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>

routes/admin_wipe_routes.py

@@ -31,7 +31,7 @@ from core.database import (
     CalendarEvent,
     CalendarCal,
 )
-from src.constants import DATA_DIR
+from src.constants import DATA_DIR, SKILLS_DIR, SKILLS_FILE, GALLERY_DIR, GALLERY_UPLOADS_DIR
 
 logger = logging.getLogger(__name__)
 
@@ -107,7 +107,7 @@ def setup_admin_wipe_routes(session_manager):
                 # Skills live as SKILL.md files under data/skills/. Drop
                 # the entire directory; the SkillsManager re-creates the
                 # tree on next write.
-                skills_dir = os.path.join(DATA_DIR, "skills")
+                skills_dir = SKILLS_DIR
                 count = 0
                 if os.path.isdir(skills_dir):
                     # Count SKILL.md files for the response — quick walk.
@@ -115,7 +115,7 @@ def setup_admin_wipe_routes(session_manager):
                         count += sum(1 for f in files if f == "SKILL.md")
                     _rmtree_quiet(skills_dir)
                 # Legacy fallback file
-                legacy = os.path.join(DATA_DIR, "skills.json")
+                legacy = SKILLS_FILE
                 if os.path.exists(legacy):
                     try:
                         os.remove(legacy)
@@ -151,8 +151,8 @@ def setup_admin_wipe_routes(session_manager):
                 db.query(GalleryAlbum).delete()
                 db.commit()
                 # Also drop the upload dir so disk doesn't keep orphans.
-                _rmtree_quiet(os.path.join(DATA_DIR, "gallery"))
-                _rmtree_quiet(os.path.join(DATA_DIR, "gallery_uploads"))
+                _rmtree_quiet(GALLERY_DIR)
+                _rmtree_quiet(GALLERY_UPLOADS_DIR)
                 return {"status": "deleted", "kind": kind, "count": count}
 
             if kind == "calendar":

routes/codex_routes.py

@@ -17,7 +17,7 @@ from fastapi.responses import StreamingResponse
 
 from src.auth_helpers import require_authenticated_request, require_user
 from src.tool_implementations import do_manage_notes
-from core.constants import DATA_DIR
+from src.constants import COOKBOOK_STATE_FILE
 
 
 COOKBOOK_READ_SCOPES = {"cookbook:read", "cookbook:launch"}
@@ -425,8 +425,8 @@ def setup_codex_routes(
 
     def _read_cookbook_state() -> dict:
         from pathlib import Path as _Path
-        import os as _os, json as _json
-        p = _Path(DATA_DIR) / "cookbook_state.json"
+        import json as _json
+        p = _Path(COOKBOOK_STATE_FILE)
         if not p.exists():
             return {}
         try:
@@ -734,7 +734,7 @@ def setup_codex_routes(
         import time as _t, json as _json
         from core.atomic_io import atomic_write_json
         from pathlib import Path as _Path
-        cookbook_state_path = _Path(DATA_DIR) / "cookbook_state.json"
+        cookbook_state_path = _Path(COOKBOOK_STATE_FILE)
         try:
             state = _json.loads(cookbook_state_path.read_text(encoding="utf-8"))
         except Exception:

routes/contacts_routes.py

@@ -25,9 +25,10 @@ from src.url_safety import check_outbound_url
 
 logger = logging.getLogger(__name__)
 
-DATA_DIR = Path(__file__).resolve().parent.parent / "data"
-SETTINGS_FILE = DATA_DIR / "settings.json"
-LOCAL_CONTACTS_FILE = DATA_DIR / "contacts.json"
+from src.constants import DATA_DIR as _DATA_DIR, SETTINGS_FILE as _SETTINGS_FILE, CONTACTS_FILE as _CONTACTS_FILE
+DATA_DIR = Path(_DATA_DIR)
+SETTINGS_FILE = Path(_SETTINGS_FILE)
+LOCAL_CONTACTS_FILE = Path(_CONTACTS_FILE)
 
 
 def _load_settings():

routes/cookbook_routes.py

@@ -15,6 +15,7 @@ from pathlib import Path
 from fastapi import APIRouter, HTTPException, Request, Depends
 
 from src.auth_helpers import require_user
+from src.constants import COOKBOOK_STATE_FILE
 from pydantic import BaseModel
 
 from core.middleware import require_admin
@@ -33,7 +34,7 @@ from core.platform_compat import (
     get_wsl_windows_user_profile,
 )
 from routes.shell_routes import TMUX_LOG_DIR
-from core.constants import DATA_DIR
+from src.constants import COOKBOOK_STATE_FILE
 
 logger = logging.getLogger(__name__)
 
