fix: preserve explicit KittenTTS output format outside Telegram

Refs #955

hermes_cli/config.py

@@ -523,7 +523,7 @@ DEFAULT_CONFIG = {
     
     # Text-to-speech configuration
     "tts": {
-        "provider": "edge",  # "edge" (free) | "elevenlabs" (premium) | "openai" | "minimax" | "mistral" | "neutts" (local)
+        "provider": "edge",  # "edge" (free) | "elevenlabs" (premium) | "openai" | "minimax" | "mistral" | "neutts" (local) | "kittentts" (local)
         "edge": {
             "voice": "en-US-AriaNeural",
             # Popular: AriaNeural, JennyNeural, AndrewNeural, BrianNeural, SoniaNeural
@@ -547,6 +547,12 @@ DEFAULT_CONFIG = {
             "model": "neuphonic/neutts-air-q4-gguf",  # HuggingFace model repo
             "device": "cpu",  # cpu, cuda, or mps
         },
+        "kittentts": {
+            "model": "KittenML/kitten-tts-nano-0.8-int8",  # 25MB int8 default
+            "voice": "Jasper",  # Jasper, Bella, Luna, Bruno, Rosie, Hugo, Kiki, Leo
+            "speed": 1.0,
+            "clean_text": True,
+        },
     },
     
     "stt": {

hermes_cli/setup.py

@@ -443,6 +443,16 @@ def _print_setup_summary(config: dict, hermes_home):
             tool_status.append(("Text-to-Speech (NeuTTS local)", True, None))
         else:
             tool_status.append(("Text-to-Speech (NeuTTS — not installed)", False, "run 'hermes setup tts'"))
+    elif tts_provider == "kittentts":
+        try:
+            import importlib.util
+            kittentts_ok = importlib.util.find_spec("kittentts") is not None
+        except Exception:
+            kittentts_ok = False
+        if kittentts_ok:
+            tool_status.append(("Text-to-Speech (KittenTTS local)", True, None))
+        else:
+            tool_status.append(("Text-to-Speech (KittenTTS — not installed)", False, "run 'hermes setup tts'"))
     else:
         tool_status.append(("Text-to-Speech (Edge TTS)", True, None))
 
@@ -891,6 +901,7 @@ def _install_neutts_deps() -> bool:
                 return False
         else:
             print_warning("espeak-ng is required for NeuTTS. Install it manually before using NeuTTS.")
+            return False
 
     # Install neutts Python package
     print()
@@ -910,8 +921,34 @@ def _install_neutts_deps() -> bool:
         return False
 
 
+def _install_kittentts_deps() -> bool:
+    """Install KittenTTS dependencies with user approval. Returns True on success."""
+    import subprocess
+    import sys
+
+    wheel_url = (
+        "https://github.com/KittenML/KittenTTS/releases/download/"
+        "0.8.1/kittentts-0.8.1-py3-none-any.whl"
+    )
+    print()
+    print_info("Installing kittentts Python package (~25-80MB model downloaded on first use)...")
+    print()
+    try:
+        subprocess.run(
+            [sys.executable, "-m", "pip", "install", "-U", wheel_url, "soundfile", "--quiet"],
+            check=True, timeout=300,
+        )
+        print_success("kittentts installed successfully")
+        return True
+    except (subprocess.CalledProcessError, subprocess.TimeoutExpired) as e:
+        print_error(f"Failed to install kittentts: {e}")
+        print_info(f"Try manually: python -m pip install -U '{wheel_url}' soundfile")
+        return False
+
+
 def _setup_tts_provider(config: dict):
-    """Interactive TTS provider selection with install flow for NeuTTS."""
+    """Interactive TTS provider selection with install flow for local providers."""
+
     tts_config = config.get("tts", {})
     current_provider = tts_config.get("provider", "edge")
     subscription_features = get_nous_subscription_features(config)
@@ -923,6 +960,7 @@ def _setup_tts_provider(config: dict):
         "minimax": "MiniMax TTS",
         "mistral": "Mistral Voxtral TTS",
         "neutts": "NeuTTS",
+        "kittentts": "KittenTTS",
     }
     current_label = provider_labels.get(current_provider, current_provider)
 
@@ -944,9 +982,10 @@ def _setup_tts_provider(config: dict):
             "MiniMax TTS (high quality with voice cloning, needs API key)",
             "Mistral Voxtral TTS (multilingual, native Opus, needs API key)",
             "NeuTTS (local on-device, free, ~300MB model download)",
+            "KittenTTS (local on-device, free, lightweight ~25-80MB ONNX)",
         ]
     )
-    providers.extend(["edge", "elevenlabs", "openai", "minimax", "mistral", "neutts"])
+    providers.extend(["edge", "elevenlabs", "openai", "minimax", "mistral", "neutts", "kittentts"])
     choices.append(f"Keep current ({current_label})")
     keep_current_idx = len(choices) - 1
     idx = prompt_choice("Select TTS provider:", choices, keep_current_idx)
@@ -988,6 +1027,28 @@ def _setup_tts_provider(config: dict):
                 print_info("Skipping install. Set tts.provider to 'neutts' after installing manually.")
                 selected = "edge"
 
+    elif selected == "kittentts":
+        try:
+            import importlib.util
+            already_installed = importlib.util.find_spec("kittentts") is not None
+        except Exception:
+            already_installed = False
+
+        if already_installed:
+            print_success("KittenTTS is already installed")
+        else:
+            print()
+            print_info("KittenTTS is lightweight (~25-80MB, CPU-only, no API key required).")
+            print_info("Voices: Jasper, Bella, Luna, Bruno, Rosie, Hugo, Kiki, Leo")
+            print()
+            if prompt_yes_no("Install KittenTTS now?", True):
+                if not _install_kittentts_deps():
+                    print_warning("KittenTTS installation incomplete. Falling back to Edge TTS.")
+                    selected = "edge"
+            else:
+                print_info("Skipping install. Set tts.provider to 'kittentts' after installing manually.")
+                selected = "edge"
+
     elif selected == "elevenlabs":
         existing = get_env_value("ELEVENLABS_API_KEY")
         if not existing:

hermes_cli/tools_config.py

@@ -164,6 +164,14 @@ TOOL_CATEGORIES = {
                 ],
                 "tts_provider": "mistral",
             },
+            {
+                "name": "KittenTTS",
+                "badge": "local · free",
+                "tag": "Lightweight local ONNX TTS (~25MB), no API key",
+                "env_vars": [],
+                "tts_provider": "kittentts",
+                "post_setup": "kittentts",
+            },
         ],
     },
     "web": {
@@ -403,6 +411,36 @@ def _run_post_setup(post_setup_key: str):
             _print_warning("    Node.js not found. Install Camofox via Docker:")
             _print_info("      docker run -p 9377:9377 -e CAMOFOX_PORT=9377 jo-inc/camofox-browser")
 
