Kansho/backend/tests/test_detect_learning.py

"""Transitional learning detect: senses from dialogue review, admin mode switch.

Fake detect/provider only. Run from backend/: python tests/test_detect_learning.py
"""
from __future__ import annotations

import os
import sys
from pathlib import Path
from unittest.mock import patch

ROOT = Path(__file__).resolve().parents[1]
sys.path.insert(0, str(ROOT))

os.environ["KANSHO_FAKE_PROVIDER"] = "1"
os.environ["KANSHO_FAKE_DETECT"] = "1"

from fastapi.testclient import TestClient
from detect_learning import (
    cue_for_mention,
    decision_for_mention,
    excerpt_view,
    get_cue_decision,
    get_detect_operating_mode,
    get_sense,
    merge_gliner_candidates,
    passage_provider,
    record_cue,
    record_sense,
    set_detect_operating_mode,
    try_local_passage_decision,
)
from detect_pipeline import (
    MentionSpan,
    compact_diff_counters,
    compare_mentions,
    map_entity_type,
    prepare_detect_pipeline,
    same_mention,
)
from providers import ChatResult, ProviderConfig
from dialogue_turn import visible_for_role
from identity_store import list_confirmed_identities
from main import app
from privacy_gateway import reset_debug


def expect(ok: bool, message: str) -> None:
    if not ok:
        raise SystemExit(f"FAIL: {message}")
    print(f"OK  {message}")


def status_ok(response, label: str) -> None:
    if response.status_code != 200:
        detail = response.json() if response.headers.get("content-type", "").startswith("application/json") else {}
        code = detail.get("detail", {}).get("code") if isinstance(detail, dict) else None
        expect(False, f"{label} HTTP {response.status_code} {code or ''}".strip())
    expect(True, label)


def header(token: str) -> dict:
    return {"X-Auth-Token": token}


def open_conv(client: TestClient, headers: dict) -> str:
    space = client.post("/api/journal/spaces", headers=headers, json={"title": "Alltag"})
    day = client.post(
        f"/api/journal/spaces/{space.json()['id']}/days",
        headers=headers,
        json={"calendar_date": "2026-09-08"},
    )
    conv = client.post(
        f"/api/journal/days/{day.json()['day']['id']}/conversations",
        headers=headers,
        json={"title": "Gespräch"},
    )
    return conv.json()["id"]


def main() -> None:
    reset_debug()
    with TestClient(app) as client:
        setup = client.post(
            "/api/auth/setup",
            json={"email": "lars@example.test", "name": "Lars", "password": "test-pass"},
        )
        headers = header(setup.json()["token"])
        profile_id = setup.json()["profile_id"]

        providers = client.get("/api/admin/providers", headers=headers)
        expect(providers.status_code == 200, "providers status")
        expect(providers.json()["detect_operating_mode"] == "bypass", "fake-env default is bypass")
        expect(get_detect_operating_mode() == "bypass", "store default in tests is bypass")
        ner = providers.json().get("local_ner") or {}
        expect(ner.get("enabled") is False, "GLiNER is off by default")
        detect_before = next(item for item in providers.json()["roles"] if item["role"] == "detect")
        remote_gliner = client.put(
            "/api/admin/providers/local-ner",
            headers=headers,
            json={"url": "https://openrouter.ai/api/v1"},
        )
        expect(remote_gliner.status_code == 400, "GLiNER URL must stay local")
        enabled = client.put(
            "/api/admin/providers/local-ner",
            headers=headers,
            json={"enabled": True, "url": "http://192.168.2.144:8090"},
        )
        status_ok(enabled, "enable local GLiNER")
        expect(enabled.json()["local_ner"]["enabled"] is True, "GLiNER enabled flag persisted")
        expect(enabled.json()["local_ner"]["url"] == "http://192.168.2.144:8090", "GLiNER LAN URL persisted")
        detect_after = next(item for item in enabled.json()["roles"] if item["role"] == "detect")
        expect(detect_after.get("url") == detect_before.get("url"), "OpenRouter detect URL is unchanged")
        client.put("/api/admin/providers/local-ner", headers=headers, json={"enabled": False})

        bad = client.put("/api/admin/providers/detect-mode", headers=headers, json={"mode": "wordlist"})
        expect(bad.status_code == 400, "invalid detect mode is rejected")

