Files
espresso_frame/server/app/main.py
T
tfaour e870898490
Build and push server image / build-and-push (push) Successful in 32s
Refine manage overlay: US/CAN state abbreviations, share-QR caption, and an escalating second menu with named-face labels
Two rounds of follow-up work on the manage-button overlay:

1. Location formatting: US/Canada now show abbreviated state/province
   ("CA", "ON") instead of the full name, other countries show the full
   country name, and each is its own line (was one line, now wraps to
   two) so longer international place names have more room without
   threatening to overlap the top-right QR box. The bottom-left share QR
   also gets a "SCAN TO DOWNLOAD" caption.

2. Escalating menu: pressing the manage button again while its overlay
   is already up adds a second level -- each Immich-identified person's
   name labeled next to their face in the photo (using Immich's own
   face recognition/People data, no detection/recognition added to this
   project). A third press exits immediately instead of waiting out the
   30s auto-revert timer. No new Immich API needed -- GET /api/faces
   already embeds a nullable person.name per face; new
   server/app/face_labels.py maps a named face's box into the final
   800x480 frame's pixel space (reusing crop-box math extracted from
   image_pipeline.py's face-aware cropping). Capped at 4 named faces,
   sized to a real firmware RAM budget: each label is its own malloc'd
   overlay region on the device, alongside the 4 fixed corner regions
   already in use. New GET /frame/face-labels returns a flattened
   fixed-slot JSON shape (not a real array) so firmware's existing
   flat-scalar parser can read it without needing an actual array
   parser. No persistent state needed for the escalation itself -- it's
   all local control flow within one continuous awake session
   (frame_client.c's run_management_menu()).
2026-07-19 09:09:06 -04:00

417 lines
15 KiB
Python

"""ESPresso Frame server: pulls photos from Immich, pre-processes them for
the panel, and serves the ESP32 a ready-to-display frame."""
from __future__ import annotations
import io
import logging
from datetime import datetime
import httpx
from fastapi import FastAPI, HTTPException, Form, Request
from fastapi.responses import HTMLResponse, RedirectResponse, Response
from fastapi.templating import Jinja2Templates
from PIL import Image
from pydantic import BaseModel
from . import config, photo_queue
from .face_labels import compute_face_labels
from .image_pipeline import render_frame
from .immich_client import ImmichClient
logger = logging.getLogger(__name__)
app = FastAPI(title="ESPresso Frame Server")
templates = Jinja2Templates(directory="app/templates")
MIN_REFRESH_INTERVAL_S = 60
MAX_REFRESH_INTERVAL_S = 86400
MIN_QUEUE_TARGET_LEN = 5
MAX_QUEUE_TARGET_LEN = 50
@app.get("/health")
def health() -> dict:
return {"status": "ok"}
@app.get("/frame/config")
def frame_config():
"""Device-facing settings, polled by the frame alongside its
reachability check. Always returns 200 with current settings
(defaults if nothing's been saved yet) -- no Immich-configured gate,
since this doubles as the "is the server up" signal."""
cfg = config.load()
return {"refresh_interval_s": cfg.refresh_interval_s}
@app.get("/", response_class=HTMLResponse)
def index(request: Request):
cfg = config.load()
return templates.TemplateResponse("index.html", {"request": request, "cfg": cfg})
@app.get("/api/albums")
def api_albums():
cfg = config.load()
if not cfg.immich_url or not cfg.immich_api_key:
raise HTTPException(400, "Immich URL/API key not configured yet")
try:
albums = ImmichClient(cfg.immich_url, cfg.immich_api_key).list_albums()
except httpx.HTTPError as e:
raise HTTPException(502, f"Could not reach Immich at {cfg.immich_url}: {e}") from e
return [{"id": a["id"], "name": a["albumName"], "count": a.get("assetCount", 0)} for a in albums]
@app.post("/api/config")
def api_config_save(
album_id: str = Form(""),
order: str = Form("sequential"),
refresh_interval_s: int = Form(3600),
smart_crop_faces: bool = Form(True),
queue_target_len: int = Form(20),
):