+    elif post_setup_key == "kittentts":
+        try:
+            __import__("kittentts")
+            _print_success("    kittentts is already installed")
+            return
+        except ImportError:
+            pass
+        import subprocess
+        _print_info("    Installing kittentts (~25-80MB model, CPU-only)...")
+        wheel_url = (
+            "https://github.com/KittenML/KittenTTS/releases/download/"
+            "0.8.1/kittentts-0.8.1-py3-none-any.whl"
+        )
+        try:
+            result = subprocess.run(
+                [sys.executable, "-m", "pip", "install", "-U", wheel_url, "soundfile", "--quiet"],
+                capture_output=True, text=True, timeout=300,
+            )
+            if result.returncode == 0:
+                _print_success("    kittentts installed")
+                _print_info("    Voices: Jasper, Bella, Luna, Bruno, Rosie, Hugo, Kiki, Leo")
+                _print_info("    Models: KittenML/kitten-tts-nano-0.8-int8 (25MB), micro (41MB), mini (80MB)")
+            else:
+                _print_warning("    kittentts install failed:")
+                _print_info(f"      {result.stderr.strip()[:300]}")
+                _print_info(f"    Run manually: python -m pip install -U '{wheel_url}' soundfile")
+        except subprocess.TimeoutExpired:
+            _print_warning("    kittentts install timed out (>5min)")
+            _print_info(f"    Run manually: python -m pip install -U '{wheel_url}' soundfile")
+
     elif post_setup_key == "rl_training":
         try:
             __import__("tinker_atropos")

tests/tools/test_fuzzy_match.py

@@ -148,184 +148,3 @@ class TestStrategyNameSurfaced:
         assert count == 0
         assert strategy is None
         assert err is not None
-
-
-class TestEscapeDriftGuard:
-    """Tests for the escape-drift guard that catches bash/JSON serialization
-    artifacts where an apostrophe gets prefixed with a spurious backslash
-    in tool-call transport.
-    """
-
-    def test_drift_blocked_apostrophe(self):
-        """File has ', old_string and new_string both have \\' — classic
-        tool-call drift. Guard must block with a helpful error instead of
-        writing \\' literals into source code."""
-        content = "x = \"hello there\"\n"
-        # Simulate transport-corrupted old_string and new_string where an
-        # apostrophe-like context got prefixed with a backslash. The content
-        # itself has no apostrophe, but both strings do — matching via
-        # whitespace/anchor strategies would otherwise succeed.
-        old_string = "x = \"hello there\" # don\\'t edit\n"
-        new_string = "x = \"hi there\" # don\\'t edit\n"
-        # This particular pair won't match anything, so it exits via
-        # no-match path. Build a case where a non-exact strategy DOES match.
-        content = "line\n    x = 1\nline"
-        old_string = "line\n  x = \\'a\\'\nline"
-        new_string = "line\n  x = \\'b\\'\nline"
-        new, count, strategy, err = fuzzy_find_and_replace(content, old_string, new_string)
-        assert count == 0
-        assert err is not None and "Escape-drift" in err
-        assert "backslash" in err.lower()
-        assert new == content  # file untouched
-
-    def test_drift_blocked_double_quote(self):
-        """Same idea but with \\" drift instead of \\'."""
-        content = 'line\n    x = 1\nline'
-        old_string = 'line\n  x = \\"a\\"\nline'
-        new_string = 'line\n  x = \\"b\\"\nline'
-        new, count, strategy, err = fuzzy_find_and_replace(content, old_string, new_string)
-        assert count == 0
-        assert err is not None and "Escape-drift" in err
-
-    def test_drift_allowed_when_file_genuinely_has_backslash_escapes(self):
-        """If the file already contains \\' (e.g. inside an existing escaped
-        string), the model is legitimately preserving it. Guard must NOT
-        fire."""
-        content = "line\n  x = \\'a\\'\nline"
-        old_string = "line\n  x = \\'a\\'\nline"
-        new_string = "line\n  x = \\'b\\'\nline"
-        new, count, strategy, err = fuzzy_find_and_replace(content, old_string, new_string)
-        assert err is None
-        assert count == 1
-        assert "\\'b\\'" in new
-
-    def test_drift_allowed_on_exact_match(self):
-        """Exact matches bypass the drift guard entirely — if the file
-        really contains the exact bytes old_string specified, it's not
-        drift."""
-        content = "hello \\'world\\'"
-        new, count, strategy, err = fuzzy_find_and_replace(
-            content, "hello \\'world\\'", "hello \\'there\\'"
-        )
-        assert err is None
-        assert count == 1
-        assert strategy == "exact"
-
-    def test_drift_allowed_when_adding_escaped_strings(self):
-        """Model is adding new content with \\' that wasn't in the original.
-        old_string has no \\', so guard doesn't fire."""
-        content = "line1\nline2\nline3"
-        old_string = "line1\nline2\nline3"
-        new_string = "line1\nprint(\\'added\\')\nline2\nline3"
-        new, count, strategy, err = fuzzy_find_and_replace(content, old_string, new_string)
-        assert err is None
-        assert count == 1
-        assert "\\'added\\'" in new
-
-    def test_no_drift_check_when_new_string_lacks_suspect_chars(self):
-        """Fast-path: if new_string has no \\' or \\", guard must not
-        fire even on fuzzy match."""
-        content = "def foo():\n    pass"  # extra space ignored by line_trimmed
-        old_string = "def foo():\n  pass"
-        new_string = "def bar():\n  return 1"
-        new, count, strategy, err = fuzzy_find_and_replace(content, old_string, new_string)
-        assert err is None
-        assert count == 1
-
-
-class TestFindClosestLines:
-    def setup_method(self):
-        from tools.fuzzy_match import find_closest_lines
-        self.find_closest_lines = find_closest_lines
-
-    def test_finds_similar_line(self):
-        content = "def foo():\n    pass\ndef bar():\n    return 1\n"
-        result = self.find_closest_lines("def baz():", content)
-        assert "def foo" in result or "def bar" in result
-
-    def test_returns_empty_for_no_match(self):
-        content = "completely different content here"
-        result = self.find_closest_lines("xyzzy_no_match_possible_!!!", content)
-        assert result == ""
-
-    def test_returns_empty_for_empty_inputs(self):
-        assert self.find_closest_lines("", "some content") == ""
-        assert self.find_closest_lines("old string", "") == ""
-
-    def test_includes_context_lines(self):
-        content = "line1\nline2\ndef target():\n    pass\nline5\n"
-        result = self.find_closest_lines("def target():", content)
-        assert "target" in result
-
-    def test_includes_line_numbers(self):
-        content = "line1\nline2\ndef foo():\n    pass\n"
-        result = self.find_closest_lines("def foo():", content)
-        # Should include line numbers in format "N| content"
-        assert "|" in result
-
-
-class TestFormatNoMatchHint:
-    """Gating tests for format_no_match_hint — the shared helper that decides
-    whether a 'Did you mean?' snippet should be appended to an error.
-    """
-
-    def setup_method(self):
-        from tools.fuzzy_match import format_no_match_hint
-        self.fmt = format_no_match_hint
-
-    def test_fires_on_could_not_find_with_match(self):
-        """Classic no-match: similar content exists → hint fires."""
-        content = "def foo():\n    pass\ndef bar():\n    pass\n"
-        result = self.fmt(
-            "Could not find a match for old_string in the file",
-            0, "def baz():", content,
-        )
-        assert "Did you mean" in result
-        assert "foo" in result or "bar" in result
-
-    def test_silent_on_ambiguous_match_error(self):
-        """'Found N matches' is not a missing-match failure — no hint."""
-        content = "aaa bbb aaa\n"
-        result = self.fmt(
-            "Found 2 matches for old_string. Provide more context to make it unique, or use replace_all=True.",
-            0, "aaa", content,
-        )
-        assert result == ""
-
-    def test_silent_on_escape_drift_error(self):
-        """Escape-drift errors are intentional blocks — hint would mislead."""
-        content = "x = 1\n"
-        result = self.fmt(
-            "Escape-drift detected: old_string and new_string contain the literal sequence '\\\\''...",
-            0, "x = \\'1\\'", content,
-        )
-        assert result == ""
-
-    def test_silent_on_identical_strings(self):
-        """old_string == new_string — hint irrelevant."""
-        result = self.fmt(
-            "old_string and new_string are identical",
-            0, "foo", "foo bar\n",
-        )
-        assert result == ""
-
-    def test_silent_when_match_count_nonzero(self):
-        """If match succeeded, we shouldn't be in the error path — defense in depth."""
-        result = self.fmt(
-            "Could not find a match for old_string in the file",
-            1, "foo", "foo bar\n",
-        )
-        assert result == ""
-
-    def test_silent_on_none_error(self):
-        """No error at all — no hint."""
-        result = self.fmt(None, 0, "foo", "bar\n")
-        assert result == ""
-
-    def test_silent_when_no_similar_content(self):
-        """Even for a valid no-match error, skip hint when nothing similar exists."""
-        result = self.fmt(
-            "Could not find a match for old_string in the file",
-            0, "totally_unique_xyzzy_qux", "abc\nxyz\n",
-        )
-        assert result == ""

