feat(transcription): add Supabase schema and API endpoints for CIS

modules/transcription/models.py

@@ -0,0 +1,208 @@
+"""Pydantic models for the Transcription system."""
+
+from pydantic import BaseModel, Field
+from typing import Optional, List
+from datetime import datetime
+
+
+# --- Session Models ---
+
+class TranscriptionSessionCreate(BaseModel):
+    user_id: str
+    title: Optional[str] = None
+    canvas_type: str = "teaching-canvas"
+
+
+class TranscriptionSessionUpdate(BaseModel):
+    title: Optional[str] = None
+    ended_at: Optional[datetime] = None
+    timetable_period_id: Optional[str] = None
+    timetable_event_type: Optional[str] = None
+    timetable_event_label: Optional[str] = None
+    auto_tagged: Optional[bool] = None
+    llm_provider: Optional[str] = None
+    llm_model: Optional[str] = None
+
+
+class TranscriptionSessionResponse(BaseModel):
+    id: str
+    user_id: str
+    title: Optional[str] = None
+    canvas_type: str
+    started_at: datetime
+    ended_at: Optional[datetime] = None
+    duration_seconds: Optional[int] = None
+    timetable_period_id: Optional[str] = None
+    timetable_event_type: Optional[str] = None
+    timetable_event_label: Optional[str] = None
+    auto_tagged: bool = False
+    llm_provider: Optional[str] = None
+    llm_model: Optional[str] = None
+    word_count: int = 0
+    segment_count: int = 0
+    metadata: dict = {}
+    created_at: datetime
+    updated_at: datetime
+
+    class Config:
+        from_attributes = True
+
+
+class SessionListResponse(BaseModel):
+    sessions: List[TranscriptionSessionResponse]
+    total: int
+    page: int
+    page_size: int
+
+
+# --- Segment Models ---
+
+class TranscriptionSegmentCreate(BaseModel):
+    session_id: str
+    sequence_index: int
+    text: str
+    start_seconds: float
+    end_seconds: float
+    is_final: bool = True
+    speaker_label: Optional[str] = None
+    keyword_matches: Optional[List[str]] = None
+
+
+class TranscriptionSegmentResponse(BaseModel):
+    id: str
+    session_id: str
+    sequence_index: int
+    text: str
+    start_seconds: float
+    end_seconds: float
+    is_final: bool = True
+    speaker_label: Optional[str] = None
+    keyword_matches: Optional[List[str]] = None
+    created_at: datetime
+
+    class Config:
+        from_attributes = True
+
+
+# --- Canvas Event Models ---
+
+class CanvasEventCreate(BaseModel):
+    session_id: Optional[str] = None
+    user_id: str
+    timestamp: Optional[datetime] = None
+    session_elapsed_seconds: Optional[float] = None
+    event_type: str
+    event_payload: dict = {}
+    canvas_snapshot_url: Optional[str] = None
+    tldraw_page_id: Optional[str] = None
+    tldraw_shape_ids: Optional[List[str]] = None
+
+
+class CanvasEventResponse(BaseModel):
+    id: str
+    session_id: Optional[str] = None
+    user_id: str
+    timestamp: datetime
+    session_elapsed_seconds: Optional[float] = None
+    event_type: str
+    event_payload: dict = {}
+    canvas_snapshot_url: Optional[str] = None
+    tldraw_page_id: Optional[str] = None
+    tldraw_shape_ids: Optional[List[str]] = None
+
+    class Config:
+        from_attributes = True
+
+
+# --- Summary Models ---
+
+class SummaryGenerateRequest(BaseModel):
+    summary_type: str  # full_lesson, questions_asked, teaching_style, key_moments, segment
+    provider: str  # anthropic, openai, ollama, openrouter, google
+    model: str
+    api_key: str  # from frontend user settings, passed per-request
+    segment_range: Optional[List[Optional[int]]] = None  # [start, end], null = all
+    include_canvas_snapshots: bool = False
+
+
+class SummaryResponse(BaseModel):
+    id: str
+    session_id: str
+    user_id: str
+    summary_type: str
+    content: str
+    prompt_used: Optional[str] = None
+    llm_provider: str
+    llm_model: str
+    input_tokens: Optional[int] = None
+    output_tokens: Optional[int] = None
+    segment_range_start: Optional[int] = None
+    segment_range_end: Optional[int] = None
+    canvas_snapshot_urls: Optional[List[str]] = None
+    created_at: datetime
+
+    class Config:
+        from_attributes = True
+
+
+# --- Keyword Watch Models ---
+
+class KeywordWatchCreate(BaseModel):
+    user_id: str
+    keyword: str
+    match_type: str = "contains"  # contains, exact, starts_with, regex
+    action: str = "log"  # log, alert, canvas_shape, webhook
+
+
+class KeywordWatchResponse(BaseModel):
+    id: str
+    user_id: str
+    keyword: str
+    match_type: str = "contains"
+    action: str = "log"
+    is_active: bool = True
+    created_at: datetime
+
+    class Config:
+        from_attributes = True
+
+
+# --- Keyword Event Models ---
+
+class KeywordEventCreate(BaseModel):
+    session_id: str
+    segment_id: Optional[str] = None
+    keyword_watch_id: Optional[str] = None
+    keyword_text: str
+    matched_in_text: str
+    session_elapsed_seconds: Optional[float] = None
+
+
+class KeywordEventResponse(BaseModel):
+    id: str
+    session_id: str
+    segment_id: Optional[str] = None
+    keyword_watch_id: Optional[str] = None
+    keyword_text: str
+    matched_in_text: str
+    session_elapsed_seconds: Optional[float] = None
+    created_at: datetime
+
+    class Config:
+        from_attributes = True
+
+
+# --- Export Models ---
+
+class ExportFormat(BaseModel):
+    format: str  # srt, txt, json
+
+
+# --- Timetable Models ---
+
+class CurrentPeriodResponse(BaseModel):
+    period_id: Optional[str] = None
+    event_type: Optional[str] = None
+    event_label: Optional[str] = None
+    start_time: Optional[datetime] = None
+    end_time: Optional[datetime] = None