Apply conversation bot improvements (proto-improvements)

Diff vs working-copy baseline = exactly this session's bot edits: - constants.py: env-var config, safe JSON loading, optional-dependency guards, env->netrc token resolution, API_SHARED_KEY + service_headers() - communication_subroutine.py: queue get(timeout) + Empty handling, daemon threads, cooperative stop_event, inbound _authorize_request() - bot.py: single asyncio event loop with cooperative shutdown - music_functions / radio_commands / librarian_commands: send X-Conjurer-Api-Key on internal HTTP calls via service_headers() Musician runtime data overlay dropped; conjurer_musician/.gitignore now keeps generated playlists/mp3 out of the repo. The 1+2+3 musician code port already lives in the base conjurer_musician. Depends on #9: must merge after restructure/working-copy-root. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-14 21:38:38 +00:00 · 2026-06-28 23:36:58 +02:00
parent f9a1e7c03a
commit f9bb0b2834
7 changed files with 334 additions and 91 deletions
@@ -1,13 +1,51 @@
+"""Centralised configuration and runtime constants for Conjurer.
+
+Historically this module performed heavy filesystem and credential reads at
+import time which made the bot brittle on hosts that did not mirror the
+original paths.  This version keeps the original platform defaults (so the
+behaviour on the Raspberry Pi / WSL / Windows deployments is unchanged when no
+environment variables are set) but adds three robustness improvements ported
+from the dockerised experiment:
+
+* every path/endpoint can be overridden via an environment variable,
+* JSON state files are loaded defensively (a missing or corrupt file no longer
+  crashes the whole bot at import time),
+* optional dependencies (openai, spotipy, netrc) and credentials are guarded so
+  the bot can still start when a secondary integration is offline, and
+* a shared ``CONJURER_API_KEY`` plus ``service_headers()`` helper enables
+  authenticated internal HTTP calls.
+
+All path constants intentionally remain plain ``str`` (with their original
+trailing separators) to stay byte-for-byte compatible with the existing string
+concatenation in the command modules.
+"""
+
 import json
-import netrc
+import logging
+import os
 from datetime import datetime
 from platform import uname
 from sys import platform
 from typing import List, Optional, TypedDict

-import openai
-import spotipy
-from spotipy.oauth2 import SpotifyClientCredentials
+try:
+    import netrc
+except ImportError:  # pragma: no cover - standard on CPython
+    netrc = None
+
+try:
+    import openai
+except ImportError:  # pragma: no cover - optional at runtime
+    openai = None
+
+try:
+    import spotipy
+    from spotipy.oauth2 import SpotifyClientCredentials
+except ImportError:  # pragma: no cover - optional component
+    spotipy = None
+    SpotifyClientCredentials = None
+
+logger = logging.getLogger("discord")

 Music_Config = TypedDict(
    "Music_Config",
@@ -30,16 +68,12 @@ MUSIC_FOLDER = ""
 MEMORY_FIVE_SIARA = ""
 MEMORY_FIVE_MUZYKA = ""
 SETTINGS_FILE = ""
-ENCODING = ""
+ENCODING = "utf-8"
 GRAPHICS_PATH = ""
 MUZYKA_MOJEGO_LUDU_HISTORIA = 1500
 MUZYKA_MOJEGO_LUDU_SLOWA_KLUCZOWE = 15
 MUZYKA_MOJEGO_LUDU_PLAJLISTA = 30

-FILE_SERVICE_ADDRESS = "http://192.168.1.15:5000"
-RADIO_HARBOR_ADDRESS = "http://192.168.1.15:54321"
-SKIP_TRACK = "/skip"
-
 GET_MP3 = "/mp3"
 SEND_MP3 = "/update_mp3"
 GET_PLAYLIST = "/get_music"
@@ -48,14 +82,13 @@ CREATE_PRIO_PLAYLIST = "/create_priority_playlist"

 REQUEST_MUSIC = "/request_radio_file"
 CLEAR_PRIO = "/clear_pr_pls"
-LIBRARIAN_SERVICE_ADDRESS = "http://192.168.1.192:5001"
 SEND_QUERY = "/query"
 TIME_BETWEEN_CALLS = 100000
 LAST_SPONTANEOUS_CALL = datetime.now()
-HOST_ADDRESS = "192.168.1.191"
-PORT_ADDRESS = 5000

-# *=========================================== Platform Specific Predefines
+# *=========================================== Platform Specific Defaults
+# These blocks only establish *default* values.  Every constant is overridable
+# through the matching environment variable further below.

 if platform in ("linux", "linux2"):
    SEPARATOR_FILE_PATH = "/"
@@ -101,47 +134,158 @@ elif platform == "win32":
    ENCODING = "utf-8"
    DIR_PATH_SADOX = "C:\\Users\\mtusz\\OneDrive\\Dokumenty\\Fansadox\\"
    SEPARATOR_FILE_PATH = "\\"
-with open(SETTINGS_FILE, "r", encoding=ENCODING) as f_settings_file:
-    DATA = json.load(f_settings_file)
-REMOTE_HOST_NAME = "openai"
-netrc_mod = netrc.netrc(NETRC_FILE)
-authTokens = netrc_mod.authenticators(REMOTE_HOST_NAME)
-openai.api_key = authTokens[2]
-OPENAICLIENT = openai.AsyncOpenAI(api_key=openai.api_key)
-REMOTE_HOST_NAME = "discord"
-authTokens = netrc_mod.authenticators(REMOTE_HOST_NAME)
-TOKEN = authTokens[2]