tests/tools/test_patch_did_you_mean.py

@@ -1,114 +0,0 @@
-import json
-import os
-import textwrap
-from pathlib import Path
-
-import tools.skill_manager_tool as skill_manager_tool
-from tools.file_tools import patch_tool
-from tools.skill_manager_tool import _create_skill, _patch_skill
-
-
-def _disable_patch_tool_guards(monkeypatch):
-    monkeypatch.setattr("tools.file_tools._check_sensitive_path", lambda _path: None)
-    monkeypatch.setattr("tools.file_tools._check_file_staleness", lambda _path, _task_id: None)
-    monkeypatch.setattr("tools.file_tools._log_and_check_conflict", lambda _path, _task_id, _action: None)
-
-
-def test_patch_tool_replace_no_match_shows_rich_hint_without_legacy_hint(tmp_path, monkeypatch):
-    _disable_patch_tool_guards(monkeypatch)
-    sample = tmp_path / "sample.py"
-    sample.write_text("def foo():\n    return 1\n\ndef bar():\n    return 2\n", encoding="utf-8")
-
-    raw = patch_tool(
-        mode="replace",
-        path=str(sample),
-        old_string="def barycentric():",
-        new_string="def barycentric_new():",
-        task_id="qa960-replace-rich-hint",
-    )
-
-    result = json.loads(raw)
-    assert result["success"] is False
-    assert "Could not find a match" in result["error"]
-    assert "Did you mean one of these sections?" in result["error"]
-    assert "def bar():" in result["error"] or "def foo():" in result["error"]
-    assert "[Hint:" not in raw
-
-
-def test_patch_tool_replace_ambiguous_error_does_not_show_did_you_mean(tmp_path, monkeypatch):
-    _disable_patch_tool_guards(monkeypatch)
-    sample = tmp_path / "sample.py"
-    sample.write_text("aaa\nbbb\naaa\n", encoding="utf-8")
-
-    raw = patch_tool(
-        mode="replace",
-        path=str(sample),
-        old_string="aaa",
-        new_string="ccc",
-        task_id="qa960-replace-ambiguous",
-    )
-
-    result = json.loads(raw)
-    assert result["success"] is False
-    assert "Found 2 matches" in result["error"]
-    assert "Did you mean one of these sections?" not in result["error"]
-    assert "[Hint:" not in raw
-
-
-def test_patch_tool_v4a_no_match_shows_rich_hint(tmp_path, monkeypatch):
-    _disable_patch_tool_guards(monkeypatch)
-    sample = tmp_path / "sample.py"
-    sample.write_text("def foo():\n    return 1\n", encoding="utf-8")
-
-    patch = textwrap.dedent(
-        f"""\
-        *** Begin Patch
-        *** Update File: {sample}
-        @@
-        -def barycentric():
-        +def barycentric_new():
-        *** End Patch
-        """
-    )
-
-    raw = patch_tool(mode="patch", patch=patch, task_id="qa960-v4a-rich-hint")
-    result = json.loads(raw)
-    assert result["success"] is False
-    assert "Patch validation failed" in result["error"]
-    assert "Did you mean one of these sections?" in result["error"]
-    assert "def foo():" in result["error"]
-
-
-def test_skill_patch_no_match_shows_rich_hint(tmp_path, monkeypatch):
-    monkeypatch.setenv("HERMES_HOME", str(tmp_path))
-    skills_dir = tmp_path / "skills"
-    skills_dir.mkdir(parents=True, exist_ok=True)
-    monkeypatch.setattr(skill_manager_tool, "SKILLS_DIR", skills_dir)
-    monkeypatch.setattr(skill_manager_tool, "_security_scan_skill", lambda _skill_dir: None)
-
-    _create_skill(
-        "qa-skill",
-        textwrap.dedent(
-            """\
-            ---
-            name: qa-skill
-            description: test
-            ---
-
-            Step 1: Do the thing.
-            Step 2: Verify the thing.
-            """
-        ),
-    )
-
-    result = _patch_skill(
-        "qa-skill",
-        "Step 1: Do the production rollout.",
-        "Step 1: Updated.",
-    )
-
-    assert result["success"] is False
-    assert "Could not find a match" in result["error"]
-    assert "Did you mean one of these sections?" in result["error"]
-    assert "Step 1: Do the thing." in result["error"]
-    assert "file_preview" in result

