T

CI / ruff · pytest (pull_request) Successful in 2m5s

Details

feat(bot): chat agent on Gemini 2.5 Flash-Lite — grounded first turn, current-prescription defaults

Live-tested on OpenRouter: Flash-Lite answers in 3–8 s with correct findings at ~$0.10/$0.40 per 1M tokens
(qwen3.7-flash and gpt-oss-120b took 26–32 s). Force a tool call on the first turn, give the model the
current prescription, let check_drug_for_patient default to it and return composition, intolerance check
and general interactions (alcohol); retry once on an empty final message.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

2026-10-04 14:59:38 +03:00

.gitea/workflows

chore(devops): project skeleton — uv, docker compose, Makefile, CI

2026-10-03 14:46:01 +03:00

.streamlit

feat(dashboard): doctor dashboard with red zones, patient card, live alerts and patient connect

2026-10-04 12:51:07 +03:00

app

feat(bot): chat agent on Gemini 2.5 Flash-Lite — grounded first turn, current-prescription defaults

2026-10-04 14:59:38 +03:00

config

feat(bot): answer treatment questions from the clinical-guideline knowledge base

2026-10-04 11:27:42 +03:00

dashboard

Merge pull request 'feat(dashboard): кабинет врача — красные зоны, карточка, живые алерты, подключение пациента' (#70 ) from feat/16-doctor-dashboard into dev

2026-10-04 12:55:23 +03:00

data

feat(bot): tool-using chat agent over RAG, ЕМИАС record and drug-safety reference

2026-10-04 14:39:16 +03:00

docs

fix(llm): RAG citation pages, scrub placeholders, disease-aware document choice

2026-10-04 04:31:59 +03:00

infra/postgres

chore(devops): project skeleton — uv, docker compose, Makefile, CI

2026-10-03 14:46:01 +03:00

scripts

feat(backend): demo seed — veteran Andrey (day 0..13) and 7 cabinet patients

2026-10-04 12:50:30 +03:00

tests

feat(bot): chat agent on Gemini 2.5 Flash-Lite — grounded first turn, current-prescription defaults

2026-10-04 14:59:38 +03:00

.dockerignore

chore(devops): project skeleton — uv, docker compose, Makefile, CI

2026-10-03 14:46:01 +03:00

.env.example

feat(bot): chat agent on Gemini 2.5 Flash-Lite — grounded first turn, current-prescription defaults

2026-10-04 14:59:38 +03:00

.gitignore

docs: bootstrap repo — CLAUDE.md, spec, ADR, TenVex-style workflow

2026-10-03 14:36:33 +03:00

.python-version

chore(devops): project skeleton — uv, docker compose, Makefile, CI

2026-10-03 14:46:01 +03:00

CLAUDE.md

chore(core): stage 1 contracts — dialog, API schemas + fixtures, integrations, monitoring, modules

2026-10-03 15:22:25 +03:00

docker-compose.yml

chore(devops): project skeleton — uv, docker compose, Makefile, CI

2026-10-03 14:46:01 +03:00

Dockerfile

chore(devops): project skeleton — uv, docker compose, Makefile, CI

2026-10-03 14:46:01 +03:00

Makefile

chore(devops): project skeleton — uv, docker compose, Makefile, CI

2026-10-03 14:46:01 +03:00

pyproject.toml

chore(core): stage 1 contracts — dialog, API schemas + fixtures, integrations, monitoring, modules

2026-10-03 15:22:25 +03:00

README.md

docs: bootstrap repo — CLAUDE.md, spec, ADR, TenVex-style workflow

2026-10-03 14:36:33 +03:00

uv.lock

chore(core): stage 1 contracts — dialog, API schemas + fixtures, integrations, monitoring, modules

2026-10-03 15:22:25 +03:00

README.md

PTSRaiAgent — ИИ-помощник сопровождения при ПТСР и депрессии

Хакатон MedITron · кейс SberMed AI «ИИ-помощник пациента». Прототип на синтетических данных. Telegram используется только для прототипа на синтетических данных; прод-канал — MAX / Госуслуги.

🚧 README заполняется к сдаче (issue «README по требованиям оформления»). Разделы по требованиям жюри:

Цели и задачи решения
Что реализовано
Развёртывание, запуск, использование
Входные и выходные данные, API
Ограничения и особенности медицинской тематики

Пока смотрите CLAUDE.md и docs/.