend uses.
+func secondsToNanos(sec float64) int64 {
+	return int64(sec * 1e9)
+}
+
+// AudioTranscriptionStream drives the cache-aware streaming RNN-T over the
+// audio at opts.Dst: it decodes the file to 16 kHz mono PCM, feeds it in
+// chunks to parakeet_capi_stream_feed, and emits each newly-finalized text
+// run as a TranscriptStreamResponse delta. <EOU>/<EOB> events close the
+// current segment; a closing FinalResult carries the full transcript and the
+// per-utterance segments.
+//
+// stream_begin returns 0 for models that are not cache-aware streaming models
+// (only e.g. nvidia/parakeet_realtime_eou_120m-v1 qualifies). For those we fall
+// back to a single offline transcription emitted as one delta plus a closing
+// FinalResult, matching LocalAI's non-streaming streaming contract (and the
+// whisper backend), so the streaming endpoint works for every model.
+func (p *ParakeetCpp) AudioTranscriptionStream(ctx context.Context, opts *pb.TranscriptRequest, results chan *pb.TranscriptStreamResponse) error {
+	defer close(results)
+
+	if p.ctxPtr == 0 {
+		return errors.New("parakeet-cpp: model not loaded")
+	}
+	if opts.Dst == "" {
+		return errors.New("parakeet-cpp: TranscriptRequest.dst (audio path) is required")
+	}
+	if err := ctx.Err(); err != nil {
+		return status.Error(codes.Canceled, "transcription cancelled")
+	}
+
+	stream := CppStreamBegin(p.ctxPtr)
+	if stream == 0 {
+		// Not a cache-aware streaming model: run a normal offline
+		// transcription and emit it as one delta + a closing final result.
+		res, err := p.AudioTranscription(ctx, opts)
+		if err != nil {
+			return err
+		}
+		if t := strings.TrimSpace(res.Text); t != "" {
+			results <- &pb.TranscriptStreamResponse{Delta: t}
+		}
+		results <- &pb.TranscriptStreamResponse{FinalResult: &res}
+		return nil
+	}
+	defer CppStreamFree(stream)
+
+	data, duration, err := decodeWavMono16k(opts.Dst)
+	if err != nil {
+		return err
+	}
+
+	var (
+		full     strings.Builder
+		segText  strings.Builder
+		segments []*pb.TranscriptSegment
+		segID    int32
+	)
+
+	flushSegment := func() {
+		t := strings.TrimSpace(segText.String())
+		segText.Reset()
+		if t == "" {
+			return
+		}
+		segments = append(segments, &pb.TranscriptSegment{Id: segID, Text: t})
+		segID++
+	}
+
+	// emitDelta consumes the malloc'd char* returned by feed/finalize: frees
+	// it, accumulates the text, and sends a delta when non-empty. A 0 return
+	// is an error (vs the "" empty-but-non-NULL no-new-text case).
+	emitDelta := func(ret uintptr) error {
+		if ret == 0 {
+			msg := CppLastError(p.ctxPtr)
+			if msg == "" {
+				msg = "unknown error"
+			}
+			return fmt.Errorf("parakeet-cpp: stream feed/finalize failed: %s", msg)
+		}
+		delta := goStringFromCPtr(ret)
+		CppFreeString(ret)
+		if delta == "" {
+			return nil
+		}
+		full.WriteString(delta)
+		segText.WriteString(delta)
+		results <- &pb.TranscriptStreamResponse{Delta: delta}
+		return nil
+	}
+
+	for off := 0; off < len(data); off += streamChunkSamples {
+		if err := ctx.Err(); err != nil {
+			return status.Error(codes.Canceled, "transcription cancelled")
+		}
+		end := min(off+streamChunkSamples, len(data))
+		chunk := data[off:end]
+
+		var eou int32
+		ret := CppStreamFeed(stream, chunk, int32(len(chunk)), unsafe.Pointer(&eou))
+		if err := emitDelta(ret); err != nil {
+			return err
+		}
+		if eou != 0 {
+			flushSegment()
+		}
+	}
+
+	// Flush the streaming tail (final encoder chunk).
+	if err := emitDelta(CppStreamFinalize(stream)); err != nil {
+		return err
+	}
+	flushSegment()
+
+	text := strings.TrimSpace(full.String())
+	if len(segments) == 0 && text != "" {
+		segments = append(segments, &pb.TranscriptSegment{Id: 0, Text: text})
+	}
+	results <- &pb.TranscriptStreamResponse{
+		FinalResult: &pb.TranscriptResult{
+			Text:     text,
+			Segments: segments,
+			Duration: duration,
+		},
+	}
+	return nil
+}
+
+// decodeWavMono16k converts any input audio to 16 kHz mono PCM and returns the
+// float samples plus the clip duration in seconds. Mirrors the whisper
+// backend: utils.AudioToWav (ffmpeg) normalises rate/channels, go-audio
+// decodes the PCM.
+func decodeWavMono16k(path string) ([]float32, float32, error) {
+	dir, err := os.MkdirTemp("", "parakeet")
+	if err != nil {
+		return nil, 0, err
+	}
+	defer func() { _ = os.RemoveAll(dir) }()
+
+	converted := filepath.Join(dir, "converted.wav")
+	if err := utils.AudioToWav(path, converted); err != nil {
+		return nil, 0, err
+	}
+
+	fh, err := os.Open(converted)
+	if err != nil {
+		return nil, 0, err
+	}
+	defer func() { _ = fh.Close() }()
+
+	buf, err := wav.NewDecoder(fh).FullPCMBuffer()
+	if err != nil {
+		return nil, 0, err
+	}
+	data := buf.AsFloat32Buffer().Data
+	var duration float32
+	if buf.Format != nil && buf.Format.SampleRate > 0 {
+		duration = float32(len(data)) / float32(buf.Format.SampleRate)
+	}
+	return data, duration, nil
+}
+
+// Free releases the underlying parakeet_ctx. Called by LocalAI when the
+// model is unloaded.
+func (p *ParakeetCpp) Free() error {
+	if p.ctxPtr != 0 {
+		CppFree(p.ctxPtr)
+		p.ctxPtr = 0
+	}
+	return nil
+}
+
+// goStringFromCPtr copies a NUL-terminated C string into Go memory.
+// cptr is the raw pointer returned by purego from the C-API (a malloc'd
+// buffer the caller owns); callers must free it via CppFreeString after
+// the copy lands.
+//
+// The uintptr->unsafe.Pointer conversion below trips go vet's unsafeptr
+// check, which can't distinguish a C-owned heap pointer from Go-managed
+// memory. It is safe here: the pointer addresses a malloc'd C buffer the
+// Go GC neither tracks nor moves, and we dereference it immediately to
+// copy the bytes out, the same pattern (and the same tolerated warning)
+// as the whisper backend's unsafe.Slice over segsPtr.
+func goStringFromCPtr(cptr uintptr) string {
+	if cptr == 0 {
+		return ""
+	}
+	p := unsafe.Pointer(cptr) //nolint:govet // C-owned malloc'd buffer, not Go-GC memory (see doc above)
+	n := 0
+	for *(*byte)(unsafe.Add(p, n)) != 0 {
+		n++
+	}
+	return string(unsafe.Slice((*byte)(p), n))
+}

backend/go/parakeet-cpp/goparakeetcpp_test.go

@@ -0,0 +1,164 @@
+package main
+
+import (
+	"context"
+	"os"
+	"strings"
+	"sync"
+	"testing"
+
+	"github.com/ebitengine/purego"
+	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+)
+
+func TestParakeetCpp(t *testing.T) {
+	RegisterFailHandler(Fail)
+	RunSpecs(t, "parakeet-cpp Backend Suite")
+}
+
+var (
+	libLoadOnce sync.Once
+	libLoadErr  error
+)
+
+// ensureLibLoaded mirrors main.go's bootstrap so a Go test can drive
+// the C-API bridge without spinning up the gRPC server. Skips the
+// current spec when libparakeet.so isn't loadable from cwd
+// ($LD_LIBRARY_PATH or a symlink in ./).
+func ensureLibLoaded() {
+	libLoadOnce.Do(func() {
+		libName := os.Getenv("PARAKEET_LIBRARY")
+		if libName == "" {
+			libName = "libparakeet.so"
+		}
+		lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)
+		if err != nil {
+			libLoadErr = err
+			return
+		}
+		purego.RegisterLibFunc(&CppAbiVersion, lib, "parakeet_capi_abi_version")
+		purego.RegisterLibFunc(&CppLoad, lib, "parakeet_capi_load")
+		purego.RegisterLibFunc(&CppFree, lib, "parakeet_capi_free")
+		purego.RegisterLibFunc(&CppTranscribePath, lib, "parakeet_capi_transcribe_path")
+		purego.RegisterLibFunc(&CppTranscribePathJSON, lib, "parakeet_capi_transcribe_path_json")
+		purego.RegisterLibFunc(&CppStreamBegin, lib, "parakeet_capi_stream_begin")
+		purego.RegisterLibFunc(&CppStreamFeed, lib, "parakeet_capi_stream_feed")
+		purego.RegisterLibFunc(&CppStreamFinalize, lib, "parakeet_capi_stream_finalize")
+		purego.RegisterLibFunc(&CppStreamFree, lib, "parakeet_capi_stream_free")
+		purego.RegisterLibFunc(&CppFreeString, lib, "parakeet_capi_free_string")
+		purego.RegisterLibFunc(&CppLastError, lib, "parakeet_capi_last_error")
+	})
+	if libLoadErr != nil {
+		Skip("libparakeet.so not loadable: " + libLoadErr.Error())
+	}
+}
+
+// fixturesOrSkip returns the model + audio paths or skips the spec if
+// either env var is unset. The smoke test never runs in default CI; it
+// needs a real parakeet GGUF and a 16 kHz mono WAV on disk.
+func fixturesOrSkip() (string, string) {
+	modelPath := os.Getenv("PARAKEET_BACKEND_TEST_MODEL")
+	audioPath := os.Getenv("PARAKEET_BACKEND_TEST_WAV")
+	if modelPath == "" || audioPath == "" {
+		Skip("set PARAKEET_BACKEND_TEST_MODEL and PARAKEET_BACKEND_TEST_WAV to run this spec")
+	}
+	return modelPath, audioPath
+}
+
+var _ = Describe("ParakeetCpp", func() {
+	Context("AudioTranscription", func() {
+		It("transcribes a WAV via the parakeet C-API", func() {
+			modelPath, audioPath := fixturesOrSkip()
+			ensureLibLoaded()
+
+			p := &ParakeetCpp{}
+			Expect(p.Load(&pb.ModelOptions{ModelFile: modelPath})).To(Succeed())
+			defer func() { _ = p.Free() }()
+
+			res, err := p.AudioTranscription(context.Background(), &pb.TranscriptRequest{
+				Dst: audioPath,
+			})
+			Expect(err).ToNot(HaveOccurred())
+			Expect(strings.TrimSpace(res.Text)).ToNot(BeEmpty(),
+				"expected non-empty transcript for %s", audioPath)
+			Expect(res.Segments).To(HaveLen(1),
+				"synthesises a single whole-clip segment")
+			Expect(res.Segments[0].Text).To(Equal(res.Text),
+				"single segment text must equal the top-level text")
+			// Default (no granularities) is segment-level: no per-word timings.
+			Expect(res.Segments[0].Words).To(BeEmpty(),
+				"word timings are opt-in via timestamp_granularities")
+		})
+
+		It("emits word-level timestamps when granularity=word", func() {
+			modelPath, audioPath := fixturesOrSkip()
+			ensureLibLoaded()
+
+			p := &ParakeetCpp{}
+			Expect(p.Load(&pb.ModelOptions{ModelFile: modelPath})).To(Succeed())
+			defer func() { _ = p.Free() }()
+
+			res, err := p.AudioTranscription(context.Background(), &pb.TranscriptRequest{
+				Dst:                    audioPath,
+				TimestampGranularities: []string{"word"},
+			})
+			Expect(err).ToNot(HaveOccurred())
+			Expect(res.Segments).To(HaveLen(1))
+			seg := res.Segments[0]
+			Expect(seg.Words).ToNot(BeEmpty(),
+				"expected per-word timestamps with granularity=word")
+			// Monotonic, non-negative timings spanning the segment.
+			Expect(seg.Words[0].Start).To(BeNumerically(">=", int64(0)))
+			Expect(seg.End).To(BeNumerically(">=", seg.Start))
+			Expect(seg.Words[len(seg.Words)-1].End).To(Equal(seg.End),
+				"segment end tracks the last word")
+		})
+	})
+
+	Context("AudioTranscriptionStream", func() {
+		It("streams deltas and a closing FinalResult from a cache-aware model", func() {
+			// Streaming needs a cache-aware streaming model (e.g.
+			// realtime_eou); the offline test model would fail stream_begin.
+			modelPath := os.Getenv("PARAKEET_BACKEND_TEST_STREAM_MODEL")
+			audioPath := os.Getenv("PARAKEET_BACKEND_TEST_WAV")
+			if modelPath == "" || audioPath == "" {
+				Skip("set PARAKEET_BACKEND_TEST_STREAM_MODEL (cache-aware streaming model) and PARAKEET_BACKEND_TEST_WAV")
+			}
+			ensureLibLoaded()
+
+			p := &ParakeetCpp{}
+			Expect(p.Load(&pb.ModelOptions{ModelFile: modelPath})).To(Succeed())
+			defer func() { _ = p.Free() }()
+
+			results := make(chan *pb.TranscriptStreamResponse, 64)
+			errCh := make(chan error, 1)
+			go func() {
+				errCh <- p.AudioTranscriptionStream(context.Background(),
+					&pb.TranscriptRequest{Dst: audioPath}, results)
+			}()
+
+			var deltas []string
+			var final *pb.TranscriptResult
+			for r := range results {
+				if r.Delta != "" {
+					deltas = append(deltas, r.Delta)
+				}
+				if r.FinalResult != nil {
+					final = r.FinalResult
+				}
+			}
+			Expect(<-errCh).ToNot(HaveOccurred())
+
+			Expect(final).ToNot(BeNil(), "expected a closing FinalResult")
+			Expect(strings.TrimSpace(final.Text)).ToNot(BeEmpty(),
+				"expected a non-empty streamed transcript")
+			Expect(final.Segments).ToNot(BeEmpty(),
+				"FinalResult always carries at least one segment")
+			// The concatenated deltas reconstruct the final transcript.
+			Expect(strings.TrimSpace(strings.Join(deltas, ""))).To(Equal(strings.TrimSpace(final.Text)),
+				"deltas should reconstruct the final text")
+		})
+	})
+})

backend/go/parakeet-cpp/main.go

@@ -0,0 +1,68 @@
+package main
+
+// Started internally by LocalAI - one gRPC server per loaded model.
+//
+// Loads libparakeet.so via purego and registers the flat C-API entry
+// points declared in parakeet_capi.h. The library name can be overridden
+// with PARAKEET_LIBRARY (mirrors the WHISPER_LIBRARY / VIBEVOICECPP_LIBRARY
+// convention in the sibling backends); the default looks for the .so next
+// to this binary.
+import (
+	"flag"
+	"fmt"
+	"os"
+
+	"github.com/ebitengine/purego"
+	grpc "github.com/mudler/LocalAI/pkg/grpc"
+)
+
+var (
+	addr = flag.String("addr", "localhost:50051", "the address to connect to")
+)
+
+type LibFuncs struct {
+	FuncPtr any
+	Name    string
+}
+
+func main() {
+	libName := os.Getenv("PARAKEET_LIBRARY")
+	if libName == "" {
+		libName = "libparakeet.so"
+	}
+
+	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)
+	if err != nil {
+		panic(fmt.Errorf("parakeet-cpp: dlopen %q: %w", libName, err))
+	}
+
+	// Bound 1:1 to parakeet_capi.h. The C-API returns malloc'd char*
+	// buffers from transcribe_*; we register those as uintptr so we get
+	// the raw pointer back and can call parakeet_capi_free_string on it
+	// (purego's string return would copy and forget the original pointer,
+	// leaking it on every call).
+	libFuncs := []LibFuncs{
+		{&CppAbiVersion, "parakeet_capi_abi_version"},
+		{&CppLoad, "parakeet_capi_load"},
+		{&CppFree, "parakeet_capi_free"},
+		{&CppTranscribePath, "parakeet_capi_transcribe_path"},
+		{&CppTranscribePathJSON, "parakeet_capi_transcribe_path_json"},
+		{&CppStreamBegin, "parakeet_capi_stream_begin"},
+		{&CppStreamFeed, "parakeet_capi_stream_feed"},
+		{&CppStreamFinalize, "parakeet_capi_stream_finalize"},
+		{&CppStreamFree, "parakeet_capi_stream_free"},
+		{&CppFreeString, "parakeet_capi_free_string"},
+		{&CppLastError, "parakeet_capi_last_error"},
+	}
+	for _, lf := range libFuncs {
+		purego.RegisterLibFunc(lf.FuncPtr, lib, lf.Name)
+	}
+
+	fmt.Fprintf(os.Stderr, "[parakeet-cpp] ABI=%d\n", CppAbiVersion())
+
+	flag.Parse()
+
+	if err := grpc.StartServer(*addr, &ParakeetCpp{}); err != nil {
+		panic(err)
+	}
+}

backend/go/parakeet-cpp/package.sh

@@ -0,0 +1,23 @@
+#!/bin/bash
+#
+# L0 packaging stub: copy the binary, run.sh and libparakeet.so* into
+# package/. The full ldd walk (libc, libstdc++, libgomp, GPU runtimes,
+# arch detection) lands in L3, mirroring backend/go/whisper/package.sh.
+
+set -e
+
+CURDIR=$(dirname "$(realpath "$0")")
+
+mkdir -p "$CURDIR/package/lib"
+
+cp -avf "$CURDIR/parakeet-cpp-grpc" "$CURDIR/package/"
+cp -avf "$CURDIR/run.sh" "$CURDIR/package/"
+
+# libparakeet.so + any soname symlinks (libparakeet.so.X, libparakeet.so.X.Y).
+cp -avf "$CURDIR"/libparakeet.so* "$CURDIR/package/lib/" 2>/dev/null || {
+	echo "ERROR: libparakeet.so not found in $CURDIR, run 'make' first" >&2
+	exit 1
+}
+
+echo "L0 package layout (full ldd walk lands in L3):"
+ls -liah "$CURDIR/package/" "$CURDIR/package/lib/"

backend/go/parakeet-cpp/run.sh

@@ -0,0 +1,16 @@
+#!/bin/bash
+set -e
+
+CURDIR=$(dirname "$(realpath "$0")")
+
+export LD_LIBRARY_PATH="$CURDIR/lib:$CURDIR:${LD_LIBRARY_PATH:-}"
+
+# If a self-contained ld.so was packaged, route through it so the
+# packaged libc / libstdc++ are used instead of the host's (matches the
+# whisper backend's runtime layout).
+if [ -f "$CURDIR/lib/ld.so" ]; then
+	echo "Using lib/ld.so"
+	exec "$CURDIR/lib/ld.so" "$CURDIR/parakeet-cpp-grpc" "$@"
+fi
+
+exec "$CURDIR/parakeet-cpp-grpc" "$@"

backend/go/rfdetr-cpp/.gitignore

@@ -0,0 +1,7 @@
+sources/
+build*/
+package/
+librfdetrcpp*.so
+rfdetr-cpp
+test-models/
+test-data/

backend/go/rfdetr-cpp/CMakeLists.txt

@@ -0,0 +1,79 @@
+cmake_minimum_required(VERSION 3.18)
+project(librfdetrcpp LANGUAGES C CXX)
+
+set(CMAKE_POSITION_INDEPENDENT_CODE ON)
+set(CMAKE_CXX_STANDARD 17)
+set(CMAKE_CXX_STANDARD_REQUIRED ON)
+
+# Static-link ggml + rfdetr so the resulting .so has no runtime dependency on
+# extra ggml/rfdetr shared libraries — only on libc/libstdc++/libgomp, which
+# the LocalAI package step bundles into the docker image.
+set(BUILD_SHARED_LIBS OFF CACHE BOOL "Build static libraries" FORCE)
+
+# rfdetr.cpp build switches: skip CLI/tests, keep static lib.
+set(RFDETR_BUILD_CLI OFF CACHE BOOL "Disable rfdetr CLI" FORCE)
+set(RFDETR_BUILD_TESTS OFF CACHE BOOL "Disable rfdetr tests" FORCE)
+set(RFDETR_SHARED OFF CACHE BOOL "Build rfdetr as static lib" FORCE)
+
+# rt-detr.cpp's top-level CMakeLists invokes
+# `bash ${CMAKE_SOURCE_DIR}/scripts/apply_ggml_patches.sh` to apply its
+# in-tree ggml patches before descending into the submodule. When we
+# `add_subdirectory` it from a parent project, `CMAKE_SOURCE_DIR` points
+# at *our* directory, not theirs, so the script path resolves wrong.
+#
+# Run the patches script ourselves up front (it's idempotent — re-running
+# is a no-op once patches are applied) so the rt-detr.cpp configure step
+# is essentially a no-op for the patch hook.
+set(RFDETR_CPP_SRC ${CMAKE_CURRENT_SOURCE_DIR}/sources/rt-detr.cpp)
+if(EXISTS ${RFDETR_CPP_SRC}/scripts/apply_ggml_patches.sh)
+    execute_process(
+        COMMAND bash ${RFDETR_CPP_SRC}/scripts/apply_ggml_patches.sh
+        RESULT_VARIABLE _rfdetr_patch_result
+        OUTPUT_VARIABLE _rfdetr_patch_output
+        ERROR_VARIABLE  _rfdetr_patch_error
+        OUTPUT_STRIP_TRAILING_WHITESPACE
+        ERROR_STRIP_TRAILING_WHITESPACE)
+    if(NOT _rfdetr_patch_result EQUAL 0)
+        message(FATAL_ERROR
+            "Failed to apply ggml patches (exit ${_rfdetr_patch_result}):\n"
+            "stdout:\n${_rfdetr_patch_output}\n"
+            "stderr:\n${_rfdetr_patch_error}")
+    endif()
+    message(STATUS "${_rfdetr_patch_output}")
+endif()
+
+# Stage a shim 'scripts/apply_ggml_patches.sh' under our source dir so that
+# rt-detr.cpp's CMakeLists — which calls
+#   bash ${CMAKE_SOURCE_DIR}/scripts/apply_ggml_patches.sh
+# — finds an idempotent no-op there. The real patches have already been
+# applied above; this just satisfies the path lookup.
+file(MAKE_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}/scripts)
+file(WRITE ${CMAKE_CURRENT_SOURCE_DIR}/scripts/apply_ggml_patches.sh
+"#!/usr/bin/env bash
+# Shim - patches were already applied by the parent CMakeLists.
+exit 0
+")
+execute_process(COMMAND chmod +x ${CMAKE_CURRENT_SOURCE_DIR}/scripts/apply_ggml_patches.sh)
+
+add_subdirectory(./sources/rt-detr.cpp)
+
+# rfdetr.cpp's C-API symbols already live inside librfdetr (src/rfdetr_capi.cpp
+# is compiled into the lib). We re-export them via a MODULE library that
+# whole-archive-links rfdetr so the symbols are visible at dlopen time.
+add_library(rfdetrcpp MODULE
+    sources/rt-detr.cpp/src/rfdetr_capi.cpp)
+
+target_include_directories(rfdetrcpp PRIVATE
+    sources/rt-detr.cpp/include
+    sources/rt-detr.cpp/src
+    sources/rt-detr.cpp/third_party/stb
+)
+
+target_link_libraries(rfdetrcpp PRIVATE rfdetr ggml)
+
+if(CMAKE_CXX_COMPILER_ID MATCHES "GNU" AND CMAKE_CXX_COMPILER_VERSION VERSION_LESS 9.0)
+    target_link_libraries(rfdetrcpp PRIVATE stdc++fs)
+endif()
+
+set_property(TARGET rfdetrcpp PROPERTY CXX_STANDARD 17)
+set_target_properties(rfdetrcpp PROPERTIES LIBRARY_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR})

backend/go/rfdetr-cpp/Makefile

@@ -0,0 +1,135 @@
+CMAKE_ARGS?=
+BUILD_TYPE?=
+NATIVE?=false
+
+GOCMD?=go
+GO_TAGS?=
+JOBS?=$(shell nproc --ignore=1)
+
+# rt-detr.cpp (GitHub redirects the historical mudler/rt-detr.cpp to the new
+# mudler/rf-detr.cpp slug). Pin to a specific commit if you need a stable
+# build; leaving this on `master` always picks up the latest C-API surface
+# (incl. the per-detection accessor functions used by gorfdetrcpp.go).
+RFDETR_REPO?=https://github.com/mudler/rf-detr.cpp.git
+RFDETR_VERSION?=65c0ffcc9a9bc9dae38252f63d0417c9845a6cf7
+
+ifeq ($(NATIVE),false)
+	CMAKE_ARGS+=-DGGML_NATIVE=OFF
+endif
+
+# Forward LocalAI's BUILD_TYPE to the matching ggml backend switch.
+ifeq ($(BUILD_TYPE),cublas)
+	CMAKE_ARGS+=-DGGML_CUDA=ON -DRFDETR_GGML_CUDA=ON
+else ifeq ($(BUILD_TYPE),openblas)
+	CMAKE_ARGS+=-DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS
+else ifeq ($(BUILD_TYPE),clblas)
+	CMAKE_ARGS+=-DGGML_CLBLAST=ON
+else ifeq ($(BUILD_TYPE),hipblas)
+	ROCM_HOME ?= /opt/rocm
+	ROCM_PATH ?= /opt/rocm
+	export CXX=$(ROCM_HOME)/llvm/bin/clang++
+	export CC=$(ROCM_HOME)/llvm/bin/clang
+	AMDGPU_TARGETS?=gfx908,gfx90a,gfx942,gfx950,gfx1030,gfx1100,gfx1101,gfx1102,gfx1200,gfx1201
+	CMAKE_ARGS+=-DGGML_HIPBLAS=ON -DRFDETR_GGML_HIPBLAS=ON -DAMDGPU_TARGETS=$(AMDGPU_TARGETS)
+else ifeq ($(BUILD_TYPE),vulkan)
+	CMAKE_ARGS+=-DGGML_VULKAN=ON -DRFDETR_GGML_VULKAN=ON
+else ifeq ($(OS),Darwin)
+	ifneq ($(BUILD_TYPE),metal)
+		CMAKE_ARGS+=-DGGML_METAL=OFF
+	else
+		CMAKE_ARGS+=-DGGML_METAL=ON
+		CMAKE_ARGS+=-DGGML_METAL_EMBED_LIBRARY=ON
+		CMAKE_ARGS+=-DRFDETR_GGML_METAL=ON
+	endif
+endif
+
+ifeq ($(BUILD_TYPE),sycl_f16)
+	CMAKE_ARGS+=-DGGML_SYCL=ON \
+		-DCMAKE_C_COMPILER=icx \
+		-DCMAKE_CXX_COMPILER=icpx \
+		-DGGML_SYCL_F16=ON
+endif
+
+ifeq ($(BUILD_TYPE),sycl_f32)
+	CMAKE_ARGS+=-DGGML_SYCL=ON \
+		-DCMAKE_C_COMPILER=icx \
+		-DCMAKE_CXX_COMPILER=icpx
+endif
+
+sources/rt-detr.cpp:
+	mkdir -p sources && \
+	git clone --recursive $(RFDETR_REPO) sources/rt-detr.cpp && \
+	cd sources/rt-detr.cpp && \
+	git checkout $(RFDETR_VERSION) && \
+	git submodule update --init --recursive --depth 1 --single-branch
+
+# Detect OS
+UNAME_S := $(shell uname -s)
+
+# Only build CPU variants on Linux
+ifeq ($(UNAME_S),Linux)
+	VARIANT_TARGETS = librfdetrcpp-avx.so librfdetrcpp-avx2.so librfdetrcpp-avx512.so librfdetrcpp-fallback.so
+else
+	# On non-Linux (e.g., Darwin), build only fallback variant
+	VARIANT_TARGETS = librfdetrcpp-fallback.so
+endif
+
+rfdetr-cpp: main.go gorfdetrcpp.go $(VARIANT_TARGETS)
+	CGO_ENABLED=0 $(GOCMD) build -tags "$(GO_TAGS)" -o rfdetr-cpp ./
+
+package: rfdetr-cpp
+	bash package.sh
+
+build: package
+
+clean: purge
+	rm -rf librfdetrcpp*.so rfdetr-cpp package sources
+
+purge:
+	rm -rf build*
+
+# Build all variants (Linux only)
+ifeq ($(UNAME_S),Linux)
+librfdetrcpp-avx.so: sources/rt-detr.cpp
+	rm -rfv build-$@
+	$(info ${GREEN}I rfdetr-cpp build info:avx${RESET})
+	SO_TARGET=$@ CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) librfdetrcpp-custom
+	rm -rfv build-$@
+
+librfdetrcpp-avx2.so: sources/rt-detr.cpp
+	rm -rfv build-$@
+	$(info ${GREEN}I rfdetr-cpp build info:avx2${RESET})
+	SO_TARGET=$@ CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=on -DGGML_AVX512=off -DGGML_FMA=on -DGGML_F16C=on -DGGML_BMI2=on" $(MAKE) librfdetrcpp-custom
+	rm -rfv build-$@
+
+librfdetrcpp-avx512.so: sources/rt-detr.cpp
+	rm -rfv build-$@
+	$(info ${GREEN}I rfdetr-cpp build info:avx512${RESET})
+	SO_TARGET=$@ CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=on -DGGML_AVX512=on -DGGML_FMA=on -DGGML_F16C=on -DGGML_BMI2=on" $(MAKE) librfdetrcpp-custom
+	rm -rfv build-$@
+endif
+
+# Build fallback variant (all platforms)
+librfdetrcpp-fallback.so: sources/rt-detr.cpp
+	rm -rfv build-$@
+	$(info ${GREEN}I rfdetr-cpp build info:fallback${RESET})
+	SO_TARGET=$@ CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) librfdetrcpp-custom
+	rm -rfv build-$@
+
+librfdetrcpp-custom: CMakeLists.txt
+	mkdir -p build-$(SO_TARGET) && \
+	cd build-$(SO_TARGET) && \
+	cmake .. $(CMAKE_ARGS) && \
+	cmake --build . --config Release -j$(JOBS) && \
+	cd .. && \
+	mv build-$(SO_TARGET)/librfdetrcpp.so ./$(SO_TARGET)
+
+all: rfdetr-cpp package
+
+# `test` is invoked by the top-level Makefile's `test-extra` target. It builds
+# the backend binary + the fallback shared library (needed for dlopen at
+# runtime), then runs test.sh which downloads the test models + COCO image
+# and exercises the gRPC Load/Detect wire path via the Go smoke test in
+# main_test.go for both the detection and segmentation models.
+test: rfdetr-cpp librfdetrcpp-fallback.so
+	bash test.sh

backend/go/rfdetr-cpp/gorfdetrcpp.go

@@ -0,0 +1,195 @@
+package main
+
+// gorfdetrcpp.go - gRPC handlers (Load, Detect) for the rfdetr-cpp backend.
+//
+// Embeds base.SingleThread to default unimplemented RPCs to "not supported"
+// while we only implement object detection.
+
+import (
+	"encoding/base64"
+	"fmt"
+	"os"
+	"path/filepath"
+	"strconv"
+	"unsafe"
+
+	"github.com/mudler/LocalAI/pkg/grpc/base"
+	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+)
+
+// Default upper bound on detections returned per image. RF-DETR's decoder
+// queries are limited to a few hundred; 300 is a safe ceiling.
+const defaultTopK = 300
+
+// rfdetr_handle_t is a uintptr-typed opaque handle (see include/rfdetr_capi.h).
+var (
+	// rfdetr_capi_load(const char* model_path, int n_threads, rfdetr_handle_t* out_handle) -> int
+	CapiLoad func(modelPath string, nThreads int32, outHandle *uintptr) int32
+	// rfdetr_capi_unload(rfdetr_handle_t handle) -> int
+	CapiUnload func(handle uintptr) int32
+	// rfdetr_capi_detect_path(handle, image_path, threshold, top_k, out_json) -> int
+	CapiDetectPath func(handle uintptr, imagePath string, threshold float32, topK uint32, outJSON *uintptr) int32
+	// rfdetr_capi_detect_buffer(handle, bytes, len, threshold, top_k, out_json) -> int
+	CapiDetectBuffer func(handle uintptr, bytes uintptr, length uintptr, threshold float32, topK uint32, outJSON *uintptr) int32
+	// rfdetr_capi_free_string(char* s)
+	CapiFreeString func(s uintptr)
+	// rfdetr_capi_get_n_detections(handle) -> int
+	CapiGetNDetections func(handle uintptr) int32
+	// rfdetr_capi_get_detection_class_id(handle, i) -> int
+	CapiGetDetectionClassID func(handle uintptr, i int32) int32
+	// rfdetr_capi_get_detection_box(handle, i, out_xyxy[4]) -> int (0 on success)
+	CapiGetDetectionBox func(handle uintptr, i int32, outXYXY uintptr) int32
+	// rfdetr_capi_get_detection_score(handle, i) -> float
+	CapiGetDetectionScore func(handle uintptr, i int32) float32
+	// rfdetr_capi_get_detection_class_name(handle, i, buf, buf_size) -> int (needed/written; two-call sizing)
+	CapiGetDetectionClassName func(handle uintptr, i int32, buf uintptr, bufSize int32) int32
+	// rfdetr_capi_get_detection_mask_png(handle, i, buf, buf_size) -> int (needed/written; 0 means no mask)
+	CapiGetDetectionMaskPNG func(handle uintptr, i int32, buf uintptr, bufSize int32) int32
+)
+
+type RFDetrCpp struct {
+	base.SingleThread
+	handle uintptr
+}
+
+// Load loads the GGUF model at opts.ModelFile (joined with opts.ModelPath if relative)
+// and stores the handle for later Detect calls.
+func (r *RFDetrCpp) Load(opts *pb.ModelOptions) error {
+	modelFile := opts.ModelFile
+	if modelFile == "" {
+		modelFile = opts.Model
+	}
+	if modelFile == "" {
+		return fmt.Errorf("rfdetr-cpp: ModelFile is empty")
+	}
+
+	var modelPath string
+	if filepath.IsAbs(modelFile) {
+		modelPath = modelFile
+	} else {
+		modelPath = filepath.Join(opts.ModelPath, modelFile)
+	}
+
+	if _, err := os.Stat(modelPath); err != nil {
+		return fmt.Errorf("rfdetr-cpp: model file not found: %s: %w", modelPath, err)
+	}
+
+	threads := opts.Threads
+	if threads <= 0 {
+		threads = 4
+	}
+
+	// Release previous model if any (re-Load).
+	if r.handle != 0 {
+		CapiUnload(r.handle)
+		r.handle = 0
+	}
+
+	var h uintptr
+	rc := CapiLoad(modelPath, threads, &h)
+	if rc != 0 || h == 0 {
+		return fmt.Errorf("rfdetr-cpp: rfdetr_capi_load failed with rc=%d for %s", rc, modelPath)
+	}
+	r.handle = h
+	return nil
+}
+
+// Detect runs object detection on the base64-encoded image in opts.Src at
+// opts.Threshold, returning one pb.Detection per result. Seg models also
+// populate Detection.Mask with PNG-encoded mask bytes.
+func (r *RFDetrCpp) Detect(opts *pb.DetectOptions) (pb.DetectResponse, error) {
+	if r.handle == 0 {
+		return pb.DetectResponse{}, fmt.Errorf("rfdetr-cpp: model not loaded")
+	}
+
+	// Decode base64 image and write to temp file.
+	imgData, err := base64.StdEncoding.DecodeString(opts.Src)
+	if err != nil {
+		return pb.DetectResponse{}, fmt.Errorf("rfdetr-cpp: failed to decode base64 image: %w", err)
+	}
+
+	tmpFile, err := os.CreateTemp("", "rfdetr-*.img")
+	if err != nil {
+		return pb.DetectResponse{}, fmt.Errorf("rfdetr-cpp: failed to create temp file: %w", err)
+	}
+	defer func() { _ = os.Remove(tmpFile.Name()) }()
+
+	if _, err := tmpFile.Write(imgData); err != nil {
+		_ = tmpFile.Close()
+		return pb.DetectResponse{}, fmt.Errorf("rfdetr-cpp: failed to write temp file: %w", err)
+	}
+	if err := tmpFile.Close(); err != nil {
+		return pb.DetectResponse{}, fmt.Errorf("rfdetr-cpp: failed to close temp file: %w", err)
+	}
+
+	threshold := opts.Threshold
+	if threshold <= 0 {
+		threshold = 0.5
+	}
+
+	// JSON output from detect_path is unused: we read structured detections via
+	// the accessor functions. Still must free the returned string.
+	var jsonPtr uintptr
+	rc := CapiDetectPath(r.handle, tmpFile.Name(), threshold, uint32(defaultTopK), &jsonPtr)
+	if jsonPtr != 0 {
+		CapiFreeString(jsonPtr)
+	}
+	if rc != 0 {
+		return pb.DetectResponse{}, fmt.Errorf("rfdetr-cpp: detect failed with rc=%d", rc)
+	}
+
+	n := CapiGetNDetections(r.handle)
+	if n < 0 {
+		return pb.DetectResponse{}, fmt.Errorf("rfdetr-cpp: invalid n_detections=%d", n)
+	}
+
+	detections := make([]*pb.Detection, 0, n)
+	for i := int32(0); i < n; i++ {
+		var bbox [4]float32 // x1, y1, x2, y2
+		if rc := CapiGetDetectionBox(r.handle, i, uintptr(unsafe.Pointer(&bbox[0]))); rc != 0 {
+			continue
+		}
+		cid := CapiGetDetectionClassID(r.handle, i)
+		score := CapiGetDetectionScore(r.handle, i)
+
+		// Two-call sizing for class_name.
+		var className string
+		nameSize := CapiGetDetectionClassName(r.handle, i, 0, 0)
+		if nameSize > 1 {
+			buf := make([]byte, nameSize)
+			written := CapiGetDetectionClassName(r.handle, i, uintptr(unsafe.Pointer(&buf[0])), nameSize)
+			// `written` is the same number (needed bytes including NUL); strip NUL.
+			if written > 0 && int(written) <= len(buf) {
+				className = string(buf[:written-1])
+			} else {
+				className = string(buf[:len(buf)-1])
+			}
+		}
+		if className == "" {
+			className = strconv.Itoa(int(cid))
+		}
+
+		// Two-call sizing for mask PNG (returns 0 when no mask).
+		var mask []byte
+		maskSize := CapiGetDetectionMaskPNG(r.handle, i, 0, 0)
+		if maskSize > 0 {
+			maskBuf := make([]byte, maskSize)
+			CapiGetDetectionMaskPNG(r.handle, i, uintptr(unsafe.Pointer(&maskBuf[0])), maskSize)
+			mask = maskBuf
+		}
+
+		detections = append(detections, &pb.Detection{
+			X:          bbox[0],
+			Y:          bbox[1],
+			Width:      bbox[2] - bbox[0],
+			Height:     bbox[3] - bbox[1],
+			Confidence: score,
+			ClassName:  className,
+			Mask:       mask,
+		})
+	}
+
+	return pb.DetectResponse{
+		Detections: detections,
+	}, nil
+}

backend/go/rfdetr-cpp/main.go

@@ -0,0 +1,61 @@
+package main
+
+// main.go - entry point for the rfdetr-cpp gRPC backend.
+//
+// Dlopens librfdetrcpp-<variant>.so via purego at the path in
+// RFDETR_LIBRARY (set by run.sh based on /proc/cpuinfo), registers the
+// rfdetr_capi_* C ABI symbols, then starts the gRPC server.
+
+import (
+	"flag"
+	"os"
+
+	"github.com/ebitengine/purego"
+	grpc "github.com/mudler/LocalAI/pkg/grpc"
+)
+
+var (
+	addr = flag.String("addr", "localhost:50051", "the address to connect to")
+)
+
+type LibFuncs struct {
+	FuncPtr any
+	Name    string
+}
+
+func main() {
+	// Get library name from environment variable, default to fallback
+	libName := os.Getenv("RFDETR_LIBRARY")
+	if libName == "" {
+		libName = "./librfdetrcpp-fallback.so"
+	}
+
+	rfdetrLib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)
+	if err != nil {
+		panic(err)
+	}
+
+	libFuncs := []LibFuncs{
+		{&CapiLoad, "rfdetr_capi_load"},
+		{&CapiUnload, "rfdetr_capi_unload"},
+		{&CapiDetectPath, "rfdetr_capi_detect_path"},
+		{&CapiDetectBuffer, "rfdetr_capi_detect_buffer"},
+		{&CapiFreeString, "rfdetr_capi_free_string"},
+		{&CapiGetNDetections, "rfdetr_capi_get_n_detections"},
+		{&CapiGetDetectionClassID, "rfdetr_capi_get_detection_class_id"},
+		{&CapiGetDetectionBox, "rfdetr_capi_get_detection_box"},
+		{&CapiGetDetectionScore, "rfdetr_capi_get_detection_score"},
+		{&CapiGetDetectionClassName, "rfdetr_capi_get_detection_class_name"},
+		{&CapiGetDetectionMaskPNG, "rfdetr_capi_get_detection_mask_png"},
+	}
+
+	for _, lf := range libFuncs {
+		purego.RegisterLibFunc(lf.FuncPtr, rfdetrLib, lf.Name)
+	}
+
+	flag.Parse()
+
+	if err := grpc.StartServer(*addr, &RFDetrCpp{}); err != nil {
+		panic(err)
+	}
+}

