Merge pull request #5920 from adabarbulescu/fix/windows-workspace-access

fix(agent): use Git Bash for Windows workspace shell

core/session_manager.py

@@ -194,7 +194,12 @@ class SessionManager:
             is_important=getattr(db_session, 'is_important', False) or False,
         )
 
-        session.message_count = getattr(db_session, 'message_count', len(history))
+        # The rows just loaded are the whole transcript, so they — not the
+        # denormalized sessions.message_count column — are the truth for this
+        # cached object. get_session's hydration gate compares against this
+        # number; seeding it from a drifted column would ask for a reload that
+        # can never close the gap.
+        session.message_count = len(history)
         return session
 
     # ------------------------------------------------------------------
@@ -398,30 +403,50 @@ class SessionManager:
     # ------------------------------------------------------------------
 
     def get_session(self, session_id: str) -> Session:
-        """Get a session by ID, loading from DB if needed.
+        """Get a session by ID, loading complete DB history when needed.
 
-        Sessions seeded by `load_sessions` start with empty history. The
+        Sessions seeded by ``load_sessions`` start with empty history, and a
-        first read here hydrates them with the message rows.
+        cached session can also become partially stale. Refresh metadata first,
+        then hydrate whenever the cached transcript is short of the stored rows.
+        Model-send routes enter through this method before building context,
+        while paginated display history reads SQLite directly.
+
+        The gate compares against ``sync_session_metadata``'s reconciled count
+        (the real ``chat_messages`` total), never the denormalized column, so a
+        hydrate always closes the gap and the next read is a cache hit.
         """
         if session_id not in self.sessions:
             self._load_session_from_db(session_id)
-        else:
-            cached = self.sessions[session_id]
-            # Lazy hydrate: metadata-only entries get their messages on first read.
-            if not cached.history and getattr(cached, "message_count", 0) > 0:
-                self._load_session_from_db(session_id)
 
         # Keep model/endpoint metadata fresh. Endpoint deletion can clear the
-        # DB row while a session object is still cached in RAM.
+        # DB row while a session object is still cached in RAM. Refreshing first
+        # also exposes the authoritative message count before completeness is
+        # checked.
         self.sync_session_metadata(session_id)
 
+        cached = self.sessions[session_id]
+        cached_count = len(cached.history or [])
+        stored_count = int(getattr(cached, "message_count", 0) or 0)
+        if cached_count < stored_count:
+            self._load_session_from_db(session_id)
+
         # Update last_accessed
         self._touch_session(session_id)
 
         return self.sessions[session_id]
 
     def sync_session_metadata(self, session_id: str) -> bool:
-        """Refresh non-message session fields from the DB into the cached object."""
+        """Refresh non-message session fields from the DB into the cached object.
+
+        ``message_count`` is reconciled against the real ``chat_messages`` rows
+        rather than copied from the denormalized ``sessions.message_count``
+        column. That column drifts in normal operation — ``_persist_message``
+        swallows a failed insert but ``add_message`` has already appended in
+        memory, so the next successful persist writes rows+1, and a persist for
+        an uncached session writes 0. Hydration keys off this number: a
+        drifted-high column would reload the whole transcript on every warm
+        read, and a drifted-low one would leave the model a truncated one.
+        """
         session = self.sessions.get(session_id)
         if session is None:
             return False
@@ -444,7 +469,11 @@ class SessionManager:
             session.archived = db_session.archived
             session.owner = getattr(db_session, "owner", None)
             session.is_important = getattr(db_session, "is_important", False) or False
-            session.message_count = getattr(db_session, "message_count", session.message_count) or 0
+            session.message_count = (
+                db.query(DbChatMessage)
+                .filter(DbChatMessage.session_id == session_id)
+                .count()
+            )
             return True
         except Exception as e:
             logger.error(f"Error syncing session metadata {session_id}: {e}")

routes/email_routes.py

@@ -2861,13 +2861,22 @@ def setup_email_routes():
                 return indexed_response
             return {"emails": [], "total": 0, "error": "Mail operation failed"}
 
-    def _read_email_sync(uid, folder, account_id, owner, mark_seen=True, full=False):
+    def _read_email_sync(uid, folder, account_id, owner, mark_seen=False, full=False):
         """Sync IMAP read — wrapped in to_thread by the async handler.
 
         The normal reader path fetches the headers plus a bounded body prefix.
         That avoids downloading multi-megabyte attachments just to open a
         message. Full-message fetch remains available for flows that need
         attachment metadata immediately, such as forwarding.
+
+        `mark_seen` defaults to False because it mutates provider state: it
+        selects the mailbox read-write and issues a STORE. Only a foreground
+        open should ask for it, and it has to ask explicitly.
+
+        A failed \\Seen transition is reported as `mark_seen_failed` on an
+        otherwise normal response, never as an error. The body has already been
+        fetched at that point, so refusing to return it would turn a cosmetic
+        flag failure into an unreadable message.
         """
         import time as _t
         _t0 = _t.monotonic()
@@ -2875,9 +2884,28 @@ def setup_email_routes():
         preview_bytes = 384 * 1024
         _t_select = 0.0
         _t_fetch = 0.0
+        mark_seen_failed = False
         try:
             with _imap(account_id, owner=owner) as conn:
+                # A foreground open owns both the body fetch and the \Seen
+                # transition. Keep them on one read-write IMAP selection so the
+                # route never schedules a second connection that can race the
+                # response. Prefetch/read-only callers retain BODY.PEEK and a
+                # read-only mailbox selection.
+                try:
+                    conn.select(_q(folder), readonly=not mark_seen)
+                except Exception as select_exc:
+                    if not mark_seen:
+                        raise
+                    # Read-only mailboxes (shared archives, some provider
+                    # folders) reject a read-write SELECT. Serve the message
+                    # read-only and report the flag failure.
+                    logger.warning(
+                        f"read-write SELECT rejected for {folder!r}; "
+                        f"serving read-only without \\Seen: {select_exc}"
+                    )
                     conn.select(_q(folder), readonly=True)
+                    mark_seen_failed = True
                 _t_select = _t.monotonic() - _t0
                 fetch_query = "(BODY.PEEK[])" if full else f"(BODY.PEEK[HEADER] BODY.PEEK[TEXT]<0.{preview_bytes}>)"
                 status, msg_data = _imap_uid_fetch(conn, uid, fetch_query)
@@ -2903,6 +2931,10 @@ def setup_email_routes():
                         header_part = msg_data[0][1] or b""
                     raw = header_part + b"\r\n" + text_part
 
+                # Parse the fetched payload before mutating provider state. If
+                # the message is malformed enough that the reader cannot build
+                # a response, the caller gets an error while the message stays
+                # unread instead of receiving a false optimistic rollback.
                 msg = email_mod.message_from_bytes(raw)
 
                 subject = _decode_header(msg.get("Subject", "(no subject)"))
@@ -2919,6 +2951,24 @@ def setup_email_routes():
                 sender_name, sender_addr = email.utils.parseaddr(sender)
                 parsed_date = email.utils.parsedate_to_datetime(date_str) if date_str else None
                 attachments = _list_attachments_from_msg(msg) if full else (_email_attachment_meta_cache_get(owner, account_id, folder, uid) or [])
+
+                if mark_seen and not mark_seen_failed:
+                    seen_status, _ = conn.uid("STORE", _uid_bytes(uid), "+FLAGS", "(\\Seen)")
+                    if seen_status != "OK":
+                        # Report, don't raise. The parsed body below is still a
+                        # valid response; only the flag claim is untrue.
+                        logger.warning(
+                            f"IMAP STORE \\Seen failed for UID {uid} in {folder!r}: {seen_status}"
+                        )
+                        mark_seen_failed = True
+
+            # Only record the local flag transition when the provider actually
+            # accepted it, so the index and list cache cannot drift ahead of
+            # the mailbox.
+            if mark_seen and not mark_seen_failed:
+                _email_index_update_flags(owner, account_id, folder, uid, "\\Seen", True)
+                _update_list_cache_seen(account_id, folder, uid, True)
+
             related_attachments = []
             if full and not _has_visible_attachments(msg):
                 related_attachments = _related_thread_attachments_sync(
@@ -3039,20 +3089,29 @@ def setup_email_routes():
                 "boundaries": cached_boundaries,
                 "thread_turns": cached_turns,
                 "sender_signature": cached_sender_sig,
+                # Per-request, not part of the message: the route strips this
+                # before caching so a one-off flag failure is never replayed to
+                # later readers.
+                "mark_seen_failed": mark_seen_failed,
             }
         except Exception as e:
             logger.error(f"Failed to read email {uid}: {e}")
             return {"error": "Mail operation failed"}
 
     def _mark_email_seen_sync(uid, folder, account_id, owner):
+        """Synchronously mark a cached email seen and report success."""
         try:
             with _imap(account_id, owner=owner) as conn:
-                conn.select(_q(folder))
+                conn.select(_q(folder), readonly=False)
-                conn.uid("STORE", _uid_bytes(uid), "+FLAGS", "\\Seen")
+                status, _ = conn.uid("STORE", _uid_bytes(uid), "+FLAGS", "(\\Seen)")
+                if status != "OK":
+                    return False
             _email_index_update_flags(owner, account_id, folder, uid, "\\Seen", True)
             _update_list_cache_seen(account_id, folder, uid, True)
+            return True
         except Exception as e:
-            logger.debug(f"mark-seen after cached read failed uid={uid}: {e}")
+            logger.warning(f"mark-seen after cached read failed uid={uid}: {e}")
+            return False
 
     @router.get("/read/{uid}")
     async def read_email_by_uid(
@@ -3078,32 +3137,32 @@ def setup_email_routes():
             if cached.get("attachment_version") != EMAIL_READ_ATTACHMENT_VERSION:
                 cached = None
         if cached is not None:
-            if mark_seen:
+            # A cache hit already holds a complete, valid message. Await the
-                try:
+            # STORE so the response reports the real flag state, but never let
-                    _asyncio.create_task(_asyncio.to_thread(_mark_email_seen_sync, uid, folder, account_id, owner))
+            # a failed STORE withhold a body we are holding in memory.
-                except RuntimeError:
+            if mark_seen and not await _asyncio.to_thread(
-                    pass
+                _mark_email_seen_sync, uid, folder, account_id, owner
+            ):
+                return {**cached, "mark_seen_failed": True}
             return cached
         if not full:
             persisted = _email_preview_cache_get(owner, account_id, folder, uid)
             if persisted and persisted.get("attachment_version") == EMAIL_READ_ATTACHMENT_VERSION:
                 _read_cache_put(ck, persisted)
-                if mark_seen:
+                if mark_seen and not await _asyncio.to_thread(
-                    try:
+                    _mark_email_seen_sync, uid, folder, account_id, owner
-                        _asyncio.create_task(_asyncio.to_thread(_mark_email_seen_sync, uid, folder, account_id, owner))
+                ):
-                    except RuntimeError:
+                    return {**persisted, "mark_seen_failed": True}
-                        pass
                 return persisted
         result = await _asyncio.to_thread(_read_email_sync, uid, folder, account_id, owner, mark_seen, full)
         if result and not result.get("error"):
-            _read_cache_put(ck, result)
+            # `mark_seen_failed` describes this request, not the message, so it
+            # must not enter either cache — a later reader would otherwise be
+            # told a STORE failed that it never issued.
+            cacheable = {k: v for k, v in result.items() if k != "mark_seen_failed"}
+            _read_cache_put(ck, cacheable)
             if not full:
-                _email_preview_cache_put(owner, account_id, folder, uid, result)
+                _email_preview_cache_put(owner, account_id, folder, uid, cacheable)
-            if mark_seen:
-                try:
-                    _asyncio.create_task(_asyncio.to_thread(_mark_email_seen_sync, uid, folder, account_id, owner))
-                except RuntimeError:
-                    pass
         return result
 
     def _schedule_recent_email_warm(emails: list, folder: str, account_id: str | None, owner: str):

routes/history/history_routes.py

@@ -137,44 +137,6 @@ 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,
@@ -198,6 +160,8 @@ def setup_history_routes(session_manager, upload_handler=None) -> APIRouter:
                 )
                 page_offset = int(offset) if offset is not None else max(total - page_limit, 0)
                 page_offset = max(0, min(page_offset, total))
+                # Keep display pagination page-scoped. ``get_session`` is the
+                # full model-context hydration seam and must not be entered here.
                 rows = (
                     db.query(DbChatMessage)
                     .filter(DbChatMessage.session_id == session_id)
@@ -206,14 +170,6 @@ 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")
@@ -258,7 +214,10 @@ def setup_history_routes(session_manager, upload_handler=None) -> APIRouter:
                     entry["metadata"] = msg["metadata"]
                 history_dict.append(entry)
 
-        # Fallback: load from DB if in-memory is empty
+        # Fallback: load from DB if in-memory renders empty. Display only —
+        # get_session above is the hydration seam, so nothing here writes back
+        # into session.history — rebuilding it from raw rows would overwrite
+        # parsed multimodal content and the _db_id edit/delete keys it just set.
         if not history_dict:
             db = SessionLocal()
             try:
@@ -268,17 +227,10 @@ def setup_history_routes(session_manager, upload_handler=None) -> APIRouter:
                     .order_by(DbChatMessage.timestamp)
                     .all()
                 )
-                db_history = []
-                for m in db_messages:
-                    db_history.append(_db_history_entry(m))
-                if db_history:
-                    # Rebuild in-memory history from the full set so hidden
-                    # messages (e.g. compaction summaries) are kept for AI context.
-                    _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
+                    entry for entry in (_db_history_entry(m) for m in db_messages)
-                    if not (m.get("metadata") or {}).get("hidden")
+                    if not (entry.get("metadata") or {}).get("hidden")
                 ]
             except Exception as e:
                 logger.error(f"DB fallback failed for {session_id}: {e}")
@@ -645,8 +597,14 @@ def setup_history_routes(session_manager, upload_handler=None) -> APIRouter:
             body = await request.json()
             keep_count = body.get("keep_count", 0)
 
-            # Get the source session
+            # Get the source session. keep_count indexes into source.history,
-            source = session_manager.sessions.get(session_id)
+            # so this must go through get_session — reading the cache directly
+            # forks an empty transcript out of a metadata-only session after a
+            # restart (display pagination no longer hydrates it).
+            try:
+                source = session_manager.get_session(session_id)
+            except KeyError:
+                raise HTTPException(404, "Session not found")
             if not source:
                 raise HTTPException(404, "Session not found")
 

routes/session_routes.py

@@ -801,15 +801,6 @@ def setup_session_routes(
         finally:
             db.close()
 
-    @router.get("/history/{sid}")
-    def get_history(request: Request, sid: str):
-        _verify_session_owner(request, sid)
-        try:
-            session = session_manager.get_session(sid)
-        except KeyError:
-            raise HTTPException(404, f"Session {sid} not found")
-        return {"history": [msg.to_dict() for msg in session.history]}
-    
     @router.get("/session/{sid}/export")
     def export_session(request: Request, sid: str, fmt: str = "md", filename: str = ""):
         """Export conversation history as a downloadable file.

src/agent_tools/subprocess_tools.py

@@ -6,6 +6,7 @@ import sys
 import time
 import collections
 from typing import Optional, Callable, Awaitable, Tuple, Dict
+from core.platform_compat import IS_WINDOWS, find_bash
 from src.constants import MAX_OUTPUT_CHARS
 
 DEFAULT_BASH_TIMEOUT = 60 * 60     # 1 hour
@@ -16,6 +17,27 @@ PROGRESS_TAIL_LINES = 12
 TMUX_CAPTURE_LINES = 2000
 
 
+async def _create_bash_subprocess(command: str, **kwargs):
+    """Start the agent shell with Bash semantics on every supported OS.
+
+    ``asyncio.create_subprocess_shell`` delegates to ``cmd.exe`` on native
+    Windows.  That contradicts the Bash tool contract and makes POSIX commands
+    such as ``pwd``, ``ls -la``, and ``cat`` unreliable even when the launcher
+    has found Git Bash.  Pass the selected workspace as a structural ``cwd``
+    argument; Git Bash inherits that native Windows directory and exposes it
+    using its normal ``/c/...`` representation.
+    """
+    if IS_WINDOWS:
+        bash = find_bash()
+        if not bash:
+            raise RuntimeError(
+                "Git Bash is required for the Bash tool on Windows; "
+                "install Git for Windows and restart Odysseus"
+            )
+        return await asyncio.create_subprocess_exec(bash, "-c", command, **kwargs)
+    return await asyncio.create_subprocess_shell(command, **kwargs)
+
+
 def _tmux_session_name(session_id: Optional[str]) -> str:
     raw = re.sub(r"[^A-Za-z0-9_.-]+", "-", str(session_id or "default")).strip("-")
     return f"ody-agent-{raw[:80] or 'default'}"
@@ -280,7 +302,10 @@ class BashTool:
         progress_cb = ctx.get("progress_cb")
         _subproc_env = ctx.get("subproc_env")
         session_id = ctx.get("session_id")
-        if session_id and shutil.which("tmux"):
+        # tmux is a POSIX persistence path. A stray MSYS/Cygwin tmux.exe on
+        # native Windows must not bypass the Git Bash launcher below: the tmux
+        # setup hard-codes /bin/bash and cannot safely consume a native cwd.
+        if session_id and not IS_WINDOWS and shutil.which("tmux"):
             stdout, stderr, rc, timed_out = await _run_tmux_bash(
                 content,
                 session_id=str(session_id),
@@ -307,13 +332,16 @@ class BashTool:
                 "tmux_session": _tmux_session_name(str(session_id)),
             }
 
-        proc = await asyncio.create_subprocess_shell(
+        try:
+            proc = await _create_bash_subprocess(
                 content,
                 stdout=asyncio.subprocess.PIPE,
                 stderr=asyncio.subprocess.PIPE,
                 env=_subproc_env,
                 cwd=agent_cwd(),
             )
+        except RuntimeError as e:
+            return {"error": f"bash: {e}", "exit_code": 1}
         stdout, stderr, rc, timed_out = await _run_subprocess_streaming(
             proc,
             timeout=DEFAULT_BASH_TIMEOUT,

static/app.js

@@ -15,6 +15,12 @@ import compareModule from './js/compare/index.js?v=20260723compareicon2';
 import documentModule from './js/document.js?v=20260722emailfastindex1';
 import searchChatModule from './js/search-chat.js';
 import { makeWindowDraggable } from './js/windowDrag.js';
+import {
+  revealApplicationShellAfterPaint,
+  runDeferredRouteOpener,
+  deferRouteOpener,
+  settleSessionHydration
+} from './js/startupShell.js';
 import markdownModule from './js/markdown.js';
 import chatRenderer from './js/chatRenderer.js?v=20260722emailfastindex1';
 import sessionModule from './js/sessions.js';
@@ -1217,12 +1223,13 @@ function initializeEventListeners() {
     '/library':  () => sessionModule && sessionModule.openLibrary && sessionModule.openLibrary(),
   };
   const _opener = _routeOpen[urlPath];
-  // Defer the opener — at this point in init, the modules whose handlers
+  // Defer the opener — at this point in init, the modules whose handlers we
-  // we trigger (#rail-new-session click handler, the email-section header
+  // trigger (#rail-new-session click handler, the email-section header click
-  // click handler in emailInbox, sessionModule's loaded session list) are
+  // handler in emailInbox, sessionModule) are still being wired up further
-  // still being wired up further down in this same function. Stash the
+  // down in this same function. startupShell decides when it can run: as soon
-  // opener so it runs from sessionModule.loadSessions().finally() below.
+  // as wiring completes, or — for the routes that read the session list —
-  if (_opener) window._odysseusRouteOpener = _opener;
+  // once /api/sessions has settled.
+  deferRouteOpener(urlPath, _opener);
 
   // Archive browser tool button
   const toolLibraryBtn = el('tool-library-btn');
@@ -4315,6 +4322,10 @@ function startOdysseusApp() {
   // Load initial data
   presetsModule.loadPresets(uiModule.showError);
 
+  // Core wiring is complete for this turn — reveal the shell independently of
+  // the session-list request.
+  revealApplicationShellAfterPaint();
+
   if (sessionModule) {
     sessionModule.initDependencies({
       API_BASE: API_BASE,
@@ -4326,21 +4337,19 @@ function startOdysseusApp() {
       scrollHistory: uiModule.scrollHistoryInstant
     });
 
-    // Load sessions first (critical path) — remove loader when done
+    // sessionModule is now wired, so every route opener has the modules it
-    sessionModule.loadSessions()
+    // drives. The ones that read no session data open here rather than
-      .catch(e => console.warn('loadSessions error:', e))
+    // queueing behind /api/sessions.
-      .finally(() => {
+    runDeferredRouteOpener();
-        const loader = document.getElementById('app-loader');
+
-        if (loader) { loader.style.opacity = '0'; setTimeout(() => loader.remove(), 300); }
+    // The shell is already usable at this point; session hydration is
-        // Fire any URL route opener now that sessions + module wiring are
+    // sidebar-local and settles on its own schedule.
-        // ready. Deferred from up top of init for exactly this reason.
+    settleSessionHydration(() => sessionModule.loadSessions());
-        if (window._odysseusRouteOpener) {
-          try { window._odysseusRouteOpener(); } catch (_) {}
-          window._odysseusRouteOpener = null;
-        }
-      });
   } else {
     console.error('Session module not loaded!');
+    // Nothing will hydrate. Settle immediately so the sidebar exposes the
+    // failure; session-dependent routes must remain unopened without data.
+    settleSessionHydration(null);
   }
 
   const runNonCriticalStartup = (fn, delay = 4000) => {

static/index.html

@@ -248,8 +248,8 @@
       }, { once: true });
     })();
   </script>
-  <link rel="stylesheet" href="/static/style.css?v=20260723tasksbulkfeedback1">
+  <link rel="stylesheet" href="/static/style.css?v=20260808startupshell1">
-  <link rel="modulepreload" href="/static/app.js?v=20260723tasksbulkfeedback1">
+  <link rel="modulepreload" href="/static/app.js?v=20260808startupshell1">
   <link rel="modulepreload" href="/static/js/chat.js?v=20260801fix1">
   <link rel="modulepreload" href="/static/js/ui.js">
   <link rel="modulepreload" href="/static/js/sessions.js">
@@ -286,7 +286,13 @@
       if(!document.getElementById('app-loader')){clearInterval(iv);return}
       render();
     },150);
-    setTimeout(function(){var l=document.getElementById('app-loader');if(l){l.style.opacity='0';setTimeout(function(){l.remove()},300)}},5000);
+    // startupShell.js hides the loader as soon as the shell is wired; it calls
+    // back here to stop the wave because this interval is owned by this script.
+    window.__odysseusLoaderWaveStop=function(){clearInterval(iv)};
+    // Last-resort fallback for a boot that never reaches app.js at all. Must
+    // still REMOVE the node: sessions.js reads its presence as "startup in
+    // progress" and stops clearing the composer while it is around.
+    setTimeout(function(){var l=document.getElementById('app-loader');if(l){clearInterval(iv);l.style.opacity='0';setTimeout(function(){l.remove()},300)}},5000);
   })();
   </script>
   <!-- Memory Management Modal -->
@@ -813,7 +819,13 @@
             <button class="session-bulk-btn" id="session-bulk-cancel" title="Cancel"><svg width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2.5" stroke-linecap="round"><line x1="18" y1="6" x2="6" y2="18"/><line x1="6" y1="6" x2="18" y2="18"/></svg></button>
           </div>
         </div>
-        <div id="session-list" role="listbox"></div>
+        <div id="session-list" role="listbox">
+          <!-- Sidebar-local bootstrap state. renderSessionList() replaces the
+               whole list on first hydration, so this row is transient. -->
+          <div id="session-list-loading" class="list-item session-list-bootstrap" role="option" aria-disabled="true" aria-live="polite" aria-atomic="true">
+            <span class="grow muted" data-session-list-status>Loading chats…</span>
+          </div>
+        </div>
       </div>
       <!-- Hidden dropdown for session actions -->
       <div id="session-actions-dropdown" class="dropdown hidden">
@@ -2531,7 +2543,7 @@
 <script type="module" src="/static/js/censor.js"></script>
 <script type="module" src="/static/js/settings.js?v=20260723compareicon1"></script>
 <script type="module" src="/static/js/assistant.js"></script>
-<script type="module" src="/static/app.js?v=20260723tasksbulkfeedback1"></script>  <!-- app.js must be LAST -->
+<script type="module" src="/static/app.js?v=20260808startupshell1"></script>  <!-- app.js must be LAST -->
   <script type="module" src="/static/js/init.js?v=20260715freshroot3"></script>
 <script type="module" src="/static/js/a11y.js"></script>
 <script nonce="{{CSP_NONCE}}">if('serviceWorker' in navigator){navigator.serviceWorker.register('/static/sw.js').catch(()=>{});}</script>

static/js/MODULE_SUMMARY.md

@@ -61,6 +61,7 @@ The largest and most central subsystem. Chat submission → backend SSE → prog
 | **`chatRenderer.js`** | Message DOM construction: `addMessage`, role labels, model route labels, color coding, footers, metrics, code blocks, sources boxes (`web`/`research`/`RAG`), findings box, images, report links, ask-user cards, welcome screen, and transcript utilities. |
 | **`streamingRenderer.js`** | Incremental streaming renderer used by `chat.js`. Freezes finalized DOM blocks and only re-renders the growing tail to avoid flicker and O(N²) re-parsing. |
 | **`streamingSegmenter.js`** | Splits a token stream into display units (text vs code fences) for `streamingRenderer.js`. |
+| **`liveThinkingThrottle.js`** | Trailing-edge coalescer for the live thinking block in `chat.js`: one DOM commit per 100 ms carrying the latest reasoning text, with `flush`/`cancel` for terminal and session-switch paths. |
 | **`slashCommands.js`** | Slash-command registry (`/help`, `/setup`, etc.), parsing, and dispatch handlers. Exported functions are consumed by `chat.js` and `slashAutocomplete.js`. |
 | **`slashAutocomplete.js`** | Composer autocomplete popup for `/` commands. |
 | **`composerArrowUpRecall.js`** | Recall last user message with `↑` on an empty composer. |

static/js/emailInbox.js

@@ -149,6 +149,7 @@ let _loading = false;
 let _expanded = false;
 let _docModule = null;
 let _listSpinner = null;
+let _openEmailRequestSeq = 0;
 let _senderFilter = null;       // email address (lowercased) to filter by, or null
 let _senderFilterLabel = null;  // display label for the active filter chip
 let _showEmailTags = localStorage.getItem('odysseus.email.showTags') !== '0';
@@ -187,7 +188,7 @@ export function init(documentModule) {
       } catch (_) {}
       if (opts.compose) { _composeNew(); return; }
       if (opts.email) {
-        await _openEmail(opts.email, null, opts.emailData, opts.mode || 'reply', opts.noteHint || '');
+        await _openEmail(opts.email, null, opts.emailData, opts.mode || 'reply', opts.noteHint || '', '', opts.mailboxContext || null);
       }
     },
   });
@@ -751,7 +752,21 @@ function _createEmailItem(em) {
   return item;
 }
 
