Live check on synthetic speech (espeak) via OpenRouter gemini-2.5-flash:
3–5 s per clip, silence → no speech.
Refs #116
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
GET /api/v1/me/{token}/garden computes the garden on the fly from taken doses,
check-ins/diary and finished questionnaires (no new table). Rules and texts in
config/garden.yaml: per-day caps, points only add up, answers never count.
Refs #118
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
POST /api/v1/me/{token}/stt takes a 16 kHz mono WAV and only transcribes:
the patient checks the text and sends it as an ordinary message, so safety,
scrub() and the LLM gateway still apply. Audio is neither stored nor logged.
OpenRouter STT is synthetic-data only (ADR-014); SaluteSpeech for the pilot is #121.
Refs #116
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- POST /dialog/{token}/events/stream: Server-Sent Events with the agent's steps («Смотрю вашу карту ЕМИАС…»,
«Ищу в клинических рекомендациях…»), the answer as the model writes it (OpenRouter stream=true), then the
final replies (same as /events, incl. the forbidden-output filter and sources). X-Accel-Buffering: no.
- Web: free-text messages use the stream — a live bubble with steps, typing dots and a cursor; falls back to
the plain request if the stream breaks.
- Phones: the bottom tab bar gets «Чат» (it had no way back to the chat).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- 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>
- Greetings / chit-chat answered without the LLM (instant, free, no medical findings dumped into «привет»).
- At most 4 tool calls per turn (one «как дела?» turn fired 23 parallel searches).
- «My drug» is never asked back; analogues → the drug's group, replacement only by the doctor.
- Markdown stripped to plain text with «•»; no sources footer under short replies.
- Diagnosis filter no longer blocks definitions («ПТСР — это расстройство…»); diagnosis-like statements about
the patient are still blocked.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Idle chat: all messages go to the agent (greetings, side-effect and substitute questions included); check-in
signals are still recorded silently, quit intent keeps its rule reaction. Seen live: «какие будут побочки»
was logged as a complaint («Спасибо, отметил»), «привет» got a canned phrase.
- Agent prompt: warm short replies to small talk; substitutes → only the doctor changes the drug.
- ЕМИАС demo persona button creates a private copy too (starting from consent + questionnaires, subject to
the screening switch); the web app drops a stored session of the old shared demo account.
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>
- An acked crisis is not raised again for the same signal: re-raised only if a newer triggering scale exists
(seen live: AUDIT-C 0/0/0 re-fired the acked PHQ-9 item 9 crisis).
- In an open crisis every non-acute message gets a reply (agent for questions, support otherwise) plus
emergency contacts; acute messages still get the fixed script.
- Questions and medicine mentions without «?» are answered mid-questionnaire; free-text steps (check-in,
side effects, question states) keep parsing their input.
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>
Clinical review of the questionnaires (ADR-013):
- Red-flag block first in stage 1 (config/instruments/red_flags.yaml); any «Да» stops the
questionnaire with an acute alert and the help screen of its category.
- One crisis rule: the crisis screen opens at a HIGH C-SSRS risk only; moderate stops and goes
to a psychiatrist (24 h as a guide), low is a flag with the safety plan. PHQ-9 item 9 with a
negative screener is a discrepancy flag; without a completed screener it asks the C-SSRS at once.
config/questionnaire.yaml: cssrs_positive_policy graded (C01).
- Every crisis leaves a callback task for the doctor on duty (post_crisis_call, one per patient)
and the app asks how the person is the next day, the safety plan one tap away.
- Routing: risk and flags first, scales second; PCL-5 >= 50 no longer means a priority
appointment (pcl5_severe is moderate on the dashboard too).
- Crisis numbers live only in config/texts/crisis.yaml; texts and the agent prompt refer to them
via {phone:<key>}. Fixes the children's helpline offered to adults by the chat agent.
Refs #92
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>
Conflict in app/api/routes.py: /demo/personas keeps the dev version (demo console, DB patients
with scenarios); the patient app gets its own /patient/demo-personas (synthetic ЕМИАС accounts).
Anonymous sign-in now always creates a doctor-less pseudonymous profile, since the dialog API
of #12 serves known profiles only.