backend/go/rfdetr-cpp/main_test.go

@@ -0,0 +1,220 @@
+package main
+
+// main_test.go - end-to-end smoke test for the rfdetr-cpp gRPC backend.
+//
+// Spawns the compiled rfdetr-cpp binary on a free local port, dials it via
+// gRPC, and exercises LoadModel + Detect against the test fixtures
+// downloaded by test.sh. Two scenarios:
+//
+//   1. detection — loads rfdetr-nano-q8_0.gguf and asserts at least one
+//      detection comes back with a non-empty class name and a bounding box
+//      of non-zero size.
+//   2. segmentation — loads rfdetr-seg-nano-q8_0.gguf and additionally
+//      asserts that at least one detection carries a PNG-encoded mask blob
+//      (verified by PNG magic bytes).
+//
+// Both specs Skip cleanly if their fixtures are missing so the test target
+// stays usable on a fresh checkout where models haven't been downloaded.
+
+import (
+	"context"
+	"encoding/base64"
+	"fmt"
+	"net"
+	"os"
+	"os/exec"
+	"path/filepath"
+	"testing"
+	"time"
+
+	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+	"google.golang.org/grpc"
+	"google.golang.org/grpc/credentials/insecure"
+)
+
+func TestRFDetrCpp(t *testing.T) {
+	RegisterFailHandler(Fail)
+	RunSpecs(t, "rfdetr-cpp backend smoke suite")
+}
+
+// freePort grabs an ephemeral TCP port and immediately releases it so the
+// spawned backend can bind to it. There is a tiny TOCTOU window here but in
+// practice it's adequate for a smoke test on a quiet runner.
+func freePort() int {
+	l, err := net.Listen("tcp", "127.0.0.1:0")
+	Expect(err).ToNot(HaveOccurred(), "freePort listen")
+	port := l.Addr().(*net.TCPAddr).Port
+	Expect(l.Close()).To(Succeed())
+	return port
+}
+
+// startBackend spawns the rfdetr-cpp binary on the given port and waits
+// until it accepts TCP connections (up to 10s). The returned cleanup func
+// kills the process and reaps it.
+func startBackend(port int) func() {
+	binary, err := filepath.Abs("./rfdetr-cpp")
+	Expect(err).ToNot(HaveOccurred())
+	if _, err := os.Stat(binary); err != nil {
+		Skip(fmt.Sprintf("backend binary not built: %s (run `make rfdetr-cpp` first)", binary))
+	}
+
+	libPath, err := filepath.Abs("./librfdetrcpp-fallback.so")
+	Expect(err).ToNot(HaveOccurred())
+	if _, err := os.Stat(libPath); err != nil {
+		Skip(fmt.Sprintf("fallback library not built: %s (run `make librfdetrcpp-fallback.so` first)", libPath))
+	}
+
+	addr := fmt.Sprintf("127.0.0.1:%d", port)
+	cmd := exec.Command(binary, "--addr", addr)
+	cmd.Env = append(os.Environ(), "RFDETR_LIBRARY="+libPath)
+	cmd.Stdout = os.Stderr
+	cmd.Stderr = os.Stderr
+	Expect(cmd.Start()).To(Succeed())
+
+	cleanup := func() {
+		if cmd.Process != nil {
+			_ = cmd.Process.Kill()
+			_, _ = cmd.Process.Wait()
+		}
+	}
+
+	deadline := time.Now().Add(10 * time.Second)
+	for time.Now().Before(deadline) {
+		c, err := net.DialTimeout("tcp", addr, 200*time.Millisecond)
+		if err == nil {
+			_ = c.Close()
+			return cleanup
+		}
+		time.Sleep(200 * time.Millisecond)
+	}
+
+	cleanup()
+	Fail(fmt.Sprintf("backend did not become ready on %s within 10s", addr))
+	return func() {}
+}
+
+// loadTestImage reads the COCO test image downloaded by test.sh and returns
+// its base64-encoded content (the wire format accepted by the Detect RPC).
+func loadTestImage() string {
+	imgPath, err := filepath.Abs("test-data/test.jpg")
+	Expect(err).ToNot(HaveOccurred())
+	imgBytes, err := os.ReadFile(imgPath)
+	if err != nil {
+		Skip(fmt.Sprintf("test image not present: %s (run test.sh first)", imgPath))
+	}
+	return base64.StdEncoding.EncodeToString(imgBytes)
+}
+
+// dialBackend opens a gRPC client connection to the spawned backend.
+func dialBackend(port int) (pb.BackendClient, func()) {
+	addr := fmt.Sprintf("127.0.0.1:%d", port)
+	conn, err := grpc.NewClient(addr, grpc.WithTransportCredentials(insecure.NewCredentials()))
+	Expect(err).ToNot(HaveOccurred())
+	return pb.NewBackendClient(conn), func() { _ = conn.Close() }
+}
+
+// modelPathOrSkip resolves a model file under ./test-models/ and Skip()s
+// the current spec if it's missing.
+func modelPathOrSkip(name string) string {
+	modelDir, err := filepath.Abs("test-models")
+	Expect(err).ToNot(HaveOccurred())
+	modelPath := filepath.Join(modelDir, name)
+	if _, err := os.Stat(modelPath); err != nil {
+		Skip(fmt.Sprintf("model not present: %s (run test.sh first)", modelPath))
+	}
+	return modelPath
+}
+
+var _ = Describe("rfdetr-cpp backend", func() {
+	It("runs object detection against a known-good COCO image", func() {
+		modelPath := modelPathOrSkip("rfdetr-nano-q8_0.gguf")
+		imgB64 := loadTestImage()
+
+		port := freePort()
+		cleanup := startBackend(port)
+		defer cleanup()
+
+		client, closeConn := dialBackend(port)
+		defer closeConn()
+
+		ctx, cancel := context.WithTimeout(context.Background(), 60*time.Second)
+		defer cancel()
+
+		loadResp, err := client.LoadModel(ctx, &pb.ModelOptions{
+			Model:     "rfdetr-nano-q8_0.gguf",
+			ModelFile: modelPath,
+			Threads:   2,
+		})
+		Expect(err).ToNot(HaveOccurred(), "LoadModel")
+		Expect(loadResp.GetSuccess()).To(BeTrue(), "LoadModel reported failure: %s", loadResp.GetMessage())
+
+		detResp, err := client.Detect(ctx, &pb.DetectOptions{
+			Src:       imgB64,
+			Threshold: 0.5,
+		})
+		Expect(err).ToNot(HaveOccurred(), "Detect")
+		Expect(detResp.GetDetections()).ToNot(BeEmpty(), "no detections returned on a known-good COCO image")
+
+		_, _ = fmt.Fprintf(GinkgoWriter, "detection OK: %d detections\n", len(detResp.GetDetections()))
+		for i, d := range detResp.GetDetections() {
+			Expect(d.GetClassName()).ToNot(BeEmpty(), "detection %d has empty class_name", i)
+			Expect(d.GetConfidence()).To(BeNumerically(">=", float32(0.5)),
+				"detection %d below threshold", i)
+			Expect(d.GetWidth()).To(BeNumerically(">", float32(0)),
+				"detection %d has non-positive width", i)
+			Expect(d.GetHeight()).To(BeNumerically(">", float32(0)),
+				"detection %d has non-positive height", i)
+		}
+	})
+
+	It("runs segmentation and returns PNG-encoded masks", func() {
+		modelPath := modelPathOrSkip("rfdetr-seg-nano-q8_0.gguf")
+		imgB64 := loadTestImage()
+
+		port := freePort()
+		cleanup := startBackend(port)
+		defer cleanup()
+
+		client, closeConn := dialBackend(port)
+		defer closeConn()
+
+		ctx, cancel := context.WithTimeout(context.Background(), 60*time.Second)
+		defer cancel()
+
+		loadResp, err := client.LoadModel(ctx, &pb.ModelOptions{
+			Model:     "rfdetr-seg-nano-q8_0.gguf",
+			ModelFile: modelPath,
+			Threads:   2,
+		})
+		Expect(err).ToNot(HaveOccurred(), "LoadModel")
+		Expect(loadResp.GetSuccess()).To(BeTrue(), "LoadModel reported failure: %s", loadResp.GetMessage())
+
+		detResp, err := client.Detect(ctx, &pb.DetectOptions{
+			Src:       imgB64,
+			Threshold: 0.5,
+		})
+		Expect(err).ToNot(HaveOccurred(), "Detect")
+		Expect(detResp.GetDetections()).ToNot(BeEmpty(), "no detections returned from segmentation model")
+
+		haveMask := false
+		for i, d := range detResp.GetDetections() {
+			m := d.GetMask()
+			if len(m) == 0 {
+				continue
+			}
+			haveMask = true
+			// Verify PNG magic: 89 50 4E 47 ("\x89PNG").
+			Expect(len(m)).To(BeNumerically(">=", 4), "detection %d mask too short", i)
+			Expect([]byte{m[0], m[1], m[2], m[3]}).To(Equal([]byte{0x89, 'P', 'N', 'G'}),
+				"detection %d mask is not a PNG", i)
+		}
+		Expect(haveMask).To(BeTrue(),
+			"segmentation model returned %d detections but none carried a mask",
+			len(detResp.GetDetections()))
+
+		_, _ = fmt.Fprintf(GinkgoWriter, "segmentation OK: %d detections, at least one with PNG mask\n",
+			len(detResp.GetDetections()))
+	})
+})

backend/go/rfdetr-cpp/package.sh

@@ -0,0 +1,59 @@
+#!/bin/bash
+
+# Script to copy the appropriate libraries based on architecture
+
+set -e
+
+CURDIR=$(dirname "$(realpath $0)")
+REPO_ROOT="${CURDIR}/../../.."
+
+# Create lib directory
+mkdir -p $CURDIR/package/lib
+
+cp -avf $CURDIR/librfdetrcpp-*.so $CURDIR/package/
+cp -avf $CURDIR/rfdetr-cpp $CURDIR/package/
+cp -fv $CURDIR/run.sh $CURDIR/package/
+
+# Detect architecture and copy appropriate libraries
+if [ -f "/lib64/ld-linux-x86-64.so.2" ]; then
+    # x86_64 architecture
+    echo "Detected x86_64 architecture, copying x86_64 libraries..."
+    cp -arfLv /lib64/ld-linux-x86-64.so.2 $CURDIR/package/lib/ld.so
+    cp -arfLv /lib/x86_64-linux-gnu/libc.so.6 $CURDIR/package/lib/libc.so.6
+    cp -arfLv /lib/x86_64-linux-gnu/libgcc_s.so.1 $CURDIR/package/lib/libgcc_s.so.1
+    cp -arfLv /lib/x86_64-linux-gnu/libstdc++.so.6 $CURDIR/package/lib/libstdc++.so.6
+    cp -arfLv /lib/x86_64-linux-gnu/libm.so.6 $CURDIR/package/lib/libm.so.6
+    cp -arfLv /lib/x86_64-linux-gnu/libgomp.so.1 $CURDIR/package/lib/libgomp.so.1
+    cp -arfLv /lib/x86_64-linux-gnu/libdl.so.2 $CURDIR/package/lib/libdl.so.2
+    cp -arfLv /lib/x86_64-linux-gnu/librt.so.1 $CURDIR/package/lib/librt.so.1
+    cp -arfLv /lib/x86_64-linux-gnu/libpthread.so.0 $CURDIR/package/lib/libpthread.so.0
+elif [ -f "/lib/ld-linux-aarch64.so.1" ]; then
+    # ARM64 architecture
+    echo "Detected ARM64 architecture, copying ARM64 libraries..."
+    cp -arfLv /lib/ld-linux-aarch64.so.1 $CURDIR/package/lib/ld.so
+    cp -arfLv /lib/aarch64-linux-gnu/libc.so.6 $CURDIR/package/lib/libc.so.6
+    cp -arfLv /lib/aarch64-linux-gnu/libgcc_s.so.1 $CURDIR/package/lib/libgcc_s.so.1
+    cp -arfLv /lib/aarch64-linux-gnu/libstdc++.so.6 $CURDIR/package/lib/libstdc++.so.6
+    cp -arfLv /lib/aarch64-linux-gnu/libm.so.6 $CURDIR/package/lib/libm.so.6
+    cp -arfLv /lib/aarch64-linux-gnu/libgomp.so.1 $CURDIR/package/lib/libgomp.so.1
+    cp -arfLv /lib/aarch64-linux-gnu/libdl.so.2 $CURDIR/package/lib/libdl.so.2
+    cp -arfLv /lib/aarch64-linux-gnu/librt.so.1 $CURDIR/package/lib/librt.so.1
+    cp -arfLv /lib/aarch64-linux-gnu/libpthread.so.0 $CURDIR/package/lib/libpthread.so.0
+elif [ $(uname -s) = "Darwin" ]; then
+    echo "Detected Darwin"
+else
+    echo "Error: Could not detect architecture"
+    exit 1
+fi
+
+# Package GPU libraries based on BUILD_TYPE
+GPU_LIB_SCRIPT="${REPO_ROOT}/scripts/build/package-gpu-libs.sh"
+if [ -f "$GPU_LIB_SCRIPT" ]; then
+    echo "Packaging GPU libraries for BUILD_TYPE=${BUILD_TYPE:-cpu}..."
+    source "$GPU_LIB_SCRIPT" "$CURDIR/package/lib"
+    package_gpu_libs
+fi
+
+echo "Packaging completed successfully"
+ls -liah $CURDIR/package/
+ls -liah $CURDIR/package/lib/

backend/go/rfdetr-cpp/run.sh

@@ -0,0 +1,52 @@
+#!/bin/bash
+set -ex
+
+# Get the absolute current dir where the script is located
+CURDIR=$(dirname "$(realpath $0)")
+
+cd /
+
+echo "CPU info:"
+if [ "$(uname)" != "Darwin" ]; then
+	grep -e "model\sname" /proc/cpuinfo | head -1
+	grep -e "flags" /proc/cpuinfo | head -1
+fi
+
+LIBRARY="$CURDIR/librfdetrcpp-fallback.so"
+
+if [ "$(uname)" != "Darwin" ]; then
+	if grep -q -e "\savx\s" /proc/cpuinfo ; then
+		echo "CPU:    AVX    found OK"
+		if [ -e $CURDIR/librfdetrcpp-avx.so ]; then
+			LIBRARY="$CURDIR/librfdetrcpp-avx.so"
+		fi
+	fi
+
+	if grep -q -e "\savx2\s" /proc/cpuinfo ; then
+		echo "CPU:    AVX2   found OK"
+		if [ -e $CURDIR/librfdetrcpp-avx2.so ]; then
+			LIBRARY="$CURDIR/librfdetrcpp-avx2.so"
+		fi
+	fi
+
+	# Check avx 512
+	if grep -q -e "\savx512f\s" /proc/cpuinfo ; then
+		echo "CPU:    AVX512F found OK"
+		if [ -e $CURDIR/librfdetrcpp-avx512.so ]; then
+			LIBRARY="$CURDIR/librfdetrcpp-avx512.so"
+		fi
+	fi
+fi
+
+export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
+export RFDETR_LIBRARY=$LIBRARY
+
+# If there is a lib/ld.so, use it
+if [ -f $CURDIR/lib/ld.so ]; then
+	echo "Using lib/ld.so"
+	echo "Using library: $LIBRARY"
+	exec $CURDIR/lib/ld.so $CURDIR/rfdetr-cpp "$@"
+fi
+
+echo "Using library: $LIBRARY"
+exec $CURDIR/rfdetr-cpp "$@"

backend/go/rfdetr-cpp/test.sh

@@ -0,0 +1,55 @@
+#!/bin/bash
+set -e
+
+CURDIR=$(dirname "$(realpath $0)")
+
+echo "Running rfdetr-cpp backend tests..."
+
+# Test models from the mudler/rfdetr-cpp-* HuggingFace repos. Both the
+# detection (nano-q8_0, ~36 MB) and segmentation (seg-nano-q8_0, ~40 MB)
+# variants are downloaded so the Go smoke test exercises both code paths.
+RFDETR_MODEL_DIR="${RFDETR_MODEL_DIR:-$CURDIR/test-models}"
+
+RFDETR_DET_FILE="${RFDETR_DET_FILE:-rfdetr-nano-q8_0.gguf}"
+RFDETR_DET_URL="${RFDETR_DET_URL:-https://huggingface.co/mudler/rfdetr-cpp-nano/resolve/main/rfdetr-nano-q8_0.gguf}"
+
+RFDETR_SEG_FILE="${RFDETR_SEG_FILE:-rfdetr-seg-nano-q8_0.gguf}"
+RFDETR_SEG_URL="${RFDETR_SEG_URL:-https://huggingface.co/mudler/rfdetr-cpp-seg-nano/resolve/main/rfdetr-seg-nano-q8_0.gguf}"
+
+mkdir -p "$RFDETR_MODEL_DIR"
+
+if [ ! -f "$RFDETR_MODEL_DIR/$RFDETR_DET_FILE" ]; then
+    echo "Downloading rfdetr nano-q8_0 detection model..."
+    curl -L -o "$RFDETR_MODEL_DIR/$RFDETR_DET_FILE" "$RFDETR_DET_URL" --progress-bar
+fi
+
+if [ ! -f "$RFDETR_MODEL_DIR/$RFDETR_SEG_FILE" ]; then
+    echo "Downloading rfdetr seg-nano-q8_0 segmentation model..."
+    curl -L -o "$RFDETR_MODEL_DIR/$RFDETR_SEG_FILE" "$RFDETR_SEG_URL" --progress-bar
+fi
+
+# Use a real COCO test image from the upstream rf-detr.cpp repo (~46 KB).
+# A synthetic 64x64 red PNG was too synthetic to elicit detections from a
+# real model — the smoke test would always trivially pass with zero
+# detections.
+TEST_IMAGE_DIR="$CURDIR/test-data"
+TEST_IMAGE_FILE="$TEST_IMAGE_DIR/test.jpg"
+TEST_IMAGE_URL="${TEST_IMAGE_URL:-https://raw.githubusercontent.com/mudler/rf-detr.cpp/main/tests/fixtures/ci/test_image.jpg}"
+
+mkdir -p "$TEST_IMAGE_DIR"
+if [ ! -f "$TEST_IMAGE_FILE" ]; then
+    echo "Downloading COCO test image..."
+    curl -L -o "$TEST_IMAGE_FILE" "$TEST_IMAGE_URL" --progress-bar
+fi
+
+echo "rfdetr-cpp test setup complete."
+echo "  detection model:    $RFDETR_MODEL_DIR/$RFDETR_DET_FILE"
+echo "  segmentation model: $RFDETR_MODEL_DIR/$RFDETR_SEG_FILE"
+echo "  test image:         $TEST_IMAGE_FILE"
+
+# Run the Go smoke test: spawns the backend binary on a free port, calls
+# LoadModel + Detect via gRPC for both detection and segmentation models.
+echo ""
+echo "Running Go smoke test..."
+cd "$CURDIR"
+go test -v -timeout 5m ./...

backend/go/stablediffusion-ggml/Makefile

@@ -8,7 +8,7 @@ JOBS?=$(shell nproc --ignore=1)
 
 # stablediffusion.cpp (ggml)
 STABLEDIFFUSION_GGML_REPO?=https://github.com/leejet/stable-diffusion.cpp
-STABLEDIFFUSION_GGML_VERSION?=a397e03488cc27e1a42da646b82dfce9f50741c0
+STABLEDIFFUSION_GGML_VERSION?=0e4ee04488159b81d95a9ffcd983a077fd5dcb77
 
 CMAKE_ARGS+=-DGGML_MAX_NAME=128
 

backend/go/whisper/Makefile

@@ -8,7 +8,7 @@ JOBS?=$(shell nproc --ignore=1)
 
 # whisper.cpp version
 WHISPER_REPO?=https://github.com/ggml-org/whisper.cpp
-WHISPER_CPP_VERSION?=0ccd896f5b882628e1c077f9769735ef4ce52860
+WHISPER_CPP_VERSION?=f24588a272ae8e23280d9c220536437164e6ed28
 SO_TARGET?=libgowhisper.so
 
 CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF

backend/index.yaml

@@ -122,6 +122,35 @@
     nvidia-cuda-12: "cuda12-whisper"
     nvidia-l4t-cuda-12: "nvidia-l4t-arm64-whisper"
     nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-whisper"
+- &parakeetcpp
+  name: "parakeet-cpp"
+  alias: "parakeet-cpp"
+  license: mit
+  icon: https://avatars.githubusercontent.com/u/95302084
+  description: |
+    parakeet.cpp is a C++/ggml port of NVIDIA NeMo Parakeet automatic speech recognition (ASR) models.
+    It supports the tdt, ctc, rnnt and hybrid decoder families as well as cache-aware streaming transcription,
+    and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL and NVIDIA Jetson (L4T) targets.
+  urls:
+    - https://github.com/mudler/parakeet.cpp
+  tags:
+    - audio-transcription
+    - CPU
+    - GPU
+    - CUDA
+    - HIP
+  capabilities:
+    default: "cpu-parakeet-cpp"
+    nvidia: "cuda12-parakeet-cpp"
+    intel: "intel-sycl-f16-parakeet-cpp"
+    metal: "metal-parakeet-cpp"
+    amd: "rocm-parakeet-cpp"
+    vulkan: "vulkan-parakeet-cpp"
+    nvidia-l4t: "nvidia-l4t-arm64-parakeet-cpp"
+    nvidia-cuda-13: "cuda13-parakeet-cpp"
+    nvidia-cuda-12: "cuda12-parakeet-cpp"
+    nvidia-l4t-cuda-12: "nvidia-l4t-arm64-parakeet-cpp"
+    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-parakeet-cpp"
 - &voxtral
   name: "voxtral"
   alias: "voxtral"
@@ -253,6 +282,34 @@
     nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-sam3-cpp"
     intel: "intel-sycl-f32-sam3-cpp"
     vulkan: "vulkan-sam3-cpp"
+- &rfdetrcpp
+  name: "rfdetr-cpp"
+  alias: "rfdetr-cpp"
+  license: apache-2.0
+  description: |
+    Native RF-DETR object detection and instance segmentation in C/C++
+    using GGML. Loads pre-built GGUF weights from the mudler/rfdetr-cpp-*
+    family (Nano/Small/Base/Medium/Large + SegNano/SegSmall/SegMedium)
+    and returns bounding boxes, class labels, confidence scores, and
+    (for segmentation variants) PNG-encoded per-detection masks.
+  urls:
+    - https://github.com/mudler/rf-detr.cpp
+  tags:
+    - object-detection
+    - image-segmentation
+    - rfdetr
+    - gpu
+    - cpu
+  capabilities:
+    default: "cpu-rfdetr-cpp"
+    nvidia: "cuda12-rfdetr-cpp"
+    nvidia-cuda-12: "cuda12-rfdetr-cpp"
+    nvidia-cuda-13: "cuda13-rfdetr-cpp"
+    nvidia-l4t: "nvidia-l4t-arm64-rfdetr-cpp"
+    nvidia-l4t-cuda-12: "nvidia-l4t-arm64-rfdetr-cpp"
+    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-rfdetr-cpp"
+    intel: "intel-sycl-f32-rfdetr-cpp"
+    vulkan: "vulkan-rfdetr-cpp"
 - &vllm
   name: "vllm"
   license: apache-2.0
@@ -1900,6 +1957,121 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-whisper"
   mirrors:
     - localai/localai-backends:master-gpu-nvidia-cuda-13-whisper
+## parakeet-cpp
+- !!merge <<: *parakeetcpp
+  name: "parakeet-cpp-development"
+  capabilities:
+    default: "cpu-parakeet-cpp-development"
+    nvidia: "cuda12-parakeet-cpp-development"
+    intel: "intel-sycl-f16-parakeet-cpp-development"
+    metal: "metal-parakeet-cpp-development"
+    amd: "rocm-parakeet-cpp-development"
+    vulkan: "vulkan-parakeet-cpp-development"
+    nvidia-l4t: "nvidia-l4t-arm64-parakeet-cpp-development"
+    nvidia-cuda-13: "cuda13-parakeet-cpp-development"
+    nvidia-cuda-12: "cuda12-parakeet-cpp-development"
+    nvidia-l4t-cuda-12: "nvidia-l4t-arm64-parakeet-cpp-development"
+    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-parakeet-cpp-development"
+- !!merge <<: *parakeetcpp
+  name: "nvidia-l4t-arm64-parakeet-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-parakeet-cpp"
+  mirrors:
+    - localai/localai-backends:latest-nvidia-l4t-arm64-parakeet-cpp
+- !!merge <<: *parakeetcpp
+  name: "nvidia-l4t-arm64-parakeet-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-parakeet-cpp"
+  mirrors:
+    - localai/localai-backends:master-nvidia-l4t-arm64-parakeet-cpp
+- !!merge <<: *parakeetcpp
+  name: "cuda13-nvidia-l4t-arm64-parakeet-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-parakeet-cpp"
+  mirrors:
+    - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-parakeet-cpp
+- !!merge <<: *parakeetcpp
+  name: "cuda13-nvidia-l4t-arm64-parakeet-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-parakeet-cpp"
+  mirrors:
+    - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-parakeet-cpp
+- !!merge <<: *parakeetcpp
+  name: "cpu-parakeet-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-parakeet-cpp"
+  mirrors:
+    - localai/localai-backends:latest-cpu-parakeet-cpp
+- !!merge <<: *parakeetcpp
+  name: "cpu-parakeet-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-cpu-parakeet-cpp"
+  mirrors:
+    - localai/localai-backends:master-cpu-parakeet-cpp
+- !!merge <<: *parakeetcpp
+  name: "metal-parakeet-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-parakeet-cpp"
+  mirrors:
+    - localai/localai-backends:latest-metal-darwin-arm64-parakeet-cpp
+- !!merge <<: *parakeetcpp
+  name: "metal-parakeet-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-parakeet-cpp"
+  mirrors:
+    - localai/localai-backends:master-metal-darwin-arm64-parakeet-cpp
+- !!merge <<: *parakeetcpp
+  name: "cuda12-parakeet-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-parakeet-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-12-parakeet-cpp
+- !!merge <<: *parakeetcpp
+  name: "cuda12-parakeet-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-parakeet-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-12-parakeet-cpp
+- !!merge <<: *parakeetcpp
+  name: "rocm-parakeet-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-parakeet-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-rocm-hipblas-parakeet-cpp
+- !!merge <<: *parakeetcpp
+  name: "rocm-parakeet-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-parakeet-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-rocm-hipblas-parakeet-cpp
+- !!merge <<: *parakeetcpp
+  name: "intel-sycl-f32-parakeet-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-parakeet-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-intel-sycl-f32-parakeet-cpp
+- !!merge <<: *parakeetcpp
+  name: "intel-sycl-f32-parakeet-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-parakeet-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-intel-sycl-f32-parakeet-cpp
+- !!merge <<: *parakeetcpp
+  name: "intel-sycl-f16-parakeet-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-parakeet-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-intel-sycl-f16-parakeet-cpp
+- !!merge <<: *parakeetcpp
+  name: "intel-sycl-f16-parakeet-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-parakeet-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-intel-sycl-f16-parakeet-cpp
+- !!merge <<: *parakeetcpp
+  name: "vulkan-parakeet-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-parakeet-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-vulkan-parakeet-cpp
+- !!merge <<: *parakeetcpp
+  name: "vulkan-parakeet-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-parakeet-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-vulkan-parakeet-cpp
+- !!merge <<: *parakeetcpp
+  name: "cuda13-parakeet-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-parakeet-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-13-parakeet-cpp
+- !!merge <<: *parakeetcpp
+  name: "cuda13-parakeet-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-parakeet-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-13-parakeet-cpp
 ## stablediffusion-ggml
 - !!merge <<: *stablediffusionggml
   name: "cpu-stablediffusion-ggml"
@@ -2349,6 +2521,99 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-sam3-cpp"
   mirrors:
     - localai/localai-backends:master-gpu-vulkan-sam3-cpp
+## rfdetr-cpp
+- !!merge <<: *rfdetrcpp
+  name: "rfdetr-cpp-development"
+  capabilities:
+    default: "cpu-rfdetr-cpp-development"
+    nvidia: "cuda12-rfdetr-cpp-development"
+    nvidia-cuda-12: "cuda12-rfdetr-cpp-development"
+    nvidia-cuda-13: "cuda13-rfdetr-cpp-development"
+    nvidia-l4t: "nvidia-l4t-arm64-rfdetr-cpp-development"
+    nvidia-l4t-cuda-12: "nvidia-l4t-arm64-rfdetr-cpp-development"
+    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-rfdetr-cpp-development"
+    intel: "intel-sycl-f32-rfdetr-cpp-development"
+    vulkan: "vulkan-rfdetr-cpp-development"
+- !!merge <<: *rfdetrcpp
+  name: "cpu-rfdetr-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-rfdetr-cpp"
+  mirrors:
+    - localai/localai-backends:latest-cpu-rfdetr-cpp
+- !!merge <<: *rfdetrcpp
+  name: "cpu-rfdetr-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-cpu-rfdetr-cpp"
+  mirrors:
+    - localai/localai-backends:master-cpu-rfdetr-cpp
+- !!merge <<: *rfdetrcpp
+  name: "cuda12-rfdetr-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-rfdetr-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-12-rfdetr-cpp
+- !!merge <<: *rfdetrcpp
+  name: "cuda12-rfdetr-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-rfdetr-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-12-rfdetr-cpp
+- !!merge <<: *rfdetrcpp
+  name: "cuda13-rfdetr-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-rfdetr-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-13-rfdetr-cpp
+- !!merge <<: *rfdetrcpp
+  name: "cuda13-rfdetr-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-rfdetr-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-13-rfdetr-cpp
+- !!merge <<: *rfdetrcpp
+  name: "nvidia-l4t-arm64-rfdetr-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-rfdetr-cpp"
+  mirrors:
+    - localai/localai-backends:latest-nvidia-l4t-arm64-rfdetr-cpp
+- !!merge <<: *rfdetrcpp
+  name: "nvidia-l4t-arm64-rfdetr-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-rfdetr-cpp"
+  mirrors:
+    - localai/localai-backends:master-nvidia-l4t-arm64-rfdetr-cpp
+- !!merge <<: *rfdetrcpp
+  name: "cuda13-nvidia-l4t-arm64-rfdetr-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-rfdetr-cpp"
+  mirrors:
+    - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-rfdetr-cpp
+- !!merge <<: *rfdetrcpp
+  name: "cuda13-nvidia-l4t-arm64-rfdetr-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-rfdetr-cpp"
+  mirrors:
+    - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-rfdetr-cpp
+- !!merge <<: *rfdetrcpp
+  name: "intel-sycl-f32-rfdetr-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-rfdetr-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-intel-sycl-f32-rfdetr-cpp
+- !!merge <<: *rfdetrcpp
+  name: "intel-sycl-f32-rfdetr-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-rfdetr-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-intel-sycl-f32-rfdetr-cpp
+- !!merge <<: *rfdetrcpp
+  name: "intel-sycl-f16-rfdetr-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-rfdetr-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-intel-sycl-f16-rfdetr-cpp
+- !!merge <<: *rfdetrcpp
+  name: "intel-sycl-f16-rfdetr-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-rfdetr-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-intel-sycl-f16-rfdetr-cpp
+- !!merge <<: *rfdetrcpp
+  name: "vulkan-rfdetr-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-rfdetr-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-vulkan-rfdetr-cpp
+- !!merge <<: *rfdetrcpp
+  name: "vulkan-rfdetr-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-rfdetr-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-vulkan-rfdetr-cpp
 ## Rerankers
 - !!merge <<: *rerankers
   name: "rerankers-development"

backend/python/nemo/backend.py

@@ -99,8 +99,15 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
             if not results or len(results) == 0:
                 return backend_pb2.TranscriptResult(segments=[], text="")
 
-            # Get the transcript text from the first result
-            text = results[0]
+            # Get the transcript text from the first result.
+            # CTC models return List[str], TDT/RNNT models return List[Hypothesis]
+            # where the actual text lives in Hypothesis.text.
+            result = results[0]
+            if isinstance(result, str):
+                text = result
+            else:
+                text = getattr(result, 'text', None) or ""
+
             if text:
                 # Create a single segment with the full transcription
                 result_segments.append(backend_pb2.TranscriptSegment(

backend/python/qwen-asr/backend.py

@@ -134,6 +134,156 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
 
         return backend_pb2.Result(message="Model loaded successfully", success=True)
 
+    @staticmethod
+    def _is_cjk(ch):
+        """Check if a character is CJK (Chinese/Japanese/Korean)."""
+        cp = ord(ch)
+        return (
+            0x4E00 <= cp <= 0x9FFF      # CJK Unified Ideographs
+            or 0x3400 <= cp <= 0x4DBF   # Extension A
+            or 0x20000 <= cp <= 0x2A6DF # Extension B
+            or 0xF900 <= cp <= 0xFAFF   # Compatibility Ideographs
+            or 0x3040 <= cp <= 0x309F   # Hiragana
+            or 0x30A0 <= cp <= 0x30FF   # Katakana
+            or 0xAC00 <= cp <= 0xD7AF   # Hangul Syllables
+        )
+
+    @staticmethod
+    def _is_punct(ch):
+        """Check if a character is punctuation (no space before it)."""
+        import unicodedata
+        cat = unicodedata.category(ch)
+        return cat.startswith('P')
+
+    @staticmethod
+    def _smart_join(tokens):
+        """Join tokens with spaces for non-CJK text, without spaces for CJK.
+
+        Rules:
+          - Between two CJK chars: no space
+          - Between two non-CJK tokens: space
+          - Before punctuation: no space
+          - CJK adjacent to non-CJK: no space (smooth mixed-text transition)
+        """
+        if not tokens:
+            return ""
+        result = [tokens[0]]
+        for token in tokens[1:]:
+            if not token:
+                continue
+            prev_ch = result[-1][-1] if result[-1] else ''
+            curr_ch = token[0]
+            # Punctuation never gets a space before it
+            if BackendServicer._is_punct(curr_ch):
+                result.append(token)
+            # CJK to CJK: no space
+            elif prev_ch and BackendServicer._is_cjk(prev_ch) and BackendServicer._is_cjk(curr_ch):
+                result.append(token)
+            # CJK adjacent to non-CJK or vice versa: no space
+            elif prev_ch and (BackendServicer._is_cjk(prev_ch) or BackendServicer._is_cjk(curr_ch)):
+                result.append(token)
+            # Both non-CJK (Latin, Cyrillic, etc.): add space
+            else:
+                result.append(' ' + token)
+        return "".join(result)
+
+    @staticmethod
+    def _extract_word_info(ts):
+        """Return (start_sec, end_sec, text) from a ForcedAlignItem or tuple."""
+        if hasattr(ts, 'start_time') and hasattr(ts, 'end_time') and hasattr(ts, 'text'):
+            return (
+                float(ts.start_time) if ts.start_time is not None else 0.0,
+                float(ts.end_time) if ts.end_time is not None else 0.0,
+                str(ts.text) if ts.text else "",
+            )
+        elif isinstance(ts, (list, tuple)) and len(ts) >= 3:
+            return (
+                float(ts[0]) if ts[0] is not None else 0.0,
+                float(ts[1]) if ts[1] is not None else 0.0,
+                ts[2] if len(ts) > 2 and ts[2] is not None else "",
+            )
+        return (0.0, 0.0, "")
+
+    @staticmethod
+    def _compute_gap_threshold(time_stamps):
+        """Compute a gap threshold for sentence boundary detection.
+
+        Uses the median inter-item gap multiplied by a factor, with a
+        minimum floor of 0.3s.  Returns 0 if there are too few items.
+        """
+        if len(time_stamps) < 2:
+            return 0.0
+        gaps = []
+        for i in range(1, len(time_stamps)):
+            prev_s, prev_e, _ = BackendServicer._extract_word_info(time_stamps[i - 1])
+            curr_s, _, _ = BackendServicer._extract_word_info(time_stamps[i])
+            gaps.append(curr_s - prev_e)
+        if not gaps:
+            return 0.0
+        gaps.sort()
+        median = gaps[len(gaps) // 2]
+        # threshold = max(median * 4, 0.3s)
+        return max(median * 4, 0.3)
+
+    def _build_segments(self, time_stamps, granularity):
+        """Build TranscriptSegment list from forced-aligner output.
+
+        granularity:
+          - "word": one segment per aligned item (character / word)
+          - "segment" (default): merge consecutive items, splitting at
+            time gaps that exceed a dynamic threshold (sentence boundaries).
+        """
+        if granularity == "word":
+            result = []
+            for idx, ts in enumerate(time_stamps):
+                s, e, t = self._extract_word_info(ts)
+                result.append(backend_pb2.TranscriptSegment(
+                    id=idx,
+                    start=int(s * 1_000_000_000),
+                    end=int(e * 1_000_000_000),
+                    text=t,
+                ))
+            return result
+
+        # segment mode — merge at time-gap boundaries
+        threshold = self._compute_gap_threshold(time_stamps)
+        result = []
+        buf_text = []
+        buf_start = None
+        buf_end = 0.0
+        prev_end = None
+
+        for ts in time_stamps:
+            s, e, t = self._extract_word_info(ts)
+
+            # Detect sentence boundary via time gap
+            if prev_end is not None and (s - prev_end) >= threshold and buf_text:
+                result.append(backend_pb2.TranscriptSegment(
+                    id=len(result),
+                    start=int(buf_start * 1_000_000_000),
+                    end=int(buf_end * 1_000_000_000),
+                    text=self._smart_join(buf_text),
+                ))
+                buf_text = []
+                buf_start = None
+
+            if buf_start is None:
+                buf_start = s
+            buf_text.append(t)
+            buf_end = e
+            prev_end = e
+
+        # flush remaining
+        if buf_text and buf_start is not None:
+            result.append(backend_pb2.TranscriptSegment(
+                id=len(result),
+                start=int(buf_start * 1_000_000_000),
+                end=int(buf_end * 1_000_000_000),
+                text=self._smart_join(buf_text),
+            ))
+
+        return result
+
     def AudioTranscription(self, request, context):
         result_segments = []
         text = ""
@@ -147,11 +297,22 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
             if request.language and request.language.strip():
                 language = request.language.strip()
 
-            context = ""
+            ctx = ""
             if request.prompt and request.prompt.strip():
-                context = request.prompt.strip()
+                ctx = request.prompt.strip()
 
-            results = self.model.transcribe(audio=audio_path, language=language, context=context)
+            # Determine requested granularity (default: segment)
+            granularities = list(request.timestamp_granularities) if request.timestamp_granularities else []
+            granularity = "word" if "word" in granularities else "segment"
+
+            has_aligner = getattr(self.model, 'forced_aligner', None) is not None
+            try:
+                results = self.model.transcribe(
+                    audio=audio_path, language=language, context=ctx,
+                    return_time_stamps=has_aligner,
+                )
+            except TypeError:
+                results = self.model.transcribe(audio=audio_path, language=language, context=ctx)
 
             if not results:
                 return backend_pb2.TranscriptResult(segments=[], text="")
@@ -160,17 +321,7 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
             text = r.text or ""
 
             if getattr(r, 'time_stamps', None) and len(r.time_stamps) > 0:
-                for idx, ts in enumerate(r.time_stamps):
-                    start_ms = 0
-                    end_ms = 0
-                    seg_text = text
-                    if isinstance(ts, (list, tuple)) and len(ts) >= 3:
-                        start_ms = int(float(ts[0]) * 1000) if ts[0] is not None else 0
-                        end_ms = int(float(ts[1]) * 1000) if ts[1] is not None else 0
-                        seg_text = ts[2] if len(ts) > 2 and ts[2] is not None else ""
-                    result_segments.append(backend_pb2.TranscriptSegment(
-                        id=idx, start=start_ms, end=end_ms, text=seg_text
-                    ))
+                result_segments = self._build_segments(r.time_stamps, granularity)
             else:
                 if text:
                     result_segments.append(backend_pb2.TranscriptSegment(

backend/python/transformers/requirements-cpu.txt

@@ -2,9 +2,9 @@ torch==2.7.1
 llvmlite==0.43.0
 numba==0.60.0
 accelerate
-transformers>=5.8.1
+transformers>=5.9.0
 bitsandbytes
-sentence-transformers==5.5.0
+sentence-transformers==5.5.1
 diffusers
 soundfile
-protobuf==6.33.5
+protobuf==7.35.0

backend/python/transformers/requirements-cublas12.txt

@@ -2,9 +2,9 @@ torch==2.7.1
 accelerate
 llvmlite==0.43.0
 numba==0.60.0
-transformers>=5.8.1
+transformers>=5.9.0
 bitsandbytes
-sentence-transformers==5.5.0
+sentence-transformers==5.5.1
 diffusers
 soundfile
-protobuf==6.33.5
+protobuf==7.35.0

backend/python/transformers/requirements-cublas13.txt

@@ -2,9 +2,9 @@
 torch==2.9.0
 llvmlite==0.43.0
 numba==0.60.0
-transformers>=5.8.1
+transformers>=5.9.0
 bitsandbytes
-sentence-transformers==5.5.0
+sentence-transformers==5.5.1
 diffusers
 soundfile
-protobuf==6.33.5
+protobuf==7.35.0

backend/python/transformers/requirements-hipblas.txt

@@ -1,11 +1,11 @@
 --extra-index-url https://download.pytorch.org/whl/rocm7.0
 torch==2.10.0+rocm7.0
 accelerate
-transformers>=5.8.1
+transformers>=5.9.0
 llvmlite==0.43.0
 numba==0.60.0
 bitsandbytes
-sentence-transformers==5.5.0
+sentence-transformers==5.5.1
 diffusers
 soundfile
-protobuf==6.33.5
+protobuf==7.35.0

backend/python/transformers/requirements-intel.txt

@@ -3,9 +3,9 @@ torch
 optimum[openvino]
 llvmlite==0.43.0
 numba==0.60.0
-transformers>=5.8.1
+transformers>=5.9.0
 bitsandbytes
-sentence-transformers==5.5.0
+sentence-transformers==5.5.1
 diffusers
 soundfile
-protobuf==6.33.5
+protobuf==7.35.0

backend/python/transformers/requirements-mps.txt

@@ -2,9 +2,9 @@ torch==2.7.1
 llvmlite==0.43.0
 numba==0.60.0
 accelerate
-transformers>=5.8.1
+transformers>=5.9.0
 bitsandbytes
-sentence-transformers==5.5.0
+sentence-transformers==5.5.1
 diffusers
 soundfile
-protobuf==6.33.5
+protobuf==7.35.0

backend/python/transformers/requirements.txt

@@ -1,5 +1,5 @@
 grpcio==1.80.0
-protobuf==6.33.5
+protobuf==7.35.0
 certifi
 setuptools
 scipy==1.15.1

backend/python/vllm/requirements-cublas13-after.txt

@@ -3,5 +3,5 @@
 # on a cu130 host. Pull the cu130-flavoured wheel from vLLM's per-tag index
 # instead — the cublas13 case in install.sh adds --index-strategy=unsafe-best-match
 # so uv consults this index alongside PyPI.
---extra-index-url https://wheels.vllm.ai/0.21.0/cu130
-vllm==0.21.0
+--extra-index-url https://wheels.vllm.ai/0.22.0/cu130
+vllm==0.22.0

cmd/launcher/internal/release_manager.go

@@ -17,6 +17,7 @@ import (
 	"time"
 
 	"github.com/mudler/LocalAI/internal"
+	"github.com/mudler/LocalAI/pkg/httpclient"
 )
 
 // Release represents a LocalAI release
@@ -67,9 +68,7 @@ func NewReleaseManager() *ReleaseManager {
 		CurrentVersion: internal.PrintableVersion(),
 		ChecksumsPath:  checksumsPath,
 		MetadataPath:   metadataPath,
-		HTTPClient: &http.Client{
-			Timeout: 30 * time.Second,
-		},
+		HTTPClient:     httpclient.NewWithTimeout(30*time.Second, httpclient.WithFollowRedirects()),
 	}
 }
 

core/application/application.go

@@ -90,6 +90,8 @@ type Application struct {
 	// LocalAI Assistant in-process MCP server. nil when DisableLocalAIAssistant
 	// is set; otherwise initialised in start() after galleryService.
 	localAIAssistant *mcpTools.LocalAIAssistantHolder
+
+	shutdownOnce sync.Once
 }
 
 func newApplication(appConfig *config.ApplicationConfig) *Application {
@@ -320,6 +322,24 @@ func (a *Application) IsDistributed() bool {
 	return a.distributed != nil
 }
 
+// Shutdown stops backend gRPC processes and distributed services
+// synchronously on the caller's stack. The context-cancel goroutine wired
+// in New does the same work asynchronously, which races test-binary exit
+// and CLI shutdown — orphaning spawned mock-backend / llama.cpp / etc.
+// children to init. Callers that need a guarantee that cleanup has
+// finished before they proceed (AfterSuite/AfterEach, signal handlers)
+// must call this. Safe to call multiple times.
+func (a *Application) Shutdown() error {
+	var err error
+	a.shutdownOnce.Do(func() {
+		a.distributed.Shutdown()
+		if a.modelLoader != nil {
+			err = a.modelLoader.StopAllGRPC()
+		}
+	})
+	return err
+}
+
 // waitForHealthyWorker blocks until at least one healthy backend worker is registered.
 // This prevents the agent pool from failing during startup when workers haven't connected yet.
 func (a *Application) waitForHealthyWorker() {

core/application/startup.go

@@ -449,13 +449,15 @@ func New(opts ...config.AppOption) (*Application, error) {
 
 	application.ModelLoader().SetBackendLoggingEnabled(options.EnableBackendLogging)
 
-	// turn off any process that was started by GRPC if the context is canceled
+	// Safety-net cleanup if the application context is cancelled without
+	// the caller invoking Shutdown directly. This is fire-and-forget — it
+	// races binary exit and is unreliable in tests; the deterministic path
+	// is application.Shutdown(), which Shutdown's sync.Once dedupes with
+	// this goroutine.
 	go func() {
 		<-options.Context.Done()
 		xlog.Debug("Context canceled, shutting down")
-		application.distributed.Shutdown()
-		err := application.ModelLoader().StopAllGRPC()
-		if err != nil {
+		if err := application.Shutdown(); err != nil {
 			xlog.Error("error while stopping all grpc backends", "error", err)
 		}
 	}()

core/backend/options_internal_test.go

@@ -4,6 +4,7 @@ import (
 	"encoding/json"
 