-async function _openEmail(em, itemEl, preloadedData = null, mode = 'reply', noteHint = '', prefilledBody = '') {
+async function _openEmail(em, itemEl, preloadedData = null, mode = 'reply', noteHint = '', prefilledBody = '', mailboxContext = null) {
+  const openRequestSeq = ++_openEmailRequestSeq;
+  const folderAtStart = mailboxContext?.messageFolder || _currentFolder;
+  const accountAtStart = mailboxContext?.accountId ?? (window.__odysseusActiveEmailAccount || '');
+  const accountQueryAtStart = accountAtStart ? `&account_id=${encodeURIComponent(accountAtStart)}` : '';
+  const mailboxContextIsCurrent = typeof mailboxContext?.isCurrent === 'function'
+    ? mailboxContext.isCurrent
+    : () => (
+        folderAtStart === _currentFolder &&
+        accountAtStart === (window.__odysseusActiveEmailAccount || '')
+      );
+  const isCurrentOpen = () => (
+    openRequestSeq === _openEmailRequestSeq &&
+    mailboxContextIsCurrent()
+  );
   const aiReplyMode = mode === 'ai-reply-fast' ? 'fast' : '';
   const wantsAiReply = mode === 'ai-reply' || !!aiReplyMode;
   // Body pre-fill from the agent's open_email_reply tool call takes the
@@ -780,9 +795,10 @@ async function _openEmail(em, itemEl, preloadedData = null, mode = 'reply', note
     let data = preloadedData;
     if (!data) {
       const fullQS = mode === 'forward' ? '&full=1' : '';
-      const res = await fetch(`${API_BASE}/api/email/read/${em.uid}?folder=${encodeURIComponent(_currentFolder)}${_acct()}${fullQS}`);
+      const res = await fetch(`${API_BASE}/api/email/read/${em.uid}?folder=${encodeURIComponent(folderAtStart)}${accountQueryAtStart}&mark_seen=true${fullQS}`);
       data = await res.json();
     }
+    if (!isCurrentOpen()) return;
     if (data.error) {
       console.error('Failed to read email:', data.error);
       return;
@@ -808,7 +824,7 @@ async function _openEmail(em, itemEl, preloadedData = null, mode = 'reply', note
       message_id: _fallback(data.message_id, em.message_id),
     };
     if (wantsAiReply) {
-      const activeReplyAccount = data.account_id || em.account_id || window.__odysseusActiveEmailAccount || '';
+      const activeReplyAccount = data.account_id || em.account_id || accountAtStart;
       if (data.cached_ai_reply && !noteHint && !activeReplyAccount) {
         aiSuggestedBody = _cleanAiReplyText(data.cached_ai_reply);
       } else {
@@ -834,7 +850,7 @@ async function _openEmail(em, itemEl, preloadedData = null, mode = 'reply', note
               session_id: currentSessionId,
               message_id: data.message_id || '',
               uid: String(em.uid || ''),
-              folder: _currentFolder,
+              folder: folderAtStart,
               account_id: activeReplyAccount,
               fast: true,
               user_hint: (noteHint || '').trim() || undefined,
@@ -842,6 +858,7 @@ async function _openEmail(em, itemEl, preloadedData = null, mode = 'reply', note
           });
           const result = await res.json();
           if (draftToastTimer) clearTimeout(draftToastTimer);
+          if (!isCurrentOpen()) return;
           if (result.success && result.reply) {
             aiSuggestedBody = _cleanAiReplyText(result.reply);
           } else {
@@ -855,6 +872,7 @@ async function _openEmail(em, itemEl, preloadedData = null, mode = 'reply', note
           }
         } catch (e) {
           if (draftToastTimer) clearTimeout(draftToastTimer);
+          if (!isCurrentOpen()) return;
           console.error('AI reply generation failed:', e);
           import('./ui.js').then(m => m.showError && m.showError('AI reply failed: ' + (e.message || e))).catch(() => {});
           return;
@@ -862,8 +880,12 @@ async function _openEmail(em, itemEl, preloadedData = null, mode = 'reply', note
       }
     }
 
-    em.is_read = true;
+    if (!isCurrentOpen()) return;
-    if (itemEl) itemEl.classList.remove('email-unread');
+    // Only claim the message is read when the provider accepted the \Seen
+    // transition. A failed STORE still opens the message; it just stays unread.
+    const markedSeen = !data.mark_seen_failed;
+    em.is_read = markedSeen;
+    if (itemEl) itemEl.classList.toggle('email-unread', !markedSeen);
 
     // Addresses to exclude from Reply All. Prefer the full set of configured
     // accounts (so a multi-account user's other mailboxes are excluded too),
@@ -911,7 +933,7 @@ async function _openEmail(em, itemEl, preloadedData = null, mode = 'reply', note
     if (mode !== 'forward' && data.message_id) content += `\nIn-Reply-To: ${data.message_id}`;
     if (mode !== 'forward' && data.message_id) content += `\nReferences: ${data.references ? data.references + ' ' + data.message_id : data.message_id}`;
     content += `\nX-Source-UID: ${em.uid}`;
-    content += `\nX-Source-Folder: ${_currentFolder}`;
+    content += `\nX-Source-Folder: ${folderAtStart}`;
     if (data.attachments && data.attachments.length > 0) {
       const attStr = data.attachments.map(a => `${a.index}:${a.filename}:${a.size}`).join('|');
       content += `\nX-Attachments: ${attStr}`;
@@ -980,21 +1002,27 @@ async function _openEmail(em, itemEl, preloadedData = null, mode = 'reply', note
       // and block Send on long threads.
       const reuseExisting = mode !== 'forward' && !!aiSuggestedBody;
       const existingDocId = (reuseExisting && _docModule.findEmailDocId)
-        ? _docModule.findEmailDocId(em.uid, _currentFolder)
+        ? _docModule.findEmailDocId(em.uid, folderAtStart)
         : null;
       if (existingDocId) {
         if (!_docModule.isPanelOpen()) _docModule.openPanel();
         await new Promise(r => requestAnimationFrame(() => requestAnimationFrame(r)));
+        if (!isCurrentOpen()) return;
         await _docModule.loadDocument(existingDocId);
+        if (!isCurrentOpen()) return;
         if (typeof _docModule.ensureEmailDraftEnvelope === 'function') {
           await _docModule.ensureEmailDraftEnvelope(existingDocId, content);
+          if (!isCurrentOpen()) return;
         }
         if (aiSuggestedBody && typeof _docModule.replaceEmailReplyBody === 'function') {
           await _docModule.replaceEmailReplyBody(existingDocId, aiSuggestedBody, { force: false });
+          if (!isCurrentOpen()) return;
         }
         _bringEmailReplyDraftToFrontOnMobile();
       } else {
+        if (!isCurrentOpen()) return;
         let activeSid = await _createEmailChat(data, { forceNew: true });
+        if (!isCurrentOpen()) return;
         if (!activeSid) {
           console.error('reply: could not obtain a session_id');
           import('./ui.js').then(m => m.showError && m.showError('Could not start a reply chat.')).catch(() => {});
@@ -1012,13 +1040,20 @@ async function _openEmail(em, itemEl, preloadedData = null, mode = 'reply', note
           }),
         });
         let docRes = await createReplyDoc(activeSid);
+        if (!isCurrentOpen()) return;
         if (docRes.status === 404) {
           console.warn('[reply-debug] draft session rejected; retrying in a fresh email chat', activeSid);
+          if (!isCurrentOpen()) return;
           activeSid = await _createEmailChat(data, { forceNew: true });
-          if (activeSid) docRes = await createReplyDoc(activeSid);
+          if (!isCurrentOpen()) return;
+          if (activeSid) {
+            docRes = await createReplyDoc(activeSid);
+            if (!isCurrentOpen()) return;
+          }
         }
         if (!docRes.ok) {
           const errText = await docRes.text();
+          if (!isCurrentOpen()) return;
           console.error('[reply-debug] POST /api/document failed', docRes.status, errText);
           // uiModule isn't statically imported here — use the dynamic
           // import pattern the rest of this file uses. (Previously this
@@ -1028,10 +1063,12 @@ async function _openEmail(em, itemEl, preloadedData = null, mode = 'reply', note
           return;
         }
         const doc = await docRes.json();
+        if (!isCurrentOpen()) return;
         if (doc.id) {
           const wasOpen = _docModule.isPanelOpen();
           if (!wasOpen) _docModule.openPanel();
           await new Promise(r => requestAnimationFrame(() => requestAnimationFrame(r)));
+          if (!isCurrentOpen()) return;
           // Use the doc dict from the POST directly — avoids a 404 race
           // when the GET fires before the new row is visible to the read
           // connection (or when caching is interfering). loadDocument's
@@ -1040,12 +1077,14 @@ async function _openEmail(em, itemEl, preloadedData = null, mode = 'reply', note
             _docModule.injectFreshDoc(doc);
           } else {
             await _docModule.loadDocument(doc.id);
+            if (!isCurrentOpen()) return;
           }
           _bringEmailReplyDraftToFrontOnMobile();
         }
       }
     }
   } catch (e) {
+    if (!isCurrentOpen()) return;
     console.error('Failed to open email:', e);
     // Surface the failure so a silent throw in the reply flow doesn't
     // look like "nothing happened". Dynamic import — uiModule isn't a

static/js/emailLibrary.js

@@ -30,6 +30,10 @@ import { bindMenuDismiss, dismissOrRemove } from './escMenuStack.js';
 const API_BASE = window.location.origin;
 let _emailUnreadChipClickWired = false;
 let _libLoadSeq = 0;
+let _emailMailboxGeneration = 0;
+let _emailCardOpenSeq = 0;
+let _emailReadMutationSeq = 0;
+const _emailReadMutations = new Map();
 let _libFolderSeq = 0;
 let _libSearchSeq = 0;
 let _libSearchHadResults = false;
@@ -837,14 +841,41 @@ document.addEventListener('keydown', (e) => {
   e.stopImmediatePropagation?.();
 }, true);
 
-function _syncEmailReadState(uid, isRead = true) {
+function _emailReadContextKey(context) {
+  return [context.accountId, context.folder, context.uid].map(value => String(value || '')).join('\u0000');
+}
+
+function _emailReadContextIsCurrent(context) {
+  if (!context) return true;
+  return (
+    String(state._libAccountId || '') === context.accountId &&
+    String(state._libFolder || 'INBOX') === context.libraryFolder &&
+    _emailMailboxGeneration === context.mailboxGeneration
+  );
+}
+
+function _emailMatchesReadContext(email, context) {
+  if (String(email?.uid || '') !== context.uid) return false;
+  const accountId = String(email?.account_id || context.accountId);
+  const folder = String(email?.folder || context.folder);
+  return accountId === context.accountId && folder === context.folder;
+}
+
+function _syncEmailReadState(uid, isRead = true, context = null) {
   if (uid == null) return;
   const uidStr = String(uid);
   const read = !!isRead;
-  const match = (state._libEmails || []).find(x => String(x.uid) === uidStr);
+  if (context && (!_emailReadContextIsCurrent(context) || uidStr !== context.uid)) return;
+  const match = (state._libEmails || []).find(x => (
+    context ? _emailMatchesReadContext(x, context) : String(x.uid) === uidStr
+  ));
   if (match) match.is_read = read;
 
   document.querySelectorAll('.doclib-card[data-uid="' + CSS.escape(uidStr) + '"]').forEach(card => {
+    if (context && (
+      String(card.dataset.emailAccount || '') !== context.accountId ||
+      String(card.dataset.emailFolder || '') !== context.folder
+    )) return;
     card.classList.toggle('email-card-unread', !read);
     const titleRow = card.querySelector('.email-card-titlerow');
     if (read) {
@@ -1762,11 +1793,18 @@ function _rememberedEmailAccountId() {
 // results and __scheduled__ are deliberately not cached.
 const _libListCache = new Map();
 const _LIB_CACHE_MAX = 24;
+const _LIB_INITIAL_PAGE_SIZE = 100;
 const _LIB_SESSION_CACHE_PREFIX = 'odysseus.email.list.';
 const _LIB_SESSION_CACHE_TTL_MS = 10 * 60 * 1000;
 const _LIB_LAST_ACCOUNT_KEY = 'odysseus.email.lastAccountId';
-let _libPrewarmTimer = null;
+const _LIB_PREWARM_COOLDOWN_MS = 5 * 60 * 1000;
+let _libPrewarmDelayTimer = null;
+let _libPrewarmIdleHandle = null;
 let _libPrewarmPromise = null;
+let _libPrewarmResolve = null;
+let _libPrewarmAbortController = null;
+let _libPrewarmDetachPriorityListeners = null;
+let _libPrewarmGeneration = 0;
 let _libLastPrewarmAt = 0;
 let _libUnreadPrewarmKey = '';
 let _libUnreadPrewarmAt = 0;
@@ -1908,6 +1946,7 @@ function _resetEmailListForFreshLoad({ useCache = true } = {}) {
   _exitEmailReaderModeForList();
   _resetBulkSelectionForContextChange();
   state._libOffset = 0;
+  _emailMailboxGeneration += 1;
   _libLoadSeq += 1;
   const ck = _libCacheKey();
   const cached = useCache ? _libCacheGet(ck) : null;
@@ -2076,66 +2115,244 @@ function _isChatInteractionBusy() {
   }
 }
 
-function _loadEmailsWhenChatIdle({ delay = 50, retries = 180, options = {} } = {}) {
+function _canRunEmailPrewarm() {
-  const run = () => {
+  if (state._libOpen || state._libLoading || _libSearchInFlight) return false;
-    if (!state._libOpen || !document.getElementById('email-lib-modal')) return;
+  if (document.visibilityState && document.visibilityState !== 'visible') return false;
-    if (_isChatInteractionBusy() && retries > 0) {
+  return !_isChatInteractionBusy();
-      setTimeout(() => _loadEmailsWhenChatIdle({ delay: 1000, retries: retries - 1, options }), 1000);
+}
+
+function _isEmailPrewarmTemporarilyBlocked() {
+  if (state._libOpen || state._libLoading || _libSearchInFlight) return false;
+  if (document.visibilityState && document.visibilityState !== 'visible') return false;
+  return _isChatInteractionBusy();
+}
+
+function _isEmailPrewarmCurrent(generation, signal) {
+  return generation === _libPrewarmGeneration
+    && !signal?.aborted
+    && _canRunEmailPrewarm();
+}
+
+function _settleEmailPrewarm(generation, value = false) {
+  if (generation !== _libPrewarmGeneration) return;
+  const resolve = _libPrewarmResolve;
+  const detachPriorityListeners = _libPrewarmDetachPriorityListeners;
+  _libPrewarmDelayTimer = null;
+  _libPrewarmIdleHandle = null;
+  _libPrewarmPromise = null;
+  _libPrewarmResolve = null;
+  _libPrewarmAbortController = null;
+  _libPrewarmDetachPriorityListeners = null;
+  detachPriorityListeners?.();
+  resolve?.(value);
+}
+
+function _cancelEmailPrewarm() {
+  const resolve = _libPrewarmResolve;
+  const detachPriorityListeners = _libPrewarmDetachPriorityListeners;
+  _libPrewarmGeneration += 1;
+  if (_libPrewarmDelayTimer !== null) {
+    clearTimeout(_libPrewarmDelayTimer);
+  }
+  if (_libPrewarmIdleHandle !== null && typeof window.cancelIdleCallback === 'function') {
+    try { window.cancelIdleCallback(_libPrewarmIdleHandle); } catch (_) {}
+  }
+  try { _libPrewarmAbortController?.abort(); } catch (_) {}
+  _libPrewarmDelayTimer = null;
+  _libPrewarmIdleHandle = null;
+  _libPrewarmPromise = null;
+  _libPrewarmResolve = null;
+  _libPrewarmAbortController = null;
+  _libPrewarmDetachPriorityListeners = null;
+  detachPriorityListeners?.();
+  resolve?.(false);
+}
+
+function _scheduleEmailPrewarm(task, { delay = 0 } = {}) {
+  if (_libPrewarmPromise) return _libPrewarmPromise;
+  // Do not disguise a timer as idle work. Browsers without the genuine idle
+  // callback simply skip this optional optimization and load on demand.
+  if (typeof window.requestIdleCallback !== 'function') return Promise.resolve(false);
+
+  const generation = ++_libPrewarmGeneration;
+  _libPrewarmPromise = new Promise(resolve => { _libPrewarmResolve = resolve; });
+  const promise = _libPrewarmPromise;
+  let attemptPending = false;
+  let retryRequested = false;
+
+  function clearScheduledAttempt() {
+    if (_libPrewarmDelayTimer !== null) clearTimeout(_libPrewarmDelayTimer);
+    if (_libPrewarmIdleHandle !== null && typeof window.cancelIdleCallback === 'function') {
+      try { window.cancelIdleCallback(_libPrewarmIdleHandle); } catch (_) {}
+    }
+    _libPrewarmDelayTimer = null;
+    _libPrewarmIdleHandle = null;
+  }
+
+  function scheduleIdleRetry(delay = 500) {
+    if (generation !== _libPrewarmGeneration) return;
+    retryRequested = true;
+    if (attemptPending || _libPrewarmDelayTimer !== null || _libPrewarmIdleHandle !== null) return;
+    if (document.visibilityState && document.visibilityState !== 'visible') return;
+    _libPrewarmDelayTimer = setTimeout(requestIdle, Math.max(50, Number(delay) || 500));
+  }
+
+  function handlePriorityChange() {
+    if (generation !== _libPrewarmGeneration) return;
+    if (_canRunEmailPrewarm()) {
+      scheduleIdleRetry(50);
       return;
     }
-    _loadEmails(options);
+
+    const priorityBlocked = _isChatInteractionBusy()
+      || (document.visibilityState && document.visibilityState !== 'visible');
+    if (!priorityBlocked) return;
+
+    retryRequested = true;
+    clearScheduledAttempt();
+    const controller = _libPrewarmAbortController;
+    _libPrewarmAbortController = null;
+    try { controller?.abort(); } catch (_) {}
+    // A hidden page waits for visibilitychange. Chat priority also retains the
+    // timer fallback for busy-until windows whose final transition has no event.
+    if (!document.visibilityState || document.visibilityState === 'visible') {
+      scheduleIdleRetry();
+    }
+  }
+
+  window.addEventListener('odysseus:chat-busy-change', handlePriorityChange);
+  document.addEventListener('visibilitychange', handlePriorityChange);
+  _libPrewarmDetachPriorityListeners = () => {
+    window.removeEventListener('odysseus:chat-busy-change', handlePriorityChange);
+    document.removeEventListener('visibilitychange', handlePriorityChange);
   };
-  setTimeout(run, Math.max(0, Number(delay) || 0));
+
+  function requestIdle() {
+    if (generation !== _libPrewarmGeneration) return;
+    _libPrewarmDelayTimer = null;
+    try {
+      _libPrewarmIdleHandle = window.requestIdleCallback((deadline) => {
+        if (generation !== _libPrewarmGeneration) return;
+        _libPrewarmIdleHandle = null;
+        const hasIdleBudget = Boolean(
+          deadline
+          && !deadline.didTimeout
+          && typeof deadline.timeRemaining === 'function'
+          && deadline.timeRemaining() > 0
+        );
+        if (!_canRunEmailPrewarm()) {
+          if (_isEmailPrewarmTemporarilyBlocked()) {
+            scheduleIdleRetry();
+          } else {
+            _settleEmailPrewarm(generation, false);
+          }
+          return;
+        }
+        if (!hasIdleBudget) {
+          scheduleIdleRetry();
+          return;
+        }
+        if (generation !== _libPrewarmGeneration) {
+          _settleEmailPrewarm(generation, false);
+          return;
+        }
+        const controller = new AbortController();
+        _libPrewarmAbortController = controller;
+        attemptPending = true;
+        retryRequested = false;
+        Promise.resolve()
+          .then(() => task({ signal: controller.signal, generation }))
+          .then(value => {
+            if (controller !== _libPrewarmAbortController || controller.signal.aborted) return;
+            _settleEmailPrewarm(generation, Boolean(value));
+          })
+          .catch(() => {
+            if (controller !== _libPrewarmAbortController || controller.signal.aborted) return;
+            _settleEmailPrewarm(generation, false);
+          })
+          .finally(() => {
+            attemptPending = false;
+            if (generation !== _libPrewarmGeneration) return;
+            if (retryRequested) scheduleIdleRetry();
+          });
+      });
+    } catch (_) {
+      _settleEmailPrewarm(generation, false);
+    }
+  }
+
+  const wait = Math.max(0, Number(delay) || 0);
+  if (wait > 0) _libPrewarmDelayTimer = setTimeout(requestIdle, wait);
+  else requestIdle();
+  return promise;
 }
 
 export function prewarmEmailLibrary({ delay = 2500 } = {}) {
-  if (_libPrewarmTimer || _libPrewarmPromise) return;
+  if (_libPrewarmPromise) return _libPrewarmPromise;
   const elapsed = Date.now() - _libLastPrewarmAt;
-  if (elapsed >= 0 && elapsed < 5 * 60 * 1000) return;
+  if (elapsed >= 0 && elapsed < _LIB_PREWARM_COOLDOWN_MS) return Promise.resolve(false);
-  _libPrewarmTimer = setTimeout(() => {
+  return _scheduleEmailPrewarm(_prewarmEmailViews, { delay });
-    _libPrewarmTimer = null;
-    _libPrewarmPromise = _prewarmEmailViews()
-      .catch(() => {})
-      .finally(() => { _libPrewarmPromise = null; });
-  }, Math.max(0, Number(delay) || 0));
 }
 