-REMOTE_HOST_NAME = "spotipy"
-authTokens = netrc_mod.authenticators(REMOTE_HOST_NAME)
-SPOTIFY_CTRL = spotipy.Spotify(
-    client_credentials_manager=SpotifyClientCredentials(
-        client_id=authTokens[0],
-        client_secret=authTokens[2],
-    )
+else:
+    # Fallback for development hosts (macOS, BSD, …) that match none of the
+    # production platforms.  Everything is rooted next to this file so the
+    # module can at least be imported and unit-tested off-deployment.
+    _BASE_DIR = os.path.dirname(os.path.abspath(__file__))
+    SEPARATOR_FILE_PATH = os.sep
+    LOGFILE = os.path.join(_BASE_DIR, "discord.log")
+    MEMORY_FIVE_SIARA = os.path.join(_BASE_DIR, "pamiec.json")
+    SYSTEM_GPT_SETTINGS = os.path.join(_BASE_DIR, "system_gpt_settings.json")
+    MEMORY_FIVE_MUZYKA = os.path.join(_BASE_DIR, "pamiec_muzyki.json")
+    MUSIC_FOLDER = os.path.join(_BASE_DIR, "music") + os.sep
+    SETTINGS_FILE = os.path.join(_BASE_DIR, "settings.json")
+    NETRC_FILE = os.path.join(os.path.expanduser("~"), ".netrc")
+    LOGSTORE = os.path.join(_BASE_DIR, "logs") + os.sep
+    ACCIDENT_LOG = os.path.join(_BASE_DIR, "accident_log.json")
+    GRAPHICS_PATH = os.path.join(_BASE_DIR, "Conjurer_graphics") + os.sep
+    DIR_PATH_SADOX = os.path.join(_BASE_DIR, "Fansadox") + os.sep
+
+
+# *=========================================== Environment overrides
+# Values stay as plain strings so existing ``PATH + filename`` concatenation in
+# the command modules keeps working unchanged.
+
+LOGFILE = os.getenv("CONJURER_LOG_FILE", LOGFILE)
+NETRC_FILE = os.getenv("CONJURER_NETRC_FILE", NETRC_FILE)
+SETTINGS_FILE = os.getenv("CONJURER_SETTINGS_FILE", SETTINGS_FILE)
+MEMORY_FIVE_SIARA = os.getenv("CONJURER_MEMORY_FILE", MEMORY_FIVE_SIARA)
+MEMORY_FIVE_MUZYKA = os.getenv("CONJURER_MUSIC_MEMORY_FILE", MEMORY_FIVE_MUZYKA)
+SYSTEM_GPT_SETTINGS = os.getenv("CONJURER_SYSTEM_GPT_SETTINGS", SYSTEM_GPT_SETTINGS)
+GRAPHICS_PATH = os.getenv("CONJURER_GRAPHICS_PATH", GRAPHICS_PATH)
+MUSIC_FOLDER = os.getenv("CONJURER_MUSIC_FOLDER", MUSIC_FOLDER)
+LOGSTORE = os.getenv("CONJURER_LOGSTORE", LOGSTORE)
+ACCIDENT_LOG = os.getenv("CONJURER_ACCIDENT_LOG", ACCIDENT_LOG)
+DIR_PATH_SADOX = os.getenv("CONJURER_SADOX_DIR", DIR_PATH_SADOX)
+ENCODING = os.getenv("CONJURER_ENCODING", ENCODING)
+SEPARATOR_FILE_PATH = os.getenv("CONJURER_PATH_SEPARATOR", SEPARATOR_FILE_PATH)
+
+FILE_SERVICE_ADDRESS = os.getenv("CONJURER_FILE_SERVICE", "http://192.168.1.15:5000")
+RADIO_HARBOR_ADDRESS = os.getenv("CONJURER_RADIO_HARBOR", "http://192.168.1.15:54321")
+SKIP_TRACK = os.getenv("CONJURER_SKIP_ENDPOINT", "/skip")
+LIBRARIAN_SERVICE_ADDRESS = os.getenv(
+    "CONJURER_LIBRARIAN_SERVICE", "http://192.168.1.192:5001"
 )
-REMOTE_HOST_NAME = "youtube"
-authTokens = netrc_mod.authenticators(REMOTE_HOST_NAME)
-YOUTUBE_AUTH = [authTokens[0],authTokens[2]]
+HOST_ADDRESS = os.getenv("CONJURER_DISCORD_HOST", "192.168.1.191")
+PORT_ADDRESS = int(os.getenv("CONJURER_DISCORD_PORT", "5000"))