 	"github.com/mudler/LocalAI/core/config"
+	"github.com/mudler/LocalAI/pkg/reasoning"
 
 	. "github.com/onsi/ginkgo/v2"
 	. "github.com/onsi/gomega"
@@ -42,3 +43,35 @@ var _ = Describe("grpcModelOpts EngineArgs", func() {
 		Expect(opts.EngineArgs).To(BeEmpty())
 	})
 })
+
+// Guards the DisableReasoning -> enable_thinking metadata conversion that the
+// per-request reasoning_effort feature (issue #10072) relies on: the request
+// merge sets ReasoningConfig.DisableReasoning, and gRPCPredictOpts is where it
+// becomes the gRPC PredictOptions.Metadata the backend reads.
+var _ = Describe("gRPCPredictOpts enable_thinking metadata", func() {
+	// withReasoning builds a fully-defaulted config (gRPCPredictOpts dereferences
+	// many pointer fields) and overrides only the reasoning toggle.
+	withReasoning := func(disable *bool) config.ModelConfig {
+		cfg := config.ModelConfig{}
+		cfg.SetDefaults()
+		cfg.ReasoningConfig = reasoning.Config{DisableReasoning: disable}
+		return cfg
+	}
+	disabled := true
+	enabled := false
+
+	It("emits enable_thinking=false when reasoning is disabled", func() {
+		opts := gRPCPredictOpts(withReasoning(&disabled), "/tmp/models")
+		Expect(opts.Metadata).To(HaveKeyWithValue("enable_thinking", "false"))
+	})
+
+	It("emits enable_thinking=true when reasoning is enabled", func() {
+		opts := gRPCPredictOpts(withReasoning(&enabled), "/tmp/models")
+		Expect(opts.Metadata).To(HaveKeyWithValue("enable_thinking", "true"))
+	})
+
+	It("omits enable_thinking when reasoning is unset", func() {
+		opts := gRPCPredictOpts(withReasoning(nil), "/tmp/models")
+		Expect(opts.Metadata).ToNot(HaveKey("enable_thinking"))
+	})
+})

core/cli/run.go

@@ -577,12 +577,8 @@ func (r *RunCMD) Run(ctx *cliContext.Context) error {
 	}
 
 	signals.RegisterGracefulTerminationHandler(func() {
-		if err := app.ModelLoader().StopAllGRPC(); err != nil {
-			xlog.Error("error while stopping all grpc backends", "error", err)
-		}
-		// Clean up distributed services (idempotent — safe if already called)
-		if d := app.Distributed(); d != nil {
-			d.Shutdown()
+		if err := app.Shutdown(); err != nil {
+			xlog.Error("error while shutting down application", "error", err)
 		}
 	})
 

core/cli/workerregistry/client.go

@@ -15,6 +15,8 @@ import (
 	"time"
 
 	"github.com/mudler/xlog"
+
+	"github.com/mudler/LocalAI/pkg/httpclient"
 )
 
 // RegistrationClient talks to the frontend's /api/node/* endpoints.
@@ -37,7 +39,7 @@ func (c *RegistrationClient) httpTimeout() time.Duration {
 // httpClient returns the shared HTTP client, initializing it on first use.
 func (c *RegistrationClient) httpClient() *http.Client {
 	c.clientOnce.Do(func() {
-		c.client = &http.Client{Timeout: c.httpTimeout()}
+		c.client = httpclient.NewWithTimeout(c.httpTimeout())
 	})
 	return c.client
 }

core/clients/store.go

@@ -6,6 +6,8 @@ import (
 	"fmt"
 	"io"
 	"net/http"
+
+	"github.com/mudler/LocalAI/pkg/httpclient"
 )
 
 // Define a struct to hold the store API client
@@ -47,7 +49,7 @@ type FindResponse struct {
 func NewStoreClient(baseUrl string) *StoreClient {
 	return &StoreClient{
 		BaseURL: baseUrl,
-		Client:  &http.Client{},
+		Client:  httpclient.New(),
 	}
 }
 

core/config/gen_inference_defaults/main.go

@@ -9,10 +9,11 @@ import (
 	"encoding/json"
 	"fmt"
 	"io"
-	"net/http"
 	"os"
 	"sort"
 	"strings"
+
+	"github.com/mudler/LocalAI/pkg/httpclient"
 )
 
 const (
@@ -55,7 +56,7 @@ var allowedFields = map[string]bool{
 func main() {
 	fmt.Fprintf(os.Stderr, "Fetching %s ...\n", unslothURL)
 
-	resp, err := http.Get(unslothURL)
+	resp, err := httpclient.New(httpclient.WithFollowRedirects()).Get(unslothURL)
 	if err != nil {
 		fatal("fetch failed: %v", err)
 	}

core/config/model_config.go

@@ -732,6 +732,17 @@ func (cfg *ModelConfig) SetDefaults(opts ...ConfigLoaderOption) {
 		cfg.Proxy.Mode = ProxyModePassthrough
 	}
 
+	// When templating is delegated to the backend (use_tokenizer_template),
+	// the backend also owns tool-call grammar generation and parsing. Sending
+	// a LocalAI-generated grammar alongside overrides the backend's native
+	// (name-first) tool pipeline and makes it stream the tool-call JSON back as
+	// plain content (issue #10052). The GGUF auto-import path already couples
+	// these two flags; enforce it here so gallery and hand-written configs that
+	// set use_tokenizer_template directly stay consistent.
+	if cfg.TemplateConfig.UseTokenizerTemplate {
+		cfg.FunctionsConfig.GrammarConfig.NoGrammar = true
+	}
+
 	// Apply model-family-specific inference defaults before generic fallbacks.
 	// This ensures gallery-installed and runtime-loaded models get optimal parameters.
 	ApplyInferenceDefaults(cfg, cfg.Name, cfg.Model)

core/config/model_config_test.go

@@ -471,4 +471,33 @@ concurrency_groups:
 			Expect(configs[0].GetConcurrencyGroups()).To(Equal([]string{"vram-heavy", "120b"}))
 		})
 	})
+
+	// When templating is delegated to the backend (use_tokenizer_template),
+	// the backend also owns tool-call grammar generation and parsing. A
+	// LocalAI-generated grammar sent alongside would override the backend's
+	// native (name-first) tool pipeline and make it stream the tool-call JSON
+	// back as plain content (issue #10052). SetDefaults must therefore couple
+	// the two: tokenizer template implies grammar generation is disabled.
+	Context("use_tokenizer_template couples with grammar disable (issue #10052)", func() {
+		It("disables Go grammar generation when the tokenizer template is used", func() {
+			cfg := &ModelConfig{
+				TemplateConfig: TemplateConfig{UseTokenizerTemplate: true},
+			}
+			Expect(cfg.FunctionsConfig.GrammarConfig.NoGrammar).To(BeFalse())
+
+			cfg.SetDefaults()
+
+			Expect(cfg.FunctionsConfig.GrammarConfig.NoGrammar).To(BeTrue(),
+				"use_tokenizer_template must imply grammar.disable so tools go to the backend's native pipeline")
+		})
+
+		It("leaves grammar generation enabled when the tokenizer template is not used", func() {
+			cfg := &ModelConfig{}
+
+			cfg.SetDefaults()
+
+			Expect(cfg.FunctionsConfig.GrammarConfig.NoGrammar).To(BeFalse(),
+				"models that template in Go still rely on the Go-generated grammar")
+		})
+	})
 })

core/gallery/importers/importers.go

@@ -115,6 +115,10 @@ var defaultImporters = []Importer{
 	&NemoImporter{},
 	&FasterWhisperImporter{},
 	&QwenASRImporter{},
+	// ParakeetCppImporter matches only parakeet GGUFs (<arch>-<size>-<quant>.gguf);
+	// kept ahead of LlamaCPPImporter so its .gguf bundles aren't claimed by the
+	// generic GGUF importer.
+	&ParakeetCppImporter{},
 	// TTS (Batch 2)
 	&PiperImporter{},
 	&BarkImporter{},

core/gallery/importers/parakeet-cpp.go

@@ -0,0 +1,180 @@
+package importers
+
+import (
+	"encoding/json"
+	"path/filepath"
+	"strings"
+
+	"github.com/mudler/LocalAI/core/config"
+	"github.com/mudler/LocalAI/core/gallery"
+	"github.com/mudler/LocalAI/core/schema"
+	"github.com/mudler/LocalAI/pkg/downloader"
+	hfapi "github.com/mudler/LocalAI/pkg/huggingface-api"
+	"go.yaml.in/yaml/v2"
+)
+
+var _ Importer = &ParakeetCppImporter{}
+
+// ParakeetCppImporter recognises parakeet.cpp GGUF weights, the C++/ggml port
+// of NVIDIA NeMo Parakeet. The signal is narrow on purpose: parakeet.cpp names
+// its weights "<arch>-<size>-<quant>.gguf" (e.g. tdt_ctc-110m-f16.gguf,
+// rnnt-0.6b-q4_k.gguf, realtime_eou_120m-v1-q8_0.gguf), so we only match a
+// .gguf whose name carries a parakeet architecture token. That keeps us from
+// claiming arbitrary llama-style GGUFs (the importer is registered before
+// llama-cpp), and it deliberately does NOT match the upstream nvidia/parakeet-*
+// NeMo repos (which ship .nemo checkpoints, not runnable GGUFs).
+// preferences.backend="parakeet-cpp" forces the importer regardless.
+type ParakeetCppImporter struct{}
+
+func (i *ParakeetCppImporter) Name() string      { return "parakeet-cpp" }
+func (i *ParakeetCppImporter) Modality() string  { return "asr" }
+func (i *ParakeetCppImporter) AutoDetects() bool { return true }
+
+func (i *ParakeetCppImporter) Match(details Details) bool {
+	preferences, err := details.Preferences.MarshalJSON()
+	if err != nil {
+		return false
+	}
+	preferencesMap := make(map[string]any)
+	if len(preferences) > 0 {
+		if err := json.Unmarshal(preferences, &preferencesMap); err != nil {
+			return false
+		}
+	}
+
+	if b, ok := preferencesMap["backend"].(string); ok && b == "parakeet-cpp" {
+		return true
+	}
+
+	// Direct URL or path to a parakeet GGUF.
+	if isParakeetGGUF(filepath.Base(details.URI)) {
+		return true
+	}
+
+	// HF repo shipping at least one parakeet GGUF.
+	if details.HuggingFace != nil {
+		for _, f := range details.HuggingFace.Files {
+			if isParakeetGGUF(filepath.Base(f.Path)) {
+				return true
+			}
+		}
+	}
+
+	return false
+}
+
+func (i *ParakeetCppImporter) Import(details Details) (gallery.ModelConfig, error) {
+	preferences, err := details.Preferences.MarshalJSON()
+	if err != nil {
+		return gallery.ModelConfig{}, err
+	}
+	preferencesMap := make(map[string]any)
+	if len(preferences) > 0 {
+		if err := json.Unmarshal(preferences, &preferencesMap); err != nil {
+			return gallery.ModelConfig{}, err
+		}
+	}
+
+	name, ok := preferencesMap["name"].(string)
+	if !ok {
+		name = filepath.Base(details.URI)
+	}
+
+	description, ok := preferencesMap["description"].(string)
+	if !ok {
+		description = "Imported from " + details.URI
+	}
+
+	// parakeet quants are near-lossless even at Q4_K (WER 0.0 vs NeMo on 110m),
+	// so default to the smallest, then fall back up the size ladder; the last
+	// file wins if none match (mirrors whisper / llama-cpp).
+	preferredQuants, _ := preferencesMap["quantizations"].(string)
+	quants := []string{"q4_k", "q5_k", "q6_k", "q8_0", "f16"}
+	if preferredQuants != "" {
+		quants = strings.Split(preferredQuants, ",")
+	}
+
+	cfg := gallery.ModelConfig{
+		Name:        name,
+		Description: description,
+	}
+
+	modelConfig := config.ModelConfig{
+		Name:                name,
+		Description:         description,
+		Backend:             "parakeet-cpp",
+		KnownUsecaseStrings: []string{"transcript"},
+	}
+
+	uri := downloader.URI(details.URI)
+	directGGUF := isParakeetGGUF(filepath.Base(details.URI))
+	switch {
+	case uri.LooksLikeURL() && directGGUF:
+		// Direct file URL (e.g. .../resolve/main/tdt_ctc-110m-f16.gguf). The
+		// exact file is known, no quant pick.
+		fileName, err := uri.FilenameFromUrl()
+		if err != nil {
+			return gallery.ModelConfig{}, err
+		}
+		target := filepath.Join("parakeet-cpp", "models", name, fileName)
+		cfg.Files = append(cfg.Files, gallery.File{
+			URI:      details.URI,
+			Filename: target,
+		})
+		modelConfig.PredictionOptions = schema.PredictionOptions{
+			BasicModelRequest: schema.BasicModelRequest{Model: target},
+		}
+	case details.HuggingFace != nil:
+		// HF repo: collect every parakeet GGUF, pick the preferred quant, and
+		// nest under parakeet-cpp/models/<name>/ so a multi-quant repo doesn't
+		// collide on disk.
+		var ggufFiles []hfapi.ModelFile
+		for _, f := range details.HuggingFace.Files {
+			if isParakeetGGUF(filepath.Base(f.Path)) {
+				ggufFiles = append(ggufFiles, f)
+			}
+		}
+		if chosen, ok := pickPreferredGGMLFile(ggufFiles, quants); ok {
+			target := filepath.Join("parakeet-cpp", "models", name, filepath.Base(chosen.Path))
+			cfg.Files = append(cfg.Files, gallery.File{
+				URI:      chosen.URL,
+				Filename: target,
+				SHA256:   chosen.SHA256,
+			})
+			modelConfig.PredictionOptions = schema.PredictionOptions{
+				BasicModelRequest: schema.BasicModelRequest{Model: target},
+			}
+		}
+	default:
+		// Bare URI with no HF metadata (pref-only path): point at the basename
+		// so users can tweak the YAML after import.
+		modelConfig.PredictionOptions = schema.PredictionOptions{
+			BasicModelRequest: schema.BasicModelRequest{Model: filepath.Base(details.URI)},
+		}
+	}
+
+	data, err := yaml.Marshal(modelConfig)
+	if err != nil {
+		return gallery.ModelConfig{}, err
+	}
+	cfg.ConfigFile = string(data)
+
+	return cfg, nil
+}
+
+// isParakeetGGUF reports whether name is a parakeet.cpp GGUF: a .gguf file
+// whose name carries a parakeet architecture token. The .gguf check is
+// case-insensitive; the tokens cover the published naming
+// (<arch>-<size>-<quant>.gguf) plus a generic "parakeet" fallback.
+func isParakeetGGUF(name string) bool {
+	lower := strings.ToLower(name)
+	if !strings.HasSuffix(lower, ".gguf") {
+		return false
+	}
+	for _, tok := range []string{"tdt_ctc", "tdt-", "tdt_", "rnnt", "ctc-", "ctc_", "realtime_eou", "parakeet"} {
+		if strings.Contains(lower, tok) {
+			return true
+		}
+	}
+	return false
+}

core/gallery/importers/parakeet-cpp_test.go

@@ -0,0 +1,103 @@
+package importers_test
+
+import (
+	"encoding/json"
+	"fmt"
+
+	"github.com/mudler/LocalAI/core/gallery/importers"
+	hfapi "github.com/mudler/LocalAI/pkg/huggingface-api"
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+)
+
+// hfWith builds Details carrying a synthetic HF file list so detection can be
+// exercised without hitting the network.
+func parakeetDetails(uri string, prefs string, files ...hfapi.ModelFile) importers.Details {
+	return importers.Details{
+		URI:         uri,
+		Preferences: json.RawMessage(prefs),
+		HuggingFace: &hfapi.ModelDetails{Files: files},
+	}
+}
+
+var _ = Describe("ParakeetCppImporter", func() {
+	imp := &importers.ParakeetCppImporter{}
+
+	Context("Importer interface metadata", func() {
+		It("exposes name/modality/autodetect", func() {
+			Expect(imp.Name()).To(Equal("parakeet-cpp"))
+			Expect(imp.Modality()).To(Equal("asr"))
+			Expect(imp.AutoDetects()).To(BeTrue())
+		})
+	})
+
+	Context("detection (Match)", func() {
+		It("matches an HF repo shipping a parakeet GGUF", func() {
+			d := parakeetDetails("huggingface://mudler/parakeet-cpp-gguf", `{}`,
+				hfapi.ModelFile{Path: "tdt_ctc-110m-f16.gguf"},
+				hfapi.ModelFile{Path: "README.md"},
+			)
+			Expect(imp.Match(d)).To(BeTrue())
+		})
+
+		It("matches a direct URL to a parakeet GGUF", func() {
+			d := parakeetDetails("https://huggingface.co/mudler/parakeet-cpp-gguf/resolve/main/rnnt-0.6b-q4_k.gguf", `{}`)
+			Expect(imp.Match(d)).To(BeTrue())
+		})
+
+		It("honours preferences.backend=parakeet-cpp for arbitrary URIs", func() {
+			d := parakeetDetails("https://example.com/whatever", `{"backend": "parakeet-cpp"}`)
+			Expect(imp.Match(d)).To(BeTrue())
+		})
+
+		It("does NOT claim a generic llama-style GGUF", func() {
+			d := parakeetDetails("huggingface://someorg/some-llm-gguf", `{}`,
+				hfapi.ModelFile{Path: "llama-3-8b-instruct-q4_k_m.gguf"},
+			)
+			Expect(imp.Match(d)).To(BeFalse())
+		})
+
+		It("does NOT claim the upstream NeMo repo (.nemo, no GGUF)", func() {
+			d := parakeetDetails("huggingface://nvidia/parakeet-tdt_ctc-110m", `{}`,
+				hfapi.ModelFile{Path: "parakeet-tdt_ctc-110m.nemo"},
+			)
+			Expect(imp.Match(d)).To(BeFalse())
+		})
+	})
+
+	Context("import (Import)", func() {
+		It("picks the default quant (q4_k) from a multi-quant HF repo", func() {
+			d := parakeetDetails("huggingface://mudler/parakeet-cpp-gguf", `{"name":"parakeet-110m"}`,
+				hfapi.ModelFile{Path: "tdt_ctc-110m-f16.gguf", URL: "https://hf/f16", SHA256: "aaa"},
+				hfapi.ModelFile{Path: "tdt_ctc-110m-q4_k.gguf", URL: "https://hf/q4k", SHA256: "bbb"},
+				hfapi.ModelFile{Path: "tdt_ctc-110m-q8_0.gguf", URL: "https://hf/q8", SHA256: "ccc"},
+			)
+			cfg, err := imp.Import(d)
+			Expect(err).ToNot(HaveOccurred())
+			Expect(cfg.ConfigFile).To(ContainSubstring("backend: parakeet-cpp"), fmt.Sprintf("%+v", cfg))
+			Expect(cfg.ConfigFile).To(ContainSubstring("transcript"))
+			Expect(cfg.Files).To(HaveLen(1))
+			Expect(cfg.Files[0].URI).To(Equal("https://hf/q4k"), "default quant should be q4_k")
+			Expect(cfg.Files[0].Filename).To(ContainSubstring("parakeet-cpp/models/parakeet-110m/tdt_ctc-110m-q4_k.gguf"))
+		})
+
+		It("honours a preferred quantization override", func() {
+			d := parakeetDetails("huggingface://mudler/parakeet-cpp-gguf", `{"name":"p","quantizations":"q8_0"}`,
+				hfapi.ModelFile{Path: "tdt_ctc-110m-f16.gguf", URL: "https://hf/f16"},
+				hfapi.ModelFile{Path: "tdt_ctc-110m-q8_0.gguf", URL: "https://hf/q8"},
+			)
+			cfg, err := imp.Import(d)
+			Expect(err).ToNot(HaveOccurred())
+			Expect(cfg.Files).To(HaveLen(1))
+			Expect(cfg.Files[0].URI).To(Equal("https://hf/q8"))
+		})
+
+		It("uses the exact file for a direct GGUF URL", func() {
+			d := parakeetDetails("https://huggingface.co/mudler/parakeet-cpp-gguf/resolve/main/ctc-0.6b-q5_k.gguf", `{"name":"ctc"}`)
+			cfg, err := imp.Import(d)
+			Expect(err).ToNot(HaveOccurred())
+			Expect(cfg.Files).To(HaveLen(1))
+			Expect(cfg.Files[0].Filename).To(ContainSubstring("parakeet-cpp/models/ctc/ctc-0.6b-q5_k.gguf"))
+		})
+	})
+})

core/gallery/importers/rfdetr.go

@@ -31,6 +31,29 @@ func repoLooksLikeRFDetr(repo string) bool {
 	return strings.Contains(lower, "rf-detr") || strings.Contains(lower, "rfdetr")
 }
 
+// repoHasGGUF inspects the HuggingFace file list (when available) to decide
+// whether the repo ships RF-DETR weights in ggml/GGUF form — the native
+// rfdetr-cpp backend's input format. Mudler's rfdetr-cpp-* repos
+// (mudler/rfdetr-cpp-nano, mudler/rfdetr-cpp-base, ...) match.
+func repoHasGGUF(details Details) bool {
+	if details.HuggingFace == nil {
+		return false
+	}
+	for _, f := range details.HuggingFace.Files {
+		if strings.HasSuffix(strings.ToLower(f.Path), ".gguf") {
+			return true
+		}
+	}
+	return false
+}
+
+func repoLooksLikeRFDetrCpp(repo string) bool {
+	lower := strings.ToLower(repo)
+	return strings.Contains(lower, "rfdetr-cpp") || strings.Contains(lower, "rf-detr-cpp") ||
+		strings.Contains(lower, "rfdetr.cpp") || strings.Contains(lower, "rt-detr.cpp") ||
+		strings.Contains(lower, "rf-detr.cpp")
+}
+
 func (i *RFDetrImporter) Match(details Details) bool {
 	preferences, err := details.Preferences.MarshalJSON()
 	if err != nil {
@@ -43,7 +66,7 @@ func (i *RFDetrImporter) Match(details Details) bool {
 		}
 	}
 
-	if b, ok := preferencesMap["backend"].(string); ok && b == "rfdetr" {
+	if b, ok := preferencesMap["backend"].(string); ok && (b == "rfdetr" || b == "rfdetr-cpp") {
 		return true
 	}
 
@@ -99,10 +122,28 @@ func (i *RFDetrImporter) Import(details Details) (gallery.ModelConfig, error) {
 		model = owner + "/" + repo
 	}
 
+	// Route GGUF-bearing repos (mudler/rfdetr-cpp-*) to the native
+	// rfdetr-cpp backend; HF transformer repos keep the Python rfdetr
+	// backend. Explicit preferences.backend overrides the heuristic.
+	backend := "rfdetr"
+	if b, ok := preferencesMap["backend"].(string); ok && b != "" {
+		backend = b
+	} else if repoHasGGUF(details) {
+		backend = "rfdetr-cpp"
+	} else if details.HuggingFace != nil {
+		repoName := details.HuggingFace.ModelID
+		if idx := strings.Index(repoName, "/"); idx >= 0 {
+			repoName = repoName[idx+1:]
+		}
+		if repoLooksLikeRFDetrCpp(repoName) {
+			backend = "rfdetr-cpp"
+		}
+	}
+
 	modelConfig := config.ModelConfig{
 		Name:                name,
 		Description:         description,
-		Backend:             "rfdetr",
+		Backend:             backend,
 		KnownUsecaseStrings: []string{"detection"},
 		PredictionOptions: schema.PredictionOptions{
 			BasicModelRequest: schema.BasicModelRequest{Model: model},

core/gallery/importers/rfdetr_test.go

@@ -129,4 +129,125 @@ var _ = Describe("RFDetrImporter", func() {
 			Expect(modelConfig.Description).To(Equal("Custom"))
 		})
 	})
+
+	// Table-driven coverage of the GGUF auto-routing path between the
+	// Python rfdetr backend (HF transformer repos) and the native
+	// rfdetr-cpp backend (GGUF repos like mudler/rfdetr-cpp-*).
+	//
+	// Cases are kept offline-deterministic by injecting Details directly
+	// rather than going through DiscoverModelConfig (which would hit live HF).
+	// The live HF cross-check lives in its own Context below.
+	Context("GGUF auto-routing (offline)", func() {
+		hfFile := func(path string) hfapi.ModelFile {
+			return hfapi.ModelFile{Path: path}
+		}
+
+		type tc struct {
+			name           string
+			uri            string
+			modelID        string
+			files          []hfapi.ModelFile
+			prefs          string
+			expectBackend  string // expected `backend:` line content
+			rejectBackends []string
+		}
+
+		entries := []tc{
+			{
+				name:          "GGUF repo with rfdetr-cpp prefix routes to rfdetr-cpp",
+				uri:           "https://huggingface.co/mudler/rfdetr-cpp-nano",
+				modelID:       "mudler/rfdetr-cpp-nano",
+				files:         []hfapi.ModelFile{hfFile("rfdetr-nano-q8_0.gguf"), hfFile("README.md")},
+				prefs:         "",
+				expectBackend: "backend: rfdetr-cpp",
+			},
+			{
+				name:          "GGUF presence alone routes to rfdetr-cpp even when repo name lacks -cpp",
+				uri:           "https://huggingface.co/some/rf-detr-ggml",
+				modelID:       "some/rf-detr-ggml",
+				files:         []hfapi.ModelFile{hfFile("rfdetr-base-f16.gguf")},
+				prefs:         "",
+				expectBackend: "backend: rfdetr-cpp",
+			},
+			{
+				name:           "transformer repo without GGUF stays on the Python rfdetr backend",
+				uri:            "https://huggingface.co/roboflow/rf-detr-base",
+				modelID:        "roboflow/rf-detr-base",
+				files:          []hfapi.ModelFile{hfFile("config.json"), hfFile("pytorch_model.bin")},
+				prefs:          "",
+				expectBackend:  "backend: rfdetr\n",
+				rejectBackends: []string{"backend: rfdetr-cpp"},
+			},
+			{
+				name:           "explicit preferences.backend=rfdetr overrides GGUF auto-detect",
+				uri:            "https://huggingface.co/mudler/rfdetr-cpp-nano",
+				modelID:        "mudler/rfdetr-cpp-nano",
+				files:          []hfapi.ModelFile{hfFile("rfdetr-nano-q8_0.gguf")},
+				prefs:          `{"backend": "rfdetr"}`,
+				expectBackend:  "backend: rfdetr\n",
+				rejectBackends: []string{"backend: rfdetr-cpp"},
+			},
+			{
+				name:          "explicit preferences.backend=rfdetr-cpp wins on non-GGUF transformer repo",
+				uri:           "https://huggingface.co/roboflow/rf-detr-base",
+				modelID:       "roboflow/rf-detr-base",
+				files:         []hfapi.ModelFile{hfFile("config.json")},
+				prefs:         `{"backend": "rfdetr-cpp"}`,
+				expectBackend: "backend: rfdetr-cpp",
+			},
+			{
+				name:          "repo name with rfdetr.cpp pattern routes to rfdetr-cpp even without HF file list",
+				uri:           "https://huggingface.co/some/rfdetr.cpp-bundle",
+				modelID:       "some/rfdetr.cpp-bundle",
+				files:         nil,
+				prefs:         "",
+				expectBackend: "backend: rfdetr-cpp",
+			},
+		}
+
+		for _, e := range entries {
+			e := e // capture for closure
+			It(e.name, func() {
+				imp := &importers.RFDetrImporter{}
+				details := importers.Details{
+					URI: e.uri,
+					HuggingFace: &hfapi.ModelDetails{
+						ModelID: e.modelID,
+						Files:   e.files,
+					},
+				}
+				if e.prefs != "" {
+					details.Preferences = json.RawMessage(e.prefs)
+				}
+
+				// Match must always be true for these fixtures — they're
+				// either preference-driven or have an rfdetr/rf-detr token.
+				Expect(imp.Match(details)).To(BeTrue(), fmt.Sprintf("Match should fire for %+v", details))
+
+				modelConfig, err := imp.Import(details)
+				Expect(err).ToNot(HaveOccurred(), fmt.Sprintf("Import error: %v", err))
+				Expect(modelConfig.ConfigFile).To(ContainSubstring(e.expectBackend),
+					fmt.Sprintf("Model config: %+v", modelConfig))
+				for _, rej := range e.rejectBackends {
+					Expect(modelConfig.ConfigFile).ToNot(ContainSubstring(rej),
+						fmt.Sprintf("did not expect %q in: %+v", rej, modelConfig))
+				}
+			})
+		}
+	})
+
+	// Live HF cross-check: the canonical native GGUF repo for the
+	// rfdetr-cpp backend. Marked broad — we only assert the routing
+	// decision, not file lists (upstream may add quants over time).
+	Context("detection from HuggingFace: mudler/rfdetr-cpp-nano", func() {
+		It("auto-routes to the native rfdetr-cpp backend without preferences", func() {
+			uri := "https://huggingface.co/mudler/rfdetr-cpp-nano"
+			modelConfig, err := importers.DiscoverModelConfig(uri, json.RawMessage(`{}`))
+
+			Expect(err).ToNot(HaveOccurred(), fmt.Sprintf("Error: %v", err))
+			Expect(modelConfig.ConfigFile).To(ContainSubstring("backend: rfdetr-cpp"),
+				fmt.Sprintf("Model config: %+v", modelConfig))
+			Expect(modelConfig.ConfigFile).To(ContainSubstring("mudler/rfdetr-cpp-nano"))
+		})
+	})
 })

core/http/app_test.go

@@ -308,6 +308,11 @@ var _ = Describe("API test", func() {
 	var cancel context.CancelFunc
 	var tmpdir string
 	var modelDir string
+	// localAIApp captures the Application so AfterEach can synchronously
+	// stop the spawned gRPC backend processes. application.New cancels
+	// them asynchronously on context cancel, which races with test-binary
+	// exit and leaks mock-backend children to init.
+	var localAIApp *application.Application
 
 	commonOpts := []config.AppOption{
 		config.WithDebug(true),
@@ -736,14 +741,14 @@ parameters:
 			)
 			Expect(err).ToNot(HaveOccurred())
 
-			application, err := application.New(
+			localAIApp, err = application.New(
 				append(commonOpts,
 					config.WithContext(c),
 					config.WithSystemState(systemState),
 				)...)
 			Expect(err).ToNot(HaveOccurred())
-			application.ModelLoader().SetExternalBackend("mock-backend", mockBackendPath)
-			app, err = API(application)
+			localAIApp.ModelLoader().SetExternalBackend("mock-backend", mockBackendPath)
+			app, err = API(localAIApp)
 			Expect(err).ToNot(HaveOccurred())
 			go func() {
 				if err := app.Start("127.0.0.1:9090"); err != nil && err != http.ErrServerClosed {
@@ -765,6 +770,11 @@ parameters:
 			}, "2m").ShouldNot(HaveOccurred())
 		})
 		AfterEach(func() {
+			// Synchronous shutdown — context-cancel cleanup is async and races
+			// test-binary exit, orphaning mock-backend children to init.
+			if localAIApp != nil {
+				_ = localAIApp.Shutdown()
+			}
 			cancel()
 			if app != nil {
 				ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
@@ -976,15 +986,15 @@ parameters:
 			)
 			Expect(err).ToNot(HaveOccurred())
 
-			application, err := application.New(
+			localAIApp, err = application.New(
 				append(commonOpts,
 					config.WithContext(c),
 					config.WithSystemState(systemState),
 					config.WithConfigFile(configFile))...,
 			)
 			Expect(err).ToNot(HaveOccurred())
-			application.ModelLoader().SetExternalBackend("mock-backend", mockBackendPath)
-			app, err = API(application)
+			localAIApp.ModelLoader().SetExternalBackend("mock-backend", mockBackendPath)
+			app, err = API(localAIApp)
 			Expect(err).ToNot(HaveOccurred())
 
 			go func() {
@@ -1005,6 +1015,11 @@ parameters:
 			}, "2m").ShouldNot(HaveOccurred())
 		})
 		AfterEach(func() {
+			// Synchronous shutdown — context-cancel cleanup is async and races
+			// test-binary exit, orphaning mock-backend children to init.
+			if localAIApp != nil {
+				_ = localAIApp.Shutdown()
+			}
 			cancel()
 			if app != nil {
 				ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)

core/http/auth/oauth.go

@@ -19,6 +19,8 @@ import (
 	"golang.org/x/oauth2"
 	githubOAuth "golang.org/x/oauth2/github"
 	"gorm.io/gorm"
+
+	"github.com/mudler/LocalAI/pkg/httpclient"
 )
 
 // providerEntry holds the OAuth2/OIDC config for a single provider.
@@ -389,7 +391,7 @@ func fetchGitHubUserInfoAsOAuth(ctx context.Context, accessToken string) (*oauth
 }
 
 func fetchGitHubUserInfo(ctx context.Context, accessToken string) (*githubUserInfo, error) {
-	client := &http.Client{Timeout: 10 * time.Second}
+	client := httpclient.NewWithTimeout(10 * time.Second)
 
 	req, _ := http.NewRequestWithContext(ctx, "GET", "https://api.github.com/user", nil)
 	req.Header.Set("Authorization", "Bearer "+accessToken)
@@ -420,7 +422,7 @@ func fetchGitHubUserInfo(ctx context.Context, accessToken string) (*githubUserIn
 }
 
 func fetchGitHubPrimaryEmail(ctx context.Context, accessToken string) (string, error) {
-	client := &http.Client{Timeout: 10 * time.Second}
+	client := httpclient.NewWithTimeout(10 * time.Second)
 
 	req, _ := http.NewRequestWithContext(ctx, "GET", "https://api.github.com/user/emails", nil)
 	req.Header.Set("Authorization", "Bearer "+accessToken)
@@ -458,7 +460,6 @@ func fetchGitHubPrimaryEmail(ctx context.Context, accessToken string) (string, e
 	return "", fmt.Errorf("no verified email found")
 }
 
-
 func generateState() (string, error) {
 	b := make([]byte, 16)
 	if _, err := rand.Read(b); err != nil {

core/http/endpoints/localai/audio.go

@@ -11,6 +11,8 @@ import (
 	"time"
 
 	"github.com/labstack/echo/v4"
+
+	"github.com/mudler/LocalAI/pkg/httpclient"
 	"github.com/mudler/LocalAI/pkg/utils"
 )
 
@@ -22,7 +24,9 @@ import (
 // decoding on the leading `data:` bytes.
 var audioDataURIPattern = regexp.MustCompile(`^data:[^,]+?;base64,`)
 
-var audioDownloadClient = http.Client{Timeout: 30 * time.Second}
+// Downloading user-supplied media URLs legitimately follows redirects (CDNs);
+// WithFollowRedirects still strips any credential header on a cross-host hop.
+var audioDownloadClient = httpclient.NewWithTimeout(30*time.Second, httpclient.WithFollowRedirects())
 
 // decodeAudioInput materialises a URL / data-URI / raw-base64 audio
 // payload to a temporary file and returns its path plus a cleanup

core/http/endpoints/localai/branding_endpoints_test.go

@@ -0,0 +1,233 @@
+package localai_test
+
+import (
+	"bytes"
+	"encoding/json"
+	"fmt"
+	"mime/multipart"
+	"net/http"
+	"net/http/httptest"
+	"net/textproto"
+	"os"
+	"path/filepath"
+
+	"github.com/labstack/echo/v4"
+	"github.com/mudler/LocalAI/core/config"
+	. "github.com/mudler/LocalAI/core/http/endpoints/localai"
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+)
+
+// multipartFile builds a multipart/form-data body with a single "file" part,
+// letting the caller control the part's filename and Content-Type so the
+// upload handler's MIME allow-list and extension-fallback paths can be tested.
+func multipartFile(filename, contentType string, data []byte) (*bytes.Buffer, string) {
+	body := &bytes.Buffer{}
+	w := multipart.NewWriter(body)
+	h := make(textproto.MIMEHeader)
+	h.Set("Content-Disposition", fmt.Sprintf(`form-data; name="file"; filename="%s"`, filename))
+	if contentType != "" {
+		h.Set("Content-Type", contentType)
+	}
+	part, err := w.CreatePart(h)
+	Expect(err).ToNot(HaveOccurred())
+	_, err = part.Write(data)
+	Expect(err).ToNot(HaveOccurred())
+	Expect(w.Close()).To(Succeed())
+	return body, w.FormDataContentType()
+}
+
+var _ = Describe("Branding endpoints", func() {
+	var (
+		dir    string
+		e      *echo.Echo
+		appCfg *config.ApplicationConfig
+	)
+
+	BeforeEach(func() {
+		var err error
+		dir, err = os.MkdirTemp("", "branding-endpoints-*")
+		Expect(err).ToNot(HaveOccurred())
+
+		appCfg = config.NewApplicationConfig()
+		appCfg.DynamicConfigsDir = dir
+		appCfg.Branding.InstanceName = "Acme AI"
+		appCfg.Branding.InstanceTagline = "do things"
+
+		e = echo.New()
+		e.GET("/api/branding", GetBrandingEndpoint(appCfg))
+		e.POST("/api/branding/asset/:kind", UploadBrandingAssetEndpoint(appCfg))
+		e.DELETE("/api/branding/asset/:kind", DeleteBrandingAssetEndpoint(appCfg))
+		e.GET("/branding/asset/:kind", ServeBrandingAssetEndpoint(appCfg))
+	})
+
+	AfterEach(func() {
+		Expect(os.RemoveAll(dir)).To(Succeed())
+	})
+
+	decode := func(rec *httptest.ResponseRecorder) BrandingResponse {
+		var b BrandingResponse
+		Expect(json.Unmarshal(rec.Body.Bytes(), &b)).To(Succeed())
+		return b
+	}
+
+	Describe("GET /api/branding", func() {
+		It("returns instance text and bundled default asset URLs when nothing is uploaded", func() {
+			req := httptest.NewRequest(http.MethodGet, "/api/branding", nil)
+			rec := httptest.NewRecorder()
+			e.ServeHTTP(rec, req)
+
+			Expect(rec.Code).To(Equal(http.StatusOK))
+			b := decode(rec)
+			Expect(b.InstanceName).To(Equal("Acme AI"))
+			Expect(b.InstanceTagline).To(Equal("do things"))
+			Expect(b.LogoURL).To(Equal("/static/logo.png"))
+			Expect(b.LogoHorizontalURL).To(Equal("/static/logo_horizontal.png"))
+			Expect(b.FaviconURL).To(Equal("/favicon.svg"))
+		})
+
+		It("points an uploaded asset at the dynamic serve route", func() {
+			appCfg.Branding.LogoFile = "logo.png"
+			req := httptest.NewRequest(http.MethodGet, "/api/branding", nil)
+			rec := httptest.NewRecorder()
+			e.ServeHTTP(rec, req)
+			Expect(decode(rec).LogoURL).To(Equal("/branding/asset/logo"))
+		})
+	})
+
+	Describe("POST /api/branding/asset/:kind", func() {
+		It("stores an uploaded PNG and persists the setting", func() {
+			body, ct := multipartFile("mylogo.png", "image/png", []byte("\x89PNG\r\n\x1a\n"))
+			req := httptest.NewRequest(http.MethodPost, "/api/branding/asset/logo", body)
+			req.Header.Set("Content-Type", ct)
+			rec := httptest.NewRecorder()
+			e.ServeHTTP(rec, req)
+
+			Expect(rec.Code).To(Equal(http.StatusOK))
+			Expect(decode(rec).LogoURL).To(Equal("/branding/asset/logo"))
+
+			// File landed under <dir>/branding/logo.png ...
+			_, err := os.Stat(filepath.Join(dir, "branding", "logo.png"))
+			Expect(err).ToNot(HaveOccurred())
+			// ... the in-memory config was updated ...
+			Expect(appCfg.Branding.LogoFile).To(Equal("logo.png"))
+			// ... and it was persisted to runtime_settings.json.
+			_, err = os.Stat(filepath.Join(dir, "runtime_settings.json"))
+			Expect(err).ToNot(HaveOccurred())
+		})
+
+		It("accepts a generic content-type when the filename extension is allowed", func() {
+			body, ct := multipartFile("favicon.svg", "application/octet-stream", []byte("<svg/>"))
+			req := httptest.NewRequest(http.MethodPost, "/api/branding/asset/favicon", body)
+			req.Header.Set("Content-Type", ct)
+			rec := httptest.NewRecorder()
+			e.ServeHTTP(rec, req)
+
+			Expect(rec.Code).To(Equal(http.StatusOK))
+			Expect(appCfg.Branding.FaviconFile).To(Equal("favicon.svg"))
+		})
+
+		It("replaces a prior asset of a different extension", func() {
+			brandingDir := filepath.Join(dir, "branding")
+			Expect(os.MkdirAll(brandingDir, 0o750)).To(Succeed())
+			Expect(os.WriteFile(filepath.Join(brandingDir, "logo.svg"), []byte("<svg/>"), 0o644)).To(Succeed())
+
+			body, ct := multipartFile("new.png", "image/png", []byte("\x89PNG\r\n\x1a\n"))
+			req := httptest.NewRequest(http.MethodPost, "/api/branding/asset/logo", body)
+			req.Header.Set("Content-Type", ct)
+			rec := httptest.NewRecorder()
+			e.ServeHTTP(rec, req)
+
+			Expect(rec.Code).To(Equal(http.StatusOK))
+			// Old companion removed, new one present.
+			_, err := os.Stat(filepath.Join(brandingDir, "logo.svg"))
+			Expect(os.IsNotExist(err)).To(BeTrue())
+			_, err = os.Stat(filepath.Join(brandingDir, "logo.png"))
+			Expect(err).ToNot(HaveOccurred())
+		})
+
+		It("rejects an unknown asset kind", func() {
+			body, ct := multipartFile("x.png", "image/png", []byte("x"))
+			req := httptest.NewRequest(http.MethodPost, "/api/branding/asset/banner", body)
+			req.Header.Set("Content-Type", ct)
+			rec := httptest.NewRecorder()
+			e.ServeHTTP(rec, req)
+			Expect(rec.Code).To(Equal(http.StatusBadRequest))
+			Expect(rec.Body.String()).To(ContainSubstring("invalid asset kind"))
+		})
+
+		It("rejects a request with no file", func() {
+			body := &bytes.Buffer{}
+			w := multipart.NewWriter(body)
+			Expect(w.Close()).To(Succeed())
+			req := httptest.NewRequest(http.MethodPost, "/api/branding/asset/logo", body)
+			req.Header.Set("Content-Type", w.FormDataContentType())
+			rec := httptest.NewRecorder()
+			e.ServeHTTP(rec, req)
+			Expect(rec.Code).To(Equal(http.StatusBadRequest))
+			Expect(rec.Body.String()).To(ContainSubstring("file is required"))
+		})
+
+		It("rejects an unsupported file type", func() {
+			body, ct := multipartFile("evil.txt", "text/html", []byte("<script>"))
+			req := httptest.NewRequest(http.MethodPost, "/api/branding/asset/logo", body)
+			req.Header.Set("Content-Type", ct)
+			rec := httptest.NewRecorder()
+			e.ServeHTTP(rec, req)
+			Expect(rec.Code).To(Equal(http.StatusBadRequest))
+			Expect(rec.Body.String()).To(ContainSubstring("unsupported file type"))
+		})
+	})
+
+	Describe("DELETE /api/branding/asset/:kind", func() {
+		It("removes the asset file and clears the setting", func() {
+			// Seed an uploaded asset first.
+			body, ct := multipartFile("logo.png", "image/png", []byte("\x89PNG\r\n\x1a\n"))
+			req := httptest.NewRequest(http.MethodPost, "/api/branding/asset/logo", body)
+			req.Header.Set("Content-Type", ct)
+			e.ServeHTTP(httptest.NewRecorder(), req)
+			Expect(appCfg.Branding.LogoFile).To(Equal("logo.png"))
+
+			req = httptest.NewRequest(http.MethodDelete, "/api/branding/asset/logo", nil)
+			rec := httptest.NewRecorder()
+			e.ServeHTTP(rec, req)
+
+			Expect(rec.Code).To(Equal(http.StatusOK))
+			Expect(appCfg.Branding.LogoFile).To(Equal(""))
+			Expect(decode(rec).LogoURL).To(Equal("/static/logo.png"))
+			_, err := os.Stat(filepath.Join(dir, "branding", "logo.png"))
+			Expect(os.IsNotExist(err)).To(BeTrue())
+		})
+
+		It("rejects an unknown asset kind", func() {
+			req := httptest.NewRequest(http.MethodDelete, "/api/branding/asset/banner", nil)
+			rec := httptest.NewRecorder()
+			e.ServeHTTP(rec, req)
+			Expect(rec.Code).To(Equal(http.StatusBadRequest))
+		})
+	})
+
+	Describe("GET /branding/asset/:kind (serve)", func() {
+		It("404s for an unknown kind", func() {
+			req := httptest.NewRequest(http.MethodGet, "/branding/asset/banner", nil)
+			rec := httptest.NewRecorder()
+			e.ServeHTTP(rec, req)
+			Expect(rec.Code).To(Equal(http.StatusNotFound))
+		})
+
+		It("404s when no override is configured", func() {
+			req := httptest.NewRequest(http.MethodGet, "/branding/asset/logo", nil)
+			rec := httptest.NewRecorder()
+			e.ServeHTTP(rec, req)
+			Expect(rec.Code).To(Equal(http.StatusNotFound))
+		})
+
+		It("404s on a path-traversal basename", func() {
+			appCfg.Branding.LogoFile = "../runtime_settings.json"
+			req := httptest.NewRequest(http.MethodGet, "/branding/asset/logo", nil)
+			rec := httptest.NewRecorder()
+			e.ServeHTTP(rec, req)
+			Expect(rec.Code).To(Equal(http.StatusNotFound))
+		})
+	})
+})

core/http/endpoints/localai/cors_proxy.go

@@ -11,9 +11,11 @@ import (
 	"time"
 