        conv_semantic = open_conv(client, headers)
        semantic_turn = client.post(
            f"/api/journal/conversations/{conv_semantic}/turn",
            headers=headers,
            json={"body": "Anna kam vorbei."},
        )
        status_ok(semantic_turn, "bypass turn")
        expect(not semantic_turn.json().get("pending_mask_review"), "bypass mode does not pause for review")
        expect(any(item.get("role") == "assistant" for item in semantic_turn.json().get("messages") or []), "bypass turn gets an assistant")

        switched = client.put("/api/admin/providers/detect-mode", headers=headers, json={"mode": "learning"})
        status_ok(switched, "switch to learning alias")
        expect(switched.json()["detect_operating_mode"] == "learning_full", "learning alias stores learning_full")

        conv = open_conv(client, headers)
        paused = client.post(
            f"/api/journal/conversations/{conv}/turn",
            headers=headers,
            json={"body": "Anna kam vorbei."},
        )
        status_ok(paused, "learning pause")
        review = paused.json().get("pending_mask_review") or {}
        expect(bool(review.get("id")), "learning mode returns a review id")
        expect(paused.json().get("assistant") is None, "paused turn has no assistant")
        candidates = review.get("candidates") or []
        anna = next((item for item in candidates if item.get("text") == "Anna"), None)
        expect(anna is not None, "Anna is a review candidate")
        hidden = visible_for_role({"pending_mask_review": review, "trace": {"egress": "x"}}, "user")
        expect("pending_mask_review" in hidden, "users still receive the mask review")
        expect("trace" not in hidden, "users do not receive the detect trace")

        reloaded = client.get(f"/api/journal/conversations/{conv}", headers=headers)
        expect(reloaded.json().get("pending_mask_review", {}).get("id") == review["id"], "pending review survives reload")

        missing = client.post(
            f"/api/journal/conversations/{conv}/turn/review",
            headers=headers,
            json={"review_id": "missing", "decisions": []},
        )
        expect(missing.status_code == 404, "unknown review is gone")

        identity = client.post(
            f"/api/journal/conversations/{conv}/turn/review",
            headers=headers,
            json={
                "review_id": review["id"],
                "decisions": [{"id": anna["id"], "decision": "identity"}],
            },
        )
        status_ok(identity, "identity review")
        expect(not identity.json().get("pending_mask_review"), "review continue clears the pause")
        expect(any(item.get("role") == "assistant" for item in identity.json().get("messages") or []), "continue produces an assistant")
        confirmed = list_confirmed_identities(profile_id)
        expect(any((item.get("canonical_label") or "").casefold() == "anna" for item in confirmed), "identity review confirms the registry")
        sense = get_sense(profile_id, "Anna")
        expect(sense["identity_hits"] >= 1 and not sense["ambiguous"], "Anna is identity-only")

        second = client.post(
            f"/api/journal/conversations/{conv}/turn",
            headers=headers,
            json={"body": "Anna hat später angerufen."},
        )
        status_ok(second, "second Anna turn")
        expect(not second.json().get("pending_mask_review"), "identity-only spelling skips the popup")

        food_conv = open_conv(client, headers)
        food = client.post(
            f"/api/journal/conversations/{food_conv}/turn",
            headers=headers,
            json={"body": "Hanna aß mit uns."},
        )
        status_ok(food, "hanna pause")
        food_review = food.json().get("pending_mask_review") or {}
        food_candidates = food_review.get("candidates") or []
        hanna = next((item for item in food_candidates if item.get("text") == "Hanna"), None)
        expect(hanna is not None, "Hanna is a review candidate")
        declined = client.post(
            f"/api/journal/conversations/{food_conv}/turn/review",
            headers=headers,
            json={
                "review_id": food_review["id"],
                "decisions": [{"id": hanna["id"], "decision": "not_identity"}],
            },
        )
        status_ok(declined, "not_identity review")
        expect(not any((item.get("canonical_label") or "").casefold() == "hanna" for item in list_confirmed_identities(profile_id)), "not_identity does not confirm Hanna")
        expect(get_sense(profile_id, "Hanna")["non_identity_hits"] >= 1, "not_identity records a sense")
        hanna_again = client.post(
            f"/api/journal/conversations/{food_conv}/turn",
            headers=headers,
            json={"body": "Hanna aß mit uns."},
        )
        status_ok(hanna_again, "second Hanna turn")
        expect(
            not hanna_again.json().get("pending_mask_review"),
            "stored Hanna cue is not re-asked against teacher PERSON",
        )

        record_sense(profile_id, "Clarissa", identity=True)
        record_sense(profile_id, "Clarissa", identity=False)
        expect(get_sense(profile_id, "Clarissa")["ambiguous"], "both senses mark Clarissa as ambiguous")
        amb_conv = open_conv(client, headers)
        with patch("detect_learning.try_local_passage_decision", return_value="not_identity"):
            amb = client.post(
                f"/api/journal/conversations/{amb_conv}/turn",
                headers=headers,
                json={"body": "Clarissa lag auf dem Tisch."},
            )
        status_ok(amb, "ambiguous local passage")
        expect(not amb.json().get("pending_mask_review"), "local passage can finish without a popup")
        expect(any(item.get("role") == "assistant" for item in amb.json().get("messages") or []), "local passage still generates")

        kin_conv = open_conv(client, headers)
        kin = client.post(
            f"/api/journal/conversations/{kin_conv}/turn",
            headers=headers,
            json={"body": "Ich war mit meinem Sohn Leon im Park."},
        )
        status_ok(kin, "kinship Leon pause")
        kin_review = kin.json().get("pending_mask_review") or {}
        kin_names = [item.get("text") for item in kin_review.get("candidates") or []]
        expect("Leon" in kin_names, "Sohn Leon is offered even when Detect does not report it")
        leon = next((item for item in kin_review.get("candidates") or [] if item.get("text") == "Leon"), None)
        expect(leon is not None, "Leon candidate id is present")
        kin_done = client.post(
            f"/api/journal/conversations/{kin_conv}/turn/review",
            headers=headers,
            json={
                "review_id": kin_review["id"],
                "decisions": [{"id": leon["id"], "decision": "identity"}],
            },
        )
        status_ok(kin_done, "Leon identity review")
        kin_again = client.post(
            f"/api/journal/conversations/{kin_conv}/turn",
            headers=headers,
            json={"body": "Ich war mit meinem Sohn Leon im Park."},
        )
        status_ok(kin_again, "second Leon turn")
        expect(not kin_again.json().get("pending_mask_review"), "confirmed Sohn Leon skips the popup")

        sushi_conv = open_conv(client, headers)
        sushi = client.post(
            f"/api/journal/conversations/{sushi_conv}/turn",
            headers=headers,
            json={
                "body": (
                    "Gestern bin ich mit meiner Frau Sushi und meinem Sohn Rohan "
                    "Sushi essen gegangen. Das Restaurant hat mich dabei total beeindruckt."
                )
            },
        )
        status_ok(sushi, "homonym sentence pause")
        sushi_names = [item.get("text") for item in (sushi.json().get("pending_mask_review") or {}).get("candidates") or []]
        expect("Rohan" in sushi_names, "Rohan from Sohn is a candidate")
        expect("Sushi" in sushi_names, "Sushi from Frau is a candidate")
        expect("Restaurant" not in sushi_names, "plain Restaurant is not kinship-offered")
        sushi_hits = [
            item
            for item in (sushi.json().get("pending_mask_review") or {}).get("candidates") or []
            if item.get("text") == "Sushi"
        ]
        expect(len(sushi_hits) >= 2, "both Sushi mentions are offered")
        expect(
            sushi_hits[0].get("highlight_start") != sushi_hits[1].get("highlight_start"),
            "the two Sushi mentions highlight different offsets",
        )
        for item in sushi_hits:
            excerpt = item.get("excerpt") or ""
            start = item.get("highlight_start")
            end = item.get("highlight_end")
            expect(excerpt[start:end] == "Sushi", "highlight covers the Sushi token")

