feat: add fast-path setup for nous account

adds a nous account specific fast flow & autolaunches into chat if
gateway isn't set up

hermes_cli/auth.py

@@ -2821,6 +2821,7 @@ def _prompt_model_selection(
     pricing: Optional[Dict[str, Dict[str, str]]] = None,
     unavailable_models: Optional[List[str]] = None,
     portal_url: str = "",
+    allow_custom = True
 ) -> Optional[str]:
     """Interactive model selection. Puts current_model first with a marker. Returns chosen model ID or None.
 
@@ -2909,8 +2910,16 @@ def _prompt_model_selection(
         from simple_term_menu import TerminalMenu
 
         choices = [f"  {_label(mid)}" for mid in ordered]
-        choices.append("  Enter custom model name")
-        choices.append("  Skip (keep current)")
+
+        custom_idx = None
+        if allow_custom:
+            custom_idx = len(choices)
+            choices.append("  Enter custom model name")
+
+        skip_idx = None
+        if current_model:
+            skip_idx = len(choices)
+            choices.append("  Skip (keep current)")
 
         # Print the unavailable block BEFORE the menu via regular print().
         # simple_term_menu pads title lines to terminal width (causes wrapping),
@@ -2947,21 +2956,29 @@ def _prompt_model_selection(
         print()
         if idx < len(ordered):
             return ordered[idx]
-        elif idx == len(ordered):
+        if idx == custom_idx:
             custom = input("Enter model name: ").strip()
             return custom if custom else None
+        if idx == skip_idx:
+            return None
         return None
     except (ImportError, NotImplementedError, OSError, subprocess.SubprocessError):
         pass
 
     # Fallback: numbered list
     print(menu_title)
-    num_width = len(str(len(ordered) + 2))
+    n = len(ordered)
+    extra = []
+    if allow_custom:
+        extra.append("Enter custom model name")
+    if current_model:
+        extra.append("Skip (keep current)")
+    total = n + len(extra)
+    num_width = len(str(total))
     for i, mid in enumerate(ordered, 1):
         print(f"  {i:>{num_width}}. {_label(mid)}")
-    n = len(ordered)
-    print(f"  {n + 1:>{num_width}}. Enter custom model name")
-    print(f"  {n + 2:>{num_width}}. Skip (keep current)")
+    for j, label in enumerate(extra, n + 1):
+        print(f"  {j:>{num_width}}. {label}")
 
     if _unavailable:
         _upgrade_url = (portal_url or DEFAULT_NOUS_PORTAL_URL).rstrip("/")
@@ -2973,18 +2990,19 @@ def _prompt_model_selection(
 
     while True:
         try:
-            choice = input(f"Choice [1-{n + 2}] (default: skip): ").strip()
+            choice = input(f"Choice [1-{total}]: ").strip()
             if not choice:
                 return None
-            idx = int(choice)
-            if 1 <= idx <= n:
-                return ordered[idx - 1]
-            elif idx == n + 1:
-                custom = input("Enter model name: ").strip()
-                return custom if custom else None
-            elif idx == n + 2:
-                return None
-            print(f"Please enter 1-{n + 2}")
+            val = int(choice)
+            if 1 <= val <= n:
+                return ordered[val - 1]
+            extra_idx = val - n - 1
+            if 0 <= extra_idx < len(extra):
+                if extra[extra_idx] == "Enter custom model name":
+                    custom = input("Enter model name: ").strip()
+                    return custom if custom else None
+                return None  # skip
+            print(f"Please enter 1-{total}")
         except ValueError:
             print("Please enter a number")
         except (KeyboardInterrupt, EOFError):
@@ -3260,7 +3278,6 @@ def _nous_device_code_login(
         open_browser = False
 
     print(f"Starting Hermes login via {pconfig.name}...")
-    print(f"Portal: {portal_base_url}")
     if insecure:
         print("TLS verification: disabled (--insecure)")
     elif ca_bundle:
@@ -3280,19 +3297,18 @@ def _nous_device_code_login(
         interval = int(device_data["interval"])
 
         print()
-        print("To continue:")
-        print(f"  1. Open: {verification_url}")
-        print(f"  2. If prompted, enter code: {user_code}")
-
         if open_browser:
             opened = webbrowser.open(verification_url)
             if opened:
-                print("  (Opened browser for verification)")
+                print("If you don't see a browser window open, navigate to this URL:")
             else:
-                print("  Could not open browser automatically — use the URL above.")
+                print("Navigate to this URL to continue:")
+        print(verification_url)
+        print(f"If you're prompted for a code, use {user_code}")
+        print()
 
         effective_interval = max(1, min(interval, DEVICE_AUTH_POLL_INTERVAL_CAP_SECONDS))
-        print(f"Waiting for approval (polling every {effective_interval}s)...")
+        print(f"Waiting for approval (checking every {effective_interval}s)...")
 
         token_data = _poll_for_token(
             client=client,
@@ -3357,7 +3373,7 @@ def _nous_device_code_login(
         raise
 
 
-def _login_nous(args, pconfig: ProviderConfig) -> None:
+def login_nous(args, pconfig: ProviderConfig) -> None:
     """Nous Portal device authorization flow."""
     timeout_seconds = getattr(args, "timeout", None) or 15.0
     insecure = bool(getattr(args, "insecure", False))
@@ -3419,7 +3435,10 @@ def _login_nous(args, pconfig: ProviderConfig) -> None:
             )
             model_ids = _PROVIDER_MODELS.get("nous", [])
 