 	"github.com/labstack/echo/v4"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/pkg/utils"
 	"github.com/mudler/xlog"
+
+	"github.com/mudler/LocalAI/core/config"
+	"github.com/mudler/LocalAI/pkg/httpclient"
+	"github.com/mudler/LocalAI/pkg/utils"
 )
 
 // CORSProxyEndpoint proxies HTTP requests to external MCP servers,
@@ -77,7 +79,7 @@ func CORSProxyEndpoint(appConfig *config.ApplicationConfig) echo.HandlerFunc {
 				)
 			},
 		}
-		client := &http.Client{Transport: transport, Timeout: 10 * time.Minute}
+		client := httpclient.New(httpclient.WithTransport(transport), httpclient.WithTimeout(10*time.Minute))
 
 		xlog.Debug("CORS proxy request", "method", c.Request().Method, "target", targetURL)
 

core/http/endpoints/localai/nodes.go

@@ -16,14 +16,16 @@ import (
 	"github.com/google/uuid"
 	"github.com/gorilla/websocket"
 	"github.com/labstack/echo/v4"
+	"github.com/mudler/xlog"
+	"gorm.io/gorm"
+
 	"github.com/mudler/LocalAI/core/config"
 	"github.com/mudler/LocalAI/core/gallery"
 	"github.com/mudler/LocalAI/core/http/auth"
 	"github.com/mudler/LocalAI/core/schema"
 	"github.com/mudler/LocalAI/core/services/galleryop"
 	"github.com/mudler/LocalAI/core/services/nodes"
-	"github.com/mudler/xlog"
-	"gorm.io/gorm"
+	"github.com/mudler/LocalAI/pkg/httpclient"
 )
 
 // nodeError builds a schema.ErrorResponse for node endpoints.
@@ -65,15 +67,15 @@ func GetNodeEndpoint(registry *nodes.NodeRegistry) echo.HandlerFunc {
 
 // RegisterNodeRequest is the request body for registering a new worker node.
 type RegisterNodeRequest struct {
-	Name          string `json:"name"`
-	NodeType      string `json:"node_type,omitempty"` // "backend" (default) or "agent"
-	Address       string `json:"address"`
-	HTTPAddress   string `json:"http_address,omitempty"`
-	Token         string `json:"token,omitempty"`
-	TotalVRAM     uint64 `json:"total_vram,omitempty"`
-	AvailableVRAM uint64 `json:"available_vram,omitempty"`
-	TotalRAM      uint64 `json:"total_ram,omitempty"`
-	AvailableRAM  uint64 `json:"available_ram,omitempty"`
+	Name          string            `json:"name"`
+	NodeType      string            `json:"node_type,omitempty"` // "backend" (default) or "agent"
+	Address       string            `json:"address"`
+	HTTPAddress   string            `json:"http_address,omitempty"`
+	Token         string            `json:"token,omitempty"`
+	TotalVRAM     uint64            `json:"total_vram,omitempty"`
+	AvailableVRAM uint64            `json:"available_vram,omitempty"`
+	TotalRAM      uint64            `json:"total_ram,omitempty"`
+	AvailableRAM  uint64            `json:"available_ram,omitempty"`
 	GPUVendor     string            `json:"gpu_vendor,omitempty"`
 	Labels        map[string]string `json:"labels,omitempty"`
 	// MaxReplicasPerModel is the per-node cap on replicas of any single model.
@@ -983,6 +985,6 @@ func proxyHTTPToWorker(httpAddress, path, token string) (*http.Response, error)
 		req.Header.Set("Authorization", "Bearer "+token)
 	}
 
-	client := &http.Client{Timeout: 15 * time.Second}
+	client := httpclient.NewWithTimeout(15 * time.Second)
 	return client.Do(req)
 }

core/http/endpoints/localai/settings_test.go

@@ -0,0 +1,111 @@
+package localai_test
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"net/http"
+	"net/http/httptest"
+	"os"
+	"path/filepath"
+
+	"github.com/labstack/echo/v4"
+	"github.com/mudler/LocalAI/core/application"
+	"github.com/mudler/LocalAI/core/config"
+	. "github.com/mudler/LocalAI/core/http/endpoints/localai"
+	"github.com/mudler/LocalAI/pkg/system"
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+)
+
+// The settings handlers take the concrete *application.Application, so the
+// suite builds a minimal real app (no watchdog/p2p — both default off — so
+// start() doesn't spawn background services) the same way the in-process HTTP
+// suite does, then drives the handlers via httptest.
+var _ = Describe("Settings endpoints", func() {
+	var (
+		tmp    string
+		app    *application.Application
+		e      *echo.Echo
+		cancel context.CancelFunc
+	)
+
+	BeforeEach(func() {
+		var err error
+		tmp, err = os.MkdirTemp("", "settings-test-*")
+		Expect(err).ToNot(HaveOccurred())
+
+		var ctx context.Context
+		ctx, cancel = context.WithCancel(context.Background())
+
+		st, err := system.GetSystemState(
+			system.WithModelPath(filepath.Join(tmp, "models")),
+			system.WithBackendPath(filepath.Join(tmp, "backends")),
+		)
+		Expect(err).ToNot(HaveOccurred())
+
+		app, err = application.New(
+			config.WithContext(ctx),
+			config.WithSystemState(st),
+		)
+		Expect(err).ToNot(HaveOccurred())
+		// Settings are persisted here; set after construction since there's no
+		// dedicated AppOption for it.
+		app.ApplicationConfig().DynamicConfigsDir = tmp
+
+		e = echo.New()
+		e.GET("/api/settings", GetSettingsEndpoint(app))
+		e.POST("/api/settings", UpdateSettingsEndpoint(app))
+	})
+
+	AfterEach(func() {
+		cancel()
+		Expect(os.RemoveAll(tmp)).To(Succeed())
+	})
+
+	post := func(body string) *httptest.ResponseRecorder {
+		req := httptest.NewRequest(http.MethodPost, "/api/settings", bytes.NewBufferString(body))
+		req.Header.Set("Content-Type", "application/json")
+		rec := httptest.NewRecorder()
+		e.ServeHTTP(rec, req)
+		return rec
+	}
+
+	It("GET returns the current runtime settings", func() {
+		req := httptest.NewRequest(http.MethodGet, "/api/settings", nil)
+		rec := httptest.NewRecorder()
+		e.ServeHTTP(rec, req)
+
+		Expect(rec.Code).To(Equal(http.StatusOK))
+		var settings map[string]any
+		Expect(json.Unmarshal(rec.Body.Bytes(), &settings)).To(Succeed())
+		Expect(settings).ToNot(BeEmpty())
+	})
+
+	It("rejects malformed JSON", func() {
+		rec := post("{not json")
+		Expect(rec.Code).To(Equal(http.StatusBadRequest))
+		Expect(rec.Body.String()).To(ContainSubstring("Failed to parse JSON"))
+	})
+
+	It("rejects an invalid watchdog timeout duration", func() {
+		rec := post(`{"watchdog_idle_timeout":"notaduration"}`)
+		Expect(rec.Code).To(Equal(http.StatusBadRequest))
+		Expect(rec.Body.String()).To(ContainSubstring("Invalid watchdog_idle_timeout"))
+	})
+
+	It("errors when DynamicConfigsDir is unset", func() {
+		app.ApplicationConfig().DynamicConfigsDir = ""
+		rec := post(`{}`)
+		Expect(rec.Code).To(Equal(http.StatusBadRequest))
+		Expect(rec.Body.String()).To(ContainSubstring("DynamicConfigsDir is not set"))
+	})
+
+	It("saves valid settings to runtime_settings.json", func() {
+		rec := post(`{}`)
+		Expect(rec.Code).To(Equal(http.StatusOK))
+		Expect(rec.Body.String()).To(ContainSubstring("Settings updated successfully"))
+		_, err := os.Stat(filepath.Join(tmp, "runtime_settings.json"))
+		Expect(err).ToNot(HaveOccurred())
+	})
+})

core/http/endpoints/localai/video.go

@@ -6,7 +6,6 @@ import (
 	"encoding/json"
 	"fmt"
 	"io"
-	"net/http"
 	"net/url"
 	"os"
 	"path/filepath"
@@ -15,18 +14,23 @@ import (
 
 	"github.com/google/uuid"
 	"github.com/labstack/echo/v4"
+
 	"github.com/mudler/LocalAI/core/config"
 	"github.com/mudler/LocalAI/core/http/middleware"
 	"github.com/mudler/LocalAI/core/schema"
 
 	"github.com/mudler/LocalAI/core/backend"
 
+	"github.com/mudler/xlog"
+
+	"github.com/mudler/LocalAI/pkg/httpclient"
 	model "github.com/mudler/LocalAI/pkg/model"
 	"github.com/mudler/LocalAI/pkg/utils"
-	"github.com/mudler/xlog"
 )
 
-var videoDownloadClient = http.Client{Timeout: 30 * time.Second}
+// Downloading user-supplied media URLs legitimately follows redirects (CDNs);
+// WithFollowRedirects still strips any credential header on a cross-host hop.
+var videoDownloadClient = httpclient.NewWithTimeout(30*time.Second, httpclient.WithFollowRedirects())
 
 func downloadFile(url string) (string, error) {
 	if err := utils.ValidateExternalURL(url); err != nil {

core/http/endpoints/mcp/tools.go

@@ -17,6 +17,7 @@ import (
 	"github.com/mudler/LocalAI/core/services/messaging"
 
 	"github.com/mudler/LocalAI/pkg/functions"
+	"github.com/mudler/LocalAI/pkg/httpclient"
 	"github.com/mudler/LocalAI/pkg/signals"
 
 	"github.com/modelcontextprotocol/go-sdk/mcp"
@@ -180,10 +181,10 @@ func SessionsFromMCPConfig(
 	for _, server := range remote.Servers {
 		xlog.Debug("[MCP remote server] Configuration", "server", server)
 		// Create HTTP client with custom roundtripper for bearer token injection
-		httpClient := &http.Client{
-			Timeout:   config.DefaultMCPToolTimeout,
-			Transport: newBearerTokenRoundTripper(server.Token, http.DefaultTransport),
-		}
+		httpClient := httpclient.New(
+			httpclient.WithTimeout(config.DefaultMCPToolTimeout),
+			httpclient.WithTransport(newBearerTokenRoundTripper(server.Token, httpclient.HardenedTransport())),
+		)
 
 		transport := &mcp.StreamableClientTransport{Endpoint: server.URL, HTTPClient: httpClient}
 		mcpSession, err := client.Connect(ctx, transport, nil)
@@ -262,10 +263,10 @@ func NamedSessionsFromMCPConfig(
 
 		for serverName, server := range remote.Servers {
 			xlog.Debug("[MCP remote server] Configuration", "name", serverName, "server", server)
-			httpClient := &http.Client{
-				Timeout:   config.DefaultMCPToolTimeout,
-				Transport: newBearerTokenRoundTripper(server.Token, http.DefaultTransport),
-			}
+			httpClient := httpclient.New(
+				httpclient.WithTimeout(config.DefaultMCPToolTimeout),
+				httpclient.WithTransport(newBearerTokenRoundTripper(server.Token, httpclient.HardenedTransport())),
+			)
 
 			transport := &mcp.StreamableClientTransport{Endpoint: server.URL, HTTPClient: httpClient}
 			mcpSession, err := client.Connect(ctx, transport, nil)

core/http/endpoints/openai/chat_stream_reasoning_test.go

@@ -0,0 +1,99 @@
+package openai
+
+import (
+	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	reason "github.com/mudler/LocalAI/pkg/reasoning"
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+)
+
+// Regression test for the prefill-misclassification artifact surfaced in
+// the review of #9991: when LocalAI templates qwen3 with
+// use_tokenizer_template (the post-#9985 gallery shape),
+// DetectThinkingStartToken finds <think> in the model's jinja chat
+// template — without evaluating the surrounding {% if enable_thinking %}
+// guard — and the Go-side extractor's PrependThinkingTokenIfNeeded then
+// treats every non-thinking output token as reasoning. The autoparser does
+// not classify qwen3's tool calls into ChatDelta.ToolCalls (qwen3's tool
+// format isn't on llama.cpp's recognized-tool list), so all tokens land in
+// ChatDelta.Content while the Go-side extractor silently accumulates a
+// "reasoning" string equal to the raw tool-call JSON. End-of-stream this
+// is flushed as a trailing `delta.reasoning` chunk to the client.
+//
+// chooseDeferredReasoning is the gate: when the autoparser was active for
+// any chunk (preferAutoparser sticky), we trust its reasoning_content
+// classification (usually empty) instead of the polluted Go-side state.
+var _ = Describe("chooseDeferredReasoning", func() {
+	// Simulate the qwen3-after-#9985 misclassification: build a real
+	// extractor with a <think> thinking-start token, then feed it
+	// non-thinking content. The extractor will (correctly per its own
+	// contract) treat the content as reasoning because
+	// PrependThinkingTokenIfNeeded synthesizes a leading <think>.
+	pollutedExtractor := func(content string) *reason.ReasoningExtractor {
+		e := reason.NewReasoningExtractor("<think>", reason.Config{})
+		e.ProcessToken(content)
+		Expect(e.Reasoning()).To(Equal(content),
+			"sanity: when the thinking-start token is set and content has no real <think>...</think>, "+
+				"the extractor classifies all content as reasoning — this is exactly the prefill pollution "+
+				"we want chooseDeferredReasoning to guard against")
+		return e
+	}
+
+	Context("autoparser was active (preferAutoparser=true)", func() {
+		It("returns the autoparser's reasoning classification, ignoring the polluted Go-side state", func() {
+			toolCallJSON := `{"arguments": {"cmd": "echo hello"}, "name": "exec"}`
+			extractor := pollutedExtractor(toolCallJSON)
+			// What the C++ autoparser sent: content chunks but no
+			// reasoning_content (qwen3 tool calls aren't classified by
+			// the upstream PEG parser).
+			chatDeltas := []*pb.ChatDelta{
+				{Content: toolCallJSON, ReasoningContent: ""},
+			}
+
+			got := chooseDeferredReasoning(true, chatDeltas, extractor)
+
+			Expect(got).To(BeEmpty(),
+				"chooseDeferredReasoning must NOT return the polluted extractor state "+
+					"when the autoparser was active — the autoparser correctly classified zero reasoning")
+		})
+
+		It("returns the autoparser's reasoning when it actually did classify reasoning", func() {
+			// The other side of the contract: when the autoparser was
+			// in jinja-with-recognized-format mode and DID classify
+			// reasoning, pass that through verbatim.
+			actualReasoning := "Okay, the user asked X. I should call exec."
+			extractor := pollutedExtractor("ignored polluted state")
+			chatDeltas := []*pb.ChatDelta{
+				{Content: "", ReasoningContent: actualReasoning},
+			}
+
+			got := chooseDeferredReasoning(true, chatDeltas, extractor)
+
+			Expect(got).To(Equal(actualReasoning))
+		})
+	})
+
+	Context("autoparser was NOT active (preferAutoparser=false)", func() {
+		It("falls back to the Go-side extractor — the right source for vLLM and other autoparser-less backends", func() {
+			realReasoning := "Genuine reasoning from a backend without an autoparser"
+			extractor := reason.NewReasoningExtractor("<think>", reason.Config{})
+			extractor.ProcessToken("<think>" + realReasoning + "</think>final answer")
+
+			got := chooseDeferredReasoning(false, nil, extractor)
+
+			Expect(got).To(Equal(realReasoning))
+		})
+
+		It("falls back even when ChatDeltas are present but the autoparser never classified anything", func() {
+			// Defensive: chatDeltas could carry vestigial data; if
+			// preferAutoparser wasn't flipped, we still use the
+			// extractor.
+			extractor := reason.NewReasoningExtractor("", reason.Config{})
+			extractor.ProcessToken("<think>some thoughts</think>answer")
+
+			got := chooseDeferredReasoning(false, []*pb.ChatDelta{{Content: "answer"}}, extractor)
+
+			Expect(got).To(Equal("some thoughts"))
+		})
+	})
+})

core/http/endpoints/openai/chat_stream_workers.go

@@ -7,11 +7,111 @@ import (
 	"github.com/mudler/LocalAI/core/config"
 	"github.com/mudler/LocalAI/core/schema"
 	"github.com/mudler/LocalAI/pkg/functions"
+	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
 	"github.com/mudler/LocalAI/pkg/model"
 	reason "github.com/mudler/LocalAI/pkg/reasoning"
 	"github.com/mudler/xlog"
 )
 
+// emitJSONToolCallDeltas iterates the JSON tool-call objects produced by the
+// streaming tool-call detector and emits SSE chunks for the ones the caller
+// hasn't already emitted. It returns the new lastEmittedCount.
+//
+// Semantics:
+//   - Skips entries before lastEmittedCount (already emitted).
+//   - Emits one tool_call chunk per consecutive entry that has a usable
+//     `name` string.
+//   - Stops at the first entry without a name (typically the partial-JSON
+//     tail or a healing-marker stub — see issue #9988) so the caller doesn't
+//     advance past it. Bumping lastEmittedCount past an unparsed stub
+//     permanently gates off content emission for the rest of the stream.
+//   - When jsonResults is empty (the autoparser-working case, where the raw
+//     text result is cleared and only ChatDeltas carry tool calls), this is
+//     a no-op and lastEmittedCount is returned unchanged.
+//
+// The autoparser-correctly-classifying-tool-calls path is unaffected: it
+// delivers tool calls via TokenUsage.ChatDeltas, and the deferred
+// end-of-stream block (ToolCallsFromChatDeltas → buildDeferredToolCallChunks)
+// emits them; this helper sees an empty jsonResults and emits nothing.
+func emitJSONToolCallDeltas(
+	jsonResults []map[string]any,
+	lastEmittedCount int,
+	id, model string,
+	created int,
+	responses chan<- schema.OpenAIResponse,
+) int {
+	for i := lastEmittedCount; i < len(jsonResults); i++ {
+		jsonObj := jsonResults[i]
+		name, ok := jsonObj["name"].(string)
+		if !ok || name == "" {
+			break
+		}
+		args := "{}"
+		if argsVal, ok := jsonObj["arguments"]; ok {
+			if argsStr, ok := argsVal.(string); ok {
+				args = argsStr
+			} else {
+				argsBytes, _ := json.Marshal(argsVal)
+				args = string(argsBytes)
+			}
+		}
+		responses <- schema.OpenAIResponse{
+			ID:      id,
+			Created: created,
+			Model:   model,
+			Choices: []schema.Choice{{
+				Delta: &schema.Message{
+					Role: "assistant",
+					ToolCalls: []schema.ToolCall{
+						{
+							Index: i,
+							ID:    id,
+							Type:  "function",
+							FunctionCall: schema.FunctionCall{
+								Name:      name,
+								Arguments: args,
+							},
+						},
+					},
+				},
+				Index:        0,
+				FinishReason: nil,
+			}},
+			Object: "chat.completion.chunk",
+		}
+		lastEmittedCount = i + 1
+	}
+	return lastEmittedCount
+}
+
+// chooseDeferredReasoning picks the source of truth for the end-of-stream
+// reasoning flush in processStreamWithTools. When the C++ autoparser was
+// active during the stream (preferAutoparser), it returns the autoparser's
+// own classified reasoning_content from ChatDeltas — usually empty when the
+// autoparser is in pure-content fallback mode. Otherwise it falls back to
+// the Go-side streaming extractor, which is the right source for backends
+// without an autoparser (vLLM, etc.).
+//
+// Why: the Go-side extractor's accumulated Reasoning() can be polluted by
+// PrependThinkingTokenIfNeeded — when the tokenizer template contains a
+// thinking start token (qwen3's jinja template has <think> inside an
+// {% if enable_thinking %} block, and DetectThinkingStartToken does not
+// evaluate jinja conditionals), prefill detection treats every chunk's
+// content as reasoning, even when the model emitted a raw tool-call JSON
+// in non-thinking mode. Without this guard, qwen3-4b with streaming + tools
+// (after #9985 flipped the gallery to use_tokenizer_template) emits a
+// trailing SSE chunk where `reasoning` carries the tool-call JSON.
+func chooseDeferredReasoning(
+	preferAutoparser bool,
+	chatDeltas []*pb.ChatDelta,
+	extractor *reason.ReasoningExtractor,
+) string {
+	if preferAutoparser {
+		return functions.ReasoningFromChatDeltas(chatDeltas)
+	}
+	return extractor.Reasoning()
+}
+
 // processStream is the streaming worker for chat completions with no
 // tool/function calling involved. It pushes SSE-shaped chunks onto
 // `responses` and returns the authoritative cumulative TokenUsage from
@@ -157,6 +257,17 @@ func processStreamWithTools(
 	hasChatDeltaToolCalls := false
 	hasChatDeltaContent := false
 
+	// preferAutoparser is sticky: once the C++ autoparser has ever delivered
+	// content or reasoning via ChatDeltas, we trust its classification for the
+	// rest of the stream — including for the end-of-stream reasoning flush in
+	// buildDeferredToolCallChunks. Otherwise the Go-side extractor's
+	// accumulated Reasoning() can be polluted by prefill detection
+	// misclassifying content as reasoning (this happens when <think> appears
+	// in the tokenizer template and the model emits non-reasoning content
+	// like a raw tool-call JSON — qwen3-4b after #9985 enabled
+	// use_tokenizer_template). Mirrors the analogous flag in processStream.
+	preferAutoparser := false
+
 	// X-LocalAI-Node attribution is handled by middleware.ExposeNodeHeader
 	// at the wrapper layer; no in-band signalling from this worker.
 
@@ -180,12 +291,17 @@ func processStreamWithTools(
 
 		if usage.HasChatDeltaContent() {
 			rawReasoning, cd := usage.ChatDeltaReasoningAndContent()
+			preferAutoparser = true
 			contentDelta = cd
 			reasoningDelta = extractor.ProcessChatDeltaReasoning(rawReasoning)
-		} else {
+		} else if !preferAutoparser {
 			reasoningDelta = goReasoning
 			contentDelta = goContent
 		}
+		// If preferAutoparser is already true but this chunk carried no
+		// autoparser data, leave both deltas empty — the next autoparser
+		// chunk will pick things up. Falling back to Go-side here would
+		// re-introduce the prefill-misclassification leak.
 
 		// Emit reasoning deltas in their own SSE chunks before any tool-call chunks
 		// (OpenAI spec: reasoning and tool_calls never share a delta)
@@ -225,6 +341,19 @@ func processStreamWithTools(
 			}
 		}
 
+		// Issue #9722: when the C++ autoparser is already producing tool
+		// calls (it delivers them via ChatDeltas, which are flushed at
+		// end-of-stream by ToolCallsFromChatDeltas -> buildDeferredToolCallChunks),
+		// skip the Go-side iterative parser below. Running both parsers makes
+		// the same logical tool call surface at multiple `index` values.
+		// The deferred flush is guarded by lastEmittedCount, so the race where
+		// the Go parser already emitted before this flag flipped also stays
+		// single-emission. Backends without an autoparser (e.g. vLLM) keep
+		// hasChatDeltaToolCalls=false and are unaffected.
+		if hasChatDeltaToolCalls {
+			return true
+		}
+
 		// Try incremental XML parsing for streaming support using iterative parser
 		// This allows emitting partial tool calls as they're being generated
 		cleanedResult := functions.CleanupLLMResult(result, cfg.FunctionsConfig)
@@ -279,49 +408,10 @@ func processStreamWithTools(
 			// Try JSON tool call parsing for streaming.
 			// Only emit NEW tool calls (same guard as XML parser above).
 			jsonResults, jsonErr := functions.ParseJSONIterative(cleanedResult, true)
-			if jsonErr == nil && len(jsonResults) > lastEmittedCount {
-				for i := lastEmittedCount; i < len(jsonResults); i++ {
-					jsonObj := jsonResults[i]
-					name, ok := jsonObj["name"].(string)
-					if !ok || name == "" {
-						continue
-					}
-					args := "{}"
-					if argsVal, ok := jsonObj["arguments"]; ok {
-						if argsStr, ok := argsVal.(string); ok {
-							args = argsStr
-						} else {
-							argsBytes, _ := json.Marshal(argsVal)
-							args = string(argsBytes)
-						}
-					}
-					initialMessage := schema.OpenAIResponse{
-						ID:      id,
-						Created: created,
-						Model:   req.Model,
-						Choices: []schema.Choice{{
-							Delta: &schema.Message{
-								Role: "assistant",
-								ToolCalls: []schema.ToolCall{
-									{
-										Index: i,
-										ID:    id,
-										Type:  "function",
-										FunctionCall: schema.FunctionCall{
-											Name:      name,
-											Arguments: args,
-										},
-									},
-								},
-							},
-							Index:        0,
-							FinishReason: nil,
-						}},
-						Object: "chat.completion.chunk",
-					}
-					responses <- initialMessage
-				}
-				lastEmittedCount = len(jsonResults)
+			if jsonErr == nil {
+				lastEmittedCount = emitJSONToolCallDeltas(
+					jsonResults, lastEmittedCount, id, req.Model, created, responses,
+				)
 			}
 		}
 		return true
@@ -367,7 +457,14 @@ func processStreamWithTools(
 	} else {
 		// Fallback: parse tool calls from raw text (no chat deltas from backend)
 		xlog.Debug("[ChatDeltas] no pre-parsed tool calls, falling back to Go-side text parsing")
-		reasoning = extractor.Reasoning()
+		// When the autoparser was active during streaming (preferAutoparser),
+		// trust its reasoning classification rather than the Go-side
+		// extractor's accumulated state — the latter may have misclassified
+		// content as reasoning due to prefill detection on a tokenizer
+		// template that contains <think>. This was visible on qwen3-4b after
+		// #9985 enabled use_tokenizer_template: a streaming tool-call JSON
+		// would leak as a trailing reasoning chunk via the deferred flush.
+		reasoning = chooseDeferredReasoning(preferAutoparser, chatDeltas, extractor)
 		cleanedResult := extractor.CleanedContent()
 		*textContentToReturn = functions.ParseTextContent(cleanedResult, cfg.FunctionsConfig)
 		cleanedResult = functions.CleanupLLMResult(cleanedResult, cfg.FunctionsConfig)

core/http/endpoints/openai/chat_stream_workers_test.go

@@ -0,0 +1,197 @@
+package openai
+
+import (
+	"github.com/mudler/LocalAI/core/schema"
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+)
+
+// drainChannel reads everything currently buffered on a channel without
+// blocking on close. The helper test channels are sized for the assertions.
+func drainChannel(ch <-chan schema.OpenAIResponse) []schema.OpenAIResponse {
+	var out []schema.OpenAIResponse
+	for {
+		select {
+		case r, ok := <-ch:
+			if !ok {
+				return out
+			}
+			out = append(out, r)
+		default:
+			return out
+		}
+	}
+}
+
+// nameOf returns the name of the first tool call carried on the choice's
+// delta, or "" if none.
+func nameOf(r schema.OpenAIResponse) string {
+	if len(r.Choices) == 0 || r.Choices[0].Delta == nil {
+		return ""
+	}
+	if len(r.Choices[0].Delta.ToolCalls) == 0 {
+		return ""
+	}
+	return r.Choices[0].Delta.ToolCalls[0].FunctionCall.Name
+}
+
+var _ = Describe("emitJSONToolCallDeltas", func() {
+	const (
+		id      = "test-stream"
+		model   = "test-model"
+		created = 1700000000
+	)
+
+	// The case that motivated this helper. With the previous version of
+	// the streaming worker, ParseJSONIterative would hand back a stub
+	// object like `{"4310046988783340008":1}` after the model had only
+	// emitted `{`. The worker bumped lastEmittedCount unconditionally,
+	// which permanently gated off content emission for the rest of the
+	// stream (qwen3-4b with stream:true + tools dribbled only `{"` to
+	// the client and then nothing). See issue #9988.
+	Context("partial stub without a usable name", func() {
+		It("does NOT bump lastEmittedCount and emits nothing", func() {
+			responses := make(chan schema.OpenAIResponse, 4)
+			// What ParseJSONIterative used to return for `{`:
+			stubResults := []map[string]any{
+				{"4310046988783340008": float64(1)},
+			}
+
+			next := emitJSONToolCallDeltas(stubResults, 0, id, model, created, responses)
+
+			Expect(next).To(Equal(0),
+				"lastEmittedCount must NOT advance past a stub without a name "+
+					"— otherwise content emission gets permanently gated off")
+			Expect(drainChannel(responses)).To(BeEmpty(),
+				"no tool_call chunk should be emitted for a stub without a name")
+		})
+	})
+
+	// No-regression #1: the autoparser-correctly-working path. When the
+	// C++ autoparser classifies tool calls itself, the raw text result is
+	// cleared and ParseJSONIterative on it returns no results — this
+	// helper must be a no-op so the deferred end-of-stream code can emit
+	// the tool calls from TokenUsage.ChatDeltas.
+	Context("empty jsonResults (autoparser-correctly-working path)", func() {
+		It("is a no-op and leaves lastEmittedCount unchanged", func() {
+			responses := make(chan schema.OpenAIResponse, 4)
+			next := emitJSONToolCallDeltas(nil, 0, id, model, created, responses)
+			Expect(next).To(Equal(0))
+			Expect(drainChannel(responses)).To(BeEmpty())
+		})
+
+		It("leaves a non-zero lastEmittedCount unchanged when later called with the same length", func() {
+			responses := make(chan schema.OpenAIResponse, 4)
+			results := []map[string]any{
+				{"name": "search", "arguments": map[string]any{"q": "hi"}},
+			}
+			// First call emits the one available tool call.
+			next := emitJSONToolCallDeltas(results, 0, id, model, created, responses)
+			Expect(next).To(Equal(1))
+			Expect(drainChannel(responses)).To(HaveLen(1))
+
+			// Subsequent chunks haven't grown the slice — must be a no-op.
+			next = emitJSONToolCallDeltas(results, next, id, model, created, responses)
+			Expect(next).To(Equal(1))
+			Expect(drainChannel(responses)).To(BeEmpty())
+		})
+	})
+
+	// No-regression #2: the normal completed-JSON path. When the model
+	// emits a real, complete tool call as JSON in raw content (e.g. qwen3
+	// without jinja but with tools), we should emit exactly one tool_call
+	// SSE chunk on the first call and become a no-op on later calls.
+	Context("single complete tool call", func() {
+		It("emits one tool_call chunk and bumps lastEmittedCount to 1", func() {
+			responses := make(chan schema.OpenAIResponse, 4)
+			results := []map[string]any{
+				{
+					"name": "search",
+					"arguments": map[string]any{
+						"q": "hello",
+					},
+				},
+			}
+
+			next := emitJSONToolCallDeltas(results, 0, id, model, created, responses)
+
+			Expect(next).To(Equal(1))
+			out := drainChannel(responses)
+			Expect(out).To(HaveLen(1))
+			Expect(nameOf(out[0])).To(Equal("search"))
+			Expect(out[0].Choices[0].Delta.ToolCalls[0].FunctionCall.Arguments).
+				To(ContainSubstring(`"q":"hello"`))
+		})
+
+		It("accepts arguments already serialized as a string", func() {
+			responses := make(chan schema.OpenAIResponse, 4)
+			results := []map[string]any{
+				{
+					"name":      "search",
+					"arguments": `{"q":"hello"}`,
+				},
+			}
+
+			emitJSONToolCallDeltas(results, 0, id, model, created, responses)
+
+			out := drainChannel(responses)
+			Expect(out).To(HaveLen(1))
+			Expect(out[0].Choices[0].Delta.ToolCalls[0].FunctionCall.Arguments).
+				To(Equal(`{"q":"hello"}`))
+		})
+	})
+
+	// No-regression #3: multiple tool calls (parallel tool calling).
+	// Both must be emitted, lastEmittedCount must end at 2.
+	Context("multiple complete tool calls", func() {
+		It("emits one chunk per tool call and bumps lastEmittedCount to len(results)", func() {
+			responses := make(chan schema.OpenAIResponse, 8)
+			results := []map[string]any{
+				{"name": "search", "arguments": map[string]any{"q": "a"}},
+				{"name": "browse", "arguments": map[string]any{"url": "b"}},
+			}
+
+			next := emitJSONToolCallDeltas(results, 0, id, model, created, responses)
+
+			Expect(next).To(Equal(2))
+			out := drainChannel(responses)
+			Expect(out).To(HaveLen(2))
+			Expect(nameOf(out[0])).To(Equal("search"))
+			Expect(nameOf(out[1])).To(Equal("browse"))
+		})
+	})
+
+	// The streaming-tail case: incremental chunks. First parse returns
+	// one complete tool call followed by a partial stub; later chunks
+	// complete the second tool call. We must emit the first immediately
+	// and the second on the later call — without ever bumping past the
+	// stub mid-stream.
+	Context("partial tail behind a real tool call", func() {
+		It("emits the complete entry, stops at the stub, and resumes once the tail completes", func() {
+			responses := make(chan schema.OpenAIResponse, 8)
+
+			// Chunk 1: one real call + a partial stub for the next.
+			chunk1 := []map[string]any{
+				{"name": "search", "arguments": map[string]any{"q": "a"}},
+				{"4310046988783340008": float64(1)},
+			}
+			next := emitJSONToolCallDeltas(chunk1, 0, id, model, created, responses)
+			Expect(next).To(Equal(1),
+				"must NOT advance to 2 — the stub at index 1 has no usable name")
+			out := drainChannel(responses)
+			Expect(out).To(HaveLen(1))
+			Expect(nameOf(out[0])).To(Equal("search"))
+
+			// Chunk 2: the stub completes into a real call.
+			chunk2 := []map[string]any{
+				{"name": "search", "arguments": map[string]any{"q": "a"}},
+				{"name": "browse", "arguments": map[string]any{"url": "b"}},
+			}
+			next = emitJSONToolCallDeltas(chunk2, next, id, model, created, responses)
+			Expect(next).To(Equal(2))
+			out = drainChannel(responses)
+			Expect(out).To(HaveLen(1))
+			Expect(nameOf(out[0])).To(Equal("browse"))
+		})
+	})
+})

core/http/endpoints/openai/image.go

@@ -6,7 +6,6 @@ import (
 	"encoding/json"
 	"fmt"
 	"io"
-	"net/http"
 	"net/url"
 	"os"
 	"path/filepath"
@@ -16,15 +15,18 @@ import (
 
 	"github.com/google/uuid"
 	"github.com/labstack/echo/v4"
+
 	"github.com/mudler/LocalAI/core/config"
 	"github.com/mudler/LocalAI/core/http/middleware"
 	"github.com/mudler/LocalAI/core/schema"
 
 	"github.com/mudler/LocalAI/core/backend"
 
+	"github.com/mudler/xlog"
+
+	"github.com/mudler/LocalAI/pkg/httpclient"
 	model "github.com/mudler/LocalAI/pkg/model"
 	"github.com/mudler/LocalAI/pkg/utils"
-	"github.com/mudler/xlog"
 )
 
 func downloadFile(url string) (string, error) {
@@ -33,7 +35,7 @@ func downloadFile(url string) (string, error) {
 	}
 
 	// Get the data
-	resp, err := http.Get(url)
+	resp, err := httpclient.New(httpclient.WithFollowRedirects()).Get(url)
 	if err != nil {
 		return "", err
 	}

core/http/endpoints/openresponses/responses.go

@@ -95,7 +95,7 @@ func ResponsesEndpoint(cl *config.ModelConfigLoader, ml *model.ModelLoader, eval
 
 		// Add instructions as system message if provided
 		if input.Instructions != "" {
-			messages = append([]schema.Message{{Role: "system", StringContent: input.Instructions}}, messages...)
+			messages = append([]schema.Message{{Role: "system", Content: input.Instructions, StringContent: input.Instructions}}, messages...)
 		}
 
 		// Handle tools
@@ -299,7 +299,7 @@ func convertORInputToMessages(input any, cfg *config.ModelConfig) ([]schema.Mess
 	switch v := input.(type) {
 	case string:
 		// Simple string = user message
-		return []schema.Message{{Role: "user", StringContent: v}}, nil
+		return []schema.Message{{Role: "user", Content: v, StringContent: v}}, nil
 	case []any:
 		// Array of items
 		for _, itemRaw := range v {
@@ -309,6 +309,16 @@ func convertORInputToMessages(input any, cfg *config.ModelConfig) ([]schema.Mess
 			}
 
 			itemType, _ := itemMap["type"].(string)
+			// OpenAI SDK helpers (e.g. client.responses.create(input=[{"role":...,"content":...}]))
+			// send message items without a "type" discriminator. Treat a bare {role, content}
+			// object as type:"message" so the chat-completions and responses paths agree.
+			if itemType == "" {
+				if _, hasRole := itemMap["role"].(string); hasRole {
+					if _, hasContent := itemMap["content"]; hasContent {
+						itemType = "message"
+					}
+				}
+			}
 			switch itemType {
 			case "message":
 				msg, err := convertORMessageItem(itemMap, cfg)

core/http/endpoints/openresponses/responses_convert_test.go

@@ -0,0 +1,62 @@
+package openresponses
+
+import (
+	"github.com/mudler/LocalAI/core/config"
+
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+)
+
+// Regression for mudler/LocalAI#10039. convertORInputToMessages must populate
+// both Content and StringContent: the templating fallback path reads
+// StringContent, while the UseTokenizerTemplate path serialises Content via
+// Messages.ToProto(). Leaving Content nil produced an empty prompt on any model
+// without a Go-side template.chat_message block (the default for imported GGUFs).
+var _ = Describe("convertORInputToMessages", func() {
+	cfg := &config.ModelConfig{}
+
+	It("populates both Content and StringContent for plain string input", func() {
+		msgs, err := convertORInputToMessages("Hello", cfg)
+		Expect(err).NotTo(HaveOccurred())
+		Expect(msgs).To(HaveLen(1))
+		Expect(msgs[0].Role).To(Equal("user"))
+		Expect(msgs[0].StringContent).To(Equal("Hello"))
+		Expect(msgs[0].Content).To(Equal("Hello"))
+	})
+
+	It("accepts a bare {role, content} item without a type discriminator", func() {
+		// The OpenAI Python SDK helper client.responses.create(input=[{...}])
+		// sends message items with no "type" field. They must not be dropped.
+		input := []any{
+			map[string]any{"role": "user", "content": "Hi there"},
+		}
+		msgs, err := convertORInputToMessages(input, cfg)
+		Expect(err).NotTo(HaveOccurred())
+		Expect(msgs).To(HaveLen(1))
+		Expect(msgs[0].Role).To(Equal("user"))
+		Expect(msgs[0].StringContent).To(Equal("Hi there"))
+		Expect(msgs[0].Content).To(Equal("Hi there"))
+	})
+
+	It("still populates both fields for an explicit type:message item", func() {
+		input := []any{
+			map[string]any{"type": "message", "role": "user", "content": "Typed"},
+		}
+		msgs, err := convertORInputToMessages(input, cfg)
+		Expect(err).NotTo(HaveOccurred())
+		Expect(msgs).To(HaveLen(1))
+		Expect(msgs[0].StringContent).To(Equal("Typed"))
+		Expect(msgs[0].Content).To(Equal("Typed"))
+	})
+
+	It("does not treat a non-message item (no content key) as a message", func() {
+		// An item with neither a known type nor a {role, content} shape must
+		// keep falling through unchanged — no behaviour change for such inputs.
+		input := []any{
+			map[string]any{"role": "user"},
+		}
+		msgs, err := convertORInputToMessages(input, cfg)
+		Expect(err).NotTo(HaveOccurred())
+		Expect(msgs).To(BeEmpty())
+	})
+})

core/http/middleware/request.go

@@ -310,6 +310,26 @@ func mergeOpenAIRequestAndModelConfig(config *config.ModelConfig, input *schema.
 		config.Temperature = input.Temperature
 	}
 