        homonym = (
            "Gestern bin ich mit meiner Frau Sushi und meinem Sohn Rohan "
            "Sushi essen gegangen."
        )
        first_at = homonym.index("Sushi")
        second_at = homonym.rindex("Sushi")
        first = excerpt_view(homonym, first_at, first_at + 5, "Sushi")
        second = excerpt_view(homonym, second_at, second_at + 5, "Sushi")
        expect(first["highlight_start"] < second["highlight_start"], "person Sushi sits left of dish Sushi")
        expect(first["excerpt"][first["highlight_start"]:first["highlight_end"]] == "Sushi", "first highlight is Sushi")
        expect(second["excerpt"][second["highlight_start"]:second["highlight_end"]] == "Sushi", "second highlight is Sushi")
        prefix = "SYSTEM\n"
        mapped = excerpt_view(
            homonym,
            len(prefix) + second_at,
            len(prefix) + second_at + 5,
            "Sushi",
            prefix + homonym,
        )
        expect(mapped["highlight_start"] == second["highlight_start"], "rendered detect offsets map to the dish Sushi")
        expect(cue_for_mention(homonym, first_at, first_at + 5, "Sushi") == "frau", "person Sushi attaches to Frau")
        expect(cue_for_mention(homonym, second_at, second_at + 5, "Sushi") == "rohan", "dish Sushi stays distinct from Frau")
        appos = "Sushi, meine Frau war erkältet."
        appos_at = appos.index("Sushi")
        expect(cue_for_mention(appos, appos_at, appos_at + 5, "Sushi") == "frau", "apposition Sushi, meine Frau binds Frau")
        far = "Meine Frau und ich aßen Sushi."
        far_at = far.rindex("Sushi")
        expect(cue_for_mention(far, far_at, far_at + 5, "Sushi") != "frau", "Frau elsewhere in the sentence does not bind the dish")

        sushi_review = sushi.json().get("pending_mask_review") or {}
        sushi_decisions = []
        for item in sushi_review.get("candidates") or []:
            label = item.get("text")
            cue = item.get("cue")
            if label == "Sushi" and cue != "frau":
                sushi_decisions.append({"id": item["id"], "decision": "not_identity"})
            else:
                sushi_decisions.append({"id": item["id"], "decision": "identity"})
        sushi_done = client.post(
            f"/api/journal/conversations/{sushi_conv}/turn/review",
            headers=headers,
            json={"review_id": sushi_review["id"], "decisions": sushi_decisions},
        )
        status_ok(sushi_done, "homonym review")
        expect(get_cue_decision(profile_id, "Sushi", "frau") == "identity", "Frau Sushi is stored as identity")
        expect(get_cue_decision(profile_id, "Sushi", "rohan") == "not_identity", "dish Sushi after Rohan is stored")
        expect(get_cue_decision(profile_id, "Rohan", "sohn") == "identity", "Sohn Rohan cue is stored")
        sushi_again = client.post(
            f"/api/journal/conversations/{sushi_conv}/turn",
            headers=headers,
            json={
                "body": (
                    "Gestern bin ich mit meiner Frau Sushi und meinem Sohn Rohan "
                    "Sushi essen gegangen. Das Restaurant hat mich dabei total beeindruckt."
                )
            },
        )
        status_ok(sushi_again, "repeat homonym sentence")
        expect(not sushi_again.json().get("pending_mask_review"), "same reviewed sentence does not re-ask")