Refs #77
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Sign-in: centred ЕМИАС card without the sidebar; anonymous entry asks «Депрессия / ПТСР».
- Stage 1 is the same for everyone and follows the fixed order of the MVP questionnaire:
PHQ-2 → trauma filter/TSQ → RUS-AUDIT-S → C-SSRS → context; stage 2 only where stage 1
is positive. Starts without a profile.
- After stage 1 the patient sees a preliminary result (screening, not a diagnosis), stored
with the record; it switches on the diary modules (depression / PTSD).
- Stage 2 diary: morning (sleep, sleep quality, alcohol) and evening (mood, medication,
3 PHQ-9 items in rotation, short PCL-5); C-SSRS since last contact only under risk;
flags on weekly means against the personal norm; scheduled full scales with change
(remission, response, worsening).
- Questionnaire log: GET /me/{token}/results and the «Мои результаты» screen.
- Questionnaires centred without the sidebar and without scale names; «Продолжить позже»
goes home; confirmations are toasts; free-text comments are optional.
- Demo policy config/questionnaire_demo.yaml (INTAKE_DEMO only, not a clinical approval).
ADR-012.
Refs #77
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
With OPENROUTER_API_KEY in a developer's .env the chat agent switched on in dialog tests (real API calls,
spent money, flaky results). An autouse fixture turns the agent off; agent tests pass explicit providers.
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>
- Patient list sorted red -> yellow -> grey -> green with KPI row, trend arrows,
7-day adherence bars, discontinuation-risk badge with factor tooltip.
- Patient card: scales with severity bands from config/scales (unscheduled marked),
mood/sleep/alcohol small multiples, dose heat-strip, alerts feed with ack,
safety plan, AI summary with disclaimer.
- Live alerts: st.fragment(run_every=2.5s) polling, toast + pinned acute banner on
every page; full rerun on new alert only on doctor pages.
- Connect form -> POST /patients/connect -> code, QR, deep link.
- Thin httpx ApiClient over the frozen schemas with graceful "API недоступен".
- app.py discovers dashboard/pages/*.py automatically (st.navigation); demo pages
of #17 plug in by adding a file.
Refs #16
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- personas degrade: /demo/personas → doctor's patients (hero first) → env token
- scenario file guessed from the transliterated first name (andrey.jsonl), like the backend
- «Подключить демо-пациента»: connects the synthetic hero via /patients/connect when no seed
- connect code prefilled from ?code= of the console link
Refs #17
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- scripts/seed_demo.py: doctor doc-smirnova (on call), Andrey day 0 (connect code,
no consent) or day N with history; 7 patients with seeded-random histories.
Alerts and colours come from the real rules evaluated day by day.
- --reset drops/recreates both DBs and zeroes the demo clock; seed keeps the
persisted clock offset so dates match the running app.
- data/synthetic/andrey.jsonl: console scenario for days 0..13 generated from
config button labels (--write-scenario).
- tests: idempotency, modes, colours, scenario format/sync and a full replay of
the scenario through the real engine, scheduler and monitoring.
Refs #18
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- pages/2_Демо-консоль.py: persona selector, virtual clock bar (+1 h, to 08:00/20:00,
next day, reset with confirm), fallback patient web chat (buttons from Reply.buttons,
kind styling, outbox drained after every action and on a 2 s fragment poll), scenario panel
- pages/3_Сплит-экран.py: patient chat or PATIENT_WEB_URL iframe on the left, compact doctor
panel (patients, live alerts, red banner on a new acute alert) on the right
- console/playback.py: data/synthetic/<persona>.jsonl runner (advance_to/press/text/
expect_color/start), date chaining between days, pause on failure with retry/skip/manual
- console/api.py: own HTTP client over the frozen API contract, ApiError only
Refs #17
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Doctor list/card/alerts/ack/connect, dialog events/outbox/history and demo
controls now read the identity and clinical DBs. Rule-based discontinuation
risk index, trend, adherence; every doctor read is audited.