+	// Map the per-request reasoning_effort onto the reasoning toggle the
+	// backend reads (enable_thinking metadata, set in gRPCPredictOpts).
+	// "none" disables thinking for this request - the use case from #10072,
+	// running a single Qwen3-style model and turning reasoning off per
+	// request. Any explicit effort level enables thinking, UNLESS the model
+	// config explicitly disabled it (DisableReasoning==true wins): an
+	// operator who deliberately turned reasoning off should not be overridden
+	// by a request. A value of "none" always disables, since that never
+	// conflicts with a config that also disables.
+	switch strings.ToLower(input.ReasoningEffort) {
+	case "none":
+		disable := true
+		config.ReasoningConfig.DisableReasoning = &disable
+	case "minimal", "low", "medium", "high":
+		if config.ReasoningConfig.DisableReasoning == nil || !*config.ReasoningConfig.DisableReasoning {
+			enable := false
+			config.ReasoningConfig.DisableReasoning = &enable
+		}
+	}
+
 	// Collapse the modern max_completion_tokens alias into the
 	// legacy Maxtokens field so downstream code reads exactly one.
 	// MaxCompletionTokens wins on conflict — it's the canonical

core/http/middleware/request_test.go

@@ -597,3 +597,137 @@ var _ = Describe("SetModelAndConfig tool_choice parsing (chat completions)", fun
 		})
 	})
 })
+
+// These tests cover the per-request reasoning_effort -> enable_thinking mapping.
+// The merge lives in mergeOpenAIRequestAndModelConfig (called from
+// SetOpenAIRequest), so they drive the full middleware chain like the
+// production /v1/chat/completions route does. The block builds its own app per
+// test so the model config can be varied (some cases need reasoning.disable set
+// in the model YAML to assert that an explicit config disable wins).
+//
+// Mapping under test (issue #10072):
+//   - reasoning_effort=none                 -> DisableReasoning=true
+//   - reasoning_effort=low/medium/high      -> DisableReasoning=false, UNLESS the
+//     model config explicitly set true
+//   - empty / unrecognized                  -> no change
+var _ = Describe("SetModelAndConfig reasoning_effort parsing (chat completions)", func() {
+	var modelDir string
+
+	BeforeEach(func() {
+		var err error
+		modelDir, err = os.MkdirTemp("", "localai-test-models-*")
+		Expect(err).ToNot(HaveOccurred())
+	})
+
+	AfterEach(func() {
+		_ = os.RemoveAll(modelDir)
+	})
+
+	// buildApp writes a model config with the given YAML body and returns an app
+	// plus a pointer to the captured per-request config.
+	buildApp := func(cfgYAML string) (*echo.Echo, **config.ModelConfig) {
+		Expect(os.WriteFile(filepath.Join(modelDir, "test-model.yaml"), []byte(cfgYAML), 0644)).To(Succeed())
+
+		ss := &system.SystemState{Model: system.Model{ModelsPath: modelDir}}
+		appConfig := config.NewApplicationConfig()
+		appConfig.SystemState = ss
+		mcl := config.NewModelConfigLoader(modelDir)
+		ml := model.NewModelLoader(ss)
+		re := NewRequestExtractor(mcl, ml, appConfig)
+
+		captured := new(*config.ModelConfig)
+		app := echo.New()
+		app.POST("/v1/chat/completions",
+			func(c echo.Context) error {
+				if cfg, ok := c.Get(CONTEXT_LOCALS_KEY_MODEL_CONFIG).(*config.ModelConfig); ok {
+					*captured = cfg
+				}
+				return c.String(http.StatusOK, "ok")
+			},
+			re.SetModelAndConfig(func() schema.LocalAIRequest { return new(schema.OpenAIRequest) }),
+			func(next echo.HandlerFunc) echo.HandlerFunc {
+				return func(c echo.Context) error {
+					if err := re.SetOpenAIRequest(c); err != nil {
+						return err
+					}
+					return next(c)
+				}
+			},
+		)
+		return app, captured
+	}
+
+	chatReq := func(effort string) string {
+		return `{"model":"test-model",` +
+			`"messages":[{"role":"user","content":"hi"}],` +
+			`"reasoning_effort":` + effort + `}`
+	}
+
+	plainCfg := "name: test-model\nbackend: llama-cpp\n"
+
+	It("disables thinking for reasoning_effort=none", func() {
+		app, captured := buildApp(plainCfg)
+		rec := postJSON(app, "/v1/chat/completions", chatReq(`"none"`))
+
+		Expect(rec.Code).To(Equal(http.StatusOK))
+		Expect(*captured).ToNot(BeNil())
+		Expect((*captured).ReasoningConfig.DisableReasoning).ToNot(BeNil())
+		Expect(*(*captured).ReasoningConfig.DisableReasoning).To(BeTrue())
+	})
+
+	It("enables thinking for reasoning_effort=high when config is unset", func() {
+		app, captured := buildApp(plainCfg)
+		rec := postJSON(app, "/v1/chat/completions", chatReq(`"high"`))
+
+		Expect(rec.Code).To(Equal(http.StatusOK))
+		Expect(*captured).ToNot(BeNil())
+		Expect((*captured).ReasoningConfig.DisableReasoning).ToNot(BeNil())
+		Expect(*(*captured).ReasoningConfig.DisableReasoning).To(BeFalse())
+	})
+
+	It("enables thinking for reasoning_effort=high when config explicitly set false", func() {
+		app, captured := buildApp(plainCfg + "reasoning:\n  disable: false\n")
+		rec := postJSON(app, "/v1/chat/completions", chatReq(`"high"`))
+
+		Expect(rec.Code).To(Equal(http.StatusOK))
+		Expect(*captured).ToNot(BeNil())
+		Expect((*captured).ReasoningConfig.DisableReasoning).ToNot(BeNil())
+		Expect(*(*captured).ReasoningConfig.DisableReasoning).To(BeFalse())
+	})
+
+	It("config wins: reasoning_effort=high cannot re-enable when config explicitly disabled", func() {
+		app, captured := buildApp(plainCfg + "reasoning:\n  disable: true\n")
+		rec := postJSON(app, "/v1/chat/completions", chatReq(`"high"`))
+
+		Expect(rec.Code).To(Equal(http.StatusOK))
+		Expect(*captured).ToNot(BeNil())
+		Expect((*captured).ReasoningConfig.DisableReasoning).ToNot(BeNil())
+		Expect(*(*captured).ReasoningConfig.DisableReasoning).To(BeTrue())
+	})
+
+	It("is a no-op when reasoning_effort is empty", func() {
+		app, captured := buildApp(plainCfg)
+		rec := postJSON(app, "/v1/chat/completions",
+			`{"model":"test-model","messages":[{"role":"user","content":"hi"}]}`)
+
+		Expect(rec.Code).To(Equal(http.StatusOK))
+		Expect(*captured).ToNot(BeNil())
+		Expect((*captured).ReasoningConfig.DisableReasoning).To(BeNil())
+	})
+
+	It("is case-insensitive (None disables, HIGH enables)", func() {
+		app, captured := buildApp(plainCfg)
+		rec := postJSON(app, "/v1/chat/completions", chatReq(`"None"`))
+		Expect(rec.Code).To(Equal(http.StatusOK))
+		Expect(*captured).ToNot(BeNil())
+		Expect((*captured).ReasoningConfig.DisableReasoning).ToNot(BeNil())
+		Expect(*(*captured).ReasoningConfig.DisableReasoning).To(BeTrue())
+
+		app2, captured2 := buildApp(plainCfg)
+		rec2 := postJSON(app2, "/v1/chat/completions", chatReq(`"HIGH"`))
+		Expect(rec2.Code).To(Equal(http.StatusOK))
+		Expect(*captured2).ToNot(BeNil())
+		Expect((*captured2).ReasoningConfig.DisableReasoning).ToNot(BeNil())
+		Expect(*(*captured2).ReasoningConfig.DisableReasoning).To(BeFalse())
+	})
+})

core/http/react-ui/.nycrc.json

@@ -0,0 +1,8 @@
+{
+  "all": true,
+  "include": ["src/**"],
+  "extension": [".js", ".jsx"],
+  "reporter": ["text-summary", "json-summary", "html"],
+  "report-dir": "coverage",
+  "temp-dir": ".nyc_output"
+}

core/http/react-ui/bun.lock

@@ -32,15 +32,19 @@
         "yaml": "^2.8.3",
       },
       "devDependencies": {
+        "@bcoe/v8-coverage": "^1.0.2",
         "@eslint/js": "^9.27.0",
         "@playwright/test": "1.58.2",
-        "@vitejs/plugin-react": "^4.5.2",
+        "@vitejs/plugin-react": "^6.0.2",
         "eslint": "^9.27.0",
         "eslint-plugin-react-hooks": "^5.2.0",
         "eslint-plugin-react-refresh": "^0.4.20",
         "globals": "^16.1.0",
         "i18next-parser": "^9.4.0",
-        "vite": "^6.4.2",
+        "nyc": "^18.0.0",
+        "v8-to-istanbul": "^9.3.0",
+        "vite": "^8.0.14",
+        "vite-plugin-istanbul": "^9.0.0",
       },
     },
   },
@@ -61,8 +65,6 @@
 
     "@babel/helper-module-transforms": ["@babel/helper-module-transforms@7.28.6", "", { "dependencies": { "@babel/helper-module-imports": "^7.28.6", "@babel/helper-validator-identifier": "^7.28.5", "@babel/traverse": "^7.28.6" }, "peerDependencies": { "@babel/core": "^7.0.0" } }, "sha512-67oXFAYr2cDLDVGLXTEABjdBJZ6drElUSI7WKp70NrpyISso3plG9SAGEF6y7zbha/wOzUByWWTJvEDVNIUGcA=="],
 
-    "@babel/helper-plugin-utils": ["@babel/helper-plugin-utils@7.28.6", "", {}, "sha512-S9gzZ/bz83GRysI7gAD4wPT/AI3uCnY+9xn+Mx/KPs2JwHJIz1W8PZkg2cqyt3RNOBM8ejcXhV6y8Og7ly/Dug=="],
-
     "@babel/helper-string-parser": ["@babel/helper-string-parser@7.27.1", "", {}, "sha512-qMlSxKbpRlAridDExk92nSobyDdpPijUq2DW6oDnUqd0iOGxmQjyqhMIihI9+zv4LPyZdRje2cavWPbCbWm3eA=="],
 
     "@babel/helper-validator-identifier": ["@babel/helper-validator-identifier@7.28.5", "", {}, "sha512-qSs4ifwzKJSV39ucNjsvc6WVHs6b7S03sOh2OcHF9UHfVPqWWALUsNUVzhSBiItjRZoLHx7nIarVjqKVusUZ1Q=="],
@@ -73,10 +75,6 @@
 
     "@babel/parser": ["@babel/parser@7.29.0", "", { "dependencies": { "@babel/types": "^7.29.0" }, "bin": "./bin/babel-parser.js" }, "sha512-IyDgFV5GeDUVX4YdF/3CPULtVGSXXMLh1xVIgdCgxApktqnQV0r7/8Nqthg+8YLGaAtdyIlo2qIdZrbCv4+7ww=="],
 
-    "@babel/plugin-transform-react-jsx-self": ["@babel/plugin-transform-react-jsx-self@7.27.1", "", { "dependencies": { "@babel/helper-plugin-utils": "^7.27.1" }, "peerDependencies": { "@babel/core": "^7.0.0-0" } }, "sha512-6UzkCs+ejGdZ5mFFC/OCUrv028ab2fp1znZmCZjAOBKiBK2jXD1O+BPSfX8X2qjJ75fZBMSnQn3Rq2mrBJK2mw=="],
-
-    "@babel/plugin-transform-react-jsx-source": ["@babel/plugin-transform-react-jsx-source@7.27.1", "", { "dependencies": { "@babel/helper-plugin-utils": "^7.27.1" }, "peerDependencies": { "@babel/core": "^7.0.0-0" } }, "sha512-zbwoTsBruTeKB9hSq73ha66iFeJHuaFkUbwvqElnygoNbj/jHRsSeokowZFN3CZ64IvEqcmmkVe89OPXc7ldAw=="],
-
     "@babel/runtime": ["@babel/runtime@7.29.2", "", {}, "sha512-JiDShH45zKHWyGe4ZNVRrCjBz8Nh9TMmZG1kh4QTK8hCBTWBi8Da+i7s1fJw7/lYpM4ccepSNfqzZ/QvABBi5g=="],
 
     "@babel/template": ["@babel/template@7.28.6", "", { "dependencies": { "@babel/code-frame": "^7.28.6", "@babel/parser": "^7.28.6", "@babel/types": "^7.28.6" } }, "sha512-YA6Ma2KsCdGb+WC6UpBVFJGXL58MDA6oyONbjyF/+5sBgxY/dwkhLogbMT2GXXyU84/IhRw/2D1Os1B/giz+BQ=="],
@@ -85,6 +83,8 @@
 
     "@babel/types": ["@babel/types@7.29.0", "", { "dependencies": { "@babel/helper-string-parser": "^7.27.1", "@babel/helper-validator-identifier": "^7.28.5" } }, "sha512-LwdZHpScM4Qz8Xw2iKSzS+cfglZzJGvofQICy7W7v4caru4EaAmyUuO6BGrbyQ2mYV11W0U8j5mBhd14dd3B0A=="],
 
+    "@bcoe/v8-coverage": ["@bcoe/v8-coverage@1.0.2", "", {}, "sha512-6zABk/ECA/QYSCQ1NGiVwwbQerUCZ+TQbp64Q3AgmfNvurHH0j8TtXa1qbShXA6qqkpAj4V5W8pP6mLe1mcMqA=="],
+
     "@codemirror/autocomplete": ["@codemirror/autocomplete@6.20.1", "", { "dependencies": { "@codemirror/language": "^6.0.0", "@codemirror/state": "^6.0.0", "@codemirror/view": "^6.17.0", "@lezer/common": "^1.0.0" } }, "sha512-1cvg3Vz1dSSToCNlJfRA2WSI4ht3K+WplO0UMOgmUYPivCyy2oueZY6Lx7M9wThm7SDUBViRmuT+OG/i8+ON9A=="],
 
     "@codemirror/commands": ["@codemirror/commands@6.10.3", "", { "dependencies": { "@codemirror/language": "^6.0.0", "@codemirror/state": "^6.6.0", "@codemirror/view": "^6.27.0", "@lezer/common": "^1.1.0" } }, "sha512-JFRiqhKu+bvSkDLI+rUhJwSxQxYb759W5GBezE8Uc8mHLqC9aV/9aTC7yJSqCtB3F00pylrLCwnyS91Ap5ej4Q=="],
@@ -101,6 +101,12 @@
 
     "@codemirror/view": ["@codemirror/view@6.40.0", "", { "dependencies": { "@codemirror/state": "^6.6.0", "crelt": "^1.0.6", "style-mod": "^4.1.0", "w3c-keyname": "^2.2.4" } }, "sha512-WA0zdU7xfF10+5I3HhUUq3kqOx3KjqmtQ9lqZjfK7jtYk4G72YW9rezcSywpaUMCWOMlq+6E0pO1IWg1TNIhtg=="],
 
+    "@emnapi/core": ["@emnapi/core@1.10.0", "", { "dependencies": { "@emnapi/wasi-threads": "1.2.1", "tslib": "^2.4.0" } }, "sha512-yq6OkJ4p82CAfPl0u9mQebQHKPJkY7WrIuk205cTYnYe+k2Z8YBh11FrbRG/H6ihirqcacOgl2BIO8oyMQLeXw=="],
+
+    "@emnapi/runtime": ["@emnapi/runtime@1.10.0", "", { "dependencies": { "tslib": "^2.4.0" } }, "sha512-ewvYlk86xUoGI0zQRNq/mC+16R1QeDlKQy21Ki3oSYXNgLb45GV1P6A0M+/s6nyCuNDqe5VpaY84BzXGwVbwFA=="],
+
+    "@emnapi/wasi-threads": ["@emnapi/wasi-threads@1.2.1", "", { "dependencies": { "tslib": "^2.4.0" } }, "sha512-uTII7OYF+/Mes/MrcIOYp5yOtSMLBWSIoLPpcgwipoiKbli6k322tcoFsxoIIxPDqW01SQGAgko4EzZi2BNv2w=="],
+
     "@esbuild/aix-ppc64": ["@esbuild/aix-ppc64@0.25.12", "", { "os": "aix", "cpu": "ppc64" }, "sha512-Hhmwd6CInZ3dwpuGTF8fJG6yoWmsToE+vYgD4nytZVxcu1ulHpUQRAB1UJ8+N1Am3Mz4+xOByoQoSZf4D+CpkA=="],
 
     "@esbuild/android-arm": ["@esbuild/android-arm@0.25.12", "", { "os": "android", "cpu": "arm" }, "sha512-VJ+sKvNA/GE7Ccacc9Cha7bpS8nyzVv0jdVgwNDaR4gDMC/2TTRc33Ip8qrNYUcpkOHUT5OZ0bUcNNVZQ9RLlg=="],
@@ -191,6 +197,10 @@
 
     "@isaacs/cliui": ["@isaacs/cliui@8.0.2", "", { "dependencies": { "string-width": "^5.1.2", "string-width-cjs": "npm:string-width@^4.2.0", "strip-ansi": "^7.0.1", "strip-ansi-cjs": "npm:strip-ansi@^6.0.1", "wrap-ansi": "^8.1.0", "wrap-ansi-cjs": "npm:wrap-ansi@^7.0.0" } }, "sha512-O8jcjabXaleOG9DQ0+ARXWZBTfnP4WNAqzuiJK7ll44AmxGKv/J2M4TPjxjY3znBCfvBXFzucm1twdyFybFqEA=="],
 
+    "@istanbuljs/load-nyc-config": ["@istanbuljs/load-nyc-config@1.1.0", "", { "dependencies": { "camelcase": "^5.3.1", "find-up": "^4.1.0", "get-package-type": "^0.1.0", "js-yaml": "^3.13.1", "resolve-from": "^5.0.0" } }, "sha512-VjeHSlIzpv/NyD3N0YuHfXOPDIixcA1q2ZV98wsMqcYlPmv2n3Yb2lYP9XMElnaFVXg5A7YLTeLu6V84uQDjmQ=="],
+
+    "@istanbuljs/schema": ["@istanbuljs/schema@0.1.6", "", {}, "sha512-+Sg6GCR/wy1oSmQDFq4LQDAhm3ETKnorxN+y5nbLULOR3P0c14f2Wurzj3/xqPXtasLFfHd5iRFQ7AJt4KH2cw=="],
+
     "@jridgewell/gen-mapping": ["@jridgewell/gen-mapping@0.3.13", "", { "dependencies": { "@jridgewell/sourcemap-codec": "^1.5.0", "@jridgewell/trace-mapping": "^0.3.24" } }, "sha512-2kkt/7niJ6MgEPxF0bYdQ6etZaA+fQvDcLKckhy1yIQOzaoKjBBjSj63/aLVjYE3qhRt5dvM+uUyfCg6UKCBbA=="],
 
     "@jridgewell/remapping": ["@jridgewell/remapping@2.3.5", "", { "dependencies": { "@jridgewell/gen-mapping": "^0.3.5", "@jridgewell/trace-mapping": "^0.3.24" } }, "sha512-LI9u/+laYG4Ds1TDKSJW2YPrIlcVYOwi2fUC6xB43lueCjgxV4lffOCZCtYFiH6TNOX+tQKXx97T4IKHbhyHEQ=="],
@@ -215,72 +225,54 @@
 
     "@modelcontextprotocol/sdk": ["@modelcontextprotocol/sdk@1.27.1", "", { "dependencies": { "@hono/node-server": "^1.19.9", "ajv": "^8.17.1", "ajv-formats": "^3.0.1", "content-type": "^1.0.5", "cors": "^2.8.5", "cross-spawn": "^7.0.5", "eventsource": "^3.0.2", "eventsource-parser": "^3.0.0", "express": "^5.2.1", "express-rate-limit": "^8.2.1", "hono": "^4.11.4", "jose": "^6.1.3", "json-schema-typed": "^8.0.2", "pkce-challenge": "^5.0.0", "raw-body": "^3.0.0", "zod": "^3.25 || ^4.0", "zod-to-json-schema": "^3.25.1" }, "peerDependencies": { "@cfworker/json-schema": "^4.1.1" }, "optionalPeers": ["@cfworker/json-schema"] }, "sha512-sr6GbP+4edBwFndLbM60gf07z0FQ79gaExpnsjMGePXqFcSSb7t6iscpjk9DhFhwd+mTEQrzNafGP8/iGGFYaA=="],
 
+    "@napi-rs/wasm-runtime": ["@napi-rs/wasm-runtime@1.1.4", "", { "dependencies": { "@tybys/wasm-util": "^0.10.1" }, "peerDependencies": { "@emnapi/core": "^1.7.1", "@emnapi/runtime": "^1.7.1" } }, "sha512-3NQNNgA1YSlJb/kMH1ildASP9HW7/7kYnRI2szWJaofaS1hWmbGI4H+d3+22aGzXXN9IJ+n+GiFVcGipJP18ow=="],
+
+    "@oxc-project/types": ["@oxc-project/types@0.132.0", "", {}, "sha512-FESMOxil5Se014ui/Eq8fT5uHJo6nIRwH0PfJrZJXs6Gek3ZVFOrpUv3YIZT20m+extU98Hg1Ym72U58rlsxUQ=="],
+
     "@pkgjs/parseargs": ["@pkgjs/parseargs@0.11.0", "", {}, "sha512-+1VkjdD0QBLPodGrJUeqarH8VAIvQODIbwh9XpP5Syisf7YoQgsJKPNFoqqLQlu+VQ/tVSshMR6loPMn8U+dPg=="],
 
     "@playwright/test": ["@playwright/test@1.58.2", "", { "dependencies": { "playwright": "1.58.2" }, "bin": { "playwright": "cli.js" } }, "sha512-akea+6bHYBBfA9uQqSYmlJXn61cTa+jbO87xVLCWbTqbWadRVmhxlXATaOjOgcBaWU4ePo0wB41KMFv3o35IXA=="],
 
-    "@rolldown/pluginutils": ["@rolldown/pluginutils@1.0.0-beta.27", "", {}, "sha512-+d0F4MKMCbeVUJwG96uQ4SgAznZNSq93I3V+9NHA4OpvqG8mRCpGdKmK8l/dl02h2CCDHwW2FqilnTyDcAnqjA=="],
+    "@rolldown/binding-android-arm64": ["@rolldown/binding-android-arm64@1.0.2", "", { "os": "android", "cpu": "arm64" }, "sha512-ZS4D1JPGn/MYQN/SYDWftIE/nVsM8j/AFOYEzAoOE2O3NktQOZru+/vYXGbR/qtdLdIfGCP0lcoJiYVzsEz+iQ=="],
 
-    "@rollup/rollup-android-arm-eabi": ["@rollup/rollup-android-arm-eabi@4.59.0", "", { "os": "android", "cpu": "arm" }, "sha512-upnNBkA6ZH2VKGcBj9Fyl9IGNPULcjXRlg0LLeaioQWueH30p6IXtJEbKAgvyv+mJaMxSm1l6xwDXYjpEMiLMg=="],
+    "@rolldown/binding-darwin-arm64": ["@rolldown/binding-darwin-arm64@1.0.2", "", { "os": "darwin", "cpu": "arm64" }, "sha512-vdFA9+C/rekyGce7WqHs/xoT0ioZEWaOFyZLIV1mEeNFaFDUQrPIo8Vs2GvJ6eetb3rzDUtUBgzto3ExpXJB3w=="],
 
-    "@rollup/rollup-android-arm64": ["@rollup/rollup-android-arm64@4.59.0", "", { "os": "android", "cpu": "arm64" }, "sha512-hZ+Zxj3SySm4A/DylsDKZAeVg0mvi++0PYVceVyX7hemkw7OreKdCvW2oQ3T1FMZvCaQXqOTHb8qmBShoqk69Q=="],
+    "@rolldown/binding-darwin-x64": ["@rolldown/binding-darwin-x64@1.0.2", "", { "os": "darwin", "cpu": "x64" }, "sha512-BewSOwTHazv77DTYiAZXSqqKZ4KP/KonFisDMVU7PImxoWfB2aepnPhd2E4SWz3zDzYgDNbs6jBmTdgNnF02GA=="],
 
-    "@rollup/rollup-darwin-arm64": ["@rollup/rollup-darwin-arm64@4.59.0", "", { "os": "darwin", "cpu": "arm64" }, "sha512-W2Psnbh1J8ZJw0xKAd8zdNgF9HRLkdWwwdWqubSVk0pUuQkoHnv7rx4GiF9rT4t5DIZGAsConRE3AxCdJ4m8rg=="],
+    "@rolldown/binding-freebsd-x64": ["@rolldown/binding-freebsd-x64@1.0.2", "", { "os": "freebsd", "cpu": "x64" }, "sha512-m41o7M0YWtUdqk61Tb+jnKb2rN++iRdIASlExkUoKfIAH30DOHCB8fVLzSUpbWHHU8esmEioY62PxzexE8MBuA=="],
 
-    "@rollup/rollup-darwin-x64": ["@rollup/rollup-darwin-x64@4.59.0", "", { "os": "darwin", "cpu": "x64" }, "sha512-ZW2KkwlS4lwTv7ZVsYDiARfFCnSGhzYPdiOU4IM2fDbL+QGlyAbjgSFuqNRbSthybLbIJ915UtZBtmuLrQAT/w=="],
+    "@rolldown/binding-linux-arm-gnueabihf": ["@rolldown/binding-linux-arm-gnueabihf@1.0.2", "", { "os": "linux", "cpu": "arm" }, "sha512-jcojB9H7W/jS29pMKWAK1N+fU99vXodHDTatS3b3y/XSOCiHo0kkA74pL3jJmkoQtYpOCxDvaKs1fo2Ij/1X5w=="],
 
-    "@rollup/rollup-freebsd-arm64": ["@rollup/rollup-freebsd-arm64@4.59.0", "", { "os": "freebsd", "cpu": "arm64" }, "sha512-EsKaJ5ytAu9jI3lonzn3BgG8iRBjV4LxZexygcQbpiU0wU0ATxhNVEpXKfUa0pS05gTcSDMKpn3Sx+QB9RlTTA=="],
+    "@rolldown/binding-linux-arm64-gnu": ["@rolldown/binding-linux-arm64-gnu@1.0.2", "", { "os": "linux", "cpu": "arm64" }, "sha512-1jn6qDU5iiOgFgygDzKUuKP0maTi0/f1+sBLgvij/76C77Nm3ts6ufz9Bjg5q5dduxiUIxtq86JIoBvo1xQ4Ig=="],
 
-    "@rollup/rollup-freebsd-x64": ["@rollup/rollup-freebsd-x64@4.59.0", "", { "os": "freebsd", "cpu": "x64" }, "sha512-d3DuZi2KzTMjImrxoHIAODUZYoUUMsuUiY4SRRcJy6NJoZ6iIqWnJu9IScV9jXysyGMVuW+KNzZvBLOcpdl3Vg=="],
+    "@rolldown/binding-linux-arm64-musl": ["@rolldown/binding-linux-arm64-musl@1.0.2", "", { "os": "linux", "cpu": "arm64" }, "sha512-QVLO/czFMdoMFSqlX3bcswcJNm/23r+qoa/jgtmFc/qEp6/jXmIkDjF/XIo8dPfGaiwy1xfQn8o77L79GeXFgw=="],
 
-    "@rollup/rollup-linux-arm-gnueabihf": ["@rollup/rollup-linux-arm-gnueabihf@4.59.0", "", { "os": "linux", "cpu": "arm" }, "sha512-t4ONHboXi/3E0rT6OZl1pKbl2Vgxf9vJfWgmUoCEVQVxhW6Cw/c8I6hbbu7DAvgp82RKiH7TpLwxnJeKv2pbsw=="],
+    "@rolldown/binding-linux-ppc64-gnu": ["@rolldown/binding-linux-ppc64-gnu@1.0.2", "", { "os": "linux", "cpu": "ppc64" }, "sha512-hgO5Abm0w5UL6FEa2iFnZqo2KlK7TQ5QhV5x09hujBf7t5KzHQ1VmfPuTpqRy/rNlSxua3eWH374xxiVrP+lcA=="],
 
-    "@rollup/rollup-linux-arm-musleabihf": ["@rollup/rollup-linux-arm-musleabihf@4.59.0", "", { "os": "linux", "cpu": "arm" }, "sha512-CikFT7aYPA2ufMD086cVORBYGHffBo4K8MQ4uPS/ZnY54GKj36i196u8U+aDVT2LX4eSMbyHtyOh7D7Zvk2VvA=="],
+    "@rolldown/binding-linux-s390x-gnu": ["@rolldown/binding-linux-s390x-gnu@1.0.2", "", { "os": "linux", "cpu": "s390x" }, "sha512-fy8rXxuYEu602abC8MUNaPjYLIFzReOaEIEMKMUa0rFEUxNpVXhs15KSSQ4qlqSaM7B6rcj9rDZgADh/IGDzLQ=="],
 
-    "@rollup/rollup-linux-arm64-gnu": ["@rollup/rollup-linux-arm64-gnu@4.59.0", "", { "os": "linux", "cpu": "arm64" }, "sha512-jYgUGk5aLd1nUb1CtQ8E+t5JhLc9x5WdBKew9ZgAXg7DBk0ZHErLHdXM24rfX+bKrFe+Xp5YuJo54I5HFjGDAA=="],
+    "@rolldown/binding-linux-x64-gnu": ["@rolldown/binding-linux-x64-gnu@1.0.2", "", { "os": "linux", "cpu": "x64" }, "sha512-0+bOkiQ779+r1WpoHOWHqncvyySci0vKph+myNDYb+im6meJAzHQXay6oEgnkHuUGouM1LKTZwqKpBow6Kj7CQ=="],
 
-    "@rollup/rollup-linux-arm64-musl": ["@rollup/rollup-linux-arm64-musl@4.59.0", "", { "os": "linux", "cpu": "arm64" }, "sha512-peZRVEdnFWZ5Bh2KeumKG9ty7aCXzzEsHShOZEFiCQlDEepP1dpUl/SrUNXNg13UmZl+gzVDPsiCwnV1uI0RUA=="],
+    "@rolldown/binding-linux-x64-musl": ["@rolldown/binding-linux-x64-musl@1.0.2", "", { "os": "linux", "cpu": "x64" }, "sha512-mjSkrzZK5Qsl0a9d1JgILOiuZOSDTVdKENcSXBoqbzSrspLR/4/IRVDo5wd2GgZjNss/viBFJdeq+j7qH2nypw=="],
 
-    "@rollup/rollup-linux-loong64-gnu": ["@rollup/rollup-linux-loong64-gnu@4.59.0", "", { "os": "linux", "cpu": "none" }, "sha512-gbUSW/97f7+r4gHy3Jlup8zDG190AuodsWnNiXErp9mT90iCy9NKKU0Xwx5k8VlRAIV2uU9CsMnEFg/xXaOfXg=="],
+    "@rolldown/binding-openharmony-arm64": ["@rolldown/binding-openharmony-arm64@1.0.2", "", { "os": "none", "cpu": "arm64" }, "sha512-1v5vHasdfQAZoEHakBV72LIFAC9JjnymsiKxp+GEr/ma3+NJCPSaYK+qavInOovJkgwFrs7GccX2d6IgDA3Z5w=="],
 
-    "@rollup/rollup-linux-loong64-musl": ["@rollup/rollup-linux-loong64-musl@4.59.0", "", { "os": "linux", "cpu": "none" }, "sha512-yTRONe79E+o0FWFijasoTjtzG9EBedFXJMl888NBEDCDV9I2wGbFFfJQQe63OijbFCUZqxpHz1GzpbtSFikJ4Q=="],
+    "@rolldown/binding-wasm32-wasi": ["@rolldown/binding-wasm32-wasi@1.0.2", "", { "dependencies": { "@emnapi/core": "1.10.0", "@emnapi/runtime": "1.10.0", "@napi-rs/wasm-runtime": "^1.1.4" }, "cpu": "none" }, "sha512-mb1VobWn6NheziTk5/WEaR6AKVbrwT5sOi6C7zk3gy/pD1qtJfU1j4PgTo2NJnOtbL9Dl3Aeei8w9jJ7qC2jZQ=="],
 
-    "@rollup/rollup-linux-ppc64-gnu": ["@rollup/rollup-linux-ppc64-gnu@4.59.0", "", { "os": "linux", "cpu": "ppc64" }, "sha512-sw1o3tfyk12k3OEpRddF68a1unZ5VCN7zoTNtSn2KndUE+ea3m3ROOKRCZxEpmT9nsGnogpFP9x6mnLTCaoLkA=="],
+    "@rolldown/binding-win32-arm64-msvc": ["@rolldown/binding-win32-arm64-msvc@1.0.2", "", { "os": "win32", "cpu": "arm64" }, "sha512-SqKonF56vA/L2yHwHYcEp2P34URpOZ7d1fS635cTkpDnUtEGdUbhI6NzsPdqeSWvAAeGDrxjWjNmibDIdFf9/A=="],
 
-    "@rollup/rollup-linux-ppc64-musl": ["@rollup/rollup-linux-ppc64-musl@4.59.0", "", { "os": "linux", "cpu": "ppc64" }, "sha512-+2kLtQ4xT3AiIxkzFVFXfsmlZiG5FXYW7ZyIIvGA7Bdeuh9Z0aN4hVyXS/G1E9bTP/vqszNIN/pUKCk/BTHsKA=="],
+    "@rolldown/binding-win32-x64-msvc": ["@rolldown/binding-win32-x64-msvc@1.0.2", "", { "os": "win32", "cpu": "x64" }, "sha512-v7qRI7gXLRINcOGXt+7YmAZ6iFuyZVMIoXAxhd8oP+DR9dLfL9GfNIx7PLMxmhZdvq8waUJBQiWN9EKNy+TRBQ=="],
 
-    "@rollup/rollup-linux-riscv64-gnu": ["@rollup/rollup-linux-riscv64-gnu@4.59.0", "", { "os": "linux", "cpu": "none" }, "sha512-NDYMpsXYJJaj+I7UdwIuHHNxXZ/b/N2hR15NyH3m2qAtb/hHPA4g4SuuvrdxetTdndfj9b1WOmy73kcPRoERUg=="],
+    "@rolldown/pluginutils": ["@rolldown/pluginutils@1.0.1", "", {}, "sha512-2j9bGt5Jh8hj+vPtgzPtl72j0yRxHAyumoo6TNfAjsLB04UtpSvPbPcDcBMxz7n+9CYB0c1GxQFxYRg2jimqGw=="],
 
-    "@rollup/rollup-linux-riscv64-musl": ["@rollup/rollup-linux-riscv64-musl@4.59.0", "", { "os": "linux", "cpu": "none" }, "sha512-nLckB8WOqHIf1bhymk+oHxvM9D3tyPndZH8i8+35p/1YiVoVswPid2yLzgX7ZJP0KQvnkhM4H6QZ5m0LzbyIAg=="],
-
-    "@rollup/rollup-linux-s390x-gnu": ["@rollup/rollup-linux-s390x-gnu@4.59.0", "", { "os": "linux", "cpu": "s390x" }, "sha512-oF87Ie3uAIvORFBpwnCvUzdeYUqi2wY6jRFWJAy1qus/udHFYIkplYRW+wo+GRUP4sKzYdmE1Y3+rY5Gc4ZO+w=="],
-
-    "@rollup/rollup-linux-x64-gnu": ["@rollup/rollup-linux-x64-gnu@4.59.0", "", { "os": "linux", "cpu": "x64" }, "sha512-3AHmtQq/ppNuUspKAlvA8HtLybkDflkMuLK4DPo77DfthRb71V84/c4MlWJXixZz4uruIH4uaa07IqoAkG64fg=="],
-
-    "@rollup/rollup-linux-x64-musl": ["@rollup/rollup-linux-x64-musl@4.59.0", "", { "os": "linux", "cpu": "x64" }, "sha512-2UdiwS/9cTAx7qIUZB/fWtToJwvt0Vbo0zmnYt7ED35KPg13Q0ym1g442THLC7VyI6JfYTP4PiSOWyoMdV2/xg=="],
-
-    "@rollup/rollup-openbsd-x64": ["@rollup/rollup-openbsd-x64@4.59.0", "", { "os": "openbsd", "cpu": "x64" }, "sha512-M3bLRAVk6GOwFlPTIxVBSYKUaqfLrn8l0psKinkCFxl4lQvOSz8ZrKDz2gxcBwHFpci0B6rttydI4IpS4IS/jQ=="],
-
-    "@rollup/rollup-openharmony-arm64": ["@rollup/rollup-openharmony-arm64@4.59.0", "", { "os": "none", "cpu": "arm64" }, "sha512-tt9KBJqaqp5i5HUZzoafHZX8b5Q2Fe7UjYERADll83O4fGqJ49O1FsL6LpdzVFQcpwvnyd0i+K/VSwu/o/nWlA=="],
-
-    "@rollup/rollup-win32-arm64-msvc": ["@rollup/rollup-win32-arm64-msvc@4.59.0", "", { "os": "win32", "cpu": "arm64" }, "sha512-V5B6mG7OrGTwnxaNUzZTDTjDS7F75PO1ae6MJYdiMu60sq0CqN5CVeVsbhPxalupvTX8gXVSU9gq+Rx1/hvu6A=="],
-
-    "@rollup/rollup-win32-ia32-msvc": ["@rollup/rollup-win32-ia32-msvc@4.59.0", "", { "os": "win32", "cpu": "ia32" }, "sha512-UKFMHPuM9R0iBegwzKF4y0C4J9u8C6MEJgFuXTBerMk7EJ92GFVFYBfOZaSGLu6COf7FxpQNqhNS4c4icUPqxA=="],
-
-    "@rollup/rollup-win32-x64-gnu": ["@rollup/rollup-win32-x64-gnu@4.59.0", "", { "os": "win32", "cpu": "x64" }, "sha512-laBkYlSS1n2L8fSo1thDNGrCTQMmxjYY5G0WFWjFFYZkKPjsMBsgJfGf4TLxXrF6RyhI60L8TMOjBMvXiTcxeA=="],
-
-    "@rollup/rollup-win32-x64-msvc": ["@rollup/rollup-win32-x64-msvc@4.59.0", "", { "os": "win32", "cpu": "x64" }, "sha512-2HRCml6OztYXyJXAvdDXPKcawukWY2GpR5/nxKp4iBgiO3wcoEGkAaqctIbZcNB6KlUQBIqt8VYkNSj2397EfA=="],
-
-    "@types/babel__core": ["@types/babel__core@7.20.5", "", { "dependencies": { "@babel/parser": "^7.20.7", "@babel/types": "^7.20.7", "@types/babel__generator": "*", "@types/babel__template": "*", "@types/babel__traverse": "*" } }, "sha512-qoQprZvz5wQFJwMDqeseRXWv3rqMvhgpbXFfVyWhbx9X47POIA6i/+dXefEmZKoAgOaTdaIgNSMqMIU61yRyzA=="],
+    "@tybys/wasm-util": ["@tybys/wasm-util@0.10.2", "", { "dependencies": { "tslib": "^2.4.0" } }, "sha512-RoBvJ2X0wuKlWFIjrwffGw1IqZHKQqzIchKaadZZfnNpsAYp2mM0h36JtPCjNDAHGgYez/15uMBpfGwchhiMgg=="],
 
     "@types/babel__generator": ["@types/babel__generator@7.27.0", "", { "dependencies": { "@babel/types": "^7.0.0" } }, "sha512-ufFd2Xi92OAVPYsy+P4n7/U7e68fex0+Ee8gSG9KX7eo084CWiQ4sdxktvdl0bOPupXtVJPY19zk6EwWqUQ8lg=="],
 
-    "@types/babel__template": ["@types/babel__template@7.4.4", "", { "dependencies": { "@babel/parser": "^7.1.0", "@babel/types": "^7.0.0" } }, "sha512-h/NUaSyG5EyxBIp8YRxo4RMe2/qQgvyowRwVMzhYhBCONbW8PUsg4lkFMrhgZhUe5z3L3MiLDuvyJ/CaPa2A8A=="],
-
-    "@types/babel__traverse": ["@types/babel__traverse@7.28.0", "", { "dependencies": { "@babel/types": "^7.28.2" } }, "sha512-8PvcXf70gTDZBgt9ptxJ8elBeBjcLOAcOtoO/mPJjtji1+CdGbHgm77om1GrsPxsiE+uXIpNSK64UYaIwQXd4Q=="],
-
     "@types/estree": ["@types/estree@1.0.8", "", {}, "sha512-dWHzHa2WqEXI/O1E9OjrocMTKJl2mSrEolh1Iomrv6U+JuNwaHXsXx9bLu5gG7BUWFIN0skIQJQ/L1rIex4X6w=="],
 
+    "@types/istanbul-lib-coverage": ["@types/istanbul-lib-coverage@2.0.6", "", {}, "sha512-2QF/t/auWm0lsy8XtKVPG19v3sSOQlJe/YHZgfjb/KBBHOGSV+J2q/S671rcq9uTBrLAXmZpqJiaQbMT+zNU1w=="],
+
     "@types/json-schema": ["@types/json-schema@7.0.15", "", {}, "sha512-5+fP8P8MFNC+AyZCDxrB2pkZFPGzqQWUzpSeuuVLvm8VMcorNYavBqoFcxK8bQz4Qsbn4oUEEem4wDLfcysGHA=="],
 
     "@types/minimatch": ["@types/minimatch@3.0.5", "", {}, "sha512-Klz949h02Gz2uZCMGwDUSDS1YBlTdDDgbWHi+81l29tQALUtvz4rAYi5uoVhE5Lagoq6DeqAUlbrHvW/mXDgdQ=="],
@@ -289,7 +281,7 @@
 
     "@types/trusted-types": ["@types/trusted-types@2.0.7", "", {}, "sha512-ScaPdn1dQczgbl0QFTeTOmVHFULt394XJgOQNoyVhZ6r2vLnMLJfBPd53SB52T/3G36VI1/g2MZaX0cwDuXsfw=="],
 
-    "@vitejs/plugin-react": ["@vitejs/plugin-react@4.7.0", "", { "dependencies": { "@babel/core": "^7.28.0", "@babel/plugin-transform-react-jsx-self": "^7.27.1", "@babel/plugin-transform-react-jsx-source": "^7.27.1", "@rolldown/pluginutils": "1.0.0-beta.27", "@types/babel__core": "^7.20.5", "react-refresh": "^0.17.0" }, "peerDependencies": { "vite": "^4.2.0 || ^5.0.0 || ^6.0.0 || ^7.0.0" } }, "sha512-gUu9hwfWvvEDBBmgtAowQCojwZmJ5mcLn3aufeCsitijs3+f2NsrPtlAWIR6OPiqljl96GVCUbLe0HyqIpVaoA=="],
+    "@vitejs/plugin-react": ["@vitejs/plugin-react@6.0.2", "", { "dependencies": { "@rolldown/pluginutils": "^1.0.0" }, "peerDependencies": { "@rolldown/plugin-babel": "^0.1.7 || ^0.2.0", "babel-plugin-react-compiler": "^1.0.0", "vite": "^8.0.0" }, "optionalPeers": ["@rolldown/plugin-babel", "babel-plugin-react-compiler"] }, "sha512-DlSMqo4WhThw4vB8Mpn0Woe9J+Jfq1geJ61AKW0QEgLzGMNwtIMdxbDUzLxcun8W7NbJO0e2Jg/Nxm3cCSVzzg=="],
 
     "accepts": ["accepts@2.0.0", "", { "dependencies": { "mime-types": "^3.0.0", "negotiator": "^1.0.0" } }, "sha512-5cvg6CtKwfgdmVqY1WIiXKc3Q1bkRqGLi+2W/6ao+6Y7gu/RCwRuAhGEzh5B4KlszSuTLgZYuqFqo5bImjNKng=="],
 
@@ -297,16 +289,22 @@
 
     "acorn-jsx": ["acorn-jsx@5.3.2", "", { "peerDependencies": { "acorn": "^6.0.0 || ^7.0.0 || ^8.0.0" } }, "sha512-rq9s+JNhf0IChjtDXxllJ7g41oZk5SlXtp0LHwyA5cejwn7vKmKp4pPri6YEePv2PU65sAsegbXtIinmDFDXgQ=="],
 
+    "aggregate-error": ["aggregate-error@3.1.0", "", { "dependencies": { "clean-stack": "^2.0.0", "indent-string": "^4.0.0" } }, "sha512-4I7Td01quW/RpocfNayFdFVk1qSuoh0E7JrbRJ16nH01HhKFQ88INq9Sd+nd72zqRySlr9BmDA8xlEJ6vJMrYA=="],
+
     "ajv": ["ajv@6.14.0", "", { "dependencies": { "fast-deep-equal": "^3.1.1", "fast-json-stable-stringify": "^2.0.0", "json-schema-traverse": "^0.4.1", "uri-js": "^4.2.2" } }, "sha512-IWrosm/yrn43eiKqkfkHis7QioDleaXQHdDVPKg0FSwwd/DuvyX79TZnFOnYpB7dcsFAMmtFztZuXPDvSePkFw=="],
 
     "ajv-formats": ["ajv-formats@3.0.1", "", { "dependencies": { "ajv": "^8.0.0" } }, "sha512-8iUql50EUR+uUcdRQ3HDqa6EVyo3docL8g5WJ3FNcWmu62IbkGUue/pEyLBW8VGKKucTPgqeks4fIU1DA4yowQ=="],
 
-    "ansi-regex": ["ansi-regex@6.2.2", "", {}, "sha512-Bq3SmSpyFHaWjPk8If9yc6svM8c56dB5BAtW4Qbw5jHTwwXXcTLoRMkpDJp6VL0XzlWaCHTXrkFURMYmD0sLqg=="],
+    "ansi-regex": ["ansi-regex@5.0.1", "", {}, "sha512-quJQXlTSUGL2LH9SUXo8VwsY4soanhgo6LNSm84E1LBcE8s3O0wpdiRzyR9z/ZZJMlMWv37qOOb9pdJlMUEKFQ=="],
 