tests/tools/test_tts_kittentts.py

@@ -0,0 +1,236 @@
+"""Tests for the KittenTTS local provider in tools/tts_tool.py."""
+
+import json
+from unittest.mock import MagicMock, patch
+
+import numpy as np
+import pytest
+
+
+@pytest.fixture(autouse=True)
+def clean_env(monkeypatch):
+    for key in ("HERMES_SESSION_PLATFORM",):
+        monkeypatch.delenv(key, raising=False)
+
+
+@pytest.fixture(autouse=True)
+def clear_kittentts_cache():
+    """Reset the module-level model cache between tests."""
+    from tools import tts_tool as _tt
+    _tt._kittentts_model_cache.clear()
+    yield
+    _tt._kittentts_model_cache.clear()
+
+
+@pytest.fixture
+def mock_kittentts_module():
+    """Inject a fake kittentts + soundfile module that return stub objects."""
+    fake_model = MagicMock()
+    # 24kHz float32 PCM at ~2s of silence
+    fake_model.generate.return_value = np.zeros(48000, dtype=np.float32)
+    fake_cls = MagicMock(return_value=fake_model)
+    fake_kittentts = MagicMock()
+    fake_kittentts.KittenTTS = fake_cls
+
+    # Stub soundfile — the real package isn't installed in CI venv, and
+    # _generate_kittentts does `import soundfile as sf` at runtime.
+    fake_sf = MagicMock()
+
+    def _fake_write(path, audio, samplerate):
+        # Emulate writing a real file so downstream path checks succeed.
+        import pathlib
+
+        pathlib.Path(path).write_bytes(b"RIFF\x00\x00\x00\x00WAVEfmt fake")
+
+    fake_sf.write = _fake_write
+
+    with patch.dict(
+        "sys.modules",
+        {"kittentts": fake_kittentts, "soundfile": fake_sf},
+    ):
+        yield fake_model, fake_cls
+
+
+class TestGenerateKittenTts:
+    def test_successful_wav_generation(self, tmp_path, mock_kittentts_module):
+        from tools.tts_tool import _generate_kittentts
+
+        fake_model, fake_cls = mock_kittentts_module
+        output_path = str(tmp_path / "test.wav")
+        result = _generate_kittentts("Hello world", output_path, {})
+
+        assert result == output_path
+        assert (tmp_path / "test.wav").exists()
+        fake_cls.assert_called_once()
+        fake_model.generate.assert_called_once()
+
+    def test_config_passes_voice_speed_cleantext(self, tmp_path, mock_kittentts_module):
+        from tools.tts_tool import _generate_kittentts
+
+        fake_model, _ = mock_kittentts_module
+        config = {
+            "kittentts": {
+                "model": "KittenML/kitten-tts-mini-0.8",
+                "voice": "Luna",
+                "speed": 1.25,
+                "clean_text": False,
+            }
+        }
+        _generate_kittentts("Hi there", str(tmp_path / "out.wav"), config)
+
+        call_kwargs = fake_model.generate.call_args.kwargs
+        assert call_kwargs["voice"] == "Luna"
+        assert call_kwargs["speed"] == 1.25
+        assert call_kwargs["clean_text"] is False
+
+    def test_default_model_and_voice(self, tmp_path, mock_kittentts_module):
+        from tools.tts_tool import (
+            DEFAULT_KITTENTTS_MODEL,
+            DEFAULT_KITTENTTS_VOICE,
+            _generate_kittentts,
+        )
+
+        fake_model, fake_cls = mock_kittentts_module
+        _generate_kittentts("Hi", str(tmp_path / "out.wav"), {})
+
+        fake_cls.assert_called_once_with(DEFAULT_KITTENTTS_MODEL)
+        assert fake_model.generate.call_args.kwargs["voice"] == DEFAULT_KITTENTTS_VOICE
+
+    def test_model_is_cached_across_calls(self, tmp_path, mock_kittentts_module):
+        from tools.tts_tool import _generate_kittentts
+
+        _, fake_cls = mock_kittentts_module
+        _generate_kittentts("One", str(tmp_path / "a.wav"), {})
+        _generate_kittentts("Two", str(tmp_path / "b.wav"), {})
+
+        # Same model name → class instantiated exactly once
+        assert fake_cls.call_count == 1
+
+    def test_different_models_are_cached_separately(self, tmp_path, mock_kittentts_module):
+        from tools.tts_tool import _generate_kittentts
+
+        _, fake_cls = mock_kittentts_module
+        _generate_kittentts(
+            "A",
+            str(tmp_path / "a.wav"),
+            {"kittentts": {"model": "KittenML/kitten-tts-nano-0.8-int8"}},
+        )
+        _generate_kittentts(
+            "B",
+            str(tmp_path / "b.wav"),
+            {"kittentts": {"model": "KittenML/kitten-tts-mini-0.8"}},
+        )
+
+        assert fake_cls.call_count == 2
+
+    def test_non_wav_extension_triggers_ffmpeg_conversion(
+        self, tmp_path, mock_kittentts_module, monkeypatch
+    ):
+        """Non-.wav output path causes WAV → target ffmpeg conversion."""
+        from tools import tts_tool as _tt
+
+        calls = []
+
+        def fake_shutil_which(cmd):
+            return "/usr/bin/ffmpeg" if cmd == "ffmpeg" else None
+
+        def fake_run(cmd, check=False, timeout=None, **kw):
+            calls.append(cmd)
+            # Emulate ffmpeg writing the output file
+            import pathlib
+
+            out_path = cmd[-1]
+            pathlib.Path(out_path).write_bytes(b"fake-mp3-data")
+            return MagicMock(returncode=0)
+
+        monkeypatch.setattr(_tt.shutil, "which", fake_shutil_which)
+        monkeypatch.setattr(_tt.subprocess, "run", fake_run)
+
+        output_path = str(tmp_path / "test.mp3")
+        result = _tt._generate_kittentts("Hi", output_path, {})
+
+        assert result == output_path
+        assert len(calls) == 1
+        assert calls[0][0] == "/usr/bin/ffmpeg"
+
