refactor(constants): single source of truth for data dir (#3368)

* refactor(constants): single source of truth for data dir + merge core/src constants

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* docs(contributing): use named src.constants for data paths, drop core/constants references

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

core/auth.py

@@ -37,9 +37,8 @@ DEFAULT_PRIVILEGES = {
 ADMIN_PRIVILEGES = {k: (True if isinstance(v, bool) else (0 if isinstance(v, int) else [])) for k, v in DEFAULT_PRIVILEGES.items()}
 ADMIN_PRIVILEGES["allowed_models_restricted"] = False
 
-DEFAULT_AUTH_PATH = os.path.join(
-    Path(__file__).parent.parent, "data", "auth.json"
-)
+from src.constants import AUTH_FILE
+DEFAULT_AUTH_PATH = AUTH_FILE
 TOKEN_TTL = 60 * 60 * 24 * 7  # 7 days
 
 # Usernames the auth + middleware layer reserve as internal "synthetic owner"

core/constants.py

@@ -1,59 +1,12 @@
-# src/constants.py
-"""Application-wide constants and configuration values."""
-import os
+# core/constants.py
+"""Backward-compatible shim — the single source of truth is src/constants.py.
 
-APP_VERSION = "0.9.1"
-
-# Base paths
-BASE_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__))) + "/"
-STATIC_DIR = os.path.join(BASE_DIR, "static")
-DATA_DIR = os.path.join(BASE_DIR, "data")
-
-# Data file paths
-SESSIONS_FILE = os.path.join(DATA_DIR, "sessions.json")
-MEMORY_FILE = os.path.join(DATA_DIR, "memory.json")
-MEMORY_DOC = os.path.join(DATA_DIR, "memory_doc.md")
-PERSONAL_DIR = os.path.join(DATA_DIR, "personal_docs")
-RUNBOOK_DIR = os.path.join(PERSONAL_DIR, "runbook")
-UPLOAD_DIR = os.path.join(DATA_DIR, "uploads")
-FEATURES_FILE = os.path.join(DATA_DIR, "features.json")
-SETTINGS_FILE = os.path.join(DATA_DIR, "settings.json")
-
-# API Configuration
-MAX_CONTEXT_MESSAGES = 90
-REQUEST_TIMEOUT = 20
-OPENAI_COMPAT_PATH = "/v1/chat/completions"
-
-# Environment variables with defaults
-DEFAULT_HOST = os.getenv("LLM_HOST", "localhost")
-LLM_HOSTS = [h.strip() for h in os.getenv("LLM_HOSTS", "").split(",") if h.strip()]
-OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
-SEARXNG_INSTANCE = os.getenv('SEARXNG_INSTANCE', 'http://localhost:8080')
-
-
-# Cleanup configuration
-CLEANUP_ENABLED = os.getenv("CLEANUP_ENABLED", "True").lower() == "true"
-CLEANUP_INTERVAL_HOURS = int(os.getenv("CLEANUP_INTERVAL_HOURS", "24"))
-
-# Default parameters
-DEFAULT_TEMPERATURE = 1.0
-DEFAULT_MAX_TOKENS = 0
-
-
-def internal_api_base() -> str:
-    """Base URL for in-process loopback calls to Odysseus's own API.
-
-    Agent tools and background jobs reach admin-gated routes by calling the
-    running server over HTTP. Resolution order:
-      1. ODYSSEUS_INTERNAL_BASE  - explicit override (e.g. behind a TLS proxy).
-      2. APP_PORT                - http://127.0.0.1:$APP_PORT (docker-compose).
-      3. Fallback http://127.0.0.1:7000 - legacy default.
-
-    127.0.0.1 (not "localhost") avoids IPv6/DNS ambiguity for a strictly-local
-    call. Without this, loopback tools fail with "All connection attempts
-    failed" whenever the server is not on port 7000.
-    """
-    override = os.environ.get("ODYSSEUS_INTERNAL_BASE")
-    if override:
-        return override.rstrip("/")
-    return f"http://127.0.0.1:{os.environ.get('APP_PORT', '7000')}"
+Historically there were two copies of this module (this one lagged behind at
+APP_VERSION 0.9.1 and was missing the consolidated tool-output constants). To
+kill the drift, this now simply re-exports everything from src.constants so
+there is exactly one place that defines paths and reads ODYSSEUS_DATA_DIR.
+internal_api_base() also lives in src.constants now and is re-exported here so
+existing `from core.constants import internal_api_base` callers keep working.
+"""
+from src.constants import *  # noqa: F401,F403
+from src.constants import internal_api_base  # noqa: F401  (explicit: functions aren't covered by some linters' * checks)

core/database.py

@@ -29,8 +29,9 @@ class TimestampMixin:
     def updated_at(cls):
         return Column(DateTime, default=utcnow_naive, onupdate=utcnow_naive, nullable=False)
 
-# Get database URL from environment, default to SQLite
-DATABASE_URL = os.getenv("DATABASE_URL", "sqlite:///./data/app.db")
+# Get database URL from environment, default to SQLite in DATA_DIR
+from src.constants import DATA_DIR, AUTH_FILE, MEMORY_FILE, USER_PREFS_FILE, SETTINGS_FILE
+DATABASE_URL = os.getenv("DATABASE_URL", f"sqlite:///{DATA_DIR}/app.db")
 
 # Create engine
 engine = create_engine(
@@ -1065,7 +1066,7 @@ def _migrate_assign_legacy_owner():
     # fell through to "first user" every time.
     auth_path = os.path.join(os.path.dirname(DATABASE_URL.replace("sqlite:///", "")), "auth.json")
     if not os.path.isabs(auth_path):
-        auth_path = os.path.join("data", "auth.json")
+        auth_path = AUTH_FILE
     admin_user = None
     try:
         with open(auth_path, "r", encoding="utf-8") as f:
@@ -1118,7 +1119,7 @@ def _migrate_assign_legacy_owner():
         logger.warning(f"Legacy owner migration failed: {e}")
 
     # Also migrate memory.json
-    mem_path = os.path.join("data", "memory.json")
+    mem_path = MEMORY_FILE
     try:
         if os.path.exists(mem_path):
             with open(mem_path, "r", encoding="utf-8") as f:
@@ -1136,7 +1137,7 @@ def _migrate_assign_legacy_owner():
         logger.warning(f"memory.json legacy migration failed: {e}")
 
     # Also migrate user_prefs.json to per-user format
-    prefs_path = os.path.join("data", "user_prefs.json")
+    prefs_path = USER_PREFS_FILE
     try:
         if os.path.exists(prefs_path):
             with open(prefs_path, "r", encoding="utf-8") as f:
@@ -1530,7 +1531,7 @@ def _migrate_seed_email_account():
         import json as _json
         import uuid as _uuid
         from pathlib import Path
-        settings_file = Path("data/settings.json")
+        settings_file = Path(SETTINGS_FILE)
         if not settings_file.exists():
             return
         try: