SparkControl is a self-hosted local-inference gateway with an OpenAI-compatible API, reached over the internal same-box StartOS address (http://spark-control.startos:9999/v1, plain HTTP). It takes no API key, so generateOpenAIStyle gained a { requireApiKey } option and now omits the Authorization header when no key is set. The Settings form auto-detects the loaded vLLM model via SparkControl's /api/endpoints probe, mirroring the Ollama auto-detect; it's $0 in the cost UI. Custom-URL => admin-only + SSRF-guarded, same as Ollama.
Also fixes a config footgun behind the empty-response report: a custom base URL could ride along to a fixed-URL provider (claude/openai/gemini) whose form field is hidden, get stored, and be silently ignored (the provider always hits its hardcoded endpoint). Both config write paths now null baseUrl for non-custom-URL providers, and the form clears it on provider change.
No schema/data change (AIConfigProfile.provider is free-text). 259 tests pass; built + sideloaded to immense-voyage.local with a clean non-root launch.
Multi-user authorization hardening from a full security evaluation (EVALUATION.md):
- P0: /api/settings/{export,import}-db are now admin-only. Previously any signed-in user could download the whole instance DB (all bcrypt hashes + plaintext AI keys) or replace it wholesale. Per-user CSV export/import stays open.
- AI custom-URL providers (Ollama, OpenAI-compatible) are now admin-only, and every server fetch to a user-supplied URL passes through assertSafeProviderUrl (blocks link-local/cloud-metadata; private LAN allowed by design). Fixed-URL cloud providers stay per-user. Removed the dead legacy /api/ai/config route.
- Dev: fixed broken quick-start (added npm run create-admin; rewrote README; dropped dead CLAUDE_API_KEY) and the export-db 0-byte path resolution (resolveDatabasePath now matches Prisma).
ExVer bumped to 1.1.0:8 (no schema/data migration). Tests 197 pass, build green, tsc clean.
User-feedback-driven release after testing v1.1.0:3. Nine themes:
1. Multi-config persistence
- New AIConfigProfile table (per-user). Save N configs, toggle one
active. Switching providers no longer wipes the previous setup.
- UserPreferences gains activeAIConfigId; legacy single-config
columns are mirrored from the active profile so existing reads
keep working without conditional logic.
- Idempotent boot migration lifts any existing single-config row
into a default profile.
2. Ollama auto-detect
- The "Add config" form probes /api/tags on the StartOS internal
addresses (ollama.startos / ollama.embassy on :11434). If
reachable: URL pre-fills, model field becomes a dropdown of
installed models. Fixes the copy-paste UX.
3. Curated model dropdowns for major providers
- Claude: Opus 4.7, Sonnet 4.6 (1M ctx), Haiku 4.5
- OpenAI: GPT-5.5, 5.4, 5.4-mini, 5.4-nano
- Gemini: 3.1-pro-preview, 2.5-pro, 2.5-flash, etc.
- "Other (type your own)" stays for niche models.
- Fixes "I tried gemini-3.0-pro and got 404."
4. Background generation
- lib/ai/generationRunner.ts: detached runner with in-memory
pub/sub bus. POST /api/ai/generate kicks it off and returns
immediately. SSE stream attaches by id. The runner survives
request cancellation; navigating away no longer kills it.
- New AIGeneration columns: progressText (in-flight stream),
durationMs (final wall-clock).
- Generate UI shows a banner explaining background-safety.
- History detail page polls progress + renders partial JSON
live for cross-process resume (page refresh, new tab).
5. System prompt overhaul
- lib/ai/systemPromptBase.ts: structural contract prepended to
every template. Forces JSON-only output, library-exerciseId
usage (kills "exerciseId doesn't belong to this user" errors),
and per-resistance-exercise suggestedWeight (with-history vs
without-history variants).
- aiExerciseSchema + ProgramExercise gain suggestedWeight +
suggestedWeightUnit. Starting a workout from a ProgramDay
pre-populates SetLog.weight from the suggestion.
6. Test connection improvements
- Latency in seconds (was ms — confusing for slow Ollama).
- Stale "✓ Connected" clears on form change.
- Per-config Test (no need to activate first).
- Generous maxOutputTokens for thinking models.
- Gemini surfaces finishReason on empty response (e.g. "blocked
by safety filter") instead of generic "empty response."
- Test endpoint accepts a draft body so you can verify before
saving + before activating.
7. History detail view
- Click row → full program tree + exact prompts sent. Apply from
here without re-generating. Pending rows poll for progress.
8. Sidebar sub-navigation
- AI: Generate / History / Templates
- Settings: General / Password / Sessions / AI integration /
Export / Instance (admin) / Danger zone, with anchor scroll.
9. API key UX
- "Key saved" indicator on saved configs (was confusing to see
an empty input after a successful save).
Schema migrations (additive, idempotent in entrypoint):
- AIConfigProfile table created
- UserPreferences.activeAIConfigId
- AIGeneration.progressText + durationMs
- ProgramExercise.suggestedWeight + suggestedWeightUnit
Tests: 16 new (systemPromptBase, modelMenu, generationRunner). 177
total pass.
Keysat