+    def test_missing_kittentts_raises_import_error(self, tmp_path, monkeypatch):
+        """When kittentts package is not installed, _import_kittentts raises."""
+        import sys
+
+        monkeypatch.setitem(sys.modules, "kittentts", None)
+        from tools.tts_tool import _generate_kittentts
+
+        with pytest.raises((ImportError, TypeError)):
+            _generate_kittentts("Hi", str(tmp_path / "out.wav"), {})
+
+
+class TestCheckKittenttsAvailable:
+    def test_reports_available_when_package_present(self, monkeypatch):
+        import importlib.util
+        from tools.tts_tool import _check_kittentts_available
+
+        fake_spec = MagicMock()
+        monkeypatch.setattr(
+            importlib.util,
+            "find_spec",
+            lambda name: fake_spec if name == "kittentts" else None,
+        )
+        assert _check_kittentts_available() is True
+
+    def test_reports_unavailable_when_package_missing(self, monkeypatch):
+        import importlib.util
+        from tools.tts_tool import _check_kittentts_available
+
+        monkeypatch.setattr(importlib.util, "find_spec", lambda name: None)
+        assert _check_kittentts_available() is False
+
+
+class TestDispatcherBranch:
+    def test_kittentts_not_installed_returns_helpful_error(self, monkeypatch, tmp_path):
+        """When provider=kittentts but package missing, return JSON error with setup hint."""
+        import sys
+
+        monkeypatch.setitem(sys.modules, "kittentts", None)
+        monkeypatch.setenv("HERMES_HOME", str(tmp_path))
+
+        from tools.tts_tool import text_to_speech_tool
+
+        # Write a config telling it to use kittentts
+        import yaml
+
+        (tmp_path / "config.yaml").write_text(
+            yaml.safe_dump({"tts": {"provider": "kittentts"}})
+        )
+
+        result = json.loads(text_to_speech_tool(text="Hello"))
+        assert result["success"] is False
+        assert "kittentts" in result["error"].lower()
+        assert "hermes setup tts" in result["error"].lower()
+
+    def test_non_telegram_explicit_wav_path_is_preserved(
+        self, monkeypatch, tmp_path, mock_kittentts_module
+    ):
+        """Explicit WAV outputs should stay WAV outside Telegram sessions."""
+        import yaml
+        from tools import tts_tool as _tt
+
+        monkeypatch.setenv("HERMES_HOME", str(tmp_path))
+        (tmp_path / "config.yaml").write_text(
+            yaml.safe_dump({"tts": {"provider": "kittentts"}})
+        )
+
+        def fail_convert(_path):
+            raise AssertionError("_convert_to_opus should not run outside Telegram")
+
+        monkeypatch.setattr(_tt, "_convert_to_opus", fail_convert)
+
+        result = json.loads(
+            _tt.text_to_speech_tool(
+                text="Hello from KittenTTS",
+                output_path=str(tmp_path / "out.wav"),
+            )
+        )
+
+        assert result["success"] is True
+        assert result["file_path"] == str(tmp_path / "out.wav")
+        assert (tmp_path / "out.wav").exists()

tools/file_operations.py

@@ -757,14 +757,12 @@ class ShellFileOperations(FileOperations):
             content, old_string, new_string, replace_all
         )
         
-        if error or match_count == 0:
-            err_msg = error or f"Could not find match for old_string in {path}"
-            try:
-                from tools.fuzzy_match import format_no_match_hint
-                err_msg += format_no_match_hint(err_msg, match_count, old_string, content)
-            except Exception:
-                pass
-            return PatchResult(error=err_msg)
+        if error:
+            return PatchResult(error=error)
+        
+        if match_count == 0:
+            return PatchResult(error=f"Could not find match for old_string in {path}")
+        
         # Write back
         write_result = self.write_file(path, new_content)
         if write_result.error:

tools/file_tools.py

@@ -8,7 +8,6 @@ import os
 import threading
 import time
 from pathlib import Path
-from typing import Any, Dict, Optional
 from tools.binary_extensions import has_binary_extension
 from tools.file_operations import ShellFileOperations
 from agent.redact import redact_sensitive_text
@@ -691,11 +690,8 @@ def patch_tool(mode: str = "replace", path: str = None, old_string: str = None,
         result_json = json.dumps(result_dict, ensure_ascii=False)
         # Hint when old_string not found — saves iterations where the agent
         # retries with stale content instead of re-reading the file.
-        # Suppressed when patch_replace already attached a rich "Did you mean?"
-        # snippet (which is strictly more useful than the generic hint).
         if result_dict.get("error") and "Could not find" in str(result_dict["error"]):
-            if "Did you mean one of these sections?" not in str(result_dict["error"]):
-                result_json += "\n\n[Hint: old_string not found. Use read_file to verify the current content, or search_files to locate the text.]"
+            result_json += "\n\n[Hint: old_string not found. Use read_file to verify the current content, or search_files to locate the text.]"
         return result_json
     except Exception as e:
         return tool_error(str(e))

tools/fuzzy_match.py

@@ -93,21 +93,6 @@ def fuzzy_find_and_replace(content: str, old_string: str, new_string: str,
                     f"Provide more context to make it unique, or use replace_all=True."
                 )
 