@@ -61,7 +62,7 @@ _HF_TOKEN_STATUS_SNIPPET = (
 
 def setup_cookbook_routes() -> APIRouter:
     router = APIRouter(tags=["cookbook"])
-    _cookbook_state_path = Path(DATA_DIR) / "cookbook_state.json"
+    _cookbook_state_path = Path(COOKBOOK_STATE_FILE)
 
     def _mask_secret(value: str) -> str:
         if not value:

routes/document_routes.py

@@ -11,6 +11,7 @@ from sqlalchemy import case, func, or_
 from core.database import SessionLocal, Document, DocumentVersion
 from core.database import Session as DbSession
 from src.auth_helpers import get_current_user
+from src.constants import MAIL_ATTACHMENTS_DIR
 
 logger = logging.getLogger(__name__)
 
@@ -1542,10 +1543,7 @@ def setup_document_routes(session_manager, upload_handler=None) -> APIRouter:
         # don't import from a routes file (cycle-prone). Same env override
         # as email_routes (ODYSSEUS_MAIL_ATTACHMENTS_DIR).
         from pathlib import Path as _Path
-        import os as _os
-        _DATA_DIR = _Path(__file__).resolve().parent.parent / "data"
-        _BASE = _os.environ.get("ODYSSEUS_MAIL_ATTACHMENTS_DIR", str(_DATA_DIR / "mail-attachments"))
-        _COMPOSE_DIR = _Path(_BASE) / "_compose"
+        _COMPOSE_DIR = _Path(MAIL_ATTACHMENTS_DIR) / "_compose"
         _COMPOSE_DIR.mkdir(parents=True, exist_ok=True)
 
         user = get_current_user(request)

routes/email_helpers.py

@@ -254,16 +254,17 @@ def _cleanup_compose_uploads(tokens) -> None:
             pass
 
 
-DATA_DIR = Path(__file__).resolve().parent.parent / "data"
-SETTINGS_FILE = DATA_DIR / "settings.json"
+from src.constants import DATA_DIR as _DATA_DIR, MAIL_ATTACHMENTS_DIR, SETTINGS_FILE as _SETTINGS_FILE, SCHEDULED_EMAILS_DB
+DATA_DIR = Path(_DATA_DIR)
+SETTINGS_FILE = Path(_SETTINGS_FILE)
 # Override at deploy time via ODYSSEUS_MAIL_ATTACHMENTS_DIR. Defaults to a
 # subdir of the install's data/ tree so the app works out-of-the-box without
 # a hardcoded /home/<user>/ path.
-ATTACHMENTS_DIR = Path(os.environ.get("ODYSSEUS_MAIL_ATTACHMENTS_DIR", str(DATA_DIR / "mail-attachments")))
+ATTACHMENTS_DIR = Path(MAIL_ATTACHMENTS_DIR)
 ATTACHMENTS_DIR.mkdir(parents=True, exist_ok=True)
 COMPOSE_UPLOADS_DIR = ATTACHMENTS_DIR / "_compose"
 COMPOSE_UPLOADS_DIR.mkdir(parents=True, exist_ok=True)
-SCHEDULED_DB = DATA_DIR / "scheduled_emails.db"
+SCHEDULED_DB = Path(SCHEDULED_EMAILS_DB)
 
 
 OWNER_SCOPED_EMAIL_CACHE_TABLES = {

routes/email_routes.py

@@ -32,6 +32,7 @@ from email.mime.multipart import MIMEMultipart
 
 from fastapi import APIRouter, Query, UploadFile, File, BackgroundTasks, HTTPException, Depends, Request
 from fastapi.responses import FileResponse
+from src.constants import DATA_DIR
 
 from src.llm_core import llm_call_async
 from src.upload_limits import read_upload_limited
@@ -2904,7 +2905,7 @@ def setup_email_routes():
         from pathlib import Path as _P
         import json as _json
         _slug = "".join(c if (c.isalnum() or c in "-_.@") else "_" for c in (owner or "default"))
-        path = _P(f"data/email_urgency_state_{_slug}.json")
+        path = _P(DATA_DIR) / f"email_urgency_state_{_slug}.json"
         if not path.exists():
             return {"total_unread": 0, "total_urgent": 0, "max_score": 0, "per_uid": {}}
         try:

routes/embedding_routes.py

@@ -7,12 +7,12 @@ import logging
 import asyncio
 from pathlib import Path
 from fastapi import APIRouter, HTTPException, Form, Depends
-from core.constants import BASE_DIR
+from core.constants import EMBEDDING_ENDPOINT_FILE, FASTEMBED_CACHE_DIR
 from core.middleware import require_admin
 
 logger = logging.getLogger(__name__)
 
-_ENDPOINT_FILE = os.path.join(BASE_DIR, "data", "embedding_endpoint.json")
+_ENDPOINT_FILE = EMBEDDING_ENDPOINT_FILE
 
 # Track in-progress downloads
 _downloading: dict = {}
@@ -35,13 +35,7 @@ def _cache_dir() -> str:
     default lived in /tmp, which many systems wipe on reboot — forcing a
     full re-download of the embedding model after every restart.
     """
-    env = os.environ.get("FASTEMBED_CACHE_PATH")
-    if env:
-        return env
-    return os.path.join(
-        os.path.dirname(os.path.dirname(os.path.abspath(__file__))),
-        "data", "fastembed_cache",
-    )
+    return FASTEMBED_CACHE_DIR
 
 
 def _model_cache_name(hf_source: str) -> str:

routes/emoji_routes.py

@@ -18,9 +18,11 @@ import httpx
 from fastapi import APIRouter
 from fastapi.responses import Response
 
+from src.constants import EMOJI_CACHE_DIR
+
 logger = logging.getLogger(__name__)
 
-_CACHE_DIR = Path(__file__).resolve().parent.parent / "data" / "emoji_cache"
+_CACHE_DIR = Path(EMOJI_CACHE_DIR)
 # OpenMoji "black" set = monochrome line-art SVGs. Filenames are the codepoints
 # in UPPERCASE (FE0F dropped, same as we compute), '-' joined.
 _OPENMOJI_BASE = "https://cdn.jsdelivr.net/npm/openmoji@15.0.0/black/svg"

routes/gallery_routes.py

@@ -14,6 +14,7 @@ from core.database import SessionLocal, GalleryImage, GalleryAlbum, ModelEndpoin
 from core.database import Session as DbSession
 from src.auth_helpers import get_current_user, require_privilege
 from src.upload_limits import read_upload_limited
+from src.constants import GENERATED_IMAGES_DIR
 
 from routes.gallery_helpers import (
     GalleryPatch, _extract_exif, _image_to_dict, _owner_filter, _human_size,
@@ -33,7 +34,7 @@ def _sanitize_gallery_filename(filename: str) -> str:
     return safe_name
 
 
-GALLERY_IMAGE_DIR = Path("data/generated_images")
+GALLERY_IMAGE_DIR = Path(GENERATED_IMAGES_DIR)
 
 
 def _gallery_image_path(filename: str) -> Path:
@@ -133,7 +134,7 @@ def setup_gallery_routes() -> APIRouter:
                 return {"ok": False, "duplicate": True, "filename": existing.filename,
                         "id": existing.id, "message": "Duplicate photo skipped"}
 
-            img_dir = Path("data/generated_images")
+            img_dir = Path(GENERATED_IMAGES_DIR)
             img_dir.mkdir(parents=True, exist_ok=True)
 
             ext = file.filename.rsplit(".", 1)[-1].lower() if "." in file.filename else "png"
@@ -199,7 +200,7 @@ def setup_gallery_routes() -> APIRouter:
                 raise HTTPException(400, "No image provided")
 
             content = await read_upload_limited(file, GALLERY_UPLOAD_MAX_BYTES, "Gallery replacement")
-            img_dir = Path("data/generated_images")
+            img_dir = Path(GENERATED_IMAGES_DIR)
             img_dir.mkdir(parents=True, exist_ok=True)
             img_path = img_dir / _sanitize_gallery_filename(img.filename)
             img_path.write_bytes(content)

routes/mcp_routes.py

@@ -13,7 +13,7 @@ import httpx
 
 from core.database import McpServer, SessionLocal
 from core.middleware import require_admin
-from src.constants import DATA_DIR
+from src.constants import DATA_DIR, MCP_OAUTH_DIR
 from src.mcp_manager import McpManager
 
 logger = logging.getLogger(__name__)
@@ -23,7 +23,7 @@ router = APIRouter(prefix="/api/mcp", tags=["mcp"])
 
 def _mcp_oauth_base_dir() -> Path:
     """Directory that may contain OAuth files managed by Odysseus."""
-    return (Path(DATA_DIR) / "mcp_oauth").resolve(strict=False)
+    return Path(MCP_OAUTH_DIR).resolve(strict=False)
 