-WORD_REACTIONS = DATA["word_reactions"]
-CYCLIC_WORDS = DATA["cyclic_words"]
+# Shared secret for authenticating internal service-to-service HTTP calls.
+API_SHARED_KEY = os.getenv("CONJURER_API_KEY", "")
+
+
+# *=========================================== Defensive state loading
+def _load_json(path: str, fallback):
+    """Load JSON from *path*, falling back gracefully on missing/corrupt files."""
+    try:
+        with open(path, "r", encoding=ENCODING) as handle:
+            return json.load(handle)
+    except FileNotFoundError:
+        logger.warning("Missing JSON file at %s - using fallback", path)
+        return fallback
+    except json.JSONDecodeError:
+        logger.warning("Corrupt JSON at %s - resetting to fallback", path)
+        return fallback
+
+
+DATA = _load_json(SETTINGS_FILE, {})
+WORD_REACTIONS = DATA.get("word_reactions", {})
+CYCLIC_WORDS = DATA.get("cyclic_words", {})
 for key in WORD_REACTIONS:
-    WORD_REACTIONS[key][2] = datetime.now()
-with open(MEMORY_FIVE_SIARA, "r+", encoding=ENCODING) as temp_memory_file:
-    # First we load existing data into a dict.
-    MESSAGE_TABLE = json.load(temp_memory_file)
+    if isinstance(WORD_REACTIONS[key], list) and len(WORD_REACTIONS[key]) >= 3:
+        WORD_REACTIONS[key][2] = datetime.now()

-with open(SYSTEM_GPT_SETTINGS, "r+", encoding=ENCODING) as temp_settings_file:
-    # First we load existing data into a dict.
-    GPT_SETTINGS = json.load(temp_settings_file)
-with open(MEMORY_FIVE_MUZYKA, "r+", encoding=ENCODING) as temp_music_memory_file:
-    # First we load existing data into a dict.
-    MESSAGE_TABLE_MUZYKA = json.load(temp_music_memory_file)
-SPECJALNE_ZIEMNIACZKI = GPT_SETTINGS[1]
+MESSAGE_TABLE = _load_json(MEMORY_FIVE_SIARA, [])
+GPT_SETTINGS = _load_json(SYSTEM_GPT_SETTINGS, {})
+MESSAGE_TABLE_MUZYKA = _load_json(MEMORY_FIVE_MUZYKA, [])
+
+SPECJALNE_ZIEMNIACZKI = GPT_SETTINGS[1] if isinstance(GPT_SETTINGS, list) else {}
 ASSISTANTS = {}


+# *=========================================== Credentials
+def _load_netrc_credentials(host: str):
+    """Return the netrc authenticators tuple for *host* or ``None``."""
+    if netrc is None:
+        return None
+    try:
+        parsed = netrc.netrc(NETRC_FILE)
+    except FileNotFoundError:
+        logger.warning("netrc file %s not found", NETRC_FILE)
+        return None
+    except netrc.NetrcParseError:
+        logger.warning("netrc file %s is invalid", NETRC_FILE)
+        return None
+    return parsed.authenticators(host)
+
+
+def _resolve_token(host: str, env_var: str) -> Optional[str]:
+    """Prefer an environment variable, then fall back to netrc."""
+    env_value = os.getenv(env_var)
+    if env_value:
+        return env_value
+    creds = _load_netrc_credentials(host)
+    if creds:
+        return creds[2]
+    logger.warning("Token for %s not configured", host)
+    return None
+
+
+OPENAI_API_KEY = _resolve_token("openai", "OPENAI_API_KEY")
+if openai and OPENAI_API_KEY:
+    openai.api_key = OPENAI_API_KEY
+    OPENAICLIENT = openai.AsyncOpenAI(api_key=OPENAI_API_KEY)
+else:
+    OPENAICLIENT = None
+
+TOKEN = _resolve_token("discord", "DISCORD_TOKEN")
+
+if spotipy:
+    _spotify_creds = _load_netrc_credentials("spotipy")
+    if _spotify_creds and SpotifyClientCredentials:
+        SPOTIFY_CTRL = spotipy.Spotify(
+            client_credentials_manager=SpotifyClientCredentials(
+                client_id=_spotify_creds[0],
+                client_secret=_spotify_creds[2],
+            )
+        )
+    else:
+        SPOTIFY_CTRL = None
+else:
+    SPOTIFY_CTRL = None
+
+_youtube_creds = _load_netrc_credentials("youtube")
+if _youtube_creds:
+    YOUTUBE_AUTH = [_youtube_creds[0], _youtube_creds[2]]
+else:
+    YOUTUBE_AUTH = [
+        os.getenv("YOUTUBE_USERNAME", ""),
+        os.getenv("YOUTUBE_PASSWORD", ""),
+    ]
+
+
+def service_headers():
+    """Shared header dict for internal service-to-service HTTP calls.
+
+    Returns an empty dict when no key is configured, keeping calls backward
+    compatible with deployments that do not (yet) enforce authentication.
+    """
+    if API_SHARED_KEY:
+        return {"X-Conjurer-Api-Key": API_SHARED_KEY}
+    return {}
+
+
 LATEX_TEX_ENGINE = "tectonic"
 LATEX_MAX_COMPILE_SECONDS = 45
 LATEX_MAX_ATTACH_MB = 8