# Immich URL/API key are env-var only (IMMICH_URL/IMMICH_API_KEY, see
# docker-compose.yml.example) -- config.load() already applies them,
# and this handler doesn't touch cfg.immich_url/immich_api_key at all,
# so there's nothing here that could overwrite or clear them.
cfg = config.load()
if album_id != cfg.album_id:
# A newly selected album starts clean -- the old current photo and
# queue don't mean anything in the new album's context.
cfg.current_asset_id = ""
cfg.current_asset_set_at = 0.0
cfg.queue = []
cfg.queue_cursor = 0
cfg.album_id = album_id
cfg.order = order if order in ("sequential", "shuffle") else "sequential"
cfg.refresh_interval_s = max(MIN_REFRESH_INTERVAL_S, min(MAX_REFRESH_INTERVAL_S, refresh_interval_s))
cfg.smart_crop_faces = smart_crop_faces
cfg.queue_target_len = max(MIN_QUEUE_TARGET_LEN, min(MAX_QUEUE_TARGET_LEN, queue_target_len))
config.save(cfg)
return {"status": "saved"}
def _require_configured(cfg: config.FrameConfig) -> None:
if not cfg.immich_url or not cfg.immich_api_key:
raise HTTPException(400, "Immich URL/API key not configured yet")
if not cfg.album_id:
raise HTTPException(400, "No album configured yet")
def _list_assets(client: ImmichClient, cfg: config.FrameConfig) -> list[dict]:
try:
assets = client.list_album_assets(cfg.album_id)
except httpx.HTTPError as e:
raise HTTPException(502, f"Could not reach Immich at {cfg.immich_url}: {e}") from e
if not assets:
raise HTTPException(404, "Album has no photos")
return assets
def _render_asset(client: ImmichClient, cfg: config.FrameConfig, asset_id: str) -> bytes:
try:
jpeg_bytes = client.download_asset_preview(asset_id)
except httpx.HTTPError as e:
raise HTTPException(502, f"Could not download asset from Immich: {e}") from e
faces = None
if cfg.smart_crop_faces:
try:
faces = client.get_asset_faces(asset_id)
except httpx.HTTPError as e:
# A faces lookup hiccup shouldn't block showing a photo at
# all -- just fall back to a plain center-crop this cycle.
logger.warning("Could not fetch faces for asset %s: %s", asset_id, e)
source = Image.open(io.BytesIO(jpeg_bytes))
return render_frame(source, faces=faces)
@app.get("/frame/image")
def frame_image():
"""Returns the current photo. Idempotent: only actually advances to
the next photo once refresh_interval_s has elapsed since the current
one was set (see app/photo_queue.py) -- safe to call as often as the
device wants, including after an unplanned reboot, without skipping
ahead in the album."""
cfg = config.load()
_require_configured(cfg)
client = ImmichClient(cfg.immich_url, cfg.immich_api_key)
assets = _list_assets(client, cfg)
if photo_queue.get_current(cfg, assets):
config.save(cfg)
return Response(content=_render_asset(client, cfg, cfg.current_asset_id), media_type="application/octet-stream")
@app.post("/frame/advance")
def frame_advance():
"""Forces an immediate advance to the next photo, ignoring
refresh_interval_s, and resets the interval clock from now. Used by
the device's next-photo button."""
cfg = config.load()
_require_configured(cfg)
client = ImmichClient(cfg.immich_url, cfg.immich_api_key)
assets = _list_assets(client, cfg)
photo_queue.advance_forced(cfg, assets)
config.save(cfg)
return Response(content=_render_asset(client, cfg, cfg.current_asset_id), media_type="application/octet-stream")
LOCATION_LINE_MAX_LEN = 14
US_STATE_ABBR = {
"alabama": "AL", "alaska": "AK", "arizona": "AZ", "arkansas": "AR", "california": "CA",
"colorado": "CO", "connecticut": "CT", "delaware": "DE", "florida": "FL", "georgia": "GA",
"hawaii": "HI", "idaho": "ID", "illinois": "IL", "indiana": "IN", "iowa": "IA",
"kansas": "KS", "kentucky": "KY", "louisiana": "LA", "maine": "ME", "maryland": "MD",
"massachusetts": "MA", "michigan": "MI", "minnesota": "MN", "mississippi": "MS", "missouri": "MO",
"montana": "MT", "nebraska": "NE", "nevada": "NV", "new hampshire": "NH", "new jersey": "NJ",
"new mexico": "NM", "new york": "NY", "north carolina": "NC", "north dakota": "ND", "ohio": "OH",
"oklahoma": "OK", "oregon": "OR", "pennsylvania": "PA", "rhode island": "RI", "south carolina": "SC",
"south dakota": "SD", "tennessee": "TN", "texas": "TX", "utah": "UT", "vermont": "VT",
"virginia": "VA", "washington": "WA", "west virginia": "WV", "wisconsin": "WI", "wyoming": "WY",
"district of columbia": "DC",
}
CA_PROVINCE_ABBR = {
"alberta": "AB", "british columbia": "BC", "manitoba": "MB", "new brunswick": "NB",
"newfoundland and labrador": "NL", "northwest territories": "NT", "nova scotia": "NS",
"nunavut": "NU", "ontario": "ON", "prince edward island": "PE", "quebec": "QC",
"saskatchewan": "SK", "yukon": "YT",
}
US_COUNTRY_NAMES = {"united states", "united states of america", "usa", "us"}
CA_COUNTRY_NAMES = {"canada"}
def _truncate(text: str, max_len: int) -> str:
if len(text) <= max_len:
return text
return text[: max_len - 3] + "..."