-async function _ensureEmailAccountsForPrewarm() {
+function _chooseEmailPrewarmAccountId(accounts) {
+  const enabled = Array.isArray(accounts) ? accounts.filter(a => a && a.enabled !== false) : [];
+  const remembered = _rememberedEmailAccountId();
+  const current = String(state._libAccountId || '').trim();
+  const chosen = enabled.find(a => String(a.id || '') === remembered)
+    || enabled.find(a => String(a.id || '') === current)
+    || enabled.find(a => a.is_default)
+    || enabled[0]
+    || null;
+  return String(chosen?.id || '').trim();
+}
+
+async function _ensureEmailAccountsForPrewarm({ signal, generation } = {}) {
+  if (!_isEmailPrewarmCurrent(generation, signal)) return null;
   const accountsFresh = _libAccountsLoadedAt && (Date.now() - _libAccountsLoadedAt) < _LIB_ACCOUNTS_TTL_MS;
-  if (Array.isArray(state._libAccounts) && state._libAccounts.length && accountsFresh) {
+  if (!(Array.isArray(state._libAccounts) && state._libAccounts.length && accountsFresh)) {
-    if (!state._libAccountId) {
-      const def = state._libAccounts.find(a => a.is_default) || state._libAccounts[0];
-      state._libAccountId = def?.id || null;
-      _publishActiveAccount();
-    }
-    return;
-  }
     try {
-    const accountsRes = await fetch(`${API_BASE}/api/email/accounts`, { credentials: 'same-origin' });
+      const accountsRes = await fetch(`${API_BASE}/api/email/accounts`, {
-    if (!accountsRes.ok) return;
+        credentials: 'same-origin',
+        signal,
+      });
+      if (!_isEmailPrewarmCurrent(generation, signal)) return null;
+      if (accountsRes.ok) {
         const accountsData = await accountsRes.json().catch(() => ({}));
+        if (!_isEmailPrewarmCurrent(generation, signal)) return null;
         if (Array.isArray(accountsData.accounts)) {
           state._libAccounts = accountsData.accounts;
           _libAccountsLoadedAt = Date.now();
-      if (!state._libAccountId && state._libAccounts.length) {
-        const def = state._libAccounts.find(a => a.is_default) || state._libAccounts[0];
-        state._libAccountId = def?.id || null;
-        _publishActiveAccount();
         }
       }
-  } catch (_) {}
+    } catch (err) {
+      if (err?.name === 'AbortError') return null;
+    }
   }
 
-export async function prewarmUnreadEmails({ limit = 8, maxUid = 0 } = {}) {
+  const accountId = _chooseEmailPrewarmAccountId(state._libAccounts);
-  if (state._libOpen) return;
+  if (!_isEmailPrewarmCurrent(generation, signal)) return null;
-  await _ensureEmailAccountsForPrewarm();
+  if (!accountId) return null;
-  if (state._libOpen) return;
+  if (accountId && state._libAccountId !== accountId) {
-  const accountId = state._libAccountId || '';
+    state._libAccountId = accountId;
+    _publishActiveAccount();
+  }
+  return accountId;
+}
+
+export function prewarmUnreadEmails({ limit = 8, maxUid = 0 } = {}) {
+  return _scheduleEmailPrewarm(
+    context => _prewarmUnreadEmailsNow({ limit, maxUid }, context),
+    { delay: 0 }
+  );
+}
+
+async function _prewarmUnreadEmailsNow({ limit = 8, maxUid = 0 } = {}, { signal, generation } = {}) {
+  if (!_isEmailPrewarmCurrent(generation, signal)) return false;
+  const accountId = await _ensureEmailAccountsForPrewarm({ signal, generation });
+  if (accountId === null || !_isEmailPrewarmCurrent(generation, signal)) return false;
   const n = Math.max(1, Math.min(20, Number(limit) || 8));
   const key = `${accountId}|${maxUid || 0}|${n}`;
-  if (_libUnreadPrewarmKey === key && (Date.now() - _libUnreadPrewarmAt) < 60 * 1000) return;
+  if (_libUnreadPrewarmKey === key && (Date.now() - _libUnreadPrewarmAt) < 60 * 1000) return true;
-  _libUnreadPrewarmKey = key;
-  _libUnreadPrewarmAt = Date.now();
   try {
     const folder = 'INBOX';
     const res = await fetch(emailApiUrl('/api/email/list', {
@@ -2144,94 +2361,73 @@ export async function prewarmUnreadEmails({ limit = 8, maxUid = 0 } = {}) {
       offset: 0,
       filter: 'unread',
       account_id: accountId || undefined,
-	    }), { credentials: 'same-origin' });
+    }), {
-	    if (state._libOpen) return;
+      credentials: 'same-origin',
-	    if (!res.ok) return;
+      signal,
+    });
+    if (!_isEmailPrewarmCurrent(generation, signal) || !res.ok) return false;
     const data = await res.json().catch(() => null);
-    if (!data || data.error || !Array.isArray(data.emails) || !data.emails.length) return;
+    if (!_isEmailPrewarmCurrent(generation, signal)) return false;
+    if (!data || data.error || !Array.isArray(data.emails) || !data.emails.length) return false;
     const sync = data.sync || {};
     _libCachePut(_libCacheKeyFor(accountId, folder, 'unread', false), {
       emails: data.emails,
       total: data.total || data.emails.length,
       sync,
     });
-  } catch (_) {}
+    _libUnreadPrewarmKey = key;
+    _libUnreadPrewarmAt = Date.now();
+    return true;
+  } catch (_) {
+    return false;
+  }
 }
 
-function _sleep(ms) {
+async function _prewarmEmailViews({ signal, generation } = {}) {
-  return new Promise(resolve => setTimeout(resolve, ms));
+  if (!_isEmailPrewarmCurrent(generation, signal)) return false;
-}
-
-async function _prewarmEmailViews() {
-  if (state._libOpen) return;
-  _libLastPrewarmAt = Date.now();
   _setEmailSyncStatus({ warming: true });
   const folder = 'INBOX';
   const filter = 'all';
-
-  // The accounts request is cheap and warms the account strip for first open.
-  // Then folder/list requests warm both the client cache and the backend
-  // IMAP/read caches. Failure stays silent: no configured mail should not nag.
   try {
-    const accountsRes = await fetch(`${API_BASE}/api/email/accounts`, { credentials: 'same-origin' });
+    const accountId = await _ensureEmailAccountsForPrewarm({ signal, generation });
-    if (accountsRes.ok) {
+    if (accountId === null || !_isEmailPrewarmCurrent(generation, signal)) return false;
-      const accountsData = await accountsRes.json().catch(() => ({}));
-      if (Array.isArray(accountsData.accounts)) {
-        state._libAccounts = accountsData.accounts;
-        _libAccountsLoadedAt = Date.now();
-      }
-    }
-  } catch (_) {}
-
-  const accounts = Array.isArray(state._libAccounts) ? state._libAccounts.filter(a => a && a.enabled !== false) : [];
-  const preferred = state._libAccountId
-    || (accounts.find(a => a.is_default)?.id)
-    || (accounts[0]?.id)
-    || '';
-  if (!state._libAccountId && preferred) {
-    state._libAccountId = preferred;
-    _publishActiveAccount();
-  }
-  const orderedAccountIds = [
-    preferred,
-    ...accounts.map(a => a.id).filter(id => id && id !== preferred),
-  ].filter((id, idx, arr) => arr.indexOf(id) === idx);
-  if (!orderedAccountIds.length) orderedAccountIds.push('');
-
-  try {
-    for (const accountId of orderedAccountIds.slice(0, 4)) {
-      if (state._libOpen) return;
     const ck = _libCacheKeyFor(accountId, folder, filter, false);
-      if (_libCacheGet(ck)) continue;
+    if (_libCacheGet(ck)) {
-      await fetch(emailApiUrl('/api/email/folders', { account_id: accountId || undefined }), { credentials: 'same-origin' }).catch(() => null);
+      _libLastPrewarmAt = Date.now();
-      await fetch(emailApiUrl('/api/email/unread-state', { folder, account_id: accountId || undefined }), { credentials: 'same-origin' }).catch(() => null);
+      return true;
+    }
+
+    // One optional first-page request only. Folder metadata, unread state, and
+    // other accounts remain demand-driven so startup cannot fan out into IMAP.
     const res = await fetch(emailApiUrl('/api/email/list', {
       folder,
-        limit: 100,
+      limit: _LIB_INITIAL_PAGE_SIZE,
       offset: 0,
       filter,
       account_id: accountId || undefined,
     }), {
       credentials: 'same-origin',
+      signal,
     });
-      if (res.ok) {
+    if (!_isEmailPrewarmCurrent(generation, signal) || !res.ok) return false;
     const data = await res.json().catch(() => null);
-        if (data && !data.error) {
+    if (!_isEmailPrewarmCurrent(generation, signal)) return false;
+    if (!data || data.error || !Array.isArray(data.emails)) return false;
     const sync = data.sync || {};
     _libCachePut(ck, {
-            emails: data.emails || [],
+      emails: data.emails,
       total: data.total || 0,
       sync,
     });
+    _libLastPrewarmAt = Date.now();
     _setEmailSyncStatus({
       updatedAt: sync.updated_at || new Date().toISOString(),
       source: sync.source || '',
       warming: true,
     });
-        }
+    return true;
-      }
+  } catch (_) {
-      await _sleep(900);
+    return false;
-    }
   } finally {
     _setEmailSyncStatus({ warming: false });
   }
@@ -2286,16 +2482,34 @@ function _publishActiveAccount() {
 
 export function initEmailLibrary(config) {
   state._docModule = config.documentModule;
-  state._onEmailClick = config.onEmailClick;
+  const onEmailClick = config.onEmailClick;
+  state._onEmailClick = typeof onEmailClick === 'function' ? (options = {}) => {
+    const accountId = String(state._libAccountId || '');
+    const libraryFolder = String(state._libFolder || 'INBOX');
+    const messageFolder = String(options.email?.folder || libraryFolder);
+    const mailboxGeneration = _emailMailboxGeneration;
+    const mailboxContext = Object.freeze({
+      accountId,
+      libraryFolder,
+      messageFolder,
+      mailboxGeneration,
+      isCurrent: () => (
+        String(state._libAccountId || '') === accountId &&
+        String(state._libFolder || 'INBOX') === libraryFolder &&
+        _emailMailboxGeneration === mailboxGeneration
+      ),
+    });
+    return onEmailClick({ ...options, mailboxContext });
+  } : null;
 }
 
 export function isOpen() { return state._libOpen; }
 
 export function openEmailLibrary(opts = {}) {
-  if (_libPrewarmTimer) {
+  // Foreground email always wins: cancel a delayed/idle callback and abort the
-    clearTimeout(_libPrewarmTimer);
+  // one optional request if it has already started. Generation checks make a
-    _libPrewarmTimer = null;
+  // non-abortable response harmless if it races this transition.
-  }
+  _cancelEmailPrewarm();
   // Force-clean any stale state from previous attempts
   const existing = document.getElementById('email-lib-modal');
   if (existing) existing.remove();
@@ -2303,6 +2517,7 @@ export function openEmailLibrary(opts = {}) {
     document.removeEventListener('keydown', state._libEscHandler, true);
     state._libEscHandler = null;
   }
+  _emailMailboxGeneration += 1;
   state._libOpen = true;
   // On mobile the sidebar overlays content — close it so the email view isn't
   // opened behind it (same pattern as session-switch/delete).
@@ -2926,7 +3141,7 @@ export function openEmailLibrary(opts = {}) {
   }
   const fastAccountAtOpen = state._libAccountId || '';
   if (fastAccountAtOpen) {
-    _loadEmailsWhenChatIdle({ delay: 0 });
+    _loadEmails({ useCache: true });
   }
   // If we already know the previous/default account, paint that inbox first
   // from the durable index and validate accounts in parallel. Cold refreshes
@@ -2936,7 +3151,7 @@ export function openEmailLibrary(opts = {}) {
     _loadFolders();
     _loadEmailReminderBellVisibility();
     if (!fastAccountAtOpen || fastAccountAtOpen !== (state._libAccountId || '')) {
-      _loadEmailsWhenChatIdle();
+      _loadEmails({ useCache: true });
     }
   })();
 }
@@ -3121,6 +3336,7 @@ export async function openEmailLibrarySettings() {
 }
 
 export function closeEmailLibrary() {
+  _cancelEmailPrewarm();
   const modal = document.getElementById('email-lib-modal');
   if (modal) modal.remove();
   if (_libSyncTicker) {
@@ -4554,7 +4770,7 @@ async function _loadEmails({ force = false, useCache = true } = {}) {
         const ctrl = new AbortController();
         const timer = setTimeout(() => ctrl.abort(), 450);
         try {
-          const fastRes = await fetch(`${API_BASE}/api/email/list?folder=${encodeURIComponent(folderAtStart)}${accountQS}&limit=100&offset=${offsetAtStart}&filter=${filterAtStart}${attQS}&cached_only=1`, {
+          const fastRes = await fetch(`${API_BASE}/api/email/list?folder=${encodeURIComponent(folderAtStart)}${accountQS}&limit=${_LIB_INITIAL_PAGE_SIZE}&offset=${offsetAtStart}&filter=${filterAtStart}${attQS}&cached_only=1`, {
             signal: ctrl.signal,
           });
           const fastData = await fastRes.json().catch(() => null);
@@ -4581,7 +4797,7 @@ async function _loadEmails({ force = false, useCache = true } = {}) {
       // opens omit it so rapid close/reopen returns instantly; the
       // Refresh button passes `force: true` to add it back.
       const buster = force ? `&_=${Date.now()}` : '';
-      const res = await fetch(`${API_BASE}/api/email/list?folder=${encodeURIComponent(folderAtStart)}${accountQS}&limit=100&offset=${offsetAtStart}&filter=${filterAtStart}${attQS}${buster}`);
+      const res = await fetch(`${API_BASE}/api/email/list?folder=${encodeURIComponent(folderAtStart)}${accountQS}&limit=${_LIB_INITIAL_PAGE_SIZE}&offset=${offsetAtStart}&filter=${filterAtStart}${attQS}${buster}`);
       const data = await res.json();
       if (seq !== _libLoadSeq || accountAtStart !== (state._libAccountId || '')) return;
       if (data.error) throw new Error(data.error);
@@ -4836,6 +5052,8 @@ function _createCard(em) {
   else if (!em.is_read) cls += ' email-card-unread';
   card.className = cls;
   card.dataset.uid = String(em.uid);
+  card.dataset.emailAccount = String(em.account_id || state._libAccountId || '');
+  card.dataset.emailFolder = String(em.folder || state._libFolder || 'INBOX');
   if (state._selectMode && state._selectedUids.has(em.uid)) card.classList.add('selected');
 
   // Checkbox in select mode
@@ -5162,6 +5380,25 @@ async function _toggleCardPreview(card, em) {
   // currently-selected folder for normal inbox cards.
   const folderAtStart = (em && em.folder) || libraryFolderAtStart;
   const uidAtStart = String(em?.uid || card?.dataset?.uid || '');
+  const wasReadAtStart = !!em?.is_read;
+  const openGeneration = ++_emailCardOpenSeq;
+  const readContext = Object.freeze({
+    accountId: String(accountAtStart),
+    libraryFolder: String(libraryFolderAtStart),
+    folder: String(folderAtStart),
+    uid: uidAtStart,
+    mailboxGeneration: _emailMailboxGeneration,
+  });
+  const readContextKey = _emailReadContextKey(readContext);
+  const isCurrentOpen = () => (
+    openGeneration === _emailCardOpenSeq &&
+    _emailReadContextIsCurrent(readContext) &&
+    accountAtStart === (state._libAccountId || '') &&
+    libraryFolderAtStart === (state._libFolder || 'INBOX') &&
+    uidAtStart === String(card?.dataset?.uid || '') &&
+    card.isConnected &&
+    card.classList.contains('email-card-expanded')
+  );
   const grid = card.closest('.doclib-grid');
   const gridRect = grid?.getBoundingClientRect?.();
   const modal = document.getElementById('email-lib-modal');
@@ -5186,6 +5423,30 @@ async function _toggleCardPreview(card, em) {
     return;
   }
 
+  // Every authoritative open supersedes any older optimistic mutation for the
+  // same immutable mailbox identity. Carry the original unread state forward
+  // so a close/reopen followed by failure still rolls back exactly once, while
+  // a late failure from the superseded request cannot undo a newer success.
+  const previousMutation = _emailReadMutations.get(readContextKey);
+  const readMutation = {
+    generation: ++_emailReadMutationSeq,
+    rollbackUnread: !wasReadAtStart || !!previousMutation?.rollbackUnread,
+  };
+  _emailReadMutations.set(readContextKey, readMutation);
+  const restoreUnreadState = () => {
+    if (_emailReadMutations.get(readContextKey)?.generation !== readMutation.generation) return;
+    _emailReadMutations.delete(readContextKey);
+    if (readMutation.rollbackUnread) _syncEmailReadState(uidAtStart, false, readContext);
+  };
+  const commitReadState = () => {
+    // A successful STORE/mark_seen is authoritative for this immutable
+    // mailbox identity even when a newer open is still pending. Retire that
+    // newer rollback token too, otherwise its later failure could restore an
+    // unread state that no longer exists at the provider.
+    _emailReadMutations.delete(readContextKey);
+    _syncEmailReadState(uidAtStart, true, readContext);
+  };
+
   // Collapse any other expanded card
   if (grid) {
     grid.querySelectorAll('.email-card-expanded').forEach(c => {
@@ -5207,10 +5468,10 @@ async function _toggleCardPreview(card, em) {
   requestAnimationFrame(() => {
     try { card.scrollIntoView({ behavior: 'smooth', block: 'start' }); } catch (_) {}
   });
-  if (!em.is_read) {
+  if (!wasReadAtStart) {
-    _syncEmailReadState(em.uid, true);
+    // Keep the current optimistic visual update, but let the read request below
-    fetch(`${API_BASE}/api/email/mark-read/${em.uid}?folder=${encodeURIComponent(folderAtStart)}${_acct()}`, { method: 'POST' })
+    // own the provider-side \Seen transition. A failure restores unread state.
-      .catch(err => console.error('Failed to mark email read:', err));
+    _syncEmailReadState(uidAtStart, true, readContext);
   }
   // Class hook on the modal so the header-hide / padding rules work on
   // browsers without :has() support (Firefox mobile) — the :has() versions
@@ -5239,25 +5500,28 @@ async function _toggleCardPreview(card, em) {
     } catch (_) {}
   };
 
+  let authoritativeReadSucceeded = false;
   try {
-    const res = await fetch(`${API_BASE}/api/email/read/${em.uid}?folder=${encodeURIComponent(folderAtStart)}${_acct()}`);
+    const accountQueryAtStart = accountAtStart ? `&account_id=${encodeURIComponent(accountAtStart)}` : '';
+    const res = await fetch(`${API_BASE}/api/email/read/${encodeURIComponent(uidAtStart)}?folder=${encodeURIComponent(folderAtStart)}${accountQueryAtStart}&mark_seen=true`);
     if (!res.ok) throw new Error(`HTTP ${res.status}`);
     const data = await res.json();
-    if (
-      accountAtStart !== (state._libAccountId || '') ||
-      libraryFolderAtStart !== (state._libFolder || 'INBOX') ||
-      uidAtStart !== String(card?.dataset?.uid || '') ||
-      !card.isConnected ||
-      !card.classList.contains('email-card-expanded')
-    ) {
-      return;
-    }
     if (data.error) {
-      showFailedReader(`Failed to load email: ${data.error}`);
+      restoreUnreadState();
+      if (isCurrentOpen()) showFailedReader(`Failed to load email: ${data.error}`);
       return;
     }
-    // Mark as read locally
+    if (data.mark_seen_failed) {
-    _syncEmailReadState(em.uid, true);
+      // The body is authoritative even when the provider refused the \Seen
+      // transition. Render the message and roll the unread marker back so the
+      // list keeps telling the truth, rather than refusing to open a message
+      // we successfully read.
+      restoreUnreadState();
+    } else {
+      authoritativeReadSucceeded = true;
+      commitReadState();
+    }
+    if (!isCurrentOpen()) return;
     _stampReaderContext(reader, { ...em, ...data }, state._libFolder, state._libAccountId);
 
     // Build the attachments wrap using the shared helper so the signature-
@@ -5439,9 +5703,12 @@ async function _toggleCardPreview(card, em) {
     // Always stop bubbling so the card's click doesn't fire while reading.
     reader.addEventListener('click', (ev) => { ev.stopPropagation(); });
   } catch (e) {
+    if (!authoritativeReadSucceeded) restoreUnreadState();
+    if (isCurrentOpen()) {
       showFailedReader(e?.message ? `Failed to load email: ${e.message}` : 'Failed to load email');
     }
   }
+}
 
 /**
  * Wrap a probable signature block in a collapsed <details> so it stops

static/js/liveThinkingThrottle.js

@@ -0,0 +1,206 @@
+// liveThinkingThrottle.js
+//
+// Pure trailing-edge coalescer for the live "thinking" block in chat.js.
+//
+// A reasoning stream delivers deltas far faster than a human can read them, and
+// the only thing that matters on screen is the LATEST cumulative text. Committing
+// every delta to the DOM makes the work grow with the length of the stream. This
+// throttle collapses a burst of updates into one commit per `delay` ms, always
+// carrying the most recent value.
+//
+// Timers are injected so the behaviour is testable without a browser or a clock:
+//
+//     const throttle = createLiveThinkingThrottle(commit, { prepare, schedule, cancel });
+//
+// Lifecycle contract, which the terminal paths in chat.js depend on:
+//
+//   update(value)  queue `value`; schedule a commit if one is not already pending
+//   flush()        commit any pending value NOW and drop the timer; returns whether
+//                  a commit happened, so a clean flush cannot duplicate a commit
+//   cancel()       drop the timer AND the pending value — nothing lands later
+//
+// `cancel()` is what stops a finished (or backgrounded) stream from mutating a
+// view the user has since navigated away to.
+
+export function stripLiveThinkingTags(text) {
+  return String(text ?? '').replace(
+    /<\/?(?:think(?:ing)?|thought)(?:\s+[^>]*)?>/gi,
+    '',
+  );
+}
+
+const THINKING_BOUNDARY_RE = /<\/?(?:(?:mm:)?think(?:ing)?|thought)(?:\s+[^>]*)?>|<\|channel>(?:thought|response)|<channel\|>/gi;
+const REPLY_PREFIX_SOURCE = "(?:Hey|Hi |Hi!|Hello|Sure|Yes|No |No,|Yo|OK|Here|Absolutely|Of course|Great|Alright|Thanks|Welcome|Good |I'm happy|I'd be)";
+const REPLY_LINE_RE = new RegExp('(?:^|\\n)\\s*' + REPLY_PREFIX_SOURCE, 'gi');
+const REPLY_INLINE_RE = new RegExp('[.!?]\\s*' + REPLY_PREFIX_SOURCE, 'gi');
+const REASONING_PREFIX_CANDIDATES = [
+  'thinking:', 'thinking process:', 'the user ', 'user wants', 'we need ',
+  'i need ', 'i should ', 'i will ', "i'll ", 'i am going ', 'let me think',
+  'let me look', 'let me see', 'let me check', 'let me read', 'let me review',
+  'let me analyze', 'let me parse', 'let me figure', 'let me draft', 'let me write',
+  'they are ', 'the question ', 'i can ',
+];
+
+const DISPLAY_FILTER_BOUNDARY_RE = /\[\/?TOOL_CALL\]|```(?:create_document|documen(?:t)?)(?:\s|$)|```[\w-]+[ \t]*[\[{]|<(?:[\w]+:)?(?:tool_call|function_call)>|<invoke\b|<\s*\/?\s*[｜|]+\s*DSML\s*[｜|]+|(?:\[\s*)?\{\s*"function"\s*:|<\/?\|(?:assistant|assistan|user|system|tool|end)\|?>|(?:^|[\r\n])\s*(?:stdout|stderr|exit_code):/i;
+
+function hasFreshMatch(text, regex, cursor, minStart = 0) {
+  regex.lastIndex = 0;
+  for (const match of text.matchAll(regex)) {
+    const end = match.index + match[0].length;
+    if (end > cursor && match.index >= minStart) return true;
+  }
+  return false;
+}
+
+// Incrementally decides when chat.js needs its compatibility-heavy cumulative
+// thinking analysis. The gate inspects only a short overlap plus the new text;
+// ordinary answer/reasoning deltas therefore stay O(delta) while split tags,
+// namespaced tags, non-tag reply boundaries, and false-close grace deadlines
+// still request the canonical full analysis.
+export function createThinkingAnalysisGate({
+  startsWithReasoningPrefix = () => false,
+  now = () => Date.now(),
+  overlap = 512,
+} = {}) {
+  let cursor = 0;
+  let prefixSettled = false;
+  let prefixProbe = '';
+
+  return {
+    shouldAnalyze(text, {
+      isThinking = false,
+      nonTagThinking = false,
+      recheckAt = 0,
+    } = {}) {
+      const fullText = String(text ?? '');
+      if (fullText.length < cursor) {
+        cursor = 0;
+        prefixSettled = false;
+        prefixProbe = '';
+      }
+      const previousCursor = cursor;
+      if (!prefixSettled && prefixProbe.length < overlap) {
+        // Build the initial probe from deltas so arbitrary leading whitespace
+        // cannot strand the gate in its undecided state. The retained state is
+        // bounded even if a provider emits a very large whitespace prefix.
+        prefixProbe = (prefixProbe + fullText.slice(previousCursor))
+          .trimStart()
+          .slice(0, overlap);
+      }
+      const scanStart = Math.max(0, previousCursor - overlap);
+      const freshText = fullText.slice(scanStart);
+      const relativeCursor = previousCursor - scanStart;
+      const hasBoundary = hasFreshMatch(freshText, THINKING_BOUNDARY_RE, relativeCursor);
+      const hasReplyBoundary = nonTagThinking && (
+        hasFreshMatch(freshText, REPLY_LINE_RE, relativeCursor)
+        || hasFreshMatch(freshText, REPLY_INLINE_RE, relativeCursor, Math.max(0, 20 - scanStart))
+      );
+      cursor = fullText.length;
+
+      if (hasBoundary || hasReplyBoundary) return true;
+      if (isThinking) return recheckAt > 0 && now() >= recheckAt;
+      if (prefixSettled) return false;
+
+      if (!prefixProbe) return false;
+      if (startsWithReasoningPrefix(prefixProbe)) {
+        prefixSettled = true;
+        return true;
+      }
+      const lowerProbe = prefixProbe.toLowerCase();
+      if (REASONING_PREFIX_CANDIDATES.some((candidate) => candidate.startsWith(lowerProbe))) {
+        return false;
+      }
+      prefixSettled = true;
+      return false;
+    },
+    reset() {
+      cursor = 0;
+      prefixSettled = false;
+      prefixProbe = '';
+    },
+  };
+}
+
+// Keep the common prose path append-only. At the first structured/tool
+// boundary, filter only the preceding visible prefix and hide the structured
+// tail until the authoritative terminal render.
+export function createIncrementalDisplayProjector(filter, { overlap = 512 } = {}) {
+  let projected = '';
+  let boundaryTail = '';
+  let rawLength = 0;
+  let structuredTailHidden = false;
+
+  return {
+    append(delta, fullText) {
+      const chunk = String(delta ?? '');
+      const raw = String(fullText ?? '');
+      if (raw.length < rawLength) this.reset();
+      const boundaryProbe = boundaryTail + chunk;
+      const boundaryMatch = !structuredTailHidden
+        ? DISPLAY_FILTER_BOUNDARY_RE.exec(boundaryProbe)
+        : null;
+      if (boundaryMatch) {
+        // Filter the visible prefix, not the incomplete marker itself: several
+        // compatibility regexes intentionally match only completed blocks.
+        const boundaryStart = Math.max(0, raw.length - boundaryProbe.length + boundaryMatch.index);
+        structuredTailHidden = true;
+        projected = String(filter(raw.slice(0, boundaryStart)) ?? '');
+      } else if (!structuredTailHidden) {
+        projected += chunk;
+      }
+      boundaryTail = (boundaryTail + chunk).slice(-overlap);
+      rawLength = raw.length;
+      return projected;
+    },
+    current() {
+      return projected;
+    },
+    reset() {
+      projected = '';
+      boundaryTail = '';
+      rawLength = 0;
+      structuredTailHidden = false;
+    },
+  };
+}
+
+export function createLiveThinkingThrottle(commit, {
+  delay = 100,
+  prepare = (value) => String(value ?? ''),
+  schedule = (callback, ms) => setTimeout(callback, ms),
+  cancel = (timer) => clearTimeout(timer),
+} = {}) {
+  let timer = null;
+  let latest = null;
+  let dirty = false;
+
+  const commitLatest = () => {
+    timer = null;
+    if (!dirty) return false;
+    dirty = false;
+    commit(prepare(latest));
+    return true;
+  };
+
+  return {
+    update(value) {
+      latest = value;
+      dirty = true;
+      if (timer === null) timer = schedule(commitLatest, delay);
+    },
+    flush() {
+      if (timer !== null) {
+        cancel(timer);
+        timer = null;
+      }
+      return commitLatest();
+    },
+    cancel() {
+      if (timer !== null) cancel(timer);
+      timer = null;
+      dirty = false;
+    },
+  };
+}
+
+export default createLiveThinkingThrottle;

static/js/sessions.js

@@ -1683,8 +1683,21 @@ export async function loadSessions() {
         url += `?active_incognito_id=${encodeURIComponent(currentSessionId)}`;
       }
       const res = await fetch(url);
+      if (!res.ok) {
+        let detail = '';
+        try {
+          const payload = await res.json();
+          detail = payload?.detail || payload?.error || '';
+        } catch (_) {}
+        const error = new Error(detail || `Session request failed (HTTP ${res.status})`);
+        error.status = res.status;
+        throw error;
+      }
       fetched = await res.json();
     }
+    if (!Array.isArray(fetched)) {
+      throw new Error('Session request returned an invalid response');
+    }
     sessions = _normalizeSessionsList(fetched);
     renderSessionList();
 
@@ -1807,10 +1820,16 @@ export async function loadSessions() {
         _autoCreateInProgress = false;
       }
     }
+    return true;
   } catch (error) {
     console.error('Error in loadSessions:', error);
+    // app.js's global fetch wrapper owns expired-auth navigation. Avoid
+    // flashing a redundant session error while that 401 redirect is pending.
+    if (error?.status !== 401) {
       uiModule.showError('Failed to load sessions: ' + error.message);
     }
+    return false;
+  }
 }
 
 export async function selectSession(id, { keepSidebar = false, showLoading = true, immediateLoading = false } = {}) {

static/js/startupShell.js

@@ -0,0 +1,153 @@
+// Odysseus UI — startup shell sequencing
+// ES6 module — no application dependencies, DOM only.
+//
+// Revealing the application shell, retiring the boot loader, settling the
+// sidebar's own loading state, and firing a deferred URL route are separate
+// startup concerns that used to sit inline in app.js behind a single promise.
+// They live here so each step has one owner and so the whole contract can be
+// exercised directly (tests/test_startup_shell_js.py) without booting the app.
+
+const LOADER_ID = 'app-loader';
+const SESSION_BOOTSTRAP_ROW_ID = 'session-list-loading';
+
+// Route openers that read the hydrated session list. Everything else only
+// needs module wiring and must not wait on /api/sessions. `/email` spawns a
+// fresh chat, and that path falls back to the most recent session's model
+// (_createDirectChatFromPreferredModel in app.js) when there is no default
+// chat configured, so it genuinely needs the list.
+const ROUTES_NEEDING_SESSIONS = new Set(['/email']);
+
+let _routeOpener = null;
+let _routeOpenerNeedsSessions = false;
+
+function _loader() {
+  return document.getElementById(LOADER_ID);
+}
+
+/** Run `fn` after the next paint has committed (two animation frames). */
+export function afterNextPaint(fn) {
+  requestAnimationFrame(() => requestAnimationFrame(fn));
+}
+
+// The loader node stays in the DOM while sessions hydrate — sidebar-layout.js
+// and sessions.js both read its presence as a "still starting up" sentinel —
+// but it must stop covering, announcing, and animating over a usable shell.
+function _makeLoaderInert(loader) {
+  if (!loader || loader.dataset.shellRevealed === 'true') return;
+  loader.dataset.shellRevealed = 'true';
+  loader.setAttribute('aria-hidden', 'true');
+  loader.style.pointerEvents = 'none';
+  loader.style.opacity = '0';
+  // index.html's inline bootstrap animates the wave on a 150ms interval.
+  // Nothing of it is visible any more, so stop rendering into it.
+  try { window.__odysseusLoaderWaveStop?.(); } catch (_) {}
+}
+
+/**
+ * Hand the shell to the user once core wiring is done. Deferred by one paint
+ * so the first frame lands with the app already laid out.
+ */
+export function revealApplicationShellAfterPaint() {
+  const loader = _loader();
+  if (!loader || loader.dataset.shellRevealScheduled === 'true') return;
+  loader.dataset.shellRevealScheduled = 'true';
+  afterNextPaint(() => _makeLoaderInert(_loader()));
+}
+
+/** Retire the loader node for good. Safe to call after a reveal. */
+export function removeApplicationLoader() {
+  const loader = _loader();
+  if (!loader) return;
+  _makeLoaderInert(loader);
+  setTimeout(() => loader.remove(), 300);
+}
+
+/**
+ * Turn the sidebar's bootstrap row into a failure row. The write is delayed
+ * until the session renderer's frame has committed so a late success cannot
+ * leave stale failure text behind.
+ */
+export function markSessionListUnavailableIfStillBootstrapping() {
+  afterNextPaint(() => {
+    const row = document.getElementById(SESSION_BOOTSTRAP_ROW_ID);
+    if (!row) return;
+    const status = row.querySelector('[data-session-list-status]') || row;
+    status.textContent = 'Chats unavailable';
+  });
+}
+
+/** True when `path`'s route opener reads the hydrated session list. */
+export function routeNeedsSessionData(path) {
+  return ROUTES_NEEDING_SESSIONS.has(path);
+}
+
+/**
+ * Stash a URL route opener for later. At the point app.js resolves the route,
+ * the modules its handlers drive (the rail new-chat handler, the email
+ * section header handler, sessionModule) are still being wired further down
+ * the same init pass, so the opener cannot run inline.
+ */
+export function deferRouteOpener(path, opener) {
+  if (!opener) return;
+  _routeOpener = opener;
+  _routeOpenerNeedsSessions = routeNeedsSessionData(path);
+}
+
+/**
+ * Fire the deferred route opener if its data is ready. Called once when
+ * wiring completes and again after authoritative session hydration; a route
+ * that needs no session data takes the first call, one that does takes the
+ * second.
+ *
+ * @returns {boolean} whether an opener ran.
+ */
+export function runDeferredRouteOpener({ sessionsSettled = false } = {}) {
+  if (!_routeOpener) return false;
+  if (_routeOpenerNeedsSessions && !sessionsSettled) return false;
+  const opener = _routeOpener;
+  _routeOpener = null;
+  _routeOpenerNeedsSessions = false;
+  try { opener(); } catch (e) { console.warn('route opener failed:', e); }
+  return true;
+}
+
+/**
+ * Drive session hydration and everything that hangs off it settling: the
+ * sidebar's failure row, the loader node, and any session-dependent route.
+ *
+ * @param {(() => Promise<boolean>)|null} loadSessions — resolves true only
+ *   after the session list was authoritatively loaded and applied. Null means
+ *   the session module failed to load.
+ */
+export function settleSessionHydration(loadSessions) {
+  const settle = (succeeded) => {
+    if (!succeeded) {
+      markSessionListUnavailableIfStillBootstrapping();
+      // A later unrelated caller must not be able to release a stale startup
+      // opener against unknown session state.
+      _routeOpener = null;
+      _routeOpenerNeedsSessions = false;
+    }
+    removeApplicationLoader();
+    if (succeeded) runDeferredRouteOpener({ sessionsSettled: true });
+    return succeeded;
+  };
+  if (!loadSessions) {
+    return Promise.resolve(settle(false));
+  }
+  // Kick the request off synchronously — a microtask hop here would delay the
+  // fetch this whole change exists to get off the critical path.
+  let pending;
+  try {
+    pending = loadSessions();
+  } catch (e) {
+    console.warn('loadSessions error:', e);
+    return Promise.resolve(settle(false));
+  }
+  return Promise.resolve(pending)
+    .then(result => settle(result === true))
+    .catch(e => {
+      console.warn('loadSessions error:', e);
+      return settle(false);
+    });
+}

static/style.css

@@ -38015,6 +38015,12 @@ button.cal-add-btn.cal-add-btn-text.cal-add-btn-sm:hover .cal-add-label {
   outline-offset: 2px;
   border-radius: 5px;
 }
+/* Bootstrap row shown while the session list hydrates, and on load failure.
+   Reads as a normal list row but is not selectable. */
+.session-list-bootstrap {
+  cursor: default;
+  pointer-events: none;
+}
 #email-lib-grid .date-section-header {
   padding: 10px 5px 3px;
 }

tests/live_thinking_scheduler.test.mjs

@@ -0,0 +1,277 @@
+// Tests for the live-thinking throttle that bounds DOM work during long
+// reasoning streams (see static/js/liveThinkingThrottle.js).
+//
+// The throttle's contract is what the terminal paths in chat.js lean on:
+// a burst of deltas becomes ONE commit carrying the latest text; flush()
+// lands trailing text synchronously and cannot double-commit; cancel()
+// guarantees nothing lands after a stream is finished or backgrounded.
+//
+// Timers are injected, so this runs with no DOM and no real clock.
+import assert from 'node:assert/strict';
+import test from 'node:test';
+
+import {
+  createIncrementalDisplayProjector,
+  createLiveThinkingThrottle,
+  createThinkingAnalysisGate,
+  stripLiveThinkingTags,
+} from '../static/js/liveThinkingThrottle.js';
+
+function fakeTimers() {
+  let nextId = 1;
+  const callbacks = new Map();
+  const delays = [];
+  return {
+    schedule(callback, delay) {
+      const id = nextId++;
+      callbacks.set(id, callback);
+      delays.push(delay);
+      return id;
+    },
+    cancel(id) {
+      callbacks.delete(id);
+    },
+    run(id) {
+      const callback = callbacks.get(id);
+      assert.ok(callback, `missing timer ${id}`);
+      callbacks.delete(id);
+      callback();
+    },
+    pendingIds() {
+      return [...callbacks.keys()];
+    },
+    delays,
+  };
+}
+
+test('coalesces a burst and commits only the latest text after 100 ms', () => {
+  const timers = fakeTimers();
+  const commits = [];
+  const throttle = createLiveThinkingThrottle((value) => commits.push(value), timers);
+
+  throttle.update('a');
+  throttle.update('ab');
+  throttle.update('abc');
+
+  assert.deepEqual(commits, []);
+  assert.deepEqual(timers.delays, [100], 'a burst must schedule exactly one commit');
+  const [timer] = timers.pendingIds();
+  timers.run(timer);
+  assert.deepEqual(commits, ['abc']);
+});
+
+test('commit count stays flat as the stream grows', () => {
+  const timers = fakeTimers();
+  const commits = [];
+  const throttle = createLiveThinkingThrottle((value) => commits.push(value), timers);
+
+  // 500 deltas arriving inside one window is the regression this guards:
+  // the old code committed once per delta, so work grew with stream length.
+  let text = '';
+  for (let i = 0; i < 500; i++) {
+    text += 'token ';
+    throttle.update(text);
+  }
+  assert.deepEqual(commits, []);
+  assert.equal(timers.pendingIds().length, 1);
+  timers.run(timers.pendingIds()[0]);
+  assert.equal(commits.length, 1);
+  assert.equal(commits[0], text);
+});
+
+test('prepares a 200K cumulative stream only at scheduled commit cadence', () => {
+  const timers = fakeTimers();
+  const commits = [];
+  let prepareCalls = 0;
+  let scannedCharacters = 0;
+  const throttle = createLiveThinkingThrottle((value) => commits.push(value), {
+    ...timers,
+    prepare(value) {
+      prepareCalls += 1;
+      scannedCharacters += value.length;
+      return stripLiveThinkingTags(value);
+    },
+  });
+
+  const delta = 'reasoning '.repeat(10); // 100 characters
+  let cumulative = '';
+  for (let i = 0; i < 2000; i++) {
+    cumulative += delta;
+    throttle.update(cumulative);
+  }
+
+  assert.equal(cumulative.length, 200_000);
+  assert.equal(prepareCalls, 0, 'cumulative extraction must not run per delta');
+  assert.equal(timers.pendingIds().length, 1);
+  timers.run(timers.pendingIds()[0]);
+  assert.equal(prepareCalls, 1);
+  assert.equal(scannedCharacters, 200_000);
+  assert.deepEqual(commits, [cumulative]);
+});
+
+test('ordinary answers and reasoning deltas do not request cumulative analysis', () => {
+  const startsReasoning = (text) => /^\s*thinking(?:\s+process)?\s*:/i.test(text);
+  const ordinaryGate = createThinkingAnalysisGate({ startsWithReasoningPrefix: startsReasoning });
+  let ordinary = '';
+  let ordinaryAnalyses = 0;
+  for (let i = 0; i < 2000; i++) {
+    ordinary += i === 0 ? 'Here is the answer. ' : 'answer '.repeat(10);
+    if (ordinaryGate.shouldAnalyze(ordinary)) ordinaryAnalyses += 1;
+  }
+  assert.equal(ordinaryAnalyses, 0);
+
+  const thinkingGate = createThinkingAnalysisGate({ startsWithReasoningPrefix: startsReasoning });
+  let thinking = 'Thin';
+  assert.equal(thinkingGate.shouldAnalyze(thinking), false);
+  thinking += 'king: inspect the problem';
+  assert.equal(thinkingGate.shouldAnalyze(thinking), true);
+  for (let i = 0; i < 2000; i++) {
+    thinking += ' reasoning'.repeat(10);
+    assert.equal(thinkingGate.shouldAnalyze(thinking, { isThinking: true, nonTagThinking: true }), false);
+  }
+  thinking += '\n\nHere is the answer';
+  assert.equal(thinkingGate.shouldAnalyze(thinking, { isThinking: true, nonTagThinking: true }), true);
+
+  const whitespaceGate = createThinkingAnalysisGate({ startsWithReasoningPrefix: startsReasoning });
+  let whitespaceThinking = ' '.repeat(250);
+  assert.equal(whitespaceGate.shouldAnalyze(whitespaceThinking), false);
+  whitespaceThinking += 'Thinking: bounded probe';
+  assert.equal(whitespaceGate.shouldAnalyze(whitespaceThinking), true);
+});
+
+test('split namespaced closes and false-close deadlines request analysis', () => {
+  let clock = 100;
+  const gate = createThinkingAnalysisGate({ now: () => clock });
+  let text = '<mm:think>x</mm:';
+  assert.equal(gate.shouldAnalyze(text, { isThinking: true }), true, 'fresh opening tag is analyzed');
+  text += 'think>answer';
+  assert.equal(gate.shouldAnalyze(text, { isThinking: true }), true, 'split namespaced close is analyzed');
+
+  text += ' still waiting';
+  assert.equal(gate.shouldAnalyze(text, { isThinking: true, recheckAt: 500 }), false);
+  clock = 500;
+  text += ' next delta';
+  assert.equal(gate.shouldAnalyze(text, { isThinking: true, recheckAt: 500 }), true);
+
+  const attributedGate = createThinkingAnalysisGate();
+  let attributed = `<think data-provider="${'x'.repeat(400)}"`;
+  assert.equal(attributedGate.shouldAnalyze(attributed), false);
+  attributed += '>reasoning';
+  assert.equal(attributedGate.shouldAnalyze(attributed), true, 'bounded carry preserves split tag attributes');
+});
+
+test('display projection is append-only and filters a structured tail once', () => {
+  let filterCalls = 0;
+  let filteredCharacters = 0;
+  const projector = createIncrementalDisplayProjector((text) => {
+    filterCalls += 1;
+    filteredCharacters += text.length;
+    return text.replace(/\[TOOL_CALL\][\s\S]*$/i, '');
+  });
+
+  let text = '';
+  for (let i = 0; i < 2000; i++) {
+    const delta = i === 0 ? 'Here is the answer. ' : 'ordinary text ';
+    text += delta;
+    assert.equal(projector.append(delta, text), text);
+  }
+  assert.equal(filterCalls, 0, 'ordinary deltas never run the cumulative filter');
+
+  text += '[TOOL_';
+  projector.append('[TOOL_', text);
+  text += 'CALL]{"name":"read"}';
+  const beforeToolPayload = projector.append('CALL]{"name":"read"}', text);
+  for (let i = 0; i < 2000; i++) {
+    const delta = 'payload ';
+    text += delta;
+    assert.equal(projector.append(delta, text), beforeToolPayload);
+  }
+  assert.equal(filterCalls, 1, 'structured payload filtering happens only at its boundary');
+  assert.ok(filteredCharacters < text.length, 'filter work is bounded by the first structured boundary');
+});
+
+test('literal escaped tags survive and malformed live tags retain trailing text', () => {
+  assert.equal(
+    stripLiveThinkingTags('&lt;think&gt;literal&lt;/think&gt;'),
+    '&lt;think&gt;literal&lt;/think&gt;',
+  );
+  assert.equal(
+    stripLiveThinkingTags('<think>first</think> middle <thinking mode="deep">trailing'),
+    'first middle trailing',
+  );
+  assert.equal(stripLiveThinkingTags('answer with 2 < 3 and 5 > 4'), 'answer with 2 < 3 and 5 > 4');
+});
+
+test('terminal flush prepares and commits the complete trailing cumulative text', () => {
+  const timers = fakeTimers();
+  const commits = [];
+  const throttle = createLiveThinkingThrottle((value) => commits.push(value), {
+    ...timers,
+    prepare: stripLiveThinkingTags,
+  });
+
+  throttle.update('<think>reasoning without a closing tag');
+  assert.equal(throttle.flush(), true);
+  assert.deepEqual(commits, ['reasoning without a closing tag']);
+  assert.deepEqual(timers.pendingIds(), []);
+});
+
+test('independent throttles cannot commit cancelled text into another session', () => {
+  const timers = fakeTimers();
+  const commits = [];
+  const first = createLiveThinkingThrottle((value) => commits.push(['first', value]), timers);
+  const second = createLiveThinkingThrottle((value) => commits.push(['second', value]), timers);
+
+  first.update('stale first-session text');
+  second.update('current second-session text');
+  first.cancel();
+  assert.equal(second.flush(), true);
+
+  assert.deepEqual(timers.pendingIds(), []);
+  assert.deepEqual(commits, [['second', 'current second-session text']]);
+});
+
+test('flush synchronously preserves trailing text and cancels the pending callback', () => {
+  const timers = fakeTimers();
+  const commits = [];
+  const throttle = createLiveThinkingThrottle((value) => commits.push(value), timers);
+
+  throttle.update('trailing text');
+  assert.equal(throttle.flush(), true);
+  assert.deepEqual(commits, ['trailing text']);
+  assert.deepEqual(timers.pendingIds(), []);
+  assert.equal(throttle.flush(), false, 'clean flush must not duplicate the commit');
+});
+
+test('cancel discards pending work without a late DOM commit', () => {
+  const timers = fakeTimers();
+  const commits = [];
+  const throttle = createLiveThinkingThrottle((value) => commits.push(value), timers);
+
+  throttle.update('stale session text');
+  throttle.cancel();
+  assert.deepEqual(timers.pendingIds(), []);
+  assert.deepEqual(commits, []);
+});
+
+test('a cancelled throttle accepts new work again', () => {
+  const timers = fakeTimers();
+  const commits = [];
+  const throttle = createLiveThinkingThrottle((value) => commits.push(value), timers);
+
+  throttle.update('discarded');
+  throttle.cancel();
+  throttle.update('fresh');
+  assert.equal(throttle.flush(), true);
+  assert.deepEqual(commits, ['fresh']);
+});
+
+test('coerces nullish updates instead of committing undefined', () => {
+  const timers = fakeTimers();
+  const commits = [];
+  const throttle = createLiveThinkingThrottle((value) => commits.push(value), timers);
+
+  throttle.update(null);
+  throttle.flush();
+  assert.deepEqual(commits, ['']);
+});

