Merge verified Odysseus fixes

routes/chat_helpers.py

@@ -5,6 +5,7 @@ import json
 import logging
 import os
 import re
+import time
 from dataclasses import dataclass, field
 from typing import Any, Optional
 
@@ -56,6 +57,9 @@ def _is_casual_low_signal(text: str) -> bool:
 # the background work (extraction, auto-naming) silently never runs.
 # Mirrors WebhookManager._spawn_tracked from src/webhook_manager.py.
 _BG_TASKS: set[asyncio.Task] = set()
+_INCOGNITO_CONTEXTS: dict[str, dict[str, Any]] = {}
+_INCOGNITO_CONTEXT_TTL_SECONDS = 6 * 60 * 60
+_INCOGNITO_CONTEXT_MAX_MESSAGES = 80
 
 
 def _spawn_bg(coro) -> asyncio.Task:
@@ -66,6 +70,40 @@ def _spawn_bg(coro) -> asyncio.Task:
     return task
 
 
+def _prune_incognito_contexts(now: float | None = None):
+    now = now or time.time()
+    stale = [
+        sid for sid, bundle in _INCOGNITO_CONTEXTS.items()
+        if now - float(bundle.get("updated_at") or 0) > _INCOGNITO_CONTEXT_TTL_SECONDS
+    ]
+    for sid in stale:
+        _INCOGNITO_CONTEXTS.pop(sid, None)
+
+
+def _incognito_messages(session_id: str) -> list[dict[str, Any]]:
+    _prune_incognito_contexts()
+    bundle = _INCOGNITO_CONTEXTS.get(str(session_id or ""))
+    if not bundle:
+        return []
+    return [dict(m) for m in bundle.get("messages", []) if isinstance(m, dict)]
+
+
+def _append_incognito_message(session_id: str, role: str, content: Any, metadata: dict | None = None):
+    sid = str(session_id or "").strip()
+    if not sid:
+        return
+    _prune_incognito_contexts()
+    bundle = _INCOGNITO_CONTEXTS.setdefault(sid, {"messages": [], "updated_at": time.time()})
+    msg: dict[str, Any] = {"role": role, "content": content}
+    if metadata:
+        msg["metadata"] = dict(metadata)
+    messages = bundle.setdefault("messages", [])
+    messages.append(msg)
+    if len(messages) > _INCOGNITO_CONTEXT_MAX_MESSAGES:
+        del messages[:-_INCOGNITO_CONTEXT_MAX_MESSAGES]
+    bundle["updated_at"] = time.time()
+
+
 # ── Data containers ────────────────────────────────────────────────────── #
 
 @dataclass
@@ -434,12 +472,13 @@ def build_uploaded_file_manifest(att_ids: list, upload_handler, owner: Optional[
 
 def add_user_message(sess, chat_handler, preprocessed: PreprocessedMessage, incognito: bool = False):
     """Add user message to session history and update session name.
-    In incognito mode, still add to in-memory history (for conversation context)
-    but skip session name update (which would persist)."""
+    Incognito messages must not mutate persistent session history, even in
+    memory, because a later normal turn can persist the same session object."""
+    if incognito:
+        return
     user_meta = {"attachments": preprocessed.attachment_meta} if preprocessed.attachment_meta else None
     sess.add_message(ChatMessage("user", preprocessed.user_content, metadata=user_meta))
-    if not incognito:
-        chat_handler.update_session_name_if_needed(sess, preprocessed.text_for_context)
+    chat_handler.update_session_name_if_needed(sess, preprocessed.text_for_context)
 
 
 def fire_message_event(request, webhook_manager, session_id: str, sess, message: str, compare_mode: bool = False):
@@ -668,8 +707,14 @@ async def build_chat_context(
         allow_tool_preprocessing=allow_tool_preprocessing,
     )
 
-    # Add user message to history
-    add_user_message(sess, chat_handler, preprocessed, incognito=incognito)
+    # Add user message to history. Nobody/incognito uses a request-local
+    # transcript store instead of session history so stale saved chats cannot
+    # bleed into context and the turn is not persisted.
+    if incognito:
+        user_meta = {"attachments": preprocessed.attachment_meta} if preprocessed.attachment_meta else None
+        _append_incognito_message(session_id, "user", preprocessed.user_content, user_meta)
+    else:
+        add_user_message(sess, chat_handler, preprocessed, incognito=False)
 
     # Fire events
     if not incognito:
@@ -760,8 +805,10 @@ async def build_chat_context(
     if norm:
         sess.model = norm
 
-    # Build messages
-    messages = preface + sess.get_context_messages()
+    # Build messages. In Nobody/incognito mode, never read saved session
+    # history: the session id may be a temporary wrapper or, in buggy clients, a
+    # stale normal session id. Only the ephemeral incognito transcript is safe.
+    messages = preface + (_incognito_messages(session_id) if incognito else sess.get_context_messages())
 
     # Current date/time — injected as a standalone *user*-role context message
     # placed immediately before the latest user turn, NOT folded into the
@@ -1027,7 +1074,12 @@ def save_assistant_response(
     tool_events: list = None,
     incognito: bool = False,
 ):
-    """Add assistant response to session history. In incognito mode, keeps in-memory context but skips DB persistence."""
+    """Add assistant response to session history.
+
+    Incognito responses are intentionally not added to the session object. The
+    session may later be saved by a normal turn, so "in-memory only" is not
+    private enough.
+    """
     md = dict(last_metrics) if last_metrics else {}
     def _model_value(value) -> str:
         if value is None:
@@ -1067,19 +1119,18 @@ def save_assistant_response(
         _content = _think_info["reply"]
     else:
         _content = full_response
+    if incognito:
+        _append_incognito_message(session_id, "assistant", _content, md)
+        return None
     sess.add_message(ChatMessage("assistant", _content, metadata=md))
 
-    if not incognito:
-        from core.database import update_session_last_accessed
-        update_session_last_accessed(session_id)
-        session_manager.save_sessions()
+    from core.database import update_session_last_accessed
+    update_session_last_accessed(session_id)
+    session_manager.save_sessions()
 
     # Return the persisted message's DB id so the stream can wire it onto the
     # freshly-rendered bubble — lets the user edit/delete a just-streamed reply
-    # without reloading. Incognito returns None: those messages are ephemeral,
-    # so we don't hand out an edit/delete handle for them.
-    if incognito:
-        return None
+    # without reloading.
     try:
         _last = sess.history[-1]
         _meta = getattr(_last, "metadata", None)

routes/chat_routes.py

@@ -42,6 +42,7 @@ from routes.chat_helpers import (
     _enforce_chat_privileges,
 )
 from src.action_intents import ToolIntent, classify_tool_intent as _classify_tool_intent
+from src.image_model_ids import looks_like_image_generation_model
 from src.tool_policy import (
     WEB_TOOL_NAMES,
     build_effective_tool_policy,
@@ -53,7 +54,6 @@ logger = logging.getLogger(__name__)
 
 # Track active streams for partial-save safety net
 _active_streams: Dict[str, dict] = {}
-_IMAGE_MODEL_PREFIXES = ("gpt-image", "dall-e", "chatgpt-image")
 
 
 def _stream_set(session_id: str, **fields) -> None:
@@ -111,7 +111,8 @@ def _ensure_current_request_is_latest_user(messages: List[Dict[str, Any]], curre
 _WEB_FOLLOWUP_RE = re.compile(
     r"^\s*(?:(?:can|could|would|will)\s+you\s+)?"
     r"(?:check|try\s+again|look(?:\s+now|\s+it\s+up)?|search(?:\s+now|\s+online|\s+it)?|"
-    r"do\s+it|again)\??\s*$",
+    r"do\s+it|again|approved|approve(?:d)?|yes|ok(?:ay)?|proceed|go\s+ahead|"
+    r"send(?:\s+it)?|submit(?:\s+it)?|email(?:\s+them|\s+it)?)\??\s*$",
     re.I,
 )
 _RECENT_WEB_CONTEXT_RE = re.compile(
@@ -119,6 +120,26 @@ _RECENT_WEB_CONTEXT_RE = re.compile(
     r"price|current|latest|search|look\s+up|online)\b",
     re.I,
 )
+_RECENT_BROWSER_CONTEXT_RE = re.compile(
+    r"\b(?:browser|browse|open\s+(?:the\s+)?(?:site|page|url|link)|click|"
+    r"fill(?:\s+out)?|submit|send\s+(?:the\s+)?form|contact\s+form|web\s*form|"
+    r"form\s+submission|playwright|automation)\b",
+    re.I,
+)
+_BROWSER_MCP_TOOLS = {
+    "mcp__builtin_browser__browser_navigate",
+    "mcp__builtin_browser__browser_snapshot",
+    "mcp__builtin_browser__browser_click",
+    "mcp__builtin_browser__browser_type",
+    "mcp__builtin_browser__browser_fill_form",
+    "mcp__builtin_browser__browser_select_option",
+    "mcp__builtin_browser__browser_press_key",
+    "mcp__builtin_browser__browser_wait_for",
+    "mcp__builtin_browser__browser_take_screenshot",
+    "mcp__builtin_browser__browser_drag",
+    "mcp__builtin_browser__browser_navigate_back",
+    "mcp__builtin_browser__browser_close",
+}
 
 
 def _recent_session_text(sess, limit: int = 8, max_chars: int = 2000) -> str:
@@ -141,6 +162,13 @@ def _is_contextual_web_followup(message: str, sess) -> bool:
     return bool(_RECENT_WEB_CONTEXT_RE.search(_recent_session_text(sess)))
 
 
+def _is_contextual_browser_followup(message: str, sess) -> bool:
+    """Treat short retry replies as browser tasks when recent context was forms/browser automation."""
+    if not message or not _WEB_FOLLOWUP_RE.search(message):
+        return False
+    return bool(_RECENT_BROWSER_CONTEXT_RE.search(_recent_session_text(sess, limit=12, max_chars=4000)))
+
+
 def _resolve_request_workspace(request, raw_value) -> tuple:
     """Resolve the posted workspace for this request: (workspace, rejected).
 
@@ -168,6 +196,46 @@ def _resolve_request_workspace(request, raw_value) -> tuple:
     return workspace, (requested if not workspace else "")
 
 
+_ABS_PATH_RE = re.compile(r"(?<!\S)(~?/[^\"'\s`<>]+)")
+_LOCAL_FILE_TASK_RE = re.compile(
+    r"\b(?:file|folder|directory|path|workspace|repo|project|movie|video|"
+    r"subtitle|subtitles|srt|vtt|ass|download|save|rename|move|copy|extract|"
+    r"convert|ffmpeg|run|execute|open|read|inspect|fix|debug|test|build)\b",
+    re.IGNORECASE,
+)
+
+
+def _resolve_workspace_from_message_path(request, message: str) -> tuple[str, str]:
+    """Auto-bind a workspace only when the user names an explicit safe path.
+
+    This is intentionally deterministic rather than LLM/RAG-driven: RAG can
+    choose the tool family, but filesystem binding must not let a prompt infer
+    or probe arbitrary host paths. For a file path, bind its parent directory.
+    For a directory path, bind that directory.
+    """
+    text = str(message or "")
+    if not text or not _LOCAL_FILE_TASK_RE.search(text):
+        return "", ""
+
+    from src.tool_security import owner_is_admin_or_single_user
+    if not owner_is_admin_or_single_user(get_current_user(request)):
+        return "", ""
+
+    from src.tool_execution import vet_workspace
+
+    for match in _ABS_PATH_RE.finditer(text):
+        raw = match.group(1).rstrip(".,;:)]}")
+        expanded = os.path.realpath(os.path.expanduser(raw))
+        candidates = [expanded]
+        if os.path.isfile(expanded):
+            candidates.insert(0, os.path.dirname(expanded))
+        for candidate in candidates:
+            workspace = vet_workspace(candidate) or ""
+            if workspace:
+                return workspace, ""
+    return "", ""
+
+
 def _session_url_matches_endpoint(session_url: str, endpoint_base: str) -> bool:
     if not session_url or not endpoint_base:
         return False
@@ -243,7 +311,7 @@ def _is_image_generation_session(sess, owner: str | None = None) -> bool:
     models into the image-generation path.
     """
     model = (getattr(sess, "model", "") or "").strip()
-    if any(model.lower().startswith(prefix) for prefix in _IMAGE_MODEL_PREFIXES):
+    if looks_like_image_generation_model(model):
         return True
 
     endpoint_url = (getattr(sess, "endpoint_url", "") or "").strip()
@@ -271,6 +339,29 @@ def _is_image_generation_session(sess, owner: str | None = None) -> bool:
     return False
 
 
+def _first_image_attachment(chat_handler, att_ids: List[str], owner: str | None = None) -> Optional[Dict[str, Any]]:
+    """Return the first attached image file that this owner can read."""
+    upload_handler = getattr(chat_handler, "upload_handler", None)
+    if not upload_handler:
+        return None
+    for att_id in att_ids or []:
+        try:
+            info = upload_handler.resolve_upload(att_id, owner=owner)
+        except Exception as e:
+            logger.warning("Failed to resolve image edit upload %s", att_id, exc_info=e)
+            continue
+        if not info:
+            continue
+        name = info.get("name") or info.get("original_name") or info.get("id") or ""
+        mime = info.get("mime", "")
+        try:
+            if upload_handler.is_image_file(name, mime):
+                return info
+        except Exception:
+            continue
+    return None
+
+
 def _recover_empty_session_model(sess, session_id: str, owner: str | None = None) -> bool:
     """Re-populate sess.model from the matching endpoint's cached models.
 
@@ -381,9 +472,85 @@ def _recover_empty_session_model(sess, session_id: str, owner: str | None = None
     except Exception as e:
         db.rollback()
         logger.warning("Failed to recover empty session model for %s: %s", session_id, e)
+    return False
+
+
+def _reconcile_selected_route_from_request(
+    request: Request,
+    sess,
+    session_id: str,
+    form_data,
+    owner: str | None = None,
+) -> bool:
+    """Apply the model route the browser selected before streaming.
+
+    The frontend creates a pending chat first and only materializes it on first
+    send. Startup/default-model refreshes can race with that UI state, so the
+    stream request includes the route that was selected at click/send time.
+    Trust only registered endpoint ids, or the session's existing endpoint URL.
+    """
+    selected_model = str(form_data.get("selected_model") or "").strip()
+    selected_endpoint_id = str(form_data.get("selected_endpoint_id") or "").strip()
+    selected_endpoint_url = str(form_data.get("selected_endpoint_url") or "").strip()
+    if not selected_model:
         return False
+
+    endpoint_url = ""
+    headers = None
+    if selected_endpoint_id or selected_endpoint_url:
+        try:
+            from src.auth_helpers import owner_filter
+            from src.endpoint_resolver import build_headers, normalize_base
+            db = SessionLocal()
+            try:
+                q = db.query(ModelEndpoint).filter(ModelEndpoint.is_enabled == True)
+                if selected_endpoint_id:
+                    q = q.filter(ModelEndpoint.id == selected_endpoint_id)
+                if owner:
+                    q = owner_filter(q, ModelEndpoint, owner)
+                candidates = q.all() if selected_endpoint_url and not selected_endpoint_id else [q.first()]
+                ep = None
+                for cand in candidates:
+                    if not cand:
+                        continue
+                    if selected_endpoint_id or _session_url_matches_endpoint(selected_endpoint_url, cand.base_url or ""):
+                        ep = cand
+                        break
+                if not ep:
+                    return False
+                endpoint_url = build_chat_url(normalize_base(ep.base_url or ""))
+                headers = build_headers(ep.api_key or "", ep.base_url or "") if ep.api_key else {}
+            finally:
+                db.close()
+        except Exception as e:
+            logger.warning("Failed to resolve selected endpoint %s/%s for %s: %s", selected_endpoint_id, selected_endpoint_url, session_id, e)
+            return False
+
+    if not endpoint_url:
+        return False
+
+    if (
+        selected_model == (getattr(sess, "model", "") or "")
+        and endpoint_url == (getattr(sess, "endpoint_url", "") or "")
+    ):
+        return False
+
+    sess.model = selected_model
+    sess.endpoint_url = endpoint_url
+    sess.headers = headers or {}
+    db = SessionLocal()
+    try:
+        db_session = db.query(DBSession).filter(DBSession.id == session_id).first()
+        if db_session:
+            db_session.model = selected_model
+            db_session.endpoint_url = endpoint_url
+            db_session.headers = sess.headers or {}
+            db_session.updated_at = datetime.utcnow()
+            db.commit()
     finally:
         db.close()
+    logger.info("Reconciled selected route for %s: model=%r endpoint=%s", session_id, selected_model, redact_url(endpoint_url))
+    return True
 
 
 def _set_user_time_from_request(request: Request) -> None:
@@ -565,9 +732,7 @@ def setup_chat_routes(
         search_context = form_data.get("search_context")  # pre-fetched web search results (compare mode)
         compare_mode = str(form_data.get("compare_mode", "")).lower() == "true"
         incognito = str(form_data.get("incognito", "")).lower() == "true"
-        # Plan mode is not part of the merge-ready UI. Ignore stale clients or
-        # manual form posts that still send plan_mode=true.
-        plan_mode = False
+        plan_mode = str(form_data.get("plan_mode") or (body or {}).get("plan_mode") or "").lower() == "true"
         chat_mode = str(form_data.get("mode", "")).lower()  # 'chat' or 'agent'
         # Workspace: confine the agent's file/shell tools to this folder.
         workspace, workspace_rejected = _resolve_request_workspace(
@@ -589,6 +754,25 @@ def setup_chat_routes(
         # not chats we quietly promoted for a notes/calendar intent.
         user_requested_agent = (chat_mode == "agent")
         _search_enabled = web_search_enabled_for_turn(allow_web_search, use_web)
+        _explicit_web_intent = False
+        _explicit_browser_intent = False
+        if isinstance(message, str):
+            _msg_l = message.lower()
+            _explicit_web_intent = bool(re.search(
+                r"\b(search|look\s*up|lookup|google|browse|web|online|latest|current|today|news|weather|forecast|rate|exchange\s+rate)\b",
+                _msg_l,
+            ))
+            _explicit_browser_intent = bool(re.search(
+                r"\b(browser|browse|open\s+(?:the\s+)?(?:site|page|url|link)|"
+                r"click|fill(?:\s+out)?|submit|send\s+(?:the\s+)?form|"
+                r"contact\s+form|web\s*form|form\s+submission)\b",
+                _msg_l,
+            ))
+        _allow_browser_for_web_turn = bool(
+            _explicit_browser_intent
+            or _explicit_web_intent
+            or _search_enabled
+        )
         # Intent auto-escalation: if the user is clearly asking the assistant
         # to create a todo, reminder, or calendar event, promote chat → agent
         # for this turn so the LLM has access to manage_notes / manage_calendar.
@@ -598,9 +782,13 @@ def setup_chat_routes(
         # shell disabled).
         auto_escalated = False
         _tool_intent = _classify_tool_intent(message) if isinstance(message, str) else None
+        _workspace_agent_intent = False
         if chat_mode == "chat" and _tool_intent and _tool_intent.needs_tools:
             chat_mode = "agent"
             auto_escalated = True
+            _workspace_agent_intent = _tool_intent.category in {"shell", "workspace"}
+            if _workspace_agent_intent:
+                allow_bash = "true"
             logger.info(
                 "chat→agent auto-escalation: category=%s reason=%s",
                 _tool_intent.category,
@@ -610,6 +798,10 @@ def setup_chat_routes(
             chat_mode = "agent"
             auto_escalated = True
             logger.info("chat→agent auto-escalation: search enabled")
+        elif chat_mode == "chat" and _explicit_web_intent:
+            chat_mode = "agent"
+            auto_escalated = True
+            logger.info("chat→agent auto-escalation: explicit web intent")
         active_doc_id = form_data.get("active_doc_id", "").strip()
         logger.info(f"[doc-inject] chat_mode={chat_mode}, active_doc_id={active_doc_id!r}")
 
@@ -688,6 +880,7 @@ def setup_chat_routes(
             _verify_session_owner(request, session)
             sess = session_manager.get_session(session)
             owner = effective_user(request)
+            _reconcile_selected_route_from_request(request, sess, session, form_data, owner=owner)
             if _clear_orphaned_session_endpoint(sess, owner=owner):
                 raise HTTPException(400, "Selected model endpoint was removed. Pick another model in Settings.")
             # Issue #587: picker shows a model from the endpoint cache but
@@ -711,11 +904,28 @@ def setup_chat_routes(
                 _tool_intent = ToolIntent(True, "web", "contextual web lookup follow-up")
                 chat_mode = "agent"
                 auto_escalated = True
+                _workspace_agent_intent = False
                 logger.info(
                     "chat→agent auto-escalation: category=%s reason=%s",
                     _tool_intent.category,
                     _tool_intent.reason,
                 )
+            if isinstance(message, str) and _is_contextual_browser_followup(message, sess):
+                _explicit_browser_intent = True
+                if chat_mode == "chat":
+                    chat_mode = "agent"
+                    auto_escalated = True
+                    _workspace_agent_intent = False
+                    logger.info("chat→agent auto-escalation: contextual browser/form follow-up")
+            if not workspace and isinstance(message, str):
+                _auto_workspace, _ = _resolve_workspace_from_message_path(request, message)
+                if _auto_workspace:
+                    workspace = _auto_workspace
+                    chat_mode = "agent"
+                    auto_escalated = True
+                    _workspace_agent_intent = True
+                    allow_bash = "true"
+                    logger.info("chat→agent auto-escalation: explicit path workspace=%s", workspace)
         except SessionNotFoundError as e:
             raise HTTPException(404, str(e))
         except (ValueError, ValidationError):
@@ -750,7 +960,12 @@ def setup_chat_routes(
             except Exception as e:
                 logger.warning("Failed to parse attachments JSON, ignoring attachments", exc_info=e)
 
+        image_generation_session = _is_image_generation_session(sess, owner=effective_user(request))
         no_memory = str(form_data.get("no_memory", "")).lower() == "true"
+        if image_generation_session:
+            no_memory = True
+            use_rag = "false"
+            search_context = None
         pre_context_tool_policy = build_effective_tool_policy(
             last_user_message=message,
         )
@@ -879,7 +1094,7 @@ def setup_chat_routes(
         # explicitly enable it.
         if allow_bash is not None and str(allow_bash).lower() != "true":
             disabled_tools.add("bash")
-        _explicit_web_intent = bool(_tool_intent and _tool_intent.category == "web")
+        _explicit_web_intent = _explicit_web_intent or bool(_tool_intent and _tool_intent.category == "web")
         if is_web_search_explicitly_denied(allow_web_search) or not _search_enabled:
             disabled_tools.update(WEB_TOOL_NAMES)
         if _explicit_web_intent:
@@ -893,7 +1108,7 @@ def setup_chat_routes(
                 "create_document", "edit_document", "update_document",
                 "send_email", "reply_to_email",
                 "manage_notes", "manage_calendar", "manage_tasks",
-                "api_call", "builtin_browser",
+                "api_call",
             })
             if _search_enabled:
                 disabled_tools.difference_update(WEB_TOOL_NAMES)
@@ -909,6 +1124,11 @@ def setup_chat_routes(
                 "manage_memory",      # persistent memory store
                 "search_chats",       # past chat history
                 "manage_skills",      # skill presets tied to user
+                "create_session",
+                "list_sessions",
+                "manage_session",
+                "send_to_session",
+                "chat_with_model",
             })
 
