Publish media catalog as markdown attachment

.env.deploy.example

@@ -5,7 +5,6 @@ ARCHIVE_STATUS_STATE=state/status-message.json
 MEDIA_CATALOG_STATE=state/media-catalog.json
 MEDIA_LIBRARY_STATE=state/media-library.json
 BOT_SETTINGS_STATE=state/bot-settings.json
-MEDIA_CATALOG_MAX_ITEMS=240
 CHECK_INTERVAL_SECONDS=60
 HTTP_USER_AGENT=ArchiveStatusBot/1.0
 DISCORD_DRY_RUN=false

.env.example

@@ -5,7 +5,6 @@ ARCHIVE_STATUS_STATE=state/status-message.json
 MEDIA_CATALOG_STATE=state/media-catalog.json
 MEDIA_LIBRARY_STATE=state/media-library.json
 BOT_SETTINGS_STATE=state/bot-settings.json
-MEDIA_CATALOG_MAX_ITEMS=240
 CHECK_INTERVAL_SECONDS=60
 HTTP_USER_AGENT=ArchiveStatusBot/1.0
 DISCORD_DRY_RUN=false

README.md

@@ -23,6 +23,7 @@ Required channel permissions for each dashboard-selected channel:
 - View Channel
 - Send Messages
 - Embed Links
+- Attach Files
 - Read Message History
 
 Channel IDs are configured from the dashboard and stored in `state/bot-settings.json`.
@@ -188,7 +189,7 @@ The dashboard currently supports:
 - forcing an immediate check and Discord message update
 - uploading `Movies.csv` and `Shows.csv`
 - editing imported movies and shows before publishing
-- publishing a paginated media catalog to a selected Discord channel
+- publishing a compact Markdown media catalog to a selected Discord channel
 
 The sidebar leaves room for future modules like polls, webhooks, automations, and service integrations without changing the bot shape later.
 
@@ -198,6 +199,8 @@ Open the dashboard and switch to `Media`. Set the target Discord channel ID, cho
 
 The editor supports adding, editing, and deleting movie/show rows before saving or publishing. Publishing sends the currently edited dashboard library, not the raw uploaded files.
 
+Discord publishing uses one message with an attached `media-catalog.md` file so the channel does not get flooded by a long embed wall.
+
 Channel selections are stored in:
 
 ```env
@@ -218,13 +221,7 @@ The editable media library is stored in:
 MEDIA_LIBRARY_STATE=state/media-library.json
 ```
 
-Republishing edits the previous catalog messages in place. If the catalog gets shorter, the bot attempts to delete old extra messages.
+Republishing deletes the previous media catalog message and posts a fresh compact Markdown attachment.
-
-By default, Discord output is capped at 240 movies and 240 shows to avoid flooding a channel. Change this with:
-
-```env
-MEDIA_CATALOG_MAX_ITEMS=240
-```
 
 ## Service Config
 

status_bot.py

@@ -39,7 +39,6 @@ MAX_REQUEST_BYTES = 8_000_000
 SESSION_COOKIE = "archive_bot_session"
 PBKDF2_ITERATIONS = 390_000
 MEDIA_ITEMS_PER_EMBED = 10
-MAX_MEDIA_ITEMS_PER_CATEGORY = 240
 
 
 @dataclass(frozen=True)
@@ -499,6 +498,53 @@ def discord_request(
         raise RuntimeError(f"Discord API {method} {path} failed: {exc.code} {detail}") from exc
 