        dish = "Ich aß Sushi."
        dish_at = dish.index("Sushi")
        food_spans = [{"text": "Sushi", "start": dish_at, "end": dish_at + 5, "label": "food", "score": 0.8}]
        food_cands, _maps = merge_gliner_candidates(profile_id, [], [], dish, dish, food_spans)
        expect(
            any(item.get("text") == "Sushi" and item.get("suggested") == "not_identity" for item in food_cands),
            "GLiNER food span suggests not_identity",
        )
        person_line = "Ich war mit meiner Frau Sushi unterwegs."
        person_at = person_line.index("Sushi")
        gliner_miss = [{"text": "Sushi", "start": person_at, "end": person_at + 5, "label": "food", "score": 0.9}]
        merged, _maps = merge_gliner_candidates(profile_id, [], [], person_line, person_line, gliner_miss)
        expect(
            not any(item.get("suggested") == "not_identity" for item in merged),
            "GLiNER food does not override Frau attachment",
        )
        expect(
            decision_for_mention(profile_id, "Sushi", person_line, person_at, person_at + 5, person_line) == "identity",
            "learned Frau cue wins over GLiNER food",
        )
        dish_line = "Ich aß Sushi."
        dish_pos = dish_line.index("Sushi")
        expect(
            decision_for_mention(profile_id, "Sushi", dish_line, dish_pos, dish_pos + 5, dish_line) == "ask",
            "Tag-21: identity hits plus new cue stay visible",
        )
        person = MentionSpan("Sushi", 20, 25, "PERSON", "identity", "cue", True, "frau")
        food = MentionSpan("Sushi", 20, 25, "FOOD", "not_identity", "teacher", False, "aß")
        expect(same_mention(person, food), "same offsets are the same mention")
        wrapped = MentionSpan("Frau Sushi", 15, 25, "PERSON", "identity", "teacher", False, "frau")
        expect(same_mention(person, wrapped), "contained Sushi matches Frau Sushi")
        expect(map_entity_type("person") == "PERSON", "GLiNER person maps to PERSON")
        guessed = MentionSpan("Sushi", 20, 25, "PERSON", "identity", "candidate", False, "aß")
        review, counters = compare_mentions(profile_id, dish_line, [guessed], [food], dish_line)
        expect(counters["diff_type_conflict"] >= 1, "FOOD versus PERSON is a type conflict")
        expect(any(item.get("reason") == "type_conflict" for item in review), "unconfirmed type conflict is offered")
        confirmed_dish = MentionSpan("Sushi", 20, 25, "FOOD", "not_identity", "cue", True, "rohan")
        teacher_person = MentionSpan("Sushi", 20, 25, "PERSON", "identity", "teacher", False, "rohan")
        kept, kept_counters = compare_mentions(
            profile_id, dish_line, [confirmed_dish], [teacher_person], dish_line
        )
        expect(kept_counters["diff_type_conflict"] >= 1, "confirmed cue still counts the type conflict")
        expect(not kept, "confirmed cue is not re-asked on type conflict")
        compact = compact_diff_counters(counters)
        dumped = str(compact)
        expect("Sushi" not in dumped and "Frau" not in dumped, "compact diff counters carry no plaintext")
        expect(set(compact) == {
            "diff_agree",
            "diff_only_student",
            "diff_only_teacher",
            "diff_type_conflict",
            "diff_new_identity",
            "diff_cue_reinforced",
        }, "compact counters are the agreed keys")
        set_detect_operating_mode("learning_reduced")
        expect(get_detect_operating_mode() == "learning_reduced", "stage 2 mode persists")
        set_detect_operating_mode("learning_manual")
        expect(get_detect_operating_mode() == "learning_manual", "manual mode persists")
        set_detect_operating_mode("student")
        pipe = prepare_detect_pipeline(profile_id, "Anna kam vorbei.", "Anna kam vorbei.")
        expect(pipe.mode == "student", "student path is selectable")
        expect(not pipe.need_review, "zielpfad does not open a teacher popup")
        record_sense(profile_id, "Sushi", identity=True)
        record_cue(profile_id, "Sushi", "frau", "identity", "meine Frau Sushi")
        expect(
            decision_for_mention(profile_id, "Sushi", "Ich aß Sushi.", dish_pos, dish_pos + 5) == "ask",
            "Tag-21 remains ask after more identity hits",
        )

        fake_passage = ProviderConfig(
            role="passage",
            name="ollama",
            mode="http",
            url="http://192.168.2.144:11434/v1/chat/completions",
            model="phi3:mini",
            key="",
            local=True,
            zdr=True,
            no_train=True,
        )
        with patch("detect_learning.passage_provider", return_value=fake_passage):
            with patch("providers.complete_chat", return_value=ChatResult(content='{"decision":"not_identity"}')) as chat:
                decided = try_local_passage_decision("Rohan Sushi essen", "Sushi")
                expect(decided == "not_identity", "passage profile can decide without local Detect")
                expect(chat.called, "passage uses complete_chat")
        expect(passage_provider() is None, "no passage profile means no silent detect fallback")

        back = client.put("/api/admin/providers/detect-mode", headers=headers, json={"mode": "semantic"})
        expect(back.json()["detect_operating_mode"] == "bypass", "semantic alias stores bypass")
        full = client.put("/api/admin/providers/detect-mode", headers=headers, json={"mode": "learning_full"})
        expect(full.json()["detect_operating_mode"] == "learning_full", "learning_full is accepted")


if __name__ == "__main__":
    main()