Closes#826.
1. Heading and subtext now read from `versionInfo` state (which the
Check Again mutation already populates) instead of the server-rendered
`props.system`. Previously the card kept showing "System Up to Date /
Your system is running the latest version!" alongside the new
`Latest Version` row + Start Update button after a successful recheck.
Status icon also switched to `versionInfo` for consistency.
2. The pulling-state heading rendered the lowercase status enum
(`pulling`, `pulled`, ...) and relied on a Tailwind `capitalize` class
for the visible glyph. Screen readers and other accessible-name
consumers got the lowercase value with no transform applied. Replaced
with a `STAGE_LABELS` map so visual + accessible names match.
3. The sidecar (install/sidecar-updater/update-watcher.sh) writes
`complete` for ~5s, then resets the status file to `idle`. The SPA
could miss that window across the admin container restart, leaving
the page parked on its last observed progress percentage indefinitely
while the upgrade was actually finished on disk. A `seenAdvancedStageRef`
now records whether the session ever observed an advanced stage; a
later poll seeing `idle` is treated as the missed completion, and the
page reloads as advertised in step 3 of the on-screen process. Reset
on each Start Update.
4. Toggling Enable Early Access now triggers a recheck on success, so
the eligible-version list updates immediately instead of requiring a
manual Check Again click.
Single file touched: admin/inertia/pages/settings/update.tsx.
Typecheck (tsc --noEmit) passes; static UI changes verified in source.
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* feat(content): add custom ZIM library sources with pre-seeded mirrors
Users reported slow download speeds from the default Kiwix CDN. This adds
the ability to browse and download ZIM files from alternative Kiwix mirrors
or self-hosted repositories, all through the GUI.
- Add "Custom Libraries" button next to "Browse the Kiwix Library"
- Source dropdown to switch between Default (Kiwix) and custom libraries
- Browsable directory structure with breadcrumb navigation
- 5 pre-seeded official Kiwix mirrors (US, DE, DK, UK, Global CDN)
- Built-in mirrors protected from deletion
- Downloads use existing pipeline (progress, cancel, Kiwix restart)
- Source selection persists across page loads via localStorage
- Scrollable directory browser (600px max) with sticky header
- SSRF protection on all custom library URLs
Closes#576
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(content): recognize Wikipedia downloads from mirror sources
When Wikipedia is downloaded via a custom mirror instead of the default
Kiwix server, the completion callback now matches by filename instead
of exact URL. This ensures the Wikipedia selector correctly shows
"Installed" status and triggers old-version cleanup regardless of
which mirror was used.
Also handles the case where no Wikipedia selection exists yet (file
downloaded before visiting the selector), creating the record
automatically.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(ZIM): use cheerio for custom mirror directory parsing
* fix(ZIM): use URL constructor for more robust joining
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Jake Turner <jturner@cosmistack.com>
Three UX issues from manual testing of #780 on NOMAD3.
1. Slider was unusable for multi-step zoom changes
`setLoading(true)` fired immediately on every selection or maxzoom change,
which disabled the slider until the request returned. Even with the 400ms
debounce delaying the network call, the UI was locked the whole time.
User couldn't drag through zoom levels to find the right one.
Fix: bump debounce to 1500ms, move `setLoading(true)` inside the setTimeout
so it only flips after the debounce expires. Slider stays interactive
throughout the wait. Slider `disabled` now only ties to `downloading`
(active extract dispatch), not `loading` (preflight in flight). The
existing requestId stale-safe pattern handles concurrent changes.
2. Newly-downloaded maps didn't show in Stored Map Files until manual refresh
`props.maps.regionFiles` is rendered server-side and passed through Inertia
props; without a partial reload it stayed stale until the user navigated
away and back.
Fix: watch `useDownloads({ filetype: 'map' })` count via a ref. When the
count drops (a download finished), trigger `router.reload({ only: ['maps'] })`
to refresh just the maps prop. Existing pattern from elsewhere in the
codebase.
3. Country picker didn't surface already-downloaded countries
When a user re-opened "Choose Countries" after downloading UK, UK appeared
unchecked with no indication it was already on disk.
Fix: pass installed pmtiles filenames into the modal as a prop; parse with
regex `^([a-z]{2})_[\w-]+_z\d+\.pmtiles$` to extract country codes from
single-country extracts (matching MapService.buildRegionSlug's iso2 lowercase
slug pattern). Render an "Installed" badge on those countries with a tooltip
explaining they're re-selectable for redownload at a different zoom.
