diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 229a4d599..5d70ee765 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -256,3 +256,10 @@ jobs:
env:
PYTEST_SHARD: ${{ matrix.shard }}
run: python -m pytest -q -rs --durations=25 --shard "$PYTEST_SHARD"
+
+ - name: Playwright mobile layout checks (shard 1/4 only)
+ if: steps.docs-check.outputs.docs_only != 'true' && matrix.shard == '1/4'
+ run: |
+ ODYSSEUS_TEST_PYTHON=python ODYSSEUS_LAYOUT_BROWSER=chromium npx --no-install playwright test \
+ --config tests/e2e/ios-layout.config.cjs \
+ --reporter=line
diff --git a/package.json b/package.json
index aa454e017..79cf83c3d 100644
--- a/package.json
+++ b/package.json
@@ -9,7 +9,11 @@
"test:photo-editor": "playwright test --config tests/e2e/playwright.config.js",
"test:photo-editor:install": "playwright install chromium firefox webkit",
"test:photo-editor:firefox": "PHOTO_EDITOR_E2E_BROWSER=firefox playwright test --config tests/e2e/playwright.config.js",
- "test:photo-editor:webkit": "PHOTO_EDITOR_E2E_BROWSER=webkit playwright test --config tests/e2e/playwright.config.js"
+ "test:photo-editor:webkit": "PHOTO_EDITOR_E2E_BROWSER=webkit playwright test --config tests/e2e/playwright.config.js",
+ "test:ios-layout": "playwright test --config tests/e2e/ios-layout.config.cjs",
+ "test:ios-layout:chromium": "ODYSSEUS_LAYOUT_BROWSER=chromium playwright test --config tests/e2e/ios-layout.config.cjs",
+ "test:ios-layout:webkit": "ODYSSEUS_LAYOUT_BROWSER=webkit playwright test --config tests/e2e/ios-layout.config.cjs",
+ "test:ios-layout:install": "playwright install chromium webkit"
},
"devDependencies": {
"@antithesishq/bombadil": "^0.7.0",
diff --git a/routes/cookbook_helpers.py b/routes/cookbook_helpers.py
index 856c8bdb5..24419c29c 100644
--- a/routes/cookbook_helpers.py
+++ b/routes/cookbook_helpers.py
@@ -1030,6 +1030,166 @@ def _append_llama_cpp_linux_accel_build_lines(runner_lines: list[str]) -> None:
runner_lines.append(' fi # end _odysseus_have_prebuilt guard')
+ODYSSEUS_LLAMA_SHIM_MARKER = "# Auto-generated by Odysseus Cookbook: a `llama-server` lookalike"
+
+
+def _append_llama_server_resolution_definition_lines(runner_lines: list[str]) -> None:
+ """Define the helper shell function that discovers, reconciles and prioritizes llama-server."""
+ marker = f"'{_bash_squote(ODYSSEUS_LLAMA_SHIM_MARKER)}'"
+ runner_lines.append('_odysseus_resolve_llama_server() {')
+ runner_lines.append(' _odysseus_llama_bin=""')
+ runner_lines.append(f' local _marker={marker}')
+ runner_lines.append(' local _saved_ifs="$IFS"')
+ runner_lines.append(" IFS=':'")
+ runner_lines.append(' local -a _parts')
+ runner_lines.append(' read -r -a _parts <<< "$PATH"')
+ runner_lines.append(' IFS="$_saved_ifs"')
+ runner_lines.append(' local _dir _cand')
+ runner_lines.append(' for _dir in "${_parts[@]}"; do')
+ runner_lines.append(' [ -n "$_dir" ] || continue')
+ runner_lines.append(' _cand="$_dir/llama-server"')
+ runner_lines.append(' [ -x "$_cand" ] || continue')
+ runner_lines.append(' if [ -f "$_cand" ] && [ ! -L "$_cand" ] && grep -Fxq "$_marker" "$_cand" 2>/dev/null; then')
+ runner_lines.append(' continue')
+ runner_lines.append(' fi')
+ runner_lines.append(' if "$_cand" --version >/dev/null 2>&1; then')
+ runner_lines.append(' _odysseus_llama_bin="$_cand"')