 
+def discord_multipart_request(
+    method: str,
+    token: str,
+    path: str,
+    payload: dict[str, Any],
+    files: list[tuple[str, str, str, bytes]],
+) -> dict[str, Any]:
+    boundary = f"----ArchiveBot{secrets.token_hex(16)}"
+    body = bytearray()
+
+    def add_part(name: str, content: bytes, content_type: str, filename: str | None = None) -> None:
+        body.extend(f"--{boundary}\r\n".encode("ascii"))
+        disposition = f'Content-Disposition: form-data; name="{name}"'
+        if filename is not None:
+            disposition += f'; filename="{filename}"'
+        body.extend(f"{disposition}\r\n".encode("utf-8"))
+        body.extend(f"Content-Type: {content_type}\r\n\r\n".encode("ascii"))
+        body.extend(content)
+        body.extend(b"\r\n")
+
+    add_part("payload_json", json.dumps(payload).encode("utf-8"), "application/json")
+    for field_name, filename, content_type, content in files:
+        add_part(field_name, content, content_type, filename)
+    body.extend(f"--{boundary}--\r\n".encode("ascii"))
+
+    request = urllib.request.Request(
+        f"{DISCORD_API}{path}",
+        data=bytes(body),
+        headers={
+            "Authorization": f"Bot {token}",
+            "User-Agent": "ArchiveStatusBot/1.0",
+            "Content-Type": f"multipart/form-data; boundary={boundary}",
+        },
+        method=method,
+    )
+
+    try:
+        with urllib.request.urlopen(request, timeout=30) as response:
+            data = response.read()
+            if not data:
+                return {}
+            return json.loads(data.decode("utf-8"))
+    except urllib.error.HTTPError as exc:
+        detail = exc.read().decode("utf-8", errors="ignore")
+        raise RuntimeError(f"Discord API {method} {path} failed: {exc.code} {detail}") from exc
+
+
 def discord_delete_message(token: str, channel_id: str, message_id: str) -> None:
     try:
         discord_request("DELETE", token, f"/channels/{channel_id}/messages/{message_id}")
@@ -975,6 +1021,83 @@ def render_media_catalog_payloads(
     return payloads
 
 
+def media_markdown_line(item: MediaItem) -> str:
+    title = media_item_heading(item)
+    details: list[str] = []
+    if item.genres:
+        details.append(item.genres)
+    if item.rating:
+        details.append(item.rating)
+    if item.runtime and item.media_type == "movie":
+        details.append(item.runtime)
+    if item.media_type == "show":
+        if item.seasons:
+            details.append(f"{item.seasons} season{'s' if item.seasons != 1 else ''}")
+        if item.episodes:
+            details.append(f"{item.episodes} episode{'s' if item.episodes != 1 else ''}")
+
+    suffix = f" - {'; '.join(details)}" if details else ""
+    return f"- **{title}**{suffix}"
+
+
+def render_media_catalog_markdown(movies: list[MediaItem], shows: list[MediaItem]) -> str:
+    now = datetime.now(timezone.utc)
+    lines = [
+        "# The Mithral Archive Media Catalog",
+        "",
+        f"Updated: {now.strftime('%Y-%m-%d %H:%M UTC')}",
+        f"Movies: {len(movies)}",
+        f"Shows: {len(shows)}",
+        "",
+    ]
+
+    if movies:
+        lines.extend(["## Movies", ""])
+        for item in movies:
+            lines.append(media_markdown_line(item))
+            if item.summary:
+                lines.append(f"  - {item.summary}")
+        lines.append("")
+
+    if shows:
+        lines.extend(["## Shows", ""])
+        for item in shows:
+            lines.append(media_markdown_line(item))
+            if item.summary:
+                lines.append(f"  - {item.summary}")
+        lines.append("")
+
+    return "\n".join(lines).strip() + "\n"
+
+
+def publish_media_markdown_message(
+    token: str,
+    channel_id: str,
+    movies: list[MediaItem],
+    shows: list[MediaItem],
+) -> str:
+    markdown = render_media_catalog_markdown(movies, shows)
+    payload = {
+        "content": (
+            "**The Mithral Archive Media Catalog**\n"
+            f"{len(movies)} movies · {len(shows)} shows\n"
+            "Attached as a compact Markdown list."
+        ),
+        "allowed_mentions": {"parse": []},
+    }
+    message = discord_multipart_request(
+        "POST",
+        token,
+        f"/channels/{channel_id}/messages",
+        payload,
+        [("files[0]", "media-catalog.md", "text/markdown; charset=utf-8", markdown.encode("utf-8"))],
+    )
+    message_id = str(message.get("id", "")).strip()
+    if not message_id:
+        raise RuntimeError("Discord did not return a message id for the media catalog")
+    return message_id
+
+
 def publish_media_items(
     runtime: BotRuntime,
     channel_id: str,
@@ -992,18 +1115,6 @@ def publish_media_items(
     if not movies_all and not shows_all:
         raise ValueError("Add at least one movie or show before publishing")
 