Group / custom multi-country extracts don't reverse-map cleanly from
filename and are skipped here. Could be a follow-up if useful.
Files:
admin/inertia/components/CountryPickerModal.tsx
- SINGLE_COUNTRY_FILENAME_RE: iso2 + flexible date + zoom
- installedFilenames prop with default []
- installedCountrySet derivation via useMemo
- "Installed" badge rendering on country list rows
- Debounce: 400ms -> 1500ms; setLoading inside setTimeout
- Slider disabled: only on `downloading`
admin/inertia/pages/settings/maps.tsx
- import useEffect/useRef
- destructure activeMapDownloads from useDownloads
- useEffect on download count drop -> router.reload({ only: ['maps'] })
- pass installedFilenames to CountryPickerModal
All three fixes tested end-to-end on NOMAD3.
* feat(maps): add regional map downloads via go-pmtiles extract
* address Copilot review feedback on PR #780
- auto-refresh preflight on selection/maxzoom change with 400ms debounce and
requestId stale-safety so the confirm button no longer requires a two-step
"Estimate Size" -> "Start Download" dance
- safeUpdateProgress helper replaces fire-and-forget updateProgress().catch()
pattern so cancelled-job errors (code -1) can't surface as unhandled rejections
- gate world basemap source on worldBasemapReady - when ensureWorldBasemap()
fails we already delete world.pmtiles, so emitting the source was producing
404s on every tile request
- verify go-pmtiles binary SHA256 at image build time; upstream doesn't ship a
checksums file so per-arch hashes are pinned as build args with a regenerate
note when bumping PMTILES_VERSION
Content Updates had three UX problems that compounded:
1. No size column, so users had to guess how big an update would be before
clicking Update All. Upstream /api/v1/resources/check-updates doesn't
return size, so CollectionUpdateService now enriches each update with
a Content-Length HEAD request in parallel (5s timeout, non-fatal on
failure — the row just renders an em-dash).
2. Small ZIM updates (1-8 MB) never appeared in Active Downloads. Two
causes, both fixed: handleApply / handleApplyAll didn't invalidate the
download-jobs query after dispatching, and useDownloads idled at 30s
between polls — enough for a fast job to dispatch, download, and get
cleaned up by removeOnComplete before the next refetch.
3. applyUpdate didn't forward title / totalBytes to RunDownloadJob, so
any update that did briefly surface in Active Downloads had no label
and no byte-count progress, just a filename and a percentage. It now
passes both (matching zim_service's dispatch pattern).
Also parallelized applyAllUpdates so dispatching five updates doesn't
serialize five sequential BullMQ round-trips.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* feat(AI): re-enable AMD GPU acceleration for Ollama via ROCm + HSA override
Re-enables AMD GPU support that was disabled in 77f1868 pending validation
of the ROCm image and device discovery. Validation done 2026-04-28 on a
Minisforum UM890 Pro (Ryzen 9 PRO 8945HS + Radeon 780M iGPU) — Ollama
correctly offloaded all model layers to the iGPU when the container was
started with /dev/kfd + /dev/dri passthrough and HSA_OVERRIDE_GFX_VERSION=11.0.0.
On llama3.2:1b, GPU inference ran at 51.83 tok/s vs 33.16 tok/s on CPU
(same hardware, same prompt) — a 1.56x speedup confirmed by Ollama logs
showing "load_tensors: offloaded 17/17 layers to GPU".
Changes
-------
docker_service.ts
- Restore _discoverAMDDevices() (simplified — pass /dev/dri as a directory
entry, mirroring `docker run --device /dev/dri` behavior, instead of the
prior brittle hardcoded card0/renderD128 fallback that broke on systems
where the AMD GPU enumerates as card1+).