def _format_location(exif: dict) -> tuple[str, str] | None:
"""Returns (city_line, region_line), each independently truncated to
fit its own corner-overlay line, or None if Immich hasn't geocoded
this photo. region_line is the abbreviated state/province for US/CAN
locations (e.g. "CA", "ON"), else the full country name."""
city = exif.get("city")
if not city:
return None
state = exif.get("state")
country = exif.get("country")
country_key = (country or "").strip().lower()
if state and country_key in US_COUNTRY_NAMES:
region = US_STATE_ABBR.get(state.strip().lower(), state)
elif state and country_key in CA_COUNTRY_NAMES:
region = CA_PROVINCE_ABBR.get(state.strip().lower(), state)
elif country:
region = country
elif state:
region = state
else:
region = ""
return _truncate(city, LOCATION_LINE_MAX_LEN), _truncate(region, LOCATION_LINE_MAX_LEN)
def _format_taken_at(exif: dict) -> str | None:
raw = exif.get("dateTimeOriginal")
if not raw:
return None
try:
return datetime.fromisoformat(raw.replace("Z", "+00:00")).strftime("%m/%d/%y")
except ValueError:
return None
@app.get("/frame/photo-info")
def frame_photo_info():
"""Location/date-taken text for the manage-button overlay, plus the
asset id used to build the share-QR's target URL. Read-only, same
idempotent current-photo semantics as /frame/image -- doesn't advance
anything."""
cfg = config.load()
_require_configured(cfg)
client = ImmichClient(cfg.immich_url, cfg.immich_api_key)
assets = _list_assets(client, cfg)
if photo_queue.get_current(cfg, assets):
config.save(cfg)
if not cfg.current_asset_id:
raise HTTPException(404, "No current photo")
try:
asset = client.get_asset(cfg.current_asset_id)
except httpx.HTTPError as e:
raise HTTPException(502, f"Could not reach Immich: {e}") from e
exif = asset.get("exifInfo") or {}
location = _format_location(exif)
return {
"asset_id": cfg.current_asset_id,
"location_line1": location[0] if location else None,
"location_line2": location[1] if location and location[1] else None,
"taken_at": _format_taken_at(exif),
}
@app.get("/frame/share/{asset_id}")
def frame_share(asset_id: str):
"""Creates a 30-minute public Immich share link for asset_id and
redirects to it -- what the manage overlay's bottom-left QR code
points to. The link is created lazily, when this actually gets hit
(i.e. when someone scans it), not when the manage button was
pressed, so the 30-minute window starts when it's actually used.
Scoped to the photo currently showing or queued -- not any arbitrary
Immich asset id -- since this is otherwise an unauthenticated
endpoint (see server/README.md)."""
cfg = config.load()
_require_configured(cfg)
if asset_id != cfg.current_asset_id and asset_id not in cfg.queue:
raise HTTPException(404, "That photo isn't currently showing or queued on this frame")
client = ImmichClient(cfg.immich_url, cfg.immich_api_key)
try:
share_url = client.create_share_link(asset_id, expires_in_s=1800)
except httpx.HTTPError as e:
raise HTTPException(502, f"Could not create share link: {e}") from e
return RedirectResponse(share_url)
@app.get("/frame/face-labels")
def frame_face_labels():
"""Named-face positions for the manage button's escalated "level 2"
menu -- who's in the current photo, per Immich's own face
recognition (no detection/recognition happens here, see
app/face_labels.py). Response is a flattened, fixed-slot shape
(name_0/x_0/y_0, name_1/x_1/y_1, ...) rather than a JSON array, so
the device's hand-rolled parser can read it with the same flat-
scalar helpers it already has, instead of needing a real array
parser. Empty (count: 0) if no faces are named, or if anything about
fetching them fails -- this is a "nice to have" addition to the
overlay, not worth failing the whole menu over."""