 
 def _resolve_mcp_oauth_path(raw_path, field_name: str) -> str:

routes/note_routes.py

@@ -11,6 +11,7 @@ from pydantic import BaseModel
 
 from core.database import SessionLocal, Note
 from src.auth_helpers import get_current_user
+from src.constants import DATA_DIR
 from sqlalchemy.orm.attributes import flag_modified
 
 logger = logging.getLogger(__name__)
@@ -170,7 +171,7 @@ async def dispatch_reminder(
             from datetime import datetime as _dt, timezone as _tz, timedelta as _td
             from pathlib import Path as _P
             _slug = "".join(c if (c.isalnum() or c in "-_.@") else "_" for c in (owner or "default"))
-            cache_path = _P(f"data/note_pings_{_slug}.json")
+            cache_path = _P(DATA_DIR) / f"note_pings_{_slug}.json"
             if cache_path.exists():
                 cache = _json.loads(cache_path.read_text(encoding="utf-8"))
             last = cache.get(cache_key)
@@ -523,7 +524,7 @@ async def dispatch_reminder(
             _STATE = cache_path
             if _STATE is None:
                 _slug = "".join(c if (c.isalnum() or c in "-_.@") else "_" for c in (owner or "default"))
-                _STATE = _P(f"data/note_pings_{_slug}.json")
+                _STATE = _P(DATA_DIR) / f"note_pings_{_slug}.json"
             _STATE.parent.mkdir(parents=True, exist_ok=True)
             try:
                 _cache = cache or (_json.loads(_STATE.read_text(encoding="utf-8")) if _STATE.exists() else {})

routes/personal_routes.py

@@ -6,13 +6,13 @@ import uuid
 from typing import List, Tuple
 from fastapi import APIRouter, HTTPException, Query, Request, UploadFile, File, Depends
 from src.request_models import DirectoryRequest
-from core.constants import BASE_DIR, PERSONAL_DIR
+from core.constants import BASE_DIR, PERSONAL_DIR, PERSONAL_UPLOADS_DIR
 from src.rag_singleton import get_rag_manager
 from src.auth_helpers import require_privilege, require_user
 from core.middleware import require_admin
 from src.upload_handler import secure_filename
 
-UPLOADS_DIR = os.path.join(BASE_DIR, "data", "personal_uploads")
+UPLOADS_DIR = PERSONAL_UPLOADS_DIR
 MAX_PERSONAL_UPLOAD_BYTES = int(
     os.getenv("ODYSSEUS_PERSONAL_UPLOAD_MAX_BYTES", str(25 * 1024 * 1024))
 )

routes/prefs_routes.py

@@ -4,8 +4,9 @@ import os
 from typing import Optional
 from fastapi import APIRouter, Request
 from src.auth_helpers import get_current_user
+from src.constants import USER_PREFS_FILE
 
-PREFS_FILE = os.path.join("data", "user_prefs.json")
+PREFS_FILE = USER_PREFS_FILE
 
 
 def _load():

routes/research_routes.py

@@ -14,6 +14,7 @@ from fastapi.responses import HTMLResponse, StreamingResponse
 from pydantic import BaseModel, Field
 from src.endpoint_resolver import resolve_endpoint
 from src.auth_helpers import _auth_disabled, get_current_user
+from src.constants import DEEP_RESEARCH_DIR
 
 _SESSION_ID_RE = re.compile(r"^[a-zA-Z0-9-]{1,128}$")
 