- Restore the AMD branch in _createContainer():
- Switches Ollama image to ollama/ollama:rocm
- Mounts /dev/kfd + /dev/dri via Devices
- Sets HSA_OVERRIDE_GFX_VERSION=11.0.0 (required for unsupported-but-RDNA3
iGPUs like gfx1103; harmless on supported discrete cards)
- KV opt-out via ai.amdGpuAcceleration (default on)
- Mirror the AMD branch in updateContainer():
- Lifted GPU detection above docker.pull() so AMD updates pull :rocm
rather than the standard :targetVersion tag (per-version ROCm tags
aren't always published)
- Replaces stale HSA_OVERRIDE in the inspect-captured env on update,
so containers built before this PR pick up the current value
system_service.ts
- New getOllamaInferenceComputeFromLogs() — parses Ollama startup log line
"msg=\"inference compute\" ... library=CUDA|ROCm ..." which Ollama emits
for both NVIDIA and AMD. Catches silent CPU fallback (e.g. NVML death
after update, or HSA_OVERRIDE failure) that the prior nvidia-smi exec
probe couldn't detect.
- gpuHealth refactored to use log parsing as the primary probe for both
vendors, with nvidia-smi exec retained as the NVIDIA-only secondary
path for hardware enrichment when log parsing has no startup line yet.
- AMD path uses gpu.type KV value (persisted by DockerService._detectGPUType)
+ ai.amdGpuAcceleration opt-out to determine hasRocmRuntime.
types/system.ts
- GpuHealthStatus extended additively: hasRocmRuntime + optional gpuVendor.
types/kv_store.ts
- New ai.amdGpuAcceleration boolean (default-on).
settings/models.tsx, settings/system.tsx
- passthrough_failed banner copy now reads vendor from gpuHealth.gpuVendor
("an AMD GPU" vs "an NVIDIA GPU"). Same Fix button hits the same
force-reinstall endpoint, which now configures AMD correctly.
install_nomad.sh
- AMD detection in verify_gpu_setup() upgraded from a strict-positive
"ROCm not currently available" message to "ROCm acceleration will be
configured automatically." Also tightens the lspci match to display
controller classes (avoids false positives from AMD CPU host bridges,
matching the same fix already in DockerService._detectGPUType).
Auto-remediation
----------------
Issue #755 proposes auto-remediation when gpuHealth.status flips to
passthrough_failed (today the user has to click "Fix: Reinstall AI
Assistant"). When that PR lands, AMD coverage falls out for free since
this PR uses the same passthrough_failed status code via the shared
gpuHealth machinery — #755's guard will need to flip from
hasNvidiaRuntime === true to (hasNvidiaRuntime || hasRocmRuntime).
Closes#124 (AMD GPU support).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(AI): detect AMD GPU presence inside admin container via marker file
The admin container doesn't have lspci installed, and AMD GPUs don't register
a Docker runtime the way NVIDIA does — so DockerService._detectGPUType() and
SystemService.gpuHealth had no way to know an AMD GPU was present.
The previous implementation fell through to lspci, which silently failed inside
the admin container, leaving gpu.type unset and gpuHealth stuck at 'no_gpu'
even on systems with an AMD GPU. (NVIDIA worked because Docker registers the
nvidia runtime, which is reachable via dockerInfo.Runtimes from any container.)
Discovered while testing the AMD acceleration patch on a Minisforum UM890 Pro:
the AMD branch in _createContainer() never fired because _detectGPUType()
returned 'none' even on a host with a working /dev/kfd.
Fix
---
install_nomad.sh writes the host-detected GPU type ('nvidia' | 'amd') to a
marker file in the storage volume the admin container already bind-mounts:
/opt/project-nomad/storage/.nomad-gpu-type → /app/storage/.nomad-gpu-type
DockerService._detectGPUType() reads the marker as a secondary probe (after
the Docker runtime check) — covers AMD detection from inside the container
without requiring lspci or a /dev bind mount.
SystemService falls back to the marker file when KV gpu.type is empty so the
System page reflects AMD presence even before the user installs AI Assistant
for the first time. (Without this, the page would say 'no_gpu' until Ollama
was installed, even on hosts with an AMD GPU detected at install time.)
Verified on NOMAD6 (UM890 Pro, Ubuntu 24.04, 780M iGPU): with the marker file
in place and admin restarted, the patch's AMD branch fires correctly on Force
Reinstall AI Assistant. Resulting nomad_ollama runs ollama/ollama:rocm with
/dev/kfd + /dev/dri passthrough and HSA_OVERRIDE_GFX_VERSION=11.0.0; Ollama
logs show 'library=ROCm compute=gfx1100 ... type=iGPU'. NOMAD's in-product
benchmark on the same hardware climbed from 33.8 tok/s (CPU) to 57.3 tok/s
(GPU) — a 1.69x speedup, with TTFT dropping from 148ms to 66ms.
