mitai-jinkendo/backend/placeholder_registrations/activity_session_insights.py

"""
Registry: Trainings-Häufigkeit, Pausen zwischen Einheiten, wöchentliche Session-JSON (KI-Rohkontext).
"""

from placeholder_registry import (
    PlaceholderMetadata,
    MissingValuePolicy,
    EvidenceType,
    OutputType,
    PlaceholderType,
    register_placeholder,
)


def _ev(meta: PlaceholderMetadata, field: str, et: EvidenceType = EvidenceType.CODE_DERIVED):
    meta.set_evidence(field, et)


def register_activity_session_insights():
    md_freq = PlaceholderMetadata(
        key="training_frequency_by_type_md",
        category="Aktivität",
        description=(
            "Markdown-Tabelle: pro Trainingsart (activity_type) Sessions, Ø/Woche, "
            "Dauer, kcal, HF, RPE, kcal/min (Intensitätsproxy)"
        ),
        resolver_module="backend/placeholder_resolver.py",
        resolver_function="get_training_frequency_by_type_md",
        data_layer_module="backend/data_layer/activity_metrics.py",
        data_layer_function="get_training_frequency_by_type_data",
        source_tables=["activity_log"],
        semantic_contract=(
            "Aggregat über activity_log gruppiert nach activity_type (Roh-Label). "
            "sessions_per_week = count / (days/7). avg_kcal_per_min = Summe kcal / Summe min."
        ),
        business_meaning="KI: Häufigkeit & Belastung pro Sportart, Erholungs-/Überlastungs-Kontext",
        unit="Markdown",
        time_window="default 28 Tage",
        output_type=OutputType.TEXT_SUMMARY,
        placeholder_type=PlaceholderType.INTERPRETED,
        format_hint="GitHub-Flavored Markdown-Tabelle",
        example_output="| Art | n | Ø/Woche | … |",
        minimum_data_requirements="Mindestens eine Session im Fenster",
        quality_filter_policy=None,
        confidence_logic="Wie calculate_confidence anhand Session-Anzahl",
        missing_value_policy=MissingValuePolicy(
            available=False,
            value_raw=None,
            missing_reason="no_data",
            legacy_display="Keine Trainingsdaten",
        ),
        known_limitations=(
            "Gruppierung nach activity_type-String (Import-Namen), nicht nur training_type_id. "
            "HF/RPE oft NULL je nach Quelle. Pausen-Analyse separater Platzhalter."
        ),
        layer_1_decision="activity_metrics.get_training_frequency_by_type_data",
        layer_2a_decision="get_training_frequency_by_type_md",
        layer_2b_reuse_possible=True,
        architecture_alignment="Phase 0c",
        issue_53_alignment="Layer 1",
        evidence={},
    )
    for f in (
        "key", "category", "description", "resolver_module", "resolver_function",
        "data_layer_module", "data_layer_function", "source_tables", "semantic_contract",
        "unit", "time_window", "output_type", "placeholder_type", "format_hint",
        "example_output", "minimum_data_requirements", "confidence_logic",
        "missing_value_policy", "layer_1_decision", "layer_2a_decision",
        "layer_2b_reuse_possible", "architecture_alignment", "issue_53_alignment",
    ):
        _ev(md_freq, f)
    _ev(md_freq, "business_meaning", EvidenceType.DRAFT_DERIVED)
    _ev(md_freq, "known_limitations", EvidenceType.MIXED)
    register_placeholder(md_freq)

