- CRISIS_BLOCKING (default off for the demo): a crisis no longer locks the dialog; the message and the
doctor's acute alert still happen. The clinical protocol (blocking, immediate stop) stays behind the flag and
keeps its tests.
- Crisis signals inside a questionnaire (intake red flags, high C-SSRS, PHQ-9 item 9) no longer stop it: the
test is finished and the crisis message comes at the end; the doctor's alert is raised at once/at the end.
- Weapon access: asked and stored, triggers nothing (rule disabled, no red flag, no safety block).
- ЕМИАС demo persona is «Никита В.»; the one-click demo stays «Андрей С.».
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- POST /auth/demo/fresh + «Демо: войти как Андрей» on the welcome screen: every sign-in gets a fresh private
copy of veteran Andrey (consent, prescription, ЕМИАС record) and lands in the chat — no codes, nobody's
crisis or half-done questionnaire leaks into another viewer.
- Initial screening switch: SCREENING_ENABLED env default + /demo/settings + a toggle in the demo console;
off → after consent straight to the chat.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A question asked mid-questionnaire, mid-check-in or during a crisis is answered right away (agent →
guidelines/instruction); the pending question is re-shown with its buttons (engine remembers the last
prompt), in a crisis the answer carries the emergency contacts and the crisis stays open until the doctor's
ack. Acute messages still get the fixed crisis script. OpenRouter blocks RF IPs: OPENROUTER_PROXY_URL routes
the agent through an HTTP proxy, as vobot does.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
OpenRouter returns 403 «Access denied by security policy» from the RF server, and parsing that string error
crashed the request (500 instead of the fallback answer). Error parsing is robust now and any agent exception
degrades to the extractive answer. GigaChat tool provider (GigaChat-2-Pro by default) converts the agent's
OpenAI-style history to function_call / role=function; auto mode prefers GigaChat when credentials are set.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
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>
Free-text treatment and medication questions go to an LLM agent with read-only tools bound to the current
patient: guideline search (RAG, doses stripped), ЕМИАС record mock (diagnoses, comorbidities, intolerances,
other specialists' drugs, current prescription), drug info (composition, contraindications, interactions)
and a deterministic patient-specific check. Providers: OpenRouter (temporary, synthetic data only) and an
offline mock; GigaChat to follow. Scrubbed input only, forbidden-output filter, any failure falls back to
the existing extractive RAG / instruction answers. Off unless OPENROUTER_API_KEY or CHAT_AGENT=mock.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
One Postgres with isolated identity/clinical databases and roles (ADR-003),
FastAPI /health, Streamlit placeholder, typed settings with offline defaults.
Refs #1
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
ElebobaandClaude Opus 5.5