@@ -100,7 +101,7 @@ def setup_research_routes(research_handler, session_manager=None) -> APIRouter:
         if entry is not None:
             return entry.get("owner", "") == user
         # Task no longer in memory — check the persisted JSON.
-        path = Path("data/deep_research") / f"{session_id}.json"
+        path = Path(DEEP_RESEARCH_DIR) / f"{session_id}.json"
         if not path.exists():
             return False
         try:
@@ -164,7 +165,7 @@ def setup_research_routes(research_handler, session_manager=None) -> APIRouter:
     def _assert_owns_research(session_id: str, user: str) -> None:
         """404-not-403 ownership gate for a research session's on-disk JSON.
         Use BEFORE returning any data or mutating the file."""
-        path = Path("data/deep_research") / f"{session_id}.json"
+        path = Path(DEEP_RESEARCH_DIR) / f"{session_id}.json"
         if not path.exists():
             raise HTTPException(404, "Research not found")
         try:
@@ -227,7 +228,7 @@ def setup_research_routes(research_handler, session_manager=None) -> APIRouter:
     ):
         user = _require_user(request)
         """List all completed research for the Library panel."""
-        data_dir = Path("data/deep_research")
+        data_dir = Path(DEEP_RESEARCH_DIR)
         items = []
         for p in data_dir.glob("*.json"):
             try:
@@ -277,7 +278,7 @@ def setup_research_routes(research_handler, session_manager=None) -> APIRouter:
         summary, stats — used by the Library preview panel."""
         user = _require_user(request)
         _validate_session_id(session_id)
-        path = Path("data/deep_research") / f"{session_id}.json"
+        path = Path(DEEP_RESEARCH_DIR) / f"{session_id}.json"
         if not path.exists():
             raise HTTPException(404, "Research not found")
         try:
@@ -294,7 +295,7 @@ def setup_research_routes(research_handler, session_manager=None) -> APIRouter:
         """Soft-archive / restore a research report (sets `archived` in its JSON)."""
         user = _require_user(request)
         _validate_session_id(session_id)
-        path = Path("data/deep_research") / f"{session_id}.json"
+        path = Path(DEEP_RESEARCH_DIR) / f"{session_id}.json"
         if not path.exists():
             raise HTTPException(404, "Research not found")
         try:
@@ -314,7 +315,7 @@ def setup_research_routes(research_handler, session_manager=None) -> APIRouter:
         """Delete a research result from disk."""
         user = _require_user(request)
         _validate_session_id(session_id)
-        data_dir = Path("data/deep_research")
+        data_dir = Path(DEEP_RESEARCH_DIR)
         json_path = data_dir / f"{session_id}.json"
         deleted = False
         if json_path.exists():
@@ -496,7 +497,7 @@ def setup_research_routes(research_handler, session_manager=None) -> APIRouter:
             raise HTTPException(404, "No research found for this session")
         result = research_handler.get_result(session_id)
         if result is None:
-            p = Path("data/deep_research") / f"{session_id}.json"
+            p = Path(DEEP_RESEARCH_DIR) / f"{session_id}.json"
             if p.exists():
                 d = json.loads(p.read_text(encoding="utf-8"))
                 return {
@@ -536,7 +537,7 @@ def setup_research_routes(research_handler, session_manager=None) -> APIRouter:
         sources = research_handler.get_sources(session_id) or []
         query = ""
 
-        path = Path("data/deep_research") / f"{session_id}.json"
+        path = Path(DEEP_RESEARCH_DIR) / f"{session_id}.json"
         if path.exists():
             try:
                 disk = json.loads(path.read_text(encoding="utf-8"))

routes/task_routes.py

@@ -13,6 +13,7 @@ from pydantic import BaseModel
 from core.database import SessionLocal, ScheduledTask, TaskRun
 from core.constants import internal_api_base
 from src.auth_helpers import get_current_user
+from src.constants import DATA_DIR, EMAIL_URGENCY_CACHE_DIR
 from src.task_scheduler import compute_next_run, HOUSEKEEPING_DEFAULTS
 from routes.prefs_routes import _load_for_user, _save_for_user
 
@@ -621,7 +622,7 @@ def setup_task_routes(task_scheduler) -> APIRouter:
 
         removed_files = 0
         if action == "check_email_urgency":
-            cache_dir = Path("data/email_urgency_cache")
+            cache_dir = Path(EMAIL_URGENCY_CACHE_DIR)
             if cache_dir.exists():
                 for child in cache_dir.glob("*.json"):
                     try:
@@ -630,7 +631,7 @@ def setup_task_routes(task_scheduler) -> APIRouter:
                     except Exception:
                         pass
             owner_slug = "".join(c if (c.isalnum() or c in "-_.@") else "_" for c in (user or "default"))
-            for state_path in [Path(f"data/email_urgency_state_{owner_slug}.json")]:
+            for state_path in [Path(DATA_DIR) / f"email_urgency_state_{owner_slug}.json"]:
                 try:
                     if state_path.exists():
                         state_path.unlink()

routes/vault_routes.py

@@ -17,10 +17,11 @@ from pydantic import BaseModel
 
 from core.middleware import require_admin
 from core.platform_compat import IS_WINDOWS, safe_chmod, which_tool
+from src.constants import VAULT_FILE as _VAULT_FILE
 
 logger = logging.getLogger(__name__)
 
-VAULT_FILE = Path("data/vault.json")
+VAULT_FILE = Path(_VAULT_FILE)
 
 
 def _find_bw() -> str: