MedITron/PTSRaiAgent
4
0
Fork 0
Code Issues 21 Pull Requests Actions Packages Projects Releases Wiki Activity
13 Commits 20 Branches 0 Tags
924a51c483f07d7fadb14df49e8296dcf49e72bc
Commit Graph
8 Commits
Author SHA1 Message Date
ElebobaandClaude Opus 5.5 924a51c483 feat(bot): LLM gateway with GigaChat and offline mock providers
CI / ruff · pytest (pull_request) Successful in 23s
Details 
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>
 2026-10-03 15:00:41 +03:00
Eleboba 84317bcfce Merge pull request 'feat(backend): модель данных identity / clinical / audit, репозитории, create_all' (#29) from feat/6-db into dev
CI / ruff · pytest (push) Successful in 38s
Details
2026-10-03 14:59:52 +03:00
ElebobaandClaude Opus 5.5 121b607414 feat(backend): data model — identity / clinical / audit, repositories, create_all
CI / ruff · pytest (pull_request) Successful in 45s
Details 
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>
 2026-10-03 14:58:26 +03:00
ElebobaandClaude Opus 5.5 711c646876 feat(core): rule engine for alerts/agent actions and virtual demo clock
CI / ruff · pytest (pull_request) Successful in 18s
Details 
- 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>
 2026-10-03 14:58:19 +03:00
ElebobaandClaude Opus 5.5 0c8cedc0c6 feat(core): scale engine with YAML schema and deterministic scoring
CI / ruff · pytest (pull_request) Successful in 23s
Details 
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>
 2026-10-03 14:56:40 +03:00
ElebobaandClaude Opus 5.5 f8b1fa561b style(core): wrap long docstrings
CI / ruff · pytest (pull_request) Successful in 18s
Details 
Refs #2

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-03 14:50:47 +03:00
ElebobaandClaude Opus 5.5 3b9cd36f92 chore(core): freeze shared core contracts — ScrubbedText, RiskLevel, AlertLevel, privacy signatures 
Lets #2-#7 proceed in parallel against stable interfaces.

Refs #2

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-03 14:50:30 +03:00
ElebobaandClaude Opus 5.5 107b8dba51 chore(devops): project skeleton — uv, docker compose, Makefile, CI
CI / ruff · pytest (pull_request) Successful in 1m50s
Details 
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>
 2026-10-03 14:46:01 +03:00