release: dev → main (сдача хакатона) #106

Merged
Eleboba merged 128 commits from dev into main 2026-10-04 23:00:56 +03:00
Owner

Что меняется

Промоушн dev → main: сдаваемая версия прототипа (128 коммитов, конфликтов нет, fast-forward).

Что входит: каркас, privacy/safety/шкалы/правила, БД, LLM-шлюз и чат-агент (RAG + карта ЕМИАС + проверка препаратов), движок диалога (онбординг ветерана, чек-ин, лекарства, кризис), опросники intake, API, шедулер, адаптеры, seed, дашборд врача и демо-консоль, веб-приложение пациента, демо-режим для презентации, деплой и CD на meditron.tenvex.ru.

Как проверить

CI на dev зелёный (1059 тестов); стенд https://meditron.tenvex.ru работает на 967ae2d.

🤖 Generated with Claude Code

## Что меняется Промоушн `dev → main`: сдаваемая версия прототипа (128 коммитов, конфликтов нет, fast-forward). Что входит: каркас, privacy/safety/шкалы/правила, БД, LLM-шлюз и чат-агент (RAG + карта ЕМИАС + проверка препаратов), движок диалога (онбординг ветерана, чек-ин, лекарства, кризис), опросники intake, API, шедулер, адаптеры, seed, дашборд врача и демо-консоль, веб-приложение пациента, демо-режим для презентации, деплой и CD на `meditron.tenvex.ru`. ## Как проверить CI на `dev` зелёный (1059 тестов); стенд https://meditron.tenvex.ru работает на `967ae2d`. 🤖 Generated with [Claude Code](https://claude.com/claude-code)
Eleboba added 128 commits 2026-10-04 22:58:04 +03:00
chore(devops): project skeleton — uv, docker compose, Makefile, CI
CI / ruff · pytest (pull_request) Successful in 1m50s
107b8dba51
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>
Lets #2-#7 proceed in parallel against stable interfaces.

Refs #2

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
style(core): wrap long docstrings
CI / ruff · pytest (pull_request) Successful in 18s
f8b1fa561b
Refs #2

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
feat(core): scale engine with YAML schema and deterministic scoring
CI / ruff · pytest (pull_request) Successful in 23s
0c8cedc0c6
Pydantic schema for config/scales/*.yaml, cached loader, score() with
severity bands (sex-specific for AUDIT-C), rule-based C-SSRS triage,
flags (PHQ-9 item 9, PCL-5 >= 33, PHQ-4 subscales) and delta().
Starting literature thresholds for phq9, gad7, pcl5, auditc, pcptsd5,
cssrs_screen, phq4; final values are approved by the psychiatrist (#8).

Refs #3

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
feat(core): rule engine for alerts/agent actions and virtual demo clock
CI / ruff · pytest (pull_request) Successful in 18s
711c646876
- app/core/clock.py: now()/today(), virtual offset (advance/set_now/reset),
  pluggable offset persistence hook (ADR-005)
- config/rules.yaml + app/core/rules.py: YAML declares rules (params, actions,
  levels, reason_ru), Python evaluators implement predicates by id; dedup of
  open alerts, crisis never suppressed; ADR-006 colours (ADR-007)
- tests: per-rule unit tests, dedup, clock, 13-day demo persona trajectory

Refs #5

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Two DeclarativeBases on two engines (ADR-003): identity holds direct
identifiers, clinical holds token-keyed pseudonymised data plus audit_log.
Portable types (JSONB variant, tz-aware UTC timestamps rejecting naive
values) so tests run on SQLite. init_db() runs create_all at startup.
Guardrail #5 checked by AST and import-graph tests.

Refs #6

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
feat(core): implement scrub() and pseudo_id() with tests
CI / ruff · pytest (pull_request) Successful in 24s
585f0af273
Rule-based PII scrubber: phones, e-mails, SNILS (checksum-aware), passport,
INN, cards, dates of birth, addresses, URLs/handles and person names
(dictionary in config/privacy/names_ru.yaml + declension, patronymic and
surname heuristics). Idempotent via fixed-point iteration; false-positive
guards for ordinary clinical text. pseudo_id normalises SNILS to 11 digits
and returns HMAC-SHA256 truncated to 32 hex chars.

Refs #2

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
feat(bot): LLM gateway with GigaChat and offline mock providers
CI / ruff · pytest (pull_request) Successful in 23s
924a51c483
Single entry point app/llm/gateway.py: extract_item, extract_checkin,
risk_classify, phrase, summarize_for_doctor. Two-level design:
LLMProvider (transport, GigaChat) and LLMTasks (PromptedTasks over a
provider, or rule-based MockTasks). Shared policy in the gateway:
assert_scrubbed backstop, confidence threshold 0.5, risk failure -> NONE,
forbidden-output filter with config/texts/phrases.yaml fallbacks.

Refs #7

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- check(text, llm_signal) -> SafetyResult: normalisation (ё, homoglyphs, translit,
  repeats), stem regexes per category, negation window (acute -> possible only),
  weapon+risk combination, final level = max(lexicon, llm)
- crisis_reply(categories, audience) loads config/texts/crisis.yaml (patient/family,
  domestic violence and harm-to-others variants)
- 99-phrase eval set; acute recall 100%, < 5 ms per message

Refs #4

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
test(core): check acute recall after scrub() pipeline
CI / ruff · pytest (pull_request) Successful in 30s
123111bc9d
Refs #4

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Freeze interfaces between lanes A (bot), B (backend), C (dashboard) so three developers work in
parallel without touching each other's files: dialog Event/Reply + engine registry with echo stub,
integration protocols with in-memory defaults, MonitoringService with noop stub, /api/v1 schemas
with fixture-backed routes, frozen main.py wiring, config/modules.yaml + due_scales(), DAR-5,
tzdata, Andrey trajectory, lanes in WORKFLOW, ADR-010.

Refs #34

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
feat(bot): med_qa answers about the drug only from ГРЛС excerpts
CI / ruff · pytest (pull_request) Successful in 21s
51cc259002
Topic from engine or keyword classifier, section via integrations.drug_info,
sentence retrieval by keyword overlap (dosing sentences dropped), LLM only
rephrases the excerpt through gateway.phrase("med_answer") with forbidden-output
and added-content guards; dose questions and missing answers -> None + fallback text.

Refs #15

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
feat(bot): add doctor summary built from structured card data
CI / ruff · pytest (pull_request) Successful in 24s
49d5f8a4e5
build_structured() aggregates a PatientCard into scores, flags and
adherence (no patient text, no names); build_summary() sends it through
the LLM gateway, falls back to a config-driven template, keeps an open
acute alert first and caches per (token, provider, data hash).

Refs #19

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Engine.handle registered via register_engine; lexicon-first safety (no LLM on ACUTE),
  fixed crisis script once per open crisis, POSSIBLE → C-SSRS screen
- FSM registry (@state/@on_enter/@trigger) with auto-loaded flows; core flow:
  new → consent → age_gate → module onboarding → idle, crisis, consent_revoked
- reusable scale session (buttons, extract_item + clarify, item 9 / C-SSRS buttons-only,
  crisis flags), execution of monitoring dialog actions, texts in config/texts/dialog.yaml

Refs #10

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
feat(bot): Telegram channel over the dialog engine
CI / ruff · pytest (pull_request) Successful in 39s
8fd1202063
Deep-link /start <code> binds the chat via IdentityProvider, text and
button presses go to get_engine().handle(), replies render as inline
keyboards and are sent verbatim (no parse_mode). TelegramOutbox delivers
scheduler pushes to bound chats and falls back to the previous outbox.
No-op without TG_BOT_TOKEN; logs carry no text or chat ids.

Refs #11

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DfbiLXFJswz2EK3qtWF7S7
Correct RUS-AUDIT-S composition, preserve C-SSRS lifetime behavior, and prepare clinical review materials.

Refs #52
docs(clinical): normalize review table serialization
CI / ruff · pytest (pull_request) Successful in 30s
da089d67cb
Refs #52
feat(core): add verified Russian C-SSRS Recent source content
CI / ruff · pytest (pull_request) Successful in 31s
57b5ad1eb2
docs(clinical): review revised specification and backtranslate PCL-5
CI / ruff · pytest (pull_request) Successful in 38s
fe5b6fe103
Refs #52
docs(clinical): simplify translation review annotations
CI / ruff · pytest (pull_request) Successful in 30s
8b61eecf1b
Refs #52
feat(questionnaire): integrate revised intake and follow-up monitoring
CI / ruff · pytest (pull_request) Successful in 55s
c42ef621e5
Add gated TSQ, Russian C-SSRS Recent, durable responses and notifications, diaries, schedules and audited clinical review. Preserve manual assessment when the Russian follow-up source is unavailable.

Refs #52
docs(clinical): attach visual PR implementation report
CI / ruff · pytest (pull_request) Successful in 56s
0bd07045cd
Refs #52
Start screening of the veteran module: peer-tone intro, trauma exposure gate for
PC-PTSD-5, PCL-5/PHQ-9/AUDIT-C via scale sessions (sex asked if unknown), weapon
access question stored as facts for lane B with a safe-storage block on risk,
plain-language result, modules enabled in profile, FAQ, resume after a crisis.

Refs #36

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Reviewed-on: #53
Daily check-in (mood → dose → sleep/nightmares → alcohol → free text with
extract_checkin, buttons win over the LLM, progressive upsert of
daily_checkins), medication reminder flow (taken / skip with reason /
side effects → doses + daily_checkins), medication question menu via
med_qa, med_info rule reactions from the drug instruction excerpt,
«записаться раньше» request recorded for lane B, friendly intros for
scheduled scales. actions.py: additive med_info handler hook.

Refs #37

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
test(bot): Andrey 13-day acceptance scenario and medication flow units
CI / ruff · pytest (pull_request) Successful in 1m3s
2972b330b0
Refs #37

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- No same-day C-SSRS repeat: a risk screen completed within cssrs_cooldown_hours is not queued again
  after PHQ-9 item 9 >= 1 (scale crisis path, rule schedule_scale, scale_due); crisis script and alerts stay.
- Scale intro registry: register_scale_intro(scale_id, text_or_fn); start_scale(intro=None) uses it.
  veteran_daily migrated from per-scale on_enter hooks.
- Prefix triggers "button:<prefix>:*" with trigger_payload(event); medication buttons carry the dose
  (med:taken:<dose_id>, ...), med_pending dropped; payload-less legacy buttons answer as stale.
- Abandoned-step timeout: settings.abandon_after_hours (default 6 h) returns abandonable states
  (daily.*, meds.*, scale.* not in onboarding) to idle before the next event; never in crisis or with intake on.

Refs #56

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>
Reviewed-on: #58
- 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>
Reviewed-on: #59
- docs/source/rag: PDF sources (KR PTSD 2023, KR depression 2024, meds module spec),
  pdf->txt converter (tables as markdown, page markers, hand-transcribed figures),
  word-level check against pdftotext; fixes HAM-D/MADRS fake headers and split rows
- config/rag: corpus txt + sources.yaml (documents, audiences, retrieval params, synonyms)
- app/llm/rag: Snowball stemmer, section-aware chunker with page citations,
  BM25 + synonym expansion + densest-passage reranking, extractive answer()
  with coverage gate, patient dose/prescribing filter, optional LLM rephrasing
  rejected when it adds content; CLI python -m app.llm.rag
- tests: gold retrieval set (hit@3 >= 15/18), off-topic, safety, faithfulness
- ADR-011

Refs #60

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>
Structure-aware units with audience/evidence metadata, manual review,
hybrid BM25 search, citation-checked answers and an eval set.

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>
- /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>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- focus screens: question and context on the left, answers on the right in
  one wide card; consent text and the 0–10 scale in one wide column
- today: dashboard with tasks, this week's doses and quick actions side by
  side; meds / doctor / profile in two-column grids; welcome gets «Как это
  работает» steps
- fix: 0–10 scale no longer overflows narrow containers

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>
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>
feat(backend): API stage 1 on real data instead of fixtures
CI / ruff · pytest (pull_request) Successful in 1m25s
25728c4b31
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>
- setup() at package import (idempotent, replaces only base.py defaults): MisMock, ConnectCodeIdentity,
  GrlsExcerpts, CompositeNotifier; outbox stays MemoryOutbox
- MisMock: clinical DB prescriptions, fallback data/meds/mis_prescriptions.json (synthetic, by token)
- ConnectCodeIdentity: one-time connect code via identity_repo, 15 min grace for the double check in one
  connect flow (Telegram /start + engine `new` state)
- GrlsExcerpts: synthetic paraphrased instruction excerpts for sertraline, paroxetine, escitalopram,
  fluoxetine, mirtazapine, prazosin
- CompositeNotifier: in-memory feed (recent(since_id)) + Telegram doctor chat, PII-free, never raises
- test_llm_med_qa: default-registry test now patches NoDrugInfo explicitly

Refs #14

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>
- 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>
feat(dashboard): console fallbacks for the real API (#12)
CI / ruff · pytest (pull_request) Successful in 1m37s
8d12aa3d08
- 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>
- 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>
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>
feat(dashboard): replace home with approved minimal design
CI / ruff · pytest (pull_request) Successful in 2m1s
c01bfc90df
Refs #73
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>
Reviewed-on: #74
test: never call a live LLM from tests, whatever the local .env says
CI / ruff · pytest (pull_request) Successful in 1m50s
05b8bc3e7e
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>
On Windows git converted infra/postgres/init.sh to CRLF; Postgres then failed to run it
(/bin/bash^M: bad interpreter), so the identity/clinical databases and roles were never
created and every API call returned 500.