     "ansi-styles": ["ansi-styles@4.3.0", "", { "dependencies": { "color-convert": "^2.0.1" } }, "sha512-zbB9rCJAT1rbjiVDb2hqKFHNYLxgtk8NURxZ3IZwD3F6NtxbXZQCnnSi1Lkx+IDohdPlFp222wVALIheZJQSEg=="],
 
     "anymatch": ["anymatch@3.1.3", "", { "dependencies": { "normalize-path": "^3.0.0", "picomatch": "^2.0.4" } }, "sha512-KMReFUr0B4t+D+OBkjR3KYqvocp2XaSzO55UcB6mgQMd3KbcE+mWTyvVV7D/zsdEbNnV6acZUutkiHQXvTr1Rw=="],
 
+    "append-transform": ["append-transform@2.0.0", "", { "dependencies": { "default-require-extensions": "^3.0.0" } }, "sha512-7yeyCEurROLQJFv5Xj4lEGTy0borxepjFv1g22oAdqFu//SrAlDl1O1Nxx15SH1RoliUml6p8dwJW9jvZughhg=="],
+
+    "archy": ["archy@1.0.0", "", {}, "sha512-Xg+9RwCg/0p32teKdGMPTPnVXKD0w3DfHnFTficozsAgsvq2XenPJq/MYpzzQ/v8zrOyJn6Ds39VA4JIDwFfqw=="],
+
     "argparse": ["argparse@2.0.1", "", {}, "sha512-8+9WqebbFzpX9OR+Wa6O29asIogeRMzcGtAINdpMHHyAg10f05aSFVBbcEqGf/PXw1EjAZ+q2/bEBg3DvurK3Q=="],
 
     "b4a": ["b4a@1.8.1", "", { "peerDependencies": { "react-native-b4a": "*" }, "optionalPeers": ["react-native-b4a"] }, "sha512-aiqre1Nr0B/6DgE2N5vwTc+2/oQZ4Wh1t4NznYY4E00y8LCt6NqdRv81so00oo27D8MVKTpUa/MwUUtBLXCoDw=="],
@@ -341,12 +339,16 @@
 
     "bytes": ["bytes@3.1.2", "", {}, "sha512-/Nf7TyzTx6S3yRJObOAV7956r8cr2+Oj8AC5dt8wSP3BQAoeX58NoHyCU8P8zGkNXStjTSi6fzO6F0pBdcYbEg=="],
 
+    "caching-transform": ["caching-transform@4.0.0", "", { "dependencies": { "hasha": "^5.0.0", "make-dir": "^3.0.0", "package-hash": "^4.0.0", "write-file-atomic": "^3.0.0" } }, "sha512-kpqOvwXnjjN44D89K5ccQC+RUrsy7jB/XLlRrx0D7/2HNcTPqzsb6XgYoErwko6QsV184CA2YgS1fxDiiDZMWA=="],
+
     "call-bind-apply-helpers": ["call-bind-apply-helpers@1.0.2", "", { "dependencies": { "es-errors": "^1.3.0", "function-bind": "^1.1.2" } }, "sha512-Sp1ablJ0ivDkSzjcaJdxEunN5/XvksFJ2sMBFfq6x0ryhQV/2b/KwFe21cMpmHtPOSij8K99/wSfoEuTObmuMQ=="],
 
     "call-bound": ["call-bound@1.0.4", "", { "dependencies": { "call-bind-apply-helpers": "^1.0.2", "get-intrinsic": "^1.3.0" } }, "sha512-+ys997U96po4Kx/ABpBCqhA9EuxJaQWDQg7295H4hBphv3IZg0boBKuwYpt4YXp6MZ5AmZQnU/tyMTlRpaSejg=="],
 
     "callsites": ["callsites@3.1.0", "", {}, "sha512-P8BjAsXvZS+VIDUI11hHCQEv74YT67YUi5JJFNWIqL235sBmjX4+qx9Muvls5ivyNENctx46xQLQ3aTuE7ssaQ=="],
 
+    "camelcase": ["camelcase@5.3.1", "", {}, "sha512-L28STB170nwWS63UjtlEOE3dldQApaJXZkOI1uMFfzf3rRuPegHaHesyee+YxQ+W6SvRDQV6UrdOdRiR153wJg=="],
+
     "caniuse-lite": ["caniuse-lite@1.0.30001776", "", {}, "sha512-sg01JDPzZ9jGshqKSckOQthXnYwOEP50jeVFhaSFbZcOy05TiuuaffDOfcwtCisJ9kNQuLBFibYywv2Bgm9osw=="],
 
     "chalk": ["chalk@4.1.2", "", { "dependencies": { "ansi-styles": "^4.1.0", "supports-color": "^7.1.0" } }, "sha512-oKnbhFyRIXpUuez8iBMmyEa4nbj4IOQyuhc/wy9kY7/WVPcwIO9VA668Pu8RkO7+0G76SLROeyw9CpQ061i4mA=="],
@@ -355,6 +357,10 @@
 
     "cheerio-select": ["cheerio-select@2.1.0", "", { "dependencies": { "boolbase": "^1.0.0", "css-select": "^5.1.0", "css-what": "^6.1.0", "domelementtype": "^2.3.0", "domhandler": "^5.0.3", "domutils": "^3.0.1" } }, "sha512-9v9kG0LvzrlcungtnJtpGNxY+fzECQKhK4EGJX2vByejiMX84MFNQw4UxPJl3bFbTMw+Dfs37XaIkCwTZfLh4g=="],
 
+    "clean-stack": ["clean-stack@2.2.0", "", {}, "sha512-4diC9HaTE+KRAMWhDhrGOECgWZxoevMc5TlkObMqNSsVU62PYzXZ/SMTjzyGAFF1YusgxGcSWTEXBhp0CPwQ1A=="],
+
+    "cliui": ["cliui@6.0.0", "", { "dependencies": { "string-width": "^4.2.0", "strip-ansi": "^6.0.0", "wrap-ansi": "^6.2.0" } }, "sha512-t6wbgtoCXvAzst7QgXxJYqPt0usEfbgQdftEPbLL/cvv6HPE5VgvqCuAIDR0NgU52ds6rFwqrgakNLrHEjCbrQ=="],
+
     "clone": ["clone@2.1.2", "", {}, "sha512-3Pe/CF1Nn94hyhIYpjtiLhdCoEoz0DqQ+988E9gmeEdQZlojxnOb74wctFyuwWQHzqyf9X7C7MG8juUpqBJT8w=="],
 
     "color-convert": ["color-convert@2.0.1", "", { "dependencies": { "color-name": "~1.1.4" } }, "sha512-RRECPsj7iu/xb5oKYcsFHSppFNnsj/52OVTRKb4zP5onXwVF3zVmmToNcOfGC+CRDpfK/U584fMg38ZHCaElKQ=="],
@@ -365,13 +371,15 @@
 
     "commander": ["commander@12.1.0", "", {}, "sha512-Vw8qHK3bZM9y/P10u3Vib8o/DdkvA2OtPtZvD871QKjy74Wj1WSKFILMPRPSdUSx5RFK1arlJzEtA4PkFgnbuA=="],
 
+    "commondir": ["commondir@1.0.1", "", {}, "sha512-W9pAhw0ja1Edb5GVdIF1mjZw/ASI0AlShXM83UUGe2DVr5TdAPEA1OA8m/g8zWp9x6On7gqufY+FatDbC3MDQg=="],
+
     "concat-map": ["concat-map@0.0.1", "", {}, "sha512-/Srv4dswyQNBfohGpz9o6Yb3Gz3SrUDqBH5rTuhGR7ahtlbYKnVxw2bCFMRljaA7EXHaXZ8wsHdodFvbkhKmqg=="],
 
     "content-disposition": ["content-disposition@1.0.1", "", {}, "sha512-oIXISMynqSqm241k6kcQ5UwttDILMK4BiurCfGEREw6+X9jkkpEe5T9FZaApyLGGOnFuyMWZpdolTXMtvEJ08Q=="],
 
     "content-type": ["content-type@1.0.5", "", {}, "sha512-nTjqfcBFEipKdXCv4YDQWCfmcLZKm81ldF0pAopTvyrFGVbcR6P/VAAd5G7N+0tTr8QqiU0tFadD6FK4NtJwOA=="],
 
-    "convert-source-map": ["convert-source-map@2.0.0", "", {}, "sha512-Kvp459HrV2FEJ1CAsi1Ku+MY3kasH19TFykTz2xWmMeq6bk2NU3XXvfJ+Q61m0xktWwt+1HSYf3JZsTms3aRJg=="],
+    "convert-source-map": ["convert-source-map@1.9.0", "", {}, "sha512-ASFBup0Mz1uyiIjANan1jzLQami9z1PoYSZCiiYW2FczPbenXc45FZdBZLzOT+r6+iciuEModtmCti+hjaAk0A=="],
 
     "cookie": ["cookie@0.7.2", "", {}, "sha512-yki5XnKuf750l50uGTllt6kKILY4nQ1eNIQatoXEByZ5dWgnKqbnqmTrBE5B4N7lrMJKQ2ytWMiTO2o0v6Ew/w=="],
 
@@ -393,10 +401,16 @@
 
     "debug": ["debug@4.4.3", "", { "dependencies": { "ms": "^2.1.3" } }, "sha512-RGwwWnwQvkVfavKVt22FGLw+xYSdzARwm0ru6DhTVA3umU5hZc28V3kO4stgYryrTlLpuvgI9GiijltAjNbcqA=="],
 
+    "decamelize": ["decamelize@1.2.0", "", {}, "sha512-z2S+W9X73hAUUki+N+9Za2lBlun89zigOyGrsax+KUQ6wKW4ZoWpEYBkGhQjwAjjDCkWxhY0VKEhk8wzY7F5cA=="],
+
     "deep-is": ["deep-is@0.1.4", "", {}, "sha512-oIPzksmTg4/MriiaYGO+okXDT7ztn/w3Eptv/+gSIdMdKsJo0u4CfYNFJPy+4SKMuCqGw2wxnA+URMg3t8a/bQ=="],
 
+    "default-require-extensions": ["default-require-extensions@3.0.1", "", { "dependencies": { "strip-bom": "^4.0.0" } }, "sha512-eXTJmRbm2TIt9MgWTsOH1wEuhew6XGZcMeGKCtLedIg/NCsg1iBePXkceTdK4Fii7pzmN9tGsZhKzZ4h7O/fxw=="],
+
     "depd": ["depd@2.0.0", "", {}, "sha512-g7nH6P6dyDioJogAAGprGpCtVImJhpPk/roCzdb3fIh61/s/nPsfR6onyMwkCAR/OlC3yBC0lESvUoQEAssIrw=="],
 
+    "detect-libc": ["detect-libc@2.1.2", "", {}, "sha512-Btj2BOOO83o3WyH59e8MgXsxEQVcarkUOpEYrubB0urwnN10yQ364rsiByU11nZlqWYZm05i/of7io4mzihBtQ=="],
+
     "dom-serializer": ["dom-serializer@2.0.0", "", { "dependencies": { "domelementtype": "^2.3.0", "domhandler": "^5.0.2", "entities": "^4.2.0" } }, "sha512-wIkAryiqt/nV5EQKqQpo3SToSOV9J0DnbJqwK7Wv/Trc92zIAYZ4FlMu+JPFW1DfGFt81ZTCGgDEabffXeLyJg=="],
 
     "domelementtype": ["domelementtype@2.3.0", "", {}, "sha512-OLETBj6w0OsagBwdXnPdN0cnMfF9opN69co+7ZrbfPGrdpPVNBUj02spi6B1N7wChLQiPn4CSH/zJvXw56gmHw=="],
@@ -415,7 +429,7 @@
 
     "electron-to-chromium": ["electron-to-chromium@1.5.307", "", {}, "sha512-5z3uFKBWjiNR44nFcYdkcXjKMbg5KXNdciu7mhTPo9tB7NbqSNP2sSnGR+fqknZSCwKkBN+oxiiajWs4dT6ORg=="],
 
-    "emoji-regex": ["emoji-regex@9.2.2", "", {}, "sha512-L18DaJsXSUk2+42pv8mLs5jJT2hqFkFE4j21wOmgbUqsZ2hL72NsUU785g9RXgo3s0ZNgVl42TiHp3ZtOv/Vyg=="],
+    "emoji-regex": ["emoji-regex@8.0.0", "", {}, "sha512-MSjYzcWNOA0ewAHpz0MxpYFvwg6yjy1NG3xteoqz644VCo/RPgnr1/GGt+ic3iJTzQ8Eu3TdM14SawnVUmGE6A=="],
 
     "encodeurl": ["encodeurl@2.0.0", "", {}, "sha512-Q0n9HRi4m6JuGIV1eFlmvJB7ZEVxu93IrMyiMsGC0lrMJMWzRgx6WGquyfQgZVb31vhGgXnfmPNNXmxnOkRBrg=="],
 
@@ -433,6 +447,8 @@
 
     "es-object-atoms": ["es-object-atoms@1.1.1", "", { "dependencies": { "es-errors": "^1.3.0" } }, "sha512-FGgH2h8zKNim9ljj7dankFPcICIK9Cp5bm+c2gQSYePhpaG5+esrLODihIorn+Pe6FGJzWhXQotPv73jTaldXA=="],
 
+    "es6-error": ["es6-error@4.1.1", "", {}, "sha512-Um/+FxMr9CISWh0bi5Zv0iOD+4cFh5qLeks1qhAopKVAJw3drgKbKySikp7wGhDL0HPeaja0P5ULZrxLkniUVg=="],
+
     "esbuild": ["esbuild@0.25.12", "", { "optionalDependencies": { "@esbuild/aix-ppc64": "0.25.12", "@esbuild/android-arm": "0.25.12", "@esbuild/android-arm64": "0.25.12", "@esbuild/android-x64": "0.25.12", "@esbuild/darwin-arm64": "0.25.12", "@esbuild/darwin-x64": "0.25.12", "@esbuild/freebsd-arm64": "0.25.12", "@esbuild/freebsd-x64": "0.25.12", "@esbuild/linux-arm": "0.25.12", "@esbuild/linux-arm64": "0.25.12", "@esbuild/linux-ia32": "0.25.12", "@esbuild/linux-loong64": "0.25.12", "@esbuild/linux-mips64el": "0.25.12", "@esbuild/linux-ppc64": "0.25.12", "@esbuild/linux-riscv64": "0.25.12", "@esbuild/linux-s390x": "0.25.12", "@esbuild/linux-x64": "0.25.12", "@esbuild/netbsd-arm64": "0.25.12", "@esbuild/netbsd-x64": "0.25.12", "@esbuild/openbsd-arm64": "0.25.12", "@esbuild/openbsd-x64": "0.25.12", "@esbuild/openharmony-arm64": "0.25.12", "@esbuild/sunos-x64": "0.25.12", "@esbuild/win32-arm64": "0.25.12", "@esbuild/win32-ia32": "0.25.12", "@esbuild/win32-x64": "0.25.12" }, "bin": { "esbuild": "bin/esbuild" } }, "sha512-bbPBYYrtZbkt6Os6FiTLCTFxvq4tt3JKall1vRwshA3fdVztsLAatFaZobhkBC8/BrPetoa0oksYoKXoG4ryJg=="],
 
     "escalade": ["escalade@3.2.0", "", {}, "sha512-WUj2qlxaQtO4g6Pq5c29GTcWGDyd8itL8zTlipgECz3JesAiiOKotd8JU6otB3PACgG6xkJUyVhboMS+bje/jA=="],
@@ -453,6 +469,8 @@
 
     "espree": ["espree@10.4.0", "", { "dependencies": { "acorn": "^8.15.0", "acorn-jsx": "^5.3.2", "eslint-visitor-keys": "^4.2.1" } }, "sha512-j6PAQ2uUr79PZhBjP5C5fhl8e39FmRnOjsD5lGnWrFU8i2G776tBK7+nP8KuQUTTyAZUwfQqXAgrVH5MbH9CYQ=="],
 
+    "esprima": ["esprima@4.0.1", "", { "bin": { "esparse": "./bin/esparse.js", "esvalidate": "./bin/esvalidate.js" } }, "sha512-eGuFFw7Upda+g4p+QHvnW0RyTX/SVeJBDM/gCtMARO0cLuT2HcEKnTPvhjV6aGeqrCB/sbNop0Kszm0jsaWU4A=="],
+
     "esquery": ["esquery@1.7.0", "", { "dependencies": { "estraverse": "^5.1.0" } }, "sha512-Ap6G0WQwcU/LHsvLwON1fAQX9Zp0A2Y6Y/cJBl9r/JbW90Zyg4/zbG6zzKa2OTALELarYHmKu0GhpM5EO+7T0g=="],
 
     "esrecurse": ["esrecurse@4.3.0", "", { "dependencies": { "estraverse": "^5.2.0" } }, "sha512-KmfKL3b6G+RXvP8N1vr3Tq1kL/oCFgn2NYXEtqP8/L3pKapUA4G8cFVaoF3SU323CD4XypR/ffioHmkti6/Tag=="],
@@ -491,6 +509,8 @@
 
     "finalhandler": ["finalhandler@2.1.1", "", { "dependencies": { "debug": "^4.4.0", "encodeurl": "^2.0.0", "escape-html": "^1.0.3", "on-finished": "^2.4.1", "parseurl": "^1.3.3", "statuses": "^2.0.1" } }, "sha512-S8KoZgRZN+a5rNwqTxlZZePjT/4cnm0ROV70LedRHZ0p8u9fRID0hJUZQpkKLzro8LfmC8sx23bY6tVNxv8pQA=="],
 
+    "find-cache-dir": ["find-cache-dir@3.3.2", "", { "dependencies": { "commondir": "^1.0.1", "make-dir": "^3.0.2", "pkg-dir": "^4.1.0" } }, "sha512-wXZV5emFEjrridIgED11OoUKLxiYjAcqot/NJdAkOhlJ+vGzwhOAfcG5OX1jP+S0PcjEn8bdMJv+g2jwQ3Onig=="],
+
     "find-up": ["find-up@5.0.0", "", { "dependencies": { "locate-path": "^6.0.0", "path-exists": "^4.0.0" } }, "sha512-78/PXT1wlLLDgTzDs7sjq9hzz0vXD+zn+7wypEe4fXQxCmdmqfGsEPQxmiCSQI3ajFV91bVSsvNtrJRiW6nGng=="],
 
     "flat-cache": ["flat-cache@4.0.1", "", { "dependencies": { "flatted": "^3.2.9", "keyv": "^4.5.4" } }, "sha512-f7ccFPK3SXFHpx15UIGyRJ/FJQctuKZ0zVuN3frBo4HnK3cay9VEW0R6yPYFHC0AgqhukPzKjq22t5DmAyqGyw=="],
@@ -503,6 +523,8 @@
 
     "fresh": ["fresh@2.0.0", "", {}, "sha512-Rx/WycZ60HOaqLKAi6cHRKKI7zxWbJ31MhntmtwMoaTeF7XFH9hhBp8vITaMidfljRQ6eYWCKkaTK+ykVJHP2A=="],
 
+    "fromentries": ["fromentries@1.3.2", "", {}, "sha512-cHEpEQHUg0f8XdtZCc2ZAhrHzKzT0MrFUTcvx+hfxYu7rGMDc5SKoXFh+n4YigxsHXRzc6OrCshdR1bWH6HHyg=="],
+
     "fs-extra": ["fs-extra@11.3.4", "", { "dependencies": { "graceful-fs": "^4.2.0", "jsonfile": "^6.0.1", "universalify": "^2.0.0" } }, "sha512-CTXd6rk/M3/ULNQj8FBqBWHYBVYybQ3VPBw0xGKFe3tuH7ytT6ACnvzpIQ3UZtB8yvUKC2cXn1a+x+5EVQLovA=="],
 
     "fs-merger": ["fs-merger@3.2.1", "", { "dependencies": { "broccoli-node-api": "^1.7.0", "broccoli-node-info": "^2.1.0", "fs-extra": "^8.0.1", "fs-tree-diff": "^2.0.1", "walk-sync": "^2.2.0" } }, "sha512-AN6sX12liy0JE7C2evclwoo0aCG3PFulLjrTLsJpWh/2mM+DinhpSGqYLbHBBbIW1PLRNcFhJG8Axtz8mQW3ug=="],
@@ -519,11 +541,15 @@
 
     "gensync": ["gensync@1.0.0-beta.2", "", {}, "sha512-3hN7NaskYvMDLQY55gnW3NQ+mesEAepTqlg+VEbj7zzqEMBVNhzcGYYeqFo/TlYz6eQiFcp1HcsCZO+nGgS8zg=="],
 
+    "get-caller-file": ["get-caller-file@2.0.5", "", {}, "sha512-DyFP3BM/3YHTQOCUL/w0OZHR0lpKeGrxotcHWcqNEdnltqFwXVfhEBQ94eIo34AfQpo0rGki4cyIiftY06h2Fg=="],
+
     "get-intrinsic": ["get-intrinsic@1.3.0", "", { "dependencies": { "call-bind-apply-helpers": "^1.0.2", "es-define-property": "^1.0.1", "es-errors": "^1.3.0", "es-object-atoms": "^1.1.1", "function-bind": "^1.1.2", "get-proto": "^1.0.1", "gopd": "^1.2.0", "has-symbols": "^1.1.0", "hasown": "^2.0.2", "math-intrinsics": "^1.1.0" } }, "sha512-9fSjSaos/fRIVIp+xSJlE6lfwhES7LNtKaCBIamHsjr2na1BiABJPo0mOjjz8GJDURarmCPGqaiVg5mfjb98CQ=="],
 
+    "get-package-type": ["get-package-type@0.1.0", "", {}, "sha512-pjzuKtY64GYfWizNAJ0fr9VqttZkNiK2iS430LtIHzjBEr6bX8Am2zm4sW4Ro5wjWW5cAlRL1qAMTcXbjNAO2Q=="],
+
     "get-proto": ["get-proto@1.0.1", "", { "dependencies": { "dunder-proto": "^1.0.1", "es-object-atoms": "^1.0.0" } }, "sha512-sTSfBjoXBp89JvIKIefqw7U2CCebsc74kiY6awiGogKtoSGbgjYE/G/+l9sF3MWFPNc9IcoOC4ODfKHfxFmp0g=="],
 
-    "glob": ["glob@7.2.3", "", { "dependencies": { "fs.realpath": "^1.0.0", "inflight": "^1.0.4", "inherits": "2", "minimatch": "^3.1.1", "once": "^1.3.0", "path-is-absolute": "^1.0.0" } }, "sha512-nFR0zLpU2YCaRxwoCJvL6UvCH2JFyFVIvwTLsIf21AuHlMskA1hhTdk+LlYJtOlYt9v6dvszD2BGRqBL+iQK9Q=="],
+    "glob": ["glob@13.0.6", "", { "dependencies": { "minimatch": "^10.2.2", "minipass": "^7.1.3", "path-scurry": "^2.0.2" } }, "sha512-Wjlyrolmm8uDpm/ogGyXZXb1Z+Ca2B8NbJwqBVg0axK9GbBeoS7yGV6vjXnYdGm6X53iehEuxxbyiKp8QmN4Vw=="],
 
     "glob-parent": ["glob-parent@6.0.2", "", { "dependencies": { "is-glob": "^4.0.3" } }, "sha512-XxwI8EOhVQgWp6iDL+3b0r86f4d6AX6zSU55HfB4ydCEuXLXc5FcYeOu+nnGftS4TEju/11rt4KJPTMgbfmv4A=="],
 
@@ -541,6 +567,8 @@
 
     "has-symbols": ["has-symbols@1.1.0", "", {}, "sha512-1cDNdwJ2Jaohmb3sg4OmKaMBwuC48sYni5HUw2DvsC8LjGTLK9h+eb1X6RyuOHe4hT0ULCW68iomhjUoKUqlPQ=="],
 
+    "hasha": ["hasha@5.2.2", "", { "dependencies": { "is-stream": "^2.0.0", "type-fest": "^0.8.0" } }, "sha512-Hrp5vIK/xr5SkeN2onO32H0MgNZ0f17HRNH39WfL0SYUNOTZ5Lz1TJ8Pajo/87dYGEFlLMm7mIc/k/s6Bvz9HQ=="],
+
     "hasown": ["hasown@2.0.2", "", { "dependencies": { "function-bind": "^1.1.2" } }, "sha512-0hJU9SCPvmMzIBdZFqNPXWa6dqh7WdH0cII9y+CyS8rG3nL48Bclra9HmKhVVUHyPWNH5Y7xDwAB7bfgSjkUMQ=="],
 
     "heimdalljs": ["heimdalljs@0.2.6", "", { "dependencies": { "rsvp": "~3.2.1" } }, "sha512-o9bd30+5vLBvBtzCPwwGqpry2+n0Hi6H1+qwt6y+0kwRHGGF8TFIhJPmnuM0xO97zaKrDZMwO/V56fAnn8m/tA=="],
@@ -551,6 +579,8 @@
 
     "hono": ["hono@4.12.8", "", {}, "sha512-VJCEvtrezO1IAR+kqEYnxUOoStaQPGrCmX3j4wDTNOcD1uRPFpGlwQUIW8niPuvHXaTUxeOUl5MMDGrl+tmO9A=="],
 
+    "html-escaper": ["html-escaper@2.0.2", "", {}, "sha512-H2iMtd0I4Mt5eYiapRdIDjp+XzelXQ0tFE4JS7YFwFevXXMmOp9myNrUvCg0D6ws8iqkRPBfKHgbwig1SmlLfg=="],
+
     "html-parse-stringify": ["html-parse-stringify@3.0.1", "", { "dependencies": { "void-elements": "3.1.0" } }, "sha512-KknJ50kTInJ7qIScF3jeaFRpMpE8/lfiTdzf/twXyPBLAGrLRTmkz3AdTnKeh40X8k9L2fdYwEp/42WGXIRGcg=="],
 
     "htmlparser2": ["htmlparser2@10.1.0", "", { "dependencies": { "domelementtype": "^2.3.0", "domhandler": "^5.0.3", "domutils": "^3.2.2", "entities": "^7.0.1" } }, "sha512-VTZkM9GWRAtEpveh7MSF6SjjrpNVNNVJfFup7xTY3UpFtm67foy9HDVXneLtFVt4pMz5kZtgNcvCniNFb1hlEQ=="],
@@ -575,6 +605,8 @@
 
     "imurmurhash": ["imurmurhash@0.1.4", "", {}, "sha512-JmXMZ6wuvDmLiHEml9ykzqO6lwFbof0GG4IkcGaENdCRDDmMVnny7s5HsIgHCbaq0w2MyPhDqkhTUgS2LU2PHA=="],
 
+    "indent-string": ["indent-string@4.0.0", "", {}, "sha512-EdDDZu4A2OyIK7Lr/2zG+w5jmbuk1DVBnEwREQvBzspBJkCEbRa8GxU1lghYcaGJCnRWibjDXlq779X1/y5xwg=="],
+
     "inflight": ["inflight@1.0.6", "", { "dependencies": { "once": "^1.3.0", "wrappy": "1" } }, "sha512-k92I/b08q4wvFscXCLvqfsHCrjrF7yiXsQuIVvVE7N82W3+aqpzuUdBbfhWcy/FZR3/4IgflMgKLOsvPDrGCJA=="],
 
     "inherits": ["inherits@2.0.4", "", {}, "sha512-k/vGaX4/Yla3WzyMCvTQOXYeIHvqOKtnqBduzTHpzpQZzAskKMhZ2K+EnBiSM9zGSoIFeMpXKxa4dYeZIQqewQ=="],
@@ -595,12 +627,32 @@
 
     "is-promise": ["is-promise@4.0.0", "", {}, "sha512-hvpoI6korhJMnej285dSg6nu1+e6uxs7zG3BYAm5byqDsgJNWwxzM6z6iZiAgQR4TJ30JmBTOwqZUw3WlyH3AQ=="],
 
+    "is-stream": ["is-stream@2.0.1", "", {}, "sha512-hFoiJiTl63nn+kstHGBtewWSKnQLpyb155KHheA1l39uvtO9nWIop1p3udqPcUd/xbF1VLMO4n7OI6p7RbngDg=="],
+
+    "is-typedarray": ["is-typedarray@1.0.0", "", {}, "sha512-cyA56iCMHAh5CdzjJIa4aohJyeO1YbwLi3Jc35MmRU6poroFjIGZzUzupGiRPOjgHg9TLu43xbpwXk523fMxKA=="],
+
     "is-valid-glob": ["is-valid-glob@1.0.0", "", {}, "sha512-AhiROmoEFDSsjx8hW+5sGwgKVIORcXnrlAx/R0ZSeaPw70Vw0CqkGBBhHGL58Uox2eXnU1AnvXJl1XlyedO5bA=="],
 
+    "is-windows": ["is-windows@1.0.2", "", {}, "sha512-eXK1UInq2bPmjyX6e3VHIzMLobc4J94i4AWn+Hpq3OU5KkrRC96OAcR3PRJ/pGu6m8TRnBHP9dkXQVsT/COVIA=="],
+
     "isarray": ["isarray@1.0.0", "", {}, "sha512-VLghIWNM6ELQzo7zwmcg0NmTVyWKYjvIeM83yjp0wRDTmUnrM678fQbcKBo6n2CJEF0szoG//ytg+TKla89ALQ=="],
 
     "isexe": ["isexe@2.0.0", "", {}, "sha512-RHxMLp9lnKHGHRng9QFhRCMbYAcVpn69smSGcq3f36xjgVVWThj4qqLbTLlq7Ssj8B+fIQ1EuCEGI2lKsyQeIw=="],
 
+    "istanbul-lib-coverage": ["istanbul-lib-coverage@3.2.2", "", {}, "sha512-O8dpsF+r0WV/8MNRKfnmrtCWhuKjxrq2w+jpzBL5UZKTi2LeVWnWOmWRxFlesJONmc+wLAGvKQZEOanko0LFTg=="],
+
+    "istanbul-lib-hook": ["istanbul-lib-hook@3.0.0", "", { "dependencies": { "append-transform": "^2.0.0" } }, "sha512-Pt/uge1Q9s+5VAZ+pCo16TYMWPBIl+oaNIjgLQxcX0itS6ueeaA+pEfThZpH8WxhFgCiEb8sAJY6MdUKgiIWaQ=="],
+
+    "istanbul-lib-instrument": ["istanbul-lib-instrument@6.0.3", "", { "dependencies": { "@babel/core": "^7.23.9", "@babel/parser": "^7.23.9", "@istanbuljs/schema": "^0.1.3", "istanbul-lib-coverage": "^3.2.0", "semver": "^7.5.4" } }, "sha512-Vtgk7L/R2JHyyGW07spoFlB8/lpjiOLTjMdms6AFMraYt3BaJauod/NGrfnVG/y4Ix1JEuMRPDPEj2ua+zz1/Q=="],
+
+    "istanbul-lib-processinfo": ["istanbul-lib-processinfo@3.0.0", "", { "dependencies": { "archy": "^1.0.0", "cross-spawn": "^7.0.3", "istanbul-lib-coverage": "^3.2.0", "p-map": "^3.0.0", "rimraf": "^6.1.3", "uuid": "^8.3.2" } }, "sha512-P7nLXRRlo7Sqinty6lNa7+4o9jBUYGpqtejqCOZKfgXlRoxY/QArflcB86YO500Ahj4pDJEG34JjMRbQgePLnQ=="],
+
+    "istanbul-lib-report": ["istanbul-lib-report@3.0.1", "", { "dependencies": { "istanbul-lib-coverage": "^3.0.0", "make-dir": "^4.0.0", "supports-color": "^7.1.0" } }, "sha512-GCfE1mtsHGOELCU8e/Z7YWzpmybrx/+dSTfLrvY8qRmaY6zXTKWn6WQIjaAFw069icm6GVMNkgu0NzI4iPZUNw=="],
+
+    "istanbul-lib-source-maps": ["istanbul-lib-source-maps@4.0.1", "", { "dependencies": { "debug": "^4.1.1", "istanbul-lib-coverage": "^3.0.0", "source-map": "^0.6.1" } }, "sha512-n3s8EwkdFIJCG3BPKBYvskgXGoy88ARzvegkitk60NxRdwltLOTaH7CUiMRXvwYorl0Q712iEjcWB+fK/MrWVw=="],
+
+    "istanbul-reports": ["istanbul-reports@3.2.0", "", { "dependencies": { "html-escaper": "^2.0.0", "istanbul-lib-report": "^3.0.0" } }, "sha512-HGYWWS/ehqTV3xN10i23tkPkpH46MLCIMFNCaaKNavAXTF1RkqxawEPtnjnGZ6XKSInBKkiOA5BKS+aZiY3AvA=="],
+
     "jackspeak": ["jackspeak@3.4.3", "", { "dependencies": { "@isaacs/cliui": "^8.0.2" }, "optionalDependencies": { "@pkgjs/parseargs": "^0.11.0" } }, "sha512-OGlZQpz2yfahA/Rd1Y8Cd9SIEsqvXkLVoSw/cgwhnhFMDbsQFeZYoJJ7bIZBS9BcamUW96asq/npPWugM+RQBw=="],
 
     "jose": ["jose@6.2.2", "", {}, "sha512-d7kPDd34KO/YnzaDOlikGpOurfF0ByC2sEV4cANCtdqLlTfBlw2p14O/5d/zv40gJPbIQxfES3nSx1/oYNyuZQ=="],
@@ -629,13 +681,41 @@
 
     "levn": ["levn@0.4.1", "", { "dependencies": { "prelude-ls": "^1.2.1", "type-check": "~0.4.0" } }, "sha512-+bT2uH4E5LGE7h/n3evcS/sQlJXCpIp6ym8OWJ5eV6+67Dsql/LaaT7qJBAt2rzfoa/5QBGBhxDix1dMt2kQKQ=="],
 
+    "lightningcss": ["lightningcss@1.32.0", "", { "dependencies": { "detect-libc": "^2.0.3" }, "optionalDependencies": { "lightningcss-android-arm64": "1.32.0", "lightningcss-darwin-arm64": "1.32.0", "lightningcss-darwin-x64": "1.32.0", "lightningcss-freebsd-x64": "1.32.0", "lightningcss-linux-arm-gnueabihf": "1.32.0", "lightningcss-linux-arm64-gnu": "1.32.0", "lightningcss-linux-arm64-musl": "1.32.0", "lightningcss-linux-x64-gnu": "1.32.0", "lightningcss-linux-x64-musl": "1.32.0", "lightningcss-win32-arm64-msvc": "1.32.0", "lightningcss-win32-x64-msvc": "1.32.0" } }, "sha512-NXYBzinNrblfraPGyrbPoD19C1h9lfI/1mzgWYvXUTe414Gz/X1FD2XBZSZM7rRTrMA8JL3OtAaGifrIKhQ5yQ=="],
+
+    "lightningcss-android-arm64": ["lightningcss-android-arm64@1.32.0", "", { "os": "android", "cpu": "arm64" }, "sha512-YK7/ClTt4kAK0vo6w3X+Pnm0D2cf2vPHbhOXdoNti1Ga0al1P4TBZhwjATvjNwLEBCnKvjJc2jQgHXH0NEwlAg=="],
+
+    "lightningcss-darwin-arm64": ["lightningcss-darwin-arm64@1.32.0", "", { "os": "darwin", "cpu": "arm64" }, "sha512-RzeG9Ju5bag2Bv1/lwlVJvBE3q6TtXskdZLLCyfg5pt+HLz9BqlICO7LZM7VHNTTn/5PRhHFBSjk5lc4cmscPQ=="],
+
+    "lightningcss-darwin-x64": ["lightningcss-darwin-x64@1.32.0", "", { "os": "darwin", "cpu": "x64" }, "sha512-U+QsBp2m/s2wqpUYT/6wnlagdZbtZdndSmut/NJqlCcMLTWp5muCrID+K5UJ6jqD2BFshejCYXniPDbNh73V8w=="],
+
+    "lightningcss-freebsd-x64": ["lightningcss-freebsd-x64@1.32.0", "", { "os": "freebsd", "cpu": "x64" }, "sha512-JCTigedEksZk3tHTTthnMdVfGf61Fky8Ji2E4YjUTEQX14xiy/lTzXnu1vwiZe3bYe0q+SpsSH/CTeDXK6WHig=="],
+
+    "lightningcss-linux-arm-gnueabihf": ["lightningcss-linux-arm-gnueabihf@1.32.0", "", { "os": "linux", "cpu": "arm" }, "sha512-x6rnnpRa2GL0zQOkt6rts3YDPzduLpWvwAF6EMhXFVZXD4tPrBkEFqzGowzCsIWsPjqSK+tyNEODUBXeeVHSkw=="],
+
+    "lightningcss-linux-arm64-gnu": ["lightningcss-linux-arm64-gnu@1.32.0", "", { "os": "linux", "cpu": "arm64" }, "sha512-0nnMyoyOLRJXfbMOilaSRcLH3Jw5z9HDNGfT/gwCPgaDjnx0i8w7vBzFLFR1f6CMLKF8gVbebmkUN3fa/kQJpQ=="],
+
+    "lightningcss-linux-arm64-musl": ["lightningcss-linux-arm64-musl@1.32.0", "", { "os": "linux", "cpu": "arm64" }, "sha512-UpQkoenr4UJEzgVIYpI80lDFvRmPVg6oqboNHfoH4CQIfNA+HOrZ7Mo7KZP02dC6LjghPQJeBsvXhJod/wnIBg=="],
+
+    "lightningcss-linux-x64-gnu": ["lightningcss-linux-x64-gnu@1.32.0", "", { "os": "linux", "cpu": "x64" }, "sha512-V7Qr52IhZmdKPVr+Vtw8o+WLsQJYCTd8loIfpDaMRWGUZfBOYEJeyJIkqGIDMZPwPx24pUMfwSxxI8phr/MbOA=="],
+
+    "lightningcss-linux-x64-musl": ["lightningcss-linux-x64-musl@1.32.0", "", { "os": "linux", "cpu": "x64" }, "sha512-bYcLp+Vb0awsiXg/80uCRezCYHNg1/l3mt0gzHnWV9XP1W5sKa5/TCdGWaR/zBM2PeF/HbsQv/j2URNOiVuxWg=="],
+
+    "lightningcss-win32-arm64-msvc": ["lightningcss-win32-arm64-msvc@1.32.0", "", { "os": "win32", "cpu": "arm64" }, "sha512-8SbC8BR40pS6baCM8sbtYDSwEVQd4JlFTOlaD3gWGHfThTcABnNDBda6eTZeqbofalIJhFx0qKzgHJmcPTnGdw=="],
+
+    "lightningcss-win32-x64-msvc": ["lightningcss-win32-x64-msvc@1.32.0", "", { "os": "win32", "cpu": "x64" }, "sha512-Amq9B/SoZYdDi1kFrojnoqPLxYhQ4Wo5XiL8EVJrVsB8ARoC1PWW6VGtT0WKCemjy8aC+louJnjS7U18x3b06Q=="],
+
     "lilconfig": ["lilconfig@3.1.3", "", {}, "sha512-/vlFKAoH5Cgt3Ie+JLhRbwOsCQePABiU3tJ1egGvyQ+33R/vcwM2Zl2QR/LzjsBeItPt3oSVXapn+m4nQDvpzw=="],
 
     "locate-path": ["locate-path@6.0.0", "", { "dependencies": { "p-locate": "^5.0.0" } }, "sha512-iPZK6eYjbxRu3uB4/WZ3EsEIMJFMqAoopl3R+zuq0UjcAm/MO6KCweDgPfP3elTztoKP3KtnVHxTn2NHBSDVUw=="],
 
+    "lodash.flattendeep": ["lodash.flattendeep@4.4.0", "", {}, "sha512-uHaJFihxmJcEX3kT4I23ABqKKalJ/zDrDg0lsFtc1h+3uw49SIJ5beyhx5ExVRti3AvKoOJngIj7xz3oylPdWQ=="],
+
     "lodash.merge": ["lodash.merge@4.6.2", "", {}, "sha512-0KpjqXRVvrYyCsX1swR/XTK0va6VQkQM6MNo7PqW77ByjAhoARA8EfrP1N4+KlKj8YS0ZUCtRT/YUuhyYDujIQ=="],
 
-    "lru-cache": ["lru-cache@5.1.1", "", { "dependencies": { "yallist": "^3.0.2" } }, "sha512-KpNARQA3Iwv+jTA0utUVVbrh+Jlrr1Fv0e56GGzAFOXN7dk/FviaDW8LHmK52DlcH4WP2n6gI8vN1aesBFgo9w=="],
+    "lru-cache": ["lru-cache@11.5.0", "", {}, "sha512-5YgH9UJd7wVb9hIouI2adWpgqrrICkt070Dnj8EUY1+B4B2P9eRLPAkAAo6NICA7CEhOIeBHl46u9zSNpNu7zA=="],
+
+    "make-dir": ["make-dir@3.1.0", "", { "dependencies": { "semver": "^6.0.0" } }, "sha512-g3FeP20LNwhALb/6Cz6Dd4F2ngze0jz7tbzrD2wAV+o9FeNHe4rL+yK2md0J/fiSf1sa1ADhXqi5+oVwOM/eGw=="],
 
     "marked": ["marked@15.0.12", "", { "bin": { "marked": "bin/marked.js" } }, "sha512-8dD6FusOQSrpv9Z1rdNMdlSgQOIP880DHqnohobOmYLElGEqAL/JvxvuxZO16r4HtjTlfPRDC1hbvxC9dPN2nA=="],
 
@@ -659,7 +739,7 @@
 
     "ms": ["ms@2.1.3", "", {}, "sha512-6FlzubTLZG3J2a/NVCAleEhjzq5oxgHyaCU9yYXvcLsvoVaHJq/s5xXI6/XXP6tz7R9xAOtHnSO/tXtF3WRTlA=="],
 
-    "nanoid": ["nanoid@3.3.11", "", { "bin": { "nanoid": "bin/nanoid.cjs" } }, "sha512-N8SpfPUnUp1bK+PMYW8qSWdl9U+wwNWI4QKxOYDy9JAro3WMX7p2OeVRF9v+347pnakNevPmiHhNmZ2HbFA76w=="],
+    "nanoid": ["nanoid@3.3.12", "", { "bin": { "nanoid": "bin/nanoid.cjs" } }, "sha512-ZB9RH/39qpq5Vu6Y+NmUaFhQR6pp+M2Xt76XBnEwDaGcVAqhlvxrl3B2bKS5D3NH3QR76v3aSrKaF/Kiy7lEtQ=="],
 
     "natural-compare": ["natural-compare@1.4.0", "", {}, "sha512-OWND8ei3VtNC9h7V60qff3SVobHr996CTwgxubgyQYEpg290h9J0buyECNNJexkFm5sOajh5G116RYA1c8ZMSw=="],
 
@@ -667,6 +747,8 @@
 
     "node-fetch": ["node-fetch@2.7.0", "", { "dependencies": { "whatwg-url": "^5.0.0" }, "peerDependencies": { "encoding": "^0.1.0" }, "optionalPeers": ["encoding"] }, "sha512-c4FRfUm/dbcWZ7U+1Wq0AwCyFL+3nt2bEw05wfxSz+DWpWsitgmSgYmy2dQdWyKC1694ELPqMs/YzUSNozLt8A=="],
 
+    "node-preload": ["node-preload@0.2.1", "", { "dependencies": { "process-on-spawn": "^1.0.0" } }, "sha512-RM5oyBy45cLEoHqCeh+MNuFAxO0vTFBLskvQbOKnEE7YTTSN4tbN8QWDIPQ6L+WvKsB/qLEGpYe2ZZ9d4W9OIQ=="],
+
     "node-releases": ["node-releases@2.0.36", "", {}, "sha512-TdC8FSgHz8Mwtw9g5L4gR/Sh9XhSP/0DEkQxfEFXOpiul5IiHgHan2VhYYb6agDSfp4KuvltmGApc8HMgUrIkA=="],
 
