Pluggable AI providers, relay credit system, picker UX overhaul
Captures roughly forty version bumps (v0.2.6 → v0.2.47) of work that
accumulated without commits.
- Pluggable provider system under server/providers/: gemini, anthropic,
openai, openai-compatible, ollama, whisper-compatible, relay. Mix and
match transcription + analysis per request via the picker UI.
- Relay backend integration. Hardcoded relay URL in server/relay-default.js
(operator-controlled at build time, not user-configurable). New
/api/relay/{status,policy} endpoints proxy to the relay; balance pings
populate a cached credit display.
- Per-install identity in server/install-id.js for relay credit accounting.
Sent to the relay as X-Recap-Install-Id; persists across upgrades, lost
on a full uninstall + reinstall. Not surfaced in the UI.
- Admin login gate (server/admin-auth.js + setAdminPassword action). Scrypt
password hash + HMAC-signed session cookie.
- Entitlement scheme rename: pro / max (each paired with subscriptions and
relay_pro / relay_max), replacing the misleading "core" entitlement
that conflicted with the user-facing "Core" tier name.
- Activation screen: dynamic credit count pulled from /api/relay/policy,
"Skip — use free mode" button, accurate paid-feature list.
- Top toolbar: inline credit-balance pill (or "BYO configured" fallback),
Upgrade + "I have a key" buttons.
- Picker UI: per-provider sections with Save/Test/Delete buttons, sections
collapsible by chevron, default-collapsed unless currently selected,
"Use comped credits (reset to relay)" link when the user has strayed,
green hint under inputs whose values are server-configured.
- Activity log: chevron-collapsible groups per video, refresh-survival via
localStorage + a 500-entry server-side buffer, explicit Clear button.
- YouTube captions fast-path with user toggle (skips audio download + AI
transcription when captions are available — uncheck for speaker labels).
- Cancel button: AbortController plumbed through every provider SDK call;
retryAPI short-circuits on AbortError; cancellation events surface in
the activity log instead of silent retries.
- Long-video analysis: auto-coalesce transcript entries before building the
analysis prompt so local-model context windows (32k-ish) don't overflow.
Original entries preserved for transcript display via an index map; the
analyzer sees a coarser view but click-to-seek timestamps stay precise.
- StartOS action grouping (Setup / AI Providers) so the actions list is
navigable.
- Manifest description rewritten to reflect multi-provider support and
free-tier relay credits.
- Smaller fixes: summarize-button enablement no longer requires a Gemini
key when other providers are configured; analysis fallback chain handles
context-length and 503 capacity errors; single-segment expansion for
providers that don't return per-segment timestamps (Parakeet et al.);
many other UX polish items.
This commit is contained in:
@@ -0,0 +1,12 @@
|
||||
import { VersionInfo } from '@start9labs/start-sdk'
|
||||
|
||||
export const v_0_2_24 = VersionInfo.of({
|
||||
version: '0.2.24:0',
|
||||
releaseNotes: {
|
||||
en_US: 'Parakeet (and any Whisper-API endpoint that returns plain text without per-segment timestamps) now produces usable summaries. Previously, the entire transcript landed as one entry at [0:00] — which (a) tripped the truncation detector ("covers 0:00 of 2:15") and triggered a wasted chunked-transcription retry, and (b) gave the analyzer one giant blob so it could only output a single topic. Now Recap detects the single-entry case and splits the transcript into synthetic sentence-based entries with interpolated timestamps. Sentence boundaries (. ! ?) drive the split; very short sentences ("Yeah.") get coalesced into neighbors; timestamps are distributed proportionally by character count across the audio duration. Result: a 2-minute Parakeet transcript becomes ~10-20 entries that the analyzer can carve into proper topic sections.',
|
||||
},
|
||||
migrations: {
|
||||
up: async ({ effects }) => {},
|
||||
down: async ({ effects }) => {},
|
||||
},
|
||||
})
|
||||
Reference in New Issue
Block a user