tests/test_agent_bash_windows.py

@@ -0,0 +1,128 @@
+"""Windows execution contract for the agent Bash tool."""
+
+import pytest
+
+from src.agent_tools import subprocess_tools
+
+
+@pytest.mark.asyncio
+async def test_windows_bash_uses_git_bash_with_structural_cwd(monkeypatch):
+    captured = {}
+    bash = r"C:\Program Files\Git\bin\bash.exe"
+    workspace = r"D:\Workspaces\Project with spaces"
+    process = object()
+
+    monkeypatch.setattr(subprocess_tools, "IS_WINDOWS", True)
+    monkeypatch.setattr(subprocess_tools, "find_bash", lambda: bash)
+
+    async def fake_exec(*argv, **kwargs):
+        captured["argv"] = argv
+        captured["kwargs"] = kwargs
+        return process
+
+    async def fail_shell(*_args, **_kwargs):
+        pytest.fail("native Windows Bash must not execute through cmd.exe")
+
+    monkeypatch.setattr(subprocess_tools.asyncio, "create_subprocess_exec", fake_exec)
+    monkeypatch.setattr(subprocess_tools.asyncio, "create_subprocess_shell", fail_shell)
+
+    result = await subprocess_tools._create_bash_subprocess(
+        "pwd; cat package.json",
+        cwd=workspace,
+        env={"HOME": r"C:\Odysseus\data"},
+    )
+
+    assert result is process
+    assert captured["argv"] == (bash, "-c", "pwd; cat package.json")
+    assert captured["kwargs"]["cwd"] == workspace
+
+
+@pytest.mark.asyncio
+async def test_windows_bash_without_git_bash_fails_clearly(monkeypatch):
+    monkeypatch.setattr(subprocess_tools, "IS_WINDOWS", True)
+    monkeypatch.setattr(subprocess_tools, "find_bash", lambda: None)
+
+    async def fail_spawn(*_args, **_kwargs):
+        pytest.fail("no subprocess should start without Git Bash")
+
+    monkeypatch.setattr(subprocess_tools.asyncio, "create_subprocess_exec", fail_spawn)
+    monkeypatch.setattr(subprocess_tools.asyncio, "create_subprocess_shell", fail_spawn)
+
+    with pytest.raises(RuntimeError, match="Git Bash is required"):
+        await subprocess_tools._create_bash_subprocess("pwd", cwd=r"C:\Work")
+
+
+@pytest.mark.asyncio
+async def test_bash_tool_returns_install_hint_when_git_bash_is_missing(monkeypatch):
+    monkeypatch.setattr(subprocess_tools, "IS_WINDOWS", True)
+    monkeypatch.setattr(subprocess_tools, "find_bash", lambda: None)
+
+    result = await subprocess_tools.BashTool().execute(
+        "pwd",
+        {"subproc_env": {}, "session_id": None},
+    )
+
+    assert result["exit_code"] == 1
+    assert "install Git for Windows" in result["error"]
+
+
+@pytest.mark.asyncio
+async def test_windows_bash_does_not_use_a_stray_tmux_executable(monkeypatch):
+    captured = {}
+    workspace = r"D:\Workspaces\Project with spaces"
+
+    monkeypatch.setattr(subprocess_tools, "IS_WINDOWS", True)
+    monkeypatch.setattr(
+        subprocess_tools.shutil,
+        "which",
+        lambda name: r"C:\msys64\usr\bin\tmux.exe",
+    )
+    monkeypatch.setattr("src.tool_execution.agent_cwd", lambda: workspace)
+
+    async def fail_tmux(*_args, **_kwargs):
+        pytest.fail("native Windows must not enter the POSIX tmux path")
+
+    async def fake_create(command, **kwargs):
+        captured["command"] = command
+        captured["kwargs"] = kwargs
+        return object()
+
+    async def fake_stream(_process, **_kwargs):
+        return "ok", "", 0, False
+
+    monkeypatch.setattr(subprocess_tools, "_run_tmux_bash", fail_tmux)
+    monkeypatch.setattr(subprocess_tools, "_create_bash_subprocess", fake_create)
+    monkeypatch.setattr(subprocess_tools, "_run_subprocess_streaming", fake_stream)
+
+    result = await subprocess_tools.BashTool().execute(
+        "pwd",
+        {"subproc_env": {}, "session_id": "chat-1"},
+    )
+
+    assert result == {"output": "ok", "exit_code": 0}
+    assert captured["command"] == "pwd"
+    assert captured["kwargs"]["cwd"] == workspace
+
+
+@pytest.mark.asyncio
+async def test_posix_bash_keeps_existing_shell_path(monkeypatch):
+    captured = {}
+    process = object()
+
+    monkeypatch.setattr(subprocess_tools, "IS_WINDOWS", False)
+
+    async def fake_shell(command, **kwargs):
+        captured["command"] = command
+        captured["kwargs"] = kwargs
+        return process
+
+    async def fail_exec(*_args, **_kwargs):
+        pytest.fail("POSIX behavior must continue through create_subprocess_shell")
+
+    monkeypatch.setattr(subprocess_tools.asyncio, "create_subprocess_shell", fake_shell)
+    monkeypatch.setattr(subprocess_tools.asyncio, "create_subprocess_exec", fail_exec)
+
+    result = await subprocess_tools._create_bash_subprocess("pwd", cwd="/tmp/work")
+
+    assert result is process
+    assert captured == {"command": "pwd", "kwargs": {"cwd": "/tmp/work"}}

tests/test_chat_stream_scope.py

@@ -1,3 +1,4 @@
+import re
 from pathlib import Path
 
 
@@ -13,7 +14,7 @@ def test_stream_render_helpers_are_visible_to_catch_block():
     assert "let _cancelThinkingTimer = () => {};" in outer_scope
     assert "let _removeThinkingSpinner = () => {};" in outer_scope
 
-    assert "_renderStream = () => {" in try_body
+    assert re.search(r"(?m)^\s*_renderStream\s*=", try_body)
     assert "_cancelThinkingTimer = () => {" in try_body
     assert "_removeThinkingSpinner = () => {" in try_body
     assert "function _renderStream()" not in try_body

tests/test_email_library_prewarm.py

@@ -0,0 +1,414 @@
+import json
+from pathlib import Path
+import shutil
+import subprocess
+
+import pytest
+
+
+_REPO = Path(__file__).resolve().parents[1]
+_EMAIL_LIBRARY = _REPO / "static" / "js" / "emailLibrary.js"
+
+
+def _source() -> str:
+    return _EMAIL_LIBRARY.read_text(encoding="utf-8")
+
+
+def _function_source(name: str) -> str:
+    """Return one top-level JS function using balanced braces."""
+    text = _source()
+    markers = (f"function {name}", f"async function {name}", f"export function {name}", f"export async function {name}")
+    starts = [text.find(marker) for marker in markers]
+    starts = [start for start in starts if start >= 0]
+    assert starts, f"missing function {name}"
+    start = min(starts)
+    paren = text.index("(", start)
+    paren_depth = 0
+    quote = None
+    escaped = False
+    for index in range(paren, len(text)):
+        char = text[index]
+        if quote:
+            if escaped:
+                escaped = False
+            elif char == "\\":
+                escaped = True
+            elif char == quote:
+                quote = None
+            continue
+        if char in ("'", '"', "`"):
+            quote = char
+        elif char == "(":
+            paren_depth += 1
+        elif char == ")":
+            paren_depth -= 1
+            if paren_depth == 0:
+                brace = text.index("{", index)
+                break
+    else:
+        raise AssertionError(f"unterminated signature {name}")
+    depth = 0
+    quote = None
+    escaped = False
+    template_depth = 0
+    for index in range(brace, len(text)):
+        char = text[index]
+        if quote:
+            if escaped:
+                escaped = False
+            elif char == "\\":
+                escaped = True
+            elif char == quote and template_depth == 0:
+                quote = None
+            elif quote == "`" and char == "$" and index + 1 < len(text) and text[index + 1] == "{":
+                template_depth += 1
+            elif quote == "`" and char == "}" and template_depth:
+                template_depth -= 1
+            continue
+        if char in ("'", '"', "`"):
+            quote = char
+        elif char == "{":
+            depth += 1
+        elif char == "}":
+            depth -= 1
+            if depth == 0:
+                return text[start:index + 1]
+    raise AssertionError(f"unterminated function {name}")
+
+
+def _run_scheduler_scenario(scenario: str):
+    node = shutil.which("node")
+    if not node:
+        pytest.skip("node not on PATH")
+    functions = "\n".join(
+        _function_source(name)
+        for name in (
+            "_isChatInteractionBusy",
+            "_canRunEmailPrewarm",
+            "_isEmailPrewarmTemporarilyBlocked",
+            "_settleEmailPrewarm",
+            "_cancelEmailPrewarm",
+            "_scheduleEmailPrewarm",
+        )
+    )
+    script = f"""
+      let now = 0;
+      Date.now = () => now;
+      const state = {{ _libOpen: false, _libLoading: false }};
+      let _libSearchInFlight = false;
+      let _libPrewarmDelayTimer = null;
+      let _libPrewarmIdleHandle = null;
+      let _libPrewarmPromise = null;
+      let _libPrewarmResolve = null;
+      let _libPrewarmAbortController = null;
+      let _libPrewarmDetachPriorityListeners = null;
+      let _libPrewarmGeneration = 0;
+      let nextHandle = 1;
+      const timers = new Map();
+      const idleCallbacks = new Map();
+      let idleRequestCount = 0;
+      function eventTarget(target) {{
+        const listeners = new Map();
+        target.addEventListener = (type, callback) => {{
+          if (!listeners.has(type)) listeners.set(type, new Set());
+          listeners.get(type).add(callback);
+        }};
+        target.removeEventListener = (type, callback) => listeners.get(type)?.delete(callback);
+        target.dispatchEvent = (event) => {{
+          for (const callback of [...(listeners.get(event.type) || [])]) callback(event);
+        }};
+        target.listenerCount = (type) => listeners.get(type)?.size || 0;
+        return target;
+      }}
+      const document = eventTarget({{ visibilityState: 'visible' }});
+      const window = {{
+        __odysseusChatBusy: false,
+        __odysseusChatBusyUntil: 0,
+        requestIdleCallback(callback) {{
+          const handle = nextHandle++;
+          idleRequestCount += 1;
+          idleCallbacks.set(handle, callback);
+          return handle;
+        }},
+        cancelIdleCallback(handle) {{ idleCallbacks.delete(handle); }},
+      }};
+      eventTarget(window);
+      function setTimeout(callback, delay) {{
+        const handle = nextHandle++;
+        timers.set(handle, {{ callback, at: now + Number(delay || 0) }});
+        return handle;
+      }}
+      function clearTimeout(handle) {{ timers.delete(handle); }}
+      async function flushMicrotasks() {{
+        for (let i = 0; i < 6; i += 1) await Promise.resolve();
+      }}
+      async function advanceTo(target) {{
+        while (true) {{
+          const pending = [...timers.entries()]
+            .filter(([, timer]) => timer.at <= target)
+            .sort((a, b) => a[1].at - b[1].at)[0];
+          if (!pending) break;
+          const [handle, timer] = pending;
+          timers.delete(handle);
+          now = timer.at;
+          timer.callback();
+          await flushMicrotasks();
+        }}
+        now = target;
+        await flushMicrotasks();
+      }}
+      async function fireNextIdle(budget = 5) {{
+        const pending = idleCallbacks.entries().next().value;
+        if (!pending) throw new Error('no idle callback pending');
+        const [handle, callback] = pending;
+        idleCallbacks.delete(handle);
+        callback({{ didTimeout: false, timeRemaining: () => budget }});
+        await flushMicrotasks();
+      }}
+      {functions}
+      {scenario}
+    """
+    proc = subprocess.run(
+        [node, "--input-type=module"],
+        input=script,
+        capture_output=True,
+        text=True,
+        cwd=str(_REPO),
+        timeout=30,
+    )
+    assert proc.returncode == 0, proc.stderr
+    return json.loads(proc.stdout.strip())
+
+
+def test_prewarm_is_genuine_idle_only_and_single_flight():
+    scheduler = _function_source("_scheduleEmailPrewarm")
+
+    assert "if (_libPrewarmPromise) return _libPrewarmPromise;" in scheduler
+    assert "typeof window.requestIdleCallback !== 'function'" in scheduler
+    assert "return Promise.resolve(false);" in scheduler
+    assert "window.requestIdleCallback((deadline)" in scheduler
+    assert "!deadline.didTimeout" in scheduler
+    assert "deadline.timeRemaining() > 0" in scheduler
+
+    idle_callback = scheduler.index("window.requestIdleCallback((deadline)")
+    assert "Promise.resolve()" in scheduler
+    task_start = scheduler.index("task({ signal: controller.signal, generation })")
+    assert idle_callback < task_start, "network work must only be reachable from the idle callback"
+
+
+def test_temporary_chat_priority_retries_one_single_flight_until_idle():
+    out = _run_scheduler_scenario("""
+      window.__odysseusChatBusyUntil = 10000;
+      let taskCalls = 0;
+      const task = async () => { taskCalls += 1; return true; };
+      const first = _scheduleEmailPrewarm(task, { delay: 1800 });
+      const joined = _scheduleEmailPrewarm(task, { delay: 0 });
+      const samePromise = first === joined;
+      await advanceTo(1800);
+      await fireNextIdle(7);
+      const callsWhileBusy = taskCalls;
+      while (now < 10300) {
+        await advanceTo(now + 500);
+        await fireNextIdle(7);
+      }
+      const result = await first;
+      console.log(JSON.stringify({
+        result, samePromise, callsWhileBusy, taskCalls, idleRequestCount,
+        timers: timers.size, idleCallbacks: idleCallbacks.size,
+      }));
+    """)
+    assert out == {
+        "result": True,
+        "samePromise": True,
+        "callsWhileBusy": 0,
+        "taskCalls": 1,
+        "idleRequestCount": 18,
+        "timers": 0,
+        "idleCallbacks": 0,
+    }
+
+
+def test_cancelled_prewarm_cannot_issue_a_delayed_duplicate():
+    out = _run_scheduler_scenario("""
+      let taskCalls = 0;
+      const pending = _scheduleEmailPrewarm(async () => { taskCalls += 1; return true; }, { delay: 1800 });
+      await advanceTo(1400);
+      _cancelEmailPrewarm();
+      await advanceTo(12000);
+      const result = await pending;
+      console.log(JSON.stringify({
+        result, taskCalls, idleRequestCount,
+        timers: timers.size, idleCallbacks: idleCallbacks.size,
+      }));
+    """)
+    assert out == {
+        "result": False,
+        "taskCalls": 0,
+        "idleRequestCount": 0,
+        "timers": 0,
+        "idleCallbacks": 0,
+    }
+
+
+@pytest.mark.parametrize("transition", ["busy", "hidden"])
+def test_active_prewarm_is_aborted_and_retried_once_after_priority_transition(transition):
+    block = (
+        "window.__odysseusChatBusy = true; "
+        "window.dispatchEvent({ type: 'odysseus:chat-busy-change' });"
+        if transition == "busy"
+        else "document.visibilityState = 'hidden'; document.dispatchEvent({ type: 'visibilitychange' });"
+    )
+    unblock = (
+        "window.__odysseusChatBusy = false; window.__odysseusChatBusyUntil = now; "
+        "window.dispatchEvent({ type: 'odysseus:chat-busy-change' });"
+        if transition == "busy"
+        else "document.visibilityState = 'visible'; document.dispatchEvent({ type: 'visibilitychange' });"
+    )
+    out = _run_scheduler_scenario(f"""
+      let taskCalls = 0;
+      let firstSignal = null;
+      let finishFirst;
+      const firstAttempt = new Promise(resolve => {{ finishFirst = resolve; }});
+      const pending = _scheduleEmailPrewarm(async ({{ signal }}) => {{
+        taskCalls += 1;
+        if (taskCalls === 1) {{ firstSignal = signal; return firstAttempt; }}
+        return true;
+      }});
+      await fireNextIdle(7);
+      {block}
+      const aborted = firstSignal.aborted;
+      {unblock}
+      const callsBeforeLateResult = taskCalls;
+      finishFirst(true);
+      await flushMicrotasks();
+      const stillPendingAfterLateResult = _libPrewarmPromise === pending;
+      await advanceTo(now + 500);
+      await fireNextIdle(7);
+      const result = await pending;
+      console.log(JSON.stringify({{
+        result, aborted, callsBeforeLateResult, taskCalls,
+        stillPendingAfterLateResult,
+        timers: timers.size, idleCallbacks: idleCallbacks.size,
+        chatListeners: window.listenerCount('odysseus:chat-busy-change'),
+        visibilityListeners: document.listenerCount('visibilitychange'),
+      }}));
+    """)
+    assert out == {
+        "result": True,
+        "aborted": True,
+        "callsBeforeLateResult": 1,
+        "taskCalls": 2,
+        "stillPendingAfterLateResult": True,
+        "timers": 0,
+        "idleCallbacks": 0,
+        "chatListeners": 0,
+        "visibilityListeners": 0,
+    }
+
+
+def test_prewarm_skips_hidden_and_foreground_work():
+    guard = _function_source("_canRunEmailPrewarm")
+
+    assert "state._libOpen" in guard
+    assert "state._libLoading" in guard
+    assert "_libSearchInFlight" in guard
+    assert "document.visibilityState !== 'visible'" in guard
+    assert "!_isChatInteractionBusy()" in guard
+
+
+def test_prewarm_selects_only_last_used_or_default_account():
+    chooser = _function_source("_chooseEmailPrewarmAccountId")
+    prewarm = _function_source("_prewarmEmailViews")
+
+    assert "_rememberedEmailAccountId()" in chooser
+    assert "a.enabled !== false" in chooser
+    assert "a.is_default" in chooser
+    assert "enabled[0]" in chooser
+
+    assert "for (" not in prewarm
+    assert "orderedAccountIds" not in prewarm
+    assert "slice(0, 4)" not in prewarm
+    assert "/api/email/folders" not in prewarm
+    assert "/api/email/unread-state" not in prewarm
+    assert prewarm.count("/api/email/list") == 1
+
+
+def test_prewarm_account_chooser_rejects_disabled_or_empty_authoritative_inventory():
+    node = shutil.which("node")
+    if not node:
+        pytest.skip("node not on PATH")
+    chooser = _function_source("_chooseEmailPrewarmAccountId")
+    script = f"""
+      const state = {{ _libAccountId: 'disabled-current' }};
+      function _rememberedEmailAccountId() {{ return 'disabled-remembered'; }}
+      {chooser}
+      const onlyDisabled = _chooseEmailPrewarmAccountId([
+        {{ id: 'disabled-remembered', enabled: false, is_default: true }},
+        {{ id: 'disabled-current', enabled: false }},
+      ]);
+      const empty = _chooseEmailPrewarmAccountId([]);
+      const mixed = _chooseEmailPrewarmAccountId([
+        {{ id: 'disabled-remembered', enabled: false, is_default: true }},
+        {{ id: 'enabled-default', enabled: true, is_default: true }},
+      ]);
+      console.log(JSON.stringify({{ onlyDisabled, empty, mixed }}));
+    """
+    proc = subprocess.run(
+        [node, "--input-type=module"],
+        input=script,
+        capture_output=True,
+        text=True,
+        cwd=str(_REPO),
+        timeout=30,
+    )
+    assert proc.returncode == 0, proc.stderr
+    assert json.loads(proc.stdout.strip()) == {
+        "onlyDisabled": "",
+        "empty": "",
+        "mixed": "enabled-default",
+    }
+
+    ensure_accounts = _function_source("_ensureEmailAccountsForPrewarm")
+    assert "if (!accountId) return null;" in ensure_accounts
+    assert ensure_accounts.index("if (!accountId) return null;") < ensure_accounts.index("_publishActiveAccount();")
+
+
+def test_prewarm_is_bounded_to_the_interactive_initial_page_size():
+    text = _source()
+    prewarm = _function_source("_prewarmEmailViews")
+
+    assert "const _LIB_INITIAL_PAGE_SIZE = 100;" in text
+    assert "limit: _LIB_INITIAL_PAGE_SIZE" in prewarm
+    assert text.count("limit=${_LIB_INITIAL_PAGE_SIZE}&offset=${offsetAtStart}") == 2
+    assert "limit: 100" not in prewarm
+
+
+def test_open_cancels_scheduled_or_inflight_prewarm_first():
+    text = _source()
+    cancel = _function_source("_cancelEmailPrewarm")
+    open_library = _function_source("openEmailLibrary")
+
+    assert "clearTimeout(_libPrewarmDelayTimer)" in cancel
+    assert "window.cancelIdleCallback(_libPrewarmIdleHandle)" in cancel
+    assert "_libPrewarmAbortController?.abort()" in cancel
+    assert "_libPrewarmGeneration += 1" in cancel
+    assert open_library.index("_cancelEmailPrewarm();") < open_library.index("state._libOpen = true;")
+    assert "_loadEmailsWhenChatIdle" not in text
+    assert text.count("_loadEmails({ useCache: true });") >= 2
+
+
+def test_close_cancels_pending_prewarm_cleanup():
+    close_library = _function_source("closeEmailLibrary")
+
+    assert close_library.index("_cancelEmailPrewarm();") < close_library.index("state._libOpen = false;")
+
+
+def test_unread_warm_joins_the_same_idle_single_flight_gate():
+    unread_entry = _function_source("prewarmUnreadEmails")
+    unread_work = _function_source("_prewarmUnreadEmailsNow")
+
+    assert "_scheduleEmailPrewarm(" in unread_entry
+    assert "fetch(" not in unread_entry
+    assert "_ensureEmailAccountsForPrewarm({ signal, generation })" in unread_work
+    assert "signal" in unread_work
+    assert "Math.min(20" in unread_work

tests/test_email_open_dedup_js.py

@@ -0,0 +1,231 @@
+"""Focused browser-side regression coverage for authoritative email opens."""
+
+import json
+import shutil
+import subprocess
+from pathlib import Path
+
+import pytest
+
+
+_REPO = Path(__file__).resolve().parent.parent
+_INBOX_JS = _REPO / "static" / "js" / "emailInbox.js"
+_LIBRARY_JS = _REPO / "static" / "js" / "emailLibrary.js"
+_HAS_NODE = shutil.which("node") is not None
+
+
+def _extract_between(source: str, signature: str, next_marker: str) -> str:
+    start = source.index(signature)
+    end = source.index(next_marker, start)
+    return source[start:end].rstrip()
+
+
+def test_library_unread_preview_has_one_authoritative_request_and_rollback():
+    source = _LIBRARY_JS.read_text(encoding="utf-8")
+    function = _extract_between(source, "async function _toggleCardPreview", "\n/**\n * Wrap a probable signature block")
+
+    assert function.count("/api/email/read/") == 1
+    assert "/api/email/mark-read/" not in function
+    assert "&mark_seen=true" in function
+    assert "_syncEmailReadState(uidAtStart, true, readContext)" in function
+    assert "_syncEmailReadState(uidAtStart, false, readContext)" in function
+    assert "openGeneration === _emailCardOpenSeq" in function
+    assert "_emailReadMutations.get(readContextKey)?.generation !== readMutation.generation" in function
+    assert "authoritativeReadSucceeded = true;" in function
+    assert "if (!authoritativeReadSucceeded) restoreUnreadState();" in function
+    assert "if (!isCurrentOpen()) return" in function
+
+
+@pytest.mark.skipif(not _HAS_NODE, reason="node binary not on PATH")
+def test_library_authoritative_success_defeats_newer_rollback_in_either_order():
+    source = _LIBRARY_JS.read_text(encoding="utf-8")
+    function = _extract_between(source, "async function _toggleCardPreview", "\n/**\n * Wrap a probable signature block")
+    settlements = _extract_between(
+        function,
+        "  const restoreUnreadState = () => {",
+        "\n\n  // Collapse any other expanded card",
+    )
+
+    harness = f"""
+const _emailReadMutations = new Map();
+const readContextKey = 'same-mailbox-message';
+const uidAtStart = '1';
+const readContext = {{ accountId: 'acct-a', folder: 'INBOX', uid: '1' }};
+const readUpdates = [];
+function _syncEmailReadState(uid, isRead, context) {{
+  readUpdates.push({{ uid, isRead, context }});
+}}
+function createSettlers(readMutation) {{
+{settlements}
+  return {{ restoreUnreadState, commitReadState }};
+}}
+function runRace(successFirst) {{
+  _emailReadMutations.clear();
+  readUpdates.length = 0;
+  const mutationA = {{ generation: 1, rollbackUnread: true }};
+  _emailReadMutations.set(readContextKey, mutationA);
+  const settlersA = createSettlers(mutationA);
+  const mutationB = {{ generation: 2, rollbackUnread: true }};
+  _emailReadMutations.set(readContextKey, mutationB);
+  const settlersB = createSettlers(mutationB);
+  if (successFirst) {{
+    settlersA.commitReadState();
+    settlersB.restoreUnreadState();
+  }} else {{
+    settlersB.restoreUnreadState();
+    settlersA.commitReadState();
+  }}
+  return {{
+    hasMutation: _emailReadMutations.has(readContextKey),
+    readUpdates: readUpdates.map(update => update.isRead),
+  }};
+}}
+console.log(JSON.stringify({{
+  successFirst: runRace(true),
+  failureFirst: runRace(false),
+}}));
+"""
+    proc = subprocess.run(
+        ["node", "--input-type=module"],
+        input=harness,
+        capture_output=True,
+        text=True,
+        cwd=str(_REPO),
+        timeout=30,
+    )
+    assert proc.returncode == 0, f"node failed: {proc.stderr}\n---\n{harness}"
+    assert json.loads(proc.stdout.strip()) == {
+        "successFirst": {"hasMutation": False, "readUpdates": [True]},
+        "failureFirst": {"hasMutation": False, "readUpdates": [False, True]},
+    }
+
+
+def test_library_reply_open_carries_immutable_mailbox_context():
+    library_source = _LIBRARY_JS.read_text(encoding="utf-8")
+    inbox_source = _INBOX_JS.read_text(encoding="utf-8")
+
+    assert "const mailboxGeneration = _emailMailboxGeneration;" in library_source
+    assert "messageFolder = String(options.email?.folder || libraryFolder)" in library_source
+    assert "return onEmailClick({ ...options, mailboxContext });" in library_source
+    assert "mailboxContext?.messageFolder || _currentFolder" in inbox_source
+    assert "mailboxContextIsCurrent()" in inbox_source
+    assert "if (!isCurrentOpen()) return;\n        let activeSid = await _createEmailChat" in inbox_source
+
+
+@pytest.mark.skipif(not _HAS_NODE, reason="node binary not on PATH")
+def test_inbox_late_read_response_cannot_apply_after_newer_open():
+    source = _INBOX_JS.read_text(encoding="utf-8")
+    function = _extract_between(source, "async function _openEmail", "\nfunction _showEmailMenu")
+    assert "let _openEmailRequestSeq = 0;" in source
+
+    harness = f"""
+const realLog = console.log;
+console.error = () => {{}};
+const API_BASE = 'https://odysseus.invalid';
+const window = {{ __odysseusActiveEmailAccount: 'acct-a' }};
+let _currentFolder = 'INBOX';
+const _acct = () => '&account_id=acct-a';
+let _openEmailRequestSeq = 0;
+let _docModule = null;
+const spinnerModule = {{ createWhirlpool() {{ throw new Error('spinner should not run'); }} }};
+const sessionModule = null;
+let firstResolve;
+const calls = [];
+async function fetch(url) {{
+  calls.push(String(url));
+  if (calls.length === 1) {{
+    return await new Promise((resolve) => {{
+      firstResolve = () => resolve({{ json: async () => ({{ uid: '1', subject: 'old' }}) }});
+    }});
+  }}
+  return {{ json: async () => ({{ error: 'newer open completed test' }}) }};
+}}
+{function}
+const oldEmail = {{ uid: '1', is_read: false }};
+const newerEmail = {{ uid: '2', is_read: false }};
+const first = _openEmail(oldEmail, null);
+await Promise.resolve();
+const second = _openEmail(newerEmail, null);
+await second;
+firstResolve();
+await first;
+realLog(JSON.stringify({{ calls, oldRead: oldEmail.is_read, newerRead: newerEmail.is_read }}));
+"""
+    proc = subprocess.run(
+        ["node", "--input-type=module"],
+        input=harness,
+        capture_output=True,
+        text=True,
+        cwd=str(_REPO),
+        timeout=30,
+    )
+    assert proc.returncode == 0, f"node failed: {proc.stderr}\n---\n{harness}"
+    result = json.loads(proc.stdout.strip())
+    assert len(result["calls"]) == 2
+    assert all("mark_seen=true" in url for url in result["calls"])
+    assert result["oldRead"] is False
+    assert result["newerRead"] is False
+
+
+@pytest.mark.skipif(not _HAS_NODE, reason="node binary not on PATH")
+@pytest.mark.parametrize("context_change", ["account", "folder", "library"])
+def test_inbox_late_read_response_cannot_apply_after_mailbox_switch(context_change):
+    source = _INBOX_JS.read_text(encoding="utf-8")
+    function = _extract_between(source, "async function _openEmail", "\nfunction _showEmailMenu")
+
+    changes = {
+        "account": "window.__odysseusActiveEmailAccount = 'acct-b';",
+        "folder": "_currentFolder = 'Archive';",
+        "library": "libraryCurrent = false;",
+    }
+    change = changes[context_change]
+    open_call = (
+        "_openEmail(email, null, null, 'reply', '', '', mailboxContext)"
+        if context_change == "library"
+        else "_openEmail(email, null)"
+    )
+    harness = f"""
+const realLog = console.log;
+console.error = () => {{}};
+const API_BASE = 'https://odysseus.invalid';
+const window = {{ __odysseusActiveEmailAccount: 'acct-a' }};
+let _currentFolder = 'INBOX';
+const _acct = () => '&account_id=acct-a';
+let _openEmailRequestSeq = 0;
+let libraryCurrent = true;
+const mailboxContext = {{
+  accountId: 'acct-a',
+  messageFolder: 'Archive',
+  isCurrent: () => libraryCurrent,
+}};
+let createCalls = 0;
+let _docModule = {{}};
+async function _createEmailChat() {{ createCalls += 1; return 'stale-session'; }}
+const spinnerModule = {{ createWhirlpool() {{ throw new Error('spinner should not run'); }} }};
+const sessionModule = null;
+let resolveRead;
+async function fetch() {{
+  return await new Promise((resolve) => {{
+    resolveRead = () => resolve({{ json: async () => ({{ uid: '1', subject: 'old' }}) }});
+  }});
+}}
+{function}
+const email = {{ uid: '1', is_read: false }};
+const pending = {open_call};
+await Promise.resolve();
+{change}
+resolveRead();
+await pending;
+realLog(JSON.stringify({{ createCalls, isRead: email.is_read }}));
+"""
+    proc = subprocess.run(
+        ["node", "--input-type=module"],
+        input=harness,
+        capture_output=True,
+        text=True,
+        cwd=str(_REPO),
+        timeout=30,
+    )
+    assert proc.returncode == 0, f"node failed: {proc.stderr}\n---\n{harness}"
+    result = json.loads(proc.stdout.strip())
+    assert result == {"createCalls": 0, "isRead": False}

tests/test_email_read_mark_seen.py

@@ -0,0 +1,278 @@
+import asyncio
+from contextlib import contextmanager
+
+import pytest
+
+
+RAW_EMAIL = (
+    b"From: Sender <sender@example.com>\r\n"
+    b"To: Alice <alice@example.com>\r\n"
+    b"Subject: Single authoritative open\r\n"
+    b"Message-ID: <single-open@example.com>\r\n"
+    b"Date: Tue, 04 Aug 2026 12:00:00 +0000\r\n"
+    b"Content-Type: text/plain; charset=utf-8\r\n"
+    b"\r\n"
+    b"Body"
+)
+
+
+def _route_endpoint(router, path: str, method: str):
+    method = method.upper()
+    for route in router.routes:
+        if route.path == path and method in getattr(route, "methods", set()):
+            return route.endpoint
+    raise AssertionError(f"route not found: {method} {path}")
+
+
+class FakeImap:
+    def __init__(self, store_status="OK", readonly_mailbox=False):
+        self.store_status = store_status
+        # Shared archives and some provider folders reject a read-write SELECT.
+        self.readonly_mailbox = readonly_mailbox
+        self.selects = []
+        self.commands = []
+
+    def select(self, mailbox, readonly=False):
+        self.selects.append((mailbox, readonly))
+        if self.readonly_mailbox and not readonly:
+            raise OSError("[READ-ONLY] Mailbox is read-only")
+        return "OK", [b"1"]
+
+    def uid(self, command, uid, *args):
+        self.commands.append((command, uid, *args))
+        if command == "FETCH":
+            header, body = RAW_EMAIL.split(b"\r\n\r\n", 1)
+            return "OK", [
+                (b"1 (UID 42 BODY[HEADER])", header + b"\r\n\r\n"),
+                (b"1 (UID 42 BODY[TEXT]<0>)", body),
+            ]
+        if command == "STORE":
+            # RFC 3501 STORE takes a parenthesized flag-list. GreenMail rejects
+            # the formerly emitted bare ``\Seen`` atom with BAD, so keep the
+            # fake strict enough to catch that provider-compatibility failure.
+            if args != ("+FLAGS", "(\\Seen)"):
+                return "BAD", [b"Expected:'(' found:'\\'"]
+            return self.store_status, []
+        raise AssertionError(f"unexpected IMAP command: {command}")
+
+
+def _install_fakes(monkeypatch, tmp_path, *, store_status="OK", readonly_mailbox=False):
+    import routes.email_helpers as email_helpers
+    import routes.email_routes as email_routes
+
+    db_path = tmp_path / "email.db"
+    monkeypatch.setattr(email_helpers, "SCHEDULED_DB", db_path)
+    monkeypatch.setattr(email_routes, "SCHEDULED_DB", db_path)
+    email_helpers._init_scheduled_db()
+
+    connections = []
+    indexed_updates = []
+
+    @contextmanager
+    def fake_imap(account_id=None, owner=""):
+        conn = FakeImap(store_status=store_status, readonly_mailbox=readonly_mailbox)
+        connections.append(conn)
+        yield conn
+
+    monkeypatch.setattr(email_routes, "_start_poller", lambda: None)
+    monkeypatch.setattr(email_routes, "_imap", fake_imap)
+    monkeypatch.setattr(email_routes, "_email_preview_cache_get", lambda *_args, **_kwargs: None)
+    monkeypatch.setattr(email_routes, "_email_preview_cache_put", lambda *_args, **_kwargs: None)
+    monkeypatch.setattr(email_routes, "_email_attachment_meta_cache_get", lambda *_args, **_kwargs: None)
+    monkeypatch.setattr(email_routes, "_email_attachment_meta_cache_put", lambda *_args, **_kwargs: None)
+    monkeypatch.setattr(
+        email_routes,
+        "_email_index_update_flags",
+        lambda *args, **_kwargs: indexed_updates.append(args),
+    )
+    return email_routes, connections, indexed_updates
+
+
+@pytest.mark.asyncio
+@pytest.mark.parametrize("mark_seen", [True, False])
+async def test_read_email_seen_contract_uses_one_imap_connection(monkeypatch, tmp_path, mark_seen):
+    email_routes, connections, indexed_updates = _install_fakes(monkeypatch, tmp_path)
+    router = email_routes.setup_email_routes()
+    read_email = _route_endpoint(router, "/api/email/read/{uid}", "GET")
+
+    result = await read_email(
+        "42",
+        folder="INBOX",
+        account_id="acct-a",
+        mark_seen=mark_seen,
+        full=False,
+        owner="alice",
+    )
+
+    assert result["uid"] == "42"
+    assert len(connections) == 1
+    conn = connections[0]
+    assert conn.selects == [(conn.selects[0][0], not mark_seen)]
+    assert [command[0] for command in conn.commands] == (
+        ["FETCH", "STORE"] if mark_seen else ["FETCH"]
+    )
+    assert "BODY.PEEK[HEADER]" in conn.commands[0][2]
+    if mark_seen:
+        assert conn.commands[1][2:] == ("+FLAGS", "(\\Seen)")
+        assert indexed_updates == [("alice", "acct-a", "INBOX", "42", "\\Seen", True)]
+    else:
+        assert indexed_updates == []
+
+
+@pytest.mark.asyncio
+async def test_cached_read_awaits_one_seen_store_without_refetch(monkeypatch, tmp_path):
+    email_routes, connections, indexed_updates = _install_fakes(monkeypatch, tmp_path)
+    router = email_routes.setup_email_routes()
+    read_email = _route_endpoint(router, "/api/email/read/{uid}", "GET")
+
+    first = await read_email(
+        "42", folder="INBOX", account_id="acct-a", mark_seen=False, full=False, owner="alice"
+    )
+    monkeypatch.setattr(
+        asyncio,
+        "create_task",
+        lambda *_args, **_kwargs: (_ for _ in ()).throw(
+            AssertionError("cached mark-seen must be awaited, not scheduled")
+        ),
+    )
+    second = await read_email(
+        "42", folder="INBOX", account_id="acct-a", mark_seen=True, full=False, owner="alice"
+    )
+
+    assert first["message_id"] == second["message_id"]
+    assert len(connections) == 2
+    assert [command[0] for command in connections[0].commands] == ["FETCH"]
+    assert [command[0] for command in connections[1].commands] == ["STORE"]
+    assert connections[1].commands[0][2:] == ("+FLAGS", "(\\Seen)")
+    assert connections[1].selects[0][1] is False
+    assert indexed_updates == [("alice", "acct-a", "INBOX", "42", "\\Seen", True)]
+
+
+@pytest.mark.asyncio
+async def test_seen_store_failure_returns_the_body_and_reports_the_failure(monkeypatch, tmp_path):
+    """A failed STORE must not cost the reader the message.
+
+    The body was fetched successfully before the flag update was attempted, so
+    the response stays a normal read and carries `mark_seen_failed` for the
+    client to roll its optimistic unread marker back.
+    """
+    email_routes, connections, indexed_updates = _install_fakes(
+        monkeypatch, tmp_path, store_status="NO"
+    )
+    router = email_routes.setup_email_routes()
+    read_email = _route_endpoint(router, "/api/email/read/{uid}", "GET")
+
+    result = await read_email(
+        "42", folder="INBOX", account_id="acct-a", mark_seen=True, full=False, owner="alice"
+    )
+
+    assert "error" not in result
+    assert result["uid"] == "42"
+    assert result["mark_seen_failed"] is True
+    assert len(connections) == 1
+    assert [command[0] for command in connections[0].commands] == ["FETCH", "STORE"]
+    # The local index must not claim a transition the provider rejected.
+    assert indexed_updates == []
+
+
+@pytest.mark.asyncio
+async def test_read_only_mailbox_serves_the_message_without_marking_seen(monkeypatch, tmp_path):
+    """A mailbox that refuses a read-write SELECT is still readable.
+
+    Opening the message is the user's actual goal; the \\Seen transition is a
+    side effect of it. A folder that cannot accept flag changes must therefore
+    fall back to a read-only selection rather than failing the open.
+    """
+    email_routes, connections, indexed_updates = _install_fakes(
+        monkeypatch, tmp_path, readonly_mailbox=True
+    )
+    router = email_routes.setup_email_routes()
+    read_email = _route_endpoint(router, "/api/email/read/{uid}", "GET")
+
+    result = await read_email(
+        "42", folder="Archive", account_id="acct-a", mark_seen=True, full=False, owner="alice"
+    )
+
+    assert "error" not in result
+    assert result["uid"] == "42"
+    assert result["mark_seen_failed"] is True
+    # Read-write attempt first, then the read-only retry on the same connection.
+    assert [readonly for _mailbox, readonly in connections[0].selects] == [False, True]
+    # No STORE is attempted once the mailbox is known to be read-only.
+    assert [command[0] for command in connections[0].commands] == ["FETCH"]
+    assert indexed_updates == []
+
+
+@pytest.mark.asyncio
+async def test_failed_seen_state_is_not_replayed_from_cache(monkeypatch, tmp_path):
+    """`mark_seen_failed` describes one request, not the stored message.
+
+    A second read that does not ask to mark seen must come back clean, or every
+    later reader would inherit a STORE failure it never issued.
+    """
+    email_routes, connections, _ = _install_fakes(monkeypatch, tmp_path, store_status="NO")
+    router = email_routes.setup_email_routes()
+    read_email = _route_endpoint(router, "/api/email/read/{uid}", "GET")
+
+    failed = await read_email(
+        "42", folder="INBOX", account_id="acct-a", mark_seen=True, full=False, owner="alice"
+    )
+    replayed = await read_email(
+        "42", folder="INBOX", account_id="acct-a", mark_seen=False, full=False, owner="alice"
+    )
+
+    assert failed["mark_seen_failed"] is True
+    assert replayed.get("mark_seen_failed", False) is False
+    assert replayed["uid"] == "42"
+
+
+@pytest.mark.asyncio
+async def test_unparseable_read_does_not_mark_seen(monkeypatch, tmp_path):
+    email_routes, connections, indexed_updates = _install_fakes(monkeypatch, tmp_path)
+    monkeypatch.setattr(
+        email_routes.email_mod,
+        "message_from_bytes",
+        lambda *_args, **_kwargs: (_ for _ in ()).throw(ValueError("malformed message")),
+    )
+    router = email_routes.setup_email_routes()
+    read_email = _route_endpoint(router, "/api/email/read/{uid}", "GET")
+
+    result = await read_email(
+        "42", folder="INBOX", account_id="acct-a", mark_seen=True, full=False, owner="alice"
+    )
+
+    assert result == {"error": "Mail operation failed"}
+    assert len(connections) == 1
+    assert [command[0] for command in connections[0].commands] == ["FETCH"]
+    assert indexed_updates == []
+
+
+@pytest.mark.asyncio
+async def test_cached_seen_store_failure_returns_the_cached_body(monkeypatch, tmp_path):
+    """A cache hit already holds a complete message; a failed STORE cannot take it away.
+
+    This is the path where withholding the body would be least defensible — the
+    response is served from memory and needed no network at all.
+    """
+    email_routes, connections, indexed_updates = _install_fakes(
+        monkeypatch, tmp_path, store_status="NO"
+    )
+    router = email_routes.setup_email_routes()
+    read_email = _route_endpoint(router, "/api/email/read/{uid}", "GET")
+
+    first = await read_email(
+        "42", folder="INBOX", account_id="acct-a", mark_seen=False, full=False, owner="alice"
+    )
+    second = await read_email(
+        "42", folder="INBOX", account_id="acct-a", mark_seen=True, full=False, owner="alice"
+    )
+
+    assert first["uid"] == "42"
+    assert "error" not in second
+    assert second["uid"] == "42"
+    assert second["body"] == first["body"]
+    assert second["mark_seen_failed"] is True
+    assert len(connections) == 2
+    assert [command[0] for command in connections[0].commands] == ["FETCH"]
+    assert [command[0] for command in connections[1].commands] == ["STORE"]
+    assert indexed_updates == []

tests/test_fork_session_metadata.py

@@ -34,6 +34,11 @@ class _FakeSessionManager:
         self.sessions = {"src-id": source}
         self.created = None
 
+    def get_session(self, session_id):
+        # Fork looks the source up through get_session — the hydration seam —
+        # so a session only present in the DB still forks a real transcript.
+        return self.sessions[session_id]
+
     def create_session(self, session_id=None, name=None, endpoint_url=None,
                        model=None, rag=False, owner=None):
         self.created = _FakeSession(name=name, owner=owner)

tests/test_history_db_fallback_hidden.py

@@ -5,9 +5,9 @@ The in-memory branch skips messages whose metadata has ``hidden`` (e.g.
 compaction summaries that are kept for AI context but not shown to the user).
 The DB fallback (taken when the in-memory history is empty, e.g. after a
 restart) built the client response from every DB row with no such filter, so
-hidden messages leaked to the client on DB-served sessions. The rebuilt
+hidden messages leaked to the client on DB-served sessions. Hydration of
-in-memory ``session.history`` must still keep them, though, so only the response
+``session.history`` belongs to ``get_session``; this fallback only shapes the
-is filtered.
+response, so only the response is filtered.
 
 get_session_history depends on the DB, the session manager and a FastAPI
 request, so this pins the regression at the source level (as other route tests

tests/test_history_display_model_hydration.py

@@ -0,0 +1,549 @@
+"""Display pagination must stay separate from full model-context hydration."""
+
+import json
+from datetime import datetime, timedelta
+
+import pytest
+from fastapi import APIRouter, FastAPI
+from fastapi.testclient import TestClient
+from starlette.requests import Request
+from sqlalchemy import create_engine, event
+from sqlalchemy.orm import sessionmaker
+from sqlalchemy.pool import StaticPool
+
+from core.database import Base, ChatMessage as DbChatMessage, Session as DbSession
+from core.models import ChatMessage, Session
+from core.session_manager import SessionManager
+from routes import chat_routes
+from routes.history import history_routes
+from routes import session_routes
+from src.request_models import ChatRequest
+
+
+def _database():
+    engine = create_engine(
+        "sqlite://",
+        connect_args={"check_same_thread": False},
+        poolclass=StaticPool,
+    )
+    Base.metadata.create_all(
+        engine,
+        tables=[DbSession.__table__, DbChatMessage.__table__],
+    )
+    return engine, sessionmaker(bind=engine, autocommit=False, autoflush=False)
+
+
+def _seed_session(db_factory, *, session_id="session-1", message_count=6, stored_count=None):
+    """Seed `message_count` real rows; `stored_count` overrides the denormalized
+    sessions.message_count column so drift can be reproduced."""
+    db = db_factory()
+    try:
+        db.add(
+            DbSession(
+                id=session_id,
+                name="Long chat",
+                endpoint_url="http://model.test/v1",
+                model="test-model",
+                owner="alice",
+                message_count=message_count if stored_count is None else stored_count,
+            )
+        )
+        start = datetime(2026, 1, 1, 12, 0, 0)
+        for index in range(message_count):
+            db.add(
+                DbChatMessage(
+                    id=f"message-{index}",
+                    session_id=session_id,
+                    role="user" if index % 2 == 0 else "assistant",
+                    content=f"content-{index}",
+                    timestamp=start + timedelta(seconds=index),
+                )
+            )
+        db.commit()
+    finally:
+        db.close()
+
+
+def _chat_message_selects(statements):
+    return [
+        " ".join(statement.lower().split())
+        for statement in statements
+        if statement.lstrip().lower().startswith("select")
+        and "chat_messages" in statement.lower()
+    ]
+
+
+def _manager(db_factory, monkeypatch, sessions=None):
+    """A real SessionManager bound to the temp DB, with load counting."""
+    monkeypatch.setattr("core.session_manager.SessionLocal", db_factory)
+    manager = object.__new__(SessionManager)
+    manager.upload_handler = None
+    manager.sessions = sessions if sessions is not None else {}
+    manager.full_loads = 0
+
+    original_load = manager._load_session_from_db
+
+    def counting_load(session_id):
+        manager.full_loads += 1
+        return original_load(session_id)
+
+    manager._load_session_from_db = counting_load
+    return manager
+
+
+def test_paginated_history_reads_only_count_and_requested_page(monkeypatch):
+    engine, db_factory = _database()
+    _seed_session(db_factory)
+
+    class DisplayOnlyManager:
+        def get_session(self, _session_id):
+            raise AssertionError("paginated display history must not hydrate model context")
+
+    monkeypatch.setattr(history_routes, "SessionLocal", db_factory)
+    monkeypatch.setattr(history_routes, "_verify_session_owner", lambda *_args: None)
+
+    app = FastAPI()
+    app.include_router(history_routes.setup_history_routes(DisplayOnlyManager()))
+
+    statements = []
+
+    def capture_sql(_conn, _cursor, statement, _parameters, _context, _executemany):
+        statements.append(statement)
+
+    event.listen(engine, "before_cursor_execute", capture_sql)
+    try:
+        response = TestClient(app).get("/api/history/session-1?limit=2")
+    finally:
+        event.remove(engine, "before_cursor_execute", capture_sql)
+        engine.dispose()
+
+    assert response.status_code == 200
+    payload = response.json()
+    assert [message["content"] for message in payload["history"]] == [
+        "content-4",
+        "content-5",
+    ]
+    assert payload["total"] == 6
+    assert payload["offset"] == 4
+    assert payload["has_more_before"] is True
+    assert payload["has_more_after"] is False
+
+    # One COUNT for the total plus one page read — never a full-transcript
+    # select. The page bounds are asserted through the response above rather
+    # than by matching SQL text.
+    chat_selects = _chat_message_selects(statements)
+    assert len(chat_selects) == 2, chat_selects
+    assert sum("count(" in statement for statement in chat_selects) == 1
+
+
+def test_production_router_order_reaches_bounded_canonical_history(monkeypatch):
+    """The assembled app must not shadow canonical history with session routes."""
+    engine, db_factory = _database()
+    _seed_session(db_factory, message_count=1200)
+
+    class DisplayOnlyManager:
+        def get_session(self, _session_id):
+            raise AssertionError("bounded initial history must not hydrate all messages")
+
+    manager = DisplayOnlyManager()
+    monkeypatch.setattr(
+        session_routes,
+        "router",
+        APIRouter(prefix="/api", tags=["sessions"]),
+    )
+    monkeypatch.setattr(history_routes, "SessionLocal", db_factory)
+    monkeypatch.setattr(history_routes, "_verify_session_owner", lambda *_args: None)
+
+    app = FastAPI()
+    app.include_router(session_routes.setup_session_routes(manager, {}))
+    app.include_router(history_routes.setup_history_routes(manager))
+
+    try:
+        response = TestClient(app).get("/api/history/session-1?limit=24")
+    finally:
+        engine.dispose()
+
+    assert response.status_code == 200
+    assert response.request.url.params["limit"] == "24"
+    payload = response.json()
+    displayed = len(payload["history"])
+    assert 0 < displayed <= payload["limit"] <= 100
+    assert payload["total"] >= 1200
+    assert payload["has_more_before"] is True
+    assert displayed < payload["total"]
+
+
+def test_incomplete_cached_history_hydrates_once_for_model_context(monkeypatch):
+    engine, db_factory = _database()
+    raw_multimodal = json.dumps(
+        [
+            {"type": "text", "text": "look at the source image"},
+            {
+                "type": "image_url",
+                "image_url": {"url": "data:image/png;base64,AAAA"},
+            },
+        ]
+    )
+    db = db_factory()
+    try:
+        db.add(
+            DbSession(
+                id="session-1",
+                name="Long chat",
+                endpoint_url="http://model.test/v1",
+                model="test-model",
+                owner="alice",
+                message_count=3,
+            )
+        )
+        start = datetime(2026, 1, 1, 12, 0, 0)
+        db.add_all(
+            [
+                DbChatMessage(
+                    id="message-0",
+                    session_id="session-1",
+                    role="user",
+                    content=raw_multimodal,
+                    meta_data=json.dumps(
+                        {
+                            "attachments": [
+                                {
+                                    "id": "upload-1",
+                                    "filename": "source.png",
+                                    "content_type": "image/png",
+                                }
+                            ]
+                        }
+                    ),
+                    timestamp=start,
+                ),
+                DbChatMessage(
+                    id="message-1",
+                    session_id="session-1",
+                    role="assistant",
+                    content="answer",
+                    timestamp=start + timedelta(seconds=1),
+                ),
+                DbChatMessage(
+                    id="message-2",
+                    session_id="session-1",
+                    role="system",
+                    content="compaction summary",
+                    meta_data=json.dumps({"hidden": True}),
+                    timestamp=start + timedelta(seconds=2),
+                ),
+            ]
+        )
+        db.commit()
+    finally:
+        db.close()
+
+    manager = _manager(
+        db_factory,
+        monkeypatch,
+        sessions={
+            "session-1": Session(
+                id="session-1",
+                name="Long chat",
+                endpoint_url="http://model.test/v1",
+                model="test-model",
+                owner="alice",
+                history=[ChatMessage("user", "stale partial cache")],
+                # Deliberately stale too: get_session must refresh metadata before
+                # checking whether the cached transcript is complete.
+                message_count=1,
+            )
+        },
+    )
+
+    try:
+        hydrated = manager.get_session("session-1")
+        first_full_loads = manager.full_loads
+        warm = manager.get_session("session-1")
+        second_full_loads = manager.full_loads
+    finally:
+        engine.dispose()
+
+    assert hydrated is warm
+    assert len(hydrated.history) == 3
+    assert first_full_loads == 1
+    assert second_full_loads == first_full_loads
+
+    context = hydrated.get_context_messages()
+    assert len(context) == 3
+    assert context[0]["content"][1]["image_url"]["url"] == "data:image/png;base64,AAAA"
+    assert context[0]["metadata"]["attachments"] == [
+        {
+            "id": "upload-1",
+            "filename": "source.png",
+            "content_type": "image/png",
+        }
+    ]
+    hidden_summary = next(message for message in context if message["role"] == "system")
+    assert hidden_summary["content"] == "compaction summary"
+    assert hidden_summary["metadata"]["hidden"] is True
+
+
+def test_inflated_message_count_column_does_not_reload_warm_sessions(monkeypatch):
+    """A drifted-high sessions.message_count must not reload on every read.
+
+    `_persist_message` swallows a failed insert while `add_message` has already
+    appended in memory, so the next successful persist writes rows+1. Keyed on
+    that column, the hydration gate would stay true forever and re-select the
+    whole transcript on every send, edit, delete and truncate.
+    """
+    engine, db_factory = _database()
+    _seed_session(db_factory, message_count=6, stored_count=8)
+
+    manager = _manager(db_factory, monkeypatch)
+    try:
+        session = manager.get_session("session-1")
+        cold_loads = manager.full_loads
+        for _ in range(3):
+            manager.get_session("session-1")
+    finally:
+        engine.dispose()
+
+    assert len(session.history) == 6
+    assert cold_loads == 1
+    assert manager.full_loads == 1
+
+
+def test_stale_low_message_count_column_still_hydrates_for_the_model(monkeypatch):
+    """The other drift direction must not hand the model a truncated transcript.
+
+    `_persist_message` writes message_count = 0 when the session is not cached.
+    A partly-filled cache plus that stale-low column previously left the send
+    path with whatever RAM happened to hold.
+    """
+    engine, db_factory = _database()
+    _seed_session(db_factory, message_count=6, stored_count=0)
+
+    manager = _manager(
+        db_factory,
+        monkeypatch,
+        sessions={
+            "session-1": Session(
+                id="session-1",
+                name="Long chat",
+                endpoint_url="http://model.test/v1",
+                model="test-model",
+                owner="alice",
+                history=[ChatMessage("user", "content-0")],
+                message_count=0,
+            )
+        },
+    )
+    try:
+        session = manager.get_session("session-1")
+        manager.get_session("session-1")
+    finally:
+        engine.dispose()
+
+    assert [message.content for message in session.history] == [
+        f"content-{index}" for index in range(6)
+    ]
+    assert manager.full_loads == 1
+
+
+def test_fork_after_restart_copies_the_real_transcript(monkeypatch):
+    """Forking reads source.history, so it must hydrate through get_session.
+
+    Display pagination no longer fills the cache, so a fork taken after a
+    restart used to return HTTP 200 with an empty conversation.
+    """
+    engine, db_factory = _database()
+    _seed_session(db_factory, message_count=6)
+
+    # Restart state: metadata-only cache entry, exactly what load_sessions seeds.
+    manager = _manager(db_factory, monkeypatch)
+    manager.load_sessions()
+
+    monkeypatch.setattr(history_routes, "SessionLocal", db_factory)
+    monkeypatch.setattr(history_routes, "_verify_session_owner", lambda *_args: None)
+    monkeypatch.setattr("core.models._SESSION_MANAGER_INSTANCE", manager)
+
+    app = FastAPI()
+    app.include_router(history_routes.setup_history_routes(manager))
+    client = TestClient(app)
+
+    try:
+        page = client.get("/api/history/session-1?limit=2")
+        assert page.status_code == 200
+        assert len(manager.sessions["session-1"].history) == 0
+
+        response = client.post("/api/session/session-1/fork", json={"keep_count": 4})
+        assert response.status_code == 200
+        payload = response.json()
+        assert payload["kept"] == 4
+
+        forked = manager.get_session(payload["id"])
+        assert [message.content for message in forked.history] == [
+            f"content-{index}" for index in range(4)
+        ]
+    finally:
+        engine.dispose()
+
+
+class _ContextBuildReached(Exception):
+    pass
+
+
+class _ToolPolicy:
+    block_all_tool_calls = False
+
+    def blocks(self, _tool_name):
+        return False
+
+
+class _ChatHandler:
+    async def handle_memory_command(self, _session, _message):
+        return None
+
+
+def _json_request(path, payload):
+    raw = json.dumps(payload).encode()
+    sent = False
+
+    async def receive():
+        nonlocal sent
+        if sent:
+            return {"type": "http.request", "body": b"", "more_body": False}
+        sent = True
+        return {"type": "http.request", "body": raw, "more_body": False}
+
+    scope = {
+        "type": "http",
+        "asgi": {"version": "3.0"},
+        "http_version": "1.1",
+        "method": "POST",
+        "scheme": "http",
+        "path": path,
+        "raw_path": path.encode(),
+        "root_path": "",
+        "query_string": b"",
+        "headers": [(b"content-type", b"application/json")],
+        "client": ("127.0.0.1", 1234),
+        "server": ("testserver", 80),
+    }
+    return Request(scope, receive)
+
+
+def _route_endpoint(router, path):
+    return next(route.endpoint for route in router.routes if route.path == path)
+
+
+@pytest.mark.asyncio
+@pytest.mark.parametrize("path", ["/api/chat", "/api/chat_stream"])
+async def test_model_send_routes_hydrate_before_context_build(monkeypatch, path):
+    # A real SessionManager over a real (temp) DB — a stub here would only
+    # assert that the stub hydrates, not that SessionManager does.
+    engine, db_factory = _database()
+    _seed_session(db_factory, message_count=6, stored_count=8)
+    manager = _manager(db_factory, monkeypatch)
+    manager.load_sessions()  # restart state: metadata only, no messages cached
+    contexts_built = []
+
+    async def assert_complete_context(session, *_args, **_kwargs):
+        contexts_built.append(session)
+        assert [message.content for message in session.history] == [
+            f"content-{index}" for index in range(6)
+        ]
+        raise _ContextBuildReached
+
+    monkeypatch.setattr(chat_routes, "_set_user_time_from_request", lambda *_args: None)
+    monkeypatch.setattr(chat_routes, "_verify_session_owner", lambda *_args: None)
+    monkeypatch.setattr(chat_routes, "effective_user", lambda *_args: "alice")
+    monkeypatch.setattr(
+        chat_routes,
+        "_clear_orphaned_session_endpoint",
+        lambda *_args, **_kwargs: False,
+    )
+    monkeypatch.setattr(
+        chat_routes,
+        "_recover_empty_session_model",
+        lambda *_args, **_kwargs: False,
+    )
+    monkeypatch.setattr(chat_routes, "_enforce_chat_privileges", lambda *_args: None)
+    monkeypatch.setattr(
+        chat_routes,
+        "build_effective_tool_policy",
+        lambda **_kwargs: _ToolPolicy(),
+    )
+    monkeypatch.setattr(chat_routes, "build_chat_context", assert_complete_context)
+    monkeypatch.setattr(
+        chat_routes,
+        "_resolve_request_workspace",
+        lambda *_args: (None, False),
+    )
+    monkeypatch.setattr(chat_routes, "_classify_tool_intent", lambda *_args: None)
+    monkeypatch.setattr(
+        chat_routes,
+        "_is_contextual_web_followup",
+        lambda *_args: False,
+    )
+    monkeypatch.setattr(
+        chat_routes,
+        "_is_contextual_browser_followup",
+        lambda *_args: False,
+    )
+    monkeypatch.setattr(
+        chat_routes,
+        "_resolve_workspace_from_message_path",
+        lambda *_args: (None, None),
+    )
+    monkeypatch.setattr(
+        chat_routes,
+        "_reconcile_selected_route_from_request",
+        lambda *_args, **_kwargs: False,
+    )
+    monkeypatch.setattr(chat_routes, "resolve_session_auth", lambda *_args, **_kwargs: None)
+    monkeypatch.setattr(chat_routes, "get_session_mode", lambda *_args: "chat")
+    monkeypatch.setattr(
+        chat_routes,
+        "_is_image_generation_session",
+        lambda *_args, **_kwargs: False,
+    )
+    monkeypatch.setattr(chat_routes, "web_search_enabled_for_turn", lambda *_args: False)
+
+    router = chat_routes.setup_chat_routes(
+        manager,
+        _ChatHandler(),
+        object(),
+        object(),
+        object(),
+        object(),
+    )
+    endpoint = _route_endpoint(router, path)
+
+    async def send():
+        if path == "/api/chat":
+            await endpoint(
+                _json_request(path, {}),
+                ChatRequest(message="hello", session="session-1"),
+            )
+        else:
+            await endpoint(
+                _json_request(
+                    path,
+                    {"message": "hello", "session": "session-1"},
+                )
+            )
+
+    try:
+        with pytest.raises(_ContextBuildReached):
+            await send()
+        first_loads = manager.full_loads
+
+        # Second send on the now-warm session: the transcript is complete, so
+        # it must be served from RAM even though sessions.message_count is
+        # still drifted high in the DB.
+        with pytest.raises(_ContextBuildReached):
+            await send()
+    finally:
+        engine.dispose()
+
+    assert len(contexts_built) == 2
+    assert contexts_built[0] is contexts_built[1]
+    assert first_loads == 1
+    assert manager.full_loads == 1

tests/test_live_thinking_chat_integration.py

@@ -0,0 +1,145 @@
+"""Source-level wiring guards for live-thinking stream lifecycle.
+
+The pure scheduler suite covers timing behavior. These assertions pin the
+browser-only integration seams that are impractical to import without the full
+application DOM.
+"""
+
+from pathlib import Path
+
+
+_CHAT = (Path(__file__).resolve().parent.parent / "static" / "js" / "chat.js").read_text(
+    encoding="utf-8"
+)
+
+
+def _between(start: str, end: str) -> str:
+    return _CHAT.split(start, 1)[1].split(end, 1)[0]
+
+
+def test_in_thinking_delta_short_circuits_before_cumulative_normalization():
+    delta_handler = _between(
+        "let _delta = json.delta;",
+        "} else if (json.type === 'research_progress')",
+    )
+    delta_path = _between(
+        "// Detect thinking-in-progress:",
+        "} else if (json.type === 'research_progress')",
+    )
+    guard = "if (!_thinkingAnalysisGate.shouldAnalyze(roundText, {"
+    normalize = "markdownModule.normalizeThinkingMarkup(roundText)"
+    assert guard in delta_path
+    assert delta_path.index(guard) < delta_path.index(normalize)
+    assert "_queueLiveThinking(roundText);" in delta_path
+    assert "createThinkingAnalysisGate" in _CHAT
+    projector_append = "_roundDisplayProjector.append(_delta, roundText);"
+    assert projector_append in delta_handler
+    assert delta_handler.index(projector_append) < delta_handler.index(guard)
+    assert "_renderStream({ knownNormal: true, displayText: _roundDisplayProjector.current() });" in delta_path
+    assert "_replyDisplayProjector.append(_delta, roundReplyText)" in delta_path
+
+
+def test_short_close_grace_expires_without_another_delta():
+    assert "function _scheduleThinkingGrace()" in _CHAT
+    grace = _between(
+        "function _scheduleThinkingGrace()",
+        "function _replyAfterClosedThinking",
+    )
+    assert "setTimeout(() =>" in grace
+    assert "_finishLiveThinkingTransition();" in grace
+    cancel = _between("_cancelLiveThinkingWork = () =>", "function _finalizeLiveThinking")
+    assert "_cancelThinkingGrace();" in cancel
+    delta_path = _between(
+        "// Detect thinking-in-progress:",
+        "} else if (json.type === 'research_progress')",
+    )
+    false_close = _between(
+        "// Detect false close:",
+        "if (hasUnclosedThink && !isThinking)",
+    )
+    assert "Do NOT require a prior unclosed delta" in false_close
+    assert "_afterClose &&" in false_close
+    assert "&& isThinking" not in false_close.split("let _falseCloseDeadline", 1)[1].split("if (isThinking)", 1)[0]
+    assert "_thinkingRecheckAt = _falseCloseDeadline || 0;" in delta_path
+
+
+def test_terminal_paths_use_one_authoritative_rich_round_render():
+    tool_path = _between(
+        "} else if (json.type === 'tool_start') {",
+        "} else if (json.type === 'tool_output') {",
+    )
+    assert "_endLiveThinkingSection({ rich: false });" in tool_path
+    assert tool_path.count("_finalizeRoundRender();") == 1
+    assert "_renderStream();" not in tool_path
+
+    agent_path = _between(
+        "} else if (json.type === 'agent_step') {",
+        "} else if (json.type === 'budget_exceeded') {",
+    )
+    assert "_endLiveThinkingSection({ rich: false });" in agent_path
+    assert agent_path.count("_finalizeRoundRender();") == 1
+    assert "if (!roundFinalized)" not in agent_path
+
+    catch_path = _between(
+        "// foreground session's text.\n      const _isBgCatch",
+        "} finally {",
+    )
+    assert "if (_isBgCatch)" in catch_path
+    assert "_cancelLiveThinkingWork();" in catch_path
+    assert "_catchTerminalView = _finalizeInterruptedView();" in catch_path
+    assert "_finalizeRoundRender();" not in catch_path
+    assert "_endThinkingOnTerminalPath({ rich: false });" in catch_path
+    assert "const _catchViewHolder = _catchTerminalView?.holder || holder;" in catch_path
+
+    round_finalizer = _between(
+        "_finalizeRoundRender = () => {",
+        "_finalizeInterruptedView = () => {",
+    )
+    assert "if (roundFinalized) return roundFinalization;" in round_finalizer
+    assert round_finalizer.index("processWithThinking") < round_finalizer.rindex("roundFinalized = true;")
+    assert "lastContentRoundHolder = terminalHolder;" in round_finalizer
+
+    interrupted_finalizer = _between(
+        "_finalizeInterruptedView = () => {",
+        "function _replyAfterClosedThinking",
+    )
+    assert "finalization?.hasContent" in interrupted_finalizer
+    assert "lastContentRoundHolder || finalization?.holder" in interrupted_finalizer
+
+    stop_path = _between(
+        "// Render whatever was accumulated so far",
+        "// Reset button state",
+    )
+    assert "const _stoppedViewHolder = _terminalView?.holder || currentHolder;" in stop_path
+    assert "_stoppedViewHolder.querySelector('.body').appendChild(stoppedIndicator);" in stop_path
+
+    done_path = _between(
+        "if (data === '[DONE]') {",
+        "try {\n              const json = JSON.parse(data);",
+    )
+    assert "_finalizeLiveThinking(_closedThinkingText(roundText), false);" in done_path
+    assert "_renderStream();" not in done_path
+
+    post_loop = _between(
+        "if (!_streamSawDone) {",
+        "// --- Final render (skip if stream was ever backgrounded or currently in background) ---",
+    )
+    assert "_cancelLiveThinkingWork();" in post_loop
+    assert "_renderStream();" not in post_loop
+
+    recovery_path = _between(
+        "function _tryAutoRecover(holder, accumulated, sessionId)",
+        "function _removeStallBanner()",
+    )
+    assert "processWithThinking" not in recovery_path
+
+
+def test_detach_synchronously_cancels_delayed_view_work():
+    registration = _between("_activeStreams.set(streamSessionId", "_syncForegroundStreamGlobals();")
+    assert "cancelViewWork: () => _cancelLiveThinkingWork()" in registration
+
+    detach = _between("export function detachCurrentStream", "// _notifyStreamComplete")
+    cancel = "if (active.cancelViewWork) active.cancelViewWork();"
+    background = "_backgroundStreams.set(sessionId"
+    assert cancel in detach
+    assert detach.index(cancel) < detach.index(background)

tests/test_live_thinking_scheduler_js.py

@@ -0,0 +1,29 @@
+"""Runs the live-thinking throttle's behavioral suite under pytest.
+
+Behavior lives in tests/live_thinking_scheduler.test.mjs (node:test, no DOM).
+This wrapper only exists so the JS suite runs in the normal pytest job.
+"""
+
+import shutil
+import subprocess
+from pathlib import Path
+
+import pytest
+
+_REPO = Path(__file__).resolve().parent.parent
+_HAS_NODE = shutil.which("node") is not None
+
+
+@pytest.mark.skipif(not _HAS_NODE, reason="node binary not on PATH")
+def test_live_thinking_scheduler_behavior():
+    result = subprocess.run(
+        ["node", "--test", "tests/live_thinking_scheduler.test.mjs"],
+        cwd=_REPO,
+        capture_output=True,
+        timeout=30,
+        text=True,
+    )
+    if result.returncode != 0:
+        raise AssertionError(
+            f"node --test failed:\nSTDOUT:\n{result.stdout}\nSTDERR:\n{result.stderr}"
+        )

tests/test_startup_session_bootstrap_js.py

@@ -0,0 +1,356 @@
+"""Exercise sessions.js and startupShell.js together at the bootstrap seam.
+
+The dependency-heavy session module is copied unchanged except for redirecting
+its static imports to tiny browser stubs. The real loadSessions implementation
+and the real startup-shell coordinator then run together under Node.
+"""
+
+import json
+import shutil
+import subprocess
+from pathlib import Path
+
+import pytest
+
+
+_REPO = Path(__file__).resolve().parent.parent
+_SESSIONS = _REPO / "static" / "js" / "sessions.js"
+_SHELL_URL = (_REPO / "static" / "js" / "startupShell.js").as_uri()
+_HAS_NODE = shutil.which("node") is not None
+
+_IMPORT_REWRITES = {
+    "import Storage from './storage.js';": "import Storage from './storage.mjs';",
+    "import uiModule, { autoResize, styledPrompt } from './ui.js';": (
+        "import uiModule, { autoResize, styledPrompt } from './ui.mjs';"
+    ),
+    "import chatRenderer from './chatRenderer.js?v=20260722ctxheader1';": (
+        "import chatRenderer from './chatRenderer.mjs';"
+    ),
+    "import { providerLogo } from './providers.js';": (
+        "import { providerLogo } from './providers.mjs';"
+    ),
+    "import { initModelPicker, updateModelPicker } from './modelPicker.js?v=20260722ctxheader1';": (
+        "import { initModelPicker, updateModelPicker } from './modelPicker.mjs';"
+    ),
+    "import themeModule from './theme.js';": "import themeModule from './theme.mjs';",
+    "import spinnerModule from './spinner.js';": "import spinnerModule from './spinner.mjs';",
+}
+
+_STUBS = {
+    "storage.mjs": r"""
+const Storage = {
+  get: (key, fallback = null) => localStorage.getItem(key) ?? fallback,
+  set: (key, value) => localStorage.setItem(key, value),
+  remove: (key) => localStorage.removeItem(key),
+  getJSON: (key, fallback) => {
+    try { return JSON.parse(localStorage.getItem(key) ?? JSON.stringify(fallback)); }
+    catch (_) { return fallback; }
+  },
+  setJSON: (key, value) => localStorage.setItem(key, JSON.stringify(value)),
+};
+export default Storage;
+""",
+    "ui.mjs": r"""
+export const autoResize = () => {};
+export const styledPrompt = async () => null;
+const ui = {
+  el: (id) => document.getElementById(id),
+  showError: (message) => globalThis.__sessionErrors.push(String(message)),
+  showToast: () => {},
+  styledConfirm: async () => true,
+};
+export default ui;
+""",
+    "chatRenderer.mjs": (
+        "export default { addMessage: () => null, hideWelcomeScreen: () => {} };\n"
+    ),
+    "providers.mjs": "export const providerLogo = () => '';\n",
+    "modelPicker.mjs": (
+        "export const initModelPicker = () => {};\n"
+        "export const updateModelPicker = () => {};\n"
+    ),
+    "theme.mjs": "export default {};\n",
+    "spinner.mjs": "export default {};\n",
+}
+
+_HARNESS = r"""
+const SESSIONS_URL = 'SESSIONS_PATH';
+const SHELL_URL = 'SHELL_PATH';
+
+function makeStore() {
+  const values = new Map();
+  return {
+    getItem(key) { return values.has(key) ? values.get(key) : null; },
+    setItem(key, value) { values.set(key, String(value)); },
+    removeItem(key) { values.delete(key); },
+  };
+}
+
+function makeClassList() {
+  const values = new Set();
+  return {
+    add(...names) { names.forEach(name => values.add(name)); },
+    remove(...names) { names.forEach(name => values.delete(name)); },
+    contains(name) { return values.has(name); },
+    toggle(name, force) {
+      const enabled = force === undefined ? !values.has(name) : !!force;
+      if (enabled) values.add(name); else values.delete(name);
+      return enabled;
+    },
+  };
+}
+
+function makeWorld() {
+  const byId = new Map();
+  const frames = [];
+  const cancelledFrames = new Set();
+  const timers = [];
+  let nextFrame = 1;
+  let historyWrites = 0;
+
+  function makeElement(id = '') {
+    let html = '';
+    const element = {
+      id,
+      dataset: {},
+      style: {},
+      classList: makeClassList(),
+      children: [],
+      status: null,
+      value: '',
+      disabled: false,
+      removed: false,
+      addEventListener() {},
+      removeEventListener() {},
+      setAttribute(name, value) { this[name] = value; },
+      getAttribute(name) { return this[name] ?? null; },
+      appendChild(child) { this.children.push(child); return child; },
+      insertBefore(child) { this.children.unshift(child); return child; },
+      contains() { return false; },
+      closest() { return null; },
+      querySelector(selector) {
+        if (selector === '[data-session-list-status]') return this.status;
+        return null;
+      },
+      querySelectorAll() { return []; },
+      focus() { document.activeElement = this; },
+      remove() { this.removed = true; if (this.id) byId.delete(this.id); },
+    };
+    Object.defineProperty(element, 'innerHTML', {
+      get() { return html; },
+      set(value) {
+        html = String(value);
+        if (id === 'session-list' && html === '') {
+          const row = byId.get('session-list-loading');
+          if (row) row.remove();
+        }
+      },
+    });
+    return element;
+  }
+
+  const document = {
+    activeElement: null,
+    getElementById: (id) => byId.get(id) || null,
+    querySelector: () => null,
+    querySelectorAll: () => [],
+    createElement: (tag) => makeElement(tag),
+    createDocumentFragment: () => makeElement('fragment'),
+    addEventListener() {},
+  };
+  globalThis.document = document;
+  globalThis.localStorage = makeStore();
+  globalThis.sessionStorage = makeStore();
+  Object.defineProperty(globalThis, 'navigator', {
+    value: { platform: 'Linux' },
+    configurable: true,
+  });
+  globalThis.history = { replaceState() { historyWrites += 1; } };
+  globalThis.window = {
+    document,
+    innerWidth: 1024,
+    innerHeight: 768,
+    location: { origin: 'http://odysseus.test', hash: '', pathname: '/', href: '/' },
+    addEventListener() {},
+    removeEventListener() {},
+    chatModule: {
+      detachCurrentStream() {},
+      showWelcomeScreen() {},
+    },
+    __odysseusDefaultChat: {
+      endpoint_url: 'http://model.test',
+      model: 'test/model',
+      endpoint_id: 'endpoint-1',
+    },
+  };
+  globalThis.location = window.location;
+  globalThis.requestAnimationFrame = (fn) => {
+    const id = nextFrame++;
+    frames.push({ id, fn });
+    return id;
+  };
+  globalThis.cancelAnimationFrame = (id) => cancelledFrames.add(id);
+  globalThis.setTimeout = (fn, ms) => { timers.push({ fn, ms }); return timers.length; };
+  globalThis.clearTimeout = () => {};
+  globalThis.__sessionErrors = [];
+
+  return {
+    add(id, options = {}) {
+      const element = makeElement(id);
+      if (options.statusText !== undefined) {
+        element.status = { textContent: options.statusText };
+      }
+      if (options.value !== undefined) element.value = options.value;
+      byId.set(id, element);
+      return element;
+    },
+    paint(rounds = 1) {
+      for (let i = 0; i < rounds; i += 1) {
+        const due = frames.splice(0, frames.length);
+        for (const frame of due) {
+          if (!cancelledFrames.has(frame.id)) frame.fn();
+        }
+      }
+    },
+    runTimers() {
+      const due = timers.splice(0, timers.length);
+      for (const timer of due) timer.fn();
+    },
+    byId,
+    historyWrites: () => historyWrites,
+    resetHistoryWrites: () => { historyWrites = 0; },
+  };
+}
+
+const world = makeWorld();
+world.add('session-list');
+world.add('sessions-section');
+const message = world.add('message', { value: 'draft before seed' });
+
+const responses = [
+  {
+    ok: true,
+    status: 200,
+    json: async () => [{ id: 'existing', name: 'Existing', folder: 'Assistant', archived: false }],
+  },
+  {
+    ok: false,
+    status: 503,
+    json: async () => ({ detail: 'temporarily unavailable' }),
+  },
+];
+let fetchCount = 0;
+globalThis.fetch = async () => {
+  fetchCount += 1;
+  const response = responses.shift();
+  if (!response) throw new Error('unexpected fetch');
+  return response;
+};
+
+const sessions = await import(SESSIONS_URL + '?bootstrap');
+const shell = await import(SHELL_URL + '?bootstrap');
+
+const seeded = await sessions.loadSessions();
+world.paint(1);
+localStorage.setItem('lastSessionId', 'existing');
+message.value = 'draft must survive';
+document.activeElement = null;
+world.resetHistoryWrites();
+const loader = world.add('app-loader');
+const row = world.add('session-list-loading', { statusText: 'Loading chats…' });
+let opened = 0;
+shell.deferRouteOpener('/email', () => { opened += 1; });
+
+const hydrated = await shell.settleSessionHydration(() => sessions.loadSessions());
+const beforePaint = row.status.textContent;
+world.paint(2);
+world.runTimers();
+const staleRouteRan = shell.runDeferredRouteOpener({ sessionsSettled: true });
+
+const errorsBeforeAuth = __sessionErrors.length;
+globalThis.fetch = async () => {
+  fetchCount += 1;
+  const response = { ok: false, status: 401, json: async () => ({ detail: 'expired' }) };
+  window.location.href = '/login'; // app.js global fetch-wrapper behaviour
+  return response;
+};
+const authResult = await sessions.loadSessions();
+
+console.log(JSON.stringify({
+  seeded,
+  hydrated,
+  beforePaint,
+  afterPaint: row.status.textContent,
+  rowStillPresent: world.byId.has('session-list-loading'),
+  loaderRemoved: loader.removed,
+  opened,
+  staleRouteRan,
+  fetchCount,
+  sessionIds: sessions.getSessions().map(session => session.id),
+  pendingChat: sessions.hasPendingChat(),
+  draft: message.value,
+  lastSessionId: localStorage.getItem('lastSessionId'),
+  historyWrites: world.historyWrites(),
+  errors: __sessionErrors,
+  authResult,
+  authRedirect: window.location.href,
+  authAddedError: __sessionErrors.length !== errorsBeforeAuth,
+}));
+"""
+
+
+@pytest.fixture(scope="module")
+def results(tmp_path_factory):
+    if not _HAS_NODE:
+        pytest.skip("node is not installed")
+
+    module_dir = tmp_path_factory.mktemp("session-bootstrap-js")
+    source = _SESSIONS.read_text(encoding="utf-8")
+    for original, replacement in _IMPORT_REWRITES.items():
+        assert original in source, f"sessions import changed: {original}"
+        source = source.replace(original, replacement, 1)
+    sessions_module = module_dir / "sessions.mjs"
+    sessions_module.write_text(source, encoding="utf-8")
+    for name, stub in _STUBS.items():
+        (module_dir / name).write_text(stub, encoding="utf-8")
+
+    harness = _HARNESS.replace("SESSIONS_PATH", sessions_module.as_uri()).replace(
+        "SHELL_PATH", _SHELL_URL
+    )
+    proc = subprocess.run(
+        ["node", "--input-type=module", "-e", harness],
+        capture_output=True,
+        text=True,
+        timeout=60,
+    )
+    assert proc.returncode == 0, f"node harness failed:\n{proc.stderr}"
+    return json.loads(proc.stdout.strip().splitlines()[-1])
+
+
+def test_fulfilled_503_is_not_applied_as_an_empty_session_list(results):
+    assert results["seeded"] is True
+    assert results["hydrated"] is False
+    assert results["sessionIds"] == ["existing"]
+    assert results["pendingChat"] is False, "failure created a default direct chat"
+    assert results["draft"] == "draft must survive"
+    assert results["lastSessionId"] == "existing"
+    assert results["historyWrites"] == 0
+
+
+def test_fulfilled_503_keeps_failure_state_and_route_deferred(results):
+    assert results["beforePaint"] == "Loading chats…"
+    assert results["afterPaint"] == "Chats unavailable"
+    assert results["rowStillPresent"] is True
+    assert results["loaderRemoved"] is True
+    assert results["opened"] == 0
+    assert results["staleRouteRan"] is False
+    assert results["errors"] == [
+        "Failed to load sessions: temporarily unavailable",
+    ]
+
+
+def test_401_keeps_global_auth_redirect_contract(results):
+    assert results["authResult"] is False
+    assert results["authRedirect"] == "/login"
+    assert results["authAddedError"] is False
+    assert results["sessionIds"] == ["existing"]

tests/test_startup_shell_js.py

@@ -0,0 +1,377 @@
+"""Pin the startup shell contract (static/js/startupShell.js).
+
+Driven through `node --input-type=module` against a stub DOM and a manually
+pumped frame/timer clock, so the real module runs without a browser (same
+approach as test_composer_arrow_up_recall_js.py). Skips when `node` is absent.
+
+Locks in the behaviour #5926 asks for: the shell is revealed one paint after
+wiring and does not wait on /api/sessions; the loader node survives hydration
+as a startup sentinel but is always retired once hydration settles; the sidebar
+owns its own loading/failure row and a successful zero-session render never
+shows a false failure; and a URL route opens only after the data it actually
+needs is authoritatively available.
+"""
+import json
+import shutil
+import subprocess
+from pathlib import Path
+
+import pytest
+
+_REPO = Path(__file__).resolve().parent.parent
+_MODULE = _REPO / "static" / "js" / "startupShell.js"
+_MODULE_URL = _MODULE.as_uri()
+_HAS_NODE = shutil.which("node") is not None
+
+_HARNESS = r"""
+const MODULE_URL = 'MODULE_PATH';
+
+// ── Stub DOM + a clock we pump by hand ────────────────────────────────────
+function makeWorld() {
+  const byId = new Map();
+  const frames = [];
+  const timers = [];
+  const world = {
+    byId,
+    waveStops: 0,
+    addElement(id, { statusText = null } = {}) {
+      const el = {
+        id,
+        dataset: {},
+        style: {},
+        attrs: {},
+        removed: false,
+        status: null,
+        setAttribute(k, v) { this.attrs[k] = v; },
+        getAttribute(k) { return this.attrs[k]; },
+        remove() { this.removed = true; byId.delete(this.id); },
+        querySelector(sel) {
+          return sel === '[data-session-list-status]' ? this.status : null;
+        },
+      };
+      if (statusText !== null) el.status = { textContent: statusText };
+      byId.set(id, el);
+      return el;
+    },
+    // One "paint" = one round of already-queued rAF callbacks. afterNextPaint
+    // chains two, so a committed paint takes two rounds.
+    paint(rounds = 1) {
+      for (let i = 0; i < rounds; i++) {
+        const due = frames.splice(0, frames.length);
+        for (const fn of due) fn();
+      }
+    },
+    runTimers() {
+      const due = timers.splice(0, timers.length);
+      for (const t of due) t.fn();
+    },
+    pendingTimers() { return timers.length; },
+  };
+  globalThis.document = { getElementById: (id) => byId.get(id) || null };
+  globalThis.window = { __odysseusLoaderWaveStop: () => { world.waveStops += 1; } };
+  globalThis.requestAnimationFrame = (fn) => { frames.push(fn); return frames.length; };
+  globalThis.setTimeout = (fn, ms) => { timers.push({ fn, ms }); return timers.length; };
+  return world;
+}
+
+// Fresh module instance per case so deferred-route state cannot leak.
+let _instance = 0;
+async function loadModule() {
+  _instance += 1;
+  return import(MODULE_URL + '?case=' + _instance);
+}
+
+function loaderSnapshot(loader) {
+  return {
+    revealed: loader.dataset.shellRevealed === 'true',
+    opacity: loader.style.opacity ?? null,
+    pointerEvents: loader.style.pointerEvents ?? null,
+    ariaHidden: loader.getAttribute('aria-hidden') ?? null,
+    removed: loader.removed,
+  };
+}
+
+const cases = {};
+
+cases.reveal_waits_one_paint_then_keeps_node = async () => {
+  const w = makeWorld();
+  const loader = w.addElement('app-loader');
+  const shell = await loadModule();
+  shell.revealApplicationShellAfterPaint();
+  const beforePaint = loaderSnapshot(loader);
+  w.paint(1);
+  const afterOneFrame = loaderSnapshot(loader);
+  w.paint(1);
+  return {
+    beforePaint,
+    afterOneFrame,
+    afterPaint: loaderSnapshot(loader),
+    waveStops: w.waveStops,
+    stillInDocument: w.byId.has('app-loader'),
+  };
+};
+
+cases.reveal_is_idempotent = async () => {
+  const w = makeWorld();
+  const loader = w.addElement('app-loader');
+  const shell = await loadModule();
+  shell.revealApplicationShellAfterPaint();
+  shell.revealApplicationShellAfterPaint();
+  w.paint(2);
+  shell.revealApplicationShellAfterPaint();
+  w.paint(2);
+  return { waveStops: w.waveStops, snapshot: loaderSnapshot(loader) };
+};
+
+cases.remove_retires_the_loader_node = async () => {
+  const w = makeWorld();
+  const loader = w.addElement('app-loader');
+  const shell = await loadModule();
+  shell.removeApplicationLoader();
+  const beforeTimers = loaderSnapshot(loader);
+  w.runTimers();
+  return { beforeTimers, afterTimers: loaderSnapshot(loader) };
+};
+
+cases.failed_hydration_marks_sidebar_row = async () => {
+  const w = makeWorld();
+  w.addElement('app-loader');
+  const row = w.addElement('session-list-loading', { statusText: 'Loading chats…' });
+  const shell = await loadModule();
+  await shell.settleSessionHydration(() => Promise.reject(new Error('boom')));
+  const beforePaint = row.status.textContent;
+  w.paint(2);
+  w.runTimers();
+  return {
+    beforePaint,
+    afterPaint: row.status.textContent,
+    loaderRemoved: !w.byId.has('app-loader'),
+  };
+};
+
+// A successful load with zero sessions must not schedule a failure write.
+cases.zero_session_success_shows_no_failure = async () => {
+  const w = makeWorld();
+  w.addElement('app-loader');
+  const row = w.addElement('session-list-loading', { statusText: 'Loading chats…' });
+  const shell = await loadModule();
+  await shell.settleSessionHydration(() => Promise.resolve(true));
+  w.paint(1);
+  row.remove();            // renderSessionList() clearing #session-list
+  w.paint(1);
+  return { statusText: row.status.textContent, rowRemoved: row.removed };
+};
+
+// The whole point is getting /api/sessions off the critical path, not later.
+cases.hydration_starts_synchronously = async () => {
+  const w = makeWorld();
+  w.addElement('app-loader');
+  const shell = await loadModule();
+  let started = false;
+  const done = shell.settleSessionHydration(() => { started = true; return Promise.resolve(true); });
+  const startedBeforeAwait = started;
+  await done;
+  return { startedBeforeAwait };
+};
+
+cases.synchronous_load_failure_still_settles = async () => {
+  const w = makeWorld();
+  w.addElement('app-loader');
+  const row = w.addElement('session-list-loading', { statusText: 'Loading chats…' });
+  const shell = await loadModule();
+  let opened = 0;
+  shell.deferRouteOpener('/email', () => { opened += 1; });
+  let threw = false;
+  let succeeded = true;
+  try {
+    succeeded = await shell.settleSessionHydration(() => { throw new Error('module blew up'); });
+  } catch (_) { threw = true; }
+  w.paint(2);
+  w.runTimers();
+  return {
+    threw,
+    succeeded,
+    opened,
+    statusText: row.status.textContent,
+    loaderRemoved: !w.byId.has('app-loader'),
+    ranAfterFailure: shell.runDeferredRouteOpener({ sessionsSettled: true }),
+  };
+};
+
+cases.route_without_session_data_opens_before_hydration = async () => {
+  const w = makeWorld();
+  w.addElement('app-loader');
+  const shell = await loadModule();
+  let opened = 0;
+  shell.deferRouteOpener('/notes', () => { opened += 1; });
+  const ranEarly = shell.runDeferredRouteOpener();
+  const openedAfterEarly = opened;
+  const ranAgain = shell.runDeferredRouteOpener({ sessionsSettled: true });
+  return { ranEarly, openedAfterEarly, ranAgain, opened };
+};
+
+cases.route_with_session_data_waits_for_hydration = async () => {
+  const w = makeWorld();
+  w.addElement('app-loader');
+  const shell = await loadModule();
+  let opened = 0;
+  shell.deferRouteOpener('/email', () => { opened += 1; });
+  const ranEarly = shell.runDeferredRouteOpener();
+  const openedAfterEarly = opened;
+  const succeeded = await shell.settleSessionHydration(() => Promise.resolve(true));
+  return {
+    ranEarly,
+    openedAfterEarly,
+    openedAfterHydration: opened,
+    succeeded,
+    needsSessions: [shell.routeNeedsSessionData('/email'), shell.routeNeedsSessionData('/notes')],
+  };
+};
+
+cases.missing_session_module_keeps_route_deferred = async () => {
+  const w = makeWorld();
+  w.addElement('app-loader');
+  const row = w.addElement('session-list-loading', { statusText: 'Loading chats…' });
+  const shell = await loadModule();
+  let opened = 0;
+  shell.deferRouteOpener('/email', () => { opened += 1; });
+  const succeeded = await shell.settleSessionHydration(null);
+  w.paint(2);
+  w.runTimers();
+  return {
+    opened,
+    succeeded,
+    statusText: row.status.textContent,
+    loaderRemoved: !w.byId.has('app-loader'),
+    ranAfterFailure: shell.runDeferredRouteOpener({ sessionsSettled: true }),
+  };
+};
+
+cases.throwing_route_opener_is_contained = async () => {
+  const w = makeWorld();
+  w.addElement('app-loader');
+  const shell = await loadModule();
+  shell.deferRouteOpener('/notes', () => { throw new Error('opener blew up'); });
+  let threw = false;
+  let ran = false;
+  try { ran = shell.runDeferredRouteOpener(); } catch (_) { threw = true; }
+  return { threw, ran, ranAgain: shell.runDeferredRouteOpener({ sessionsSettled: true }) };
+};
+
+const out = {};
+for (const [name, fn] of Object.entries(cases)) out[name] = await fn();
+console.log(JSON.stringify(out));
+""".replace("MODULE_PATH", _MODULE_URL)
+
+
+@pytest.fixture(scope="module")
+def results():
+    if not _HAS_NODE:
+        pytest.skip("node is not installed")
+    proc = subprocess.run(
+        ["node", "--input-type=module", "-e", _HARNESS],
+        capture_output=True,
+        text=True,
+        timeout=60,
+    )
+    assert proc.returncode == 0, f"node harness failed:\n{proc.stderr}"
+    return json.loads(proc.stdout.strip().splitlines()[-1])
+
+
+def test_module_exists():
+    assert _MODULE.is_file(), f"missing {_MODULE}"
+
+
+def test_shell_is_revealed_one_paint_after_wiring(results):
+    r = results["reveal_waits_one_paint_then_keeps_node"]
+    assert r["beforePaint"]["revealed"] is False, "revealed before any frame ran"
+    assert r["afterOneFrame"]["revealed"] is False, "revealed before the paint committed"
+    assert r["afterPaint"] == {
+        "revealed": True,
+        "opacity": "0",
+        "pointerEvents": "none",
+        "ariaHidden": "true",
+        "removed": False,
+    }
+    assert r["waveStops"] == 1, "loader wave interval kept running after reveal"
+
+
+def test_revealed_loader_stays_as_startup_sentinel(results):
+    # sessions.js / sidebar-layout.js read #app-loader as "startup in progress".
+    r = results["reveal_waits_one_paint_then_keeps_node"]
+    assert r["stillInDocument"] is True
+    assert r["afterPaint"]["removed"] is False
+
+
+def test_reveal_is_idempotent(results):
+    r = results["reveal_is_idempotent"]
+    assert r["waveStops"] == 1, "reveal ran its side effects more than once"
+    assert r["snapshot"]["revealed"] is True
+
+
+def test_loader_node_is_retired_after_the_fade(results):
+    r = results["remove_retires_the_loader_node"]
+    assert r["beforeTimers"]["revealed"] is True, "removal should hide immediately"
+    assert r["beforeTimers"]["removed"] is False, "removal should wait for the fade"
+    assert r["afterTimers"]["removed"] is True, "loader node outlived hydration"
+
+
+def test_failed_session_load_marks_the_sidebar_row(results):
+    r = results["failed_hydration_marks_sidebar_row"]
+    assert r["beforePaint"] == "Loading chats…", "failure written before the render frame"
+    assert r["afterPaint"] == "Chats unavailable"
+    assert r["loaderRemoved"] is True, "a failed load must still free the shell"
+
+
+def test_zero_session_success_never_shows_a_failure(results):
+    r = results["zero_session_success_shows_no_failure"]
+    assert r["rowRemoved"] is True
+    assert r["statusText"] == "Loading chats…", "false 'Chats unavailable' on empty success"
+
+
+def test_hydration_request_starts_synchronously(results):
+    r = results["hydration_starts_synchronously"]
+    assert r["startedBeforeAwait"] is True, "/api/sessions start was deferred a microtask"
+
+
+def test_synchronous_load_failure_still_settles(results):
+    r = results["synchronous_load_failure_still_settles"]
+    assert r["threw"] is False, "a throwing loadSessions must not escape"
+    assert r["succeeded"] is False
+    assert r["opened"] == 0, "session-dependent route opened without session data"
+    assert r["ranAfterFailure"] is False, "failed startup left a stale route opener"
+    assert r["statusText"] == "Chats unavailable"
+    assert r["loaderRemoved"] is True
+
+
+def test_route_needing_no_session_data_opens_before_hydration(results):
+    r = results["route_without_session_data_opens_before_hydration"]
+    assert r["ranEarly"] is True, "/notes waited on /api/sessions it does not read"
+    assert r["openedAfterEarly"] == 1
+    assert r["ranAgain"] is False, "route opener fired twice"
+    assert r["opened"] == 1
+
+
+def test_route_needing_session_data_waits_for_hydration(results):
+    r = results["route_with_session_data_waits_for_hydration"]
+    assert r["ranEarly"] is False, "/email opened before the session list was there"
+    assert r["openedAfterEarly"] == 0
+    assert r["openedAfterHydration"] == 1
+    assert r["succeeded"] is True
+    assert r["needsSessions"] == [True, False]
+
+
+def test_missing_session_module_still_settles_without_opening_data_route(results):
+    r = results["missing_session_module_keeps_route_deferred"]
+    assert r["succeeded"] is False
+    assert r["opened"] == 0, "route opened without the session module it depends on"
+    assert r["ranAfterFailure"] is False, "missing module left a stale route opener"
+    assert r["statusText"] == "Chats unavailable"
+    assert r["loaderRemoved"] is True
+
+
+def test_throwing_route_opener_is_contained(results):
+    r = results["throwing_route_opener_is_contained"]
+    assert r["threw"] is False
+    assert r["ran"] is True
+    assert r["ranAgain"] is False, "a failed opener must not be retried"