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>
Requirement: no extra software beyond the regulated set. The web app is built in a Node stage and served by
nginx (:8080, /api → app, SSE unbuffered); the server override keeps it off (host nginx serves the bundle).
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>
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>
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>
Eleboba
Arxip222
Soyavo