    md_gap = PlaceholderMetadata(
        key="training_inter_session_gap_md",
        category="Aktivität",
        description="Median/Mittel/Min der Stunden zwischen aufeinanderfolgenden Trainingseinheiten",
        resolver_module="backend/placeholder_resolver.py",
        resolver_function="get_training_inter_session_gap_md",
        data_layer_module="backend/data_layer/activity_metrics.py",
        data_layer_function="get_training_inter_session_gap_data",
        source_tables=["activity_log"],
        semantic_contract=(
            "Sessions chronologisch; Zeitstempel = date + start_time oder 12:00. "
            "Lücken in Stunden zwischen aufeinanderfolgenden Starts."
        ),
        business_meaning="KI: ausreichend Erholung zwischen Belastungen? Doppelbelastung?",
        unit="Markdown",
        time_window="default 28 Tage",
        output_type=OutputType.TEXT_SUMMARY,
        placeholder_type=PlaceholderType.INTERPRETED,
        format_hint="Kurzer Markdown-Fließtext",
        example_output="**Pause zwischen Trainings** …",
        minimum_data_requirements="Mindestens 2 Sessions",
        quality_filter_policy=None,
        confidence_logic="calculate_confidence über Session-Anzahl",
        missing_value_policy=MissingValuePolicy(
            available=False,
            value_raw=None,
            missing_reason="insufficient_data",
            legacy_display="Zu wenige Trainings",
        ),
        known_limitations=(
            "Kein Unterscheidung aktiv/passiv außerhalb activity_log. "
            "Fehlende Uhrzeit verzerrt Reihenfolge am selben Tag nicht (nur ein künstlicher Mittag)."
        ),
        layer_1_decision="activity_metrics.get_training_inter_session_gap_data",
        layer_2a_decision="get_training_inter_session_gap_md",
        layer_2b_reuse_possible=True,
        architecture_alignment="Phase 0c",
        issue_53_alignment="Layer 1",
        evidence={},
    )
    for f in (
        "key", "category", "description", "resolver_module", "resolver_function",
        "data_layer_module", "data_layer_function", "source_tables", "semantic_contract",
        "unit", "time_window", "output_type", "placeholder_type", "format_hint",
        "example_output", "minimum_data_requirements", "confidence_logic",
        "missing_value_policy", "layer_1_decision", "layer_2a_decision",
        "layer_2b_reuse_possible", "architecture_alignment", "issue_53_alignment",
    ):
        _ev(md_gap, f)
    _ev(md_gap, "business_meaning", EvidenceType.DRAFT_DERIVED)
    _ev(md_gap, "known_limitations", EvidenceType.MIXED)
    register_placeholder(md_gap)

    pj = PlaceholderMetadata(
        key="training_sessions_recent_json",
        category="Aktivität",
        description=(
            "JSON: ISO-Wochen mit Sessions (activity_log-Kopf) plus session_metrics[] — gemergte Profil-Metriken "
            "(dynamische Keys)"
        ),
        resolver_module="backend/placeholder_resolver.py",
        resolver_function="_safe_json",
        data_layer_module="backend/data_layer/activity_metrics.py",
        data_layer_function="get_training_sessions_recent_weeks_data",
        source_tables=["activity_log", "training_types", "activity_session_metrics", "training_parameters"],
        semantic_contract=(
            "Root: weeks[] mit week_iso; sessions[] pro Einheit u. a. id, date, activity_type, "
            "duration_min, kcal_active, hr_avg, hr_max, rpe, training_category, training_type_name, "
            "session_metrics[]. "
            "session_metrics: effektive Liste nach merge_column_backed_and_eav_metrics — Einträge mit "
            "training_parameter_id, key, data_type, unit, value, name_de/name_en, description_de/description_en; "
            "nur Parameter aus Attributschema "
            "(training_category_parameter + training_type_parameter Overrides), keys sortiert. "
            "Kanon Lesen: activity_log-Spalte vor EAV bei Konflikt. "
            "meta: weeks_requested, days_loaded, session_count, confidence. "
            "Default ca. 4 ISO-Wochen (28 Tage Rohdatenfenster)."
        ),
        business_meaning="Rohkontext für wochenweise Auswertung (Erholung, Intensität) in der KI",
        unit="JSON string",
        time_window="4 ISO-Wochen (28 Tage Datenfenster)",
        output_type=OutputType.JSON,
        placeholder_type=PlaceholderType.RAW_DATA,
        format_hint="JSON-Objekt als String",
        example_output='{"weeks":[...],"meta":{...}}',
        minimum_data_requirements="Optional Sessions; meta.confidence bei leer insufficient",
        quality_filter_policy=None,
        confidence_logic="meta.confidence aus Session-Anzahl",
        missing_value_policy=MissingValuePolicy(
            available=False,
            value_raw=None,
            missing_reason="no_data",
            legacy_display="{}",
        ),
        known_limitations=(
            "Token-Länge bei vielen Sessions. training_type_name nur bei gesetztem training_type_id. "
            "session_metrics oft [] (kein Typ, kein Profil, keine gespeicherten Werte). "
            "Anzahl und Namen der Metrik-Keys sind instanz-/adminabhängig — JSON nicht als festes Schema "
            "für Downstream-Parsing harter Logik verwenden. "
            "Für KI-Semantik zusätzlich {{training_parameters_glossary_md}} (gesamter aktiver Katalog) in den Prompt legen. "
            "Composite-Parameter (JSON in EAV) noch nicht im MVP expandiert; ggf. Roh-value_text in späterer Phase."
        ),
        layer_1_decision="activity_metrics.get_training_sessions_recent_weeks_data",
        layer_2a_decision="_safe_json('training_sessions_recent_json')",
        layer_2b_reuse_possible=True,
        architecture_alignment="Phase 0c",
        issue_53_alignment="Layer 1",
        evidence={},
    )
    for f in (
        "key", "category", "description", "resolver_module", "resolver_function",
        "data_layer_module", "data_layer_function", "source_tables", "semantic_contract",
        "unit", "time_window", "output_type", "placeholder_type", "format_hint",
        "example_output", "minimum_data_requirements", "confidence_logic",
        "missing_value_policy", "layer_1_decision", "layer_2a_decision",
        "layer_2b_reuse_possible", "architecture_alignment", "issue_53_alignment",
    ):
        _ev(pj, f)
    _ev(pj, "business_meaning", EvidenceType.DRAFT_DERIVED)
    _ev(pj, "known_limitations", EvidenceType.MIXED)
    register_placeholder(pj)

