The Drug Reference shipped in #1137 but had no documentation. Adds a guide
covering installation, the three tabs, comparing labels, content updates,
and storage, then registers it in DOC_ORDER after Supply Depot Apps.
Written against the redesigned UI as it shipped: a single home-screen tile,
the first-open disclaimer gate, ingredient-grouped drug search, multi-select
situations, and "Compare label warnings". The guide is explicit that the
comparison view shows each manufacturer's warning text side by side and does
not calculate interactions, since that distinction matters for safety.
Download and indexing sizes match the figures already shown in the empty
state (~1.7 GB compressed, ~8-10 GB after ingestion).
No title override needed; "drug-reference" prettifies to "Drug Reference".
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Three changes that together let ARM hardware appear on the leaderboard honestly.
Shipping them separately would leave ARM half-supported either way: without the
image a Pi cannot submit at all, and without the architecture field it submits
but is indistinguishable from x86.
1. PIN THE OFFICIAL MULTI-ARCH SYSBENCH IMAGE
severalnines/sysbench publishes amd64 only, so ARM hosts could not run the
System Benchmark at all — not a graceful failure, the container simply cannot
execute. Apple Silicon could only run it under Rosetta emulation, which distorts
the measurement it is taking, and that is what drove a community macOS fork to
substitute a different benchmark and submit incomparable numbers.
Swaps to ghcr.io/crosstalk-solutions/nomad-sysbench (Debian 12 + sysbench
1.0.20+ds-5, built for linux/amd64 + linux/arm64). One digest covers both
architectures; verified that pulling the pinned manifest-list digest resolves to
arm64 on a Raspberry Pi 5 and amd64 on x86, and that RepoDigests reports the
same manifest-list digest on both — so a single allowlist entry serves both.
No rescoring: 1.0.17 -> 1.0.20 measured 1.25% apart on identical hardware with
identical flags (7170.18 vs 7259.56 events/sec), inside run-to-run noise and
~0.3% on a composite. Both digests are allowlisted server-side, so the fleet can
cross over gradually.
2. REPORT THE DIGEST ACTUALLY RESOLVED
The submission previously sent SYSBENCH_DIGEST, the constant the client was
compiled with. The leaderboard validates that field, but a constant attests to
how a client was BUILT rather than what it RAN, so any build inherits a valid
value simply by carrying the same source.
Now reads it back from the image. Uses RepoDigests (the manifest digest we
pulled by), never Id — Id is the config digest, differs per architecture, and
would never match the allowlist. Falls back to the constant if inspection yields
nothing usable, so a benchmark never fails over provenance metadata.
Still forgeable, and always will be with an open-source client. It moves the bar
from "no effort" to "deliberate", which is the distinction that matters when
judging whether a submission is a mistake or a choice.
3. RECORD CPU ARCHITECTURE AND OS
The leaderboard is a single board across instruction sets by design, with
disclosure as the fairness mechanism. Without an architecture field an ARM result
sits unlabelled beside x86 — exactly what the disclosure exists to prevent.
All three fields come from the Docker daemon, reusing the docker.info() call
_detectRunEnvironment already makes. That is deliberate: inside the admin
container os.arch() and si.osInfo() describe the CONTAINER, not the host being
benchmarked.
cpu_architecture Architecture x86_64 -> amd64, aarch64 -> arm64
os_version OSVersion '24.04' (already structured, no parsing)
os_name OperatingSystem 'Ubuntu 24.04.4 LTS' minus the version
run_environment is kept rather than replaced: "which distro" and "is this
virtualised" are different questions, and WSL2 is a real performance factor.
String handling lives in app/utils/platform_metadata.ts with unit tests, matching
the amd_hsa_override convention, so it is testable without a Docker daemon.
Unknown architectures pass through verbatim rather than being guessed at, and
os_name falls back to the full description whenever the version is missing or
absent from it — an over-long name is harmless, a wrong one is not.
Columns are nullable and the submission fields optional, so results recorded
before this shipped remain submittable.
Closes#1156
Refs #1151
DockerService.getServiceURL() resolves ai.remoteOllamaUrl ahead of the local
container, so when a remote AI host is configured the AI channel measures THAT
machine while every other channel measures this one. The submission then reports
someone else's tok/s under this hardware's CPU, RAM and disk.
Under v2 this matters more than it did under v1: ai_tokens_per_second carries
0.30 of the weight and the score is uncapped, so a remote GPU's throughput is no
longer limited by a clamp.
Adds a guard alongside the existing submit-time checks. Uses the same truthiness
predicate as getServiceURL, so the guard fires exactly when the remote routing
it is guarding against would occur. KVStore.clearValue() nulls the value and
getValue() returns null for that, so a cleared key correctly does not trip it.
Blocks submission only. Running the benchmark locally is still useful to the
operator — it just isn't a result about this box, so it shouldn't go on a board
that ranks hardware.
Known limitation: the check reads the KV at submit time, not at measurement
time, so benchmarking with a remote host and then clearing the setting before
submitting would still get through. That is a deliberate workaround rather than
an accident, and closing it properly needs a column on benchmark_results to
record how inference was reached. Worth doing if it ever shows up in practice;
not worth a migration on the evidence available.
Refs #1151
The modern-rogue pack entry landed in collections/creator-packs.json
(#1145/#1146) but its banner image was never committed, so the app fell
back to /creator-packs/modern-rogue.webp which 404s and the card rendered
without a header.
Adds the 1060x175 banner (RGB webp), matching the existing
project-nomad.webp and crosstalk-solutions.webp, generated from the
pack's source banner.png built on the pack-build workspace.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The MeshCore Web app doc listed meshcore.co.uk as the official site. The
canonical MeshCore project (github.com/meshcore-dev/MeshCore, the firmware +
protocol) declares its homepage as meshcore.io, so update the two references
in the MeshCore Web section to point there.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Validated Project NOMAD on Ubuntu 26.04 LTS across two builds (an AMD/CPU
box and an NVIDIA RTX 5060 box), so recommend 26.04 as the default going
forward. 24.04 LTS and Debian 12 remain supported.
- bug_report.yml: add Ubuntu 26.04 (Resolute Raccoon) to the OS dropdown
- README / CONTRIBUTING / FAQ: name Ubuntu 26.04 LTS as the recommended version
- getting-started.md: correct the GPU note. NOMAD's installer sets up the
NVIDIA Container Toolkit and Docker runtime automatically; the user only
needs the NVIDIA driver (via "Install third-party drivers" at OS setup)
The AI benchmark evicted resident models (forcing the benchmark model cold)
and then went straight into the timed median-of-N loop with no warm-up. On a
cold box the model-load + GPU spin-up cost landed inside the timed runs
(observed: 173s TTFT / 5.83 tok/s vs a ~80 tok/s warm steady-state), and
consecutive runs weren't isolated (a prior run left the model warm). Because
the AI channel is uncapped and ~30% of the composite, the same machine could
post a ~2x-different NOMAD Score depending on warm/cold state (888 vs 1958
observed back-to-back).
Add one discarded warm-up inference after eviction and before the timed loop
so every timed run measures warm, steady-state throughput. Cold and warm
invocations now converge on the same score. Best-effort: a warm-up hiccup
never fails the run.
Closes#1139
The submit flow discarded the real failure reason and always returned the
generic "Failed to submit benchmark results." to the UI. The most common
cause is the leaderboard's one-per-hour rate limit (HTTP 429), which left
users with no idea why their submission failed or that retrying shortly
would also fail.
- benchmark_controller: return a clear, actionable message. Name the rate
limit explicitly on 429; otherwise pass through the underlying detail
(repository error or a service validation message like "already
submitted"), falling back to the generic only when we have nothing.
- benchmark_service: attach the raw upstream `detail` to the thrown error so
the controller can surface it.
The frontend already renders the server `error` string, so no client change
is needed.
* feat(drug-reference): compact header + single dashboard tile
Phase 1 of the drug-reference redesign:
- AppLayout gains an opt-in `compact` prop (small inline logo+title) so tool
pages reclaim the ~230px the full branding block costs; drug-reference/index
opts in.
- Consolidate the two dashboard tiles (Drug Reference + When to use what) into a
single Drug Reference tile with a broadened description (/conditions already
redirects to /drug-reference).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(drug-reference): tabbed redesign — search-by-drug + by-situation + FDA data
- Split /drug-reference into three tabs (Headless UI TabGroup): 'Search by
drug', 'By situation', 'FDA data'. Each tab runs only its own direction,
which removes the two-overlapping-sections confusion.
- Search by drug: results grouped by active ingredient (IngredientGroup,
single-ingredient groups first, combos after), drug-first result rows, and a
collapsible de-jargoned filter drawer (Over-the-counter / Prescription, Form,
Sort) that auto-collapses once results land.
- By situation: multi-select symptom chips → an 'Treats all N selected'
intersection section pinned on top (computed client-side from each
situation's result set) + one union group per situation.
- FDA data: the download/ingest control + status moved behind its own tab
(the pre-ingest empty state stays the prominent download prompt).
- DrugResultRow now leads with the active ingredient (drug-first) by default,
or the brand when rendered inside an ingredient group.
- Rename 'Compare interactions' → 'Compare label warnings' to match what it does.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(drug-reference): rank situation matches single-ingredient-first
The raw FDA indication match floods a situation (e.g. Headache) with
many-ingredient homeopathic products, burying real OTC drugs and leaving the
cross-situation intersection empty. Pull a wider result set (200) and sort by
active-ingredient count ascending — not a medical judgement, the same
'single-ingredient first' principle as the drug-search grouping. Now real
drugs (acetaminophen, ibuprofen) surface on top and the 'Treats all N selected'
intersection actually finds the shared OTC options. Per-situation cards cap the
display to the top 25 (ranked), intersection uses the full set.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(drug-reference): first-open disclaimer gate + first-group-expanded
- Add a required disclaimer modal on first open of the Drug Reference (Jake's
mechanism): comprehensive not-medical-advice notice the user must acknowledge;
acceptance is saved to the browser's localStorage (versioned key) so it isn't
shown again on that browser, while new browsers/devices see it on first open.
Non-dismissible (no backdrop/Escape) — only the acknowledge button closes it.
- Search-by-drug: expand the first ingredient group by default, collapse all
subsequent groups (IngredientGroup gains an explicit defaultOpen prop,
replacing the size heuristic).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(drug-reference): intersection-first multi-select
Multiple situations now lead with the 'Treats all N selected' intersection and
only break out per-situation sections when the intersection is empty (nothing
treats all) — with a 'No single option treats all N of these' explainer. Keeps
the view combined when there's a shared answer, and only fragments as a fallback.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(drug-reference): compact header on detail/interactions/conditions pages
Apply the compact AppLayout header to the drug detail, interactions, and
condition pages so they match the redesigned index instead of the full-height
branding block.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(drug-reference): rename interactions heading to 'Compare label warnings'
Match the page heading + title to the button label, so the name reflects what
the view does (each drug's own FDA-labeled warnings side by side, not a
cross-drug interaction checker).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
_ensureCollection() runs once per document on the embed path, but only
createCollection sat behind the collectionExists guard — the
getCollections probe and the three createPayloadIndex calls fired
unconditionally every time. On large ZIM ingestions those redundant
requests consumed roughly 45% of per-document Qdrant time, making jobs
look stalled while they were slowly progressing.
Memoize ensured collections in a per-instance Set, recorded only after
every step succeeds so partial failures retry. The cache is cleared
when the Qdrant health check resets the client (server may have been
recreated), and the entry is dropped before resetAndRebuild()
recreates the collection it just deleted.
Memoizing instead of moving the index calls inside the guard keeps
missing indexes healing on collections that predate the current
payload schema.
Closes#1129
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
PR #1076 stopped forcing HSA_OVERRIDE_GFX_VERSION=11.0.0 on
"natively-supported" AMD iGPUs. That was correct for gfx1150/gfx1151
(Strix 890M / Strix Halo, which are in the bundled rocblas allowlist)
but wrong for gfx1103 (Phoenix/Hawk Point 780M/760M), which is NOT in
that list. Without the override, ollama drops the 780M with "no rocblas
support for gfx target" and falls back to CPU on a fresh AI provision.
Extract the gfx→HSA mapping into a pure, unit-tested util and map
gfx1103 → 11.0.0 (gfx1100 kernels), the value that worked on v1.33.0 and
that restores full GPU offload in the field. gfx1150/1151 stay native.