Migration for existing AMD installs
-----------------------------------
Users on an existing NOMAD install with an AMD GPU have no marker file (the
install script wrote it on a fresh install). Two paths get them on the GPU:
1. Re-run install_nomad.sh — writes the marker, no other side effects
2. Manually: echo amd | sudo tee /opt/project-nomad/storage/.nomad-gpu-type
Either then triggers AMD detection on the next AI Assistant install/reinstall.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(AI): pull ollama/ollama:rocm separately when AMD branch overrides image
The pull-if-missing logic in _createContainer ran against service.container_image
(the DB-pinned tag, e.g. ollama/ollama:0.18.2). The AMD branch then overrode
finalImage to ollama/ollama:rocm — but if that image wasn't already local, the
container creation step failed with "no such image: ollama/ollama:rocm".
Caught while validating on NOMAD2 (Ryzen AI 9 HX 370 + Radeon 890M / RDNA 3.5):
the prior end-to-end test on NOMAD6 had silently passed because the rocm image
was already pulled there from an earlier sidecar test, masking the bug.
Fix: inside the AMD branch, after setting finalImage to ollama/ollama:rocm,
run a parallel _checkImageExists + docker.pull dance for the new tag.
Also confirmed via this validation: the same HSA_OVERRIDE_GFX_VERSION=11.0.0
override works on the 890M (gfx1150 / RDNA 3.5) — Ollama logs report
'library=ROCm compute=gfx1100 description="AMD Radeon 890M Graphics"' and
inference runs at 51.68 tok/s (matching the existing X1 Pro published tile
of 51.7 tok/s on the same hardware class). RDNA 3 (780M, gfx1103) and RDNA
3.5 (890M, gfx1150) both use the same override successfully.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* build(Dockerfile): include pciutils for lspci gpu detection fallback
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Co-authored-by: Jake Turner <jturner@cosmistack.com>
Closes#685
Content Manager now surfaces the on-disk size of each ZIM file alongside
title/summary, and lets users sort the list by Size or Title. Defaults to
Size descending so the largest files are visible first.
- ZimService.list() now stats each file and returns size_bytes
- Content Manager table adds a formatted Size column (via formatBytes)
- Sortable headers for Title and Size with asc/desc toggle
When many ZIMs are already installed locally, a single Kiwix catalog page
(12 items) could return 12 already-installed items, which zim_service
would fully filter out client-side. The endpoint returned items: [] with
has_more: true, and the frontend's infinite-scroll guard
(flatData.length > 0) blocked fetchNextPage — leaving the user with
"No records found" despite plenty of uninstalled ZIMs available.
Backend now accumulates across up to 5 Kiwix fetches (60 items each)
until it has enough post-filter results to return, dedupes by entry id,
advances currentStart by actual entries returned (not requested), and
returns a next_start cursor. The frontend consumes that cursor instead
of computing Kiwix offsets locally, and the flatData.length > 0 guard is
removed so the existing on-mount effect drives bounded auto-fetch when
a short page lands.
The pre-existing has_more off-by-one (compared totalResults against the
input start rather than the post-fetch position) is fixed implicitly.
Diagnosis credit: @johno10661.
Closes#731
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
When the OpenAI-compatible fallback (/v1/models) is used, models are mapped as { name: m.id, size: 0 } with no details field. Accessing model.details.parameter_size throws `TypeError: Cannot read properties of undefined`, which crashes the React render and causes the entire page to go blank.
New defaults:
OLLAMA_NO_CLOUD=1 - "Ollama can run in local only mode by disabling
Ollama’s cloud features. By turning off Ollama’s cloud features, you
will lose the ability to use Ollama’s cloud models and web search."
https://ollama.com/blog/web-searchhttps://docs.ollama.com/faq#how-do-i-disable-ollama%E2%80%99s-cloud-features
example output:
```
ollama run minimax-m2.7:cloud
Error: ollama cloud is disabled: remote model details are unavailable
```
This setting can be safely disabled as you have to click on a link to
login to ollama cloud and theres no real way to do that in nomad outside
of looking at the nomad_ollama logs.
This one can be disabled in settings in case theres a model out there
that doesn't play nice. but that doesnt seem necessary so far.