     "normalize-path": ["normalize-path@3.0.0", "", {}, "sha512-6eZs5Ls3WtCisHWp9S2GUy8dqkpGi4BVSz3GaqiE6ezub0512ESztXUwUB6C6IKbQkY2Pnb/mD4WYojCRwcwLA=="],
@@ -675,6 +757,8 @@
 
     "nth-check": ["nth-check@2.1.1", "", { "dependencies": { "boolbase": "^1.0.0" } }, "sha512-lqjrjmaOoAnWfMmBPL+XNnynZh2+swxiX3WUE0s4yEHI6m+AwrK2UZOimIRl3X/4QctVqS8AiZjFqyOGrMXb/w=="],
 
+    "nyc": ["nyc@18.0.0", "", { "dependencies": { "@istanbuljs/load-nyc-config": "^1.0.0", "@istanbuljs/schema": "^0.1.2", "caching-transform": "^4.0.0", "convert-source-map": "^1.7.0", "decamelize": "^1.2.0", "find-cache-dir": "^3.2.0", "find-up": "^4.1.0", "foreground-child": "^3.3.0", "get-package-type": "^0.1.0", "glob": "^13.0.6", "istanbul-lib-coverage": "^3.0.0", "istanbul-lib-hook": "^3.0.0", "istanbul-lib-instrument": "^6.0.2", "istanbul-lib-processinfo": "^3.0.0", "istanbul-lib-report": "^3.0.0", "istanbul-lib-source-maps": "^4.0.0", "istanbul-reports": "^3.0.2", "make-dir": "^3.0.0", "node-preload": "^0.2.1", "p-map": "^3.0.0", "process-on-spawn": "^1.0.0", "resolve-from": "^5.0.0", "rimraf": "^6.1.3", "signal-exit": "^3.0.2", "spawn-wrap": "^3.0.0", "test-exclude": "^8.0.0", "yargs": "^15.0.2" }, "bin": { "nyc": "bin/nyc.js" } }, "sha512-G5UyHinFkB1BxqGTrmZdB6uIYH0+v7ZnVssuflUDi+J+RhKWyAhRT1RCehBSI6jLFLuUUgFDyLt49mUtdO1XeQ=="],
+
     "object-assign": ["object-assign@4.1.1", "", {}, "sha512-rJgTQnkUnH1sFw8yT6VSU3zD3sWmu6sZhIseY8VX+GRu3P6F7Fu+JNDoXfklElbLJSnc3FUQHVe4cU5hj+BcUg=="],
 
     "object-inspect": ["object-inspect@1.13.4", "", {}, "sha512-W67iLl4J2EXEGTbfeHCffrjDfitvLANg0UlX3wFUUSTx92KXRFegMHUVgSqE+wvhAbi4WqjGg9czysTV2Epbew=="],
@@ -689,6 +773,12 @@
 
     "p-locate": ["p-locate@5.0.0", "", { "dependencies": { "p-limit": "^3.0.2" } }, "sha512-LaNjtRWUBY++zB5nE/NwcaoMylSPk+S+ZHNB1TzdbMJMny6dynpAGt7X/tl/QYq3TIeE6nxHppbo2LGymrG5Pw=="],
 
+    "p-map": ["p-map@3.0.0", "", { "dependencies": { "aggregate-error": "^3.0.0" } }, "sha512-d3qXVTF/s+W+CdJ5A29wywV2n8CQQYahlgz2bFiA+4eVNJbHJodPZ+/gXwPGh0bOqA+j8S+6+ckmvLGPk1QpxQ=="],
+
+    "p-try": ["p-try@2.2.0", "", {}, "sha512-R4nPAVTAU0B9D35/Gk3uJf/7XYbQcyohSKdvAxIRSNghFl4e71hVoGnBNQz9cWaXxO2I10KTC+3jMdvvoKw6dQ=="],
+
+    "package-hash": ["package-hash@4.0.0", "", { "dependencies": { "graceful-fs": "^4.1.15", "hasha": "^5.0.0", "lodash.flattendeep": "^4.4.0", "release-zalgo": "^1.0.0" } }, "sha512-whdkPIooSu/bASggZ96BWVvZTRMOFxnyUG5PnTSGKoJE2gd5mbVNmR2Nj20QFzxYYgAXpoqC+AiXzl+UMRh7zQ=="],
+
     "package-json-from-dist": ["package-json-from-dist@1.0.1", "", {}, "sha512-UEZIS3/by4OC8vL3P2dTXRETpebLI2NiI5vIrjaD/5UtrkFX/tNbwjTSRAGC/+7CAo2pIcBaRgWmcBBHcsaCIw=="],
 
     "parent-module": ["parent-module@1.0.1", "", { "dependencies": { "callsites": "^3.0.0" } }, "sha512-GQ2EWRpQV8/o+Aw8YqtfZZPfNRWZYkbidE9k5rpl/hC3vtHHBfGm2Ifi6qWV+coDGkrUKZAxE3Lot5kcsRlh+g=="],
@@ -709,26 +799,30 @@
 
     "path-posix": ["path-posix@1.0.0", "", {}, "sha512-1gJ0WpNIiYcQydgg3Ed8KzvIqTsDpNwq+cjBCssvBtuTWjEqY1AW+i+OepiEMqDCzyro9B2sLAe4RBPajMYFiA=="],
 
-    "path-scurry": ["path-scurry@1.11.1", "", { "dependencies": { "lru-cache": "^10.2.0", "minipass": "^5.0.0 || ^6.0.2 || ^7.0.0" } }, "sha512-Xa4Nw17FS9ApQFJ9umLiJS4orGjm7ZzwUrwamcGQuHSzDyth9boKDaycYdDcZDuqYATXw4HFXgaqWTctW/v1HA=="],
+    "path-scurry": ["path-scurry@2.0.2", "", { "dependencies": { "lru-cache": "^11.0.0", "minipass": "^7.1.2" } }, "sha512-3O/iVVsJAPsOnpwWIeD+d6z/7PmqApyQePUtCndjatj/9I5LylHvt5qluFaBT3I5h3r1ejfR056c+FCv+NnNXg=="],
 
     "path-to-regexp": ["path-to-regexp@8.3.0", "", {}, "sha512-7jdwVIRtsP8MYpdXSwOS0YdD0Du+qOoF/AEPIt88PcCFrZCzx41oxku1jD88hZBwbNUIEfpqvuhjFaMAqMTWnA=="],
 
     "picocolors": ["picocolors@1.1.1", "", {}, "sha512-xceH2snhtb5M9liqDsmEw56le376mTZkEX/jEb/RxNFyegNul7eNslCXP9FDj/Lcu0X8KEyMceP2ntpaHrDEVA=="],
 
-    "picomatch": ["picomatch@4.0.3", "", {}, "sha512-5gTmgEY/sqK6gFXLIsQNH19lWb4ebPDLA4SdLP7dsWkIXHWlG66oPuVvXSGFPppYZz8ZDZq0dYYrbHfBCVUb1Q=="],
+    "picomatch": ["picomatch@4.0.4", "", {}, "sha512-QP88BAKvMam/3NxH6vj2o21R6MjxZUAd6nlwAS/pnGvN9IVLocLHxGYIzFhg6fUQ+5th6P4dv4eW9jX3DSIj7A=="],
 
     "pkce-challenge": ["pkce-challenge@5.0.1", "", {}, "sha512-wQ0b/W4Fr01qtpHlqSqspcj3EhBvimsdh0KlHhH8HRZnMsEa0ea2fTULOXOS9ccQr3om+GcGRk4e+isrZWV8qQ=="],
 
+    "pkg-dir": ["pkg-dir@4.2.0", "", { "dependencies": { "find-up": "^4.0.0" } }, "sha512-HRDzbaKjC+AOWVXxAU/x54COGeIv9eb+6CkDSQoNTt4XyWoIJvuPsXizxu/Fr23EiekbtZwmh1IcIG/l/a10GQ=="],
+
     "playwright": ["playwright@1.58.2", "", { "dependencies": { "playwright-core": "1.58.2" }, "optionalDependencies": { "fsevents": "2.3.2" }, "bin": { "playwright": "cli.js" } }, "sha512-vA30H8Nvkq/cPBnNw4Q8TWz1EJyqgpuinBcHET0YVJVFldr8JDNiU9LaWAE1KqSkRYazuaBhTpB5ZzShOezQ6A=="],
 
     "playwright-core": ["playwright-core@1.58.2", "", { "bin": { "playwright-core": "cli.js" } }, "sha512-yZkEtftgwS8CsfYo7nm0KE8jsvm6i/PTgVtB8DL726wNf6H2IMsDuxCpJj59KDaxCtSnrWan2AeDqM7JBaultg=="],
 
-    "postcss": ["postcss@8.5.8", "", { "dependencies": { "nanoid": "^3.3.11", "picocolors": "^1.1.1", "source-map-js": "^1.2.1" } }, "sha512-OW/rX8O/jXnm82Ey1k44pObPtdblfiuWnrd8X7GJ7emImCOstunGbXUpp7HdBrFQX6rJzn3sPT397Wp5aCwCHg=="],
+    "postcss": ["postcss@8.5.15", "", { "dependencies": { "nanoid": "^3.3.12", "picocolors": "^1.1.1", "source-map-js": "^1.2.1" } }, "sha512-FfR8sjd4em2T6fb3I2MwAJU7HWVMr9zba+enmQeeWFfCbm+UOC/0X4DS8XtpUTMwWMGbjKYP7xjfNekzyGmB3A=="],
 
     "prelude-ls": ["prelude-ls@1.2.1", "", {}, "sha512-vkcDPrRZo1QZLbn5RLGPpg/WmIQ65qoWWhcGKf/b5eplkkarX0m9z8ppCat4mlOqUsWpyNuYgO3VRyrYHSzX5g=="],
 
     "process-nextick-args": ["process-nextick-args@2.0.1", "", {}, "sha512-3ouUOpQhtgrbOa17J7+uxOTpITYWaGP7/AhoR3+A+/1e9skrzelGi/dXzEYyvbxubEF6Wn2ypscTKiKJFFn1ag=="],
 
+    "process-on-spawn": ["process-on-spawn@1.1.0", "", { "dependencies": { "fromentries": "^1.2.0" } }, "sha512-JOnOPQ/8TZgjs1JIH/m9ni7FfimjNa/PRx7y/Wb5qdItsnhO0jE4AT7fC0HjC28DUQWDr50dwSYZLdRMlqDq3Q=="],
+
     "promise-map-series": ["promise-map-series@0.3.0", "", {}, "sha512-3npG2NGhTc8BWBolLLf8l/92OxMGaRLbqvIh9wjCHhDXNvk4zsxaTaCpiCunW09qWPrN2zeNSNwRLVBrQQtutA=="],
 
     "proxy-addr": ["proxy-addr@2.0.7", "", { "dependencies": { "forwarded": "0.2.0", "ipaddr.js": "1.9.1" } }, "sha512-llQsMLSUDUPT44jdrU/O37qlnifitDP+ZwrmmZcoSKyLKvtZxpyV0n2/bD/N4tBAAZ/gJEdZU7KMraoK1+XYAg=="],
@@ -749,29 +843,33 @@
 
     "react-i18next": ["react-i18next@17.0.6", "", { "dependencies": { "@babel/runtime": "^7.29.2", "html-parse-stringify": "^3.0.1", "use-sync-external-store": "^1.6.0" }, "peerDependencies": { "i18next": ">= 26.0.1", "react": ">= 16.8.0", "typescript": "^5 || ^6" }, "optionalPeers": ["typescript"] }, "sha512-WzJ6SMKF+GTD7JZZqxSR1AKKmXjaSu39sClUrNlwxS4Tl7a99O+ltFy6yhPMO+wgZuxpQjJ2PZkfrQKmAqrLhw=="],
 
-    "react-refresh": ["react-refresh@0.17.0", "", {}, "sha512-z6F7K9bV85EfseRCp2bzrpyQ0Gkw1uLoCel9XBVWPg/TjRj94SkJzUTGfOa4bs7iJvBWtQG0Wq7wnI0syw3EBQ=="],
-
     "react-router": ["react-router@7.13.1", "", { "dependencies": { "cookie": "^1.0.1", "set-cookie-parser": "^2.6.0" }, "peerDependencies": { "react": ">=18", "react-dom": ">=18" }, "optionalPeers": ["react-dom"] }, "sha512-td+xP4X2/6BJvZoX6xw++A2DdEi++YypA69bJUV5oVvqf6/9/9nNlD70YO1e9d3MyamJEBQFEzk6mbfDYbqrSA=="],
 
     "react-router-dom": ["react-router-dom@7.13.1", "", { "dependencies": { "react-router": "7.13.1" }, "peerDependencies": { "react": ">=18", "react-dom": ">=18" } }, "sha512-UJnV3Rxc5TgUPJt2KJpo1Jpy0OKQr0AjgbZzBFjaPJcFOb2Y8jA5H3LT8HUJAiRLlWrEXWHbF1Z4SCZaQjWDHw=="],
 
     "readable-stream": ["readable-stream@2.3.8", "", { "dependencies": { "core-util-is": "~1.0.0", "inherits": "~2.0.3", "isarray": "~1.0.0", "process-nextick-args": "~2.0.0", "safe-buffer": "~5.1.1", "string_decoder": "~1.1.1", "util-deprecate": "~1.0.1" } }, "sha512-8p0AUk4XODgIewSi0l8Epjs+EVnWiK7NoDIEGU0HhE7+ZyY8D1IMY7odu5lRrFXGg71L15KG8QrPmum45RTtdA=="],
 
+    "release-zalgo": ["release-zalgo@1.0.0", "", { "dependencies": { "es6-error": "^4.0.1" } }, "sha512-gUAyHVHPPC5wdqX/LG4LWtRYtgjxyX78oanFNTMMyFEfOqdC54s3eE82imuWKbOeqYht2CrNf64Qb8vgmmtZGA=="],
+
     "remove-trailing-separator": ["remove-trailing-separator@1.1.0", "", {}, "sha512-/hS+Y0u3aOfIETiaiirUFwDBDzmXPvO+jAfKTitUngIPzdKc6Z0LoFjM/CK5PL4C+eKwHohlHAb6H0VFfmmUsw=="],
 
     "replace-ext": ["replace-ext@2.0.0", "", {}, "sha512-UszKE5KVK6JvyD92nzMn9cDapSk6w/CaFZ96CnmDMUqH9oowfxF/ZjRITD25H4DnOQClLA4/j7jLGXXLVKxAug=="],
 
+    "require-directory": ["require-directory@2.1.1", "", {}, "sha512-fGxEI7+wsG9xrvdjsrlmL22OMTTiHRwAMroiEeMgq8gzoLC/PQr7RsRDSTLUg/bZAZtF+TVIkHc6/4RIKrui+Q=="],
+
     "require-from-string": ["require-from-string@2.0.2", "", {}, "sha512-Xf0nWe6RseziFMu+Ap9biiUbmplq6S9/p+7w7YXP/JBHhrUDDUhwa+vANyubuqfZWTveU//DYVGsDG7RKL/vEw=="],
 
-    "resolve-from": ["resolve-from@4.0.0", "", {}, "sha512-pb/MYmXstAkysRFx8piNI1tGFNQIFA3vkE3Gq4EuA1dF6gHp/+vgZqsCGJapvy8N3Q+4o7FwvquPJcnZ7RYy4g=="],
+    "require-main-filename": ["require-main-filename@2.0.0", "", {}, "sha512-NKN5kMDylKuldxYLSUfrbo5Tuzh4hd+2E8NPPX02mZtn1VuREQToYe/ZdlJy+J3uCpfaiGF05e7B8W0iXbQHmg=="],
+
+    "resolve-from": ["resolve-from@5.0.0", "", {}, "sha512-qYg9KP24dD5qka9J47d0aVky0N+b4fTU89LN9iDnjB5waksiC49rvMB0PrUJQGoTmH50XPiqOvAjDfaijGxYZw=="],
 
     "resolve-options": ["resolve-options@2.0.0", "", { "dependencies": { "value-or-function": "^4.0.0" } }, "sha512-/FopbmmFOQCfsCx77BRFdKOniglTiHumLgwvd6IDPihy1GKkadZbgQJBcTb2lMzSR1pndzd96b1nZrreZ7+9/A=="],
 
     "reusify": ["reusify@1.1.0", "", {}, "sha512-g6QUff04oZpHs0eG5p83rFLhHeV00ug/Yf9nZM6fLeUrPguBTkTQOdpAWWspMh55TZfVQDPaN3NQJfbVRAxdIw=="],
 
-    "rimraf": ["rimraf@3.0.2", "", { "dependencies": { "glob": "^7.1.3" }, "bin": { "rimraf": "bin.js" } }, "sha512-JZkJMZkAGFFPP2YqXZXPbMlMBgsxzE8ILs4lMIX/2o0L9UBw9O/Y3o6wFw/i9YLapcUJWwqbi3kdxIPdC62TIA=="],
+    "rimraf": ["rimraf@6.1.3", "", { "dependencies": { "glob": "^13.0.3", "package-json-from-dist": "^1.0.1" }, "bin": { "rimraf": "dist/esm/bin.mjs" } }, "sha512-LKg+Cr2ZF61fkcaK1UdkH2yEBBKnYjTyWzTJT6KNPcSPaiT7HSdhtMXQuN5wkTX0Xu72KQ1l8S42rlmexS2hSA=="],
 
-    "rollup": ["rollup@4.59.0", "", { "dependencies": { "@types/estree": "1.0.8" }, "optionalDependencies": { "@rollup/rollup-android-arm-eabi": "4.59.0", "@rollup/rollup-android-arm64": "4.59.0", "@rollup/rollup-darwin-arm64": "4.59.0", "@rollup/rollup-darwin-x64": "4.59.0", "@rollup/rollup-freebsd-arm64": "4.59.0", "@rollup/rollup-freebsd-x64": "4.59.0", "@rollup/rollup-linux-arm-gnueabihf": "4.59.0", "@rollup/rollup-linux-arm-musleabihf": "4.59.0", "@rollup/rollup-linux-arm64-gnu": "4.59.0", "@rollup/rollup-linux-arm64-musl": "4.59.0", "@rollup/rollup-linux-loong64-gnu": "4.59.0", "@rollup/rollup-linux-loong64-musl": "4.59.0", "@rollup/rollup-linux-ppc64-gnu": "4.59.0", "@rollup/rollup-linux-ppc64-musl": "4.59.0", "@rollup/rollup-linux-riscv64-gnu": "4.59.0", "@rollup/rollup-linux-riscv64-musl": "4.59.0", "@rollup/rollup-linux-s390x-gnu": "4.59.0", "@rollup/rollup-linux-x64-gnu": "4.59.0", "@rollup/rollup-linux-x64-musl": "4.59.0", "@rollup/rollup-openbsd-x64": "4.59.0", "@rollup/rollup-openharmony-arm64": "4.59.0", "@rollup/rollup-win32-arm64-msvc": "4.59.0", "@rollup/rollup-win32-ia32-msvc": "4.59.0", "@rollup/rollup-win32-x64-gnu": "4.59.0", "@rollup/rollup-win32-x64-msvc": "4.59.0", "fsevents": "~2.3.2" }, "bin": { "rollup": "dist/bin/rollup" } }, "sha512-2oMpl67a3zCH9H79LeMcbDhXW/UmWG/y2zuqnF2jQq5uq9TbM9TVyXvA4+t+ne2IIkBdrLpAaRQAvo7YI/Yyeg=="],
+    "rolldown": ["rolldown@1.0.2", "", { "dependencies": { "@oxc-project/types": "=0.132.0", "@rolldown/pluginutils": "^1.0.0" }, "optionalDependencies": { "@rolldown/binding-android-arm64": "1.0.2", "@rolldown/binding-darwin-arm64": "1.0.2", "@rolldown/binding-darwin-x64": "1.0.2", "@rolldown/binding-freebsd-x64": "1.0.2", "@rolldown/binding-linux-arm-gnueabihf": "1.0.2", "@rolldown/binding-linux-arm64-gnu": "1.0.2", "@rolldown/binding-linux-arm64-musl": "1.0.2", "@rolldown/binding-linux-ppc64-gnu": "1.0.2", "@rolldown/binding-linux-s390x-gnu": "1.0.2", "@rolldown/binding-linux-x64-gnu": "1.0.2", "@rolldown/binding-linux-x64-musl": "1.0.2", "@rolldown/binding-openharmony-arm64": "1.0.2", "@rolldown/binding-wasm32-wasi": "1.0.2", "@rolldown/binding-win32-arm64-msvc": "1.0.2", "@rolldown/binding-win32-x64-msvc": "1.0.2" }, "bin": { "rolldown": "./bin/cli.mjs" } }, "sha512-oZx5zVDtVB44AW3eaifgDml1gWRDZGvjcfdxonE4swNPG98PrrXjaO/KrnUjzlMnztCCRVlUueA1kCXhARGk6g=="],
 
     "router": ["router@2.2.0", "", { "dependencies": { "debug": "^4.4.0", "depd": "^2.0.0", "is-promise": "^4.0.0", "parseurl": "^1.3.3", "path-to-regexp": "^8.0.0" } }, "sha512-nLTrUKm2UyiL7rlhapu/Zl45FwNgkZGaCpZbIHajDYgwlJCOzLSk+cIPAnsEqV955GjILJnKbdQC1nVPz+gAYQ=="],
 
@@ -783,12 +881,14 @@
 
     "scheduler": ["scheduler@0.27.0", "", {}, "sha512-eNv+WrVbKu1f3vbYJT/xtiF5syA5HPIMtf9IgY/nKg0sWqzAUEvqY/xm7OcZc/qafLx/iO9FgOmeSAp4v5ti/Q=="],
 
-    "semver": ["semver@6.3.1", "", { "bin": { "semver": "bin/semver.js" } }, "sha512-BR7VvDCVHO+q2xBEWskxS6DJE1qRnb7DxzUrogb71CWoSficBxYsiAGd+Kl0mmq/MprG9yArRkyrQxTO6XjMzA=="],
+    "semver": ["semver@7.8.1", "", { "bin": { "semver": "bin/semver.js" } }, "sha512-rkVq3IXh+4FDGch+KwzX3aV9W3kO54GyEgpvBzSyctDA6Xtd7RJQV1xmXbeQp5v7+VzLOfVqiutSE6GICgPFvg=="],
 
     "send": ["send@1.2.1", "", { "dependencies": { "debug": "^4.4.3", "encodeurl": "^2.0.0", "escape-html": "^1.0.3", "etag": "^1.8.1", "fresh": "^2.0.0", "http-errors": "^2.0.1", "mime-types": "^3.0.2", "ms": "^2.1.3", "on-finished": "^2.4.1", "range-parser": "^1.2.1", "statuses": "^2.0.2" } }, "sha512-1gnZf7DFcoIcajTjTwjwuDjzuz4PPcY2StKPlsGAQ1+YH20IRVrBaXSWmdjowTJ6u8Rc01PoYOGHXfP1mYcZNQ=="],
 
     "serve-static": ["serve-static@2.2.1", "", { "dependencies": { "encodeurl": "^2.0.0", "escape-html": "^1.0.3", "parseurl": "^1.3.3", "send": "^1.2.0" } }, "sha512-xRXBn0pPqQTVQiC8wyQrKs2MOlX24zQ0POGaj0kultvoOCstBQM5yvOhAVSUwOMjQtTvsPWoNCHfPGwaaQJhTw=="],
 
+    "set-blocking": ["set-blocking@2.0.0", "", {}, "sha512-KiKBS8AnWGEyLzofFfmvKwpdPzqiy16LvQfK3yv/fVH7Bj13/wl3JSR1J+rfgRE9q7xUJK4qvgS8raSOeLUehw=="],
+
     "set-cookie-parser": ["set-cookie-parser@2.7.2", "", {}, "sha512-oeM1lpU/UvhTxw+g3cIfxXHyJRc/uidd3yK1P242gzHds0udQBYzs3y8j4gCCW+ZJ7ad0yctld8RYO+bdurlvw=="],
 
     "setprototypeof": ["setprototypeof@1.2.0", "", {}, "sha512-E5LDX7Wrp85Kil5bhZv46j8jOeboKq5JMmYM3gVGdGH8xFpPWXUMsNrlODCrkoxMEeNi/XZIwuRvY4XNwYMJpw=="],
@@ -805,12 +905,16 @@
 
     "side-channel-weakmap": ["side-channel-weakmap@1.0.2", "", { "dependencies": { "call-bound": "^1.0.2", "es-errors": "^1.3.0", "get-intrinsic": "^1.2.5", "object-inspect": "^1.13.3", "side-channel-map": "^1.0.1" } }, "sha512-WPS/HvHQTYnHisLo9McqBHOJk2FkHO/tlpvldyrnem4aeQp4hai3gythswg6p01oSoTl58rcpiFAjF2br2Ak2A=="],
 
-    "signal-exit": ["signal-exit@4.1.0", "", {}, "sha512-bzyZ1e88w9O1iNJbKnOlvYTrWPDl46O1bG0D3XInv+9tkPrxrN8jUUTiFlDkkmKWgn1M6CfIA13SuGqOa9Korw=="],
+    "signal-exit": ["signal-exit@3.0.7", "", {}, "sha512-wnD2ZE+l+SPC/uoS0vXeE9L1+0wuaMqKlfz9AMUo38JsyLSBWSFcHR1Rri62LZc12vLr1gb3jl7iwQhgwpAbGQ=="],
 
     "sort-keys": ["sort-keys@5.1.0", "", { "dependencies": { "is-plain-obj": "^4.0.0" } }, "sha512-aSbHV0DaBcr7u0PVHXzM6NbZNAtrr9sF6+Qfs9UUVG7Ll3jQ6hHi8F/xqIIcn2rvIVbr0v/2zyjSdwSV47AgLQ=="],
 
+    "source-map": ["source-map@0.7.6", "", {}, "sha512-i5uvt8C3ikiWeNZSVZNWcfZPItFQOsYTUAOkcUPGd8DqDy1uOUikjt5dG+uRlwyvR108Fb9DOd4GvXfT0N2/uQ=="],
+
     "source-map-js": ["source-map-js@1.2.1", "", {}, "sha512-UXWMKhLOwVKb728IUtQPXxfYU+usdybtUrK/8uGE8CQMvrhOpwvzDBwj0QhSL7MQc7vIsISBG8VQ8+IDQxpfQA=="],
 
+    "spawn-wrap": ["spawn-wrap@3.0.0", "", { "dependencies": { "cross-spawn": "^7.0.6", "foreground-child": "^2.0.0", "is-windows": "^1.0.2", "make-dir": "^3.0.0", "rimraf": "^6.1.3", "signal-exit": "^3.0.2", "which": "^2.0.1" } }, "sha512-z+s5vv4KzFPJVddGab0xX2n7kQPGMdNUX5l9T8EJqsXdKTWpcxmAqWHpsgHEXoC1taGBCc7b79bi62M5kdbrxQ=="],
+
     "sprintf-js": ["sprintf-js@1.1.3", "", {}, "sha512-Oo+0REFV59/rz3gfJNKQiBlwfHaSESl1pcGyABQsnnIfWOFt6JNj5gCog2U6MLZ//IGYD+nA8nI+mTShREReaA=="],
 
     "statuses": ["statuses@2.0.2", "", {}, "sha512-DvEy55V3DB7uknRo+4iOGT5fP1slR8wQohVdknigZPMpMstaKJQWhwiYBACJE3Ul2pTnATihhBYnRhZQHGBiRw=="],
@@ -819,16 +923,18 @@
 
     "streamx": ["streamx@2.25.0", "", { "dependencies": { "events-universal": "^1.0.0", "fast-fifo": "^1.3.2", "text-decoder": "^1.1.0" } }, "sha512-0nQuG6jf1w+wddNEEXCF4nTg3LtufWINB5eFEN+5TNZW7KWJp6x87+JFL43vaAUPyCfH1wID+mNVyW6OHtFamg=="],
 
-    "string-width": ["string-width@5.1.2", "", { "dependencies": { "eastasianwidth": "^0.2.0", "emoji-regex": "^9.2.2", "strip-ansi": "^7.0.1" } }, "sha512-HnLOCR3vjcY8beoNLtcjZ5/nxn2afmME6lhrDrebokqMap+XbeW8n9TXpPDOqdGK5qcI3oT0GKTW6wC7EMiVqA=="],
+    "string-width": ["string-width@4.2.3", "", { "dependencies": { "emoji-regex": "^8.0.0", "is-fullwidth-code-point": "^3.0.0", "strip-ansi": "^6.0.1" } }, "sha512-wKyQRQpjJ0sIp62ErSZdGsjMJWsap5oRNihHhu6G7JVO/9jIB6UyevL+tXuOqrng8j/cxKTWyWUwvSTriiZz/g=="],
 
     "string-width-cjs": ["string-width@4.2.3", "", { "dependencies": { "emoji-regex": "^8.0.0", "is-fullwidth-code-point": "^3.0.0", "strip-ansi": "^6.0.1" } }, "sha512-wKyQRQpjJ0sIp62ErSZdGsjMJWsap5oRNihHhu6G7JVO/9jIB6UyevL+tXuOqrng8j/cxKTWyWUwvSTriiZz/g=="],
 
     "string_decoder": ["string_decoder@1.1.1", "", { "dependencies": { "safe-buffer": "~5.1.0" } }, "sha512-n/ShnvDi6FHbbVfviro+WojiFzv+s8MPMHBczVePfUpDJLwoLT0ht1l4YwBCbi8pJAveEEdnkHyPyTP/mzRfwg=="],
 
-    "strip-ansi": ["strip-ansi@7.2.0", "", { "dependencies": { "ansi-regex": "^6.2.2" } }, "sha512-yDPMNjp4WyfYBkHnjIRLfca1i6KMyGCtsVgoKe/z1+6vukgaENdgGBZt+ZmKPc4gavvEZ5OgHfHdrazhgNyG7w=="],
+    "strip-ansi": ["strip-ansi@6.0.1", "", { "dependencies": { "ansi-regex": "^5.0.1" } }, "sha512-Y38VPSHcqkFrCpFnQ9vuSXmquuv5oXOKpGeT6aGrr3o3Gc9AlVa6JBfUSOCnbxGGZF+/0ooI7KrPuUSztUdU5A=="],
 
     "strip-ansi-cjs": ["strip-ansi@6.0.1", "", { "dependencies": { "ansi-regex": "^5.0.1" } }, "sha512-Y38VPSHcqkFrCpFnQ9vuSXmquuv5oXOKpGeT6aGrr3o3Gc9AlVa6JBfUSOCnbxGGZF+/0ooI7KrPuUSztUdU5A=="],
 
+    "strip-bom": ["strip-bom@4.0.0", "", {}, "sha512-3xurFv5tEgii33Zi8Jtp55wEIILR9eh34FAW00PZf+JnSsTmV/ioewSgQl97JHvgjoRGwPShsWm+IdrxB35d0w=="],
+
     "strip-json-comments": ["strip-json-comments@3.1.1", "", {}, "sha512-6fPc+R4ihwqP6N/aIv2f1gMH8lOVtWQHoqC4yK6oSDVVocumAsfCqjkXnqiYMhmMwS/mEHLp7Vehlt3ql6lEig=="],
 
     "style-mod": ["style-mod@4.1.3", "", {}, "sha512-i/n8VsZydrugj3Iuzll8+x/00GH2vnYsk1eomD8QiRrSAeW6ItbCQDtfXCeJHd0iwiNagqjQkvpvREEPtW3IoQ=="],
@@ -839,11 +945,13 @@
 
     "teex": ["teex@1.0.1", "", { "dependencies": { "streamx": "^2.12.5" } }, "sha512-eYE6iEI62Ni1H8oIa7KlDU6uQBtqr4Eajni3wX7rpfXD8ysFx8z0+dri+KWEPWpBsxXfxu58x/0jvTVT1ekOSg=="],
 
+    "test-exclude": ["test-exclude@8.0.0", "", { "dependencies": { "@istanbuljs/schema": "^0.1.2", "glob": "^13.0.6", "minimatch": "^10.2.2" } }, "sha512-ZOffsNrXYggvU1mDGHk54I96r26P8SyMjO5slMKSc7+IWmtB/MQKnEC2fP51imB3/pT6YK5cT5E8f+Dd9KdyOQ=="],
+
     "text-decoder": ["text-decoder@1.2.7", "", { "dependencies": { "b4a": "^1.6.4" } }, "sha512-vlLytXkeP4xvEq2otHeJfSQIRyWxo/oZGEbXrtEEF9Hnmrdly59sUbzZ/QgyWuLYHctCHxFF4tRQZNQ9k60ExQ=="],
 
     "through2": ["through2@2.0.5", "", { "dependencies": { "readable-stream": "~2.3.6", "xtend": "~4.0.1" } }, "sha512-/mrRod8xqpA+IHSLyGCQ2s8SPHiCDEeQJSep1jqLYeEUClOFG2Qsh+4FU6G9VeqpZnGW/Su8LQGc4YKni5rYSQ=="],
 
-    "tinyglobby": ["tinyglobby@0.2.15", "", { "dependencies": { "fdir": "^6.5.0", "picomatch": "^4.0.3" } }, "sha512-j2Zq4NyQYG5XMST4cbs02Ak8iJUdxRM0XI5QyxXuZOzKOINmWurp3smXu3y5wDcJrptwpSjgXHzIQxR0omXljQ=="],
+    "tinyglobby": ["tinyglobby@0.2.16", "", { "dependencies": { "fdir": "^6.5.0", "picomatch": "^4.0.4" } }, "sha512-pn99VhoACYR8nFHhxqix+uvsbXineAasWm5ojXoN8xEwK5Kd3/TrhNn1wByuD52UxWRLy8pu+kRMniEi6Eq9Zg=="],
 
     "to-through": ["to-through@3.0.0", "", { "dependencies": { "streamx": "^2.12.5" } }, "sha512-y8MN937s/HVhEoBU1SxfHC+wxCHkV1a9gW8eAdTadYh/bGyesZIVcbjI+mSpFbSVwQici/XjBjuUyri1dnXwBw=="],
 
@@ -851,10 +959,16 @@
 
     "tr46": ["tr46@0.0.3", "", {}, "sha512-N3WMsuqV66lT30CrXNbEjx4GEwlow3v6rr4mCcv6prnfwhS01rkgyFdjPNBYd9br7LpXV1+Emh01fHnq2Gdgrw=="],
 
+    "tslib": ["tslib@2.8.1", "", {}, "sha512-oJFu94HQb+KVduSUQL7wnpmqnfmLsOA/nAh6b6EH0wCEoK0/mPeXU6c3wKDV83MkOuHPRHtSXKKU99IBazS/2w=="],
+
     "type-check": ["type-check@0.4.0", "", { "dependencies": { "prelude-ls": "^1.2.1" } }, "sha512-XleUoc9uwGXqjWwXaUTZAmzMcFZ5858QA2vvx1Ur5xIcixXIP+8LnFDgRplU30us6teqdlskFfu+ae4K79Ooew=="],
 
+    "type-fest": ["type-fest@0.8.1", "", {}, "sha512-4dbzIzqvjtgiM5rw1k5rEHtBANKmdudhGyBEajN01fEyhaAIhsoKNy6y7+IN93IfpFtwY9iqi7kD+xwKhQsNJA=="],
+
     "type-is": ["type-is@2.0.1", "", { "dependencies": { "content-type": "^1.0.5", "media-typer": "^1.1.0", "mime-types": "^3.0.0" } }, "sha512-OZs6gsjF4vMp32qrCbiVSkrFmXtG/AZhY3t0iAMrMBiAZyV9oALtXO8hsrHbMXF9x6L3grlFuwW2oAz7cav+Gw=="],
 
+    "typedarray-to-buffer": ["typedarray-to-buffer@3.1.5", "", { "dependencies": { "is-typedarray": "^1.0.0" } }, "sha512-zdu8XMNEDepKKR+XYOXAVPtWui0ly0NtohUscw+UmaHiAWT8hrV1rr//H6V+0DvJ3OQ19S979M0laLfX8rm82Q=="],
+
     "typescript": ["typescript@5.9.3", "", { "bin": { "tsc": "bin/tsc", "tsserver": "bin/tsserver" } }, "sha512-jl1vZzPDinLr9eUt3J/t7V6FgNEw9QjvBPdysz9KfQDD41fQrC2Y4vKQdiaUpFT4bXlb1RHhLpp8wtm6M5TgSw=="],
 
     "underscore.string": ["underscore.string@3.3.6", "", { "dependencies": { "sprintf-js": "^1.1.1", "util-deprecate": "^1.0.2" } }, "sha512-VoC83HWXmCrF6rgkyxS9GHv8W9Q5nhMKho+OadDJGzL2oDYbYEppBaCMH6pFlwLeqj2QS+hhkw2kpXkSdD1JxQ=="],
@@ -873,6 +987,10 @@
 
     "util-deprecate": ["util-deprecate@1.0.2", "", {}, "sha512-EPD5q1uXyFxJpCrLnCc1nHnq3gOa6DZBocAIiI2TaSCA7VCJ1UJDMagCzIkXNsUYfD1daK//LTEQ8xiIbrHtcw=="],
 
+    "uuid": ["uuid@8.3.2", "", { "bin": { "uuid": "dist/bin/uuid" } }, "sha512-+NYs2QeMWy+GWFOEm9xnn6HCDp0l7QBD7ml8zLUmJ+93Q5NF0NocErnwkTkXVFNiX3/fpC6afS8Dhb/gz7R7eg=="],
+
+    "v8-to-istanbul": ["v8-to-istanbul@9.3.0", "", { "dependencies": { "@jridgewell/trace-mapping": "^0.3.12", "@types/istanbul-lib-coverage": "^2.0.1", "convert-source-map": "^2.0.0" } }, "sha512-kiGUalWN+rgBJ/1OHZsBtU4rXZOfj/7rKQxULKlIzwzQSvMJUUNgPwJEEh7gU6xEVxC0ahoOBvN2YI8GH6FNgA=="],
+
     "value-or-function": ["value-or-function@4.0.0", "", {}, "sha512-aeVK81SIuT6aMJfNo9Vte8Dw0/FZINGBV8BfCraGtqVxIeLAEhJyoWs8SmvRVmXfGss2PmmOwZCuBPbZR+IYWg=="],
 
     "vary": ["vary@1.1.2", "", {}, "sha512-BNGbWLfd0eUPabhkXUVm0j8uuvREyTh5ovRa/dyow/BqAbZJyC+5fU+IzQOzmAKzYqYRAISoRhdQr3eIZ/PXqg=="],
@@ -885,7 +1003,9 @@
 
     "vinyl-sourcemap": ["vinyl-sourcemap@2.0.0", "", { "dependencies": { "convert-source-map": "^2.0.0", "graceful-fs": "^4.2.10", "now-and-later": "^3.0.0", "streamx": "^2.12.5", "vinyl": "^3.0.0", "vinyl-contents": "^2.0.0" } }, "sha512-BAEvWxbBUXvlNoFQVFVHpybBbjW1r03WhohJzJDSfgrrK5xVYIDTan6xN14DlyImShgDRv2gl9qhM6irVMsV0Q=="],
 
-    "vite": ["vite@6.4.2", "", { "dependencies": { "esbuild": "^0.25.0", "fdir": "^6.4.4", "picomatch": "^4.0.2", "postcss": "^8.5.3", "rollup": "^4.34.9", "tinyglobby": "^0.2.13" }, "optionalDependencies": { "fsevents": "~2.3.3" }, "peerDependencies": { "@types/node": "^18.0.0 || ^20.0.0 || >=22.0.0", "jiti": ">=1.21.0", "less": "*", "lightningcss": "^1.21.0", "sass": "*", "sass-embedded": "*", "stylus": "*", "sugarss": "*", "terser": "^5.16.0", "tsx": "^4.8.1", "yaml": "^2.4.2" }, "optionalPeers": ["@types/node", "jiti", "less", "lightningcss", "sass", "sass-embedded", "stylus", "sugarss", "terser", "tsx", "yaml"], "bin": { "vite": "bin/vite.js" } }, "sha512-2N/55r4JDJ4gdrCvGgINMy+HH3iRpNIz8K6SFwVsA+JbQScLiC+clmAxBgwiSPgcG9U15QmvqCGWzMbqda5zGQ=="],
+    "vite": ["vite@8.0.14", "", { "dependencies": { "lightningcss": "^1.32.0", "picomatch": "^4.0.4", "postcss": "^8.5.15", "rolldown": "1.0.2", "tinyglobby": "^0.2.16" }, "optionalDependencies": { "fsevents": "~2.3.3" }, "peerDependencies": { "@types/node": "^20.19.0 || >=22.12.0", "@vitejs/devtools": "^0.1.18", "esbuild": "^0.27.0 || ^0.28.0", "jiti": ">=1.21.0", "less": "^4.0.0", "sass": "^1.70.0", "sass-embedded": "^1.70.0", "stylus": ">=0.54.8", "sugarss": "^5.0.0", "terser": "^5.16.0", "tsx": "^4.8.1", "yaml": "^2.4.2" }, "optionalPeers": ["@types/node", "@vitejs/devtools", "esbuild", "jiti", "less", "sass", "sass-embedded", "stylus", "sugarss", "terser", "tsx", "yaml"], "bin": { "vite": "bin/vite.js" } }, "sha512-s4BJJ+5y1pYL6Otw51FHhVJQhPnuRinKig64g/1+EUNaJsd3gCKdD31IPFvswUgW9/60QT9oFHbZHbQK5imcxw=="],
+
+    "vite-plugin-istanbul": ["vite-plugin-istanbul@9.0.0", "", { "dependencies": { "@babel/generator": "^7.29.1", "@istanbuljs/load-nyc-config": "^1.1.0", "@types/babel__generator": "7.27.0", "espree": "^11.2.0", "istanbul-lib-instrument": "^6.0.3", "picocolors": "^1.1.1", "source-map": "^0.7.6", "test-exclude": "^8.0.0" }, "peerDependencies": { "vite": ">=7" } }, "sha512-Ia0GYwVAYZMyGM9vZFAb1+xy/s+aFWBO0lWfpuBbl9XyHEm1rVCBtpk+52G2M54t272q9b07CMlwSuew7DNhqQ=="],
 
     "void-elements": ["void-elements@3.1.0", "", {}, "sha512-Dhxzh5HZuiHQhbvTW9AMetFfBHDMYpo23Uo9btPXgdYP+3T5S+p+jgNy7spra+veYhBP2dCSgxR/i2Y02h5/6w=="],
 
@@ -903,30 +1023,58 @@
 
     "which": ["which@2.0.2", "", { "dependencies": { "isexe": "^2.0.0" }, "bin": { "node-which": "./bin/node-which" } }, "sha512-BLI3Tl1TW3Pvl70l3yq3Y64i+awpwXqsGBYWkkqMtnbXgrMD+yj7rhW0kuEDxzJaYXGjEW5ogapKNMEKNMjibA=="],
 
+    "which-module": ["which-module@2.0.1", "", {}, "sha512-iBdZ57RDvnOR9AGBhML2vFZf7h8vmBjhoaZqODJBFWHVtKkDmKuHai3cx5PgVMrX5YDNp27AofYbAwctSS+vhQ=="],
+
     "word-wrap": ["word-wrap@1.2.5", "", {}, "sha512-BN22B5eaMMI9UMtjrGd5g5eCYPpCPDUy0FJXbYsaT5zYxjFOckS53SQDE3pWkVoWpHXVb3BrYcEN4Twa55B5cA=="],
 
