feat: support audio & vidéo — lecteurs HTML5 intégrés #109

backend/bookslm.py

@@ -15,6 +15,7 @@ import time
 from pathlib import Path
 from typing import Any
 
+from backend.media_types import is_media
 from backend.secret_redactor import redact_file_content
 
 logger = logging.getLogger("obsigate.bookslm")
@@ -185,6 +186,10 @@ def collect_directory_context(vault_path: Path, directory: str) -> dict[str, Any
 def _file_entry(target: Path, rel_path: str, remaining: int) -> dict[str, Any] | None:
     """Read, redact and truncate a single file into a context entry."""
     suffix = target.suffix.lower()
+    # #109-D3 — audio/video (and images) carry no extractable text; never feed
+    # raw bytes to the model. Images are handled separately via vision data URLs.
+    if is_media(suffix):
+        return None
     try:
         if suffix == ".pdf":
             from backend.pdf_reader import extract_pdf_text

backend/indexer.py

@@ -11,7 +11,7 @@ from typing import Any
 
 import frontmatter
 
-from backend.media_types import IMAGE_EXTENSIONS, is_media
+from backend.media_types import AUDIO_EXTENSIONS, IMAGE_EXTENSIONS, VIDEO_EXTENSIONS, is_media
 
 logger = logging.getLogger("obsigate.indexer")
 
@@ -71,7 +71,7 @@ SUPPORTED_EXTENSIONS = {
     ".dockerfile", ".makefile", ".cmake",
     ".excalidraw",
     ".excalidraw.md",
-} | set(IMAGE_EXTENSIONS)
+} | set(IMAGE_EXTENSIONS) | set(AUDIO_EXTENSIONS) | set(VIDEO_EXTENSIONS)
 
 
 # Ignored directories (configurable via OBSIGATE_IGNORED_DIRS env var)

backend/main.py

@@ -53,7 +53,7 @@ from backend.indexer import (
     update_single_file,
 )
 from backend.media_thumbs import generate_thumbnail, is_decodable
-from backend.media_types import IMAGE_EXTENSIONS, is_image, media_mime_type
+from backend.media_types import IMAGE_EXTENSIONS, is_audio, is_image, is_video, media_mime_type
 from backend.openapi_docs import (
     API_DESCRIPTION,
     TAGS_METADATA,
@@ -205,6 +205,11 @@ class FileContentResponse(BaseModel):
     size_bytes: int | None = Field(default=None, description="File size in bytes (for unsupported files)")
     is_pdf: bool | None = Field(default=None, description="True for PDF files")
     is_image: bool | None = Field(default=None, description="True for image files")
+    is_audio: bool | None = Field(default=None, description="True for audio files (HTML5 <audio>, roadmap #109)")
+    is_video: bool | None = Field(default=None, description="True for video files (HTML5 <video>, roadmap #109)")
+    media_too_large: bool | None = Field(default=None, description="True when audio/video exceeds the inline streaming limit")
+    stream_url: str | None = Field(default=None, description="Byte-range streaming URL under /api/media (audio/video)")
+    media_mime: str | None = Field(default=None, description="MIME type for audio/video files")
     is_csv: bool | None = Field(default=None, description="True for CSV files")
     is_json: bool | None = Field(default=None, description="True for JSON files")
     is_excalidraw: bool | None = Field(default=None, description="True for Excalidraw diagram files")
@@ -1037,6 +1042,27 @@ def _content_disposition(disposition: str, filename: str) -> str:
     return f"{disposition}; filename=\"{ascii_name}\"; filename*=UTF-8''{quote(filename)}"
 
 
+def _media_max_inline_bytes() -> int:
+    """Maximum size (bytes) for inline audio/video playback (roadmap #109-A3).
+
+    Configurable via ``OBSIGATE_MEDIA_MAX_INLINE_MB`` (default 500 MB). Files
+    above the limit are not streamed in the viewer (the UI falls back to the
+    download button), which keeps a single uvicorn worker from being pinned by
+    multi-gigabyte media. Invalid or non-positive values fall back to default.
+    """
+    default_mb = 500
+    raw = os.environ.get("OBSIGATE_MEDIA_MAX_INLINE_MB", "").strip()
+    if not raw:
+        return default_mb * 1024 * 1024
+    try:
+        mb = float(raw)
+    except ValueError:
+        return default_mb * 1024 * 1024
+    if mb <= 0:
+        return default_mb * 1024 * 1024
+    return int(mb * 1024 * 1024)
+
+
 def _resolve_safe_path(vault_root: Path, relative_path: str | None) -> Path:
     """Resolve a relative path safely within the vault root.
 