         # Active email reader open → strip the tools that let the agent drift
@@ -935,7 +1155,7 @@ def setup_chat_routes(
             if not _privs.get("can_use_bash", True):
                 disabled_tools.update({"bash", "python", "read_file", "write_file"})
             if not _privs.get("can_use_browser", True):
-                disabled_tools.add("builtin_browser")
+                disabled_tools.update(_BROWSER_MCP_TOOLS)
             if not _privs.get("can_use_documents", True):
                 disabled_tools.update({"create_document", "edit_document", "update_document", "suggest_document"})
             if not _privs.get("can_generate_images", True):
@@ -958,10 +1178,12 @@ def setup_chat_routes(
         # the heavy "do things on the computer" tools — otherwise the model
         # tries to shell out for a request that never needed it, then fails
         # (and looks broken when the shell is disabled).
-        if auto_escalated:
+        if auto_escalated and not _workspace_agent_intent:
             disabled_tools.update({
-                "bash", "python", "read_file", "write_file", "builtin_browser",
+                "bash", "python", "read_file", "write_file",
             })
+            if not _allow_browser_for_web_turn:
+                disabled_tools.update(_BROWSER_MCP_TOOLS)
 
         # Disable document tools in compare sessions — they break the pane UI
         if sess.name and sess.name.startswith("[CMP]"):
@@ -1195,7 +1417,7 @@ def setup_chat_routes(
                 _model_info["character_name"] = ctx.preset.character_name
             yield f'data: {json.dumps(_model_info)}\n\n'
 
-            if _is_image_generation_session(sess, owner=_user):
+            if image_generation_session:
                 from src.settings import get_setting
                 if tool_policy.blocks("generate_image"):
                     _blocked_msg = tool_policy.reason_for("generate_image")
@@ -1208,26 +1430,85 @@ def setup_chat_routes(
                     yield "data: [DONE]\n\n"
                     _active_streams.pop(session, None)
                     return
-                from src.ai_interaction import do_generate_image
+                from src.ai_interaction import do_edit_image, do_generate_image
                 _user_msg = message or ""
-                yield f'data: {json.dumps({"type": "tool_start", "tool": "generate_image", "command": _user_msg[:100]})}\n\n'
+                _image_upload = _first_image_attachment(chat_handler, att_ids, owner=_user)
+                _image_tool_name = "edit_image" if _image_upload else "generate_image"
+                yield f'data: {json.dumps({"type": "tool_start", "tool": _image_tool_name, "command": _user_msg[:100]})}\n\n'
                 yield ": heartbeat\n\n"
-                _img_result = await do_generate_image(f"{_user_msg}\n{sess.model}", session, owner=_user)
+                _progress_queue: asyncio.Queue = asyncio.Queue()
+
+                async def _image_progress_callback(progress: Dict[str, Any]):
+                    try:
+                        _progress_queue.put_nowait(progress)
+                    except Exception:
+                        pass
+
+                if _image_upload:
+                    _img_task = asyncio.create_task(do_edit_image(
+                        _user_msg,
+                        _image_upload.get("path", ""),
+                        model_spec=sess.model,
+                        session_id=session,
+                        owner=_user,
+                        size="1024x1024",
+                        progress_callback=_image_progress_callback,
+                    ))
+                else:
+                    _img_task = asyncio.create_task(do_generate_image(f"{_user_msg}\n{sess.model}\n512x512", session, owner=_user))
+                _img_started = time.time()
+                _img_tick = 0
+                while not _img_task.done():
+                    try:
+                        _progress = await asyncio.wait_for(_progress_queue.get(), timeout=2.0)
+                    except asyncio.TimeoutError:
+                        _progress = None
+                    _img_tick += 1
+                    _elapsed = int(time.time() - _img_started)
+                    _label = "Editing image" if _image_upload else "Generating image"
+                    yield ": image generation still running\n\n"
+                    _progress_data = {"type": "tool_progress", "tool": _image_tool_name, "message": f"{_label}… {_elapsed}s", "elapsed": _elapsed, "tick": _img_tick}
+                    if isinstance(_progress, dict) and _progress.get("total"):
+                        _step = int(_progress.get("step") or 0)
+                        _total = int(_progress.get("total") or 0)
+                        _percent = _progress.get("percent")
+                        _progress_data.update({
+                            "step": _step,
+                            "total": _total,
+                            "percent": _percent,
+                            "message": f"{_label}… {_step}/{_total}",
+                        })
+                    yield f'data: {json.dumps(_progress_data)}\n\n'
+                _img_result = await _img_task
                 _img_output = _img_result.get("results", _img_result.get("error", ""))
-                _img_tool_data = {"type": "tool_output", "tool": "generate_image", "command": _user_msg[:100], "output": _img_output, "exit_code": 0 if "error" not in _img_result else 1}
+                _img_tool_data = {"type": "tool_output", "tool": _image_tool_name, "command": _user_msg[:100], "output": _img_output, "exit_code": 0 if "error" not in _img_result else 1}
                 for _k in ("image_url", "image_id", "image_prompt", "image_model", "image_size", "image_quality"):
                     if _k in _img_result:
                         _img_tool_data[_k] = _img_result[_k]
+                if _image_upload:
+                    _img_tool_data["source_image"] = {
+                        "id": _image_upload.get("id"),
+                        "name": _image_upload.get("name") or _image_upload.get("original_name"),
+                    }
                 yield f'data: {json.dumps(_img_tool_data)}\n\n'
+                if _img_result.get("image_url"):
+                    _img_event = {"type": "generated_image", "url": _img_result.get("image_url")}
+                    for _k in ("image_url", "image_id", "image_prompt", "image_model", "image_size", "image_quality"):
+                        if _img_result.get(_k):
+                            _img_event[_k] = _img_result[_k]
+                    yield f'data: {json.dumps(_img_event)}\n\n'
                 _desc = _img_result.get("results", _img_result.get("error", "Image generation complete"))
                 full_response = _desc
                 yield f'data: {json.dumps({"delta": _desc})}\n\n'
                 # Save to session history
                 if not incognito:
-                    _ev = {"round": 1, "tool": "generate_image", "command": _user_msg[:100], "output": _img_output, "exit_code": 0 if "error" not in _img_result else 1}
+                    _ev = {"round": 1, "tool": _image_tool_name, "command": _user_msg[:100], "output": _img_output, "exit_code": 0 if "error" not in _img_result else 1}
                     for _ek in ("image_url", "image_id", "image_prompt", "image_model", "image_size", "image_quality"):
                         if _img_result.get(_ek):
                             _ev[_ek] = _img_result[_ek]
+                    if _image_upload:
+                        _ev["source_image_id"] = _image_upload.get("id")
+                        _ev["source_image_name"] = _image_upload.get("name") or _image_upload.get("original_name")
                     sess.add_message(ChatMessage("assistant", full_response, metadata={"tool_events": [_ev], "model": sess.model}))
                     session_manager.save_sessions()
                 yield f'data: {json.dumps({"type": "metrics", "data": {"total_time": 0}})}\n\n'
@@ -1292,8 +1573,10 @@ def setup_chat_routes(
                                         last_metrics["context_messages_after_trim"] = ctx.context_messages_after_trim
                                         last_metrics["context_tokens_before_trim"] = ctx.context_tokens_before_trim
                                         last_metrics["context_tokens_after_trim"] = ctx.context_tokens_after_trim
-                                    if ctx.context_length and last_metrics.get("input_tokens"):
-                                        pct = min(round((last_metrics["input_tokens"] / ctx.context_length) * 100, 1), 100.0)
+                                    request_context_tokens = ctx.context_tokens_after_trim or estimate_tokens(messages)
+                                    last_metrics["request_context_tokens"] = request_context_tokens
+                                    if ctx.context_length and request_context_tokens:
+                                        pct = min(round((request_context_tokens / ctx.context_length) * 100, 1), 100.0)
                                         last_metrics["context_percent"] = pct
                                         last_metrics["context_length"] = ctx.context_length
                                     # The frontend reads `tokens_per_second`; the raw usage event
@@ -1326,6 +1609,7 @@ def setup_chat_routes(
                                     "input_tokens": _est_in,
                                     "output_tokens": _est_out,
                                     "tokens_per_second": _tps,
+                                    "request_context_tokens": _est_in,
                                     "context_percent": _ctx_pct,
                                     "context_length": ctx.context_length,
                                     "model": _actual_model or _answered_by or _requested_model,
@@ -1360,7 +1644,7 @@ def setup_chat_routes(
                             _stream_set(session, status="done")
                             yield chunk
                 except (asyncio.CancelledError, GeneratorExit):
-                    if full_response:
+                    if full_response and not incognito:
                         logger.info("Client disconnected mid-stream (chat mode) for session %s, saving partial (%d chars)", session, len(full_response))
                         _stopped_content, _stopped_md = clean_thinking_for_save(
                             full_response,
@@ -1371,8 +1655,7 @@ def setup_chat_routes(
                             },
                         )
                         sess.add_message(ChatMessage("assistant", _stopped_content, metadata=_stopped_md))
-                        if not incognito:
-                            session_manager.save_sessions()
+                        session_manager.save_sessions()
                     raise
                 finally:
                     _active_streams.pop(session, None)
@@ -1405,6 +1688,10 @@ def setup_chat_routes(
                     _forced_tools = None
                     if _search_enabled:
                         _forced_tools = set(WEB_TOOL_NAMES)
+                        if _explicit_browser_intent:
+                            _forced_tools |= set(_BROWSER_MCP_TOOLS)
+                    elif _explicit_browser_intent:
+                        _forced_tools = set(_BROWSER_MCP_TOOLS)
 
                     async for chunk in stream_agent_loop(
                         sess.endpoint_url,
@@ -1529,7 +1816,7 @@ def setup_chat_routes(
                     # outer finally from running and left _active_streams
                     # with a stale entry).
                     try:
-                        if full_response:
+                        if full_response and not incognito:
                             logger.info("Client disconnected mid-stream for session %s, saving partial response (%d chars)", session, len(full_response))
                             _stopped_content2, _stopped_md2 = clean_thinking_for_save(
                                 full_response,
@@ -1540,8 +1827,7 @@ def setup_chat_routes(
                                 },
                             )
                             sess.add_message(ChatMessage("assistant", _stopped_content2, metadata=_stopped_md2))
-                            if not incognito:
-                                session_manager.save_sessions()
+                            session_manager.save_sessions()
                     except Exception:
                         logger.exception("Failed to save partial response on disconnect (session %s)", session)
                     raise

routes/cookbook_helpers.py

@@ -463,14 +463,22 @@ def _cached_model_scan_script(model_dirs: list[str] | None = None, add_hf_cache:
         "        if sz == 0 and os.path.isdir(snap):",
         "            sz2, nf2, ic2 = snapshot_size()",
         "            sz, nf, ic = sz2, nf2, ic or ic2",
-        "        is_diffusion = False; gguf_files = []",
+        "        is_video = bool(re.search(r'(?i)(^|/)Lightricks/LTX-|(^|/)LTX[-_/]|video|text-to-video|image-to-video', rid))",
+        "        is_diffusion = is_video; is_adapter = bool(re.search(r'(?i)(lora|adapter|peft|qlora|control[-_]?lora|diffusion[-_]?lora)', rid)); gguf_files = []",
         "        if os.path.isdir(snap):",
         "            for sd in os.listdir(snap):",
         "                sf = os.path.join(snap, sd)",
         "                if not os.path.isdir(sf): continue",
         "                if os.path.exists(os.path.join(sf, 'model_index.json')): is_diffusion = True",
+        "                if os.path.exists(os.path.join(sf, 'adapter_config.json')) or os.path.exists(os.path.join(sf, 'adapter_model.safetensors')): is_adapter = True",
+        "                for _root, _dirs, _fns in safe_walk(sf):",
+        "                    for _fn in _fns:",
+        "                        _lfn = _fn.lower()",
+        "                        if _lfn.endswith('.safetensors') and re.search(r'(?i)(ltx|video|upscaler)', _lfn): is_video = True; is_diffusion = True",
+        "                        if _lfn in ('adapter_config.json','adapter_model.safetensors','pytorch_lora_weights.safetensors') or 'lora' in _lfn:",
+        "                            is_adapter = True",
         "                for f in collect_ggufs(sf): f['rel_path'] = sd + '/' + f['rel_path']; gguf_files.append(f)",
-        "        models.append({'repo_id':rid,'size_bytes':sz,'nb_files':nf,'has_incomplete':ic,'path':cache,'is_diffusion':is_diffusion,'is_gguf':bool(gguf_files),'gguf_files':gguf_files})",
+        "        models.append({'repo_id':rid,'size_bytes':sz,'nb_files':nf,'has_incomplete':ic,'path':cache,'is_diffusion':is_diffusion,'is_video':is_video,'is_adapter':is_adapter,'is_gguf':bool(gguf_files),'gguf_files':gguf_files})",
         "def hf_cache_paths():",
         "    candidates = []",
         "    def add(p):",
@@ -505,11 +513,12 @@ def _cached_model_scan_script(model_dirs: list[str] | None = None, add_hf_cache:
         "        fp = os.path.join(p, d)",
         "        if not os.path.isdir(fp) or os.path.islink(fp) or not safe_path(fp): continue",
         "        if d in seen: continue",
-        "        is_model = False; gguf_files = []",
+        "        is_model = False; is_adapter = bool(re.search(r'(?i)(lora|adapter|peft|qlora|control[-_]?lora|diffusion[-_]?lora)', d)); gguf_files = []",
         "        for root, dirs, fns in safe_walk(fp):",
         "            for fn in fns:",
         "                if fn.lower().endswith('.gguf'): is_model = True",
         "                elif fn == 'config.json' or fn.endswith('.safetensors') or fn.endswith('.bin'): is_model = True",
+        "                if fn in ('adapter_config.json','adapter_model.safetensors','pytorch_lora_weights.safetensors') or 'lora' in fn.lower(): is_adapter = True",
         "            if is_model: break",
         "        if not is_model: continue",
         "        gguf_files = collect_ggufs(fp)",
@@ -520,7 +529,7 @@ def _cached_model_scan_script(model_dirs: list[str] | None = None, add_hf_cache:
         "                try: nf += 1; sz += os.path.getsize(os.path.join(dp, fn))",
         "                except Exception: pass",
         "        is_diff = os.path.exists(os.path.join(fp, 'model_index.json'))",
-        "        models.append({'repo_id':d,'size_bytes':sz,'nb_files':nf,'has_incomplete':False,'path':p,'is_local_dir':True,'is_diffusion':is_diff,'is_gguf':bool(gguf_files),'gguf_files':gguf_files})",
+        "        models.append({'repo_id':d,'size_bytes':sz,'nb_files':nf,'has_incomplete':False,'path':p,'is_local_dir':True,'is_diffusion':is_diff,'is_adapter':is_adapter,'is_gguf':bool(gguf_files),'gguf_files':gguf_files})",
         "def parse_size(num, unit):",
         "    try: n = float(num)",
         "    except Exception: return 0",
@@ -1320,6 +1329,26 @@ def _diagnose_serve_output(text: str) -> dict | None:
             "MLX LM is not installed on this server.",
             [{"label": "install mlx-lm in Cookbook Dependencies", "op": "dependency", "package": "mlx-lm"}],
         ),
+        (
+            r"OmniGen2Pipeline|module diffusers has no attribute .*Pipeline|custom_pipeline=.*failed",
+            "This image model uses a custom Diffusers pipeline that the launch environment does not know yet.",
+            [{"label": "update Diffusers image dependencies", "op": "dependency", "package": "diffusers transformers accelerate"}],
+        ),
+        (
+            r"mflux-generate-qwen.*not found|mflux-generate.*not found|MLX image serving requires mflux|No module named ['\"]?mflux",
+            "MLX image serving requires mflux on this Apple Silicon server.",
+            [{"label": "install mflux in Cookbook Dependencies", "op": "dependency", "package": "mflux"}],
+        ),
+        (
+            r"mlx-lama-swift|odysseus-mlx-inpaint|mlx-lama-serve|LaMa / MI-GAN MLX inpainting models require",
+            "LaMa / MI-GAN MLX inpainting requires an Odysseus-compatible mlx-lama-swift bridge on this Apple Silicon server.",
+            [{"label": "build mlx-lama-swift bridge and put odysseus-mlx-inpaint or mlx-lama-serve on PATH", "op": "dependency", "package": "mlx_lama_swift"}],
+        ),
+        (
+            r"mlx-ddcolor-swift|odysseus-mlx-colorize|mlx-ddcolor-serve|DDColor MLX models require",
+            "DDColor MLX colorization requires an Odysseus-compatible mlx-ddcolor-swift bridge on this Apple Silicon server.",
+            [{"label": "build mlx-ddcolor-swift bridge and put odysseus-mlx-colorize or mlx-ddcolor-serve on PATH", "op": "dependency", "package": "mlx_ddcolor_swift"}],
+        ),
         (
             r"Unable to quantize model of type <class ['\"]mlx_lm\.models\.switch_layers\.QuantizedSwitchLinear['\"]>|QuantizedSwitchLinear",
             "MLX-LM tried to quantize an already-quantized DeepSeek switch layer.",
@@ -1358,9 +1387,9 @@ def _diagnose_serve_output(text: str) -> dict | None:
             [{"label": "download a GGUF build of this model (repo name usually ends in -GGUF, file like Q4_K_M.gguf)", "op": "manual"}],
         ),
         (
-            r"No module named 'torch'|No module named torch|No module named 'diffusers'|No module named diffusers",
-            "Diffusion serving requires PyTorch and diffusers.",
-            [{"label": "install diffusers[torch] in Cookbook Dependencies", "op": "dependency", "package": "diffusers[torch]"}],
+            r"No module named 'torch'|No module named torch|No module named 'torchvision'|No module named torchvision|No module named 'diffusers'|No module named diffusers|No module named 'scipy'|No module named scipy|install scipy if you want to use beta sigmas|requires the Torchvision library",
+            "Diffusion serving requires PyTorch, Torchvision, Diffusers, Accelerate, and SciPy.",
+            [{"label": "install Diffusers image deps in Cookbook Dependencies", "op": "dependency", "package": "diffusers[torch] torchvision accelerate scipy python-multipart"}],
         ),
         (
             r"403 Forbidden|401 Unauthorized|Access to model.*is restricted|gated repo|not in the authorized list|awaiting a review",

routes/cookbook_routes.py

@@ -73,6 +73,23 @@ _HF_TOKEN_STATUS_SNIPPET = (
 )
 
 
+def _append_mlx_image_server_script(runner_lines: list[str]) -> None:
+    """Write the MLX image API helper next to the tmux runner on remote hosts."""
+    script_path = Path(__file__).resolve().parents[1] / "scripts" / "mlx_image_server.py"
+    try:
+        script = script_path.read_text(encoding="utf-8")
+    except Exception as e:
+        logger.warning("Failed to read mlx_image_server.py: %s", e)
+        runner_lines.append('echo "ERROR: Odysseus could not prepare the MLX image server helper."')
+        runner_lines.append('ODYSSEUS_PREFLIGHT_EXIT=127')
+        return
+    runner_lines.append('mkdir -p scripts')
+    runner_lines.append("cat > scripts/mlx_image_server.py <<'PY'")
+    runner_lines.extend(script.splitlines())
+    runner_lines.append("PY")
+    runner_lines.append('chmod +x scripts/mlx_image_server.py 2>/dev/null || true')
+
+
 def _venv_root_from_serve_cmd(cmd: str) -> str:
     """Best-effort venv root from an absolute venv python in a serve command."""
     try:
@@ -492,6 +509,11 @@ def setup_cookbook_routes() -> APIRouter:
                 "MLX LM is not installed on this server.",
                 [{"label": "install mlx-lm in Cookbook Dependencies", "op": "dependency", "package": "mlx-lm"}],
             ),
+            (
+                r"OmniGen2Pipeline|module diffusers has no attribute .*Pipeline|custom_pipeline=.*failed",
+                "This image model uses a custom Diffusers pipeline that the launch environment does not know yet.",
+                [{"label": "update Diffusers image dependencies", "op": "dependency", "package": "diffusers transformers accelerate"}],
+            ),
             (
                 r"Unable to quantize model of type <class ['\"]mlx_lm\.models\.switch_layers\.QuantizedSwitchLinear['\"]>|QuantizedSwitchLinear",
                 "MLX-LM tried to quantize an already-quantized DeepSeek switch layer.",
@@ -530,9 +552,9 @@ def setup_cookbook_routes() -> APIRouter:
                 [{"label": "download a GGUF build of this model (repo name usually ends in -GGUF, file like Q4_K_M.gguf)", "op": "manual"}],
             ),
             (
-                r"No module named 'torch'|No module named torch|No module named 'diffusers'|No module named diffusers",
-                "Diffusion serving requires PyTorch and diffusers.",
-                [{"label": "install diffusers[torch] in Cookbook Dependencies", "op": "dependency", "package": "diffusers[torch]"}],
+                r"No module named 'torch'|No module named torch|No module named 'torchvision'|No module named torchvision|No module named 'diffusers'|No module named diffusers|No module named 'scipy'|No module named scipy|install scipy if you want to use beta sigmas|requires the Torchvision library",
+                "Diffusion serving requires PyTorch, Torchvision, Diffusers, Accelerate, and SciPy.",
+                [{"label": "install Diffusers image deps in Cookbook Dependencies", "op": "dependency", "package": "diffusers[torch] torchvision accelerate scipy python-multipart"}],
             ),
             (
                 r"403 Forbidden|401 Unauthorized|Access to model.*is restricted|gated repo|not in the authorized list|awaiting a review",
@@ -1433,9 +1455,11 @@ def setup_cookbook_routes() -> APIRouter:
                     "nb_files": m["nb_files"],
                     "has_incomplete": m["has_incomplete"],
                     "status": "downloading" if m["has_incomplete"] else "ready",
-                    "path": m.get("path", ""),
-                    "is_diffusion": m.get("is_diffusion", False),
-                }
+	                    "path": m.get("path", ""),
+	                    "is_diffusion": m.get("is_diffusion", False),
+	                    "is_video": m.get("is_video", False),
+	                    "is_adapter": m.get("is_adapter", False),
+	                }
                 if m.get("is_local_dir"):
                     entry["is_local_dir"] = True
                 if m.get("is_gguf"):
@@ -1460,6 +1484,7 @@ def setup_cookbook_routes() -> APIRouter:
         """Register a diffusion model as an image endpoint so it appears in the model selector."""
         import re
         from core.database import SessionLocal, ModelEndpoint
+        from src.settings import load_settings, save_settings
 
