IP cameras (ONVIF/RTSP)

Add an ONVIF/RTSP IP camera. Ask the user for the camera's IP address (from its app or router) and pick a short name such as "garage". Credentials are never passed as arguments: by default the user is shown a login form; with credentials_via="file" a secrets file is created for the user to fill in, then call add_camera again with credentials_via="file". Use credentials_via="file" when the user is on Remote Control or a phone and the form does not appear. onvif_port: only if the camera uses a non-standard ONVIF port (80 and 2020 are tried). scene: the place it watches, if not its own name (several cameras may share a scene).

Take a new snapshot and report what changed compared with this camera's previous snapshot in its current scene, or with a named baseline saved in that scene. Use the reported cells as `region` in camera_snapshot to look closer.

Record a video clip (1-60 s) from a camera to an mp4 file on the local machine. Returns the file path and size; the video itself is not returned, so take a snapshot if you need to see the scene. quality: "high" = main stream (1080p); "low" = sub stream (smaller file).

Take a snapshot and keep it as a named reference for camera_compare (e.g. 'door-closed').

Take a still picture from a camera. Returns the image (downscaled to at most 1280 px wide) and the path of the full-size JPEG saved on the local machine. quality: "high" = main stream (1080p); "low" = sub stream (smaller, quicker). crop: [x, y, w, h] as fractions of the frame (0-1) to see a detail at full resolution. region: a named ninth of the frame instead of crop (not both). from_path: reuse an earlier full-size snapshot (e.g. the one just viewed, or one from scene_timeline) instead of taking a new one; combine with crop/region to zoom into it. The camera is not contacted, and camera may be omitted.

Delete a camera and all its snapshots, recordings and baselines, or the leftover files of a removed camera with that name. The user approves in a form that lists what will be deleted; you cannot approve it. Without form support nothing is deleted and the result says how to do it by hand.

List configured cameras with their ids (names), uids, types and capabilities (camera, ptz). include_removed=true also lists removed cameras whose files are still on disk ("removed": true), e.g. to clean them up with delete_camera.

The scenes (places watched): their configured cameras, removed cameras that were there, the time of the oldest and newest capture, and how many there are.

Move a pan/tilt camera to a saved preset, given by name or token.

List the saved camera positions (presets) of a pan/tilt camera.

Pan or tilt a camera. Directions are as seen in the camera image ("left" turns the view left). amount: "small" is a slight nudge, "medium" a noticeable turn, "large" a big sweep. Waits until the camera has stopped, then returns its pan/tilt position if the camera reports one. Take a snapshot afterwards to see the new view.

Delete a saved preset by name or token. This cannot be undone.

Save the camera's current position as a preset. Refuses an existing name unless overwrite=true.

Re-read cameras.toml after it was edited by hand and list the cameras, in the same format as list_cameras.

Remove a camera from the configuration. Never deletes snapshots or recordings (delete_camera does, after the user approves).

Change a camera's name. Its baselines, snapshots and recordings stay with it.

camera_compare for every camera in the scene, labelled with the camera's name.

Take a snapshot with every camera in the scene, labelled with the camera's name.

The scene's snapshots, recordings and baselines, newest first, from every camera that watched it (removed ones too). start/end: YYYY-MM-DD (whole day) or an ISO datetime. Open a snapshot with camera_snapshot(from_path=...).

Move a camera to another scene (the place it watches). Its earlier snapshots stay with the earlier scene; camera_compare only compares within the current scene. If removed cameras watched that scene, the user is asked in a form whether this camera replaces one of them (it then continues that camera's compare and baselines). Call it with the camera's current scene to answer that question later.