-    "wrap-ansi": ["wrap-ansi@8.1.0", "", { "dependencies": { "ansi-styles": "^6.1.0", "string-width": "^5.0.1", "strip-ansi": "^7.0.1" } }, "sha512-si7QWI6zUMq56bESFvagtmzMdGOtoxfR+Sez11Mobfc7tm+VkUckk9bW2UeffTGVUbOksxmSw0AA2gs8g71NCQ=="],
+    "wrap-ansi": ["wrap-ansi@6.2.0", "", { "dependencies": { "ansi-styles": "^4.0.0", "string-width": "^4.1.0", "strip-ansi": "^6.0.0" } }, "sha512-r6lPcBGxZXlIcymEu7InxDMhdW0KDxpLgoFLcguasxCaJ/SOIZwINatK9KY/tf+ZrlywOKU0UDj3ATXUBfxJXA=="],
 
     "wrap-ansi-cjs": ["wrap-ansi@7.0.0", "", { "dependencies": { "ansi-styles": "^4.0.0", "string-width": "^4.1.0", "strip-ansi": "^6.0.0" } }, "sha512-YVGIj2kamLSTxw6NsZjoBxfSwsn0ycdesmc4p+Q21c5zPuZ1pl+NfxVdxPtdHvmNVOQ6XSYG4AUtyt/Fi7D16Q=="],
 
     "wrappy": ["wrappy@1.0.2", "", {}, "sha512-l4Sp/DRseor9wL6EvV2+TuQn63dMkPjZ/sp9XkghTEbV9KlPS1xUsZ3u7/IQO4wxtcFB4bgpQPRcR3QCvezPcQ=="],
 
+    "write-file-atomic": ["write-file-atomic@3.0.3", "", { "dependencies": { "imurmurhash": "^0.1.4", "is-typedarray": "^1.0.0", "signal-exit": "^3.0.2", "typedarray-to-buffer": "^3.1.5" } }, "sha512-AvHcyZ5JnSfq3ioSyjrBkH9yW4m7Ayk8/9My/DD9onKeu/94fwrMocemO2QAJFAlnnDN+ZDS+ZjAR5ua1/PV/Q=="],
+
     "xtend": ["xtend@4.0.2", "", {}, "sha512-LKYU1iAXJXUgAXn9URjiu+MWhyUXHsvfp7mcuYm9dSUKK0/CjtrUwFAxD82/mCWbtLsGjFIad0wIsod4zrTAEQ=="],
 
+    "y18n": ["y18n@4.0.3", "", {}, "sha512-JKhqTOwSrqNA1NY5lSztJ1GrBiUodLMmIZuLiDaMRJ+itFd+ABVE8XBjOvIWL+rSqNDC74LCSFmlb/U4UZ4hJQ=="],
+
     "yallist": ["yallist@3.1.1", "", {}, "sha512-a4UGQaWPH59mOXUYnAG2ewncQS4i4F43Tv3JoAM+s2VDAmS9NsK8GpDMLrCHPksFT7h3K6TOoUNn2pb7RoXx4g=="],
 
     "yaml": ["yaml@2.8.3", "", { "bin": { "yaml": "bin.mjs" } }, "sha512-AvbaCLOO2Otw/lW5bmh9d/WEdcDFdQp2Z2ZUH3pX9U2ihyUY0nvLv7J6TrWowklRGPYbB/IuIMfYgxaCPg5Bpg=="],
 
+    "yargs": ["yargs@15.4.1", "", { "dependencies": { "cliui": "^6.0.0", "decamelize": "^1.2.0", "find-up": "^4.1.0", "get-caller-file": "^2.0.1", "require-directory": "^2.1.1", "require-main-filename": "^2.0.0", "set-blocking": "^2.0.0", "string-width": "^4.2.0", "which-module": "^2.0.0", "y18n": "^4.0.0", "yargs-parser": "^18.1.2" } }, "sha512-aePbxDmcYW++PaqBsJ+HYUFwCdv4LVvdnhBy78E57PIor8/OVvhMrADFFEDh8DHDFRv/O9i3lPhsENjO7QX0+A=="],
+
+    "yargs-parser": ["yargs-parser@18.1.3", "", { "dependencies": { "camelcase": "^5.0.0", "decamelize": "^1.2.0" } }, "sha512-o50j0JeToy/4K6OZcaQmW6lyXXKhq7csREXcDwk2omFPJEwUNOVtJKvmDr9EI1fAJZUyZcRF7kxGBWmRXudrCQ=="],
+
     "yocto-queue": ["yocto-queue@0.1.0", "", {}, "sha512-rVksvsnNCdJ/ohGc6xgPwyN8eheCxsiLM8mxuE/t/mOVqJewPuO1miLpTHQiRgTKCLexL4MeAFVagts7HmNZ2Q=="],
 
     "zod": ["zod@4.3.6", "", {}, "sha512-rftlrkhHZOcjDwkGlnUtZZkvaPHCsDATp4pGpuOOMDaTdDDXF91wuVDJoWoPsKX/3YPQ5fHuF3STjcYyKr+Qhg=="],
 
     "zod-to-json-schema": ["zod-to-json-schema@3.25.1", "", { "peerDependencies": { "zod": "^3.25 || ^4" } }, "sha512-pM/SU9d3YAggzi6MtR4h7ruuQlqKtad8e9S0fmxcMi+ueAK5Korys/aWcV9LIIHTVbj01NdzxcnXSN+O74ZIVA=="],
 
+    "@babel/core/convert-source-map": ["convert-source-map@2.0.0", "", {}, "sha512-Kvp459HrV2FEJ1CAsi1Ku+MY3kasH19TFykTz2xWmMeq6bk2NU3XXvfJ+Q61m0xktWwt+1HSYf3JZsTms3aRJg=="],
+
+    "@babel/core/semver": ["semver@6.3.1", "", { "bin": { "semver": "bin/semver.js" } }, "sha512-BR7VvDCVHO+q2xBEWskxS6DJE1qRnb7DxzUrogb71CWoSficBxYsiAGd+Kl0mmq/MprG9yArRkyrQxTO6XjMzA=="],
+
+    "@babel/helper-compilation-targets/lru-cache": ["lru-cache@5.1.1", "", { "dependencies": { "yallist": "^3.0.2" } }, "sha512-KpNARQA3Iwv+jTA0utUVVbrh+Jlrr1Fv0e56GGzAFOXN7dk/FviaDW8LHmK52DlcH4WP2n6gI8vN1aesBFgo9w=="],
+
+    "@babel/helper-compilation-targets/semver": ["semver@6.3.1", "", { "bin": { "semver": "bin/semver.js" } }, "sha512-BR7VvDCVHO+q2xBEWskxS6DJE1qRnb7DxzUrogb71CWoSficBxYsiAGd+Kl0mmq/MprG9yArRkyrQxTO6XjMzA=="],
+
     "@eslint-community/eslint-utils/eslint-visitor-keys": ["eslint-visitor-keys@3.4.3", "", {}, "sha512-wpc+LXeiyiisxPlEkUzU6svyS1frIO3Mgxj1fdy7Pm8Ygzguax2N3Fa/D/ag1WqbOprdI+uY6wMUl8/a2G+iag=="],
 
     "@eslint/eslintrc/globals": ["globals@14.0.0", "", {}, "sha512-oahGvuMGQlPw/ivIYBjVSrWAfWLBeku5tpPE2fOPLi+WHffIWbuh2tCjhyQhTBPMf5E9jDEH4FOmTYgYwbKwtQ=="],
 
+    "@isaacs/cliui/string-width": ["string-width@5.1.2", "", { "dependencies": { "eastasianwidth": "^0.2.0", "emoji-regex": "^9.2.2", "strip-ansi": "^7.0.1" } }, "sha512-HnLOCR3vjcY8beoNLtcjZ5/nxn2afmME6lhrDrebokqMap+XbeW8n9TXpPDOqdGK5qcI3oT0GKTW6wC7EMiVqA=="],
+
+    "@isaacs/cliui/strip-ansi": ["strip-ansi@7.2.0", "", { "dependencies": { "ansi-regex": "^6.2.2" } }, "sha512-yDPMNjp4WyfYBkHnjIRLfca1i6KMyGCtsVgoKe/z1+6vukgaENdgGBZt+ZmKPc4gavvEZ5OgHfHdrazhgNyG7w=="],
+
+    "@isaacs/cliui/wrap-ansi": ["wrap-ansi@8.1.0", "", { "dependencies": { "ansi-styles": "^6.1.0", "string-width": "^5.0.1", "strip-ansi": "^7.0.1" } }, "sha512-si7QWI6zUMq56bESFvagtmzMdGOtoxfR+Sez11Mobfc7tm+VkUckk9bW2UeffTGVUbOksxmSw0AA2gs8g71NCQ=="],
+
+    "@istanbuljs/load-nyc-config/find-up": ["find-up@4.1.0", "", { "dependencies": { "locate-path": "^5.0.0", "path-exists": "^4.0.0" } }, "sha512-PpOwAdQ/YlXQ2vj8a3h8IipDuYRi3wceVQQGYWxNINccq40Anw7BlsEXCMbt1Zt+OLA6Fq9suIpIWD0OsnISlw=="],
+
+    "@istanbuljs/load-nyc-config/js-yaml": ["js-yaml@3.14.2", "", { "dependencies": { "argparse": "^1.0.7", "esprima": "^4.0.0" }, "bin": { "js-yaml": "bin/js-yaml.js" } }, "sha512-PMSmkqxr106Xa156c2M265Z+FTrPl+oxd/rgOQy2tijQeK5TxQ43psO1ZCwhVOSdnn+RzkzlRz/eY4BgJBYVpg=="],
+
     "@modelcontextprotocol/sdk/ajv": ["ajv@8.18.0", "", { "dependencies": { "fast-deep-equal": "^3.1.3", "fast-uri": "^3.0.1", "json-schema-traverse": "^1.0.0", "require-from-string": "^2.0.2" } }, "sha512-PlXPeEWMXMZ7sPYOHqmDyCJzcfNrUr3fGNKtezX14ykXOEIvyK81d+qydx89KY5O71FKMPaQ2vBfBFI5NHR63A=="],
 
     "ajv-formats/ajv": ["ajv@8.18.0", "", { "dependencies": { "fast-deep-equal": "^3.1.3", "fast-uri": "^3.0.1", "json-schema-traverse": "^1.0.0", "require-from-string": "^2.0.2" } }, "sha512-PlXPeEWMXMZ7sPYOHqmDyCJzcfNrUr3fGNKtezX14ykXOEIvyK81d+qydx89KY5O71FKMPaQ2vBfBFI5NHR63A=="],
@@ -939,8 +1087,14 @@
 
     "broccoli-output-wrapper/fs-extra": ["fs-extra@8.1.0", "", { "dependencies": { "graceful-fs": "^4.2.0", "jsonfile": "^4.0.0", "universalify": "^0.1.0" } }, "sha512-yhlQgA6mnOJUKOsRUFsgJdQCvkKhcz8tlZG5HBQfReYZy46OwLcY+Zia0mtdHsOo9y/hP+CxMN0TU9QxoOtG4g=="],
 
+    "broccoli-plugin/rimraf": ["rimraf@3.0.2", "", { "dependencies": { "glob": "^7.1.3" }, "bin": { "rimraf": "bin.js" } }, "sha512-JZkJMZkAGFFPP2YqXZXPbMlMBgsxzE8ILs4lMIX/2o0L9UBw9O/Y3o6wFw/i9YLapcUJWwqbi3kdxIPdC62TIA=="],
+
+    "foreground-child/signal-exit": ["signal-exit@4.1.0", "", {}, "sha512-bzyZ1e88w9O1iNJbKnOlvYTrWPDl46O1bG0D3XInv+9tkPrxrN8jUUTiFlDkkmKWgn1M6CfIA13SuGqOa9Korw=="],
+
     "fs-merger/fs-extra": ["fs-extra@8.1.0", "", { "dependencies": { "graceful-fs": "^4.2.0", "jsonfile": "^4.0.0", "universalify": "^0.1.0" } }, "sha512-yhlQgA6mnOJUKOsRUFsgJdQCvkKhcz8tlZG5HBQfReYZy46OwLcY+Zia0mtdHsOo9y/hP+CxMN0TU9QxoOtG4g=="],
 
+    "glob/minimatch": ["minimatch@10.2.5", "", { "dependencies": { "brace-expansion": "^5.0.5" } }, "sha512-MULkVLfKGYDFYejP07QOurDLLQpcjk7Fw+7jXS2R2czRQzR56yHRveU5NDJEOviH+hETZKSkIk5c+T23GjFUMg=="],
+
     "heimdalljs/rsvp": ["rsvp@3.2.1", "", {}, "sha512-Rf4YVNYpKjZ6ASAmibcwTNciQ5Co5Ztq6iZPEykHpkoflnD/K5ryE/rHehFsTm4NJj8nKDhbi3eKBWGogmNnkg=="],
 
     "heimdalljs-logger/debug": ["debug@2.6.9", "", { "dependencies": { "ms": "2.0.0" } }, "sha512-bC7ElrdJaJnPbAP+1EotYvqZsb3ecl5wi6Bfi6BJTUcNowp6cvspg0jXznRTKDjm/E7AdgFBVeAPVMNcKGsHMA=="],
@@ -949,9 +1103,19 @@
 
     "i18next-parser/i18next": ["i18next@24.2.3", "", { "dependencies": { "@babel/runtime": "^7.26.10" }, "peerDependencies": { "typescript": "^5" }, "optionalPeers": ["typescript"] }, "sha512-lfbf80OzkocvX7nmZtu7nSTNbrTYR52sLWxPtlXX1zAhVw8WEnFk4puUkCR4B1dNQwbSpEHHHemcZu//7EcB7A=="],
 
+    "import-fresh/resolve-from": ["resolve-from@4.0.0", "", {}, "sha512-pb/MYmXstAkysRFx8piNI1tGFNQIFA3vkE3Gq4EuA1dF6gHp/+vgZqsCGJapvy8N3Q+4o7FwvquPJcnZ7RYy4g=="],
+
+    "istanbul-lib-report/make-dir": ["make-dir@4.0.0", "", { "dependencies": { "semver": "^7.5.3" } }, "sha512-hXdUTZYIVOt1Ex//jAQi+wTZZpUpwBj/0QsOzqegb3rGMMeJiSEu5xLHnYfBrRV4RH2+OCSOO95Is/7x1WJ4bw=="],
+
+    "istanbul-lib-source-maps/source-map": ["source-map@0.6.1", "", {}, "sha512-UjgapumWlbMhkBgzT7Ykc5YXUT46F0iKu8SGXq0bcwP5dz/h0Plj6enJqjz1Zbq2l5WaqYnrVbwWOWMyF3F47g=="],
+
+    "make-dir/semver": ["semver@6.3.1", "", { "bin": { "semver": "bin/semver.js" } }, "sha512-BR7VvDCVHO+q2xBEWskxS6DJE1qRnb7DxzUrogb71CWoSficBxYsiAGd+Kl0mmq/MprG9yArRkyrQxTO6XjMzA=="],
+
+    "nyc/find-up": ["find-up@4.1.0", "", { "dependencies": { "locate-path": "^5.0.0", "path-exists": "^4.0.0" } }, "sha512-PpOwAdQ/YlXQ2vj8a3h8IipDuYRi3wceVQQGYWxNINccq40Anw7BlsEXCMbt1Zt+OLA6Fq9suIpIWD0OsnISlw=="],
+
     "parse5/entities": ["entities@6.0.1", "", {}, "sha512-aN97NXWF6AWBTahfVOIrB/NShkzi5H7F9r1s9mD3cDj4Ko5f2qhhVoYMibXF7GlLveb/D2ioWay8lxI97Ven3g=="],
 
-    "path-scurry/lru-cache": ["lru-cache@10.4.3", "", {}, "sha512-JNAzZcXrCt42VGLuYz0zfAzDfAvJWW6AfYlDBQyDV5DClI2m5sAmK+OIO7s59XfsRsWHp02jAJrRadPRGTt6SQ=="],
+    "pkg-dir/find-up": ["find-up@4.1.0", "", { "dependencies": { "locate-path": "^5.0.0", "path-exists": "^4.0.0" } }, "sha512-PpOwAdQ/YlXQ2vj8a3h8IipDuYRi3wceVQQGYWxNINccq40Anw7BlsEXCMbt1Zt+OLA6Fq9suIpIWD0OsnISlw=="],
 
     "playwright/fsevents": ["fsevents@2.3.2", "", { "os": "darwin" }, "sha512-xiqMQR4xAeHTuB9uWm+fFRcIOgKBMiOBP+eXiyT7jsgVCq1bkVygt00oASowB7EdtpOHaaPgKt812P9ab+DDKA=="],
 
@@ -961,17 +1125,27 @@
 
     "react-router/cookie": ["cookie@1.1.1", "", {}, "sha512-ei8Aos7ja0weRpFzJnEA9UHJ/7XQmqglbRwnf2ATjcB9Wq874VKH9kfjjirM6UhU2/E5fFYadylyhFldcqSidQ=="],
 
-    "string-width-cjs/emoji-regex": ["emoji-regex@8.0.0", "", {}, "sha512-MSjYzcWNOA0ewAHpz0MxpYFvwg6yjy1NG3xteoqz644VCo/RPgnr1/GGt+ic3iJTzQ8Eu3TdM14SawnVUmGE6A=="],
+    "spawn-wrap/foreground-child": ["foreground-child@2.0.0", "", { "dependencies": { "cross-spawn": "^7.0.0", "signal-exit": "^3.0.2" } }, "sha512-dCIq9FpEcyQyXKCkyzmlPTFNgrCzPudOe+mhvJU5zAtlBnGVy2yKxtfsxK2tQBThwq225jcvBjpw1Gr40uzZCA=="],
 
-    "string-width-cjs/strip-ansi": ["strip-ansi@6.0.1", "", { "dependencies": { "ansi-regex": "^5.0.1" } }, "sha512-Y38VPSHcqkFrCpFnQ9vuSXmquuv5oXOKpGeT6aGrr3o3Gc9AlVa6JBfUSOCnbxGGZF+/0ooI7KrPuUSztUdU5A=="],
+    "test-exclude/minimatch": ["minimatch@10.2.5", "", { "dependencies": { "brace-expansion": "^5.0.5" } }, "sha512-MULkVLfKGYDFYejP07QOurDLLQpcjk7Fw+7jXS2R2czRQzR56yHRveU5NDJEOviH+hETZKSkIk5c+T23GjFUMg=="],
 
-    "strip-ansi-cjs/ansi-regex": ["ansi-regex@5.0.1", "", {}, "sha512-quJQXlTSUGL2LH9SUXo8VwsY4soanhgo6LNSm84E1LBcE8s3O0wpdiRzyR9z/ZZJMlMWv37qOOb9pdJlMUEKFQ=="],
+    "v8-to-istanbul/convert-source-map": ["convert-source-map@2.0.0", "", {}, "sha512-Kvp459HrV2FEJ1CAsi1Ku+MY3kasH19TFykTz2xWmMeq6bk2NU3XXvfJ+Q61m0xktWwt+1HSYf3JZsTms3aRJg=="],
 
-    "wrap-ansi/ansi-styles": ["ansi-styles@6.2.3", "", {}, "sha512-4Dj6M28JB+oAH8kFkTLUo+a2jwOFkuqb3yucU0CANcRRUbxS0cP0nZYCGjcc3BNXwRIsUVmDGgzawme7zvJHvg=="],
+    "vinyl-sourcemap/convert-source-map": ["convert-source-map@2.0.0", "", {}, "sha512-Kvp459HrV2FEJ1CAsi1Ku+MY3kasH19TFykTz2xWmMeq6bk2NU3XXvfJ+Q61m0xktWwt+1HSYf3JZsTms3aRJg=="],
 
-    "wrap-ansi-cjs/string-width": ["string-width@4.2.3", "", { "dependencies": { "emoji-regex": "^8.0.0", "is-fullwidth-code-point": "^3.0.0", "strip-ansi": "^6.0.1" } }, "sha512-wKyQRQpjJ0sIp62ErSZdGsjMJWsap5oRNihHhu6G7JVO/9jIB6UyevL+tXuOqrng8j/cxKTWyWUwvSTriiZz/g=="],
+    "vite-plugin-istanbul/espree": ["espree@11.2.0", "", { "dependencies": { "acorn": "^8.16.0", "acorn-jsx": "^5.3.2", "eslint-visitor-keys": "^5.0.1" } }, "sha512-7p3DrVEIopW1B1avAGLuCSh1jubc01H2JHc8B4qqGblmg5gI9yumBgACjWo4JlIc04ufug4xJ3SQI8HkS/Rgzw=="],
 
-    "wrap-ansi-cjs/strip-ansi": ["strip-ansi@6.0.1", "", { "dependencies": { "ansi-regex": "^5.0.1" } }, "sha512-Y38VPSHcqkFrCpFnQ9vuSXmquuv5oXOKpGeT6aGrr3o3Gc9AlVa6JBfUSOCnbxGGZF+/0ooI7KrPuUSztUdU5A=="],
+    "yargs/find-up": ["find-up@4.1.0", "", { "dependencies": { "locate-path": "^5.0.0", "path-exists": "^4.0.0" } }, "sha512-PpOwAdQ/YlXQ2vj8a3h8IipDuYRi3wceVQQGYWxNINccq40Anw7BlsEXCMbt1Zt+OLA6Fq9suIpIWD0OsnISlw=="],
+
+    "@isaacs/cliui/string-width/emoji-regex": ["emoji-regex@9.2.2", "", {}, "sha512-L18DaJsXSUk2+42pv8mLs5jJT2hqFkFE4j21wOmgbUqsZ2hL72NsUU785g9RXgo3s0ZNgVl42TiHp3ZtOv/Vyg=="],
+
+    "@isaacs/cliui/strip-ansi/ansi-regex": ["ansi-regex@6.2.2", "", {}, "sha512-Bq3SmSpyFHaWjPk8If9yc6svM8c56dB5BAtW4Qbw5jHTwwXXcTLoRMkpDJp6VL0XzlWaCHTXrkFURMYmD0sLqg=="],
+
+    "@isaacs/cliui/wrap-ansi/ansi-styles": ["ansi-styles@6.2.3", "", {}, "sha512-4Dj6M28JB+oAH8kFkTLUo+a2jwOFkuqb3yucU0CANcRRUbxS0cP0nZYCGjcc3BNXwRIsUVmDGgzawme7zvJHvg=="],
+
+    "@istanbuljs/load-nyc-config/find-up/locate-path": ["locate-path@5.0.0", "", { "dependencies": { "p-locate": "^4.1.0" } }, "sha512-t7hw9pI+WvuwNJXwk5zVHpyhIqzg2qTlklJOf0mVxGSbe3Fp2VieZcduNYjaLDoy6p9uGpQEGWG87WpMKlNq8g=="],
+
+    "@istanbuljs/load-nyc-config/js-yaml/argparse": ["argparse@1.0.10", "", { "dependencies": { "sprintf-js": "~1.0.2" } }, "sha512-o5Roy6tNG4SL/FOkCAN6RzjiakZS25RLYFrcMttJqbdd8BWrnA+fGz57iN5Pb06pvBGvl5gQ0B48dJlslXvoTg=="],
 
     "@modelcontextprotocol/sdk/ajv/json-schema-traverse": ["json-schema-traverse@1.0.0", "", {}, "sha512-NM8/P9n3XjXhIZn1lLhkFaACTOURQXjWhV4BA/RnOv8xvgqtqpAX9IO4mRQxSx1Rlo4tqzeqb0sOlruaOy3dug=="],
 
@@ -981,22 +1155,56 @@
 
     "broccoli-output-wrapper/fs-extra/universalify": ["universalify@0.1.2", "", {}, "sha512-rBJeI5CXAlmy1pV+617WB9J63U6XcazHHF2f2dbJix4XzpUF0RS3Zbj0FGIOCAva5P/d/GBOYaACQ1w+0azUkg=="],
 
+    "broccoli-plugin/rimraf/glob": ["glob@7.2.3", "", { "dependencies": { "fs.realpath": "^1.0.0", "inflight": "^1.0.4", "inherits": "2", "minimatch": "^3.1.1", "once": "^1.3.0", "path-is-absolute": "^1.0.0" } }, "sha512-nFR0zLpU2YCaRxwoCJvL6UvCH2JFyFVIvwTLsIf21AuHlMskA1hhTdk+LlYJtOlYt9v6dvszD2BGRqBL+iQK9Q=="],
+
     "fs-merger/fs-extra/jsonfile": ["jsonfile@4.0.0", "", { "optionalDependencies": { "graceful-fs": "^4.1.6" } }, "sha512-m6F1R3z8jjlf2imQHS2Qez5sjKWQzbuuhuJ/FKYFRZvPE3PuHcSMVZzfsLhGVOkfd20obL5SWEBew5ShlquNxg=="],
 
     "fs-merger/fs-extra/universalify": ["universalify@0.1.2", "", {}, "sha512-rBJeI5CXAlmy1pV+617WB9J63U6XcazHHF2f2dbJix4XzpUF0RS3Zbj0FGIOCAva5P/d/GBOYaACQ1w+0azUkg=="],
 
+    "glob/minimatch/brace-expansion": ["brace-expansion@5.0.6", "", { "dependencies": { "balanced-match": "^4.0.2" } }, "sha512-kLpxurY4Z4r9sgMsyG0Z9uzsBlgiU/EFKhj/h91/8yHu0edo7XuixOIH3VcJ8kkxs6/jPzoI6U9Vj3WqbMQ94g=="],
+
     "heimdalljs-logger/debug/ms": ["ms@2.0.0", "", {}, "sha512-Tpp60P6IUJDTuOq/5Z8cdskzJujfwqfOTkrwIwj7IRISpnkJnT6SyJ4PCPnGMoFjC9ddhal5KVIYtAt97ix05A=="],
 
+    "nyc/find-up/locate-path": ["locate-path@5.0.0", "", { "dependencies": { "p-locate": "^4.1.0" } }, "sha512-t7hw9pI+WvuwNJXwk5zVHpyhIqzg2qTlklJOf0mVxGSbe3Fp2VieZcduNYjaLDoy6p9uGpQEGWG87WpMKlNq8g=="],
+
+    "pkg-dir/find-up/locate-path": ["locate-path@5.0.0", "", { "dependencies": { "p-locate": "^4.1.0" } }, "sha512-t7hw9pI+WvuwNJXwk5zVHpyhIqzg2qTlklJOf0mVxGSbe3Fp2VieZcduNYjaLDoy6p9uGpQEGWG87WpMKlNq8g=="],
+
     "quick-temp/rimraf/glob": ["glob@10.5.0", "", { "dependencies": { "foreground-child": "^3.1.0", "jackspeak": "^3.1.2", "minimatch": "^9.0.4", "minipass": "^7.1.2", "package-json-from-dist": "^1.0.0", "path-scurry": "^1.11.1" }, "bin": { "glob": "dist/esm/bin.mjs" } }, "sha512-DfXN8DfhJ7NH3Oe7cFmu3NCu1wKbkReJ8TorzSAFbSKrlNaQSKfIzqYqVY8zlbs2NLBbWpRiU52GX2PbaBVNkg=="],
 
-    "string-width-cjs/strip-ansi/ansi-regex": ["ansi-regex@5.0.1", "", {}, "sha512-quJQXlTSUGL2LH9SUXo8VwsY4soanhgo6LNSm84E1LBcE8s3O0wpdiRzyR9z/ZZJMlMWv37qOOb9pdJlMUEKFQ=="],
+    "test-exclude/minimatch/brace-expansion": ["brace-expansion@5.0.6", "", { "dependencies": { "balanced-match": "^4.0.2" } }, "sha512-kLpxurY4Z4r9sgMsyG0Z9uzsBlgiU/EFKhj/h91/8yHu0edo7XuixOIH3VcJ8kkxs6/jPzoI6U9Vj3WqbMQ94g=="],
 
-    "wrap-ansi-cjs/string-width/emoji-regex": ["emoji-regex@8.0.0", "", {}, "sha512-MSjYzcWNOA0ewAHpz0MxpYFvwg6yjy1NG3xteoqz644VCo/RPgnr1/GGt+ic3iJTzQ8Eu3TdM14SawnVUmGE6A=="],
+    "vite-plugin-istanbul/espree/eslint-visitor-keys": ["eslint-visitor-keys@5.0.1", "", {}, "sha512-tD40eHxA35h0PEIZNeIjkHoDR4YjjJp34biM0mDvplBe//mB+IHCqHDGV7pxF+7MklTvighcCPPZC7ynWyjdTA=="],
 
-    "wrap-ansi-cjs/strip-ansi/ansi-regex": ["ansi-regex@5.0.1", "", {}, "sha512-quJQXlTSUGL2LH9SUXo8VwsY4soanhgo6LNSm84E1LBcE8s3O0wpdiRzyR9z/ZZJMlMWv37qOOb9pdJlMUEKFQ=="],
+    "yargs/find-up/locate-path": ["locate-path@5.0.0", "", { "dependencies": { "p-locate": "^4.1.0" } }, "sha512-t7hw9pI+WvuwNJXwk5zVHpyhIqzg2qTlklJOf0mVxGSbe3Fp2VieZcduNYjaLDoy6p9uGpQEGWG87WpMKlNq8g=="],
+
+    "@istanbuljs/load-nyc-config/find-up/locate-path/p-locate": ["p-locate@4.1.0", "", { "dependencies": { "p-limit": "^2.2.0" } }, "sha512-R79ZZ/0wAxKGu3oYMlz8jy/kbhsNrS7SKZ7PxEHBgJ5+F2mtFW2fK2cOtBh1cHYkQsbzFV7I+EoRKe6Yt0oK7A=="],
+
+    "@istanbuljs/load-nyc-config/js-yaml/argparse/sprintf-js": ["sprintf-js@1.0.3", "", {}, "sha512-D9cPgkvLlV3t3IzL0D0YLvGA9Ahk4PcvVwUbN0dSGr1aP0Nrt4AEnTUbuGvquEC0mA64Gqt1fzirlRs5ibXx8g=="],
+
+    "glob/minimatch/brace-expansion/balanced-match": ["balanced-match@4.0.4", "", {}, "sha512-BLrgEcRTwX2o6gGxGOCNyMvGSp35YofuYzw9h1IMTRmKqttAZZVU67bdb9Pr2vUHA8+j3i2tJfjO6C6+4myGTA=="],
+
+    "nyc/find-up/locate-path/p-locate": ["p-locate@4.1.0", "", { "dependencies": { "p-limit": "^2.2.0" } }, "sha512-R79ZZ/0wAxKGu3oYMlz8jy/kbhsNrS7SKZ7PxEHBgJ5+F2mtFW2fK2cOtBh1cHYkQsbzFV7I+EoRKe6Yt0oK7A=="],
+
+    "pkg-dir/find-up/locate-path/p-locate": ["p-locate@4.1.0", "", { "dependencies": { "p-limit": "^2.2.0" } }, "sha512-R79ZZ/0wAxKGu3oYMlz8jy/kbhsNrS7SKZ7PxEHBgJ5+F2mtFW2fK2cOtBh1cHYkQsbzFV7I+EoRKe6Yt0oK7A=="],
 
     "quick-temp/rimraf/glob/minimatch": ["minimatch@9.0.9", "", { "dependencies": { "brace-expansion": "^2.0.2" } }, "sha512-OBwBN9AL4dqmETlpS2zasx+vTeWclWzkblfZk7KTA5j3jeOONz/tRCnZomUyvNg83wL5Zv9Ss6HMJXAgL8R2Yg=="],
 
+    "quick-temp/rimraf/glob/path-scurry": ["path-scurry@1.11.1", "", { "dependencies": { "lru-cache": "^10.2.0", "minipass": "^5.0.0 || ^6.0.2 || ^7.0.0" } }, "sha512-Xa4Nw17FS9ApQFJ9umLiJS4orGjm7ZzwUrwamcGQuHSzDyth9boKDaycYdDcZDuqYATXw4HFXgaqWTctW/v1HA=="],
+
+    "test-exclude/minimatch/brace-expansion/balanced-match": ["balanced-match@4.0.4", "", {}, "sha512-BLrgEcRTwX2o6gGxGOCNyMvGSp35YofuYzw9h1IMTRmKqttAZZVU67bdb9Pr2vUHA8+j3i2tJfjO6C6+4myGTA=="],
+
+    "yargs/find-up/locate-path/p-locate": ["p-locate@4.1.0", "", { "dependencies": { "p-limit": "^2.2.0" } }, "sha512-R79ZZ/0wAxKGu3oYMlz8jy/kbhsNrS7SKZ7PxEHBgJ5+F2mtFW2fK2cOtBh1cHYkQsbzFV7I+EoRKe6Yt0oK7A=="],
+
+    "@istanbuljs/load-nyc-config/find-up/locate-path/p-locate/p-limit": ["p-limit@2.3.0", "", { "dependencies": { "p-try": "^2.0.0" } }, "sha512-//88mFWSJx8lxCzwdAABTJL2MyWB12+eIY7MDL2SqLmAkeKU9qxRvWuSyTjm3FUmpBEMuFfckAIqEaVGUDxb6w=="],
+
+    "nyc/find-up/locate-path/p-locate/p-limit": ["p-limit@2.3.0", "", { "dependencies": { "p-try": "^2.0.0" } }, "sha512-//88mFWSJx8lxCzwdAABTJL2MyWB12+eIY7MDL2SqLmAkeKU9qxRvWuSyTjm3FUmpBEMuFfckAIqEaVGUDxb6w=="],
+
+    "pkg-dir/find-up/locate-path/p-locate/p-limit": ["p-limit@2.3.0", "", { "dependencies": { "p-try": "^2.0.0" } }, "sha512-//88mFWSJx8lxCzwdAABTJL2MyWB12+eIY7MDL2SqLmAkeKU9qxRvWuSyTjm3FUmpBEMuFfckAIqEaVGUDxb6w=="],
+
     "quick-temp/rimraf/glob/minimatch/brace-expansion": ["brace-expansion@2.1.0", "", { "dependencies": { "balanced-match": "^1.0.0" } }, "sha512-TN1kCZAgdgweJhWWpgKYrQaMNHcDULHkWwQIspdtjV4Y5aurRdZpjAqn6yX3FPqTA9ngHCc4hJxMAMgGfve85w=="],
+
+    "quick-temp/rimraf/glob/path-scurry/lru-cache": ["lru-cache@10.4.3", "", {}, "sha512-JNAzZcXrCt42VGLuYz0zfAzDfAvJWW6AfYlDBQyDV5DClI2m5sAmK+OIO7s59XfsRsWHp02jAJrRadPRGTt6SQ=="],
+
+    "yargs/find-up/locate-path/p-locate/p-limit": ["p-limit@2.3.0", "", { "dependencies": { "p-try": "^2.0.0" } }, "sha512-//88mFWSJx8lxCzwdAABTJL2MyWB12+eIY7MDL2SqLmAkeKU9qxRvWuSyTjm3FUmpBEMuFfckAIqEaVGUDxb6w=="],
   }
 }

core/http/react-ui/coverage-baseline.txt

@@ -0,0 +1 @@
+38.29

core/http/react-ui/e2e/agents.spec.js

@@ -0,0 +1,24 @@
+import { test, expect } from './coverage-fixtures.js'
+
+// Agents feature page (src/pages/Agents.jsx).
+test.describe('Agents page', () => {
+  test.beforeEach(async ({ page }) => {
+    await page.goto('/app/agents')
+  })
+
+  test('renders the agents list and empty state', async ({ page }) => {
+    await expect(page).toHaveURL(/\/app\/agents$/)
+    await expect(page.getByRole('heading', { name: 'Agents', exact: true })).toBeVisible()
+    await expect(page.getByText(/No agents configured/i)).toBeVisible()
+    await expect(page.getByRole('button', { name: 'Create Agent' }).first()).toBeVisible()
+  })
+
+  test('Create Agent navigates to the agent creation form', async ({ page }) => {
+    const create = page.getByRole('button', { name: 'Create Agent' }).last()
+    await create.scrollIntoViewIfNeeded()
+    await Promise.all([
+      page.waitForURL(/\/app\/agents\/new$/),
+      create.click(),
+    ])
+  })
+})

core/http/react-ui/e2e/audio-transform.spec.js

@@ -1,4 +1,4 @@
-import { test, expect } from '@playwright/test'
+import { test, expect } from './coverage-fixtures.js'
 
 function mockCapabilities(page, capabilities) {
   return page.route('**/api/models/capabilities', (route) => {

core/http/react-ui/e2e/backend-logs.spec.js

@@ -1,4 +1,4 @@
-import { test, expect } from '@playwright/test'
+import { test, expect } from './coverage-fixtures.js'
 
 test.describe('Backend Logs', () => {
   test('model detail page shows title', async ({ page }) => {

core/http/react-ui/e2e/backends-management.spec.js

@@ -0,0 +1,28 @@
+import { test, expect } from './coverage-fixtures.js'
+
+// Backends admin page (src/pages/Backends.jsx).
+test.describe('Backends management page', () => {
+  test.beforeEach(async ({ page }) => {
+    await page.goto('/app/backends')
+  })
+
+  test('renders the management header and gallery tabs', async ({ page }) => {
+    await expect(page).toHaveURL(/\/app\/backends$/)
+    await expect(page.getByRole('heading', { name: 'Backend Management' })).toBeVisible()
+    await expect(page.getByRole('button', { name: 'Manual Install' })).toBeVisible()
+    await expect(page.getByRole('button').filter({ hasText: /^All$/ })).toBeVisible()
+    await expect(page.getByRole('button').filter({ hasText: /^Image$/ })).toBeVisible()
+  })
+
+  test('search field accepts input', async ({ page }) => {
+    const search = page.getByPlaceholder(/search backends/i)
+    await expect(search).toBeVisible()
+    await search.fill('whisper')
+    await expect(search).toHaveValue('whisper')
+  })
+
+  test('Manual Install reveals the OCI install form', async ({ page }) => {
+    await page.getByRole('button', { name: 'Manual Install' }).click()
+    await expect(page.getByPlaceholder('oci://quay.io/example/backend:latest')).toBeVisible()
+  })
+})

core/http/react-ui/e2e/chat-errors.spec.js

@@ -1,4 +1,4 @@
-import { test, expect } from '@playwright/test'
+import { test, expect } from './coverage-fixtures.js'
 
 async function setupChatPage(page) {
   // Mock capabilities endpoint so ModelSelector auto-selects a model

core/http/react-ui/e2e/chat-polling-selection.spec.js

@@ -1,4 +1,4 @@
-import { test, expect } from '@playwright/test'
+import { test, expect } from './coverage-fixtures.js'
 
 // Regression coverage for issue #9904:
 // - /api/operations was polled every 1s and *always* re-rendered the Chat

core/http/react-ui/e2e/collections.spec.js

@@ -0,0 +1,22 @@
+import { test, expect } from './coverage-fixtures.js'
+
+// Collections (Knowledge Base) feature page (src/pages/Collections.jsx).
+test.describe('Collections page', () => {
+  test.beforeEach(async ({ page }) => {
+    await page.goto('/app/collections')
+  })
+
+  test('renders the knowledge base with an empty state and create control', async ({ page }) => {
+    await expect(page).toHaveURL(/\/app\/collections$/)
+    await expect(page.getByRole('heading', { name: 'Knowledge Base' })).toBeVisible()
+    await expect(page.getByText(/No collections yet/i)).toBeVisible()
+    await expect(page.getByRole('button').filter({ hasText: 'Create' })).toBeVisible()
+  })
+
+  test('new-collection name field accepts input', async ({ page }) => {
+    const input = page.locator('input, textarea').first()
+    await expect(input).toBeVisible()
+    await input.fill('my-kb')
+    await expect(input).toHaveValue('my-kb')
+  })
+})

core/http/react-ui/e2e/coverage-fixtures.js

@@ -0,0 +1,73 @@
+// Playwright test fixture that harvests istanbul code coverage.
+//
+// When the app is built with COVERAGE=true (see vite.config.js), every source
+// module is instrumented and exposes its counters on window.__coverage__. This
+// fixture writes that object to .nyc_output/ after each test so `nyc report`
+// can merge the runs into a per-file coverage report.
+//
+// The app is a React SPA (client-side routing), so window.__coverage__
+// accumulates across in-app navigation within a single test; only a full page
+// reload / fresh page.goto resets it. Specs import { test, expect } from this
+// module instead of '@playwright/test' so collection is automatic.
+import { test as base, expect } from '@playwright/test'
+import { mkdirSync, writeFileSync } from 'node:fs'
+import { randomUUID } from 'node:crypto'
+import path from 'node:path'
+
+const COVERAGE_DIR = path.resolve(process.cwd(), '.nyc_output')
+const V8_COVERAGE = process.env.PW_V8_COVERAGE === '1'
+
+const withCoverage = base.extend({
+  // Worker-scoped V8 coverage accumulator: collects every test's native
+  // Chromium coverage and converts it to istanbul ONCE at worker teardown
+  // (conversion is expensive; see e2e/v8-coverage.js). null when V8 mode is off.
+  _v8acc: [
+    async ({}, use) => {
+      if (!V8_COVERAGE) {
+        await use(null)
+        return
+      }
+      const { createAccumulator } = await import('./v8-coverage.js')
+      const acc = createAccumulator()
+      await use(acc)
+      await acc.flush()
+    },
+    { scope: 'worker' },
+  ],
+
+  page: async ({ page, _v8acc }, use) => {
+    // V8 coverage path: collect native Chromium coverage (cheap), hand it to the
+    // worker accumulator on teardown. Avoids running an instrumented bundle.
+    if (V8_COVERAGE) {
+      const { startV8 } = await import('./v8-coverage.js')
+      await startV8(page)
+      await use(page)
+      try {
+        _v8acc.add(await page.coverage.stopJSCoverage())
+      } catch {
+        // page already closed — nothing to collect
+      }
+      return
+    }
+
+    await use(page)
+
+    let coverage
+    try {
+      coverage = await page.evaluate(() => window.__coverage__)
+    } catch {
+      // Page was already closed by the test — nothing to collect.
+      return
+    }
+    if (!coverage) return // build wasn't instrumented (COVERAGE unset)
+
+    mkdirSync(COVERAGE_DIR, { recursive: true })
+    writeFileSync(
+      path.join(COVERAGE_DIR, `playwright-${randomUUID()}.json`),
+      JSON.stringify(coverage),
+    )
+  },
+})
+
+export const test = withCoverage
+export { expect }

core/http/react-ui/e2e/import-form-ux-batch-a.spec.js

@@ -1,4 +1,4 @@
-import { test, expect } from '@playwright/test'
+import { test, expect } from './coverage-fixtures.js'
 
 // Mock /backends/known shape mirrors schema.KnownBackend. The suite covers
 // three concerns from Batch A: manual-pick badge (A1), inline ambiguity

core/http/react-ui/e2e/import-form-ux-batch-b.spec.js

@@ -1,4 +1,4 @@
-import { test, expect } from '@playwright/test'
+import { test, expect } from './coverage-fixtures.js'
 
 // Batch B — Simple / Power mode with quick switch. This suite exercises the
 // mode switch itself, the collapsible Options disclosure in Simple mode,

core/http/react-ui/e2e/import-form-ux-batch-d.spec.js

@@ -1,4 +1,4 @@
-import { test, expect } from '@playwright/test'
+import { test, expect } from './coverage-fixtures.js'
 
 // Batch D — progressive disclosure of preference fields. Power > Preferences
 // tab gates Quantizations, MMProj Quantizations, and Model Type so they only

core/http/react-ui/e2e/import-form-ux-batch-e.spec.js

@@ -1,4 +1,4 @@
-import { test, expect } from '@playwright/test'
+import { test, expect } from './coverage-fixtures.js'
 
 // Batch E — modality chip row. A horizontal chip row sits above the Backend
 // dropdown (inside the Simple-mode Options disclosure and in Power >

core/http/react-ui/e2e/import-form-ux-batch-f.spec.js

@@ -1,4 +1,4 @@
-import { test, expect } from '@playwright/test'
+import { test, expect } from './coverage-fixtures.js'
 
 // Batch F3 — Enter-to-submit on the URI input in Simple mode. Wrapping the
 // URI input + ambiguity alert + Options disclosure in a <form> means pressing