         # Parse port from command (--port NNNN), default 8100 for diffusion_server
         port_match = re.search(r'--port\s+(\d+)', req.cmd)
@@ -1477,6 +1502,7 @@ def setup_cookbook_routes() -> APIRouter:
         # Friendly display name from repo_id
         short_name = req.repo_id.split("/")[-1] if "/" in req.repo_id else req.repo_id
         display_name = f"{short_name} (image)"
+        pinned_models = [req.repo_id] if req.repo_id else []
 
         db = SessionLocal()
         try:
@@ -1486,7 +1512,16 @@ def setup_cookbook_routes() -> APIRouter:
                 existing.is_enabled = True
                 existing.model_type = "image"
                 existing.name = display_name
+                existing.endpoint_kind = "local"
+                existing.model_refresh_mode = "manual"
+                if pinned_models:
+                    existing.cached_models = json.dumps(pinned_models)
+                    existing.pinned_models = json.dumps(pinned_models)
                 db.commit()
+                settings = load_settings()
+                if settings.get("image_gen_enabled") is not True:
+                    settings["image_gen_enabled"] = True
+                    save_settings(settings)
                 logger.info(f"Updated existing image endpoint: {base_url}")
                 return existing.id
 
@@ -1498,9 +1533,18 @@ def setup_cookbook_routes() -> APIRouter:
                 api_key=None,
                 is_enabled=True,
                 model_type="image",
+                endpoint_kind="local",
+                model_refresh_mode="manual",
+                cached_models=json.dumps(pinned_models) if pinned_models else None,
+                pinned_models=json.dumps(pinned_models) if pinned_models else None,
             )
             db.add(ep)
             db.commit()
+            settings = load_settings()
+            settings["image_gen_enabled"] = True
+            if not settings.get("image_model"):
+                settings["image_model"] = req.repo_id
+            save_settings(settings)
             logger.info(f"Auto-registered image endpoint: {display_name} @ {base_url}")
             return ep_id
         except Exception as e:
@@ -2356,24 +2400,8 @@ def setup_cookbook_routes() -> APIRouter:
                 runner_lines.append('fi')
             elif "sglang.launch_server" in req.cmd:
                 runner_lines.append('export PATH="$HOME/.local/bin:$PATH"')
-                runner_lines.append('if ! command -v sglang &>/dev/null; then')
-                runner_lines.append('  echo "ERROR: SGLang is not installed."')
-                runner_lines.append('  ODYSSEUS_PREFLIGHT_EXIT=127')
-                runner_lines.append('elif ! ODYSSEUS_SGLANG_IMPORT_ERROR="$(python3 -c "import sglang" 2>&1)"; then')
-                runner_lines.append('  echo "ERROR: SGLang is installed but failed to import."')
-                runner_lines.append('  printf "%s\\n" "$ODYSSEUS_SGLANG_IMPORT_ERROR"')
-                runner_lines.append('  ODYSSEUS_PREFLIGHT_EXIT=127')
-                runner_lines.append('fi')
-            elif "mlx_lm.server" in req.cmd:
-                runner_lines.append('export PATH="$HOME/.local/bin:/opt/homebrew/bin:/usr/local/bin:$PATH"')
-                runner_lines.append('if ! ODYSSEUS_MLX_IMPORT_ERROR="$(python3 -c "import mlx_lm" 2>&1)"; then')
-                runner_lines.append('  echo "ERROR: MLX LM is not installed."')
-                runner_lines.append('  printf "%s\\n" "$ODYSSEUS_MLX_IMPORT_ERROR"')
-                runner_lines.append('  ODYSSEUS_PREFLIGHT_EXIT=127')
-                runner_lines.append('fi')
                 runner_lines.append(f"ODYSSEUS_SERVE_CMD='{_bash_squote(req.cmd)}'")
-                runner_lines.append('if [ -z "$ODYSSEUS_PREFLIGHT_EXIT" ]; then')
-                runner_lines.append('  ODYSSEUS_MLX_CMD_PY="$(python3 - "$ODYSSEUS_SERVE_CMD" <<\'PY\'')
+                runner_lines.append('ODYSSEUS_SGLANG_CMD_PY="$(python3 - "$ODYSSEUS_SERVE_CMD" <<\'PY\'')
                 runner_lines.append('import shlex, sys')
                 runner_lines.append('parts = shlex.split(sys.argv[1])')
                 runner_lines.append('py = "python3"')
@@ -2384,6 +2412,36 @@ def setup_cookbook_routes() -> APIRouter:
                 runner_lines.append('print(py)')
                 runner_lines.append('PY')
                 runner_lines.append(')"')
+                runner_lines.append('if ! "$ODYSSEUS_SGLANG_CMD_PY" -c "import sglang" &>/dev/null; then')
+                runner_lines.append('  if ! command -v sglang &>/dev/null; then')
+                runner_lines.append('    echo "ERROR: SGLang is not installed."')
+                runner_lines.append('  else')
+                runner_lines.append('    echo "ERROR: SGLang is installed but failed to import in the launch Python."')
+                runner_lines.append('  fi')
+                runner_lines.append('  ODYSSEUS_SGLANG_IMPORT_ERROR="$("$ODYSSEUS_SGLANG_CMD_PY" -c "import sglang" 2>&1)"')
+                runner_lines.append('  printf "%s\\n" "$ODYSSEUS_SGLANG_IMPORT_ERROR"')
+                runner_lines.append('  ODYSSEUS_PREFLIGHT_EXIT=127')
+                runner_lines.append('fi')
+            elif "mlx_lm.server" in req.cmd:
+                runner_lines.append('export PATH="$HOME/.local/bin:/opt/homebrew/bin:/usr/local/bin:$PATH"')
+                runner_lines.append(f"ODYSSEUS_SERVE_CMD='{_bash_squote(req.cmd)}'")
+                runner_lines.append('ODYSSEUS_MLX_CMD_PY="$(python3 - "$ODYSSEUS_SERVE_CMD" <<\'PY\'')
+                runner_lines.append('import shlex, sys')
+                runner_lines.append('parts = shlex.split(sys.argv[1])')
+                runner_lines.append('py = "python3"')
+                runner_lines.append('for i, part in enumerate(parts):')
+                runner_lines.append('    if part.endswith("/bin/python") or part.endswith("/bin/python3") or "/bin/python3." in part:')
+                runner_lines.append('        py = part')
+                runner_lines.append('        break')
+                runner_lines.append('print(py)')
+                runner_lines.append('PY')
+                runner_lines.append(')"')
+                runner_lines.append('if ! ODYSSEUS_MLX_IMPORT_ERROR="$("$ODYSSEUS_MLX_CMD_PY" -c "import mlx_lm" 2>&1)"; then')
+                runner_lines.append('  echo "ERROR: MLX LM is not installed in the launch Python: $ODYSSEUS_MLX_CMD_PY"')
+                runner_lines.append('  printf "%s\\n" "$ODYSSEUS_MLX_IMPORT_ERROR"')
+                runner_lines.append('  ODYSSEUS_PREFLIGHT_EXIT=127')
+                runner_lines.append('fi')
+                runner_lines.append('if [ -z "$ODYSSEUS_PREFLIGHT_EXIT" ]; then')
                 runner_lines.append('  ODYSSEUS_SERVE_CMD="$("$ODYSSEUS_MLX_CMD_PY" - "$ODYSSEUS_SERVE_CMD" <<\'PY\'')
                 runner_lines.append('import json, os, shlex, sys')
                 runner_lines.append('from pathlib import Path')
@@ -2474,10 +2532,111 @@ def setup_cookbook_routes() -> APIRouter:
                 runner_lines.append('PY')
                 runner_lines.append(')"')
                 runner_lines.append('fi')
+            elif "scripts/mlx_image_server.py" in req.cmd or ".mlx_image_server.py" in req.cmd:
+                _append_mlx_image_server_script(runner_lines)
+                runner_lines.append('export PATH="$HOME/.local/bin:/opt/homebrew/bin:/usr/local/bin:$PATH"')
+                runner_lines.append(f"ODYSSEUS_SERVE_CMD='{_bash_squote(req.cmd)}'")
+                runner_lines.append('ODYSSEUS_MLX_IMAGE_CMD_PY="$(python3 - "$ODYSSEUS_SERVE_CMD" <<\'PY\'')
+                runner_lines.append('import shlex, sys')
+                runner_lines.append('parts = shlex.split(sys.argv[1])')
+                runner_lines.append('py = "python3"')
+                runner_lines.append('for part in parts:')
+                runner_lines.append('    if part.endswith("/bin/python") or part.endswith("/bin/python3") or "/bin/python3." in part:')
+                runner_lines.append('        py = part')
+                runner_lines.append('        break')
+                runner_lines.append('print(py)')
+                runner_lines.append('PY')
+                runner_lines.append(')"')
+                runner_lines.append('ODYSSEUS_MLX_IMAGE_BIN_DIR="$(dirname "$ODYSSEUS_MLX_IMAGE_CMD_PY" 2>/dev/null || true)"')
+                runner_lines.append('if [ -n "$ODYSSEUS_MLX_IMAGE_BIN_DIR" ]; then export PATH="$ODYSSEUS_MLX_IMAGE_BIN_DIR:$PATH"; fi')
+                runner_lines.append('if ! "$ODYSSEUS_MLX_IMAGE_CMD_PY" -c "import fastapi, uvicorn, multipart" >/dev/null 2>&1; then')
+                runner_lines.append('  echo "ERROR: MLX image serving requires FastAPI + uvicorn + python-multipart in the launch Python: $ODYSSEUS_MLX_IMAGE_CMD_PY. Install the MLX image dependencies in Cookbook Dependencies."')
+                runner_lines.append('  ODYSSEUS_PREFLIGHT_EXIT=127')
+                runner_lines.append('fi')
+                runner_lines.append('ODYSSEUS_MLX_IMAGE_MODEL="$(python3 - "$ODYSSEUS_SERVE_CMD" <<\'PY\'')
+                runner_lines.append('import shlex, sys')
+                runner_lines.append('parts = shlex.split(sys.argv[1])')
+                runner_lines.append('model = ""')
+                runner_lines.append('for i, part in enumerate(parts):')
+                runner_lines.append('    if part == "--model" and i + 1 < len(parts):')
+                runner_lines.append('        model = parts[i + 1]')
+                runner_lines.append('        break')
+                runner_lines.append('print(model)')
+                runner_lines.append('PY')
+                runner_lines.append(')"')
+                runner_lines.append('if printf "%s" "$ODYSSEUS_MLX_IMAGE_MODEL" | grep -qi hidream; then')
+                runner_lines.append('  if ! "$ODYSSEUS_MLX_IMAGE_CMD_PY" -c "import mlx, mlx_vlm, transformers, huggingface_hub, safetensors, numpy, PIL" >/dev/null 2>&1; then')
+                runner_lines.append('    echo "ERROR: HiDream MLX serving needs the model requirements in the launch Python: $ODYSSEUS_MLX_IMAGE_CMD_PY."')
+                runner_lines.append('    echo "Install with: $ODYSSEUS_MLX_IMAGE_CMD_PY -m pip install -U fastapi uvicorn python-multipart mlx mlx-vlm \'transformers>=4.57.0,<6.0\' huggingface_hub safetensors numpy pillow tqdm sentencepiece hf_transfer"')
+                runner_lines.append('    ODYSSEUS_PREFLIGHT_EXIT=127')
+                runner_lines.append('  fi')
+                runner_lines.append('elif printf "%s" "$ODYSSEUS_MLX_IMAGE_MODEL" | grep -qi boogu; then')
+                runner_lines.append('  if ! "$ODYSSEUS_MLX_IMAGE_CMD_PY" -c "import boogu_image_mlx, mlx, huggingface_hub, safetensors, numpy, PIL" >/dev/null 2>&1; then')
+                runner_lines.append('    echo "ERROR: Boogu MLX serving needs boogu-image-mlx in the launch Python: $ODYSSEUS_MLX_IMAGE_CMD_PY."')
+                runner_lines.append('    echo "Install with: $ODYSSEUS_MLX_IMAGE_CMD_PY -m pip install -U git+https://github.com/xocialize/boogu-image-mlx.git fastapi uvicorn python-multipart pillow"')
+                runner_lines.append('    ODYSSEUS_PREFLIGHT_EXIT=127')
+                runner_lines.append('  fi')
+                runner_lines.append('elif printf "%s" "$ODYSSEUS_MLX_IMAGE_MODEL" | grep -Eqi "ddcolor"; then')
+                runner_lines.append('  if ! "$ODYSSEUS_MLX_IMAGE_CMD_PY" -c "import PIL" >/dev/null 2>&1; then')
+                runner_lines.append('    echo "ERROR: DDColor MLX serving needs Pillow in the launch Python: $ODYSSEUS_MLX_IMAGE_CMD_PY."')
+                runner_lines.append('    echo "Install with: $ODYSSEUS_MLX_IMAGE_CMD_PY -m pip install -U fastapi uvicorn python-multipart pillow huggingface_hub"')
+                runner_lines.append('    ODYSSEUS_PREFLIGHT_EXIT=127')
+                runner_lines.append('  fi')
+                runner_lines.append('  if ! command -v odysseus-mlx-colorize >/dev/null 2>&1 && ! command -v mlx-ddcolor-serve >/dev/null 2>&1; then')
+                runner_lines.append('    echo "ERROR: DDColor MLX serving requires the Odysseus mlx-ddcolor-swift bridge on PATH: odysseus-mlx-colorize or mlx-ddcolor-serve."')
+                runner_lines.append('    echo "Build it from swift/odysseus-mlx-image-bridge in Cookbook Dependencies."')
+                runner_lines.append('    ODYSSEUS_PREFLIGHT_EXIT=127')
+                runner_lines.append('  fi')
+                runner_lines.append('  ODYSSEUS_DDCOLOR_BIN="$(command -v odysseus-mlx-colorize 2>/dev/null || command -v mlx-ddcolor-serve 2>/dev/null || true)"')
+                runner_lines.append('  if [ -n "$ODYSSEUS_DDCOLOR_BIN" ]; then')
+                runner_lines.append('    ODYSSEUS_DDCOLOR_DIR="$(dirname "$ODYSSEUS_DDCOLOR_BIN")"')
+                runner_lines.append('    if [ ! -f "$ODYSSEUS_DDCOLOR_DIR/mlx.metallib" ] && [ ! -f "$ODYSSEUS_DDCOLOR_DIR/default.metallib" ]; then')
+                runner_lines.append('      echo "ERROR: DDColor MLX serving found the Swift runner, but mlx.metallib/default.metallib is missing next to it."')
+                runner_lines.append('      echo "Run the DDColor MLX image editing dependency install again; it copies mlx.metallib from the launch Python MLX package."')
+                runner_lines.append('      ODYSSEUS_PREFLIGHT_EXIT=127')
+                runner_lines.append('    fi')
+                runner_lines.append('  fi')
+                runner_lines.append('elif printf "%s" "$ODYSSEUS_MLX_IMAGE_MODEL" | grep -Eqi "mi-gan|migan|lama"; then')
+                runner_lines.append('  if ! "$ODYSSEUS_MLX_IMAGE_CMD_PY" -c "import PIL" >/dev/null 2>&1; then')
+                runner_lines.append('    echo "ERROR: LaMa / MI-GAN MLX serving needs Pillow in the launch Python: $ODYSSEUS_MLX_IMAGE_CMD_PY."')
+                runner_lines.append('    echo "Install with: $ODYSSEUS_MLX_IMAGE_CMD_PY -m pip install -U fastapi uvicorn python-multipart pillow huggingface_hub"')
+                runner_lines.append('    ODYSSEUS_PREFLIGHT_EXIT=127')
+                runner_lines.append('  fi')
+                runner_lines.append('  if ! command -v odysseus-mlx-inpaint >/dev/null 2>&1 && ! command -v mlx-lama-serve >/dev/null 2>&1; then')
+                runner_lines.append('    echo "ERROR: LaMa / MI-GAN MLX serving requires the Odysseus mlx-lama-swift bridge on PATH: odysseus-mlx-inpaint or mlx-lama-serve."')
+                runner_lines.append('    echo "Build it from swift/odysseus-mlx-image-bridge in Cookbook Dependencies."')
+                runner_lines.append('    ODYSSEUS_PREFLIGHT_EXIT=127')
+                runner_lines.append('  fi')
+                runner_lines.append('  ODYSSEUS_INPAINT_BIN="$(command -v odysseus-mlx-inpaint 2>/dev/null || command -v mlx-lama-serve 2>/dev/null || true)"')
+                runner_lines.append('  if [ -n "$ODYSSEUS_INPAINT_BIN" ]; then')
+                runner_lines.append('    ODYSSEUS_INPAINT_DIR="$(dirname "$ODYSSEUS_INPAINT_BIN")"')
+                runner_lines.append('    if [ ! -f "$ODYSSEUS_INPAINT_DIR/mlx.metallib" ] && [ ! -f "$ODYSSEUS_INPAINT_DIR/default.metallib" ]; then')
+                runner_lines.append('      echo "ERROR: LaMa / MI-GAN MLX serving found the Swift runner, but mlx.metallib/default.metallib is missing next to it."')
+                runner_lines.append('      echo "Run the LaMa / MI-GAN MLX image editing dependency install again; it copies mlx.metallib from the launch Python MLX package."')
+                runner_lines.append('      ODYSSEUS_PREFLIGHT_EXIT=127')
+                runner_lines.append('    fi')
+                runner_lines.append('  fi')
+                runner_lines.append('elif ! command -v mflux-generate >/dev/null 2>&1 && ! command -v mflux-generate-qwen >/dev/null 2>&1; then')
+                runner_lines.append('  echo "ERROR: mflux-compatible MLX image serving requires mflux-generate or mflux-generate-qwen in PATH for launch Python: $ODYSSEUS_MLX_IMAGE_CMD_PY."')
+                runner_lines.append('  echo "Install with: $ODYSSEUS_MLX_IMAGE_CMD_PY -m pip install -U mflux fastapi uvicorn python-multipart"')
+                runner_lines.append('  ODYSSEUS_PREFLIGHT_EXIT=127')
+                runner_lines.append('fi')
             elif "scripts/diffusion_server.py" in req.cmd or ".diffusion_server.py" in req.cmd:
                 runner_lines.append('export PATH="$HOME/.local/bin:$PATH"')
-                runner_lines.append('if ! ODYSSEUS_DIFFUSION_IMPORT_ERROR="$(python3 -c "import torch, diffusers" 2>&1)"; then')
-                runner_lines.append('  echo "ERROR: Diffusion serving requires PyTorch + diffusers."')
+                runner_lines.append(f"ODYSSEUS_SERVE_CMD='{_bash_squote(req.cmd)}'")
+                runner_lines.append('ODYSSEUS_DIFFUSION_CMD_PY="$(python3 - "$ODYSSEUS_SERVE_CMD" <<\'PY\'')
+                runner_lines.append('import shlex, sys')
+                runner_lines.append('parts = shlex.split(sys.argv[1])')
+                runner_lines.append('py = "python3"')
+                runner_lines.append('for part in parts:')
+                runner_lines.append('    if part.endswith("/bin/python") or part.endswith("/bin/python3") or "/bin/python3." in part:')
+                runner_lines.append('        py = part')
+                runner_lines.append('        break')
+                runner_lines.append('print(py)')
+                runner_lines.append('PY')
+                runner_lines.append(')"')
+                runner_lines.append('if ! ODYSSEUS_DIFFUSION_IMPORT_ERROR="$("$ODYSSEUS_DIFFUSION_CMD_PY" -c "import torch, torchvision, diffusers" 2>&1)"; then')
+                runner_lines.append('  echo "ERROR: Diffusion serving requires PyTorch + Torchvision + diffusers in the launch Python: $ODYSSEUS_DIFFUSION_CMD_PY."')
                 runner_lines.append('  printf "%s\\n" "$ODYSSEUS_DIFFUSION_IMPORT_ERROR"')
                 runner_lines.append('  ODYSSEUS_PREFLIGHT_EXIT=127')
                 runner_lines.append('fi')
@@ -2588,8 +2747,8 @@ def setup_cookbook_routes() -> APIRouter:
         # endpoint; any other real model serve (i.e. not a pip-install task) gets
         # a local LLM endpoint pointed at its /v1.
         endpoint_id = None
-        is_diffusion = "diffusion_server.py" in req.cmd
-        if is_diffusion:
+        is_image_endpoint = "diffusion_server.py" in req.cmd or "mlx_image_server.py" in req.cmd
+        if is_image_endpoint:
             endpoint_id = _auto_register_image_endpoint(req, remote)
         elif not is_pip_install:
             endpoint_id = _auto_register_llm_endpoint(req, remote)
@@ -2605,7 +2764,7 @@ def setup_cookbook_routes() -> APIRouter:
         # if N != 0 within the watch window, delete the endpoint we just
         # created. Skipped for diffusion (different image-endpoint cleanup
         # path) and pip-install tasks (no endpoint to drop).
-        if endpoint_id and not is_diffusion and not is_pip_install:
+        if endpoint_id and not is_image_endpoint and not is_pip_install:
             asyncio.create_task(_serve_crash_watchdog(
                 endpoint_id=endpoint_id,
                 session_id=session_id,

routes/email_helpers.py

@@ -246,6 +246,7 @@ import re as _re_reply
 # serves replies and summaries (any fenced final-output block).
 _REPLY_OPEN_RE = _re_reply.compile(r"<<<\s*(?:REPLY|SUMMARY|OUTPUT)\s*>>+", _re_reply.I)
 _REPLY_CLOSE_RE = _re_reply.compile(r"<<<\s*END\s*>>+", _re_reply.I)
+_REPLY_ROLE_MARKER_RE = _re_reply.compile(r"</?\|(?:assistant|assistan|user|system|tool)\|>?|</\|end\|>?", _re_reply.I)
 
 
 def _extract_reply(text: str) -> str:
@@ -272,6 +273,7 @@ def _extract_reply(text: str) -> str:
     # Drop any stray/duplicate marker tokens, then strip think markup.
     t = _REPLY_OPEN_RE.sub("", t)
     t = _REPLY_CLOSE_RE.sub("", t)
+    t = _REPLY_ROLE_MARKER_RE.sub("", t)
     return _strip_think(t).strip()
 
 

routes/email_pollers.py

@@ -100,6 +100,272 @@ def _owner_for_email_account(account_id: str | None) -> str:
         return ""
 
 
+def _email_date_only(value: str | None):
+    value = (value or "").strip()
+    if not value:
+        return None
+    try:
+        return datetime.strptime(value[:10], "%Y-%m-%d").date()
+    except Exception:
+        return None
+
+
+_AUTO_REPLY_KEYS = {
+    "email_auto_reply",
+    "email_auto_reply_start",
+    "email_auto_reply_end",
+    "email_auto_reply_subject",
+    "email_auto_reply_message",
+    "email_auto_reply_cooldown",
+    "email_auto_reply_scope",
+    "email_auto_reply_account_id",
+    "email_auto_reply_exclude_automated",
+    "email_auto_reply_pause_notifications",
+    "email_auto_reply_enabled_at",
+}
+
+
+def _effective_settings_for_email_account(settings: dict, account_id: str | None) -> dict:
+    """Overlay per-account auto-reply settings onto global settings.
+
+    Other automation toggles remain global. This lets each mailbox have its own
+    away reply while preserving existing installs that only have global keys.
+    """
+    effective = dict(settings or {})
+    key = str(account_id or "").strip()
+    by_account = effective.get("email_auto_reply_by_account") or {}
+    account_cfg = by_account.get(key) if key and isinstance(by_account, dict) else None
+    if isinstance(account_cfg, dict):
+        for k in _AUTO_REPLY_KEYS:
+            if k in account_cfg:
+                effective[k] = account_cfg[k]
+    return effective
+
+
+def _away_reply_active(settings: dict, account_id: str | None) -> bool:
+    if not settings.get("email_auto_reply", False):
+        return False
+
+    scope = str(settings.get("email_auto_reply_scope") or "all").strip().lower()
+    if scope == "account":
+        selected = str(settings.get("email_auto_reply_account_id") or "").strip()
+        if selected and selected != str(account_id or ""):
+            return False
+
+    today = datetime.utcnow().date()
+    start = _email_date_only(settings.get("email_auto_reply_start"))
+    end = _email_date_only(settings.get("email_auto_reply_end"))
+    if start and today < start:
+        return False
+    if end and today > end:
+        return False
+    return True
+
+
+def _message_after_away_enabled(settings: dict, msg) -> bool:
+    enabled_at = (settings.get("email_auto_reply_enabled_at") or "").strip()
+    if not enabled_at:
+        # Existing installs may already have the toggle on before this feature
+        # existed. Do not back-reply old mail until the user saves/toggles it.
+        return False
+    try:
+        enabled_dt = datetime.fromisoformat(enabled_at.replace("Z", "+00:00"))
+    except Exception:
+        return False
+    try:
+        msg_dt = email.utils.parsedate_to_datetime(msg.get("Date", ""))
+    except Exception:
+        return False
+    try:
+        if enabled_dt.tzinfo and not msg_dt.tzinfo:
+            msg_dt = msg_dt.replace(tzinfo=enabled_dt.tzinfo)
+        elif msg_dt.tzinfo and not enabled_dt.tzinfo:
+            enabled_dt = enabled_dt.replace(tzinfo=msg_dt.tzinfo)
+    except Exception:
+        pass
+    return msg_dt >= enabled_dt
+
+
+def _away_reply_period_key(settings: dict) -> str:
+    start = (settings.get("email_auto_reply_start") or "").strip()
+    end = (settings.get("email_auto_reply_end") or "").strip()
+    return f"{start or '*'}..{end or '*'}"
+
+
+def _away_reply_cooldown_seconds(settings: dict) -> int | None:
+    raw = str(settings.get("email_auto_reply_cooldown") or "period").strip().lower()
+    if raw == "1d":
+        return 24 * 60 * 60
+    if raw == "3d":
+        return 3 * 24 * 60 * 60
+    if raw == "7d":
+        return 7 * 24 * 60 * 60
+    return None
+
+
+def _ensure_away_reply_table():
+    import sqlite3 as _sql3
+    conn = _sql3.connect(SCHEDULED_DB)
+    try:
+        conn.execute("""
+            CREATE TABLE IF NOT EXISTS email_away_replies (
+                id INTEGER PRIMARY KEY AUTOINCREMENT,
+                owner TEXT DEFAULT '',
+                account_id TEXT DEFAULT '',
+                message_id TEXT DEFAULT '',
+                sender_addr TEXT DEFAULT '',
+                subject TEXT DEFAULT '',
+                period_key TEXT DEFAULT '',
+                sent_at TEXT DEFAULT ''
+            )
+        """)
+        conn.execute("CREATE INDEX IF NOT EXISTS idx_email_away_msg ON email_away_replies(owner, account_id, message_id)")
+        conn.execute("CREATE INDEX IF NOT EXISTS idx_email_away_sender ON email_away_replies(owner, account_id, sender_addr, sent_at)")
+        conn.commit()
+    finally:
+        conn.close()
+
+
+def _sender_is_automated(msg, sender_addr: str) -> bool:
+    auto_submitted = (msg.get("Auto-Submitted") or "").strip().lower()
+    if auto_submitted and auto_submitted != "no":
+        return True
+    precedence = (msg.get("Precedence") or "").strip().lower()
+    if precedence in {"bulk", "junk", "list"}:
+        return True
+    if msg.get("List-Id") or msg.get("List-Unsubscribe"):
+        return True
+    local = (sender_addr or "").split("@", 1)[0].lower()
+    return local in {
+        "no-reply", "noreply", "do-not-reply", "donotreply",
+        "notification", "notifications", "automated", "mailer-daemon",
+        "postmaster",
+    }
+
+
+def _away_reply_already_sent(settings: dict, account_owner: str, account_id: str | None,
+                             message_id: str, sender_addr: str) -> bool:
+    import sqlite3 as _sql3
+    _ensure_away_reply_table()
+    owner = account_owner or ""
+    aid = account_id or ""
+    sender = (sender_addr or "").strip().lower()
+    conn = _sql3.connect(SCHEDULED_DB)
+    try:
+        row = conn.execute(
+            "SELECT 1 FROM email_away_replies WHERE owner=? AND account_id=? AND message_id=? LIMIT 1",
+            (owner, aid, message_id),
+        ).fetchone()
+        if row:
+            return True
+
+        cooldown = _away_reply_cooldown_seconds(settings)
+        if cooldown is None:
+            period_key = _away_reply_period_key(settings)
+            row = conn.execute(
+                "SELECT 1 FROM email_away_replies WHERE owner=? AND account_id=? AND sender_addr=? AND period_key=? LIMIT 1",
+                (owner, aid, sender, period_key),
+            ).fetchone()
+            return bool(row)
+
+        since = datetime.utcnow().timestamp() - cooldown
+        rows = conn.execute(
+            "SELECT sent_at FROM email_away_replies WHERE owner=? AND account_id=? AND sender_addr=? ORDER BY sent_at DESC LIMIT 5",
+            (owner, aid, sender),
+        ).fetchall()
+        for (sent_at,) in rows:
+            try:
+                if datetime.fromisoformat(sent_at).timestamp() >= since:
+                    return True
+            except Exception:
+                continue
+        return False
+    finally:
+        conn.close()
+
+
+def _record_away_reply(settings: dict, account_owner: str, account_id: str | None,
+                       message_id: str, sender_addr: str, subject: str):
+    import sqlite3 as _sql3
+    _ensure_away_reply_table()
+    conn = _sql3.connect(SCHEDULED_DB)
+    try:
+        conn.execute(
+            """
+            INSERT INTO email_away_replies
+            (owner, account_id, message_id, sender_addr, subject, period_key, sent_at)
+            VALUES (?, ?, ?, ?, ?, ?, ?)
+            """,
+            (
+                account_owner or "",
+                account_id or "",
+                message_id,
+                (sender_addr or "").strip().lower(),
+                subject or "",
+                _away_reply_period_key(settings),
+                datetime.utcnow().isoformat(),
+            ),
+        )
+        conn.commit()
+    finally:
+        conn.close()
+
+
+def _send_away_reply(settings: dict, account_owner: str, account_id: str | None,
+                     msg, message_id: str, sender: str, subject: str):
+    sender_name, sender_addr = email.utils.parseaddr(sender or "")
+    sender_addr = (sender_addr or "").strip()
+    if not sender_addr:
+        return False, "missing sender"
+
+    cfg = _get_email_config(account_id, owner=account_owner)
+    from_addr = (cfg.get("from_address") or cfg.get("smtp_user") or "").strip()
+    if not from_addr:
+        return False, "missing from address"
+    if sender_addr.lower() == from_addr.lower():
+        return False, "self mail"
+    if settings.get("email_auto_reply_exclude_automated", True) and _sender_is_automated(msg, sender_addr):
+        return False, "automated sender"
+    if _away_reply_already_sent(settings, account_owner, account_id, message_id, sender_addr):
+        return False, "already sent"
+
+    body = (settings.get("email_auto_reply_message") or "").strip()
+    if not body:
+        body = "Thanks for your email. I'm away and may be slower to reply."
+
+    subject_template = (settings.get("email_auto_reply_subject") or "(Away) {subject}").strip()
+    if subject_template:
+        original_subject = subject or ""
+        reply_subject = (
+            subject_template
+            .replace("{subject}", original_subject)
+            .replace("{original_subject}", original_subject)
+        ).strip() or "Re:"
+    else:
+        reply_subject = subject or ""
+        if not reply_subject.lower().lstrip().startswith("re:"):
+            reply_subject = f"Re: {reply_subject}" if reply_subject else "Re:"
+
+    outer = MIMEMultipart("alternative")
+    display = cfg.get("display_name") or ""
+    outer["From"] = email.utils.formataddr((display, from_addr)) if display else from_addr
+    outer["To"] = email.utils.formataddr((sender_name, sender_addr)) if sender_name else sender_addr
+    outer["Subject"] = reply_subject
+    outer["Date"] = email.utils.formatdate(localtime=False)
+    outer["Message-ID"] = email.utils.make_msgid()
+    outer["Auto-Submitted"] = "auto-replied"
+    outer["X-Auto-Response-Suppress"] = "All"
+    if message_id:
+        outer["In-Reply-To"] = message_id
+        refs = (msg.get("References") or "").strip()
+        outer["References"] = f"{refs} {message_id}".strip()
+    outer.attach(MIMEText(body, "plain", "utf-8"))
+
+    _send_smtp_message(cfg, from_addr, [sender_addr], outer.as_string())
+    _record_away_reply(settings, account_owner, account_id, message_id, sender_addr, subject)
+    return True, sender_addr
+
+
 # ── Routes ──
 
 async def _emit_progress(progress_cb, message: str):
@@ -125,9 +391,10 @@ async def _run_auto_summarize_once(do_summary: bool = True, do_reply: bool = Tru
     settings = _load_settings()
     prev = {k: settings.get(k, False) for k in
             ("email_auto_summarize", "email_auto_reply", "email_auto_tag",
-             "email_auto_spam", "email_auto_calendar")}
+             "email_auto_spam", "email_auto_calendar", "_email_auto_reply_draft_only")}
     settings["email_auto_summarize"] = bool(do_summary)
     settings["email_auto_reply"] = bool(do_reply)
+    settings["_email_auto_reply_draft_only"] = bool(do_reply)
     settings["email_auto_tag"] = bool(do_tag)
     settings["email_auto_spam"] = bool(do_spam)
     settings["email_auto_calendar"] = bool(do_calendar)
@@ -142,7 +409,10 @@ async def _run_auto_summarize_once(do_summary: bool = True, do_reply: bool = Tru
     finally:
         s2 = _load_settings()
         for k, v in prev.items():
-            s2[k] = v
+            if v is None and k.startswith("_"):
+                s2.pop(k, None)
+            else:
+                s2[k] = v
         _save_settings(s2)
 
 
@@ -176,7 +446,7 @@ def _latest_inbox_fallback_uids(conn, reconnect):
         return [], reconnect()
 
 
-async def _auto_summarize_pass(days_back: int = 1, account_id: str | None = None, max_process: int | None = None, progress_cb=None) -> str:
+async def _auto_summarize_pass(days_back: int = 1, account_id: str | None = None, max_process: int | None = None, progress_cb=None, away_only: bool = False) -> str:
     """Single pass of the auto-summarize/reply scan.
 
     When account_id is None, iterates over every enabled account in
@@ -208,6 +478,7 @@ async def _auto_summarize_pass(days_back: int = 1, account_id: str | None = None
                 account_id=(ids[0] if ids else None),
                 max_process=max_process,
                 progress_cb=progress_cb,
+                away_only=away_only,
             )
         outs = []
         for idx, aid in enumerate(ids, start=1):
@@ -218,6 +489,7 @@ async def _auto_summarize_pass(days_back: int = 1, account_id: str | None = None
                     account_id=aid,
                     max_process=max_process,
                     progress_cb=progress_cb,
+                    away_only=away_only,
                 )
                 outs.append(f"[{names.get(aid, aid[:8])}] {result}")
             except Exception as e:
@@ -229,23 +501,32 @@ async def _auto_summarize_pass(days_back: int = 1, account_id: str | None = None
         account_id=account_id,
         max_process=max_process,
         progress_cb=progress_cb,
+        away_only=away_only,
     )
 
 
-async def _auto_summarize_pass_single(days_back: int = 1, account_id: str | None = None, max_process: int | None = None, progress_cb=None) -> str:
+async def _auto_summarize_pass_single(days_back: int = 1, account_id: str | None = None, max_process: int | None = None, progress_cb=None, away_only: bool = False) -> str:
     """Single pass of the auto-summarize/reply scan for ONE account.
     Reads current settings flags."""
     import asyncio
     import sqlite3 as _sql3
     from src.llm_core import _uses_max_completion_tokens
 
-    settings = _load_settings()
+    settings = _effective_settings_for_email_account(_load_settings(), account_id)
     auto_sum = settings.get("email_auto_summarize", False)
     auto_reply = settings.get("email_auto_reply", False)
+    auto_reply_draft = bool(auto_reply and settings.get("_email_auto_reply_draft_only", False))
+    auto_reply_away = bool(auto_reply and not auto_reply_draft and _away_reply_active(settings, account_id))
     auto_tag = settings.get("email_auto_tag", False)
     auto_spam = settings.get("email_auto_spam", False)
     auto_cal = settings.get("email_auto_calendar", False)
-    if not auto_sum and not auto_reply and not auto_tag and not auto_spam and not auto_cal:
+    if away_only:
+        auto_sum = False
+        auto_reply_draft = False
+        auto_tag = False
+        auto_spam = False
+        auto_cal = False
+    if not auto_sum and not auto_reply_draft and not auto_reply_away and not auto_tag and not auto_spam and not auto_cal:
         return "Nothing to do"
 
     # Owner of the account being processed. All calendar + mailbox reads/writes
@@ -304,11 +585,11 @@ async def _auto_summarize_pass_single(days_back: int = 1, account_id: str | None
 
         _c = _sql3.connect(SCHEDULED_DB)
         _cache_owner_clause, _cache_owner_params = _email_cache_owner_clause(account_owner)
-        _sum_existing = {r[0] for r in _c.execute(
+        _sum_existing = set() if away_only else {r[0] for r in _c.execute(
             f"SELECT message_id FROM email_summaries WHERE {_cache_owner_clause}",
             _cache_owner_params,
         ).fetchall()}
-        _reply_existing = {r[0] for r in _c.execute(
+        _reply_existing = set() if away_only else {r[0] for r in _c.execute(
             f"SELECT message_id FROM email_ai_replies WHERE {_cache_owner_clause}",
             _cache_owner_params,
         ).fetchall()}
@@ -325,7 +606,7 @@ async def _auto_summarize_pass_single(days_back: int = 1, account_id: str | None
                 ).fetchall()}
         else:
             _tag_existing = set()
-        _cal_existing = {r[0] for r in _c.execute(
+        _cal_existing = set() if away_only else {r[0] for r in _c.execute(
             f"SELECT message_id FROM email_calendar_extractions WHERE {_cache_owner_clause}",
             _cache_owner_params,
         ).fetchall()} if auto_cal else set()
@@ -351,12 +632,21 @@ async def _auto_summarize_pass_single(days_back: int = 1, account_id: str | None
         if auto_spam and not spam_folder:
             logger.warning("Auto-spam enabled but no Junk/Spam folder detected — will classify but not move")
 
-        task_candidates = resolve_task_candidates(owner=account_owner)
-        if not task_candidates:
-            return "No model configured"
-        url, model, headers = task_candidates[0]
+        needs_llm = bool(auto_sum or auto_reply_draft or auto_tag or auto_spam or auto_cal)
+        if needs_llm:
+            task_candidates = resolve_task_candidates(owner=account_owner)
+            if not task_candidates:
+                return "No model configured"
+            url, model, headers = task_candidates[0]
+        else:
+            url, model, headers = None, "", None
 
-        writing_style = settings.get("email_writing_style", "")
+        by_account_styles = settings.get("email_writing_styles_by_account") or {}
+        writing_style = ""
+        if account_id and isinstance(by_account_styles, dict):
+            writing_style = str(by_account_styles.get(str(account_id)) or "")
+        if not writing_style:
+            writing_style = settings.get("email_writing_style", "")
         processed = 0
         already_cached = 0
         too_short = 0
@@ -366,12 +656,15 @@ async def _auto_summarize_pass_single(days_back: int = 1, account_id: str | None
         _events_created = 0
         _replies_drafted = 0
         _reply_failed = 0
+        _away_replies_sent = 0
+        _away_replies_skipped = 0
+        _away_replies_failed = 0
         _detail_lines = []
         _current_folder = "INBOX"
         # Calendar extraction is sequential and each row can involve a model
         # call plus a calendar write. Keep the scheduled calendar-only pass
         # below the 5-minute action budget instead of timing out mid-run.
-        _default_max_process = 3 if (auto_cal and not auto_sum and not auto_reply and not auto_tag and not auto_spam) else 5
+        _default_max_process = 3 if (auto_cal and not auto_sum and not auto_reply_draft and not auto_reply_away and not auto_tag and not auto_spam) else 5
         try:
             _max_process = max(1, int(max_process)) if max_process is not None else _default_max_process
         except Exception:
@@ -402,10 +695,6 @@ async def _auto_summarize_pass_single(days_back: int = 1, account_id: str | None
                     seed = f"{_folder}|{uid_str}|{msg.get('From','')}|{msg.get('Date','')}|{msg.get('Subject','')}"
                     message_id = f"<synth-{_hl.sha256(seed.encode()).hexdigest()[:16]}@local>"
                     no_msgid += 1
-                need_sum = auto_sum and message_id not in _sum_existing
-                need_reply = auto_reply and message_id not in _reply_existing
-                need_class = (auto_tag or auto_spam) and message_id not in _tag_existing
-                need_cal = bool(settings.get("email_auto_calendar", False)) and message_id not in _cal_existing
                 # Only check urgency on INBOX (received mail), not Sent
                 # Skip messages that are themselves urgency alerts, or that
                 # we sent to ourselves — otherwise the alert loop re-flags
@@ -422,17 +711,45 @@ async def _auto_summarize_pass_single(days_back: int = 1, account_id: str | None
                 except Exception:
                     _from_addr_only = ""
                 _is_self_mail = bool(_self_self_addr) and _from_addr_only.lower() == _self_self_addr
+                need_sum = auto_sum and message_id not in _sum_existing
+                need_reply = auto_reply_draft and message_id not in _reply_existing
+                need_away_reply = bool(
+                    auto_reply_away
+                    and _folder.upper() == "INBOX"
+                    and not _is_self_mail
+                    and (away_only or _message_after_away_enabled(settings, msg))
+                    and not _away_reply_already_sent(settings, account_owner, account_id, message_id, _from_addr_only)
+                )
+                need_class = (auto_tag or auto_spam) and message_id not in _tag_existing
+                need_cal = bool(settings.get("email_auto_calendar", False)) and message_id not in _cal_existing
                 need_urgent = (auto_urgent and message_id not in _urgent_existing
                                and not _folder.lower().startswith("sent")
                                and "sent" not in _folder.lower()
                                and not _is_alert_echo
                                and not _is_self_mail)
-                if not need_sum and not need_reply and not need_class and not need_cal and not need_urgent:
+                if not need_sum and not need_reply and not need_away_reply and not need_class and not need_cal and not need_urgent:
                     already_cached += 1
                     await _emit_progress(progress_cb, f"Checked {examined}/{len(uid_list)} · {already_cached} already cached")
                     continue
                 subject = _decode_header(msg.get("Subject", ""))
                 sender = _decode_header(msg.get("From", ""))
+                if need_away_reply:
+                    try:
+                        sent_away, away_detail = _send_away_reply(
+                            settings, account_owner, account_id, msg, message_id, sender, subject
+                        )
+                        if sent_away:
+                            _away_replies_sent += 1
+                            _uid_text = uid.decode() if isinstance(uid, bytes) else str(uid)
+                            _detail_lines.append(f"away reply · {_folder}#{_uid_text} · {subject or '(no subject)'} — {away_detail}")
+                        else:
+                            _away_replies_skipped += 1
+                            logger.info(f"Away reply skipped for uid={uid}: {away_detail}")
+                    except Exception as e:
+                        _away_replies_failed += 1
+                        _uid_text = uid.decode() if isinstance(uid, bytes) else str(uid)
+                        _detail_lines.append(f"away reply failed · {_folder}#{_uid_text} · {subject or '(no subject)'}")
+                        logger.warning(f"Away reply {uid} failed: {e}")
                 body = _extract_text(msg)
                 # Pull text out of any PDFs / text attachments and append to
                 # the body so summaries / replies can actually reason about
@@ -454,7 +771,7 @@ async def _auto_summarize_pass_single(days_back: int = 1, account_id: str | None
                 elif need_reply:
                     if not body:
                         body = subject
-                elif (not body or len(body) < 100) and not att_text:
+                elif not need_away_reply and (not body or len(body) < 100) and not att_text:
                     too_short += 1
                     continue
                 # Augmented body sent to the LLM: original body + attachment text.
@@ -993,7 +1310,8 @@ async def _auto_summarize_pass_single(days_back: int = 1, account_id: str | None
         # Build a clear status message
         ops = []
         if auto_sum: ops.append("summary")
-        if auto_reply: ops.append("reply")
+        if auto_reply_draft: ops.append("reply")
+        if auto_reply_away: ops.append("away")
         if auto_tag: ops.append("tag")
         if auto_spam: ops.append("spam")
         ops_label = "/".join(ops) or "none"
@@ -1002,10 +1320,14 @@ async def _auto_summarize_pass_single(days_back: int = 1, account_id: str | None
             parts.append(f"processed {processed} new")
         if auto_sum:
             parts.append(f"summarized {_summaries_created}")
-        if auto_reply:
+        if auto_reply_draft:
             parts.append(f"drafted {_replies_drafted} repl" + ("y" if _replies_drafted == 1 else "ies"))
             if _reply_failed:
                 parts.append(f"{_reply_failed} reply failed")
+        if auto_reply_away:
+            parts.append(f"sent {_away_replies_sent} away repl" + ("y" if _away_replies_sent == 1 else "ies"))
+            if _away_replies_failed:
+                parts.append(f"{_away_replies_failed} away failed")
         if already_cached:
             parts.append(f"{already_cached} already cached")
         if too_short:
@@ -1032,12 +1354,13 @@ async def _auto_summarize_pass_single(days_back: int = 1, account_id: str | None
 
 
 async def _auto_summarize_poller():
-    """Background loop kept for backward compatibility — calls _auto_summarize_pass every 60s.
+    """Background loop kept for backward compatibility — calls _auto_summarize_pass periodically.
     Newer setups should use scheduled tasks instead (summarize_emails, draft_email_replies)."""
     import asyncio as _asyncio
     while True:
         try:
-            await _asyncio.sleep(1800)
+            settings = _load_settings()
+            await _asyncio.sleep(60 if settings.get("email_auto_reply", False) else 1800)
             await _auto_summarize_pass()
         except Exception as e:
             logger.error(f"Auto-summarize poller crash: {e}")

routes/email_routes.py

@@ -26,6 +26,7 @@ import re
 import html
 import io
 import zipfile
+from urllib.parse import parse_qs, unquote, urlparse
 from html.parser import HTMLParser as _HTMLParser
 import logging
 import uuid
@@ -89,6 +90,86 @@ def _google_oauth_imap_transport_allowed(port: int, starttls: bool) -> bool:
 def _google_oauth_smtp_transport_allowed(port: int, security: str) -> bool:
     return (port == 465 and security == "ssl") or (port == 587 and security == "starttls")
 
+def _email_style_key(account_id: str | None) -> str:
+    return str(account_id or "").strip()
+
+
+def _get_email_writing_style_for_account(settings: dict, account_id: str | None = None) -> str:
+    key = _email_style_key(account_id)
+    by_account = settings.get("email_writing_styles_by_account") or {}
+    if key and isinstance(by_account, dict):
+        val = by_account.get(key)
+        if isinstance(val, str) and val.strip():
+            return val
+    return str(settings.get("email_writing_style") or "")
+
+
+def _set_email_writing_style_for_account(settings: dict, style: str, account_id: str | None = None) -> None:
+    key = _email_style_key(account_id)
+    style = str(style or "")
+    if key:
+        by_account = settings.get("email_writing_styles_by_account")
+        if not isinstance(by_account, dict):
+            by_account = {}
+        by_account[key] = style
+        settings["email_writing_styles_by_account"] = by_account
+        return
+    settings["email_writing_style"] = style
+
+
+_AUTO_REPLY_BOOL_KEYS = {
+    "email_auto_reply",
+    "email_auto_reply_exclude_automated",
+    "email_auto_reply_pause_notifications",
+}
+_AUTO_REPLY_TEXT_KEYS = {
+    "email_auto_reply_start",
+    "email_auto_reply_end",
+    "email_auto_reply_subject",
+    "email_auto_reply_message",
+    "email_auto_reply_cooldown",
+    "email_auto_reply_scope",
+    "email_auto_reply_account_id",
+    "email_auto_reply_enabled_at",
+}
+_AUTO_REPLY_KEYS = _AUTO_REPLY_BOOL_KEYS | _AUTO_REPLY_TEXT_KEYS
+
+
+def _get_auto_reply_settings_for_account(settings: dict, account_id: str | None = None) -> dict:
+    key = _email_style_key(account_id)
+    out = {k: settings.get(k) for k in _AUTO_REPLY_KEYS if k in settings}
+    by_account = settings.get("email_auto_reply_by_account") or {}
+    if key and isinstance(by_account, dict) and isinstance(by_account.get(key), dict):
+        out.update({k: v for k, v in by_account[key].items() if k in _AUTO_REPLY_KEYS})
+    return out
+
+
+def _set_auto_reply_settings_for_account(settings: dict, data: dict, account_id: str | None = None) -> tuple[bool, bool]:
+    key = _email_style_key(account_id)
+    target = _get_auto_reply_settings_for_account(settings, account_id) if key else settings
+    prev_auto_reply = bool(target.get("email_auto_reply", False))
+    for name in _AUTO_REPLY_BOOL_KEYS:
+        if name in data:
+            target[name] = bool(data[name])
+    for name in _AUTO_REPLY_TEXT_KEYS - {"email_auto_reply_enabled_at"}:
+        if name in data:
+            target[name] = str(data.get(name) or "").strip()
+    if "email_auto_reply" in data:
+        next_auto_reply = bool(target.get("email_auto_reply", False))
+        if next_auto_reply and (not prev_auto_reply or not str(target.get("email_auto_reply_enabled_at") or "").strip()):
+            target["email_auto_reply_enabled_at"] = datetime.utcnow().isoformat()
+        elif not next_auto_reply:
+            target.pop("email_auto_reply_enabled_at", None)
+    if key:
+        by_account = settings.get("email_auto_reply_by_account")
+        if not isinstance(by_account, dict):
+            by_account = {}
+        by_account[key] = {k: target.get(k) for k in _AUTO_REPLY_KEYS if k in target}
+        by_account[key]["email_auto_reply_account_id"] = key
+        by_account[key]["email_auto_reply_scope"] = "account"
+        settings["email_auto_reply_by_account"] = by_account
+    return prev_auto_reply, bool(target.get("email_auto_reply", False))
+
 
 def _safe_attachment_zip_name(name: str, fallback: str) -> str:
     """Return a zip entry filename without path traversal or empty names."""
@@ -273,6 +354,25 @@ def _record_email_received_events(owner: str, account_id: str | None, folder: st
             for _ in new_keys[:50]:
                 fire_event("email_received", owner)
             logger.info("Fired email_received for %d new message(s)", min(len(new_keys), 50))
+            try:
+                loop = asyncio.get_running_loop()
+
+                async def _run_away_reply_check():
+                    try:
+                        from routes.email_pollers import _auto_summarize_pass
+                        result = await _auto_summarize_pass(
+                            days_back=1,
+                            account_id=account_id,
+                            max_process=min(max(len(new_keys), 1), 5),
+                            away_only=True,
+                        )
+                        logger.info("Auto away-reply pass after email_received account=%s: %s", account_id, result)
+                    except Exception:
+                        logger.warning("Auto away-reply pass after email_received failed", exc_info=True)
+
+                loop.create_task(_run_away_reply_check())
+            except RuntimeError:
+                logger.debug("No running event loop for immediate away-reply check")
     except Exception:
         logger.debug("email_received event detection skipped", exc_info=True)
 
@@ -383,6 +483,148 @@ def _uid_from_fetch_meta(meta_b: bytes) -> str:
     return m.group(1).decode() if m else ""
 
 
+def _parse_list_unsubscribe_header(value: str | None) -> list[dict]:
+    """Parse RFC List-Unsubscribe entries into safe reviewable actions.
+
+    We return mailto/http entries but only the mailto kind is executable by the
+    first-pass Odysseus flow. HTTP unsubscribe links are useful evidence but
+    often contain tracking tokens and should be opened manually unless/until we
+    add a browser-confirmed flow.
+    """
+    raw = str(value or "").strip()
+    if not raw:
+        return []
+    pieces = re.findall(r"<([^>]+)>", raw)
+    if not pieces:
+        pieces = [p.strip() for p in raw.split(",") if p.strip()]
+    out: list[dict] = []
+    seen = set()
+    for piece in pieces:
+        target = piece.strip().strip("<>").strip()
+        if not target:
+            continue
+        parsed = urlparse(target)
+        scheme = parsed.scheme.lower()
+        key = target.lower()
+        if key in seen:
+            continue
+        seen.add(key)
+        if scheme == "mailto":
+            addr = unquote(parsed.path or "").strip()
+            if not addr or "\r" in addr or "\n" in addr:
+                continue
+            query = parse_qs(parsed.query or "", keep_blank_values=True)
+            subject = unquote((query.get("subject") or ["unsubscribe"])[0] or "unsubscribe")
+            body = unquote((query.get("body") or ["unsubscribe"])[0] or "unsubscribe")
+            subject = re.sub(r"[\r\n]+", " ", subject).strip() or "unsubscribe"
+            body = re.sub(r"[\r\n]+", "\n", body).strip() or "unsubscribe"
+            out.append({
+                "kind": "mailto",
+                "target": addr,
+                "subject": subject[:200],
+                "body": body[:1000],
+                "executable": True,
+            })
+        elif scheme in {"http", "https"}:
+            out.append({
+                "kind": "url",
+                "target": target,
+                "executable": False,
+            })
+    return out
+
+
+def _email_unsubscribe_candidate_from_msg(msg, uid: str, folder: str, *, spam_cached: dict | None = None) -> dict | None:
+    sender = _decode_header(msg.get("From", ""))
+    sender_name, sender_addr = email.utils.parseaddr(sender)
+    subject = _decode_header(msg.get("Subject", "(no subject)"))
+    list_id = _decode_header(msg.get("List-Id", ""))
+    precedence = (msg.get("Precedence") or "").strip().lower()
+    auto_submitted = (msg.get("Auto-Submitted") or "").strip().lower()
+    methods = _parse_list_unsubscribe_header(msg.get("List-Unsubscribe"))
+    has_unsub = bool(methods)
+    reasons: list[str] = []
+    score = 0
+    if has_unsub:
+        score += 45
+        reasons.append("has unsubscribe header")
+    if list_id:
+        score += 20
+        reasons.append("mailing-list header")
+    if precedence in {"bulk", "junk", "list"}:
+        score += 20
+        reasons.append(f"precedence={precedence}")
+    if auto_submitted and auto_submitted != "no":
+        score += 10
+        reasons.append(f"auto-submitted={auto_submitted}")
+    if spam_cached and spam_cached.get("spam"):
+        score += 35
+        if spam_cached.get("reason"):
+            reasons.append(str(spam_cached.get("reason")))
+        else:
+            reasons.append("previously classified as spam")
+    subj_l = (subject or "").lower()
+    if re.search(r"\b(unsubscribe|newsletter|sale|discount|offer|promo|limited time)\b", subj_l):
+        score += 10
+        reasons.append("promotional subject")
+    executable = [m for m in methods if m.get("executable")]
+    if score < 45 or not has_unsub:
+        return None
+    return {
+        "uid": str(uid),
+        "folder": folder,
+        "message_id": (msg.get("Message-ID") or "").strip(),
+        "subject": subject,
+        "from_name": sender_name or sender_addr,
+        "from_address": sender_addr,
+        "list_id": list_id,
+        "score": min(score, 100),
+        "reasons": reasons[:5],
+        "methods": methods,
+        "can_execute": bool(executable),
+        "recommended_method": executable[0] if executable else (methods[0] if methods else None),
+        "spam_reason": (spam_cached or {}).get("reason") or "",
+    }
+
+
+def _unsubscribe_candidate_dedupe_key(candidate: dict) -> tuple[str, str, str]:
+    list_id = str(candidate.get("list_id") or "").strip().lower()
+    method = candidate.get("recommended_method") or {}
+    method_kind = str(method.get("kind") or "").strip().lower()
+    method_target = str(method.get("target") or "").strip().lower()
+    sender = str(candidate.get("from_address") or "").strip().lower()
+    if list_id:
+        return ("list", list_id, method_target or sender)
+    if method_target:
+        return ("method", method_kind, method_target)
+    return ("sender", sender, str(candidate.get("subject") or "").strip().lower())
+
+
+def _dedupe_unsubscribe_candidates(candidates: list[dict]) -> list[dict]:
+    deduped: dict[tuple[str, str, str], dict] = {}
+    for candidate in candidates or []:
+        key = _unsubscribe_candidate_dedupe_key(candidate)
+        existing = deduped.get(key)
+        if not existing:
+            copy = dict(candidate)
+            copy["duplicate_count"] = 1
+            copy["duplicate_uids"] = [str(candidate.get("uid") or "")]
+            deduped[key] = copy
+            continue
+        existing["duplicate_count"] = int(existing.get("duplicate_count") or 1) + 1
+        uid = str(candidate.get("uid") or "")
+        if uid:
+            existing.setdefault("duplicate_uids", []).append(uid)
+        if int(candidate.get("score") or 0) > int(existing.get("score") or 0):
+            keep_count = existing.get("duplicate_count")
+            keep_uids = existing.get("duplicate_uids")
+            replacement = dict(candidate)
+            replacement["duplicate_count"] = keep_count
+            replacement["duplicate_uids"] = keep_uids
+            deduped[key] = replacement
+    return list(deduped.values())
+
+
 _FETCH_SEQ_RE = re.compile(rb"^(\d+)\s+\(")
 
 
@@ -517,6 +759,82 @@ def _email_index_rows(owner: str, account_id: str | None, folder: str, uids: lis
     return out
 
 
+def _email_index_list(owner: str, account_id: str | None, folder: str, filter_: str, limit: int, offset: int, has_attachments: bool = False) -> tuple[list[dict], int, str | None]:
+    """Return a newest-first page from the durable local email index.
+
+    This is intentionally a paint-fast cache path for the UI, not the source of
+    truth. The normal IMAP list still runs after this in the browser to refresh
+    flags/new mail.
+    """
+    limit = max(1, min(int(limit or 50), 200))
+    offset = max(0, int(offset or 0))
+    account_key = _account_cache_key(account_id, owner)
+    clauses = ["owner=?", "account_key=?", "folder=?"]
+    params: list = [owner or "", account_key, folder]
+    if filter_ == "unread":
+        clauses.append("(flags IS NULL OR instr(flags, '\\Seen') = 0)")
+    elif filter_ in {"unanswered", "undone"}:
+        clauses.append("(flags IS NULL OR instr(flags, '\\Answered') = 0)")
+    elif filter_ == "favorites":
+        clauses.append("instr(COALESCE(flags, ''), '\\Flagged') > 0")
+    elif filter_ not in {"all", "", None}:
+        return [], 0, None
+    if has_attachments:
+        clauses.append("has_attachments=1")
+    where = " AND ".join(clauses)
+    try:
+        conn = _sql3.connect(SCHEDULED_DB)
+        try:
+            total_row = conn.execute(
+                f"SELECT COUNT(*), MAX(updated_at) FROM email_message_index WHERE {where}",
+                params,
+            ).fetchone()
+            total = int((total_row or [0])[0] or 0)
+            if not total:
+                return [], 0, (total_row or [None, None])[1]
+            rows = conn.execute(
+                f"""
+                SELECT uid, message_id, subject, from_name, from_address, to_text, cc_text,
+                       date_iso, date_display, date_epoch, size, flags, has_attachments
+                FROM email_message_index
+                WHERE {where}
+                ORDER BY date_epoch DESC
+                LIMIT ? OFFSET ?
+                """,
+                [*params, limit, offset],
+            ).fetchall()
+        finally:
+            conn.close()
+    except Exception:
+        logger.debug("email index list skipped", exc_info=True)
+        return [], 0, None
+
+    emails: list[dict] = []
+    for row in rows:
+        uid, message_id, subject, from_name, from_address, to_text, cc_text, date_iso, date_display, date_epoch, size, flags, has_attachments_raw = row
+        flags = flags or ""
+        emails.append({
+            "uid": str(uid),
+            "message_id": (message_id or "").strip(),
+            "subject": subject or "(no subject)",
+            "from_name": from_name or from_address or "",
+            "from_address": from_address or "",
+            "to": to_text or "",
+            "cc": cc_text or "",
+            "date": date_iso or "",
+            "date_display": date_display or "",
+            "date_epoch": float(date_epoch or 0),
+            "size": int(size or 0),
+            "is_read": "\\Seen" in flags,
+            "is_answered": "\\Answered" in flags,
+            "is_flagged": "\\Flagged" in flags,
+            "flags": flags,
+            "has_attachments": bool(has_attachments_raw),
+            "folder": folder,
+        })
+    return emails, total, (total_row or [None, None])[1]
+
+
 def _email_index_search(owner: str, account_id: str | None, folder: str, query: str, limit: int, global_search: bool = True) -> tuple[list[dict], int, str | None]:
     q = (query or "").strip()
     if not q:
@@ -990,8 +1308,7 @@ def _normalize_addr_field(field: str) -> str:
     """Strip the malformed-but-common trailing/leading commas and stray
     whitespace from a To/Cc/Bcc string before it lands in the MIME header
     or the SMTP envelope. Users often paste a single address with a
-    trailing comma (e.g. `user@example.com,`) and most MTAs reject the
-    resulting `To: user@example.com,` line as a syntax error. Collapse
+    trailing comma, which most MTAs reject as a syntax error. Collapse
     any run of separator junk between addresses too."""
     if not field:
         return field
@@ -1162,7 +1479,7 @@ def setup_email_routes():
     _IMAP_POOL = {}   # account_id → (conn, last_used_at)
     _IMAP_IDLE_MAX = 60.0
     _WARMING_READS = set()
-    _WARM_READ_LIMIT = 2
+    _WARM_READ_LIMIT = 6
     _WARM_MAX_BYTES = 192 * 1024
     _WARM_RECENT_SECONDS = 7 * 24 * 60 * 60
     _pool_lock = _threading.Lock()
@@ -1245,6 +1562,10 @@ def setup_email_routes():
             return None
         return v[1]
 
+    def _folder_cache_get_stale(account_id, owner):
+        v = _FOLDER_CACHE.get((account_id or "", owner or ""))
+        return v[1] if v else None
+
     def _folder_cache_put(account_id, owner, value):
         _FOLDER_CACHE[(account_id or "", owner or "")] = (_time.monotonic() + _FOLDER_TTL, value)
         if len(_FOLDER_CACHE) > 32:
@@ -1951,18 +2272,44 @@ def setup_email_routes():
         from_addr: str | None = Query(None, alias="from"),
         account_id: str | None = Query(None),
         has_attachments: int = Query(0),
+        cached_only: int = Query(0),
         cache_bust: str | None = Query(None, alias="_"),
         owner: str = Depends(require_owner),
     ):
         """List emails. Uses an 8s in-memory cache + offloads blocking IMAP
         calls to a worker thread so the event loop never stalls."""
         started_at = _time.monotonic()
-        _deferred = getattr(_start_poller, '_deferred', None)
-        if _deferred:
-            await _deferred()
         fixture_result = _fixture_email_list(folder, limit, offset, filter, from_addr, owner)
         if fixture_result is not None:
             return fixture_result
+        if cached_only and not from_addr:
+            indexed_emails, indexed_total, indexed_at = _email_index_list(
+                owner, account_id, folder, filter, limit, offset, bool(has_attachments),
+            )
+            if indexed_total:
+                _hide_unlinked_calendar_tags(indexed_emails)
+                return {
+                    "emails": indexed_emails,
+                    "total": indexed_total,
+                    "folder": folder,
+                    "offset": offset,
+                    "sync": {
+                        "source": "index",
+                        "indexed": indexed_total,
+                        "updated_at": indexed_at,
+                        "cached_only": True,
+                    },
+                }
+            return {
+                "emails": [],
+                "total": 0,
+                "folder": folder,
+                "offset": offset,
+                "sync": {"source": "index", "cached_only": True},
+            }
+        _deferred = getattr(_start_poller, '_deferred', None)
+        if _deferred:
+            await _deferred()
         # SECURITY: include `owner` in the cache key so two users with
         # different account scopes don't share a cached list.
         ck = _list_cache_key(account_id, folder, filter, limit, offset, from_addr or "") + (int(bool(has_attachments)), owner)
@@ -2090,6 +2437,230 @@ def setup_email_routes():
             logger.error(f"unflag-spam failed: {e}")
             return {"ok": False, "error": "Mail operation failed"}
 
+    def _unsubscribe_spam_cache(owner: str, account_id: str | None, folder: str) -> dict[str, dict]:
+        out: dict[str, dict] = {}
+        try:
+            conn = _sql3.connect(SCHEDULED_DB)
+            try:
+                owner_clause, owner_params = _email_tag_owner_clause(account_id, owner)
+                account_clause, account_params = _email_tag_account_clause(account_id)
+                rows = conn.execute(
+                    "SELECT uid, message_id, spam_verdict, spam_reason FROM email_tags "
+                    "WHERE folder=? AND "
+                    f"{owner_clause} AND {account_clause}",
+                    (folder, *owner_params, *account_params),
+                ).fetchall()
+            finally:
+                conn.close()
+            for uid, message_id, spam_verdict, spam_reason in rows:
+                payload = {"spam": bool(spam_verdict), "reason": spam_reason or ""}
+                if uid:
+                    out[str(uid)] = payload
+                if message_id:
+                    out[str(message_id).strip()] = payload
+        except Exception:
+            logger.debug("unsubscribe spam cache lookup skipped", exc_info=True)
+        return out
+
+    def _scan_unsubscribe_candidates_sync(folder: str, account_id: str | None, owner: str, limit: int, max_scan: int) -> dict:
+        folder = folder or "INBOX"
+        limit = max(1, min(int(limit or 25), 100))
+        max_scan = max(limit, min(int(max_scan or 150), 500))
+        spam_cache = _unsubscribe_spam_cache(owner, account_id, folder)
+        candidates: list[dict] = []
+        with _imap(account_id, owner=owner) as conn:
+            st, _ = conn.select(_q(folder), readonly=True)
+            if st != "OK":
+                return {"success": False, "error": f"Folder not found: {folder}", "candidates": []}
+            st, data = _imap_uid_search(conn, "ALL")
+            if st != "OK" or not data or not data[0]:
+                return {"success": True, "candidates": [], "total": 0, "scanned": 0, "folder": folder}
+            uids = []
+            for raw_uid in data[0].split():
+                try:
+                    uids.append(int(raw_uid))
+                except Exception:
+                    continue
+            uids = sorted(uids, reverse=True)[:max_scan]
+            if not uids:
+                return {"success": True, "candidates": [], "total": 0, "scanned": 0, "folder": folder}
+            fetch_set = ",".join(str(u) for u in uids)
+            st, msg_data = _imap_uid_fetch(conn, fetch_set, "(UID RFC822.HEADER)")
+            if st != "OK":
+                return {"success": False, "error": "Failed to fetch email headers", "candidates": []}
+        for item in msg_data or []:
+            if not isinstance(item, tuple) or len(item) < 2:
+                continue
+            meta_b = item[0] if isinstance(item[0], bytes) else str(item[0]).encode()
+            uid = _uid_from_fetch_meta(meta_b)
+            if not uid:
+                continue
+            try:
+                msg = email_mod.message_from_bytes(item[1] or b"")
+            except Exception:
+                continue
+            mid = (msg.get("Message-ID") or "").strip()
+            spam_info = spam_cache.get(uid) or (spam_cache.get(mid) if mid else None) or {}
+            candidate = _email_unsubscribe_candidate_from_msg(msg, uid, folder, spam_cached=spam_info)
+            if candidate:
+                candidates.append(candidate)
+        def _uid_sort_value(candidate: dict) -> int:
+            try:
+                return int(candidate.get("uid") or 0)
+            except Exception:
+                return 0
+        raw_total = len(candidates)
+        candidates = _dedupe_unsubscribe_candidates(candidates)
+        candidates.sort(key=lambda c: (int(c.get("score") or 0), int(c.get("duplicate_count") or 1), _uid_sort_value(c)), reverse=True)
+        return {
+            "success": True,
+            "candidates": candidates[:limit],
+            "total": len(candidates),
+            "raw_total": raw_total,
+            "scanned": len(uids),
+            "folder": folder,
+            "account_id": account_id or "",
+        }
+
+    @router.get("/unsubscribe/scan")
+    async def scan_unsubscribe_candidates(
+        folder: str = Query("INBOX"),
+        account_id: str | None = Query(None),
+        limit: int = Query(25),
+        max_scan: int = Query(150),
+        owner: str = Depends(require_owner),
+    ):
+        """Review-only scan for spam/newsletter unsubscribe candidates."""
+        if account_id:
+            _assert_owns_account(account_id, owner)
+        if _fixture_email_enabled():
+            return {"success": True, "candidates": [], "total": 0, "scanned": 0, "folder": folder, "sync": {"source": "fixture"}}
+        try:
+            return await _asyncio.to_thread(_scan_unsubscribe_candidates_sync, folder, account_id, owner, limit, max_scan)
+        except Exception as e:
+            logger.error(f"unsubscribe scan failed: {e}")
+            return {"success": False, "error": "Mail operation failed", "candidates": []}
+
+    @router.post("/unsubscribe/execute")
+    def execute_unsubscribe(data: dict, owner: str = Depends(require_owner)):
+        """Execute an approved unsubscribe action.
+
+        First implementation supports mailto List-Unsubscribe only. The message
+        header is re-read server-side; client-supplied addresses are not trusted.
+        """
+        uid = str((data or {}).get("uid") or "").strip()
+        folder = str((data or {}).get("folder") or "INBOX").strip() or "INBOX"
+        account_id = (data or {}).get("account_id") or None
+        method_index = int((data or {}).get("method_index") or 0)
+        move_to_spam = bool((data or {}).get("move_to_spam"))
+        if not uid:
+            raise HTTPException(400, "Missing uid")
+        if account_id:
+            _assert_owns_account(account_id, owner)
+        try:
+            with _imap(account_id, owner=owner) as conn:
+                st, _ = conn.select(_q(folder), readonly=True)
+                if st != "OK":
+                    return {"success": False, "error": f"Folder not found: {folder}"}
+                st, msg_data = _imap_uid_fetch(conn, uid, "(UID RFC822.HEADER)")
+            if st != "OK" or not msg_data:
+                return {"success": False, "error": "Email not found"}
+            raw_header = b""
+            for item in msg_data or []:
+                if isinstance(item, tuple) and len(item) >= 2:
+                    raw_header = item[1] or b""
+                    break
+            msg = email_mod.message_from_bytes(raw_header)
+            candidate = _email_unsubscribe_candidate_from_msg(msg, uid, folder)
+            if not candidate:
+                return {"success": False, "error": "No unsubscribe header found for this email"}
+            methods = [m for m in (candidate.get("methods") or []) if m.get("kind") == "mailto" and m.get("executable")]
+            if not methods:
+                return {"success": False, "error": "This email only has web unsubscribe links; open manually for now", "candidate": candidate}
+            method = methods[method_index] if 0 <= method_index < len(methods) else methods[0]
+            target = str(method.get("target") or "").strip()
+            if not target or "\r" in target or "\n" in target:
+                return {"success": False, "error": "Invalid unsubscribe address"}
+            cfg = _resolve_send_config(account_id, owner=owner)
+            subject = str(method.get("subject") or "unsubscribe")[:200]
+            body = str(method.get("body") or "unsubscribe")[:1000]
+            msg_out = MIMEText(body or "unsubscribe", "plain", "utf-8")
+            msg_out["From"] = email.utils.formataddr((cfg.get("display_name") or "", cfg["from_address"]))
+            msg_out["To"] = target
+            msg_out["Subject"] = subject
+            msg_out["Message-ID"] = email.utils.make_msgid(domain="odysseus.local")
+            _apply_odysseus_headers(msg_out, "unsubscribe", uid)
+            _send_smtp_message(cfg, cfg["from_address"], [target], msg_out.as_string())
+            moved = False
+            if move_to_spam:
+                try:
+                    with _imap(account_id, owner=owner) as conn:
+                        conn.select(_q(folder))
+                        moved = _move_email_message(conn, uid, "Junk", role="junk")
+                    if moved:
+                        _email_index_delete(owner, account_id, folder, uid)
+                        _invalidate_list_cache(account_id)
+                except Exception:
+                    logger.debug("unsubscribe move-to-spam skipped", exc_info=True)
+            return {
+                "success": True,
+                "method": method,
+                "candidate": candidate,
+                "moved_to_spam": moved,
+            }
+        except ValueError as e:
+            return {"success": False, "error": str(e)}
+        except Exception as e:
+            logger.error(f"unsubscribe execute failed uid={uid}: {e}")
+            return {"success": False, "error": "Mail operation failed"}
+
+    @router.post("/unsubscribe/cleanup")
+    def cleanup_unsubscribe_candidates(data: dict, owner: str = Depends(require_owner)):
+        """Move reviewed unsubscribe candidate messages to Junk or Trash."""
+        folder = str((data or {}).get("folder") or "INBOX").strip() or "INBOX"
+        account_id = (data or {}).get("account_id") or None
+        action = str((data or {}).get("action") or "").strip().lower()
+        raw_uids = (data or {}).get("uids") or []
+        if action not in {"junk", "delete"}:
+            raise HTTPException(400, "Unsupported cleanup action")
+        if account_id:
+            _assert_owns_account(account_id, owner)
+        uids: list[str] = []
+        seen = set()
+        for raw_uid in raw_uids:
+            uid = str(raw_uid or "").strip()
+            if not uid or uid in seen:
+                continue
+            if not uid.isdigit():
+                continue
+            seen.add(uid)
+            uids.append(uid)
+        if not uids:
+            return {"success": False, "error": "No email UIDs provided", "changed": 0, "failed": 0}
+        role = "junk" if action == "junk" else "trash"
+        target = "Junk" if action == "junk" else "Trash"
+        changed = 0
+        failed = 0
+        try:
+            with _imap(account_id, owner=owner) as conn:
+                conn.select(_q(folder))
+                for uid in uids:
+                    try:
+                        if _move_email_message(conn, uid, target, role=role):
+                            changed += 1
+                            _email_index_delete(owner, account_id, folder, uid)
+                        else:
+                            failed += 1
+                    except Exception:
+                        failed += 1
+                        logger.debug("unsubscribe cleanup failed for uid=%s", uid, exc_info=True)
+            if changed:
+                _invalidate_list_cache(account_id)
+            return {"success": True, "action": action, "changed": changed, "failed": failed}
+        except Exception as e:
+            logger.error(f"unsubscribe cleanup failed: {e}")
+            return {"success": False, "error": "Mail operation failed", "changed": changed, "failed": failed}
+
     @router.get("/contacts")
     async def list_contacts(
         q: str = Query(""),
@@ -2566,7 +3137,7 @@ def setup_email_routes():
             return
 
