Commit Graph

26 Commits

Author SHA1 Message Date
jakeaturner
a9c48fc098 refactor(AI): single source of truth for embedding model name
Lift the hardcoded 'nomic-embed-text:v1.5' string out of both
RagService and OllamaService into a shared EMBEDDING_MODEL_NAME
constant in constants/ollama.ts. The duplicate in OllamaService
existed only to dodge a circular import with RagService; the
constants module has no service imports, so a shared constant
eliminates both the duplication and the drift risk called out
in the inline "keep in sync" comment.
2026-05-20 10:16:00 -07:00
chriscrosstalk
8eb8809154 feat(KB): Always/Manual ingest policy toggle (RFC #883 §1/§4) (#894)
* feat(KB): per-file ingest state machine (Phase 1 of RFC #883)

Adds a persistent state machine for AI knowledge-base ingestion so the
scanner can distinguish "fully indexed", "user opted out", "failed", and
"stalled" from each other — none of which were derivable from the prior
binary "any chunks in Qdrant ⇒ embedded" check.

## What lands

- New table `kb_ingest_state` keyed by `file_path` with enum state column
  (`pending_decision | indexed | browse_only | failed | stalled`).
  Independent of `installed_resources` so it covers both curated downloads
  and manually-uploaded KB files.
- New KV key `rag.defaultIngestPolicy` (string: `Always | Manual`).
  Registered now but not consumed yet — JIT prompt + wizard step land in
  Phase 3 of the RFC.
- `EmbedFileJob.handle` writes state on terminal outcomes:
  - Success (final batch) → `indexed` + chunks count
  - `UnrecoverableError` → `failed` + error message
  - Retryable errors are left to BullMQ's existing retry path
- `scanAndSyncStorage` swaps the binary qdrant check for a state-aware
  decision tree (see `decideScanAction`). Existing installs auto-backfill
  on first scan: files with chunks in Qdrant but no state row become
  `indexed`; new files start as `pending_decision`.
- `deleteFileBySource` drops the state row last, so removed files
  disappear entirely instead of leaving an orphan that the next scan
  would re-dispatch into nothing.

## What does NOT land here

- Ratio registry (separate PR) — needed for partial-stall detection and
  cost estimates, but a separable concern.
- #880 follow-up initial-progress anchor (separate tiny PR).
- Phase 2 UI (status pill, per-card actions, conditional warnings).
- Phase 3 policy surfaces (wizard step, JIT prompt, guardrail modal).
- PR #886's bulk-action hookup — `_deletePointsBySource` / Re-embed All
  / Reset & Rebuild would also want to set state, but #886 isn't merged
  yet; that wiring goes in a follow-up once #886 lands.

## Target

This is forward work for v1.40.0 (RFC #883). Branching off `rc` because
that's the current latest base and post-GA Jake will sync rc→dev; a
retarget at PR-open time is a fast-forward if requested.

## Tests

- 9 new unit tests for `decideScanAction` covering all five states plus
  the no-row / chunks-present / chunks-missing combinations
- Type-check clean
- Smoke-tested end-to-end on NOMAD3 via hot-patch:
  - Backfill: 5 ZIMs + 2 KB uploads with existing chunks in Qdrant all
    came back `indexed` on first scan
  - Pending dispatch: a video-only ZIM with no chunks (`lrnselfreliance`)
    came back `pending_decision` and was correctly re-dispatched (Bull
    deduped to its historical `:completed` jobId — bgauger's #886 fix
    drains that)
  - Delete hook: deleting a KB upload via `DELETE /api/rag/files`
    removed both the disk file and the state row

* feat(KB): Always/Manual ingest policy toggle (RFC #883 §1/§4)

Activates the `rag.defaultIngestPolicy` KV registered in Phase 1
(#888) so users on a fresh install (or anyone who picks Manual mode)
no longer get every new ZIM auto-dispatched to the embed pipeline.

## Stacks on #888

This PR's base is `feat/kb-ingest-state-machine` (#888). The state
machine has to be in place for the decision function to be policy-aware;
GitHub will fast-forward the base to `rc` once #888 merges.

## Backend changes

- `decideScanAction` now takes a `policy: 'Always' | 'Manual'` argument
  (defaults to `Always` for backward compatibility).
- New `ScanAction` kind: `create_pending`. Manual mode records that the
  scanner has seen a new file (so the UI can surface a per-card Index
  affordance later) without dispatching an EmbedFileJob.
- `scanAndSyncStorage` reads the KV and passes it through. The scan-result
  log line now includes the active policy and a `waiting on user` count
  for Manual-mode hits.
- `rag.defaultIngestPolicy` added to `SETTINGS_KEYS` so it's reachable
  through the existing `GET/PATCH /api/system/settings` surface — no new
  endpoint.