Refs #12
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- menu button «Вопрос о лечении» -> kb.question -> rag.answer (KR quote + source)
or «уточните у врача»; dose questions get a fixed doctor redirect
- free text in idle that looks like a question (no check-in signals, not a drug
question) -> knowledge base; no answer -> the usual support phrase
- routing order unchanged: consent/safety first, side effects/quit/alcohol -> check-in,
own drug -> med_qa (instruction only, SPEC §7 p.5)
- question cues, small talk and texts in config/texts/knowledge.yaml; scrub placeholders
before "что такое X" no longer hide the definition question
Refs #64
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Focus screen renders versioned questionnaire items (iq: buttons): section chip, position
(adaptive forms without "of N"), recall date, pause / help-now actions, optional skip,
sleep-hours input, 0-10 scale anchors, RUS-AUDIT item 2 standard-drink table.
- Paused / held-for-review questionnaires get their own screen.
- Today: intake and diary tasks, review notice, therapy-day card on days 1/7/14.
- Drug card /meds/:ref from data/meds/meds_reference.json (draft built from the Minzdrav
guidelines: depression 2024, PTSD 2023) — expected effect, course, side effects, red flags;
no doses shown. "Report a side effect" always available (med:side_effects:<ref>).
- API: /instruments/catalog, /meds/reference; today gains questionnaire state, reference id,
indication and therapy day; demo persona seeds the dashboard dose history.
- INTAKE_DEMO=1 (demo clock only) opens the questionnaires on synthetic data without touching
the clinical release gate in config/intake_runtime.yaml.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- /flow renders the dialog engine's current step as a mock screen (consent,
age, onboarding and scales with progress, mood 0–10, free text, dose
reminder, crisis with hotlines and breathing, safety plan), so every
engine scenario gets the design without duplicating its logic
- today / meds / doctor / profile / messages tabs; navy sidebar and
emergency rail on desktop, emergency block and tab bar on phones
- API: GET /me/{token}/today (today's doses, week marks, next visit, demo
clock time); demo ЕМИАС sign-in seeds the persona's synthetic profile and
prescription from the dashboard fixtures
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A second channel to the same dialog engine as the Telegram bot: consent,
onboarding, scales and check-ins come from app/dialog; the bot is unchanged.
- API: /auth/emias (doctor's one-time connect code via EmiasMock),
/auth/emias/demo (synthetic personas), /auth/anonymous (random token,
nothing stored in the identity DB), /crisis/resources from crisis.yaml
- web/: React + TS + Vite, mobile-first, safe areas, hash routing,
tokens and texts isolated for a Capacitor mobile build
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- converter marks a paragraph glued across a page break with ⟦стр. N⟧; the chunker
strips the marker and extends the chunk's page range (wrong-page citations 24 -> 3,
the rest are scale-form table rows split by a page)
- [NAME]/[PHONE] placeholders from privacy.scrub() no longer count as unknown words
(a scrubbed question used to fall below the coverage gate)
- a question naming one disease boosts its guideline in retrieval and passage choice
("ТМС при депрессии" was answered from the PTSD guideline); "антидепрессант" is not a cue
Refs #62
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- app/scheduler/demo.py: run_until(now) replays due and fresh events in time order: dose rows +
med_reminder, missed after 2 h without an answer → monitoring, daily_checkin, scale_due by the
config/modules.yaml schedules, daily monitoring pass (silence, missed doses) → reach_out/scale_due
- idempotent via scheduler_events (unique token+key); stale events are not sent; no contact without
consent or during an open crisis
- config/scheduler.yaml: times and windows; runs while the questionnaire release is off
- POST /demo/clock/advance replays the scheduler up to the new time
Refs #13
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- app/services/snapshot.py: PatientSnapshot from the clinical DB (field mapping, age, therapy day,
recent C-SSRS risk, weapon access from dialog facts)
- app/services/monitoring.py: RuleMonitoring registered via register_monitoring; persists alert/crisis
actions, crisis_acute audit, enhanced_monitoring flag, cached status_color, notifies the doctor (and
the doctor on duty for crises) after commit; a running crisis is not restarted
- demo clock offset persisted in clock_state, restored on scheduler start
- tests: Andrey's 13 days through the service → G G G Y Y G G G G Y Y Y R
Refs #38
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
ElebobaandClaude Opus 5.5
Arxip222