- get_llm_provider() now accepts provider + model args so DB overrides
propagate through to all provider constructors (was always reading
env vars, ignoring the admin UI selection)
- /test-llm replaced with lightweight ping (max_tokens=20) instead of
running a full bill analysis; shows model name + reply, no truncation
- /api/settings/llm-models endpoint fetches available models live from
each provider's API (OpenAI, Anthropic REST, Gemini, Ollama)
- Admin UI model picker dynamically populated from provider API;
falls back to manual text input on error; Custom model name option kept
- Default Gemini model updated: gemini-1.5-pro → gemini-2.0-flash
Co-Authored-By: Jack Levy
Backend:
- Add fetch_bill_actions task with pagination and idempotent upsert
- Add fetch_actions_for_active_bills nightly batch (4 AM UTC beat schedule)
- Wire fetch_bill_actions into new-bill creation and _update_bill_if_changed
- Add backfill_brief_citations task: detects pre-citation briefs by JSONB
type check, deletes them, re-queues LLM processing against stored text
(LLM calls only — zero Congress.gov or GovInfo calls)
- Add admin endpoints: POST /bills/{id}/reprocess, /backfill-citations,
/trigger-fetch-actions; add uncited_briefs count to /stats
Frontend:
- New BriefPanel component: wraps AIBriefCard, adds amber "What Changed"
badge for amendment briefs and collapsible version history with
inline brief expansion
- Swap AIBriefCard for BriefPanel on bill detail page
- Admin panel: Backfill Citations + Fetch Bill Actions buttons; amber
warning in stats when uncited briefs remain
- Add feature roadmap document with phased plan through Phase 5
Co-Authored-By: Jack Levy
- Replace fragile entry.get("link") with _gnews_entry_url() helper that
checks entry.link attribute then falls back to entry.links[].href,
fixing cases where feedparser puts the URL in a non-standard location
- Lazy news re-fetch on bill detail now only triggers when the stored
trend score confirms gnews_count > 0, preventing endless re-queuing
for bills with genuinely no news coverage
Co-Authored-By: Jack Levy
- Drop global unique constraint on news_articles.url; replace with
(bill_id, url) so the same article can appear for multiple bills
- news_fetcher dedup now scoped to bill_id instead of global URL
- Bill detail endpoint triggers a background news fetch when no
articles are stored, so gnews articles surface on next load
Migration 0009.
Co-Authored-By: Jack Levy
Adds Google Trends, NewsAPI, and Google News RSS scoring for members,
mirroring the existing bill interest pipeline. Member profiles now show
a Public Interest chart (with signal breakdown) and a Related News panel.
Key changes:
- New member_trend_scores + member_news_articles tables (migration 0008)
- fetch_gnews_articles() added to news_service for unlimited RSS article storage
- Bill news fetcher now combines NewsAPI + Google News RSS (more coverage)
- New member_interest Celery worker with scheduled news + trend tasks
- GET /members/{id}/trend and /news API endpoints
- TrendChart redesigned with signal breakdown badges and bar+line combo chart
- NewsPanel accepts generic article shape (bills and members)
Co-Authored-By: Jack Levy
Lazy-enriches member profiles on first view via Congress.gov detail API.
Adds office address, phone, official website, congress.gov link, birth
year, terms history, leadership roles, and sponsored/cosponsored counts.
Includes DB migration 0007 for new member columns.
Co-Authored-By: Jack Levy
- Poller now fetches bill detail on insert to get sponsor (list endpoint
has no sponsor data)
- Add backfill_sponsor_ids task + admin endpoint + UI button to fix the
1,616 existing bills with NULL sponsor_id
- Member name search now matches both "Last, First" and "First Last"
using split_part() on the stored name column; same fix applied to
global search
- Load Bill.sponsor relationship eagerly in get_member_bills to prevent
MissingGreenlet error during Pydantic serialization
- Remove .trim() on search onChange so spaces can be typed
Authored-By: Jack Levy
LLM prompts updated to output {text, citation, quote} objects for every
key_point and risk. govinfo_url stored on BillBrief (migration 0006) so
the frontend can link directly to the source document without an extra
query. AIBriefCard renders § citation chips that expand inline to show
the verbatim quote and a View source → GovInfo link. Old plain-string
briefs continue to render unchanged.
Authored-By: Jack Levy
- GET /api/admin/stats returns total bills, docs fetched, briefs generated
(full + amendment), and remaining count
- Admin page shows stat cards + progress bar, auto-refreshes every 30s
Authored-By: Jack Levy
- Drop hres/sres/hconres/sconres (simple/concurrent resolutions) from poller;
only track hr, s, hjres, sjres (legislation that can become law)
- On first run, seed from 60 days back instead of full congress history,
keeping the bill count to ~1,600 instead of 13,000+
Authored-By: Jack Levy
- User model with email/hashed_password/is_admin/notification_prefs
- JWT auth: POST /api/auth/register, /login, /me
- First registered user auto-promoted to admin
- Migration 0005: users table + user_id FK on follows (clears global follows)
- Follows, dashboard, settings, admin endpoints all require authentication
- Admin endpoints (settings writes, celery triggers) require is_admin
- Frontend: login/register pages, Zustand auth store (localStorage persist)
- AuthGuard component gates all app routes, shows app shell only when authed
- Sidebar shows user email + logout; Admin nav link visible to admins only
- Admin panel (/settings): user list with delete + promote/demote, LLM config,
data source settings, and manual celery controls
Authored-By: Jack Levy