         async def _warm():
-            await _asyncio.sleep(3.0)
+            await _asyncio.sleep(0.25)
             for uid, ck in selected:
                 if _read_cache_get(ck) is not None:
                     _WARMING_READS.discard(ck)
@@ -2739,7 +3310,7 @@ def setup_email_routes():
             return {"error": "Mail operation failed"}
 
     @router.post("/attachment-as-doc/{uid}/{index}")
-    async def attachment_as_doc(uid: str, index: int, request: Request, folder: str = Query("INBOX"), account_id: str | None = Query(None), owner: str = Depends(require_owner)):
+    def attachment_as_doc(uid: str, index: int, request: Request, folder: str = Query("INBOX"), account_id: str | None = Query(None), owner: str = Depends(require_owner)):
         """Extract an email attachment and open it in the document editor.
 
         Supported extensions:
@@ -3225,7 +3796,11 @@ def setup_email_routes():
             return {"success": False, "error": "Mail operation failed"}
 
     @router.get("/folders")
-    async def list_folders(account_id: str | None = Query(None), owner: str = Depends(require_owner)):
+    async def list_folders(
+        account_id: str | None = Query(None),
+        cached_only: int = Query(0),
+        owner: str = Depends(require_owner),
+    ):
         """List IMAP folders."""
         if _fixture_email_enabled():
             return {"folders": ["INBOX", "Archive", "Sent"], "sync": {"source": "fixture"}}
@@ -3236,19 +3811,57 @@ def setup_email_routes():
             sync_meta["source"] = "folder_cache"
             payload["sync"] = sync_meta
             return payload
-        try:
+        if cached_only:
+            stale = _folder_cache_get_stale(account_id, owner)
+            if stale:
+                payload = dict(stale)
+                sync_meta = dict(payload.get("sync") or {})
+                sync_meta["source"] = "folder_cache_stale"
+                payload["sync"] = sync_meta
+                return payload
+            return {
+                "folders": ["INBOX", "Sent", "Archive"],
+                "sync": {"source": "folder_cached_only_fallback"},
+            }
+
+        def _list_folders_sync():
             with _imap(account_id, owner=owner) as conn:
                 status, folders = conn.list()
             result = []
-            for f in folders:
+            for f in folders or []:
                 decoded = f.decode() if isinstance(f, bytes) else f
                 match = re.search(r'"([^"]*)"$|(\S+)$', decoded)
                 if match:
                     name = match.group(1) or match.group(2)
                     result.append(name)
-            payload = {"folders": result, "sync": {"source": "imap", "updated_at": datetime.utcnow().isoformat() + "Z"}}
+            return {
+                "folders": result,
+                "sync": {
+                    "source": "imap",
+                    "updated_at": datetime.utcnow().isoformat() + "Z",
+                    "status": status.decode() if isinstance(status, bytes) else status,
+                },
+            }
+
+        try:
+            payload = await _asyncio.wait_for(_asyncio.to_thread(_list_folders_sync), timeout=8.0)
             _folder_cache_put(account_id, owner, payload)
             return payload
+        except _asyncio.TimeoutError:
+            logger.warning(f"list_folders timed out for account={account_id or 'default'} owner={owner}")
+            stale = _folder_cache_get_stale(account_id, owner)
+            if stale:
+                payload = dict(stale)
+                sync_meta = dict(payload.get("sync") or {})
+                sync_meta["source"] = "folder_cache_stale"
+                sync_meta["warning"] = "Folder list timed out"
+                payload["sync"] = sync_meta
+                return payload
+            return {
+                "folders": ["INBOX", "Sent", "Archive"],
+                "error": "Folder list timed out",
+                "sync": {"source": "folder_timeout_fallback"},
+            }
         except Exception as e:
             logger.error(f"list_folders failed: {e}")
             return {"folders": [], "error": "Mail operation failed"}
@@ -4040,17 +4653,23 @@ def setup_email_routes():
         return {"success": True, "message": "Draft saved"}
 
     @router.post("/extract-style")
-    async def extract_writing_style(req: ExtractStyleRequest, owner: str = Depends(require_owner)):
+    async def extract_writing_style(
+        req: ExtractStyleRequest,
+        account_id: str | None = Query(None),
+        owner: str = Depends(require_owner),
+    ):
         """Extract writing style from sent emails using LLM.
 
         IMAP fetch is offloaded to a worker thread; the LLM call uses the
         async client. Otherwise this handler froze the event loop for ~5s
         on the IMAP step alone with a remote server.
         """
+        if account_id:
+            _assert_owns_account(account_id, owner)
 
         def _gather_samples() -> tuple[list[str], str | None]:
             try:
-                with _imap(owner=owner) as imap:
+                with _imap(account_id, owner=owner) as imap:
                     imap.select(_q(_detect_sent_folder(imap)), readonly=True)
                     status, data = imap.search(None, "ALL")
                     if status != "OK" or not data[0]:
@@ -4132,7 +4751,7 @@ def setup_email_routes():
 
             # Save to settings
             settings = _load_settings()
-            settings["email_writing_style"] = style
+            _set_email_writing_style_for_account(settings, style, account_id)
             _save_settings(settings)
 
             logger.info("Writing style extracted and saved")
@@ -4424,8 +5043,11 @@ def setup_email_routes():
             message_id = (data.get("message_id") or "").strip()
             source_uid = (data.get("uid") or "").strip()
             source_folder = (data.get("folder") or "INBOX").strip()
+            account_id = (data.get("account_id") or "").strip() or None
             fast_reply = bool(data.get("fast", False))
             user_hint = (data.get("user_hint") or "").strip()
+            if account_id:
+                _assert_owns_account(account_id, owner)
 
             if not original_body:
                 return {"success": False, "error": "No email body provided"}
@@ -4433,7 +5055,7 @@ def setup_email_routes():
             # Skip cache lookup when the caller supplied a user_hint — the
             # cached generic reply doesn't reflect the instructions and
             # would silently override them.
-            if message_id and not user_hint:
+            if message_id and not user_hint and not account_id:
                 try:
                     _c = _sql3.connect(SCHEDULED_DB)
                     owner_clause, owner_params = _email_cache_owner_clause(owner)
@@ -4455,7 +5077,7 @@ def setup_email_routes():
                     logger.warning(f"AI reply cache lookup failed: {e}")
 
             settings = _load_settings()
-            style = settings.get("email_writing_style", "")
+            style = _get_email_writing_style_for_account(settings, account_id)
 
             # Try session's endpoint first if session_id provided
             url = None
@@ -4576,8 +5198,11 @@ def setup_email_routes():
             )
             if user_hint:
                 user_msg += (
-                    f"User's instructions for THIS reply (follow these — they override "
-                    f"defaults like length/tone):\n{user_hint[:2000]}\n\n"
+                    "User guidance for THIS reply. Treat this as intent/context to fold "
+                    "into a normal polished email reply in the user's writing style. "
+                    "Do not answer with only this guidance unless the user explicitly "
+                    "asked for a one-word reply:\n"
+                    f"{user_hint[:2000]}\n\n"
                 )
             user_msg += "Draft a reply. Return only the reply body text."
 
@@ -4703,23 +5328,41 @@ def setup_email_routes():
             return {"success": False, "error": "Mail operation failed"}
 
     @router.get("/style")
-    async def get_writing_style(owner: str = Depends(require_user)):
+    async def get_writing_style(
+        account_id: str | None = Query(None),
+        owner: str = Depends(require_user),
+    ):
         """Get the current writing style prompt."""
+        if account_id:
+            _assert_owns_account(account_id, owner)
         settings = _load_settings()
-        return {"style": settings.get("email_writing_style", "")}
+        return {"style": _get_email_writing_style_for_account(settings, account_id)}
 
     @router.put("/style")
-    async def update_writing_style(data: dict, owner: str = Depends(require_user)):
+    async def update_writing_style(
+        data: dict,
+        account_id: str | None = Query(None),
+        owner: str = Depends(require_user),
+    ):
         """Manually update the writing style prompt."""
+        if account_id:
+            _assert_owns_account(account_id, owner)
         settings = _load_settings()
-        settings["email_writing_style"] = data.get("style", "")
+        _set_email_writing_style_for_account(settings, data.get("style", ""), account_id)
         _save_settings(settings)
         return {"success": True}
 
     @router.get("/config")
-    async def get_email_config(owner: str = Depends(require_user)):
+    async def get_email_config(
+        account_id: str | None = Query(None),
+        owner: str = Depends(require_user),
+    ):
         """Get email configuration (passwords masked)."""
-        cfg = _get_email_config(owner=owner)
+        if account_id is not None and not isinstance(account_id, str):
+            account_id = None
+        if account_id:
+            _assert_owns_account(account_id, owner)
+        cfg = _get_email_config(account_id, owner=owner)
         cfg["smtp_password"] = "***" if cfg["smtp_password"] else ""
         cfg["imap_password"] = "***" if cfg["imap_password"] else ""
         # `_get_email_config` includes encrypted OAuth fields for the server's
@@ -4731,11 +5374,21 @@ def setup_email_routes():
         cfg.pop("oauth_token_expiry", None)
         # Include preferences from settings.json
         settings = _load_settings()
+        auto_reply_settings = _get_auto_reply_settings_for_account(settings, account_id)
         cfg["email_auto_summarize"] = bool(settings.get("email_auto_summarize", False))
-        cfg["email_auto_reply"] = bool(settings.get("email_auto_reply", False))
+        cfg["email_auto_reply"] = bool(auto_reply_settings.get("email_auto_reply", False))
         cfg["email_auto_tag"] = bool(settings.get("email_auto_tag", False))
         cfg["email_auto_spam"] = bool(settings.get("email_auto_spam", False))
         cfg["email_auto_calendar"] = bool(settings.get("email_auto_calendar", False))
+        cfg["email_auto_reply_start"] = auto_reply_settings.get("email_auto_reply_start", "")
+        cfg["email_auto_reply_end"] = auto_reply_settings.get("email_auto_reply_end", "")
+        cfg["email_auto_reply_subject"] = auto_reply_settings.get("email_auto_reply_subject", "(Away) {subject}")
+        cfg["email_auto_reply_message"] = auto_reply_settings.get("email_auto_reply_message", "")
+        cfg["email_auto_reply_cooldown"] = auto_reply_settings.get("email_auto_reply_cooldown", "period")
+        cfg["email_auto_reply_scope"] = auto_reply_settings.get("email_auto_reply_scope", "account" if account_id else "all")
+        cfg["email_auto_reply_account_id"] = auto_reply_settings.get("email_auto_reply_account_id", account_id or "")
+        cfg["email_auto_reply_exclude_automated"] = bool(auto_reply_settings.get("email_auto_reply_exclude_automated", True))
+        cfg["email_auto_reply_pause_notifications"] = bool(auto_reply_settings.get("email_auto_reply_pause_notifications", False))
         # Email translation is owned by the background task now; opening an email
         # should not trigger reader-side auto-translation from Settings.
         cfg["email_auto_translate"] = False
@@ -4743,7 +5396,11 @@ def setup_email_routes():
         return cfg
 
     @router.put("/config")
-    async def update_email_config(data: dict, owner: str = Depends(require_owner)):
+    async def update_email_config(
+        data: dict,
+        account_id: str | None = Query(None),
+        owner: str = Depends(require_owner),
+    ):
         """Update email configuration.
 
         Automation flags (email_auto_*) still live in settings.json. Credentials
@@ -4751,11 +5408,19 @@ def setup_email_routes():
         overwritten when a non-empty value is provided, so saving the form
         without retyping the password no longer wipes it.
         """
-        # Automation flags stay in settings.json (they're global, not per-account)
+        if account_id:
+            _assert_owns_account(account_id, owner)
+
+        # Non-reply automation flags stay global. Away/auto-reply settings are
+        # account-scoped when an account_id is supplied by the Email Settings UI.
         settings = _load_settings()
-        for key in ["email_auto_summarize", "email_auto_reply", "email_auto_tag", "email_auto_spam", "email_auto_calendar"]:
+        bool_keys = [
+            "email_auto_summarize", "email_auto_tag", "email_auto_spam", "email_auto_calendar",
+        ]
+        for key in bool_keys:
             if key in data:
-                settings[key] = data[key]
+                settings[key] = bool(data[key])
+        _set_auto_reply_settings_for_account(settings, data, account_id)
         _save_settings(settings)
 
         # Credentials go into the default account row

routes/gallery/gallery_routes.py

@@ -1,7 +1,9 @@
 """Gallery routes — browsable library for photos and AI-generated images."""
 
 import os
+import base64
 import hashlib
+import io
 import logging
 import re
 import uuid
@@ -27,6 +29,165 @@ from routes.gallery.gallery_helpers import (
 
 logger = logging.getLogger(__name__)
 
+_SAM_STATE: Dict[str, Any] = {}
+_GROUNDING_STATE: Dict[str, Any] = {}
+
+
+def _b64_to_pil_image(image_b64: str, *, mode: str = "RGBA"):
+    if not image_b64:
+        raise HTTPException(400, "Missing image")
+    if "," in image_b64 and image_b64.split(",", 1)[0].startswith("data:"):
+        image_b64 = image_b64.split(",", 1)[1]
+    try:
+        from PIL import Image
+
+        raw = base64.b64decode(image_b64)
+        return Image.open(io.BytesIO(raw)).convert(mode)
+    except HTTPException:
+        raise
+    except Exception as exc:
+        raise HTTPException(400, "Invalid image") from exc
+
+
+def _pil_image_to_b64(img, *, fmt: str = "PNG") -> str:
+    buf = io.BytesIO()
+    img.save(buf, format=fmt)
+    return base64.b64encode(buf.getvalue()).decode("ascii")
+
+
+def _load_sam_backend():
+    model_id = os.getenv("ODYSSEUS_SAM_MODEL", "facebook/sam-vit-base")
+    cached = _SAM_STATE.get(model_id)
+    if cached:
+        return cached
+    try:
+        import torch
+        from transformers import SamModel, SamProcessor
+    except Exception as exc:
+        raise HTTPException(
+            501,
+            "SAM mask tools are not installed. Install Cookbook Dependencies -> SAM mask tools.",
+        ) from exc
+
+    device = "cpu"
+    try:
+        if torch.cuda.is_available():
+            device = "cuda"
+        elif getattr(torch.backends, "mps", None) and torch.backends.mps.is_available():
+            device = "mps"
+    except Exception:
+        device = "cpu"
+
+    try:
+        processor = SamProcessor.from_pretrained(model_id)
+        model = SamModel.from_pretrained(model_id)
+        model.to(device)
+        model.eval()
+    except Exception as exc:
+        raise HTTPException(500, f"Failed to load SAM model {model_id}: {exc}") from exc
+
+    cached = {"torch": torch, "processor": processor, "model": model, "device": device, "model_id": model_id}
+    _SAM_STATE[model_id] = cached
+    return cached
+
+
+def _load_grounding_backend():
+    model_id = os.getenv("ODYSSEUS_GROUNDING_MODEL", "google/owlvit-base-patch32")
+    cached = _GROUNDING_STATE.get(model_id)
+    if cached:
+        return cached
+    try:
+        import torch
+        from transformers import OwlViTForObjectDetection, OwlViTProcessor
+    except Exception as exc:
+        raise HTTPException(
+            501,
+            "Object mask tools are not installed. Install Cookbook Dependencies -> SAM mask tools.",
+        ) from exc
+
+    device = "cpu"
+    try:
+        if torch.cuda.is_available():
+            device = "cuda"
+        elif getattr(torch.backends, "mps", None) and torch.backends.mps.is_available():
+            device = "mps"
+    except Exception:
+        device = "cpu"
+
+    try:
+        processor = OwlViTProcessor.from_pretrained(model_id)
+        model = OwlViTForObjectDetection.from_pretrained(model_id)
+        model.to(device)
+        model.eval()
+    except Exception as exc:
+        raise HTTPException(500, f"Failed to load object mask model {model_id}: {exc}") from exc
+
+    cached = {"torch": torch, "processor": processor, "model": model, "device": device, "model_id": model_id}
+    _GROUNDING_STATE[model_id] = cached
+    return cached
+
+
+def _ground_text_to_box(image, text: str, *, threshold: float = 0.05):
+    query = (text or "").strip()
+    if not query:
+        raise HTTPException(400, "Missing object text")
+    backend = _load_grounding_backend()
+    torch = backend["torch"]
+    processor = backend["processor"]
+    model = backend["model"]
+    device = backend["device"]
+
+    labels = [query]
+    if not query.lower().startswith(("a ", "an ", "the ")):
+        labels.append(f"a photo of {query}")
+    try:
+        inputs = processor(text=[labels], images=image, return_tensors="pt")
+        model_inputs = {
+            k: (v.to(device) if hasattr(v, "to") else v)
+            for k, v in inputs.items()
+        }
+        with torch.no_grad():
+            outputs = model(**model_inputs)
+        target_sizes = torch.tensor([[image.height, image.width]])
+        if hasattr(processor, "post_process_object_detection"):
+            results = processor.post_process_object_detection(
+                outputs=outputs,
+                target_sizes=target_sizes,
+                threshold=float(threshold),
+            )
+        elif hasattr(processor, "post_process_grounded_object_detection"):
+            results = processor.post_process_grounded_object_detection(
+                outputs=outputs,
+                target_sizes=target_sizes,
+                threshold=float(threshold),
+                text_labels=[labels],
+            )
+        else:
+            raise HTTPException(500, "Installed Transformers does not expose OWL-ViT object detection post-processing")
+        boxes = results[0].get("boxes")
+        scores = results[0].get("scores")
+        labels_idx = results[0].get("labels")
+        text_labels = results[0].get("text_labels") or results[0].get("labels_text")
+        if boxes is None or scores is None or len(boxes) == 0:
+            raise HTTPException(404, f"No visible object matched '{query}'")
+        idx = int(torch.argmax(scores).item())
+        box = [float(v) for v in boxes[idx].detach().cpu().tolist()]
+        label_idx = int(labels_idx[idx].detach().cpu().item()) if labels_idx is not None and len(labels_idx) else 0
+        label = labels[min(label_idx, len(labels) - 1)]
+        if text_labels and len(text_labels) > idx:
+            label = str(text_labels[idx])
+        return {
+            "box": box,
+            "score": float(scores[idx].detach().cpu().item()),
+            "label": label,
+            "model": backend["model_id"],
+        }
+    except HTTPException:
+        raise
+    except Exception as exc:
+        logger.exception("ground_text_to_box failed")
+        raise HTTPException(500, f"Object mask failed: {exc}") from exc
+
 
 def _current_user_is_admin(request: Request, user: str | None) -> bool:
     if not user:
@@ -1240,20 +1401,89 @@ def setup_gallery_routes() -> APIRouter:
             except httpx.TimeoutException:
                 raise HTTPException(504, "OpenAI inpaint timed out (120s)")
 