OLLAMA_FLASH_ATTENTION=1 - "Flash Attention is a feature of most modern
models that can significantly reduce memory usage as the context size
grows. "
Tested with llama3.2:
```
docker logs nomad_ollama --tail 1000 2>&1 |grep --color -i flash_attn
llama_context: flash_attn = enabled
```
And with second_constantine/deepseek-coder-v2 with is based on
https://huggingface.co/lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-GGUF
which is a model that specifically calls out that you should disable
flash attention, but during testing it seems ollama can do this for you
automatically:
```
docker logs nomad_ollama --tail 1000 2>&1 |grep --color -i flash_attn
llama_context: flash_attn = disabled
```
Surfaces all installed AI models in a dedicated table between Settings
and Active Model Downloads, so users can quickly see what's installed
and delete models without hunting through the expandable model catalog.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
roguesupport.com changed to rogue.support (the actual domain).
Updates href and display text in two places.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
After an update completes, the page reloads but the KV store still has
updateAvailable=true from the pre-update check. This causes the banner
to show "Current 1.30.0-rc.1 → New 1.30.0-rc.1" until the user
manually clicks Check Again.
Now triggers a version re-check before the post-update reload so the
KV store is updated and the banner reflects the correct state.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Adds a new settings page with Ko-fi donation link, Rogue Support
banner, and community contribution options (GitHub, Discord).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add a warm charcoal dark mode ("Night Ops") using CSS variable swapping
under [data-theme="dark"]. All 23 desert palette variables are overridden
with dark-mode counterparts, and ~313 generic Tailwind classes (bg-white,
text-gray-*, border-gray-*) are replaced with semantic tokens.
Infrastructure:
- CSS variable overrides in app.css for both themes
- ThemeProvider + useTheme hook (localStorage + KV store sync)
- ThemeToggle component (moon/sun icons, "Night Ops"/"Day Ops" labels)
- FOUC prevention script in inertia_layout.edge
- Toggle placed in StyledSidebar and Footer for access on every page
Color replacements across 50 files:
- bg-white → bg-surface-primary
- bg-gray-50/100 → bg-surface-secondary
- text-gray-900/800 → text-text-primary
- text-gray-600/500 → text-text-secondary/text-text-muted
- border-gray-200/300 → border-border-subtle/border-border-default
- text-desert-white → text-white (fixes invisible text on colored bg)
- Button hover/active states use dedicated btn-green-hover/active vars
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Ollama can silently run on CPU even when the host has an NVIDIA GPU,
resulting in ~3 tok/s instead of ~167 tok/s. This happens when Ollama
was installed before the GPU toolkit, or when the container was
recreated without proper DeviceRequests. Users had zero indication.
Adds a GPU health check to the system info API response that detects
when the host has an NVIDIA runtime but nvidia-smi fails inside the
Ollama container. Shows a warning banner on the System Information
and AI Settings pages with a one-click "Reinstall AI Assistant"
button that force-reinstalls Ollama with GPU passthrough.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace MIT license text with Apache 2.0 to match the repo LICENSE file,
update copyright to 2024-2026, and add Qdrant to third-party attribution.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
mem.used on Linux includes reclaimable buff/cache, which caused the
System Information page to show 97% memory usage on a 64GB machine
that actually had 53GB available. The warning banner fired at >90%
creating a false alarm.
Now uses (total - available) for the gauge, percentage, and displayed
values. Also renames "Free RAM" to "Available RAM" using mem.available
instead of mem.free, since free is misleadingly small on Linux (it
excludes reclaimable cache).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The percentage was using (total - available) / total which excludes
reclaimable buffers/cache, but the displayed "Used RAM" value uses
mem.used which includes them. This mismatch showed 14% alongside
22 GB / 62 GB. Now uses mem.used / mem.total so the percentage
matches the displayed numbers.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Inside Docker, systeminformation reports the container's Alpine Linux
distro, container ID as hostname, and no GPU. This enriches the System
Information page with actual host details via the Docker API:
- Distribution and kernel version from docker.info()
- Real hostname from docker.info().Name
- GPU model and VRAM via nvidia-smi inside the Ollama container
- Graphics card in System Details (Model, Vendor, VRAM)
- Friendly uptime display (days/hours/minutes instead of minutes only)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Removes the InstalledTier model and instead checks presence of files on-the-fly. Avoid broken state by handling on the server-side vs. marking as installed by client-side API call
Ben Gauger
chriscrosstalk
0xGlitch
Chris Sherwood
cuyua9
Ryanba
Henry Estela
Jake Turner