@@ -2443,6 +2469,61 @@ async def api_file(vault_name: str, path: str = Query(..., description="Relative
             "size_bytes": size,
         }
 
+    # === Audio / Video: HTML5 players streamed from /api/media (roadmap #109) ===
+    if is_audio(ext) or is_video(ext):
+        size = file_path.stat().st_size
+        mime = media_mime_type(str(file_path))
+        media_kind = "audio" if is_audio(ext) else "video"
+
+        # #109-A3 — beyond the inline limit the viewer falls back to download
+        # (a single uvicorn worker must not be pinned by multi-GB media).
+        if size > _media_max_inline_bytes():
+            return {
+                "vault": vault_name,
+                "path": path,
+                "title": file_path.name,
+                "tags": [],
+                "frontmatter": {},
+                "html": "",
+                "raw_length": size,
+                "extension": ext,
+                "is_markdown": False,
+                "unsupported": True,
+                "media_too_large": True,
+                "size_bytes": size,
+            }
+
+        # #109-A2 — byte-range endpoint: enables scrub and is required by Safari.
+        stream_url = f"/api/media/{quote(vault_name, safe='')}?path={quote(path, safe='')}"
+        if media_kind == "audio":
+            html = (
+                f'<div class="audio-viewer">'
+                f'<audio controls preload="metadata" src="{stream_url}"></audio>'
+                f'</div>'
+            )
+        else:
+            html = (
+                f'<div class="video-viewer">'
+                f'<video controls playsinline preload="metadata" src="{stream_url}"></video>'
+                f'</div>'
+            )
+        return {
+            "vault": vault_name,
+            "path": path,
+            "title": file_path.name,
+            "tags": [],
+            "frontmatter": {},
+            "html": html,
+            "raw_length": size,
+            "extension": ext,
+            "is_markdown": False,
+            "is_audio": media_kind == "audio",
+            "is_video": media_kind == "video",
+            "media_mime": mime,
+            "stream_url": stream_url,
+            "size_bytes": size,
+        }
+
     try:
         raw = file_path.read_text(encoding="utf-8", errors="replace")
     except PermissionError as e:
@@ -2618,32 +2699,21 @@ async def api_file(vault_name: str, path: str = Query(..., description="Relative
         }
 
 
-@app.get("/api/file/{vault_name}/pdf/stream", response_class=FileResponse)
-async def api_pdf_stream(
-    request: Request,
-    vault_name: str,
-    path: str = Query(...),
-    current_user=Depends(require_auth),
-):
-    """Stream a PDF file with Content-Type: application/pdf for inline browser viewing.
+def _stream_file_with_range(file_path: Path, request: Request, media_type: str):
+    """Return a file response honouring the HTTP ``Range`` header (roadmap #109).
 
-    Supports HTTP Range requests (206 Partial Content) so browsers can
-    progressively render large PDFs in the native viewer.
+    Shared by ``pdf/stream`` and ``/api/media``: a plain :class:`FileResponse`
+    with ``Accept-Ranges: bytes`` when no range is requested, or a
+    :class:`StreamingResponse` (206 Partial Content, 64 KiB chunks) for a valid
+    single range. An unsatisfiable range yields ``416`` with a
+    ``Content-Range: bytes */size`` header.
+
+    Reads are offloaded to threads so the event loop is never blocked
+    (ASYNC230), matching the previous inline implementation.
     """
-    if not check_vault_access(vault_name, current_user):
-        raise HTTPException(status_code=403, detail=f"Accès refusé à la vault '{vault_name}'")
-    vault_data = get_vault_data(vault_name)
-    if not vault_data:
-        raise HTTPException(status_code=404, detail=f"Vault '{vault_name}' not found")
-    vault_root = Path(vault_data["path"])
-    file_path = _resolve_safe_path(vault_root, path)
-    if not file_path.exists() or not file_path.is_file():
-        raise HTTPException(status_code=404, detail=f"File not found: {path}")
-    if file_path.suffix.lower() != ".pdf":
-        raise HTTPException(status_code=400, detail="Not a PDF file")
-
     file_size = file_path.stat().st_size
     range_header = request.headers.get("range")
+    disposition = _content_disposition("inline", file_path.name)
 
     if range_header:
         # Parse "bytes=start-end" (single range only; multi-range is not used by viewers)
@@ -2671,7 +2741,6 @@ async def api_pdf_stream(
         chunk_size = end - start + 1
 