-        # Self-hosted diffusion server path
+        # Self-hosted diffusion server path. Newer Odysseus image
+        # wrappers expose the OpenAI-compatible /v1/images/edits
+        # multipart route even when they are local/self-hosted. Older
+        # diffusion_server.py exposes /v1/images/inpaint as JSON. Try the
+        # OpenAI-compatible local route first, then fall back.
         try:
             # Forward chosen_model so the diffusion server can route if it ever
             # supports multiple models per process. Harmless if ignored.
             if chosen_model:
                 body["model"] = chosen_model
-            async with httpx.AsyncClient(timeout=120) as client:
+            async with httpx.AsyncClient(timeout=240) as client:
+                try:
+                    import base64, io
+                    from PIL import Image
+
+                    img_bytes = base64.b64decode(body["image"])
+                    mask_bytes = base64.b64decode(body["mask"])
+                    # Normalize both inputs to PNG bytes. Local MLX and
+                    # Diffusers wrappers expect white mask pixels to mean
+                    # "edit this region", which matches the editor's mask.
+                    source_png = Image.open(io.BytesIO(img_bytes)).convert("RGBA")
+                    mask_png = Image.open(io.BytesIO(mask_bytes)).convert("L")
+                    src_buf = io.BytesIO()
+                    source_png.save(src_buf, format="PNG")
+                    mask_buf = io.BytesIO()
+                    mask_png.save(mask_buf, format="PNG")
+                    files = {
+                        "image": ("source.png", src_buf.getvalue(), "image/png"),
+                        "mask": ("mask.png", mask_buf.getvalue(), "image/png"),
+                    }
+                    data = {
+                        "model": chosen_model or body.get("model") or "",
+                        "prompt": body.get("prompt", ""),
+                        "size": f"{int(body.get('width') or source_png.width)}x{int(body.get('height') or source_png.height)}",
+                        "n": "1",
+                    }
+                    r = await client.post(_join_checked_gallery_endpoint(base, "/images/edits"), data=data, files=files)
+                    if r.status_code == 200:
+                        result = r.json()
+                        if isinstance(result, dict) and result.get("data"):
+                            item = result["data"][0]
+                            if item.get("b64_json"):
+                                return {"image": item["b64_json"]}
+                            if item.get("url"):
+                                raw_b64 = await _fetch_result_image_b64(item["url"])
+                                if raw_b64:
+                                    return {"image": raw_b64}
+                        if isinstance(result, dict) and result.get("image"):
+                            return {"image": result["image"]}
+                        raise HTTPException(502, "Image edit endpoint returned no image")
+                    if r.status_code not in (404, 405):
+                        logger.warning("inpaint_proxy self-hosted edits: status %s", r.status_code)
+                        detail = "Image edit request failed"
+                        try:
+                            err = r.json()
+                            detail = err.get("detail") or err.get("error") or detail
+                        except Exception:
+                            pass
+                        # A plain SD/SDXL checkpoint often exposes
+                        # generation only at /images/edits.
+                        # That does not mean the endpoint cannot inpaint:
+                        # Odysseus diffusion_server.py has a dedicated
+                        # /images/inpaint route that can derive/fallback to
+                        # inpaint, img2img crop+composite, or txt2img
+                        # crop+composite. Fall through to that route instead
+                        # of surfacing "does not support image edits".
+                        if r.status_code == 400 and "does not support image edits" in str(detail).lower():
+                            logger.info("inpaint_proxy self-hosted edits unsupported; falling back to /images/inpaint")
+                        else:
+                            raise HTTPException(r.status_code, detail)
+                except HTTPException:
+                    raise
+                except Exception:
+                    logger.exception("inpaint_proxy: failed to prepare self-hosted edit request")
+                    raise HTTPException(400, "Failed to prepare inpaint request")
+
                 r = await client.post(_join_checked_gallery_endpoint(base, "/images/inpaint"), json=body)
                 if r.status_code != 200:
                     logger.error("inpaint_proxy diffusion: status %s", r.status_code)
                     raise HTTPException(r.status_code, "Inpaint request failed")
                 return r.json()
         except httpx.TimeoutException:
-            raise HTTPException(504, "Inpaint request timed out (120s)")
+            raise HTTPException(504, "Inpaint request timed out (240s)")
         except HTTPException:
             raise
         except Exception:
@@ -1588,6 +1818,135 @@ def setup_gallery_routes() -> APIRouter:
             return {"error": "AI upscale failed"}
 
     # ---- POST /api/image/remove-bg ----
+    @router.post("/api/image/mask")
+    async def smart_mask(request: Request):
+        """Create a neutral segmentation mask from user-provided points or a box.
+
+        This endpoint intentionally does not inspect edit prompts. It only
+        turns explicit visual selection hints into a binary mask that the
+        editor can reuse for wand/layer-mask/inpaint workflows.
+        """
+        require_privilege(request, "can_generate_images")
+        body = await request.json()
+        image = _b64_to_pil_image(body.get("image") or "", mode="RGB")
+        points = body.get("points") or []
+        box = body.get("box")
+        text = (body.get("text") or body.get("query") or "").strip()
+        grounded = None
+
+        if not points and not box and text:
+            grounded = _ground_text_to_box(image, text)
+            box = grounded["box"]
+
+        if not points and not box:
+            raise HTTPException(400, "Provide at least one point, box, or object text")
+
+        backend = _load_sam_backend()
+        torch = backend["torch"]
+        processor = backend["processor"]
+        model = backend["model"]
+        device = backend["device"]
+
+        kwargs: Dict[str, Any] = {"return_tensors": "pt"}
+        input_points = []
+        if points:
+            input_labels = []
+            for p in points:
+                try:
+                    input_points.append([float(p["x"]), float(p["y"])])
+                    input_labels.append(int(p.get("label", 1)))
+                except Exception as exc:
+                    raise HTTPException(400, "Invalid point format") from exc
+            kwargs["input_points"] = [input_points]
+            kwargs["input_labels"] = [input_labels]
+        if box:
+            if not isinstance(box, list) or len(box) != 4:
+                raise HTTPException(400, "Box must be [x1, y1, x2, y2]")
+            try:
+                kwargs["input_boxes"] = [[[float(v) for v in box]]]
+            except Exception as exc:
+                raise HTTPException(400, "Invalid box format") from exc
+
+        try:
+            inputs = processor(image, **kwargs)
+            model_inputs = {
+                k: (v.to(device) if hasattr(v, "to") else v)
+                for k, v in inputs.items()
+            }
+            with torch.no_grad():
+                outputs = model(**model_inputs)
+            masks = processor.image_processor.post_process_masks(
+                outputs.pred_masks.detach().cpu(),
+                inputs["original_sizes"].detach().cpu(),
+                inputs["reshaped_input_sizes"].detach().cpu(),
+            )
+            mask_tensor = masks[0]
+            while getattr(mask_tensor, "ndim", 0) > 3:
+                mask_tensor = mask_tensor[0]
+            if getattr(mask_tensor, "ndim", 0) == 3:
+                scores = outputs.iou_scores.detach().cpu()[0]
+                while getattr(scores, "ndim", 0) > 1:
+                    scores = scores[0]
+                # SAM commonly returns multiple candidates for a click. The
+                # highest-IoU candidate can be the entire image, which is
+                # useless as an editor selection. Prefer a candidate that
+                # contains the clicked point while keeping area reasonable.
+                point_xy = None
+                if input_points:
+                    try:
+                        point_xy = (
+                            int(round(float(input_points[0][0]))),
+                            int(round(float(input_points[0][1]))),
+                        )
+                    except Exception:
+                        point_xy = None
+                best_idx = 0
+                best_rank = None
+                total_px = max(1, int(mask_tensor.shape[-1]) * int(mask_tensor.shape[-2]))
+                for i in range(int(mask_tensor.shape[0])):
+                    candidate = mask_tensor[i]
+                    area_ratio = float(candidate.sum().item()) / float(total_px)
+                    if area_ratio >= 0.985:
+                        continue
+                    contains_click = True
+                    if point_xy:
+                        px = max(0, min(int(candidate.shape[-1]) - 1, point_xy[0]))
+                        py = max(0, min(int(candidate.shape[-2]) - 1, point_xy[1]))
+                        contains_click = bool(candidate[py, px].item())
+                    if not contains_click:
+                        continue
+                    score = float(scores[min(i, len(scores) - 1)].item()) if len(scores) else 0.0
+                    # Strongly penalize broad masks; a click-selection should
+                    # usually be local unless the user gives a box.
+                    rank = score - (area_ratio * 0.35)
+                    if best_rank is None or rank > best_rank:
+                        best_rank = rank
+                        best_idx = i
+                if best_rank is None and len(scores):
+                    best_idx = int(torch.argmax(scores).item())
+                mask_tensor = mask_tensor[min(best_idx, mask_tensor.shape[0] - 1)]
+            mask_array = (mask_tensor.numpy() > 0).astype("uint8") * 255
+            from PIL import Image
+
+            mask_img = Image.fromarray(mask_array, mode="L")
+            if mask_img.size != image.size:
+                mask_img = mask_img.resize(image.size, Image.NEAREST)
+            bbox = mask_img.getbbox()
+            result = {
+                "mask": _pil_image_to_b64(mask_img),
+                "bbox": list(bbox) if bbox else None,
+                "model": backend["model_id"],
+                "device": device,
+            }
+            if grounded:
+                result["grounding"] = grounded
+            return result
+        except HTTPException:
+            raise
+        except Exception as exc:
+            logger.exception("smart_mask failed")
+            raise HTTPException(500, f"SAM mask failed: {exc}") from exc
+
     @router.post("/api/image/remove-bg")
     async def remove_background(request: Request):
         """Remove background from an image. If the client passes a `hint_mask`

routes/history/history_routes.py

@@ -137,6 +137,44 @@ def setup_history_routes(session_manager, upload_handler=None) -> APIRouter:
             entry["metadata"] = meta
         return entry
 
+    def _db_message_metadata(m: DbChatMessage) -> Dict[str, Any]:
+        meta = {}
+        if m.meta_data:
+            try:
+                meta = json.loads(m.meta_data) or {}
+            except (json.JSONDecodeError, ValueError):
+                meta = {}
+        if m.timestamp and "timestamp" not in meta:
+            meta["timestamp"] = m.timestamp.isoformat() + "Z"
+        return meta
+
+    def _hydrate_session_history_from_db(session_id: str, rows: list[DbChatMessage]) -> None:
+        """Rebuild in-memory context from raw DB rows after a history load.
+
+        The browser history endpoint can return paged/display-trimmed messages,
+        but the next model call reads ``session.history``. After a restart or a
+        stale in-memory session, selecting an old chat through the paged endpoint
+        used to show the transcript while the model only saw fresh context.
+        """
+        if not rows:
+            return
+        try:
+            session = session_manager.get_session(session_id)
+        except KeyError:
+            return
+        session.history = [
+            ChatMessage(role=m.role, content=m.content, metadata=_db_message_metadata(m) or None)
+            for m in rows
+        ]
+        session.message_count = len(session.history)
+
+    def _session_needs_db_history_hydration(session_id: str, total: int) -> bool:
+        try:
+            session = session_manager.get_session(session_id)
+        except KeyError:
+            return False
+        return len(session.history or []) < int(total or 0)
+
     @router.get("/api/history/{session_id}")
     async def get_session_history(
         request: Request,
@@ -168,6 +206,14 @@ def setup_history_routes(session_manager, upload_handler=None) -> APIRouter:
                     .limit(page_limit)
                     .all()
                 )
+                if _session_needs_db_history_hydration(session_id, total):
+                    full_rows = (
+                        db.query(DbChatMessage)
+                        .filter(DbChatMessage.session_id == session_id)
+                        .order_by(DbChatMessage.timestamp)
+                        .all()
+                    )
+                    _hydrate_session_history_from_db(session_id, full_rows)
                 history_dict = [
                     entry for entry in (_db_history_entry(m) for m in rows)
                     if not (entry.get("metadata") or {}).get("hidden")
@@ -228,10 +274,7 @@ def setup_history_routes(session_manager, upload_handler=None) -> APIRouter:
                 if db_history:
                     # Rebuild in-memory history from the full set so hidden
                     # messages (e.g. compaction summaries) are kept for AI context.
-                    session.history = [
-                        ChatMessage(role=m["role"], content=m["content"], metadata=m.get("metadata"))
-                        for m in db_history
-                    ]
+                    _hydrate_session_history_from_db(session_id, db_messages)
                 # Response excludes hidden messages, matching the in-memory path.
                 history_dict = [
                     m for m in db_history
@@ -656,6 +699,55 @@ def setup_history_routes(session_manager, upload_handler=None) -> APIRouter:
         except Exception as e:
             raise HTTPException(500, f"Topic analysis failed: {e}")
 
+    @router.get("/api/session/{session_id}/context")
+    async def get_session_context_usage(request: Request, session_id: str) -> Dict[str, Any]:
+        """Return an estimated whole-chat context usage for the session's model.
+
+        Streaming footers report the prompt size for the last request. This
+        endpoint estimates the persisted session context so the header can show
+        when the whole chat is approaching compaction.
+        """
+        _verify_session_owner(request, session_id)
+        try:
+            session = session_manager.get_session(session_id)
+        except KeyError:
+            raise HTTPException(404, "Session not found")
+
+        try:
+            from src.model_context import estimate_tokens, get_context_length
+
+            messages = session.get_context_messages()
+            used = int(estimate_tokens(messages))
+            ctx_len = int(get_context_length(session.endpoint_url, session.model) or 0)
+            pct = round((used / ctx_len) * 100, 1) if ctx_len else 0.0
+            pct = max(0.0, min(100.0, pct))
+            visible_messages = sum(
+                1 for m in session.history
+                if not (getattr(m, "metadata", None) or {}).get("hidden")
+            )
+            compacted_messages = sum(
+                1 for m in session.history
+                if (getattr(m, "metadata", None) or {}).get("compacted")
+            )
+            can_compact = used > 0
+            return {
+                "session_id": session_id,
+                "model": session.model,
+                "endpoint_url": session.endpoint_url,
+                "used_tokens": used,
+                "context_length": ctx_len,
+                "context_percent": pct,
+                "messages": visible_messages,
+                "context_messages": len(messages),
+                "compacted_messages": compacted_messages,
+                "can_compact": can_compact,
+                "should_compact": pct >= 70,
+                "auto_compact_threshold": 85,
+            }
+        except Exception as e:
+            logger.error(f"Context usage error {session_id}: {e}")
+            raise HTTPException(500, str(e))
+
     @router.post("/api/session/{session_id}/compact")
     async def compact_session(request: Request, session_id: str):
         """Manually trigger context compaction for a session."""
@@ -700,7 +792,7 @@ def setup_history_routes(session_manager, upload_handler=None) -> APIRouter:
             compact_model = util_model or session.model
             compact_headers = util_headers if util_url else session.headers
 
-            from src.context_compactor import SELF_SUMMARY_SYSTEM_PROMPT
+            from src.context_compactor import SELF_SUMMARY_SYSTEM_PROMPT, normalize_compaction_summary
             compaction_count = sum(1 for m in session.history if isinstance(m, ChatMessage) and "[Conversation summary" in (m.content or ""))
             sys_prompt = SELF_SUMMARY_SYSTEM_PROMPT.replace("{count}", str(len(older))).replace("{n}", str(compaction_count + 1))
             summary = await llm_call_async(
@@ -712,6 +804,7 @@ def setup_history_routes(session_manager, upload_handler=None) -> APIRouter:
                 temperature=0.2, max_tokens=1024,
                 headers=compact_headers, timeout=30,
             )
+            summary = normalize_compaction_summary(summary)
 
             # Replace session history: summary as system message + recent messages
             # System message holds the full summary for AI context

routes/hwfit_routes.py

@@ -429,11 +429,27 @@ def setup_hwfit_routes():
             system["available_ram_gb"] = 0
             system["total_ram_gb"] = 0
         system = _apply_manual_hardware(system, manual_mode, manual_gpu_count, manual_vram_gb, manual_ram_gb, manual_backend)
-        # Image models use a single GPU — always use per-GPU VRAM
-        gpu_vrams = [float(g.get("vram_gb") or 0) for g in (system.get("gpus") or []) if isinstance(g, dict)]
-        single_vram = max(gpu_vrams) if gpu_vrams else ((system.get("gpu_vram_gb") or 0) / max(system.get("gpu_count") or 1, 1))
-        system["gpu_vram_gb"] = single_vram
-        system["gpu_count"] = 1 if single_vram > 0 else 0
+        try:
+            requested_gpu_count = int(gpu_count) if gpu_count != "" else None
+        except ValueError:
+            requested_gpu_count = None
+        if requested_gpu_count == 0:
+            # Respect the UI's RAM toggle. Before this route always rewrote the
+            # system to best-single-GPU VRAM, so image rows never changed when
+            # switching RAM/GPU.
+            system["has_gpu"] = False
+            system["gpu_vram_gb"] = 0
+            system["gpu_count"] = 0
+            system["gpu_only"] = False
+        else:
+            # Image diffusion backends generally use one device per pipeline,
+            # so rank GPU mode against the best single GPU rather than total
+            # multi-GPU VRAM.
+            gpu_vrams = [float(g.get("vram_gb") or 0) for g in (system.get("gpus") or []) if isinstance(g, dict)]
+            single_vram = max(gpu_vrams) if gpu_vrams else ((system.get("gpu_vram_gb") or 0) / max(system.get("gpu_count") or 1, 1))
+            system["gpu_vram_gb"] = single_vram
+            system["gpu_count"] = 1 if single_vram > 0 else 0
+            system["gpu_only"] = True if single_vram > 0 else False
         results = rank_image_models(system, search=search or None, sort=sort)
         return {"system": system, "models": results}
 

routes/model_routes.py

@@ -1310,6 +1310,56 @@ def _visible_models(cached_models, hidden_models, pinned_models=None):
     return [m for m in merged if m not in hidden]
 
 
+def _picker_requires_pinning(base_url: str, kind: str) -> bool:
+    return _classify_endpoint(base_url, kind) == "api"
+
+
+def _has_explicit_pinned_models(ep) -> bool:
+    """Whether pinned_models was deliberately written for this endpoint.
+
+    API endpoints use pinned_models as an allow-list. An explicit empty JSON
+    list means "show no models"; it must not fall back to the old hidden-list
+    migration behavior.
+    """
+    raw = getattr(ep, "pinned_models", None)
+    return raw is not None and str(raw).strip() != ""
+
+
+def _legacy_visible_api_models(ep) -> List[str]:
+    """Return API models selected under the old hidden-list picker.
+
+    Before API endpoints switched to an explicit allow-list, selected models
+    were represented as cached_models minus hidden_models. Existing OpenRouter
+    rows can therefore have many checked models and an empty pinned_models
+    field. Treat that old state as the initial pinned list so settings and chat
+    agree after upgrade.
+    """
+    return _visible_models(
+        _cached_model_ids(ep),
+        getattr(ep, "hidden_models", None),
+        None,
+    )
+
+
+def _picker_models_for_endpoint(ep, base_url: str, kind: str):
+    """Return model IDs that should appear in the picker for an endpoint.
+
+    API providers expose remote inventory from /v1/models. Treat that cache as
+    inventory, not approval: only manually pinned API models should appear in
+    the picker. Local/self-hosted endpoints keep the older hide-list behavior.
+    """
+    pinned = _normalize_model_ids(getattr(ep, "pinned_models", None))
+    if _picker_requires_pinning(base_url, kind):
+        if not _has_explicit_pinned_models(ep):
+            pinned = _legacy_visible_api_models(ep) if _hidden_model_ids(ep) else []
+        return pinned, pinned
+    return _visible_models(
+        _cached_model_ids(ep),
+        getattr(ep, "hidden_models", None),
+        pinned,
+    ), pinned
+
+
 def _api_key_fingerprint(api_key: Optional[str]) -> str:
     """Stable, non-secret label for distinguishing same-URL credentials."""
     key = (api_key or "").strip()
@@ -1508,24 +1558,18 @@ def setup_model_routes(model_discovery):
         for ep in endpoints:
             base = _normalize_base(ep.base_url)
             provider = _safe_detect_provider(base)
-            # Merge cached + pinned models, then filter out hidden ones
             ep_model_type = getattr(ep, "model_type", None) or "llm"
-            model_ids = _visible_models(
-                _cached_model_ids(ep),
-                ep.hidden_models,
-                getattr(ep, "pinned_models", None),
-            )
             # Build correct URL based on provider
             chat_url = build_chat_url(base)
             kind = _effective_endpoint_kind(ep, base)
             category = _classify_endpoint(base, kind)
+            model_ids, pinned = _picker_models_for_endpoint(ep, base, kind)
 