+            _portal = auth_state.get("portal_base_url", "")
+
             print()
+
             unavailable_models: list = []
             if model_ids:
                 pricing = get_pricing_for_provider("nous")
@@ -3428,14 +3447,17 @@ def _login_nous(args, pconfig: ProviderConfig) -> None:
                     model_ids, unavailable_models = partition_nous_models_by_tier(
                         model_ids, pricing, free_tier=True,
                     )
-            _portal = auth_state.get("portal_base_url", "")
-            if model_ids:
-                print(f"Showing {len(model_ids)} curated models — use \"Enter custom model name\" for others.")
-                selected_model = _prompt_model_selection(
-                    model_ids, pricing=pricing,
-                    unavailable_models=unavailable_models,
-                    portal_url=_portal,
-                )
+                if not free_tier:
+                    print(f"Showing {len(model_ids)} curated models — use \"Enter custom model name\" for others.")
+                if len(model_ids) > 1:
+                    selected_model = _prompt_model_selection(
+                        model_ids, pricing=pricing,
+                        unavailable_models=unavailable_models,
+                        portal_url=_portal,
+                        allow_custom=not free_tier
+                    )
+                else:
+                    selected_model = model_ids[0]
             elif unavailable_models:
                 _url = (_portal or DEFAULT_NOUS_PORTAL_URL).rstrip("/")
                 print("No free models currently available.")

hermes_cli/main.py

@@ -1085,9 +1085,6 @@ def cmd_chat(args):
         print(
             "It looks like Hermes isn't configured yet -- no API keys or providers found."
         )
-        print()
-        print("  Run:  hermes setup")
-        print()
 
         from hermes_cli.setup import (
             is_interactive_stdin,
@@ -1100,16 +1097,8 @@ def cmd_chat(args):
             )
             sys.exit(1)
 
-        try:
-            reply = input("Run setup now? [Y/n] ").strip().lower()
-        except (EOFError, KeyboardInterrupt):
-            reply = "n"
-        if reply in ("", "y", "yes"):
-            cmd_setup(args)
-            return
-        print()
-        print("You can run 'hermes setup' at any time to configure.")
-        sys.exit(1)
+        cmd_setup(args)
+        return
 
     # Start update check in background (runs while other init happens)
     try:
@@ -2135,7 +2124,7 @@ def _model_flow_nous(config, current_model="", args=None):
         resolve_nous_runtime_credentials,
         AuthError,
         format_auth_error,
-        _login_nous,
+        login_nous,
         PROVIDER_REGISTRY,
     )
     from hermes_cli.config import (
@@ -2148,8 +2137,6 @@ def _model_flow_nous(config, current_model="", args=None):
 
     state = get_provider_auth_state("nous")
     if not state or not state.get("access_token"):
-        print("Not logged into Nous Portal. Starting login...")
-        print()
         try:
             mock_args = argparse.Namespace(
                 portal_url=getattr(args, "portal_url", None),
@@ -2161,7 +2148,7 @@ def _model_flow_nous(config, current_model="", args=None):
                 ca_bundle=getattr(args, "ca_bundle", None),
                 insecure=bool(getattr(args, "insecure", False)),
             )
-            _login_nous(mock_args, PROVIDER_REGISTRY["nous"])
+            login_nous(mock_args, PROVIDER_REGISTRY["nous"])
             # Offer Tool Gateway enablement for paid subscribers
             try:
                 _refreshed = load_config() or {}
@@ -2212,7 +2199,7 @@ def _model_flow_nous(config, current_model="", args=None):
                     ca_bundle=None,
                     insecure=False,
                 )
-                _login_nous(mock_args, PROVIDER_REGISTRY["nous"])
+                login_nous(mock_args, PROVIDER_REGISTRY["nous"])
             except Exception as login_exc:
                 print(f"Re-login failed: {login_exc}")
             return

hermes_cli/setup.py

@@ -18,9 +18,10 @@ import shutil
 import sys
 import copy
 from pathlib import Path
-from typing import Optional, Dict, Any
+from typing import Literal, Optional, Dict, Any
 
 from hermes_cli.nous_subscription import get_nous_subscription_features
+from hermes_cli.main import _model_flow_nous
 from tools.tool_backend_helpers import managed_nous_tools_enabled
 from utils import base_url_hostname
 from hermes_constants import get_optional_skills_dir
@@ -655,7 +656,7 @@ def _prompt_container_resources(config: dict):
 
 
 
-def setup_model_provider(config: dict, *, quick: bool = False):
+def setup_model_provider(config: dict, *, quick: bool | Literal["nous_portal"] = False):
     """Configure the inference provider and default model.
 
     Delegates to ``cmd_model()`` (the same flow used by ``hermes model``)
@@ -677,7 +678,11 @@ def setup_model_provider(config: dict, *, quick: bool = False):
     # credential prompting, model selection, and config persistence.
     from hermes_cli.main import select_provider_and_model
     try:
-        select_provider_and_model()
+        if quick == "nous_portal":
+            config = load_config()
+            _model_flow_nous(config)
+        else:
+            select_provider_and_model()
     except (SystemExit, KeyboardInterrupt):
         print()
         print_info("Provider setup skipped.")
@@ -3030,11 +3035,15 @@ def run_setup_wizard(args):
             config = load_config()
 
         setup_mode = prompt_choice("How would you like to set up Hermes?", [
-            "Quick setup — provider, model & messaging (recommended)",
+            "Nous Account setup — model & messaging (recommended)",
+            "Quick setup — provider, model & messaging",
             "Full setup — configure everything",
         ], 0)
 
         if setup_mode == 0:
+            _run_first_time_quick_setup(config, hermes_home, is_existing, nous_quick=True)
+            return
+        if setup_mode == 1:
             _run_first_time_quick_setup(config, hermes_home, is_existing)
             return
 
@@ -3095,7 +3104,7 @@ def _resolve_hermes_chat_argv() -> Optional[list[str]]:
     return None
 
 
-def _offer_launch_chat():
+def _offer_launch_chat(auto_launch = False):
     """Prompt the user to jump straight into chat after setup."""
     print()
     if not prompt_yes_no("Launch hermes chat now?", True):
@@ -3109,7 +3118,7 @@ def _offer_launch_chat():
     os.execvp(chat_argv[0], chat_argv)
 
 
-def _run_first_time_quick_setup(config: dict, hermes_home, is_existing: bool):
+def _run_first_time_quick_setup(config: dict, hermes_home, is_existing: bool, nous_quick=False):
     """Streamlined first-time setup: provider + model only.
 