-            # Escape-drift guard: when the matched strategy is NOT `exact`,
-            # we matched via some form of normalization. If new_string
-            # contains shell/JSON-style escape sequences (\\' or \\") that
-            # would be written literally into the file but the matched
-            # region of the file has no such sequences, this is almost
-            # certainly tool-call serialization drift — the model typed
-            # an apostrophe/quote and the transport added a stray
-            # backslash. Writing new_string as-is would corrupt the file.
-            # Block with a helpful error so the model re-reads and retries
-            # instead of the caller silently persisting garbage (or not).
-            if strategy_name != "exact":
-                drift_err = _detect_escape_drift(content, matches, old_string, new_string)
-                if drift_err:
-                    return content, 0, None, drift_err
-
             # Perform replacement
             new_content = _apply_replacements(content, matches, new_string)
             return new_content, len(matches), strategy_name, None
@@ -116,46 +101,6 @@ def fuzzy_find_and_replace(content: str, old_string: str, new_string: str,
     return content, 0, None, "Could not find a match for old_string in the file"
 
 
-def _detect_escape_drift(content: str, matches: List[Tuple[int, int]],
-                         old_string: str, new_string: str) -> Optional[str]:
-    """Detect tool-call escape-drift artifacts in new_string.
-
-    Looks for ``\\'`` or ``\\"`` sequences that are present in both
-    old_string and new_string (i.e. the model copy-pasted them as "context"
-    it intended to preserve) but don't exist in the matched region of the
-    file. That pattern indicates the transport layer inserted spurious
-    shell-style escapes around apostrophes or quotes — writing new_string
-    verbatim would literally insert ``\\'`` into source code.
-
-    Returns an error string if drift is detected, None otherwise.
-    """
-    # Cheap pre-check: bail out unless new_string actually contains a
-    # suspect escape sequence. This keeps the guard free for all the
-    # common, correct cases.
-    if "\\'" not in new_string and '\\"' not in new_string:
-        return None
-
-    # Aggregate matched regions of the file — that's what new_string will
-    # replace. If the suspect escapes are present there already, the
-    # model is genuinely preserving them (valid for some languages /
-    # escaped strings); accept the patch.
-    matched_regions = "".join(content[start:end] for start, end in matches)
-
-    for suspect in ("\\'", '\\"'):
-        if suspect in new_string and suspect in old_string and suspect not in matched_regions:
-            plain = suspect[1]  # "'" or '"'
-            return (
-                f"Escape-drift detected: old_string and new_string contain "
-                f"the literal sequence {suspect!r} but the matched region of "
-                f"the file does not. This is almost always a tool-call "
-                f"serialization artifact where an apostrophe or quote got "
-                f"prefixed with a spurious backslash. Re-read the file with "
-                f"read_file and pass old_string/new_string without "
-                f"backslash-escaping {plain!r} characters."
-            )
-    return None
-
-
 def _apply_replacements(content: str, matches: List[Tuple[int, int]], new_string: str) -> str:
     """
     Apply replacements at the given positions.
@@ -619,86 +564,3 @@ def _map_normalized_positions(original: str, normalized: str,
         original_matches.append((orig_start, min(orig_end, len(original))))
     
     return original_matches
-
-
-def find_closest_lines(old_string: str, content: str, context_lines: int = 2, max_results: int = 3) -> str:
-    """Find lines in content most similar to old_string for "did you mean?" feedback.
-
-    Returns a formatted string showing the closest matching lines with context,
-    or empty string if no useful match is found.
-    """
-    if not old_string or not content:
-        return ""
-
-    old_lines = old_string.splitlines()
-    content_lines = content.splitlines()
-
-    if not old_lines or not content_lines:
-        return ""
-
-    # Use first line of old_string as anchor for search
-    anchor = old_lines[0].strip()
-    if not anchor:
-        # Try second line if first is blank
-        candidates = [l.strip() for l in old_lines if l.strip()]
-        if not candidates:
-            return ""
-        anchor = candidates[0]
-
-    # Score each line in content by similarity to anchor
-    scored = []
-    for i, line in enumerate(content_lines):
-        stripped = line.strip()
-        if not stripped:
-            continue
-        ratio = SequenceMatcher(None, anchor, stripped).ratio()
-        if ratio > 0.3:
-            scored.append((ratio, i))
-
-    if not scored:
-        return ""
-
-    # Take top matches
-    scored.sort(key=lambda x: -x[0])
-    top = scored[:max_results]
-
-    parts = []
-    seen_ranges = set()
-    for _, line_idx in top:
-        start = max(0, line_idx - context_lines)
-        end = min(len(content_lines), line_idx + len(old_lines) + context_lines)
-        key = (start, end)
-        if key in seen_ranges:
-            continue
-        seen_ranges.add(key)
-        snippet = "\n".join(
-            f"{start + j + 1:4d}| {content_lines[start + j]}"
-            for j in range(end - start)
-        )
-        parts.append(snippet)
-
-    if not parts:
-        return ""
-
-    return "\n---\n".join(parts)
-
-
-def format_no_match_hint(error: Optional[str], match_count: int,
-                         old_string: str, content: str) -> str:
-    """Return a '\\n\\nDid you mean...' snippet for plain no-match errors.
-
-    Gated so the hint only fires for actual "old_string not found" failures.
-    Ambiguous-match ("Found N matches"), escape-drift, and identical-strings
-    errors all have ``match_count == 0`` but a "did you mean?" snippet would
-    be misleading — those failed for unrelated reasons.
-
-    Returns an empty string when there's nothing useful to append.
-    """
-    if match_count != 0:
-        return ""
-    if not error or not error.startswith("Could not find"):
-        return ""
-    hint = find_closest_lines(old_string, content)
-    if not hint:
-        return ""
-    return "\n\nDid you mean one of these sections?\n" + hint

