Jack Levy defc2c116d fix(admin): LLM provider/model switching now reads DB overrides correctly ...

- 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

2026-03-01 04:03:51 -05:00

backend

fix(admin): LLM provider/model switching now reads DB overrides correctly

2026-03-01 04:03:51 -05:00

frontend

fix(admin): LLM provider/model switching now reads DB overrides correctly

2026-03-01 04:03:51 -05:00

nginx

fix(nginx): add Docker DNS resolver to prevent stale upstream IPs

2026-02-28 22:51:46 -05:00

.env.example

Add multi-user auth system and admin panel

2026-02-28 21:44:34 -05:00

.gitattributes

Add multi-user auth system and admin panel

2026-02-28 21:44:34 -05:00

.gitignore

Initial commit

2026-02-28 21:08:19 -05:00

ARCHITECTURE.md

docs: update architecture for v0.2.2 fixes

2026-02-28 23:31:35 -05:00

docker-compose.yml

Initial commit

2026-02-28 21:08:19 -05:00

PocketVeto — Feature Roadmap.md

feat: bill action pipeline, What Changed UI, citation backfill, admin panel

2026-03-01 03:03:29 -05:00

queue_docs.py

Initial commit

2026-02-28 21:08:19 -05:00

status.py

Initial commit

2026-02-28 21:08:19 -05:00

Description

Self-hosted US Congress monitoring with AI bill analysis, personalized tracking, and multi-channel notifications.

GPL-3.0 809 KiB

Languages

Python 53.6%

TypeScript 45.8%

CSS 0.2%

Dockerfile 0.2%