cfg = config.load()
_require_configured(cfg)
client = ImmichClient(cfg.immich_url, cfg.immich_api_key)
assets = _list_assets(client, cfg)
if photo_queue.get_current(cfg, assets):
config.save(cfg)
if not cfg.current_asset_id:
return {"count": 0}
try:
faces = client.get_asset_faces(cfg.current_asset_id)
except httpx.HTTPError as e:
logger.warning("Could not fetch faces for asset %s: %s", cfg.current_asset_id, e)
return {"count": 0}
if not any((face.get("person") or {}).get("name") for face in faces):
return {"count": 0} # skip the extra preview download in the common no-named-faces case
try:
preview_bytes = client.download_asset_preview(cfg.current_asset_id)
except httpx.HTTPError as e:
logger.warning("Could not download asset %s for face-label mapping: %s", cfg.current_asset_id, e)
return {"count": 0}
labels = compute_face_labels(preview_bytes, faces, cfg.smart_crop_faces)
result: dict[str, object] = {"count": len(labels)}
for i, label in enumerate(labels):
result[f"name_{i}"] = label["name"]
result[f"x_{i}"] = label["x"]
result[f"y_{i}"] = label["y"]
return result
@app.get("/api/queue")
def api_queue():
cfg = config.load()
_require_configured(cfg)
client = ImmichClient(cfg.immich_url, cfg.immich_api_key)
assets = _list_assets(client, cfg)
current_changed = photo_queue.get_current(cfg, assets)
queue_before = list(cfg.queue)
photo_queue.sync_queue_length(cfg, assets)
if current_changed or cfg.queue != queue_before:
config.save(cfg)
def entry(asset_id: str) -> dict:
return {"id": asset_id, "thumbnail_url": f"/api/photo-thumbnail/{asset_id}"}
return {
"current": entry(cfg.current_asset_id) if cfg.current_asset_id else None,
"upcoming": [entry(asset_id) for asset_id in cfg.queue],
}
class QueueReorderRequest(BaseModel):
queue: list[str]
@app.post("/api/queue/reorder")
def api_queue_reorder(body: QueueReorderRequest):
"""Applies the client's requested order, tolerating drift between the
browser's last-fetched snapshot and the server's current queue (e.g.
a top-up/trim landed in between) instead of hard-rejecting: any ID
the client sent that's no longer actually queued is dropped, and any
ID the server has that the client didn't know about is appended
rather than lost."""
cfg = config.load()
current_set = set(cfg.queue)
reordered = [asset_id for asset_id in body.queue if asset_id in current_set]
reordered += [asset_id for asset_id in cfg.queue if asset_id not in set(reordered)]
cfg.queue = reordered
config.save(cfg)
return {"status": "saved"}
class QueuePromoteRequest(BaseModel):
asset_id: str
@app.post("/api/queue/promote")
def api_queue_promote(body: QueuePromoteRequest):
"""Moves a single photo to the front of the queue -- "Show next" in
the web UI. Unlike /api/queue/reorder, this doesn't depend on the
client supplying a full, exactly-current snapshot of the queue at
all, so it can't fail due to the queue having shifted server-side
since the browser's last fetch."""
cfg = config.load()
if body.asset_id not in cfg.queue:
raise HTTPException(400, "That photo is no longer in the upcoming queue")
cfg.queue = [body.asset_id] + [asset_id for asset_id in cfg.queue if asset_id != body.asset_id]
config.save(cfg)
return {"status": "saved"}
@app.get("/api/photo-thumbnail/{asset_id}")
def api_photo_thumbnail(asset_id: str):
cfg = config.load()
_require_configured(cfg)
client = ImmichClient(cfg.immich_url, cfg.immich_api_key)
try:
content, content_type = client.download_asset_thumbnail(asset_id)
except httpx.HTTPError as e:
raise HTTPException(502, f"Could not download thumbnail from Immich: {e}") from e
return Response(content=content, media_type=content_type)