    md_gloss = PlaceholderMetadata(
        key="training_parameters_glossary_md",
        category="Aktivität",
        description=(
            "Markdown-Tabelle: alle aktiven training_parameters (key, DE/EN, Beschreibungen, Typ, Einheit, Kategorie). "
            "Ergänzung zu training_sessions_recent_json für KI (Bedeutung dynamischer Metrik-Keys)."
        ),
        resolver_module="backend/placeholder_resolver.py",
        resolver_function="get_training_parameters_glossary_md",
        data_layer_module="backend/data_layer/activity_metrics.py",
        data_layer_function="get_training_parameters_ki_glossary_data",
        source_tables=["training_parameters"],
        semantic_contract=(
            "SELECT auf training_parameters WHERE is_active; sortiert category, key. "
            "profile_id-Parameter im Resolver reserviert, aktuell globaler Katalog."
        ),
        business_meaning="KI: Legende zu session_metrics-Keys und Custom-Parametern",
        unit="Markdown",
        time_window="n/a (Katalog-Snapshot)",
        output_type=OutputType.TEXT_SUMMARY,
        placeholder_type=PlaceholderType.INTERPRETED,
        format_hint="GitHub-Flavored Markdown-Tabelle",
        example_output="| Feld (key) | DE | EN | Beschreibung DE | … |",
        minimum_data_requirements="Optional leer → Kurztext statt Tabelle",
        quality_filter_policy=None,
        confidence_logic="Immer verfügbar wenn DB erreichbar",
        missing_value_policy=MissingValuePolicy(
            available=False,
            value_raw=None,
            missing_reason="no_data",
            legacy_display="Keine aktiven Trainingsparameter im Katalog.",
        ),
        known_limitations=(
            "Keine profil-spezifische Einschränkung auf tatsächlich genutzte Keys (V2). "
            "Tabellen können bei großem Katalog lang werden."
        ),
        layer_1_decision="activity_metrics.get_training_parameters_ki_glossary_data",
        layer_2a_decision="get_training_parameters_glossary_md",
        layer_2b_reuse_possible=True,
        architecture_alignment="Phase 0c",
        issue_53_alignment="Layer 2a",
        evidence={},
    )
    for f in (
        "key", "category", "description", "resolver_module", "resolver_function",
        "data_layer_module", "data_layer_function", "source_tables", "semantic_contract",
        "unit", "time_window", "output_type", "placeholder_type", "format_hint",
        "example_output", "minimum_data_requirements", "confidence_logic",
        "missing_value_policy", "layer_1_decision", "layer_2a_decision",
        "layer_2b_reuse_possible", "architecture_alignment", "issue_53_alignment",
    ):
        _ev(md_gloss, f)
    _ev(md_gloss, "business_meaning", EvidenceType.DRAFT_DERIVED)
    _ev(md_gloss, "known_limitations", EvidenceType.MIXED)
    register_placeholder(md_gloss)


register_activity_session_insights()