     Applies sensible defaults for TTS (Edge), terminal (local), agent
@@ -3117,7 +3126,7 @@ def _run_first_time_quick_setup(config: dict, hermes_home, is_existing: bool):
     ``hermes setup <section>``.
     """
     # Step 1: Model & Provider (essential — skips rotation/vision/TTS)
-    setup_model_provider(config, quick=True)
+    setup_model_provider(config, quick="nous_portal" if nous_quick else True )
 
     # Step 2: Apply defaults for everything else
     _apply_default_agent_settings(config)
@@ -3150,7 +3159,9 @@ def _run_first_time_quick_setup(config: dict, hermes_home, is_existing: bool):
 
     _print_setup_summary(config, hermes_home)
 
-    _offer_launch_chat()
+    # if the user hasn't set up the gateway, assume they want to launch chat.
+    force_launch_chat = gateway_choice == 0
+    _offer_launch_chat(force_launch_chat)
 
 
 def _run_quick_setup(config: dict, hermes_home):

tests/cli/test_cli_provider_resolution.py

@@ -571,7 +571,7 @@ def test_cmd_model_forwards_nous_login_tls_options(monkeypatch):
         captured["ca_bundle"] = login_args.ca_bundle
         captured["insecure"] = login_args.insecure
 
-    monkeypatch.setattr("hermes_cli.auth._login_nous", _fake_login)
+    monkeypatch.setattr("hermes_cli.auth.login_nous", _fake_login)
 
     hermes_main.cmd_model(
         SimpleNamespace(

tests/gateway/test_complete_path_at_filter.py

@@ -1,22 +1,28 @@
 """Regression tests for the TUI gateway's `complete.path` handler.
 
-Reported during the TUI v2 blitz retest: typing `@folder:` (and `@folder`
-with no colon yet) still surfaced files alongside directories in the
-TUI composer, because the gateway-side completion lives in
-`tui_gateway/server.py` and was never touched by the earlier fix to
-`hermes_cli/commands.py`.
+Reported during the TUI v2 blitz retest:
+  - typing `@folder:` (and `@folder` with no colon yet) surfaced files
+    alongside directories — the gateway-side completion lives in
+    `tui_gateway/server.py` and was never touched by the earlier fix to
+    `hermes_cli/commands.py`.
+  - typing `@appChrome` required the full `@ui-tui/src/components/app…`
+    path to find the file — users expect Cmd-P-style fuzzy basename
+    matching across the repo, not a strict directory prefix filter.
 
 Covers:
   - `@folder:` only yields directories
   - `@file:` only yields regular files
   - Bare `@folder` / `@file` (no colon) lists cwd directly
   - Explicit prefix is preserved in the completion text
+  - `@<name>` with no slash fuzzy-matches basenames anywhere in the tree
 """
 
 from __future__ import annotations
 
 from pathlib import Path
 
+import pytest
+
 from tui_gateway import server
 
 
@@ -33,6 +39,15 @@ def _items(word: str):
     return [(it["text"], it["display"], it.get("meta", "")) for it in resp["result"]["items"]]
 
 
+@pytest.fixture(autouse=True)
+def _reset_fuzzy_cache(monkeypatch):
+    # Each test walks a fresh tmp dir; clear the cached listing so prior
+    # roots can't leak through the TTL window.
+    server._fuzzy_cache.clear()
+    yield
+    server._fuzzy_cache.clear()
+
+
 def test_at_folder_colon_only_dirs(tmp_path, monkeypatch):
     monkeypatch.chdir(tmp_path)
     _fixture(tmp_path)
@@ -89,3 +104,176 @@ def test_bare_at_still_shows_static_refs(tmp_path, monkeypatch):
 