-    limit = int(os.getenv("MEDIA_CATALOG_MAX_ITEMS", str(MAX_MEDIA_ITEMS_PER_CATEGORY)))
-    movies = movies_all[:limit]
-    shows = shows_all[:limit]
-    payloads = render_media_catalog_payloads(
-        movies=movies,
-        shows=shows,
-        movie_total=len(movies_all),
-        show_total=len(shows_all),
-        movie_source=movie_source,
-        show_source=show_source,
-    )
-
     state = load_state(runtime.media_state_path)
     old_channel = str(state.get("channel_id", "")).strip()
     existing_ids = [
@@ -1011,33 +1122,20 @@ def publish_media_items(
         for message_id in state.get("message_ids", [])
         if str(message_id).strip()
     ]
-    if old_channel and old_channel != channel:
+    delete_channel = old_channel or channel
-        for old_id in existing_ids:
+    for old_id in existing_ids:
-            discord_delete_message(runtime.token, old_channel, old_id)
+        discord_delete_message(runtime.token, delete_channel, old_id)
-        existing_ids = []
 
-    message_ids: list[str] = []
+    message_id = publish_media_markdown_message(runtime.token, channel, movies_all, shows_all)
-    for index, payload in enumerate(payloads):
-        if index < len(existing_ids):
-            discord_request("PATCH", runtime.token, f"/channels/{channel}/messages/{existing_ids[index]}", payload)
-            message_ids.append(existing_ids[index])
-            continue
-        message = discord_request("POST", runtime.token, f"/channels/{channel}/messages", payload)
-        message_id = str(message.get("id", "")).strip()
-        if not message_id:
-            raise RuntimeError("Discord did not return a message id for the media catalog")
-        message_ids.append(message_id)
-
-    for old_id in existing_ids[len(payloads) :]:
-        discord_delete_message(runtime.token, channel, old_id)
 
     save_state(
         runtime.media_state_path,
         {
             "channel_id": channel,
-            "message_ids": message_ids,
+            "message_ids": [message_id],
             "movie_count": len(movies_all),
             "show_count": len(shows_all),
+            "format": "markdown",
             "published_at": datetime.now(timezone.utc).isoformat(),
         },
     )
@@ -1045,11 +1143,12 @@ def publish_media_items(
 
     return {
         "channelId": channel,
-        "messageIds": message_ids,
+        "messageIds": [message_id],
         "movieCount": len(movies_all),
         "showCount": len(shows_all),
-        "displayedMovieCount": len(movies),
+        "displayedMovieCount": len(movies_all),
-        "displayedShowCount": len(shows),
+        "displayedShowCount": len(shows_all),
+        "format": "markdown",
     }
 
 
@@ -1083,8 +1182,8 @@ def media_catalog_status(runtime: BotRuntime) -> dict[str, Any]:
         "messageIds": state.get("message_ids", []) if isinstance(state.get("message_ids"), list) else [],
         "movieCount": state.get("movie_count"),
         "showCount": state.get("show_count"),
+        "format": state.get("format", "markdown"),
         "publishedAt": state.get("published_at"),
-        "maxItemsPerCategory": int(os.getenv("MEDIA_CATALOG_MAX_ITEMS", str(MAX_MEDIA_ITEMS_PER_CATEGORY))),
         "library": media_library_to_jsonable(movies, shows),
     }