openscribe/server/app/main.py

# SPDX-License-Identifier: GPL-3.0-only
"""OpenScribe server - FastAPI app.

M0 scaffold: wires the routes from api/openapi.yaml with in-memory stubs so the API shape
is real and browsable at /docs. The AI pipeline (faster-whisper transcription in M5,
Ollama summaries in M6) and real storage/DB replace the stubs in later milestones.
"""
from __future__ import annotations

from fastapi import FastAPI, HTTPException

from .config import settings
from .models import Recording, RecordingPage, Summary, Transcript

app = FastAPI(
    title="OpenScribe API",
    version="0.1.0",
    description="Self-hosted AI voice recorder server. See api/openapi.yaml.",
)

# In-memory store stands in for the DB + object storage until M5.
_recordings: dict[str, Recording] = {}


@app.get("/health")
def health() -> dict:
    # Report the resolved provider names (never secrets) so operators can confirm config.
    from .providers import build_summariser, build_transcriber

    try:
        summariser = build_summariser().name
    except Exception as exc:  # e.g. anthropic dep not installed
        summariser = f"unavailable ({type(exc).__name__})"
    return {
        "status": "ok",
        "storage_backend": settings.storage_backend,
        "transcription_provider": settings.transcription_provider,
        "transcriber": build_transcriber().name,
        "llm_provider": settings.llm_provider,
        "summariser": summariser,
    }


@app.get("/api/v1/recordings", response_model=RecordingPage, tags=["recordings"])
def list_recordings(limit: int = 50) -> RecordingPage:
    return RecordingPage(items=list(_recordings.values())[:limit], next_cursor=None)


@app.get("/api/v1/recordings/{rec_id}", response_model=Recording, tags=["recordings"])
def get_recording(rec_id: str) -> Recording:
    rec = _recordings.get(rec_id)
    if rec is None:
        raise HTTPException(status_code=404, detail="No such recording")
    return rec


@app.get("/api/v1/recordings/{rec_id}/transcript", response_model=Transcript, tags=["server"])
def get_transcript(rec_id: str) -> Transcript:
    # Implemented in M5 (faster-whisper). Until then, signal "not transcribed yet".
    if rec_id not in _recordings:
        raise HTTPException(status_code=404, detail="No such recording")
    raise HTTPException(status_code=409, detail="Not transcribed yet (M5)")


@app.get("/api/v1/recordings/{rec_id}/summary", response_model=Summary, tags=["server"])
def get_summary(rec_id: str) -> Summary:
    # Implemented in M6 (Ollama). Until then, signal "not summarised yet".
    if rec_id not in _recordings:
        raise HTTPException(status_code=404, detail="No such recording")
    raise HTTPException(status_code=409, detail="Not summarised yet (M6)")


@app.post("/api/v1/ingest", response_model=Recording, status_code=202, tags=["server"])
def ingest(recording: Recording) -> Recording:
    # M5 will store audio to the object store and queue transcription + summary.
    _recordings[recording.id] = recording
    return recording