tools/patch_parser.py

@@ -290,16 +290,10 @@ def _validate_operations(
                 )
                 if count == 0:
                     label = f"'{hunk.context_hint}'" if hunk.context_hint else "(no hint)"
-                    msg = (
+                    errors.append(
                         f"{op.file_path}: hunk {label} not found"
                         + (f" — {match_error}" if match_error else "")
                     )
-                    try:
-                        from tools.fuzzy_match import format_no_match_hint
-                        msg += format_no_match_hint(match_error, count, search_pattern, simulated)
-                    except Exception:
-                        pass
-                    errors.append(msg)
                 else:
                     # Advance simulation so subsequent hunks validate correctly.
                     # Reuse the result from the call above — no second fuzzy run.
@@ -543,13 +537,7 @@ def _apply_update(op: PatchOperation, file_ops: Any) -> Tuple[bool, str]:
                             error = None
                 
                 if error:
-                    err_msg = f"Could not apply hunk: {error}"
-                    try:
-                        from tools.fuzzy_match import format_no_match_hint
-                        err_msg += format_no_match_hint(error, 0, search_pattern, new_content)
-                    except Exception:
-                        pass
-                    return False, err_msg
+                    return False, f"Could not apply hunk: {error}"
         else:
             # Addition-only hunk (no context or removed lines).
             # Insert at the location indicated by the context hint, or at end of file.

tools/skill_manager_tool.py

@@ -575,15 +575,9 @@ def _patch_skill(
     if match_error:
         # Show a short preview of the file so the model can self-correct
         preview = content[:500] + ("..." if len(content) > 500 else "")
-        err_msg = match_error
-        try:
-            from tools.fuzzy_match import format_no_match_hint
-            err_msg += format_no_match_hint(match_error, match_count, old_string, content)
-        except Exception:
-            pass
         return {
             "success": False,
-            "error": err_msg,
+            "error": match_error,
             "file_preview": preview,
         }
 

tools/tts_tool.py

@@ -2,13 +2,14 @@
 """
 Text-to-Speech Tool Module
 
-Supports six TTS providers:
+Supports seven TTS providers:
 - Edge TTS (default, free, no API key): Microsoft Edge neural voices
 - ElevenLabs (premium): High-quality voices, needs ELEVENLABS_API_KEY
 - OpenAI TTS: Good quality, needs OPENAI_API_KEY
 - MiniMax TTS: High-quality with voice cloning, needs MINIMAX_API_KEY
 - Mistral (Voxtral TTS): Multilingual, native Opus, needs MISTRAL_API_KEY
 - NeuTTS (local, free, no API key): On-device TTS via neutts_cli, needs neutts installed
+- KittenTTS (local, free, no API key): Lightweight on-device ONNX TTS via kittentts
 
 Output formats:
 - Opus (.ogg) for Telegram voice bubbles (requires ffmpeg for Edge TTS)
@@ -77,6 +78,12 @@ def _import_sounddevice():
     return sd
 
 
+def _import_kittentts():
+    """Lazy import KittenTTS. Returns the class or raises ImportError."""
+    from kittentts import KittenTTS
+    return KittenTTS
+
+
 # ===========================================================================
 # Defaults
 # ===========================================================================
@@ -86,6 +93,8 @@ DEFAULT_ELEVENLABS_VOICE_ID = "pNInz6obpgDQGcFmaJgB"  # Adam
 DEFAULT_ELEVENLABS_MODEL_ID = "eleven_multilingual_v2"
 DEFAULT_ELEVENLABS_STREAMING_MODEL_ID = "eleven_flash_v2_5"
 DEFAULT_OPENAI_MODEL = "gpt-4o-mini-tts"
+DEFAULT_KITTENTTS_MODEL = "KittenML/kitten-tts-nano-0.8-int8"  # 25MB
+DEFAULT_KITTENTTS_VOICE = "Jasper"
 DEFAULT_OPENAI_VOICE = "alloy"
 DEFAULT_OPENAI_BASE_URL = "https://api.openai.com/v1"
 DEFAULT_MINIMAX_MODEL = "speech-2.8-hd"
@@ -448,6 +457,15 @@ def _check_neutts_available() -> bool:
         return False
 
 
+def _check_kittentts_available() -> bool:
+    """Check if the kittentts engine is importable (installed locally)."""
+    try:
+        import importlib.util
+        return importlib.util.find_spec("kittentts") is not None
+    except Exception:
+        return False
+
+
 def _default_neutts_ref_audio() -> str:
     """Return path to the bundled default voice reference audio."""
     return str(Path(__file__).parent / "neutts_samples" / "jo.wav")
@@ -511,6 +529,51 @@ def _generate_neutts(text: str, output_path: str, tts_config: Dict[str, Any]) ->
     return output_path
 