             if model_ids:
                 curated_key = _match_provider_curated(base, None)
                 curated, extra = _curate_models(model_ids, curated_key)
                 # Pinned models are admin-selected — they always belong in the
                 # primary curated list, not buried in extras.
-                pinned = _normalize_model_ids(getattr(ep, "pinned_models", None))
                 for m in pinned:
                     if m not in curated:
                         curated.append(m)
@@ -1887,18 +1931,24 @@ def setup_model_routes(model_discovery):
                 _invalidate_models_cache()
             rows = db.query(ModelEndpoint).order_by(ModelEndpoint.created_at).all()
             results = []
+            upgraded_legacy_pins = False
             for r in rows:
                 all_models = _cached_model_ids(r)
                 hidden = _hidden_model_ids(r)
                 pinned = _normalize_model_ids(getattr(r, "pinned_models", None))
-                visible = _visible_models(all_models, r.hidden_models, pinned)
                 # Keep the list route cache-only. It feeds Settings →
                 # Added Models and must render immediately; explicit
                 # Refresh/Probe endpoints do the network work.
-                status = "online" if (all_models or pinned) else ("empty" if r.is_enabled else "offline")
                 ping = None
                 base = _normalize_base(r.base_url)
                 kind = _effective_endpoint_kind(r, base)
+                visible, pinned = _picker_models_for_endpoint(r, base, kind)
+                if _picker_requires_pinning(base, kind) and pinned and not _has_explicit_pinned_models(r):
+                    r.pinned_models = json.dumps(pinned)
+                    upgraded_legacy_pins = True
+                model_inventory_count = len(_merge_model_ids(all_models, pinned))
+                picker_requires_pinning = _picker_requires_pinning(base, kind)
+                status = "online" if (all_models or visible or pinned) else ("empty" if r.is_enabled else "offline")
                 results.append({
                     "id": r.id,
                     "name": r.name,
@@ -1907,6 +1957,8 @@ def setup_model_routes(model_discovery):
                     "api_key_fingerprint": _api_key_fingerprint(r.api_key),
                     "is_enabled": r.is_enabled,
                     "models": visible,
+                    "model_count": model_inventory_count,
+                    "picker_requires_pinning": picker_requires_pinning,
                     "pinned_models": pinned,
                     "hidden_count": len(hidden),
                     "online": status != "offline",
@@ -1920,6 +1972,9 @@ def setup_model_routes(model_discovery):
                     "model_refresh_interval": getattr(r, "model_refresh_interval", None),
                     "model_refresh_timeout": getattr(r, "model_refresh_timeout", None),
                 })
+            if upgraded_legacy_pins:
+                db.commit()
+                _invalidate_models_cache()
             return results
         finally:
             db.close()
@@ -2023,6 +2078,10 @@ def setup_model_routes(model_discovery):
                 if refresh_timeout is not None:
                     existing.model_refresh_timeout = refresh_timeout
                     changed = True
+                incoming_model_type = (model_type or "").strip() or "llm"
+                if incoming_model_type and (getattr(existing, "model_type", None) or "llm") != incoming_model_type:
+                    existing.model_type = incoming_model_type
+                    changed = True
                 if api_key.strip() and not existing.api_key:
                     existing.api_key = api_key.strip()
                     changed = True
@@ -2255,9 +2314,10 @@ def setup_model_routes(model_discovery):
                 raise HTTPException(404, "Endpoint not found")
             hidden = _hidden_model_ids(ep)
             all_models = _cached_model_ids(ep)
+            base = _normalize_base(ep.base_url)
+            kind = _effective_endpoint_kind(ep, base)
+            picker_requires_pinning = _picker_requires_pinning(base, kind)
             if refresh:
-                base = _normalize_base(ep.base_url)
-                kind = _effective_endpoint_kind(ep, base)
                 category = _classify_endpoint(base, kind)
                 timeout = _manual_refresh_timeout(ep, category, refresh_timeout)
                 try:
@@ -2276,6 +2336,8 @@ def setup_model_routes(model_discovery):
                     response.headers["X-Model-Refresh-Status"] = "failed"
                     response.headers["X-Model-Refresh-Warning"] = "Model refresh failed or returned no models; kept cached models."
             pinned = _normalize_model_ids(getattr(ep, "pinned_models", None))
+            if picker_requires_pinning and not _has_explicit_pinned_models(ep):
+                pinned = _legacy_visible_api_models(ep)
             pinned_set = set(pinned)
             return [
                 {
@@ -2283,6 +2345,7 @@ def setup_model_routes(model_discovery):
                     "display": m.split("/")[-1],
                     "is_hidden": m in hidden,
                     "is_pinned": m in pinned_set,
+                    "picker_requires_pinning": picker_requires_pinning,
                 }
                 for m in _merge_model_ids(all_models, pinned)
             ]
@@ -2311,11 +2374,28 @@ def setup_model_routes(model_discovery):
                 hidden = body.get("hidden")
                 if not isinstance(hidden, list):
                     raise HTTPException(400, "hidden must be a list of model IDs")
-                ep.hidden_models = json.dumps(hidden) if hidden else None
+                base = _normalize_base(ep.base_url)
+                kind = _effective_endpoint_kind(ep, base)
+                if _picker_requires_pinning(base, kind):
+                    # Compatibility for older/admin UI paths that still submit
+                    # the previous hide-list shape. API pickers are allow-lists:
+                    # convert "unchecked models" into an explicit pinned list so
+                    # Settings summary, /api/models, and chat agree.
+                    selected = _visible_models(_cached_model_ids(ep), hidden, None)
+                    ep.pinned_models = json.dumps(selected)
+                    ep.hidden_models = None
+                else:
+                    ep.hidden_models = json.dumps(hidden) if hidden else None
             # Accept either "pinned" or "pinned_models" for the manual IDs list.
             if "pinned_models" in body or "pinned" in body:
                 pinned = _normalize_model_ids(body.get("pinned_models", body.get("pinned")))
-                ep.pinned_models = json.dumps(pinned) if pinned else None
+                base = _normalize_base(ep.base_url)
+                kind = _effective_endpoint_kind(ep, base)
+                if _picker_requires_pinning(base, kind):
+                    ep.pinned_models = json.dumps(pinned)
+                    ep.hidden_models = None
+                else:
+                    ep.pinned_models = json.dumps(pinned) if pinned else None
             db.commit()
             _invalidate_models_cache()
             hidden_count = len(json.loads(ep.hidden_models)) if ep.hidden_models else 0
@@ -2468,7 +2548,13 @@ def setup_model_routes(model_discovery):
                     ep.model_type = body["model_type"].strip() or ep.model_type
                 if "pinned_models" in body:
                     _pinned = _normalize_model_ids(body["pinned_models"])
-                    ep.pinned_models = json.dumps(_pinned) if _pinned else None
+                    _base_for_pins = _normalize_base(ep.base_url)
+                    _kind_for_pins = _effective_endpoint_kind(ep, _base_for_pins)
+                    if _picker_requires_pinning(_base_for_pins, _kind_for_pins):
+                        ep.pinned_models = json.dumps(_pinned)
+                        ep.hidden_models = None
+                    else:
+                        ep.pinned_models = json.dumps(_pinned) if _pinned else None
                 if "endpoint_kind" in body:
                     ep.endpoint_kind = _normalize_endpoint_kind(body.get("endpoint_kind"))
                 if "model_refresh_mode" in body:

routes/session_routes.py

@@ -12,6 +12,7 @@ from core.models import ChatMessage
 from src.request_models import SessionResponse
 from core.database import Session as DbSession, SessionLocal, Document, GalleryImage, utcnow_naive
 from src.auth_helpers import effective_user, _auth_disabled, owner_filter
+from src.session_image_cleanup import _generated_image_path_for_cleanup, session_image_refs
 from src.session_actions import is_session_recently_active
 from src.upload_handler import reserve_message_upload_references
 
@@ -220,6 +221,7 @@ def setup_session_routes(
     @router.get("/sessions")
     def list_sessions(request: Request):
         user = effective_user(request)
+        active_incognito_id = str(request.query_params.get("active_incognito_id") or "").strip()
         # Lazy purge: incognito sessions are ephemeral by design — wipe leftovers
         # from the DB and session_manager so they vanish on the next page refresh.
         # BUT: skip sessions that were created within the last 10 minutes.
@@ -240,6 +242,8 @@ def setup_session_routes(
                     DbSession.created_at < _cutoff,
                 ).all()
                 for _g in _ghosts:
+                    if active_incognito_id and _g.id == active_incognito_id:
+                        continue
                     _purge_db.query(_DbMsg).filter(_DbMsg.session_id == _g.id).delete()
                     _purge_db.delete(_g)
                     if hasattr(session_manager, "delete_session"):
@@ -641,13 +645,43 @@ def setup_session_routes(
         db = SessionLocal()
         try:
             from core.database import ChatMessage as DbChatMessage
+            session_ids = [row[0] for row in db.query(DbSession.id).all()]
             count = db.query(DbSession).count()
+            image_ids: set[str] = set()
+            filenames: set[str] = set()
+            for sid in session_ids:
+                ids, names = session_image_refs(db, sid)
+                image_ids.update(ids)
+                filenames.update(names)
+            image_query = db.query(GalleryImage).filter(GalleryImage.session_id.in_(session_ids)) if session_ids else db.query(GalleryImage).filter(False)
+            if image_ids or filenames:
+                from sqlalchemy import or_
+                clauses = []
+                if session_ids:
+                    clauses.append(GalleryImage.session_id.in_(session_ids))
+                if image_ids:
+                    clauses.append(GalleryImage.id.in_(list(image_ids)))
+                if filenames:
+                    clauses.append(GalleryImage.filename.in_(list(filenames)))
+                image_query = db.query(GalleryImage).filter(or_(*clauses))
+            images = image_query.all()
+            removed_images = 0
+            for img in images:
+                img.is_active = False
+                if img.filename:
+                    path = _generated_image_path_for_cleanup(img.filename)
+                    if path and path.exists():
+                        try:
+                            path.unlink()
+                        except Exception as exc:
+                            logger.warning("Could not remove generated image %s during all-session delete: %s", img.filename, exc)
+                removed_images += 1
             db.query(DbChatMessage).delete()
             db.query(DbSession).delete()
             db.commit()
             session_manager.sessions.clear()
-            logger.info(f"Admin deleted all {count} sessions")
-            return {"status": "deleted", "count": count}
+            logger.info(f"Admin deleted all {count} sessions and {removed_images} linked images")
+            return {"status": "deleted", "count": count, "images_deleted": removed_images}
         except Exception as e:
             db.rollback()
             logger.error(f"Error deleting all sessions: {e}")

routes/shell_routes.py

@@ -157,6 +157,7 @@ def _package_installed_from_probe(name: str, probe: dict) -> bool:
     binaries = probe.get("binaries") if isinstance(probe.get("binaries"), dict) else {}
     dists = probe.get("dists") if isinstance(probe.get("dists"), dict) else {}
     modules = probe.get("modules") if isinstance(probe.get("modules"), dict) else {}
+    files = probe.get("files") if isinstance(probe.get("files"), dict) else {}
 
     if name == "vllm":
         return bool(binaries.get("vllm"))
@@ -166,11 +167,43 @@ def _package_installed_from_probe(name: str, probe: dict) -> bool:
         return bool(dists.get("sglang") or modules.get("sglang", {}).get("real_module"))
     if name == "mlx_lm":
         return bool(dists.get("mlx-lm") or modules.get("mlx_lm", {}).get("real_module"))
+    if name == "mflux":
+        return bool(
+            dists.get("mflux")
+            or modules.get("mflux", {}).get("real_module")
+            or binaries.get("mflux-generate-qwen")
+            or binaries.get("mflux-generate")
+        )
+    if name == "boogu_image_mlx":
+        return bool(
+            dists.get("boogu-image-mlx")
+            or modules.get("boogu_image_mlx", {}).get("real_module")
+        )
+    if name == "mlx_lama_swift":
+        return bool(
+            (binaries.get("odysseus-mlx-inpaint") or binaries.get("mlx-lama-serve"))
+            and (files.get("mlx.metallib") or files.get("default.metallib"))
+        )
+    if name == "mlx_ddcolor_swift":
+        return bool(
+            (binaries.get("odysseus-mlx-colorize") or binaries.get("mlx-ddcolor-serve"))
+            and (files.get("mlx.metallib") or files.get("default.metallib"))
+        )
     if name == "diffusers":
         return bool(
             (dists.get("diffusers") or modules.get("diffusers", {}).get("real_module"))
             and (dists.get("torch") or modules.get("torch", {}).get("real_module"))
         )
+    if name == "krea_diffusers":
+        return bool(
+            (dists.get("diffusers") or modules.get("diffusers", {}).get("real_module"))
+            and (dists.get("torch") or modules.get("torch", {}).get("real_module"))
+        )
+    if name == "sam_mask":
+        return bool(
+            (dists.get("transformers") or modules.get("transformers", {}).get("real_module"))
+            and (dists.get("torch") or modules.get("torch", {}).get("real_module"))
+        )
     if name == "hf_transfer":
         return bool(
             dists.get("hf-transfer")
@@ -183,6 +216,7 @@ def _package_status_note(name: str, probe: dict) -> str:
     binaries = probe.get("binaries") if isinstance(probe.get("binaries"), dict) else {}
     modules = probe.get("modules") if isinstance(probe.get("modules"), dict) else {}
     dists = probe.get("dists") if isinstance(probe.get("dists"), dict) else {}
+    files = probe.get("files") if isinstance(probe.get("files"), dict) else {}
     module = modules.get(name) if isinstance(modules.get(name), dict) else {}
     locations = module.get("locations") or []
     if name == "vllm":
@@ -212,10 +246,53 @@ def _package_status_note(name: str, probe: dict) -> str:
         if _package_installed_from_probe(name, probe):
             return f"diffusers {dists.get('diffusers', 'available')} with torch {dists.get('torch', 'available')}"
         return "Diffusers serving needs both diffusers and torch."
+    if name == "krea_diffusers":
+        if _package_installed_from_probe(name, probe):
+            return f"Latest Diffusers runtime: diffusers {dists.get('diffusers', 'available')} with torch {dists.get('torch', 'available')}. Use Update/Reinstall to pull latest Diffusers from Git."
+        return "Some newer image models need torch plus latest Diffusers from Git."
+    if name == "sam_mask":
+        if _package_installed_from_probe(name, probe):
+            return f"SAM object masks: transformers {dists.get('transformers', 'available')} with torch {dists.get('torch', 'available')}"
+        return "SAM click/object mask selection needs transformers and torch."
     if name == "mlx_lm":
         if _package_installed_from_probe(name, probe):
             return f"MLX LM {dists.get('mlx-lm', 'available')}"
         return "MLX serving needs mlx-lm on an Apple Silicon Mac."
+    if name == "mflux":
+        if _package_installed_from_probe(name, probe):
+            parts = []
+            if dists.get("mflux"):
+                parts.append(f"mflux {dists['mflux']}")
+            if binaries.get("mflux-generate-qwen"):
+                parts.append(f"Qwen CLI: {binaries['mflux-generate-qwen']}")
+            if binaries.get("mflux-generate"):
+                parts.append(f"Flux CLI: {binaries['mflux-generate']}")
+            return "; ".join(parts) if parts else "mflux available"
+        return "MLX image serving needs mflux on an Apple Silicon Mac."
+    if name == "boogu_image_mlx":
+        if _package_installed_from_probe(name, probe):
+            return f"Boogu MLX pipeline {dists.get('boogu-image-mlx', 'available')}"
+        return "Boogu image models need boogu-image-mlx on an Apple Silicon Mac."
+    if name == "mlx_lama_swift":
+        if _package_installed_from_probe(name, probe):
+            found = [
+                binaries.get("odysseus-mlx-inpaint"),
+                binaries.get("mlx-lama-serve"),
+            ]
+            return f"LaMa/MI-GAN Swift MLX runner: {next((p for p in found if p), 'available')}"
+        if binaries.get("odysseus-mlx-inpaint") or binaries.get("mlx-lama-serve"):
+            return "LaMa/MI-GAN Swift runner is installed, but mlx.metallib is missing next to the runner."
+        return "LaMa/MI-GAN inpainting models need an Odysseus-compatible mlx-lama-swift bridge on an Apple Silicon Mac."
+    if name == "mlx_ddcolor_swift":
+        if _package_installed_from_probe(name, probe):
+            found = [
+                binaries.get("odysseus-mlx-colorize"),
+                binaries.get("mlx-ddcolor-serve"),
+            ]
+            return f"DDColor Swift MLX runner: {next((p for p in found if p), 'available')}"
+        if binaries.get("odysseus-mlx-colorize") or binaries.get("mlx-ddcolor-serve"):
+            return "DDColor Swift runner is installed, but mlx.metallib is missing next to the runner."
+        return "DDColor colorization models need an Odysseus-compatible mlx-ddcolor-swift bridge on an Apple Silicon Mac."
     if name in dists:
         return f"{name} {dists[name]}"
     return ""
@@ -314,12 +391,22 @@ dist_names={{
     'llama_cpp':['llama-cpp-python'],
     'sglang':['sglang'],
     'mlx_lm':['mlx-lm'],
+    'mlx_vlm':['mlx-vlm'],
+    'mflux':['mflux'],
+    'boogu_image_mlx':['boogu-image-mlx'],
+    'mlx_lama_swift':[],
+    'mlx_ddcolor_swift':[],
     'diffusers':['diffusers','torch'],
+    'krea_diffusers':['diffusers','torch'],
+    'sam_mask':['transformers','torch'],
     'hf_transfer':['hf-transfer','hf_transfer'],
 }}
 bin_names={{
     'vllm':['vllm'],
     'llama_cpp':['llama-server'],
+    'mflux':['mflux-generate-qwen', 'mflux-generate'],
+    'mlx_lama_swift':['odysseus-mlx-inpaint', 'mlx-lama-serve'],
+    'mlx_ddcolor_swift':['odysseus-mlx-colorize', 'mlx-ddcolor-serve'],
     'tmux':['tmux'],
 }}
 
@@ -372,7 +459,19 @@ def probe(n):
         mods['torch'] = mod_status('torch')
     dists = dist_status(dist_names.get(n, [n]))
     bins = {{b: shutil.which(b) for b in bin_names.get(n, [])}}
-    return {{'modules': mods, 'dists': dists, 'binaries': bins}}
+    files = {{}}
+    if n in ('mlx_lama_swift', 'mlx_ddcolor_swift'):
+        for key in ('mlx.metallib', 'default.metallib'):
+            found = None
+            for b in bins.values():
+                if not b:
+                    continue
+                p = os.path.join(os.path.dirname(b), key)
+                if os.path.exists(p):
+                    found = p
+                    break
+            files[key] = found
+    return {{'modules': mods, 'dists': dists, 'binaries': bins, 'files': files}}
 
 print(json.dumps({{n: probe(n) for n in names}}))
 """
@@ -1088,6 +1187,8 @@ def setup_shell_routes() -> APIRouter:
         ssh_port: str | None = None,
         venv: str | None = None,
         backend: str | None = None,
+        platform: str | None = None,
+        model_hint: str | None = None,
     ):
         """Check which optional packages are installed.
 
@@ -1104,6 +1205,14 @@ def setup_shell_routes() -> APIRouter:
         import site
         import sys
 
+        platform_l = (platform or "").strip().lower()
+        model_hint_l = (model_hint or "").strip().lower()
+        has_krea_model = "krea" in model_hint_l
+        has_lama_mlx_model = any(
+            key in model_hint_l
+            for key in ("lama", "mi-gan", "migan", "inpainting-mlx")
+        )
+        has_ddcolor_mlx_model = "ddcolor" in model_hint_l
         _prepend_user_install_bins_to_path()
         importlib.invalidate_caches()
         try:
@@ -1158,7 +1267,7 @@ def setup_shell_routes() -> APIRouter:
                 "name": "hf_transfer",
                 "pip": "hf_transfer",
                 "desc": "Fast model downloads from HuggingFace",
-                "category": "LLM",
+                "category": "Tools",
                 "target": "remote",
             },
             {
@@ -1210,8 +1319,52 @@ def setup_shell_routes() -> APIRouter:
             # ── Image ── editor + diffusion model serving
             {
                 "name": "diffusers",
-                "pip": "diffusers[torch]",
-                "desc": "Image generation/editing pipelines (SD, Flux) with PyTorch",
+                "pip": "diffusers[torch] torchvision accelerate scipy python-multipart",
+                "desc": "Image generation/editing pipelines with PyTorch and Diffusers",
+                "category": "Image",
+                "target": "remote",
+            },
+            {
+                "name": "krea_diffusers",
+                "pip": "git+https://github.com/huggingface/diffusers.git torchvision accelerate scipy python-multipart",
+                "desc": "Latest Diffusers from Git for newly released image pipelines",
+                "category": "Image",
+                "target": "remote",
+            },
+            {
+                "name": "mflux",
+                "pip": "mflux",
+                "desc": "MLX image generation runtime for Apple Silicon models like Qwen Image",
+                "category": "Image",
+                "target": "remote",
+            },
+            {
+                "name": "boogu_image_mlx",
+                "pip": "git+https://github.com/xocialize/boogu-image-mlx.git",
+                "desc": "MLX image generation pipeline for Boogu Image models on Apple Silicon",
+                "category": "Image",
+                "target": "remote",
+            },
+            {
+                "name": "mlx_lama_swift",
+                "pip": "",
+                "desc": "Swift MLX runtime for LaMa / MI-GAN inpainting and object removal",
+                "category": "Image",
+                "target": "remote",
+                "install_hint": "Build an Odysseus-compatible mlx-lama-swift bridge on the selected Apple Silicon Mac and put odysseus-mlx-inpaint or mlx-lama-serve on PATH. Upstream currently ships Swift libraries plus smoke executables, not a stable image-edit CLI.",
+            },
+            {
+                "name": "mlx_ddcolor_swift",
+                "pip": "",
+                "desc": "Swift MLX runtime for DDColor automatic image colorization",
+                "category": "Image",
+                "target": "remote",
+                "install_hint": "Build an Odysseus-compatible mlx-ddcolor-swift bridge on the selected Apple Silicon Mac and put odysseus-mlx-colorize or mlx-ddcolor-serve on PATH. Upstream currently ships Swift libraries plus smoke executables, not a stable colorize CLI.",
+            },
+            {
+                "name": "mlx_vlm",
+                "pip": "mlx-vlm",
+                "desc": "MLX-VLM backbone used by HiDream image models on Apple Silicon",
                 "category": "Image",
                 "target": "remote",
             },
@@ -1222,6 +1375,13 @@ def setup_shell_routes() -> APIRouter:
                 "category": "Image",
                 "target": "remote",
             },
+            {
+                "name": "sam_mask",
+                "pip": "torch torchvision transformers accelerate pillow",
+                "desc": "Neutral click/box/object segmentation masks for the image editor",
+                "category": "Image",
+                "target": "local",
+            },
             {
                 "name": "rembg",
                 "pip": "rembg[gpu]",
@@ -1251,6 +1411,21 @@ def setup_shell_routes() -> APIRouter:
         for pkg in packages:
             pkg.setdefault("install_cmd", None)
             pkg.setdefault("update_cmd", None)
+        if not has_krea_model:
+            packages = [
+                p for p in packages
+                if p.get("name") not in {"krea_diffusers", "transformers"}
+            ]
+        if not has_lama_mlx_model:
+            packages = [
+                p for p in packages
+                if p.get("name") != "mlx_lama_swift"
+            ]
+        if not has_ddcolor_mlx_model:
+            packages = [
+                p for p in packages
+                if p.get("name") != "mlx_ddcolor_swift"
+            ]
         # Remote check: for remote-target packages, probe the selected server's
         # venv over SSH so a remote `pip install` actually reflects here.
         remote_status: dict = {}
@@ -1381,8 +1556,22 @@ def setup_shell_routes() -> APIRouter:
                 target_os_id = ""
             if sys.platform == "darwin":
                 target_os_id = "macos"
+        if not target_os_id and platform_l in {"darwin", "macos", "mac"}:
+            target_os_id = "macos"
 
         for pkg in packages:
+            if pkg.get("name") in {"mflux", "boogu_image_mlx", "mlx_vlm", "mlx_lama_swift", "mlx_ddcolor_swift"}:
+                is_apple_target = target_os_id == "macos" or (
+                    not host and IS_APPLE_SILICON
+                )
+                known_non_apple_target = bool(target_os_id and target_os_id != "macos") or (
+                    not host and not IS_APPLE_SILICON
+                )
+                pkg["applicable"] = is_apple_target
+                if known_non_apple_target:
+                    pkg["installed"] = None
+                    pkg["status_note"] = "Only relevant for Apple Silicon / MLX image serving."
+                    continue
             on_remote = bool(host and pkg.get("target") == "remote")
             probe = None
             if on_remote:
@@ -1588,6 +1777,10 @@ def setup_shell_routes() -> APIRouter:
             "sglang[all]",
             "diffusers",
             "diffusers[torch]",
+            "git+https://github.com/huggingface/diffusers.git",
+            "mflux",
+            "git+https://github.com/xocialize/boogu-image-mlx.git",
+            "mlx-vlm",
             "transformers",
             "TTS",
             "bark",