     for expected in ("@diff", "@staged", "@file:", "@folder:", "@url:", "@git:"):
         assert expected in texts, f"missing static ref {expected!r} in {texts!r}"
+
+
+# ── Fuzzy basename matching ──────────────────────────────────────────────
+# Users shouldn't have to know the full path — typing `@appChrome` should
+# find `ui-tui/src/components/appChrome.tsx`.
+
+
+def _nested_fixture(tmp_path: Path):
+    (tmp_path / "readme.md").write_text("x")
+    (tmp_path / ".env").write_text("x")
+    (tmp_path / "ui-tui/src/components").mkdir(parents=True)
+    (tmp_path / "ui-tui/src/components/appChrome.tsx").write_text("x")
+    (tmp_path / "ui-tui/src/components/appLayout.tsx").write_text("x")
+    (tmp_path / "ui-tui/src/components/thinking.tsx").write_text("x")
+    (tmp_path / "ui-tui/src/hooks").mkdir(parents=True)
+    (tmp_path / "ui-tui/src/hooks/useCompletion.ts").write_text("x")
+    (tmp_path / "tui_gateway").mkdir()
+    (tmp_path / "tui_gateway/server.py").write_text("x")
+
+
+def test_fuzzy_at_finds_file_without_directory_prefix(tmp_path, monkeypatch):
+    """`@appChrome` — with no slash — should surface the nested file."""
+    monkeypatch.chdir(tmp_path)
+    _nested_fixture(tmp_path)
+
+    entries = _items("@appChrome")
+    texts = [t for t, _, _ in entries]
+
+    assert "@file:ui-tui/src/components/appChrome.tsx" in texts, texts
+
+    # Display is the basename, meta is the containing directory, so the
+    # picker can show `appChrome.tsx  ui-tui/src/components` on one row.
+    row = next(r for r in entries if r[0] == "@file:ui-tui/src/components/appChrome.tsx")
+    assert row[1] == "appChrome.tsx"
+    assert row[2] == "ui-tui/src/components"
+
+
+def test_fuzzy_ranks_exact_before_prefix_before_subseq(tmp_path, monkeypatch):
+    """Better matches sort before weaker matches regardless of path depth."""
+    monkeypatch.chdir(tmp_path)
+    _nested_fixture(tmp_path)
+    (tmp_path / "server.py").write_text("x")  # exact basename match at root
+
+    texts = [t for t, _, _ in _items("@server")]
+
+    # Exact `server.py` beats `tui_gateway/server.py` (prefix match) — both
+    # rank 1 on basename but exact basename wins on the sort key; shorter
+    # rel path breaks ties.
+    assert texts[0] == "@file:server.py", texts
+    assert "@file:tui_gateway/server.py" in texts
+
+
+def test_fuzzy_camelcase_word_boundary(tmp_path, monkeypatch):
+    """Mid-basename camelCase pieces match without substring scanning."""
+    monkeypatch.chdir(tmp_path)
+    _nested_fixture(tmp_path)
+
+    texts = [t for t, _, _ in _items("@Chrome")]
+
+    # `Chrome` starts a camelCase word inside `appChrome.tsx`.
+    assert "@file:ui-tui/src/components/appChrome.tsx" in texts, texts
+
+
+def test_fuzzy_subsequence_catches_sparse_queries(tmp_path, monkeypatch):
+    """`@uCo` → `useCompletion.ts` via subsequence, last-resort tier."""
+    monkeypatch.chdir(tmp_path)
+    _nested_fixture(tmp_path)
+
+    texts = [t for t, _, _ in _items("@uCo")]
+
+    assert "@file:ui-tui/src/hooks/useCompletion.ts" in texts, texts
+
+
+def test_fuzzy_at_file_prefix_preserved(tmp_path, monkeypatch):
+    """Explicit `@file:` prefix still wins the completion tag."""
+    monkeypatch.chdir(tmp_path)
+    _nested_fixture(tmp_path)
+
+    texts = [t for t, _, _ in _items("@file:appChrome")]
+
+    assert "@file:ui-tui/src/components/appChrome.tsx" in texts, texts
+
+
+def test_fuzzy_skipped_when_path_has_slash(tmp_path, monkeypatch):
+    """Any `/` in the query = user is navigating; keep directory listing."""
+    monkeypatch.chdir(tmp_path)
+    _nested_fixture(tmp_path)
+
+    texts = [t for t, _, _ in _items("@ui-tui/src/components/app")]
+
+    # Directory-listing mode prefixes with `@file:` / `@folder:` per entry.
+    # It should only surface direct children of the named dir — not the
+    # nested `useCompletion.ts`.
+    assert any("appChrome.tsx" in t for t in texts), texts
+    assert not any("useCompletion.ts" in t for t in texts), texts
+
+
+def test_fuzzy_skipped_when_folder_tag(tmp_path, monkeypatch):
+    """`@folder:<name>` still lists directories — fuzzy scanner only walks
+    files (git-tracked + untracked), so defer to the dir-listing path."""
+    monkeypatch.chdir(tmp_path)
+    _nested_fixture(tmp_path)
+
+    texts = [t for t, _, _ in _items("@folder:ui")]
+
+    # Root has `ui-tui/` as a directory; the listing branch should surface it.
+    assert any(t.startswith("@folder:ui-tui") for t in texts), texts
+
+
+def test_fuzzy_hides_dotfiles_unless_asked(tmp_path, monkeypatch):
+    """`.env` doesn't leak into `@env` but does show for `@.env`."""
+    monkeypatch.chdir(tmp_path)
+    _nested_fixture(tmp_path)
+
+    assert not any(".env" in t for t, _, _ in _items("@env"))
+    assert any(t.endswith(".env") for t, _, _ in _items("@.env"))
+
+
+def test_fuzzy_caps_results(tmp_path, monkeypatch):
+    """The 30-item cap survives a big tree."""
+    monkeypatch.chdir(tmp_path)
+    for i in range(60):
+        (tmp_path / f"mod_{i:03d}.py").write_text("x")
+
+    items = _items("@mod")
+
+    assert len(items) == 30
+
+
+def test_fuzzy_paths_relative_to_cwd_inside_subdir(tmp_path, monkeypatch):
+    """When the gateway runs from a subdirectory of a git repo, fuzzy
+    completion paths must resolve under that cwd — not under the repo root.
+
+    Without this, `@appChrome` from inside `apps/web/` would suggest
+    `@file:apps/web/src/foo.tsx` but the agent (resolving from cwd) would
+    look for `apps/web/apps/web/src/foo.tsx` and fail. We translate every
+    `git ls-files` result back to a `relpath(root)` and drop anything
+    outside `root` so the completion contract stays "paths are cwd-relative".
+    """
+    import subprocess
+
+    subprocess.run(["git", "init", "-q"], cwd=tmp_path, check=True)
+    subprocess.run(["git", "config", "user.email", "test@example.com"], cwd=tmp_path, check=True)
+    subprocess.run(["git", "config", "user.name", "test"], cwd=tmp_path, check=True)
+
+    (tmp_path / "apps" / "web" / "src").mkdir(parents=True)
+    (tmp_path / "apps" / "web" / "src" / "appChrome.tsx").write_text("x")
+    (tmp_path / "apps" / "api" / "src").mkdir(parents=True)
+    (tmp_path / "apps" / "api" / "src" / "server.ts").write_text("x")
+    (tmp_path / "README.md").write_text("x")
+
+    subprocess.run(["git", "add", "."], cwd=tmp_path, check=True)
+    subprocess.run(["git", "commit", "-q", "-m", "init"], cwd=tmp_path, check=True)
+
+    # Run from `apps/web/` — completions should be relative to here, and
+    # files outside this subtree (apps/api, README.md at root) shouldn't
+    # appear at all.
+    monkeypatch.chdir(tmp_path / "apps" / "web")
+
+    texts = [t for t, _, _ in _items("@appChrome")]
+
+    assert "@file:src/appChrome.tsx" in texts, texts
+    assert not any("apps/web/" in t for t in texts), texts
+
+    server._fuzzy_cache.clear()
+    other_texts = [t for t, _, _ in _items("@server")]
+
+    assert not any("server.ts" in t for t in other_texts), other_texts
+
+    server._fuzzy_cache.clear()
+    readme_texts = [t for t, _, _ in _items("@README")]
+
+    assert not any("README.md" in t for t in readme_texts), readme_texts

tui_gateway/server.py

@@ -3256,6 +3256,162 @@ def _(rid, params: dict) -> dict:
 
 # ── Methods: complete ─────────────────────────────────────────────────
 
+_FUZZY_CACHE_TTL_S = 5.0
+_FUZZY_CACHE_MAX_FILES = 20000
+_FUZZY_FALLBACK_EXCLUDES = frozenset(
+    {
+        ".git",
+        ".hg",
+        ".svn",
+        ".next",
+        ".cache",
+        ".venv",
+        "venv",
+        "node_modules",
+        "__pycache__",
+        "dist",
+        "build",
+        "target",
+        ".mypy_cache",
+        ".pytest_cache",
+        ".ruff_cache",
+    }
+)
+_fuzzy_cache_lock = threading.Lock()
+_fuzzy_cache: dict[str, tuple[float, list[str]]] = {}
+
+
+def _list_repo_files(root: str) -> list[str]:
+    """Return file paths relative to ``root``.
+
+    Uses ``git ls-files`` from the repo top (resolved via
+    ``rev-parse --show-toplevel``) so the listing covers tracked + untracked
+    files anywhere in the repo, then converts each path back to be relative
+    to ``root``. Files outside ``root`` (parent directories of cwd, sibling
+    subtrees) are excluded so the picker stays scoped to what's reachable
+    from the gateway's cwd. Falls back to a bounded ``os.walk(root)`` when
+    ``root`` isn't inside a git repo. Result cached per-root for
+    ``_FUZZY_CACHE_TTL_S`` so rapid keystrokes don't respawn git processes.
+    """
+    now = time.monotonic()
+    with _fuzzy_cache_lock:
+        cached = _fuzzy_cache.get(root)
+        if cached and now - cached[0] < _FUZZY_CACHE_TTL_S:
+            return cached[1]
+
+    files: list[str] = []
+    try:
+        top_result = subprocess.run(
+            ["git", "-C", root, "rev-parse", "--show-toplevel"],
+            capture_output=True,
+            timeout=2.0,
+            check=False,
+        )
+        if top_result.returncode == 0:
+            top = top_result.stdout.decode("utf-8", "replace").strip()
+            list_result = subprocess.run(
+                ["git", "-C", top, "ls-files", "-z", "--cached", "--others", "--exclude-standard"],
+                capture_output=True,
+                timeout=2.0,
+                check=False,
+            )
+            if list_result.returncode == 0:
+                for p in list_result.stdout.decode("utf-8", "replace").split("\0"):
+                    if not p:
+                        continue
+                    rel = os.path.relpath(os.path.join(top, p), root).replace(os.sep, "/")
+                    # Skip parents/siblings of cwd — keep the picker scoped
+                    # to root-and-below, matching Cmd-P workspace semantics.
+                    if rel.startswith("../"):
+                        continue
+                    files.append(rel)
+                    if len(files) >= _FUZZY_CACHE_MAX_FILES:
+                        break
+    except (OSError, subprocess.TimeoutExpired):
+        pass
+
+    if not files:
+        # Fallback walk: skip vendor/build dirs + dot-dirs so the walk stays
+        # tractable. Dotfiles themselves survive — the ranker decides based
+        # on whether the query starts with `.`.
+        try:
+            for dirpath, dirnames, filenames in os.walk(root, followlinks=False):
+                dirnames[:] = [
+                    d
+                    for d in dirnames
+                    if d not in _FUZZY_FALLBACK_EXCLUDES and not d.startswith(".")
+                ]
+                rel_dir = os.path.relpath(dirpath, root)
+                for f in filenames:
+                    rel = f if rel_dir == "." else f"{rel_dir}/{f}"
+                    files.append(rel.replace(os.sep, "/"))
+                    if len(files) >= _FUZZY_CACHE_MAX_FILES:
+                        break
+                if len(files) >= _FUZZY_CACHE_MAX_FILES:
+                    break
+        except OSError:
+            pass
+
+    with _fuzzy_cache_lock:
+        _fuzzy_cache[root] = (now, files)
+
+    return files
+
+
+def _fuzzy_basename_rank(name: str, query: str) -> tuple[int, int] | None:
+    """Rank ``name`` against ``query``; lower is better. Returns None to reject.
+
+    Tiers (kind):
+      0 — exact basename
+      1 — basename prefix (e.g. `app` → `appChrome.tsx`)
+      2 — word-boundary / camelCase hit (e.g. `chrome` → `appChrome.tsx`)
+      3 — substring anywhere in basename
+      4 — subsequence match (every query char appears in order)
+
+    Secondary key is `len(name)` so shorter names win ties.
+    """
+    if not query:
+        return (3, len(name))
+
+    nl = name.lower()
+    ql = query.lower()
+
+    if nl == ql:
+        return (0, len(name))
+
+    if nl.startswith(ql):
+        return (1, len(name))
+
+    # Word-boundary split: `foo-bar_baz.qux` → ["foo","bar","baz","qux"].
+    # camelCase split: `appChrome` → ["app","Chrome"]. Cheap approximation;
+    # falls through to substring/subsequence if it misses.
+    parts: list[str] = []
+    buf = ""
+    for ch in name:
+        if ch in "-_." or (ch.isupper() and buf and not buf[-1].isupper()):
+            if buf:
+                parts.append(buf)
+            buf = ch if ch not in "-_." else ""
+        else:
+            buf += ch
+    if buf:
+        parts.append(buf)
+    for p in parts:
+        if p.lower().startswith(ql):
+            return (2, len(name))
+
+    if ql in nl:
+        return (3, len(name))
+
+    i = 0
+    for ch in nl:
+        if ch == ql[i]:
+            i += 1
+            if i == len(ql):
+                return (4, len(name))
+
+    return None
+
 
 @method("complete.path")
 def _(rid, params: dict) -> dict:
@@ -3291,6 +3447,42 @@ def _(rid, params: dict) -> dict:
             prefix_tag = ""
             path_part = query if is_context else query
 
+        # Fuzzy basename search across the repo when the user types a bare
+        # name with no path separator — `@appChrome` surfaces every file
+        # whose basename matches, regardless of directory depth. Matches what
+        # editors like Cursor / VS Code do for Cmd-P. Path-ish queries (with
+        # `/`, `./`, `~/`, `/abs`) fall through to the directory-listing
+        # path so explicit navigation intent is preserved.
+        if (
+            is_context
+            and path_part
+            and "/" not in path_part
+            and prefix_tag != "folder"
+        ):
+            root = os.getcwd()
+            ranked: list[tuple[tuple[int, int], str, str]] = []
+            for rel in _list_repo_files(root):
+                basename = os.path.basename(rel)
+                if basename.startswith(".") and not path_part.startswith("."):
+                    continue
+                rank = _fuzzy_basename_rank(basename, path_part)
+                if rank is None:
+                    continue
+                ranked.append((rank, rel, basename))
+
+            ranked.sort(key=lambda r: (r[0], len(r[1]), r[1]))
+            tag = prefix_tag or "file"
+            for _, rel, basename in ranked[:30]:
+                items.append(
+                    {
+                        "text": f"@{tag}:{rel}",
+                        "display": basename,
+                        "meta": os.path.dirname(rel),
+                    }
+                )
+
+            return _ok(rid, {"items": items})
+
         expanded = _normalize_completion_path(path_part) if path_part else "."
         if expanded == "." or not expanded:
             search_dir, match = ".", ""

ui-tui/src/__tests__/createGatewayEventHandler.test.ts

@@ -152,91 +152,79 @@ describe('createGatewayEventHandler', () => {
     expect(appended[0]?.thinkingTokens).toBe(estimateTokensRough(fromServer))
   })
 
-  it('attaches inline_diff to the assistant completion body', () => {
+  it('anchors inline_diff as its own segment where the edit happened', () => {
     const appended: Msg[] = []
     const onEvent = createGatewayEventHandler(buildCtx(appended))
     const diff = '\u001b[31m--- a/foo.ts\u001b[0m\n\u001b[32m+++ b/foo.ts\u001b[0m\n@@\n-old\n+new'
     const cleaned = '--- a/foo.ts\n+++ b/foo.ts\n@@\n-old\n+new'
+    const block = `\`\`\`diff\n${cleaned}\n\`\`\``
 
-    onEvent({
-      payload: { context: 'foo.ts', name: 'patch', tool_id: 'tool-1' },
-      type: 'tool.start'
-    } as any)
-    onEvent({
-      payload: { inline_diff: diff, summary: 'patched', tool_id: 'tool-1' },
-      type: 'tool.complete'
-    } as any)
+    // Narration → tool → tool-complete → more narration → message-complete.
+    // The diff MUST land between the two narration segments, not tacked
+    // onto the final one.
+    onEvent({ payload: { text: 'Editing the file' }, type: 'message.delta' } as any)
+    onEvent({ payload: { context: 'foo.ts', name: 'patch', tool_id: 'tool-1' }, type: 'tool.start' } as any)
+    onEvent({ payload: { inline_diff: diff, summary: 'patched', tool_id: 'tool-1' }, type: 'tool.complete' } as any)
 
-    // Diff is buffered for message.complete and sanitized (ANSI stripped).
+    // Diff is already committed to segmentMessages as its own segment.
     expect(appended).toHaveLength(0)
-    expect(turnController.pendingInlineDiffs).toEqual([cleaned])
+    expect(turnController.segmentMessages).toEqual([
+      { role: 'assistant', text: 'Editing the file' },
+      { kind: 'diff', role: 'assistant', text: block }
+    ])
 
-    onEvent({
-      payload: { text: 'patch applied' },
-      type: 'message.complete'
-    } as any)
+    onEvent({ payload: { text: 'patch applied' }, type: 'message.complete' } as any)
 
-    // Diff is rendered in the same assistant message body as the completion.
-    expect(appended).toHaveLength(1)
-    expect(appended[0]).toMatchObject({ role: 'assistant' })
-    expect(appended[0]?.text).toContain('patch applied')
-    expect(appended[0]?.text).toContain('```diff')
-    expect(appended[0]?.text).toContain(cleaned)
+    // Three transcript messages: pre-tool narration → diff (kind='diff',
+    // so MessageLine gives it blank-line breathing room) → post-tool
+    // narration. The final message does NOT contain a diff.
+    expect(appended).toHaveLength(3)
+    expect(appended[0]?.text).toBe('Editing the file')
+    expect(appended[1]).toMatchObject({ kind: 'diff', text: block })
+    expect(appended[2]?.text).toBe('patch applied')
+    expect(appended[2]?.text).not.toContain('```diff')
   })
 
-  it('does not append inline_diff twice when assistant text already contains it', () => {
+  it('drops the diff segment when the final assistant text narrates the same diff', () => {
     const appended: Msg[] = []
     const onEvent = createGatewayEventHandler(buildCtx(appended))
     const cleaned = '--- a/foo.ts\n+++ b/foo.ts\n@@\n-old\n+new'
     const assistantText = `Done. Here's the inline diff:\n\n\`\`\`diff\n${cleaned}\n\`\`\``
 
-    onEvent({
-      payload: { inline_diff: cleaned, summary: 'patched', tool_id: 'tool-1' },
-      type: 'tool.complete'
-    } as any)
-    onEvent({
-      payload: { text: assistantText },
-      type: 'message.complete'
-    } as any)
+    onEvent({ payload: { inline_diff: cleaned, summary: 'patched', tool_id: 'tool-1' }, type: 'tool.complete' } as any)
+    onEvent({ payload: { text: assistantText }, type: 'message.complete' } as any)
 
+    // Only the final message — diff-only segment dropped so we don't
+    // render two stacked copies of the same patch.
     expect(appended).toHaveLength(1)
     expect(appended[0]?.text).toBe(assistantText)
     expect((appended[0]?.text.match(/```diff/g) ?? []).length).toBe(1)
   })
 
-  it('strips the CLI "┊ review diff" header from queued inline diffs', () => {
+  it('strips the CLI "┊ review diff" header from inline diff segments', () => {
     const appended: Msg[] = []
     const onEvent = createGatewayEventHandler(buildCtx(appended))
     const raw = '  \u001b[33m┊ review diff\u001b[0m\n--- a/foo.ts\n+++ b/foo.ts\n@@\n-old\n+new'
 
-    onEvent({
-      payload: { inline_diff: raw, summary: 'patched', tool_id: 'tool-1' },
-      type: 'tool.complete'
-    } as any)
-    onEvent({
-      payload: { text: 'done' },
-      type: 'message.complete'
-    } as any)
+    onEvent({ payload: { inline_diff: raw, summary: 'patched', tool_id: 'tool-1' }, type: 'tool.complete' } as any)
+    onEvent({ payload: { text: 'done' }, type: 'message.complete' } as any)
 
-    expect(appended).toHaveLength(1)
+    // diff segment first (kind='diff'), final narration second
+    expect(appended).toHaveLength(2)
+    expect(appended[0]?.kind).toBe('diff')
     expect(appended[0]?.text).not.toContain('┊ review diff')
     expect(appended[0]?.text).toContain('--- a/foo.ts')
+    expect(appended[1]?.text).toBe('done')
   })
 
-  it('suppresses inline_diff when assistant already wrote a diff fence', () => {
+  it('drops the diff segment when assistant writes its own ```diff fence', () => {
     const appended: Msg[] = []
     const onEvent = createGatewayEventHandler(buildCtx(appended))
     const inlineDiff = '--- a/foo.ts\n+++ b/foo.ts\n@@\n-old\n+new'
     const assistantText = 'Done. Clean swap:\n\n```diff\n-old\n+new\n```'
 
-    onEvent({
-      payload: { inline_diff: inlineDiff, summary: 'patched', tool_id: 'tool-1' },
-      type: 'tool.complete'
-    } as any)
-    onEvent({
-      payload: { text: assistantText },
-      type: 'message.complete'
-    } as any)
+    onEvent({ payload: { inline_diff: inlineDiff, summary: 'patched', tool_id: 'tool-1' }, type: 'tool.complete' } as any)
+    onEvent({ payload: { text: assistantText }, type: 'message.complete' } as any)
 
     expect(appended).toHaveLength(1)
     expect(appended[0]?.text).toBe(assistantText)
@@ -252,15 +240,18 @@ describe('createGatewayEventHandler', () => {
       payload: { inline_diff: diff, name: 'review_diff', summary: diff, tool_id: 'tool-1' },
       type: 'tool.complete'
     } as any)
-    onEvent({
-      payload: { text: 'done' },
-      type: 'message.complete'
-    } as any)
+    onEvent({ payload: { text: 'done' }, type: 'message.complete' } as any)
 
-    expect(appended).toHaveLength(1)
-    expect(appended[0]?.tools?.[0]).toContain('Review Diff')
-    expect(appended[0]?.tools?.[0]).not.toContain('--- a/foo.ts')
+    // Two segments: the diff block (kind='diff', no tool row) and the final
+    // narration (tool row belongs here since pendingSegmentTools carries
+    // across the flushStreamingSegment call).
+    expect(appended).toHaveLength(2)
+    expect(appended[0]?.kind).toBe('diff')
     expect(appended[0]?.text).toContain('```diff')
+    expect(appended[0]?.tools ?? []).toEqual([])
+    expect(appended[1]?.text).toBe('done')
+    expect(appended[1]?.tools?.[0]).toContain('Review Diff')
+    expect(appended[1]?.tools?.[0]).not.toContain('--- a/foo.ts')
   })
 
   it('shows setup panel for missing provider startup error', () => {

ui-tui/src/app/createGatewayEventHandler.ts

@@ -385,10 +385,12 @@ export function createGatewayEventHandler(ctx: GatewayEventHandlerContext): (ev:
           return
         }
 
-        // Keep inline diffs attached to the assistant completion body so
-        // they render in the same message flow, not as a standalone system
-        // artifact that can look out-of-place around tool rows.
-        turnController.queueInlineDiff(inlineDiffText)
+        // Anchor the diff to where the edit happened in the turn — between
+        // the narration that preceded the tool call and whatever the agent
+        // streams afterwards. The previous end-merge put the diff at the
+        // bottom of the final message even when the edit fired mid-turn,
+        // which read as "the agent wrote this after saying that".
+        turnController.pushInlineDiffSegment(inlineDiffText)
 
         return
       }

ui-tui/src/app/turnController.ts

@@ -19,6 +19,20 @@ const INTERRUPT_COOLDOWN_MS = 1500
 const ACTIVITY_LIMIT = 8
 const TRAIL_LIMIT = 8
 
+// Extracts the raw patch from a diff-only segment produced by
+// pushInlineDiffSegment. Used at message.complete to dedupe against final
+// assistant text that narrates the same patch. Returns null for anything
+// else so real assistant narration never gets touched.
+const diffSegmentBody = (msg: Msg): null | string => {
+  if (msg.kind !== 'diff') {
+    return null
+  }
+
+  const m = msg.text.match(/^```diff\n([\s\S]*?)\n```$/)
+
+  return m ? m[1]! : null
+}
+
 export interface InterruptDeps {
   appendMessage: (msg: Msg) => void
   gw: { request: <T = unknown>(method: string, params?: Record<string, unknown>) => Promise<T> }
@@ -40,7 +54,6 @@ class TurnController {
   bufRef = ''
   interrupted = false
   lastStatusNote = ''
-  pendingInlineDiffs: string[] = []
   persistedToolLabels = new Set<string>()
   persistSpawnTree?: (subagents: SubagentProgress[], sessionId: null | string) => Promise<void>
   protocolWarned = false
@@ -79,7 +92,6 @@ class TurnController {
     this.activeTools = []
     this.streamTimer = clear(this.streamTimer)
     this.bufRef = ''
-    this.pendingInlineDiffs = []
     this.pendingSegmentTools = []
     this.segmentMessages = []
 
@@ -186,18 +198,35 @@ class TurnController {
     }, REASONING_PULSE_MS)
   }
 
-  queueInlineDiff(diffText: string) {
+  pushInlineDiffSegment(diffText: string) {
     // Strip CLI chrome the gateway emits before the unified diff (e.g. a
     // leading "┊ review diff" header written by `_emit_inline_diff` for the
     // terminal printer). That header only makes sense as stdout dressing,
     // not inside a markdown ```diff block.
-    const text = diffText.replace(/^\s*┊[^\n]*\n?/, '').trim()
+    const stripped = diffText.replace(/^\s*┊[^\n]*\n?/, '').trim()
 
-    if (!text || this.pendingInlineDiffs.includes(text)) {
+    if (!stripped) {
       return
     }
 
-    this.pendingInlineDiffs = [...this.pendingInlineDiffs, text]
+    // Flush any in-progress streaming text as its own segment first, so the
+    // diff lands BETWEEN the assistant narration that preceded the edit and
+    // whatever the agent streams afterwards — not glued onto the final
+    // message. This is the whole point of segment-anchored diffs: the diff
+    // renders where the edit actually happened.
+    this.flushStreamingSegment()
+
+    const block = `\`\`\`diff\n${stripped}\n\`\`\``
+
+    // Skip consecutive duplicates (same tool firing tool.complete twice, or
+    // two edits producing the same patch). Keeping this cheap — deeper
+    // dedupe against the final assistant text happens at message.complete.
+    if (this.segmentMessages.at(-1)?.text === block) {
+      return
+    }
+
+    this.segmentMessages = [...this.segmentMessages, { kind: 'diff', role: 'assistant', text: block }]
+    patchTurnState({ streamSegments: this.segmentMessages })
   }
 
   pushActivity(text: string, tone: ActivityItem['tone'] = 'info', replaceLabel?: string) {
@@ -234,7 +263,6 @@ class TurnController {
     this.idle()
     this.clearReasoning()
     this.clearStatusTimer()
-    this.pendingInlineDiffs = []
     this.pendingSegmentTools = []
     this.segmentMessages = []
     this.turnTools = []
@@ -245,31 +273,31 @@ class TurnController {
     const rawText = (payload.rendered ?? payload.text ?? this.bufRef).trimStart()
     const split = splitReasoning(rawText)
     const finalText = split.text
-    // Skip appending if the assistant already narrated the diff inside a
-    // markdown fence of its own — otherwise we render two stacked diff
-    // blocks for the same edit.
-    const assistantAlreadyHasDiff = /```(?:diff|patch)\b/i.test(finalText)
-
-    const remainingInlineDiffs = assistantAlreadyHasDiff
-      ? []
-      : this.pendingInlineDiffs.filter(diff => !finalText.includes(diff))
-
-    const inlineDiffBlock = remainingInlineDiffs.length
-      ? `\`\`\`diff\n${remainingInlineDiffs.join('\n\n')}\n\`\`\``
-      : ''
-
-    const mergedText = [finalText, inlineDiffBlock].filter(Boolean).join('\n\n')
     const existingReasoning = this.reasoningText.trim() || String(payload.reasoning ?? '').trim()
     const savedReasoning = [existingReasoning, existingReasoning ? '' : split.reasoning].filter(Boolean).join('\n\n')
     const savedReasoningTokens = savedReasoning ? estimateTokensRough(savedReasoning) : 0
     const savedToolTokens = this.toolTokenAcc
     const tools = this.pendingSegmentTools
-    const finalMessages = [...this.segmentMessages]
 
-    if (mergedText) {
+    // Drop diff-only segments the agent is about to narrate in the final
+    // reply. Without this, a closing "here's the diff …" message would
+    // render two stacked copies of the same patch. Only touches segments
+    // with `kind: 'diff'` emitted by pushInlineDiffSegment — real
+    // assistant narration stays put.
+    const finalHasOwnDiffFence = /```(?:diff|patch)\b/i.test(finalText)
+
+    const segments = this.segmentMessages.filter(msg => {
+      const body = diffSegmentBody(msg)
+
+      return body === null || (!finalHasOwnDiffFence && !finalText.includes(body))
+    })
+
+    const finalMessages = [...segments]
+
+    if (finalText) {
       finalMessages.push({
         role: 'assistant',
-        text: mergedText,
+        text: finalText,
         thinking: savedReasoning || undefined,
         thinkingTokens: savedReasoning ? savedReasoningTokens : undefined,
         toolTokens: savedToolTokens || undefined,
@@ -300,7 +328,7 @@ class TurnController {
     this.bufRef = ''
     patchTurnState({ activity: [], outcome: '' })
 
-    return { finalMessages, finalText: mergedText, wasInterrupted }
+    return { finalMessages, finalText, wasInterrupted }
   }
 
   recordMessageDelta({ rendered, text }: { rendered?: string; text?: string }) {
@@ -406,7 +434,6 @@ class TurnController {
     this.bufRef = ''
     this.interrupted = false
     this.lastStatusNote = ''
-    this.pendingInlineDiffs = []
     this.pendingSegmentTools = []
     this.protocolWarned = false
     this.segmentMessages = []
@@ -452,7 +479,6 @@ class TurnController {
     this.endReasoningPhase()
     this.clearReasoning()
     this.activeTools = []
-    this.pendingInlineDiffs = []
     this.turnTools = []
     this.toolTokenAcc = 0
     this.persistedToolLabels.clear()

ui-tui/src/components/messageLine.tsx

@@ -81,11 +81,16 @@ export const MessageLine = memo(function MessageLine({
     return <Text {...(body ? { color: body } : {})}>{msg.text}</Text>
   })()
 
+  // Diff segments (emitted by pushInlineDiffSegment between narration
+  // segments) need a blank line on both sides so the patch doesn't butt up
+  // against the prose around it.
+  const isDiffSegment = msg.kind === 'diff'
+
   return (
     <Box
       flexDirection="column"
-      marginBottom={msg.role === 'user' ? 1 : 0}
-      marginTop={msg.role === 'user' || msg.kind === 'slash' ? 1 : 0}
+      marginBottom={msg.role === 'user' || isDiffSegment ? 1 : 0}
+      marginTop={msg.role === 'user' || msg.kind === 'slash' || isDiffSegment ? 1 : 0}
     >
       {showDetails && (
         <Box flexDirection="column" marginBottom={1}>

ui-tui/src/types.ts

@@ -102,7 +102,7 @@ export interface ClarifyReq {
 
 export interface Msg {
   info?: SessionInfo
-  kind?: 'intro' | 'panel' | 'slash' | 'trail'
+  kind?: 'diff' | 'intro' | 'panel' | 'slash' | 'trail'
   panelData?: PanelData
   role: Role
   text: string