+ runner_lines.append(' break')
+ runner_lines.append(' fi')
+ runner_lines.append(' done')
+ runner_lines.append(' if [ -f "$HOME/bin/llama-server" ] && [ ! -L "$HOME/bin/llama-server" ] && grep -Fxq "$_marker" "$HOME/bin/llama-server" 2>/dev/null; then')
+ runner_lines.append(' if [ -n "$_odysseus_llama_bin" ]; then')
+ runner_lines.append(' echo "[odysseus] Native llama-server detected — retiring Odysseus compatibility shim in ~/bin"')
+ runner_lines.append(' rm -f "$HOME/bin/llama-server"')
+ runner_lines.append(' hash -r')
+ runner_lines.append(' elif python3 -c "import llama_cpp.server" 2>/dev/null; then')
+ runner_lines.append(' _odysseus_llama_bin="$HOME/bin/llama-server"')
+ runner_lines.append(' else')
+ runner_lines.append(' echo "[odysseus] Removing stale Odysseus llama-server shim (python3 -m llama_cpp.server unavailable)"')
+ runner_lines.append(' rm -f "$HOME/bin/llama-server"')
+ runner_lines.append(' hash -r')
+ runner_lines.append(' fi')
+ runner_lines.append(' fi')
+ runner_lines.append(' if [ -n "$_odysseus_llama_bin" ]; then')
+ runner_lines.append(' local _cand_dir')
+ runner_lines.append(' _cand_dir="$(dirname "$_odysseus_llama_bin")"')
+ runner_lines.append(' if [ "${PATH%%:*}" != "$_cand_dir" ]; then')
+ runner_lines.append(' export PATH="$_cand_dir:$PATH"')
+ runner_lines.append(' fi')
+ runner_lines.append(' hash -r')
+ runner_lines.append(' return 0')
+ runner_lines.append(' fi')
+ runner_lines.append(' return 1')
+ runner_lines.append('}')
+
+
+def _append_llama_server_shim_definition_lines(runner_lines: list[str]) -> None:
+ """Define the helper shell function that generates the Odysseus compatibility shim."""
+ _append_llama_server_resolution_definition_lines(runner_lines)
+ marker = f"'{_bash_squote(ODYSSEUS_LLAMA_SHIM_MARKER)}'"
+ runner_lines.append('_odysseus_create_llama_shim() {')
+ runner_lines.append(' local _target="$HOME/bin/llama-server"')
+ runner_lines.append(f' local _marker={marker}')
+ runner_lines.append(' if [ -e "$_target" ] || [ -L "$_target" ]; then')
+ runner_lines.append(' if [ -f "$_target" ] && [ ! -L "$_target" ] && grep -Fxq "$_marker" "$_target" 2>/dev/null; then')
+ runner_lines.append(' : # existing Odysseus shim — safe to replace')
+ runner_lines.append(' else')
+ runner_lines.append(' echo "[odysseus] WARNING: $_target already exists and is not an Odysseus-managed shim; leaving untouched." >&2')
+ runner_lines.append(' return 1')
+ runner_lines.append(' fi')
+ runner_lines.append(' fi')
+ runner_lines.append(' mkdir -p "$HOME/bin" || return 1')
+ runner_lines.append(' local _tmp')
+ runner_lines.append(' _tmp="$(mktemp "$HOME/bin/.llama-server.odysseus.tmp.XXXXXX")" || {')
+ runner_lines.append(' echo "[odysseus] ERROR: unable to create secure temporary llama-server shim in $HOME/bin" >&2')
+ runner_lines.append(' return 1')
+ runner_lines.append(' }')
+ runner_lines.append(" if ! cat > \"$_tmp\" <<'_ODY_LLAMA_SHIM_EOF'")
+ runner_lines.append('#!/usr/bin/env bash')
+ runner_lines.append(ODYSSEUS_LLAMA_SHIM_MARKER)
+ runner_lines.append('# that translates the native CLI to `python -m llama_cpp.server`.')
+ runner_lines.append('# Lets cookbook-generated launch commands run unchanged on hosts')
+ runner_lines.append('# where only the pip llama-cpp-python package is installed.')
+ runner_lines.append('ARGS=()')
+ runner_lines.append('while [ $# -gt 0 ]; do')
+ runner_lines.append(' case "$1" in')
+ runner_lines.append(' -ngl|--gpu-layers|--n-gpu-layers) ARGS+=(--n_gpu_layers "$2"); shift 2 ;;')
+ runner_lines.append(' -c|--ctx-size) ARGS+=(--n_ctx "$2"); shift 2 ;;')
+ runner_lines.append(' -b|--batch-size) ARGS+=(--n_batch "$2"); shift 2 ;;')
+ runner_lines.append(' -ub|--ubatch-size) shift 2 ;; # llama-cpp-python has no separate ubatch')
+ runner_lines.append(' --flash-attn) ARGS+=(--flash_attn true); shift 2 ;;')
+ runner_lines.append(' --cache-type-k) ARGS+=(--type_k "$2"); shift 2 ;;')
+ runner_lines.append(' --cache-type-v) ARGS+=(--type_v "$2"); shift 2 ;;')
+ runner_lines.append(' --n-cpu-moe) ARGS+=(--n_cpu_moe "$2"); shift 2 ;;')
+ runner_lines.append(' --mmproj) ARGS+=(--clip_model_path "$2"); shift 2 ;;')
+ runner_lines.append(' --image-max-tokens) shift 2 ;; # native-only')
+ runner_lines.append(' --no-mmap) ARGS+=(--no_mmap true); shift ;;')
+ runner_lines.append(' --no-warmup) shift ;; # native-only')
+ runner_lines.append(' --chat-template) ARGS+=(--chat_format "$2"); shift 2 ;;')
+ runner_lines.append(' --fit|--split-mode|--tensor-split|--main-gpu|--parallel) shift 2 ;; # native-only')
+ runner_lines.append(' --mlock) ARGS+=(--use_mlock true); shift ;;')
+ runner_lines.append(' *) ARGS+=("$1"); shift ;;')
+ runner_lines.append(' esac')
+ runner_lines.append('done')
+ runner_lines.append('exec python3 -m llama_cpp.server "${ARGS[@]}"')
+ runner_lines.append('_ODY_LLAMA_SHIM_EOF')
+ runner_lines.append(' then')
+ runner_lines.append(' rm -f -- "$_tmp"')
+ runner_lines.append(' return 1')
+ runner_lines.append(' fi')
+ runner_lines.append(' chmod +x "$_tmp" || { rm -f -- "$_tmp"; return 1; }')
+ runner_lines.append(' mv -f -- "$_tmp" "$_target" || { rm -f -- "$_tmp"; return 1; }')
+ runner_lines.append(' hash -r')
+ runner_lines.append(' echo "[odysseus] Created llama-server shim → python -m llama_cpp.server (no native binary needed)"')
+ runner_lines.append('}')
+
+
+def _append_llama_server_shim_reconciliation_lines(runner_lines: list[str]) -> None:
+ """Reconcile an existing ~/bin/llama-server if it is owned by Odysseus Cookbook.
+
+ Invariants:
+ - Never touch an arbitrary user-owned executable or symlink.
+ - If ~/bin/llama-server is an Odysseus generated shim:
+ - If a native llama-server is present and healthy elsewhere on PATH, remove the shim
+ so the native binary is used.
+ - If python3 -m llama_cpp.server is unavailable, remove the stale shim
+ and hash -r so the fallback/build path is triggered.
+ - If no healthy native server exists and llama_cpp.server is working, preserve it.
+ - If a healthy native candidate exists on PATH (even later in PATH), prioritize it and
+ ensure the launched executable is the validated candidate.
+ """
+ runner_lines.append('[ -r ~/.config/odysseus-llama-cpp-env ] && . ~/.config/odysseus-llama-cpp-env')
+ runner_lines.append('if ! declare -F _odysseus_resolve_llama_server >/dev/null 2>&1; then')
+ _append_llama_server_resolution_definition_lines(runner_lines)
+ runner_lines.append('fi')
+ runner_lines.append('_odysseus_resolve_llama_server || true')
+
+
+def _append_llama_server_finalization_lines(runner_lines: list[str], platform_hint: str = "") -> None:
+ """Reconcile post-install launcher availability and enforce fail-closed invariant.
+
+ Guarantees that if python3 -m llama_cpp.server is usable but the `llama-server`
+ command is unresolvable, the compatibility launcher is created. If no usable
+ launcher exists after all build/install attempts, sets ODYSSEUS_PREFLIGHT_EXIT=127.
+ """
+ err_msg = (
+ f"ERROR: llama.cpp serving is not available on {platform_hint} after install attempts."
+ if platform_hint
+ else "ERROR: llama.cpp serving is not available after install/build attempts."
+ )
+ runner_lines.append('if ! declare -F _odysseus_resolve_llama_server >/dev/null 2>&1; then')
+ _append_llama_server_resolution_definition_lines(runner_lines)
+ runner_lines.append('fi')
+ runner_lines.append('if [ -z "$_odysseus_llama_bin" ] && python3 -c "import llama_cpp.server" 2>/dev/null; then')
+ runner_lines.append(' _odysseus_create_llama_shim')
+ runner_lines.append(' _odysseus_resolve_llama_server || true')
+ runner_lines.append('fi')
+ runner_lines.append('if [ -z "$_odysseus_llama_bin" ]; then')
+ runner_lines.append(f' echo "{err_msg}"')
+ runner_lines.append(' ODYSSEUS_PREFLIGHT_EXIT=127')
+ runner_lines.append('fi')
+
+
def _llama_cpp_rebuild_cmd(update_source: bool = False) -> str:
"""Shell command that clears the Cookbook-managed llama.cpp build.
diff --git a/routes/cookbook_routes.py b/routes/cookbook_routes.py
index 02b419894..ae2667f65 100644
--- a/routes/cookbook_routes.py
+++ b/routes/cookbook_routes.py
@@ -57,9 +57,11 @@ from routes.cookbook_helpers import (
_pip_install_no_cache, _user_shell_path_bootstrap, _venv_safe_local_pip_install_cmd,
_diagnose_serve_output, run_ssh_command_async,
_ollama_bind_from_cmd, _pip_install_fallback_chain, _pip_install_no_cache,
- _user_shell_path_bootstrap, _venv_safe_local_pip_install_cmd,
_append_pip_install_runner_lines, _pip_install_command_without_break_system_packages,
_normalize_llama_cpp_python_cache_types,
+ _append_llama_server_shim_definition_lines,
+ _append_llama_server_shim_reconciliation_lines,
+ _append_llama_server_finalization_lines,
ModelDownloadRequest, ServeRequest,
)
@@ -2161,7 +2163,7 @@ def setup_cookbook_routes() -> APIRouter:
ps_lines.append('}')
elif "llama_cpp" in req.cmd or "llama-server" in req.cmd:
ps_lines.append('# Auto-install llama-cpp-python if missing')
- ps_lines.append('try { python -c "import llama_cpp" 2>$null } catch {}')
+ ps_lines.append('try { python -c "import llama_cpp.server" 2>$null } catch {}')
ps_lines.append('if ($LASTEXITCODE -ne 0) {')
ps_lines.append(' Write-Host "Installing llama-cpp-python..."')
ps_lines.append(' python -m pip install llama-cpp-python[server]')
@@ -2247,14 +2249,17 @@ def setup_cookbook_routes() -> APIRouter:
# ollama is found (otherwise macOS falls back to a slow source build).
# /opt/homebrew = Apple Silicon, /usr/local = Intel; harmless on Linux.
runner_lines.append('export PATH="$HOME/.local/bin:$HOME/bin:$HOME/llama.cpp/build/bin:/opt/homebrew/bin:/usr/local/bin:$PATH"')
+ _append_llama_server_shim_definition_lines(runner_lines)
+ _append_llama_server_shim_reconciliation_lines(runner_lines)
runner_lines.append('if [ -d /data/data/com.termux ]; then')
runner_lines.append(' # Termux: no native build — use the Python bindings (CPU).')
- runner_lines.append(' if ! python3 -c "import llama_cpp" 2>/dev/null; then')
+ runner_lines.append(' if ! python3 -c "import llama_cpp.server" 2>/dev/null; then')
runner_lines.append(' pkg install -y cmake 2>/dev/null')
runner_lines.append(' pip install numpy diskcache jinja2 2>/dev/null')
runner_lines.append(' CMAKE_ARGS="-DGGML_BLAS=OFF -DGGML_LLAMAFILE=OFF" pip install \'llama-cpp-python[server]\' --no-build-isolation --no-cache-dir 2>&1 || true')
runner_lines.append(' fi')
- runner_lines.append('elif ! command -v llama-server &>/dev/null; then')
+ _append_llama_server_finalization_lines(runner_lines, platform_hint="Termux")
+ runner_lines.append('elif [ -z "$_odysseus_llama_bin" ]; then')
runner_lines.append(' echo "Native llama-server not found — building from source (one-time, may take a few minutes)..."')
runner_lines.append(' mkdir -p ~/bin')
runner_lines.append(' cd ~ && [ -d llama.cpp ] || git clone --depth 1 https://github.com/ggml-org/llama.cpp')
@@ -2271,8 +2276,7 @@ def setup_cookbook_routes() -> APIRouter:
# would reuse the bad settings and fail again. CMAKE_BUILD_TYPE is
# explicit so the binary is optimized (Metal auto-enables on macOS).
runner_lines.append(' cd ~/llama.cpp && rm -rf build && cmake -B build -DCMAKE_BUILD_TYPE=Release \\')
- runner_lines.append(' && cmake --build build -j"$NPROC" --target llama-server \\')
- runner_lines.append(' && ln -sf ~/llama.cpp/build/bin/llama-server ~/bin/llama-server')
+ runner_lines.append(' && cmake --build build -j"$NPROC" --target llama-server')
runner_lines.append(' else')
_append_llama_cpp_linux_accel_build_lines(runner_lines)
runner_lines.append(' fi')
@@ -2296,58 +2300,13 @@ def setup_cookbook_routes() -> APIRouter:
runner_lines.append(' fi')
runner_lines.append(' fi')
runner_lines.append(' fi')
- # SHORT-CIRCUIT before the build/pip fallback: if the
- # native binary is missing but llama_cpp Python is already
- # installed, drop a wrapper at ~/bin/llama-server that
- # translates llama-server CLI args to llama_cpp.server's
- # underscore-style flags. The user's serve command stays
- # `llama-server ...` and "just works" — no build, no cmake,
- # no second install. This is the path that unblocks every
- # remote where pip-installed llama-cpp-python is already
- # working but Cookbook used to insist on a native binary.
- runner_lines.append(' if ! command -v llama-server >/dev/null 2>&1 && python3 -c "import llama_cpp" 2>/dev/null; then')
- runner_lines.append(' mkdir -p ~/bin')
- runner_lines.append(' cat > ~/bin/llama-server <<\'_ODY_LLAMA_SHIM_EOF\'')
- runner_lines.append('#!/usr/bin/env bash')
- runner_lines.append('# Auto-generated by Odysseus Cookbook: a `llama-server` lookalike')
- runner_lines.append('# that translates the native CLI to `python -m llama_cpp.server`.')
- runner_lines.append('# Lets cookbook-generated launch commands run unchanged on hosts')
- runner_lines.append('# where only the pip llama-cpp-python package is installed.')
- runner_lines.append('ARGS=()')
- runner_lines.append('while [ $# -gt 0 ]; do')
- runner_lines.append(' case "$1" in')
- runner_lines.append(' -ngl|--gpu-layers|--n-gpu-layers) ARGS+=(--n_gpu_layers "$2"); shift 2 ;;')
- runner_lines.append(' -c|--ctx-size) ARGS+=(--n_ctx "$2"); shift 2 ;;')
- runner_lines.append(' -b|--batch-size) ARGS+=(--n_batch "$2"); shift 2 ;;')
- runner_lines.append(' -ub|--ubatch-size) shift 2 ;; # llama-cpp-python has no separate ubatch')
- runner_lines.append(' --flash-attn) ARGS+=(--flash_attn true); shift 2 ;;')
- runner_lines.append(' --cache-type-k) ARGS+=(--type_k "$2"); shift 2 ;;')
- runner_lines.append(' --cache-type-v) ARGS+=(--type_v "$2"); shift 2 ;;')
- runner_lines.append(' --n-cpu-moe) ARGS+=(--n_cpu_moe "$2"); shift 2 ;;')
- runner_lines.append(' --mmproj) ARGS+=(--clip_model_path "$2"); shift 2 ;;')
- runner_lines.append(' --image-max-tokens) shift 2 ;; # native-only')
- runner_lines.append(' --no-mmap) ARGS+=(--no_mmap true); shift ;;')
- runner_lines.append(' --no-warmup) shift ;; # native-only')
- runner_lines.append(' --chat-template) ARGS+=(--chat_format "$2"); shift 2 ;;')
- runner_lines.append(' --fit|--split-mode|--tensor-split|--main-gpu|--parallel) shift 2 ;; # native-only')
- runner_lines.append(' --mlock) ARGS+=(--use_mlock true); shift ;;')
- runner_lines.append(' *) ARGS+=("$1"); shift ;;')
- runner_lines.append(' esac')
- runner_lines.append('done')
- runner_lines.append('exec python3 -m llama_cpp.server "${ARGS[@]}"')
- runner_lines.append('_ODY_LLAMA_SHIM_EOF')
- runner_lines.append(' chmod +x ~/bin/llama-server')
- runner_lines.append(' echo "[odysseus] Created llama-server shim → python -m llama_cpp.server (no native binary needed)"')
- runner_lines.append(' fi')
- runner_lines.append(' # If the native build failed, fall back to the Python bindings.')
- runner_lines.append(' if ! command -v llama-server &>/dev/null && ! python3 -c "import llama_cpp" 2>/dev/null; then')
+ runner_lines.append(' _odysseus_resolve_llama_server || true')
+ # If the native build failed, fall back to the Python bindings.
+ runner_lines.append(' if [ -z "$_odysseus_llama_bin" ] && ! python3 -c "import llama_cpp.server" 2>/dev/null; then')
runner_lines.append(' echo "llama-server build failed — installing Python bindings as fallback..."')
runner_lines.append(f" {_pip_install_fallback_chain('llama-cpp-python[server]', python_cmd='pip')} || true")
runner_lines.append(' fi')
- runner_lines.append(' if ! command -v llama-server &>/dev/null && ! python3 -c "import llama_cpp" 2>/dev/null; then')
- runner_lines.append(' echo "ERROR: llama.cpp serving is not available after install/build attempts."')
- runner_lines.append(' ODYSSEUS_PREFLIGHT_EXIT=127')
- runner_lines.append(' fi')
+ _append_llama_server_finalization_lines(runner_lines)
runner_lines.append('fi')
elif re.search(r"\bollama\s+serve\b", req.cmd):
handled_ollama_serve = True
diff --git a/routes/session_routes.py b/routes/session_routes.py
index 1c903f194..388de5b20 100644
--- a/routes/session_routes.py
+++ b/routes/session_routes.py
@@ -1315,7 +1315,7 @@ def setup_session_routes(
def auto_sort_sessions(request: Request, skip_llm: bool = False):
"""Use AI to categorize all sessions into folders.
- Phase 1 deletes empty/throwaway sessions and Phase 2 asks the LLM
+ Phase 1 deletes empty/Incognito sessions and Phase 2 asks the LLM
to assign folders. When `skip_llm=true` the endpoint returns
after Phase 1 — used by the "Tidy (no AI)" UI affordance so
users can clean junk without spending tokens.
@@ -1326,21 +1326,11 @@ def setup_session_routes(
single_user_mode = not user and _auth_disabled()
user_sessions = session_manager.get_sessions_for_user(user)
- # Delete empty and throwaway sessions before sorting
+ # Saved conversations are never disposable based on their title or prompt.
from core.database import ChatMessage as DbMsg
db = SessionLocal()
deleted_empty = 0
deleted_throwaway = 0
- # Names that indicate a throwaway/test session (case-insensitive exact or prefix match)
- _THROWAWAY_NAMES = {
- "test", "testing", "asdf", "asd", "hello", "hi", "hey",
- "yo", "sup", "hola", "hii", "hiii", "heyo",
- "foo", "bar", "baz", "tmp", "temp", "scratch", "untitled",
- "new chat", "delete", "remove", "junk", "trash", "xxx",
- "abc", "qwerty", "blah", "stuff", "whatever", "idk",
- "ok", "lol", "bruh", "hmm", "hm", "meh",
- }
- _THROWAWAY_MAX_MESSAGES = 4 # only delete if <= this many messages
try:
rows_q = db.query(DbSession).filter(DbSession.archived == False)
if user:
@@ -1349,15 +1339,11 @@ def setup_session_routes(
rows_q = rows_q.filter(DbSession.owner == user)
rows = rows_q.limit(2000).all()
folder_map = {r.id: r.folder for r in rows}
- # Precompute per-session message counts in TWO aggregate queries
+ # Precompute per-session message counts in one aggregate query
# instead of 1–3 queries PER session — with many chats the per-row
# loop was doing thousands of round-trips and blowing the timeout.
from sqlalchemy import func as _sa_func
_counts = dict(db.query(DbMsg.session_id, _sa_func.count(DbMsg.id)).group_by(DbMsg.session_id).all())
- _asst_counts = dict(
- db.query(DbMsg.session_id, _sa_func.count(DbMsg.id))
- .filter(DbMsg.role == "assistant").group_by(DbMsg.session_id).all()
- )
cleanup_now = utcnow_naive()
for row in rows:
# Never delete important sessions
@@ -1367,9 +1353,10 @@ def setup_session_routes(
if (row.name or "").strip() == "Incognito":
should_delete = True
deleted_throwaway += 1
- db.delete(row)
if hasattr(session_manager, 'delete_session'):
session_manager.delete_session(row.id)
+ else:
+ db.delete(row)
continue
if is_session_recently_active(row, now=cleanup_now):
continue
@@ -1378,31 +1365,11 @@ def setup_session_routes(
if msg_count == 0:
should_delete = True
deleted_empty += 1
- elif msg_count <= _THROWAWAY_MAX_MESSAGES:
- name = (row.name or "").strip().lower()
- # Check first user message content (AI renames sessions, so
- # "hi" becomes "Casual Greeting Exchange" — name alone won't match)
- first_msg = db.query(DbMsg.content).filter(
- DbMsg.session_id == row.id, DbMsg.role == "user"
- ).order_by(DbMsg.timestamp).first()
- first_text = (first_msg[0] or "").strip().lower() if first_msg else ""
- # Count assistant messages — if user sent something but AI never replied, it's dead
- assistant_count = _asst_counts.get(row.id, 0)
- if name in _THROWAWAY_NAMES or name.startswith("chat:") or first_text in _THROWAWAY_NAMES:
- should_delete = True
- deleted_throwaway += 1
- # Single user message with no AI response = dead session
- elif msg_count == 1 and assistant_count == 0:
- should_delete = True
- deleted_throwaway += 1
- # Short phrase (1-3 words) with no real AI conversation (<=2 msgs)
- elif msg_count <= 2 and first_text and len(first_text.split()) <= 3 and len(first_text) <= 40:
- should_delete = True
- deleted_throwaway += 1
if should_delete:
- db.delete(row)
if hasattr(session_manager, 'delete_session'):
session_manager.delete_session(row.id)
+ else:
+ db.delete(row)
if deleted_empty or deleted_throwaway:
db.commit()
logger.info(f"Auto-sort: deleted {deleted_empty} empty + {deleted_throwaway} throwaway sessions")
diff --git a/src/mcp_manager.py b/src/mcp_manager.py
index 53112009d..b47d0e1d7 100644
--- a/src/mcp_manager.py
+++ b/src/mcp_manager.py
@@ -10,6 +10,7 @@ import logging
import os
import re
import asyncio
+import contextlib
from typing import Any, Dict, List, Optional, Set, Tuple
from src.database import McpServer, SessionLocal
@@ -383,12 +384,21 @@ class McpManager:
provider = build_provider(server_id, url, on_redirect=_on_redirect)
stack = AsyncExitStack()
- transport = await stack.enter_async_context(streamablehttp_client(url, auth=provider))
- read_stream, write_stream, _get_session_id = transport
- session = await stack.enter_async_context(ClientSession(read_stream, write_stream))
- await session.initialize()
+ try:
+ transport = await stack.enter_async_context(streamablehttp_client(url, auth=provider))
+ read_stream, write_stream, _get_session_id = transport
+ session = await stack.enter_async_context(ClientSession(read_stream, write_stream))
+ await session.initialize()
- tools_result = await session.list_tools()
+ tools_result = await session.list_tools()
+ except BaseException:
+ # Close the half-open transport here, in the task that entered
+ # it. Left for the garbage collector, its AnyIO cancel scope is
+ # exited from the wrong task and the event loop keeps spinning
+ # (#5518). Its own teardown error would only mask the real one.
+ with contextlib.suppress(Exception):
+ await stack.aclose()
+ raise
tools = []
for tool in tools_result.tools:
tools.append({
diff --git a/src/session_actions.py b/src/session_actions.py
index 1efa484e3..9859ef486 100644
--- a/src/session_actions.py
+++ b/src/session_actions.py
@@ -12,16 +12,6 @@ from datetime import datetime, timedelta, timezone
logger = logging.getLogger(__name__)
-# Names that indicate a throwaway/test session
-_THROWAWAY_NAMES = {
- "test", "testing", "asdf", "asd", "hello", "hi", "hey",
- "yo", "sup", "hola", "hii", "hiii", "heyo",
- "foo", "bar", "baz", "tmp", "temp", "scratch", "untitled",
- "new chat", "delete", "remove", "junk", "trash", "xxx",
- "abc", "qwerty", "blah", "stuff", "whatever", "idk",
- "ok", "lol", "bruh", "hmm", "hm", "meh",
-}
-_THROWAWAY_MAX_MESSAGES = 4
_FRESH_EMPTY_SESSION_GRACE = timedelta(minutes=10)
_FRESH_SESSION_GRACE = _FRESH_EMPTY_SESSION_GRACE
@@ -54,14 +44,15 @@ def is_session_recently_active(row, now=None, grace=_FRESH_SESSION_GRACE) -> boo
async def run_auto_sort(owner: str, skip_llm: bool = False, delete_throwaway: bool = True) -> str:
- """Run session cleanup + (optional) AI folder sort for the given owner.
+ """Remove empty/Incognito sessions and optionally organize saved chats.
Args:
owner: user whose sessions to process
- skip_llm: when True, do only Phase 1 (delete empty/throwaway sessions);
+ skip_llm: when True, do only Phase 1 (delete empty/Incognito sessions);
skip Phase 2 (AI folder assignment). Used by the built-in daily
background sweep so it never burns LLM tokens.
- delete_throwaway: when False, only empty/incognito sessions are deleted.
+ delete_throwaway: retained for caller compatibility. Ordinary sessions
+ with saved messages are always preserved, regardless of this flag.
Returns a human-readable summary of what was done.
"""
@@ -71,7 +62,7 @@ async def run_auto_sort(owner: str, skip_llm: bool = False, delete_throwaway: bo
db = SessionLocal()
try:
- # ── Phase 1: Delete empty/throwaway sessions ──
+ # ── Phase 1: Delete only empty and explicitly Incognito sessions ──
deleted_empty = 0
deleted_throwaway = 0
@@ -93,47 +84,13 @@ async def run_auto_sort(owner: str, skip_llm: bool = False, delete_throwaway: bo
if is_session_recently_active(row, now=cleanup_now):
continue
- msg_count = db.query(DbMsg.id).filter(
+ has_messages = db.query(DbMsg.id).filter(
DbMsg.session_id == row.id
- ).limit(_THROWAWAY_MAX_MESSAGES + 1).count()
- should_delete = False
-
- if msg_count == 0:
+ ).first() is not None
+ if not has_messages:
if is_fresh:
continue
- should_delete = True
deleted_empty += 1
- elif delete_throwaway and msg_count <= _THROWAWAY_MAX_MESSAGES:
- name = (row.name or "").strip().lower()
- first_msg = db.query(DbMsg.content).filter(
- DbMsg.session_id == row.id, DbMsg.role == "user"
- ).order_by(DbMsg.timestamp).first()
- first_text = (first_msg[0] or "").strip().lower() if first_msg else ""
- assistant_count = db.query(DbMsg.id).filter(
- DbMsg.session_id == row.id, DbMsg.role == "assistant"
- ).limit(1).count()
-
- if name in _THROWAWAY_NAMES or name.startswith("chat:") or first_text in _THROWAWAY_NAMES:
- should_delete = True
- deleted_throwaway += 1
- elif msg_count == 1 and assistant_count == 0:
- should_delete = True
- deleted_throwaway += 1
- elif msg_count <= 4 and first_text and len(first_text.split()) <= 8 and len(first_text) <= 80:
- # Short trivial chats — e.g. "write hi to a friend" → "Hi!"
- should_delete = True
- deleted_throwaway += 1
- else:
- # Aggressive: total message text under 250 chars combined = trivial
- msg_rows = db.query(DbMsg.content).filter(
- DbMsg.session_id == row.id
- ).all()
- total_chars = sum(len(m[0] or "") for m in msg_rows)
- if total_chars <= 250:
- should_delete = True
- deleted_throwaway += 1
-
- if should_delete:
db.delete(row)
if deleted_empty or deleted_throwaway:
diff --git a/static/css/17-research.css b/static/css/17-research.css
index c4de5cb75..2c43aa2c8 100644
--- a/static/css/17-research.css
+++ b/static/css/17-research.css
@@ -2690,11 +2690,14 @@ body.theme-frosted .modal {
max-height: 95dvh !important;
}
+ /* Notes and Documents must respect the same viewport and safe-area
+ top as other mobile full-height sheets. Keep these authoritative rules
+ consistent with 05-documents.css and 14-email.css. */
body.doc-view .doc-editor-pane,
body.notes-view .notes-pane {
- inset: auto 0 0 !important;
- height: 95dvh !important;
- max-height: 95dvh !important;
+ inset: var(--sheet-top) 0 0 !important;
+ height: calc(var(--app-height) - var(--sheet-top)) !important;
+ max-height: calc(var(--app-height) - var(--sheet-top)) !important;
}
}
diff --git a/static/index.html b/static/index.html
index aafacc2e1..df3045af3 100644
--- a/static/index.html
+++ b/static/index.html
@@ -16,13 +16,6 @@