         async def _partial():
-            # Open + reads offloaded to threads (avoid blocking the event loop — ASYNC230)
             f = await asyncio.to_thread(open, str(file_path), "rb")
             try:
                 await asyncio.to_thread(f.seek, start)
@@ -2688,18 +2757,45 @@ async def api_pdf_stream(
         return StreamingResponse(
             _partial(),
             status_code=206,
-            media_type="application/pdf",
+            media_type=media_type,
             headers={
                 "Content-Range": f"bytes {start}-{end}/{file_size}",
                 "Accept-Ranges": "bytes",
                 "Content-Length": str(chunk_size),
-                "Content-Disposition": _content_disposition("inline", file_path.name),
+                "Content-Disposition": disposition,
             },
         )
 
-    return FileResponse(str(file_path), media_type="application/pdf", headers={
+    return FileResponse(str(file_path), media_type=media_type, headers={
         "Accept-Ranges": "bytes",
-        "Content-Disposition": _content_disposition("inline", file_path.name)})
+        "Content-Disposition": disposition})
+
+
+@app.get("/api/file/{vault_name}/pdf/stream", response_class=FileResponse)
+async def api_pdf_stream(
+    request: Request,
+    vault_name: str,
+    path: str = Query(...),
+    current_user=Depends(require_auth),
+):
+    """Stream a PDF file with Content-Type: application/pdf for inline browser viewing.
+
+    Supports HTTP Range requests (206 Partial Content) so browsers can
+    progressively render large PDFs in the native viewer.
+    """
+    if not check_vault_access(vault_name, current_user):
+        raise HTTPException(status_code=403, detail=f"Accès refusé à la vault '{vault_name}'")
+    vault_data = get_vault_data(vault_name)
+    if not vault_data:
+        raise HTTPException(status_code=404, detail=f"Vault '{vault_name}' not found")
+    vault_root = Path(vault_data["path"])
+    file_path = _resolve_safe_path(vault_root, path)
+    if not file_path.exists() or not file_path.is_file():
+        raise HTTPException(status_code=404, detail=f"File not found: {path}")
+    if file_path.suffix.lower() != ".pdf":
+        raise HTTPException(status_code=400, detail="Not a PDF file")
+
+    return _stream_file_with_range(file_path, request, "application/pdf")
 
 
 @app.get("/api/file/{vault_name}/pdf/info", response_model=PdfInfoResponse)
@@ -3207,6 +3303,42 @@ async def api_image(vault_name: str, path: str = Query(..., description="Relativ
         raise HTTPException(status_code=500, detail=f"Error serving image: {e!s}")
 
 
+@app.get("/api/media/{vault_name}", response_class=FileResponse)
+async def api_media_stream(
+    request: Request,
+    vault_name: str,
+    path: str = Query(..., description="Relative path to audio/video file"),
+    current_user=Depends(require_auth),
+):
+    """Stream an audio/video file with HTTP Range support (roadmap #109-A2).
+
+    Serves the bytes with the correct MIME type and honours ``Range`` requests
+    (``206 Partial Content`` + ``Content-Range``/``Accept-Ranges``), which is
+    what enables scrubbing in ``<audio>``/``<video>`` and is required by Safari
+    for MP4. Files above ``OBSIGATE_MEDIA_MAX_INLINE_MB`` (default 500 MB) are
+    refused with ``413`` — the viewer falls back to the download button.
+    """
+    if not check_vault_access(vault_name, current_user):
+        raise HTTPException(status_code=403, detail=f"Accès refusé à la vault '{vault_name}'")
+    vault_data = get_vault_data(vault_name)
+    if not vault_data:
+        raise HTTPException(status_code=404, detail=f"Vault '{vault_name}' not found")
+
+    vault_root = Path(vault_data["path"])
+    file_path = _resolve_safe_path(vault_root, path)
+    if not file_path.exists() or not file_path.is_file():
+        raise HTTPException(status_code=404, detail=f"Media not found: {path}")
+
+    ext = file_path.suffix.lower()
+    if not (is_audio(ext) or is_video(ext)):
+        raise HTTPException(status_code=400, detail="Not an audio/video file")
+
+    if file_path.stat().st_size > _media_max_inline_bytes():
+        raise HTTPException(status_code=413, detail="Media too large for inline streaming")
+
+    return _stream_file_with_range(file_path, request, media_mime_type(str(file_path)))
+
+
 @app.get("/api/media/{vault_name}/thumb", response_class=FileResponse)
 async def api_media_thumb(
     vault_name: str,