 
+# ===========================================================================
+# Provider: KittenTTS (local, lightweight)
+# ===========================================================================
+
+# Module-level cache for KittenTTS model instances
+_kittentts_model_cache: Dict[str, Any] = {}
+
+
+def _generate_kittentts(text: str, output_path: str, tts_config: Dict[str, Any]) -> str:
+    """Generate speech using the local KittenTTS ONNX model."""
+    KittenTTS = _import_kittentts()
+    kt_config = tts_config.get("kittentts", {})
+    model_name = kt_config.get("model", DEFAULT_KITTENTTS_MODEL)
+    voice = kt_config.get("voice", DEFAULT_KITTENTTS_VOICE)
+    speed = kt_config.get("speed", 1.0)
+    clean_text = kt_config.get("clean_text", True)
+
+    global _kittentts_model_cache
+    if model_name not in _kittentts_model_cache:
+        logger.info("[KittenTTS] Loading model: %s", model_name)
+        _kittentts_model_cache[model_name] = KittenTTS(model_name)
+
+    model = _kittentts_model_cache[model_name]
+    audio = model.generate(text, voice=voice, speed=speed, clean_text=clean_text)
+
+    import soundfile as sf
+
+    wav_path = output_path
+    if not output_path.endswith(".wav"):
+        wav_path = output_path.rsplit(".", 1)[0] + ".wav"
+
+    sf.write(wav_path, audio, 24000)
+
+    if wav_path != output_path:
+        ffmpeg = shutil.which("ffmpeg")
+        if ffmpeg:
+            conv_cmd = [ffmpeg, "-i", wav_path, "-y", "-loglevel", "error", output_path]
+            subprocess.run(conv_cmd, check=True, timeout=30)
+            os.remove(wav_path)
+        else:
+            os.rename(wav_path, output_path)
+
+    return output_path
+
+
 # ===========================================================================
 # Main tool function
 # ===========================================================================
@@ -622,6 +685,19 @@ def text_to_speech_tool(
             logger.info("Generating speech with NeuTTS (local)...")
             _generate_neutts(text, file_str, tts_config)
 
+        elif provider == "kittentts":
+            try:
+                _import_kittentts()
+            except ImportError:
+                return json.dumps({
+                    "success": False,
+                    "error": "KittenTTS provider selected but 'kittentts' package not installed. "
+                             "Run 'hermes setup tts' and choose KittenTTS, or install manually: "
+                             "pip install https://github.com/KittenML/KittenTTS/releases/download/0.8.1/kittentts-0.8.1-py3-none-any.whl"
+                }, ensure_ascii=False)
+            logger.info("Generating speech with KittenTTS (local, lightweight)...")
+            _generate_kittentts(text, file_str, tts_config)
+
         else:
             # Default: Edge TTS (free), with NeuTTS as local fallback
             edge_available = True
@@ -658,10 +734,10 @@ def text_to_speech_tool(
                 "error": f"TTS generation produced no output (provider: {provider})"
             }, ensure_ascii=False)
 
-        # Try Opus conversion for Telegram compatibility
-        # Edge TTS outputs MP3, NeuTTS outputs WAV — both need ffmpeg conversion
+        # Try Opus conversion for Telegram compatibility only.
+        # Outside Telegram, preserve the caller's explicit output format.
         voice_compatible = False
-        if provider in ("edge", "neutts", "minimax") and not file_str.endswith(".ogg"):
+        if want_opus and provider in ("edge", "neutts", "minimax", "kittentts") and not file_str.endswith(".ogg"):
             opus_path = _convert_to_opus(file_str)
             if opus_path:
                 file_str = opus_path
@@ -742,6 +818,8 @@ def check_tts_requirements() -> bool:
         pass
     if _check_neutts_available():
         return True
+    if _check_kittentts_available():
+        return True
     return False
 
 

website/docs/user-guide/features/tts.md

@@ -10,7 +10,7 @@ Hermes Agent supports both text-to-speech output and voice message transcription
 
 ## Text-to-Speech
 
-Convert text to speech with six providers:
+Convert text to speech with seven providers:
 
 | Provider | Quality | Cost | API Key |
 |----------|---------|------|---------|
@@ -20,6 +20,7 @@ Convert text to speech with six providers:
 | **MiniMax TTS** | Excellent | Paid | `MINIMAX_API_KEY` |
 | **Mistral (Voxtral TTS)** | Excellent | Paid | `MISTRAL_API_KEY` |
 | **NeuTTS** | Good | Free | None needed |
+| **KittenTTS** | Good | Free (local) | None needed |
 
 ### Platform Delivery
 
@@ -35,7 +36,7 @@ Convert text to speech with six providers:
 ```yaml
 # In ~/.hermes/config.yaml
 tts:
-  provider: "edge"              # "edge" | "elevenlabs" | "openai" | "minimax" | "mistral" | "neutts"
+  provider: "edge"              # "edge" | "elevenlabs" | "openai" | "minimax" | "mistral" | "neutts" | "kittentts"
   speed: 1.0                    # Global speed multiplier (provider-specific settings override this)
   edge:
     voice: "en-US-AriaNeural"   # 322 voices, 74 languages
@@ -62,6 +63,11 @@ tts:
     ref_text: ''
     model: neuphonic/neutts-air-q4-gguf
     device: cpu
+  kittentts:
+    model: KittenML/kitten-tts-nano-0.8-int8   # 25MB int8 default; also micro and mini variants
+    voice: Jasper                               # Jasper, Bella, Luna, Bruno, Rosie, Hugo, Kiki, Leo
+    speed: 1.0
+    clean_text: true
 ```
 
 **Speed control**: The global `tts.speed` value applies to all providers by default. Each provider can override it with its own `speed` setting (e.g., `tts.openai.speed: 1.5`). Provider-specific speed takes precedence over the global value. Default is `1.0` (normal speed).
@@ -74,6 +80,7 @@ Telegram voice bubbles require Opus/OGG audio format:
 - **Edge TTS** (default) outputs MP3 and needs **ffmpeg** to convert:
 - **MiniMax TTS** outputs MP3 and needs **ffmpeg** to convert for Telegram voice bubbles
 - **NeuTTS** outputs WAV and also needs **ffmpeg** to convert for Telegram voice bubbles
+- **KittenTTS** outputs WAV and also needs **ffmpeg** to convert for Telegram voice bubbles
 
 ```bash
 # Ubuntu/Debian
@@ -86,7 +93,7 @@ brew install ffmpeg
 sudo dnf install ffmpeg
 ```
 
-Without ffmpeg, Edge TTS, MiniMax TTS, and NeuTTS audio are sent as regular audio files (playable, but shown as a rectangular player instead of a voice bubble).
+Without ffmpeg, Edge TTS, MiniMax TTS, NeuTTS, and KittenTTS audio are sent as regular audio files (playable, but shown as a rectangular player instead of a voice bubble).
 
 :::tip
 If you want voice bubbles without installing ffmpeg, switch to the OpenAI, ElevenLabs, or Mistral provider.