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>
Live run through the API (Andrey, real OpenRouter): onset questions now answered from the instruction
excerpt, «можно пиво?» reaches the agent although the check-in records alcohol, quit intent keeps the single
rule reaction, findings are mentioned only for intake/combination questions, one retry on a provider error,
provider error message logged.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Merge origin/dev into feat/rag-clinical-guidelines
CI / ruff · pytest (pull_request) Successful in 2m9s
0106aefc33
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>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
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>
feat(contract): add opt-in MAX configuration and lifecycle
CI / ruff · pytest (pull_request) Successful in 2m24s
b3e103954f
Refs #81
Refs #82
fix(backend): redact retryable MAX storage failures
CI / ruff · pytest (pull_request) Successful in 2m4s
461c3d02ea
Refs #82
feat(ui): extend minimal doctor design across all screens
CI / ruff · pytest (pull_request) Successful in 2m16s
2a2fdb171e
Refs #85
fix(contract): redact input values in settings errors
CI / ruff · pytest (pull_request) Successful in 2m22s
28967c7c37
Refs #87
feat(bot): add MAX notifications adapter and operator handoff
CI / ruff · pytest (pull_request) Successful in 2m27s
7780b484f3
Refs #83
fix(web): allow returning home from questionnaires
CI / ruff · pytest (pull_request) Successful in 2m28s
a4ee3d25f0
Keep the shared dialog and submitted answers while leaving the focus screen. Remove the history trap and wire the text-step home action.

Refs #85
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Reviewed-on: #88
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>
chore(devops): HTTPS for meditron.tenvex.ru too
CI / ruff · pytest (pull_request) Successful in 2m20s
f14efac7ac
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
fix(web): offer anonymous screening and doctor contact without identity
CI / ruff · pytest (pull_request) Successful in 2m30s
f5987c72f0
Refs #95, #96
Reviewed-on: #97
chore(devops): CD — every merge into dev deploys dev.meditron.tenvex.ru
CI / ruff · pytest (pull_request) Successful in 2m24s
285c95ac6b
Gitea Actions: lint + tests, then infra/deploy/deploy.sh over ssh as the dedicated ptsr-deploy user
(secrets DEPLOY_SSH_KEY, DEPLOY_HOST), then an HTTPS smoke check. deploy.sh now ships a tar.gz via scp and
retries every remote step (the host drops some ssh connections); the web build runs as the deploy user so the
next release can clean up.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Merge pull request 'chore(devops): CD — автодеплой dev на сервер' (#98) from chore/cd-deploy into dev
CD / ruff · pytest (push) Successful in 2m21s
CI / ruff · pytest (push) Successful in 2m30s
CD / deploy dev (push) Successful in 1m27s
683a74b004
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>
Merge pull request 'feat(bot): чат отвечает в любом состоянии + OpenRouter через прокси' (#99) from feat/chat-anywhere into dev
CD / ruff · pytest (push) Successful in 2m47s
CI / ruff · pytest (push) Successful in 2m49s
CD / deploy dev (push) Successful in 1m58s
475800436e
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Merge pull request 'fix: карта ЕМИАС для веб-демо Андрея + REVISION после успешного деплоя' (#100) from fix/emias-demo-token into dev
CD / ruff · pytest (push) Successful in 2m25s
CI / ruff · pytest (push) Successful in 2m38s
CD / deploy dev (push) Successful in 1m50s
a026a8cd48
- 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>
- 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>
test: demo_settings is a clinical table
CI / ruff · pytest (pull_request) Successful in 2m52s
c8887dc4b3
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
fix(bot): composition questions without «?» are questions
CI / ruff · pytest (pull_request) Successful in 2m44s
4b64086ad7
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Merge pull request 'fix(bot): вопросы о составе без «?»' (#103) from fix/question-words into dev
CD / ruff · pytest (push) Successful in 3m12s
CI / ruff · pytest (push) Successful in 3m45s
CD / deploy dev (push) Successful in 2m32s
535838e941
- 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>
- 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>
Merge pull request 'fix(bot): полировка чат-агента' (#105) from fix/agent-polish into dev
CI / ruff · pytest (push) Successful in 2m45s
CD / ruff · pytest (push) Successful in 2m51s
CI / ruff · pytest (pull_request) Successful in 2m41s
CD / deploy dev (push) Successful in 3m27s
967ae2d5b6
Eleboba merged commit b58d91fdce into main 2026-10-04 23:00:56 +03:00
Sign in to join this conversation.