## Frontend changes

- New section in the KB panel between "Why upload" and "Processing Queue":
  "Auto-index new content for AI? [Always | Manual]" — segmented radio
  with copy explaining the 5-10× disk multiplier. Default Always.
- `useQuery('ingestPolicy')` reads the current value; clicking the
  inactive option mutates and shows a notification confirming the new
  behavior.

## Tests

- 14 unit tests on `decideScanAction` (was 9) — split into Always-mode
  cases (preserves Phase 1's contract) and Manual-mode cases
  (`create_pending`, `pending_decision → skip`, etc.).
- Type-check clean.
- Hot-patch + browser verification deferred until #888 lands; the state
  machine smoke-tested cleanly on NOMAD3 in #888's PR, and this PR's
  decision-tree changes are exhaustively unit-tested.

## RFC open question §3 — policy-change re-trigger

Switching Manual → Always doesn't auto-dispatch existing `pending_decision`
rows immediately. The next scan re-evaluates and dispatches them under
the new policy. This matches the RFC's "treat the switch as I've-
thought-about-it" instinct for the guardrail; full guardrail
implementation lands in Phase 3 task 14.

---------

Co-authored-by: Jake Turner <52841588+jakeaturner@users.noreply.github.com>
2026-05-20 10:16:00 -07:00
0xGlitch
94059b0aaf feat(Maps): regional map downloads via go-pmtiles extract (#780)
* 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
2026-05-20 10:16:00 -07:00
Jake Turner
9e3828bcba feat(Kiwix): migrate to Kiwix library mode for improved stability (#622) 2026-04-03 14:26:50 -07:00
Henry Estela
0edfdead90 feat(AI): enable flash_attn by default and disable ollama cloud (#616)
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-search
https://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
```
2026-04-03 14:26:50 -07:00
Henry Estela
69c15b8b1e feat(AI): enable remote AI chat host 2026-04-03 14:26:50 -07:00
Chris Sherwood
b1edef27e8 feat(UI): add Night Ops dark mode with theme toggle
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>
2026-03-20 11:46:10 -07:00
Jake Turner
96e5027055 feat(AI Assistant): performance improvements and smarter RAG context usage 2026-03-11 14:08:09 -07:00
Jake Turner
460756f581 feat(AI Assistant): improved state management and performance 2026-03-11 14:08:09 -07:00
Jake Turner
6f0fae0033 feat(AI Assistant): remember last model used 2026-03-11 14:08:09 -07:00
Jake Turner
58b106f388 feat: support for updating services 2026-03-11 14:08:09 -07:00
Jake Turner
96beab7e69 feat(AI Assistant): custom name option for AI Assistant 2026-03-04 20:05:14 -08:00
Jake Turner
efa57ec010 feat: early access release channel 2026-03-03 20:51:38 -08:00
Jake Turner
00bd864831 fix(AI): improved perf via rewrite and streaming logic 2026-03-03 20:51:38 -08:00
Jake Turner
765207f956 fix(AI): type error in fallback models 2026-02-18 21:42:36 -08:00
Jake Turner
d55ff7b466
feat: curated content update checking 2026-02-11 21:49:46 -08:00
Jake Turner
df6247b425 feat(Easy Setup): visual cue to start at Easy Setup for OOBE 2026-02-11 11:16:52 -08:00
Jake Turner
276bdcd0b2 feat(AI Assistant): query rewriting for enhanced context retrieval 2026-02-08 16:19:27 -08:00
Jake Turner
8726700a0a feat: zim content embedding 2026-02-08 13:20:10 -08:00
Jake Turner
12286b9d34 feat: display model download progress 2026-02-06 16:22:23 -08:00
Jake Turner
c3278efc01 fix(AI): add cloud flag to fallback models 2026-02-04 21:35:18 -08:00
Jake Turner
d1f40663d3 feat(RAG): initial beta with preprocessing, embedding, semantic retrieval, and ctx passage 2026-02-01 23:59:21 +00:00
Jake Turner
1923cd4cde feat(AI): chat suggestions and assistant settings 2026-02-01 07:24:21 +00:00
Jake Turner
31c671bdb5 fix: service name defs and ollama ui location 2026-02-01 05:46:23 +00:00
Jake Turner
243f749090 feat: [wip] native AI chat interface 2026-01-31 20:39:49 -08:00
Jake Turner
cb85785cb1 feat(Ollama): fallback list of recommended models if API down 2026-01-28 15:54:15 -08:00