Merge origin/dev into main

src/constants.py

@@ -2,12 +2,14 @@
 """Application-wide constants and configuration values."""
 import os
 
+from src.runtime_paths import get_app_root, get_default_data_dir
+
 APP_VERSION = "1.0.1"
 
 # Base paths
-BASE_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__))) + "/"
+BASE_DIR = os.path.join(get_app_root(), "")
 STATIC_DIR = os.path.join(BASE_DIR, "static")
-DATA_DIR = os.getenv("ODYSSEUS_DATA_DIR", os.path.join(BASE_DIR, "data"))
+DATA_DIR = os.getenv("ODYSSEUS_DATA_DIR", get_default_data_dir())
 
 # Data file paths
 # Single source of truth: every persisted file/dir lives under DATA_DIR, which
@@ -55,7 +57,13 @@ MEMORY_VECTORS_DIR = os.path.join(DATA_DIR, "memory_vectors")
 
 # Paths with an intentional dedicated env override, defaulting under DATA_DIR.
 MAIL_ATTACHMENTS_DIR = os.getenv("ODYSSEUS_MAIL_ATTACHMENTS_DIR", os.path.join(DATA_DIR, "mail-attachments"))
-FASTEMBED_CACHE_DIR = os.getenv("FASTEMBED_CACHE_PATH", os.path.join(DATA_DIR, "fastembed_cache"))
+# `or` (not os.getenv's default arg) so a PRESENT-but-EMPTY value falls back to
+# the default. docker-compose.yml injects `FASTEMBED_CACHE_PATH=${FASTEMBED_CACHE_PATH:-}`,
+# which sets the var to "" when the host hasn't defined it. os.getenv(name, default)
+# only returns the default when the var is ABSENT, so the empty string would win →
+# os.makedirs("") raises [Errno 2] No such file or directory: '' → FastEmbed fails to
+# init and all vector features (RAG, semantic memory, tool index) silently degrade.
+FASTEMBED_CACHE_DIR = os.getenv("FASTEMBED_CACHE_PATH") or os.path.join(DATA_DIR, "fastembed_cache")
 
 # Agent tool output limits (single source of truth — imported by tool_execution.py,
 # tool_implementations.py, agent_tools.py, and any other module that needs them)
@@ -63,11 +71,26 @@ MAX_OUTPUT_CHARS = 10_000       # cap for bash/python/web_search/web_fetch outpu
 MAX_READ_CHARS = 20_000         # cap for read_file / document preview
 MAX_DIFF_LINES = 400            # cap for edit_file unified-diff display
 
+# web_fetch response-size policy (#3812). MAX_OUTPUT_CHARS above only trims
+# what the agent SEES; these caps bound what the server downloads, parses,
+# and writes to the content cache. The soft cap is the default download
+# budget; the agent can raise it per call (full/max_bytes) but never past
+# the hard cap, so a model can't decide to pull a multi-GB file.
+WEB_FETCH_SOFT_MAX_BYTES = 2_000_000    # default download budget (2 MB)
+WEB_FETCH_HARD_MAX_BYTES = 20_000_000   # absolute ceiling, even with override (20 MB)
+
 # API Configuration
 MAX_CONTEXT_MESSAGES = 90
 REQUEST_TIMEOUT = 20
 OPENAI_COMPAT_PATH = "/v1/chat/completions"
 
+# Outbound UA for web_fetch / web_search scraping; common desktop UA so pages serve normal HTML.
+WEB_FETCH_USER_AGENT = os.environ.get(
+    "WEB_FETCH_USER_AGENT",
+    "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 "
+    "(KHTML, like Gecko) Chrome/148.0.0.0 Safari/537.36",
+)
+
 # 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()]
@@ -79,6 +102,9 @@ SEARXNG_INSTANCE = os.getenv("SEARXNG_INSTANCE", "http://localhost:8080")
 CLEANUP_ENABLED = os.getenv("CLEANUP_ENABLED", "True").lower() == "true"
 CLEANUP_INTERVAL_HOURS = int(os.getenv("CLEANUP_INTERVAL_HOURS", "24"))
 
+# Auth policy
+PASSWORD_MIN_LENGTH = 8
+
 # Default parameters
 DEFAULT_TEMPERATURE = 1.0
 DEFAULT_MAX_TOKENS = 0