Also harden the installer's 780M detection (Hawk Point / "Radeon 780M/
760M" strings) so the gfx marker isn't silently deleted, and upgrade the
no-marker fallback log from info to warn since it can mask CPU fallback.
Generate app/data/{conditions,natural_remedies,home_remedies}.ts from the
repo-root collections/*.json via `npm run gen:curated-data`, so the JSON is the
only file edited by hand. The generated modules keep the data compiled into the
image (no runtime file read, no path fragility, which is why the data was a TS
constant), and curated_data_sync.standalone.ts fails CI if a generated module
ever drifts from its JSON.
This removes the burden of hand-keeping the .json mirror and the .ts constant in
sync. Follow-up to the review discussion on #1040.
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(drug-reference): offline FDA drug labels, conditions, and remedies
Adds an offline medical-reference feature with three coupled layers:
- Drug Reference: full-text search over openFDA drug-label indications,
a detail page per label, and a side-by-side single-drug comparison view.
A two-phase background pipeline downloads the openFDA label parts to the
storage volume (resumable) and ingests them into the search table.
- Conditions ("When to use what"): a curated spine of first-aid situations
that maps each situation to matching OTC drugs, each linking back to its
Drug Reference detail page.
- Curated remedies: hand-authored natural and home-remedy entries drawn from
US-government public-domain sources (NCCIH, CDC, MedlinePlus, FDA), shown
with their source links and the same safety disclaimers as the rest of the
feature.
The drug-reference and conditions layers are intentionally coupled: the drug
detail page shows the situations a drug treats, and the conditions controller
reads the same drug_labels table.
Safety surfaces ship as written. The amber SafetyBanner ("informational only,
not medical advice, not an FDA endorsement, not a drug-interaction checker, in
an emergency call emergency services") renders on the condition pages and the
search page; the detail and comparison pages carry their own "not a cross-drug
interaction checker" callout; and every page carries the openFDA CC0 source
citation and no-FDA-affiliation footer.
Wiring on this branch:
- start/routes.ts: the /drug-reference and /conditions page GETs plus their
/api/* groups.
- commands/queue/work.ts: the drug-download and drug-ingest queues, both at
concurrency 1. The two drug queues get a per-queue stall override
(lockDuration 1_800_000, maxStalledCount 3) because each part is one long
stream; every other queue keeps the existing 300000 default.
- inertia/pages/home.tsx: Drug Reference and "When to use what" tiles. The
icon and display_order are a starting point, open to change.
- types/kv_store.ts: the two drugReference.* keys the pipeline reads and writes.
- package.json: yauzl and stream-json (plus their @types), used by the ingest
job to stream the label JSON out of the downloaded zips.
The app reads the conditions and remedy data from the compiled TS constants in
app/data/; the repo-root collections/*.json files are the browseable mirrors.
The natural-remedies standalone test reads collections/natural_remedies.json to
assert the two stay in sync, so that file is also a test fixture.
The four standalone tests pass (drug_interactions, drug_ingest_status,
conditions, natural_remedies). tsc reports no errors in the feature code.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(drug-reference): drop a fork-internal comment reference
* fix(drug-reference): address review — defer FULLTEXT, fallback remedies prop, strip fork refs
- migration: wrap the FULLTEXT ALTER in this.defer so it runs after the
deferred createTable (was silently swallowed, index never created)
- controller: add remedies:[] to the index() error fallback (required prop)
- strip fork-internal issue/spec references from ported comments
- tsconfig: exclude tests/standalone (node --experimental-strip-types only)
- correct the varchar(768) byte-math comment; extend remedy-spine test
* fix(drug-reference): make the interaction comparison readable at five drugs
The comparison view laid its columns out on an equal-fraction CSS grid
(repeat(N, minmax(0, 1fr))), so each added drug shrank every column; at the
five-drug maximum the FDA interaction text was squeezed into unreadable slivers.
Lay the columns out with flex instead: full-width and stacked on phones, then
fixed-width columns that scroll sideways from the sm: breakpoint up, so they
never shrink below a readable width. Theme the columns with the same palette as
the rest of the page (they were on stock gray), and give the headers a fixed
min-height so columns line up when drug names wrap.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* feat(collections): route a 'dataset' tier resource to the drug pipeline
Add an optional `type` discriminator to SpecResource ('zim' | 'dataset',
absent == 'zim'), so the tier installer can carry a DB-ingested resource
alongside ZIM files. ZimService.downloadCategoryTier branches on it: a
'dataset' resource dispatches the existing FDA download+ingest pipeline
instead of RunDownloadJob, guarded against duplicate dispatch by the drug
ingest status. Every existing manifest entry has no `type` and keeps the
exact ZIM path.
Widen InstalledResource.resource_type to include 'dataset' and exclude
dataset rows from the ZIM/map catalog-update scan (datasets aren't
filename-versioned; their freshness path is separate). No dataset rows are
written yet: the InstalledResource 'dataset' row on ingest-ready, the
manifest entry, install-gating, and the downloads-aggregator integration
are follow-up commits.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* feat(drug-reference): rework into an opt-in medicine-standard tier dataset
Reshapes the offline FDA drug reference from a built-in feature into curated
content installed by selecting the Medicine / Standard tier, per maintainer
direction.
- install-state: the ingest writes an installed_resources 'dataset' row on
ready (version = the openFDA export_date), threaded installer to download to
ingest; the tier-status math and the home-tile gate read it. Manual ingests
write no row, so install-state stays tied to the curated path.
- manifest: declare the dataset in the medicine-standard tier (runtime fetches
the remote manifest, so this also needs to land upstream).
- install-gating: the drug-reference home tiles render only when installed.
- uninstall: DrugReferenceService.uninstall() stops the two drug queues, deletes
the on-disk parts, truncates drug_labels (schema kept), clears the KV markers,
and drops the install row. Best-effort, logged, scoped to drug data only.
- downloads: the download phase reports the canonical {percent, downloadedBytes,
totalBytes} shape as one drug-data card in the Active Downloads aggregator with
cancel/remove; the heavy ingest stays in the IngestStatus surface with an
Indexing handoff on the card.
- auto-update: a daily DrugAutoUpdateJob compares the manifest export_date and
re-downloads when newer, gated on installed + no active job.
typecheck clean; the drug standalone suites pass. Three points are flagged in
code for the maintainer: the InstalledResource 'dataset' approach, the tier
home, and the export_date string format.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(downloads): keep the drug download card live across all parts
The Active Downloads card filtered to the deterministic jobId, but the
download's continuations run under auto-generated jobIds (only part 0 uses the
deterministic one). So the card tracked part 0 and then vanished while parts
2..N kept downloading. The queue is concurrency 1, so collapse to whichever
single part is in flight and report the deterministic jobId: one card tracks
aggregate progress through the whole download and cancel/remove still routes.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* feat(drug-reference): co-locate a persistent safety note with affirmative remedy guidance
Add RemedySafetyNote at the head of every natural-remedy section — the two on
Drug Reference and the one on "When to use what" — so the "informational only,
not medical advice, seek real medical care in an emergency" framing appears with
the guidance itself, not only in the page-top banner. Replaces the terse
per-section caveat with the same amber alert language as SafetyBanner.
Addresses the upstream #1040 review request that the disclaimer be unmistakable
and present wherever affirmative self-care guidance appears, not a one-time banner.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(drug-reference): fold dataset freshness into the content-auto-update path
The drug dataset auto-updated on its own daily cron that ignored the
contentAutoUpdate.* master switch, so it would refresh even with content
auto-update turned off, and it didn't ride the content-update path the way
ZIMs and maps do.
Move the export_date freshness/apply orchestration onto
DrugReferenceService.attemptAutoUpdate(), add
ContentAutoUpdateService.attemptDrugDataset() gated on the same enabled +
window config, and have the hourly ContentAutoUpdateJob drive both. Retire
the standalone DrugAutoUpdateJob. The ZIM/map attempt() path is unchanged.
Addresses the upstream #1040 request to wire the openFDA export_date check
into the content updater so the dataset updates alongside ZIMs and maps.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* feat(drug-reference): strengthen the remedy note to consult a clinician before combining with meds
Widen the affirmative-remedy safety note from "talk to a clinician before use"
to explicitly cover using a remedy AND combining one with a medication the user
already takes — the interaction case is the higher-risk path for an off-grid
user self-treating.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* feat(drug-reference): gate affirmative remedy content behind an off-by-default flag
Add drugReference.remediesEnabled (default off), independent of the tier
install. When off, the server emits no remedy data at any boundary — the
drug-reference page prop, conditions show, and the /api/conditions/drugs
situation search — and the "Natural" filter is hidden, so installing the
medicine-standard tier lights up the verbatim FDA label search and the
condition-to-OTC matching but not the hand-authored self-care and herbal
sections. No user-facing toggle: it is flipped on after a clinician content-pass.
Implements the upstream #1040 split-by-risk request: the regulated label content
ships with the tier; the authored remedy guidance stays gated until sign-off.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: Jake Turner <52841588+jakeaturner@users.noreply.github.com>
Replaces the stale 40.5 placeholder (a llama3.2:1b CPU-era number) with 13.2,
measured on the Reference Build (NOMAD6, 780M) under the v2 AI harness with
llama3.1:8b and iGPU acceleration (OLLAMA_IGPU_ENABLE — the provisioning fix in
PR #1074). This is the AI channel's reference for the uncapped v2 score.
Must ship together with #1074 in v1.34.0: the reference assumes iGPU-accelerated
AMD boxes, so shipping it without the iGPU fix would score AMD installs on CPU
numbers against a GPU bar. The exact value gets a final confirm against the
shipping Ollama config before GA.
Must stay byte-identical to the leaderboard's score_service.ts REFERENCE_SCORES_V2
(the server recomputes the score on submit); the matching leaderboard change is a
sibling PR. Changing the leaderboard reference has no effect on existing rows —
the v1->v2 backfill neutralizes the AI channel (ratio 1 regardless of the
reference), and there are no real v2 submissions yet.
Sibling to the Score v2 app client (#1094); stacked on it (same file/constant).
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Shows a dismissible dashboard banner to users who submitted a benchmark under
v1 scoring but don't yet have a Score v2 result, nudging them to re-run so the
community leaderboard gets their v2 number.
- Show logic (benchmark_service.shouldShowRerunBanner): has a result with
submitted_to_repository=true AND no result with nomad_score_v2 AND the
dismiss KV isn't set. Self-clears two ways — dismiss sets the KV, and any v2
run gives a result a nomad_score_v2 so the condition flips off on its own.
- New GET /api/benchmark/rerun-banner + useBenchmarkRerunBanner hook (mirrors
useUpdateAvailable), rendered as a dismissible Alert on the dashboard with a
"Re-run benchmark" CTA to /settings/benchmark.
- New KV key benchmark.rerunBannerDismissed (boolean) in both KV_STORE_SCHEMA
and the SETTINGS_KEYS whitelist (the PATCH /system/settings validator enum);
dismiss writes it via the existing updateSetting endpoint + invalidates the
query.
Sibling to the Score v2 app client (#1094); stacked on it for the
nomad_score_v2 column. Browser-verified on the NOMAD3 dev env: show/dismiss/
reload-persist/self-clear-on-v2 all correct.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Phase 4 of the NOMAD Score v2 effort (stacked on #1089). Captures the raw
channel values the leaderboard scores from, computes the uncapped v2 score
in-app (byte-matching the leaderboard's server-side recompute), submits the
v2 payload, and surfaces it in the benchmark UI.
- Capture raws: per-channel sysbench values + O_DIRECT disk (W4), single/multi
thread CPU + memory, W6 consistency companions, and run-environment metadata
(run_environment, storage_path_type, gpu_compute_detected, #1016).
- AI hardening: reference model llama3.1:8b, num_predict=256, VRAM eviction
before the run + unload own model after, pre-flight disk check (~6.5GB, only
when the model is uncached), median-of-3 run (W7).
- Score: _calculateNomadScoreV2 (uncapped, reference->1000) byte-matches the
leaderboard recompute. nomad_score_v2 stays null unless a full run with AI.
- Payload: submitToRepository sends the v2 raws + score alongside legacy v1.
- UI: v2 headline score, legacy v1 as secondary, raws/env in details.
- Migration: 13 nullable columns; double (not knex float(8,2)) so millions-scale
raws keep full precision and don't break the leaderboard byte-match.
Reference constant REFERENCE_SCORES_V2.ai_tokens_per_second is still the stale
40.5 placeholder (TODO in source); locking it to the measured 13.2 is a
follow-up gated on the AMD iGPU fix (#1074). Live prod v2 submit is separately
blocked by the leaderboard TTFT floor (tracked in the leaderboard follow-up).
Verified on NOMAD3 (RTX 5060) dev env: migration applies, raws recorded,
v2 score computed, backend + benchmark.tsx typecheck clean.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
An install that never went online while visiting /maps never provisions
world.pmtiles (it is lazily extracted from the internet), leaving the map
blank/grey offline outside any downloaded regional extracts.
Detect the world basemap's presence on disk and surface it to the UI so:
- /maps shows a clear notice explaining the base map isn't downloaded and
how to fix it, instead of a silent grey screen.
- /settings/maps offers an explicit "Download Base Map" action (~15 MB) to
provision it deliberately while online.
Adds MapService.checkWorldBasemapExists() / provisionWorldBasemap(), a
POST /maps/setup-world-basemap endpoint, and threads worldBasemapExists
through the maps page props.
Refs #1030
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat(AI): per-model thinking toggle with global default (off)
Stop forcing thinking on for every capable model. Adds a global default
(ai.autoThinking, ships OFF) and a per-model override in the chat window,
shown only for thinking-capable models and remembered client-side.
The /v1 (OpenAI-compat) endpoint ignores `think`; reasoning_effort is the
real lever. The controller resolves per-request preference -> global default
-> OFF (gated on capability), and the service maps that to reasoning_effort
('none' to suppress on a capable model, 'medium' for gpt-oss, unset to let a
capable model default thinking on). A new thinkingCapable flag keeps
non-Ollama backends from ever receiving reasoning_effort.
installed-models is enriched with a `thinking` flag (checkModelHasThinking,
now memoized) so the picker knows which models get the toggle.
Stacks on #1078 (reasoning-field read + client-disconnect abort).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(AI): thinking toggle as NOMAD Switch + info tooltip
Address review feedback on the per-model thinking control:
- Use the shared Switch component (matches AI Assistant settings) instead
of a raw checkbox.
- Label "Thinking:" with a colon to match the adjacent "Model:" label.
- Add an InfoTooltip explaining what thinking does and where the default
lives. Extend InfoTooltip with optional `position` ('top'|'bottom') and
`align` ('center'|'right') so it opens downward and expands leftward from
the right-edge header slot instead of being clipped/crushed against the
viewport edge. Defaults preserve existing (benchmark page) behavior.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(creator-packs): backend rail for gated creator content packs
Phase 1 of Creator Packs: the app-side download rail for per-creator
video ZIMs served from the private R2 bucket behind the entitlement
Worker. No UI yet (Phase 2).
- Thread optional requestHeaders through the download util + job so the
ZIM fetch can carry `Authorization: Bearer <APP_KEY>` on both the HEAD
probe and the GET stream (Worker streams the ZIM directly, gated).
- Add resourceMetadata.skip_embedding and gate the RAG/EmbedFileJob
branch on it so video ZIMs are never sent to the knowledge base.
- New creator_packs ManifestType + creatorPacksSpecSchema (display
metadata only, no url) + CollectionManifestService wiring and
getCreatorPacksWithStatus() status join.
- collections/creator-packs.json catalog with the two seed packs.
- CreatorPackService.installPack: ensure Kiwix (auto-install if absent),
resolve the stable Worker URL, dispatch the gated download with
skip_embedding. Typed result codes.
- CreatorPacksController + GET/POST /api/creator-packs routes.
- CREATOR_PACKS_APP_KEY / CREATOR_PACKS_WORKER_BASE env (release-injected
key; app degrades to a clear not_configured error when unset).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(creator-packs): Phase 2 UI — Content Explorer, settings page, wizard step
Adds the three user-facing surfaces for Creator Packs on top of the Phase 1
backend rail. All surfaces HIDE entirely on builds without the release-injected
key (configured=false) so a fork never shows a broken install button.
- Backend: CreatorPackService.isConfigured() + `configured` flag on the
GET /api/creator-packs response; /settings/creator-packs route + controller
action.
- api client + useCreatorPacks hook (shared cached source of configured/packs/
downloads for every surface) + CreatorPackCard (status badges, art fallback,
update pill) + CreatorPacksSection (install-on-click grid + confirm modal with
the license note), reused by the Content Explorer block and settings page.
- Content Explorer: Creator Packs section before Additional Content.
- Settings: new /settings/creator-packs manage page + conditional nav item.
- Easy Setup wizard: new Creator Packs step after Content. Replaces the fragile
hardcoded AI-skip math with a computed activeSteps list so the two optional
steps (Creator Packs + AI) navigate correctly in every on/off combination;
selection state, storage projection, review summary, and finish-install wired.
Browser-tested on NOMAD3 across all surfaces (configured + fork paths), incl.
live install→download→cancel and AI-on/off wizard renumbering.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(creator-packs): use branded pack banners on the cards
Replace the generic colored-block cards with the branded 1060x175 banners we
build into each pack ZIM, shown on both the settings page and the Easy Setup
wizard step (and the Content Explorer block, via the shared card).
- Bundle the seed-pack banners as local webp under admin/public/creator-packs/
so they render offline (no external image dependency, matching the existing
/rogue-support-banner.webp convention).
- CreatorPackCard is now banner-forward: the banner is the hero, with a compact
status/metadata footer (videos · size, Installed/Downloading/Selected/Install,
update pill). Falls back to a simple header if an image is ever missing.
- Prefer an optional catalog `banner_url` (future remote creators) over the
bundled-by-id path; add banner_url to the CreatorPack type + validator.
- Widen the card grids to 1–2 columns since banners are wide.
Browser-tested on NOMAD3: banners render on the settings page and wizard step;
selection/installed/downloading states and storage projection still correct.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(creator-packs): Phase 3 — uninstall, license, release key-injection
Completes the Creator Packs feature.
- Uninstall: CreatorPackService.uninstallPack reuses ZimService.delete (removes
the ZIM, drops it from the Kiwix library, clears the InstalledResource) behind
DELETE /api/creator-packs/:id. A trash control on installed cards appears only
on the settings "manage" surface (allowUninstall) — never on the Content
Explorer block or the wizard — with a danger confirm modal.
- License: draft "Project NOMAD Creator Pack License v1.0" at
collections/creator-pack-license.md (marked DRAFT — pending legal review;
personal-use, no-redistribution, official-channel-only, creators retain
copyright). The install modal links to it ("View license").
- Release key-injection: Dockerfile ARG/ENV CREATOR_PACKS_APP_KEY in the runtime
stage (empty default → source/CI builds ship unconfigured and hide the UI) +
build-primary-image.yml passes it from the CREATOR_PACKS_APP_KEY CI secret.
NOTE FOR JAKE: add that repo secret = the entitlement Worker's key.
- Update flow was already functional (installed-with-update cards → "Update
pack"); verified.
Browser-tested on NOMAD3: uninstall round-trip (file + DB row + kiwix library
cleaned, then reinstalled), settings-only uninstall control, install-modal
license link, and the "Update available" pill via a temporary catalog bump.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(downloads): clean up header merge logic
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: jakeaturner <jturner@cosmistack.com>
* fix(rag): add proper .docx text extraction via mammoth
.docx files were classified as plain text and routed through raw-text
extraction (extractTXTText). Since .docx is a ZIP archive containing XML,
this produced garbage content in the Knowledge Base — XML tags and binary
noise instead of the actual document text.
Adds a dedicated 'docx' file type (split out of the generic 'text' bucket
in determineFileType) and a mammoth-based extractor that parses the
document XML properly.
* fix: clean up package-lock.json diff
* chore(deps): pin mammoth version
---------
Co-authored-by: John Cortright <jcortright@zscaler.com>
Co-authored-by: jakeaturner <jturner@cosmistack.com>
* feat(rag): add subject/collection organization to knowledge base
- Add nullable collection field to KbIngestState, propagated through the
embed job, RAG service, and Qdrant point payloads (indexed for filtering)
- Add upload-time category selection and per-file collection reassignment
in the Knowledge Base modal, with a filterable Stored Files table
- Add a 'Search in' collection filter to the chat interface, threaded
through to searchSimilarDocuments as an optional Qdrant filter
- Fix .docx extraction: previously routed through raw-text extraction
(garbage output for a ZIP-based XML format); adds a proper mammoth-based
extractor and a dedicated 'docx' file-type case
* feat(rag): support dynamic KB collection creation, rename, and removal
Extends collection organization with a Manage Collections UI: collections
are created on the fly when a file is assigned to a new name, can be
renamed (bulk-updates every tagged file and Qdrant point), and can be
removed (reassigns tagged files back to Uncategorized rather than
deleting anything).
* fix(rag): use dynamic collections query in chat search filter
chat/index.tsx still imported the static KB_COLLECTIONS constant for its
'Search in' dropdown, inconsistent with KnowledgeBaseModal.tsx which already
uses the live getKnowledgeCollections() query. Renamed/added collections
via the new Manage Collections UI weren't reflected in the chat filter.
* feat(rag): broaden preset tags and add creatable collection combobox
Replaces the survival-specific preset list with general-purpose starter
tags (recipes, diy, health, technology, finance, travel, hobbies,
reference, survival, energy) so the Knowledge Base reads well for
home-lab/reference use, not just prepping.
Adds sanitizeCollectionName() (trim, lowercase, length cap) applied on
every write path server-side, and a dependency-free CollectionCombobox
component replacing the plain <select> + window.prompt pattern for
tagging — autocompletes against presets + tags already in use, with a
'+ Create' option for anything new.
* chore(rag): remove .docx fix from this branch, split into #1100
Per review feedback, the .docx extraction fix is unrelated to the
collections feature and can merge independently. Moved to a standalone
PR (Crosstalk-Solutions/project-nomad#1100) off dev.
* chore: remove unrelated diff noise (lockfile, comments, indentation)
---------
Co-authored-by: John Cortright <jcortright@zscaler.com>
Score v2 Phase 1. Safe under v1 — no scoring, weight, reference, or
submission-payload changes; only the benchmark's failure behavior and
forensic metadata.
- Fail-on-parse-miss (W3): the four SCORED sysbench metrics (CPU
events/sec, memory ops/sec, disk read/write MiB/s) now THROW when the
regex misses or the value is <= 0, instead of silently returning 0.
A parse failure (e.g. an upstream image output-format change) now
fails the run with a clear error via the existing _runBenchmark
try/catch, rather than submitting a phantom zero sub-score. Secondary/
informational fields keep their existing defaults.
- Pin sysbench by digest (W3): severalnines/sysbench@sha256:64cd003b...
(was :latest), so a latest-tag format change can't break the parsers
fleet-wide. Digest validated on the NOMAD6 reference build.
- Record provenance (W7): sysbench_digest + ollama_version (from Ollama
/api/version, null-tolerant) stored on each result. New nullable
columns + additive migration.
Verified: pinned digest pulls/runs/parses on NOMAD3; migration applies
(columns present); typecheck clean.
Part of the NOMAD Score v2 effort.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
A System-Only or AI-Only run is a partial result, not the NOMAD Score
(which is the full-benchmark composite). Two problems addressed:
1. Scoring bug: AI-only runs were NOT renormalized. _calculateNomadScore
always added the system weights (0.60) to the denominator even for an
AI-only run (default-zero system scores), so an excellent AI-only run
scored ~39.8 -- scaled against the full NOMAD 100 where AI is only 40%
-- while system-only already renormalized correctly. Fix: pass
systemScores only when the system benchmarks actually ran, so AI-only
renormalizes to its own 0-100 (39.8 -> ~99.7). Full and System-only
scores are unchanged.
2. Presentation: partial runs were shown with the full "NOMAD Score"
label + big gauge, outweighing the small "Partial" notice. Now partial
runs are relabelled "System Score" / "AI Score" with a PARTIAL badge,
a muted (neutral) gauge + number, and a "run a Full Benchmark for your
NOMAD Score" CTA -- applied to both the persistent score section and
the Phase 3 ScoreReveal via a shared getScoreDisplay() helper. Adds a
`muted` prop to CircularGauge.
Browser-validated on NOMAD3: AI-only now shows "AI Score" + PARTIAL,
muted gauge, 99.7 (was 39.8); Full still shows "NOMAD Score" green.
Implements the display-layer fix from the Score v2 red-team's W2; the
AI-ceiling saturation (W1) remains v2 work.
Part of #1082.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Phase 3 of the live benchmark run experience.
- ScoreReveal: replaces the abrupt run-view unmount with a deliberate
end-of-run "REPORT" card -- animated NOMAD score gauge + odometer
count-up number, sub-score gauges cascading in, Continue button +
5s auto-dismiss. Takes score scale as a prop so it survives Score v2.
- GPU-util overlay (NVIDIA): during the AI stage, a ~1Hz nvidia-smi poll
inside the Ollama container feeds live GPU utilization + VRAM into the
telemetry frames; shown in the AI hero, hidden when absent (AMD/none).
Poller is side-effect-only and cleared in a finally -- scored numbers
unchanged.
- Disk polish: reset in-test buffers on stage transition so the write
stage no longer briefly shows the carried disk-read value.
Browser-validated on NOMAD3 (RTX 5060): GPU overlay live (1% util,
0.2/8.0 GB VRAM during model load); reveal cascade + count-up; AI-only
score 39.8 (scored path unchanged).
Part of #1082 (tracker stays open).
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Phase 2 of the live benchmark run experience. Streams sysbench
--report-interval=1 interim lines over a Docker attach so the run view
shows authoritative in-test CPU events/sec and disk read/write MiB/s
(overlaying the Phase 1 host-proxy disk numbers), and fills a
"results so far" strip as each stage completes.
- _runSysbenchCommandStreaming: attaches to the container output for
live onLine callbacks, but returns the authoritative output via
container.logs() after exit -- byte-identical to _runSysbenchCommand,
so the SCORED numbers are unchanged (attach 'data' can flush after
container.wait() resolves, which would truncate the final report).
- CPU + disk stages stream interim eps: / reads:/writes: MiB/s into
setStageMetric; memory stays non-streaming (too fast to sample).
- _emitPartialResult broadcasts each finished stage's raw result on the
progress channel; useBenchmarkRun accumulates them; ResultsSoFar
renders the chip strip.
- Frontend: live CPU ev/s readout+sparkline, disk hero switches to
"Benchmark throughput" when in-test numbers arrive.
Browser-validated on NOMAD3 (System-Only): CPU 6536 ev/s live, disk
10399 MB/s benchmark throughput, results strip, final score 68.3.
Part of #1082 (tracker stays open for Phase 3).
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Phase 1 of the live benchmark-run experience. Replaces the opaque (and
in sync mode, simulated) progress bar with a real-time run view driven by
actual host telemetry.
- Async run path: the UI now dispatches to the queue worker and keys off
SSE instead of faking stage progress with client-side timers.
- New BenchmarkTelemetrySampler broadcasts per-core CPU load, CPU temp
(best-effort, hidden when unavailable), and disk MB/s at 1 Hz over a new
benchmark-telemetry SSE channel. Runs in the orchestration process, never
the sysbench container, so it cannot affect scores.
- BenchmarkProgress carries the ordered stage plan + index so the frontend
renders a live stage rail.
- AI benchmark streams /api/generate for live tokens/sec and true TTFT; the
scored numbers still come from Ollama's authoritative final eval fields.
- Frontend: useBenchmarkRun hook owns both subscriptions; self-contained SVG
components (StageRail, CoreGrid, Sparkline, LiveReadout) + BenchmarkRunView,
styled in the desert palette. No chart library added.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The Content Explorer remote list already filters out installed ZIMs client-side
(flatData excludes localNames), but the installed-files query has
refetchOnWindowFocus disabled and was never invalidated on download completion.
So when a ZIM finished downloading it dropped off the active-downloads list
(isDownloading -> false) while localFiles stayed stale (isPresent -> false),
letting the just-installed ZIM reappear as a ghost entry until the page remounted.
Add an effect that invalidates the ['zim-files'] query whenever a job drops off
the polled downloads list, so the completed install is picked up and pruned.
Fix originally diagnosed by @johno10661 in #771; reimplemented focused onto
current dev (the accumulated-page/filter groundwork already landed via #731).
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
download.kiwix.org routes the large Wikimedia-family ZIMs (Wikipedia,
Wikiversity, Wikibooks — including the flagship full Wikipedia) to
dumps.wikimedia.org, which enforces a User-Agent policy and returns HTTP
403 for requests with a missing or generic (axios/x) User-Agent. Because
doResumableDownload sent no User-Agent, every Wikimedia-hosted ZIM failed
to download while Kiwix-mirror-hosted ZIMs succeeded — so a curated set or
Easy Setup run would silently stall on exactly the highest-value content.
Add a descriptive User-Agent to the HEAD and GET requests. Verified
against the live mirror: default/empty UA -> 403, ProjectNOMAD UA -> 200/206.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Surface post-upgrade release highlights on the Command Center: a
dismissable banner keyed to the running build's release line (major.minor).
It appears when a user upgrades into the line and every patch within it,
then disappears on the next minor. Dismissal is remembered per-line in
localStorage, so dismissing v1.34 won't suppress a future v1.35 note.
Reuses the existing dismissable Alert component and the dashboard's top
banner slot; reads the running version from the appVersion shared prop.
No schema or migration needed — to surface a new release's highlights,
bump WHATS_NEW.version and replace its highlights.
Initial content: Creator Packs and the offline Medication Reference.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Step 1: remove the "Additional Tools" (Notes/Data Tools) section from
onboarding and point users to Supply Depot, the browsable app catalog,
for everything beyond the three core capabilities.
Step 2: add a note that individual countries and a full global map can
be installed any time from the Maps Manager.
Step 4: default the KB auto-index policy to "Ask me first" (Manual)
instead of "Yes, always" — auto-indexing has cost/resource implications
a non-technical user won't anticipate from the toggle alone.
ollama_service: the recommended-models fallback only fired on a null
result, so a successful-but-empty upstream response (models: []) showed
"No recommended AI models available" and poisoned the 24h cache. Now the
fallback fires on empty too, empty results are never cached, empty caches
are ignored, and the upstream request has a 10s timeout.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The Debug Info bundle carried no storage-path info, which stalled diagnosis of
relocation issues like #1050 (moved data not seen by the admin). Add the fields
support actually asks for, all best-effort so one failure never blanks the bundle:
- Storage: resolved host storage root (#938), container path, whether
NOMAD_STORAGE_PATH is set, and the Kiwix library book count (0 books is the
tell for an empty/wrong-path library).
- Docker Engine version (reporters currently paste it by hand; needed for
container/updater issues).
- GPU passthrough health (gpuHealth.status + detected gpu.type) for the
passthrough-lost-after-update class (#755/#878).
- Auto-update status for core/apps/content plus any auto-disabled reason,
since the auto-update trilogy shipped.
Adds a public DockerService.getHostStorageRoot() wrapper over the existing
#938 resolver.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The uninstall and update scripts called header_red() and referenced color
variables (GREEN/RED/RESET) that were never defined, so running them printed
"header_red: command not found" instead of the section banners. Also corrects
the update script's success message (it said "installation completed" and
pointed at an undefined ${nomad_dir} path) and fixes two spelling typos.
- uninstall_nomad.sh: add Color Codes block + header_red()
- update_nomad.sh: add header_red(); fix success wording and start_nomad.sh path
- CONTRIBUTING.md, admin/constants/ollama.ts: spelling fixes
Reported by @fix2015 in #1058; reimplemented in-house.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Two defects made chat hang forever with thinking-capable models on the OpenAI-compat
(/v1) path, which NOMAD uses for both local and remote Ollama:
1. Field mismatch. chatStream()/chat() read `delta.thinking` / `message.thinking`,
but Ollama's /v1 endpoint emits thinking tokens as `reasoning`. All thinking output
was silently dropped, so the SSE stream was nothing but empty content+thinking chunks
and never reached done. Now read `thinking ?? reasoning` in both paths (the inline
<think>-tag parser for other backends is unchanged).
2. No abort on client disconnect. When the user gave up and closed the chat, the
upstream generation kept decoding server-side. With Ollama's default
OLLAMA_NUM_PARALLEL=1 that abandoned request occupied the only slot, so every later
chat/RAG request queued behind it and the whole assistant appeared dead. The
controller now wires an AbortController to the response 'close' event and threads the
signal into the OpenAI SDK request, so a disconnect aborts the upstream generation.
Verified on NOMAD2 (qwen3:0.6b, which reports the `thinking` capability and emits
`reasoning` on /v1): before, the stream was endless empty chunks; after, thinking streams
visibly and reaches done. On disconnect, Ollama's decode counter freezes and the server
logs `cancel task` / `slot release`, freeing the slot for the next request.
Note: thinking is still force-on for capable models here; a user-facing per-model
thinking toggle (default off) is a planned follow-up.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Homebox >= 0.26 (ghcr.io/sysadminsmedia/homebox:0.26.2) panics at boot unless
HBOX_AUTH_API_KEY_PEPPER is set to a >= 32-byte value. The seeder ships no Env
block, so every clean install crash-loops immediately.
Generate a per-install pepper, persist it in the KV store
(apps.homebox.apiKeyPepper), and inject it as HBOX_AUTH_API_KEY_PEPPER at every
container-create path. The pepper is generated once and reused: rotating it would
invalidate every API key a user has issued from Homebox.
Inject at all three create paths so no lifecycle action drops it:
- _createContainer (install / force-reinstall)
- the service update path (heals a pre-fix container on update)
- recreateCustomAppContainer (the Edit / reconfigure rebuild — the in-app docs
tell users to add HBOX_OPTIONS_ALLOW_REGISTRATION=false via Manage > Edit,
which rebuilds Env from container_config alone and would otherwise drop the
pepper and re-trigger the crash loop)
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The current ollama:rocm image bundles ROCm 7.2, which natively supports the
RDNA 3/3.5 mobile parts (780M gfx1103, 890M gfx1150, Strix Halo gfx1151).
Forcing HSA_OVERRIDE_GFX_VERSION=11.0.0 coerces them onto gfx1100's kernels:
unnecessary on the 890M and a source of faults on the 780M, which lacks the
gfx1100 WMMA instructions those kernels use.
- Map gfx1103/gfx1150/gfx1151 to no override (was 11.0.0) so ROCm discovers
them natively.
- Change the no-marker default from 11.0.0 to null. A hardcoded default gets
more wrong as ROCm adds native targets; native discovery is the safer
forward-looking default. Hardware that still needs coercion (e.g. RDNA 2
iGPUs on an install without the gfx marker) can force a value via the
ai.amdHsaOverride KV.
- Keep gfx1031..gfx1036 (RDNA 2 iGPUs like the 680M) on 10.3.0 — still not
natively supported.
Verified on NOMAD2 (Radeon 890M): after a Force Reinstall the container has
no HSA_OVERRIDE, Ollama discovers the GPU as its native gfx1150 with the
rocm_v7_2 libraries, and a model loads at 100% GPU with no faults.
Depends on #1056 context; see companion issue for the 780M follow-up.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Ollama's scheduler drops integrated GPUs unless OLLAMA_IGPU_ENABLE=1 is set.
NOMAD sets HSA_OVERRIDE_GFX_VERSION for AMD but never this flag, so AMD APUs
(780M/890M/8060S) silently fell back to CPU-only inference despite correct
/dev/kfd and /dev/dri passthrough.
Set OLLAMA_IGPU_ENABLE=1 whenever AMD acceleration is configured, on both the
install and update provisioning paths. The flag is a no-op on discrete AMD
cards, so it's safe to set unconditionally within the AMD branch. On the update
path we also strip any prior value so containers provisioned before this change
pick up the flag on their next update.
Verified on NOMAD2 (Ryzen AI 9 HX 370 / Radeon 890M): before, Ollama logged
"dropping integrated GPU" and ran on CPU; after, it reports the 890M as an
iGPU ROCm inference device and models load at 100% GPU.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Wordmark application filed (USPTO serial 99912179). Mark the
persistent Command Center footer wordmark (both the AppLayout footer
and the settings/docs sidebar footer) and the first mention on the
Legal Notices page. Browser-tab titles and body copy left unmarked.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
