feat(memory): add grounded observation synthesis layer

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) | "kittentts" (local)
+        "provider": "edge",  # "edge" (free) | "elevenlabs" (premium) | "openai" | "minimax" | "mistral" | "neutts" (local)
         "edge": {
             "voice": "en-US-AriaNeural",
             # Popular: AriaNeural, JennyNeural, AndrewNeural, BrianNeural, SoniaNeural
@@ -547,12 +547,6 @@ 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

@@ -443,16 +443,6 @@ 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))
 
@@ -901,7 +891,6 @@ 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()
@@ -921,34 +910,8 @@ 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 local providers."""
-
+    """Interactive TTS provider selection with install flow for NeuTTS."""
     tts_config = config.get("tts", {})
     current_provider = tts_config.get("provider", "edge")
     subscription_features = get_nous_subscription_features(config)
@@ -960,7 +923,6 @@ 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)
 
@@ -982,10 +944,9 @@ 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", "kittentts"])
+    providers.extend(["edge", "elevenlabs", "openai", "minimax", "mistral", "neutts"])
     choices.append(f"Keep current ({current_label})")
     keep_current_idx = len(choices) - 1
     idx = prompt_choice("Select TTS provider:", choices, keep_current_idx)
@@ -1027,28 +988,6 @@ 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

@@ -164,14 +164,6 @@ 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": {
@@ -411,36 +403,6 @@ 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")

plugins/memory/holographic/__init__.py

@@ -26,6 +26,7 @@ from agent.memory_provider import MemoryProvider
 from tools.registry import tool_error
 from .store import MemoryStore
 from .retrieval import FactRetriever
+from .observations import ObservationSynthesizer
 
 logger = logging.getLogger(__name__)
 
@@ -37,28 +38,29 @@ logger = logging.getLogger(__name__)
 FACT_STORE_SCHEMA = {
     "name": "fact_store",
     "description": (
-        "Deep structured memory with algebraic reasoning. "
+        "Deep structured memory with algebraic reasoning and grounded observation synthesis. "
         "Use alongside the memory tool — memory for always-on context, "
-        "fact_store for deep recall and compositional queries.\n\n"
+        "fact_store for deep recall, compositional queries, and higher-order observations.\n\n"
         "ACTIONS (simple → powerful):\n"
         "• add — Store a fact the user would expect you to remember.\n"
         "• search — Keyword lookup ('editor config', 'deploy process').\n"
         "• probe — Entity recall: ALL facts about a person/thing.\n"
         "• related — What connects to an entity? Structural adjacency.\n"
         "• reason — Compositional: facts connected to MULTIPLE entities simultaneously.\n"
+        "• observe — Synthesized higher-order observations backed by supporting facts.\n"
         "• contradict — Memory hygiene: find facts making conflicting claims.\n"
         "• update/remove/list — CRUD operations.\n\n"
-        "IMPORTANT: Before answering questions about the user, ALWAYS probe or reason first."
+        "IMPORTANT: Before answering questions about the user, ALWAYS probe/reason/observe first."
     ),
     "parameters": {
         "type": "object",
         "properties": {
             "action": {
                 "type": "string",
-                "enum": ["add", "search", "probe", "related", "reason", "contradict", "update", "remove", "list"],
+                "enum": ["add", "search", "probe", "related", "reason", "observe", "contradict", "update", "remove", "list"],
             },
             "content": {"type": "string", "description": "Fact content (required for 'add')."},
-            "query": {"type": "string", "description": "Search query (required for 'search')."},
+            "query": {"type": "string", "description": "Search query (required for 'search'/'observe')."},
             "entity": {"type": "string", "description": "Entity name for 'probe'/'related'."},
             "entities": {"type": "array", "items": {"type": "string"}, "description": "Entity names for 'reason'."},
             "fact_id": {"type": "integer", "description": "Fact ID for 'update'/'remove'."},
@@ -66,6 +68,12 @@ FACT_STORE_SCHEMA = {
             "tags": {"type": "string", "description": "Comma-separated tags."},
             "trust_delta": {"type": "number", "description": "Trust adjustment for 'update'."},
             "min_trust": {"type": "number", "description": "Minimum trust filter (default: 0.3)."},
+            "min_confidence": {"type": "number", "description": "Minimum observation confidence (default: 0.6)."},
+            "observation_type": {
+                "type": "string",
+                "enum": ["recurring_preference", "stable_direction", "behavioral_pattern"],
+                "description": "Optional observation type filter for 'observe'.",
+            },
             "limit": {"type": "integer", "description": "Max results (default: 10)."},
         },
         "required": ["action"],
@@ -118,7 +126,9 @@ class HolographicMemoryProvider(MemoryProvider):
         self._config = config or _load_plugin_config()
         self._store = None
         self._retriever = None
+        self._observation_synth = None
         self._min_trust = float(self._config.get("min_trust_threshold", 0.3))
+        self._observation_min_confidence = float(self._config.get("observation_min_confidence", 0.6))
 
     @property
     def name(self) -> str:
@@ -177,6 +187,7 @@ class HolographicMemoryProvider(MemoryProvider):
             hrr_weight=hrr_weight,
             hrr_dim=hrr_dim,
         )
+        self._observation_synth = ObservationSynthesizer(self._store)
         self._session_id = session_id
 
     def system_prompt_block(self) -> str:
@@ -193,30 +204,76 @@ class HolographicMemoryProvider(MemoryProvider):
                 "# Holographic Memory\n"
                 "Active. Empty fact store — proactively add facts the user would expect you to remember.\n"
                 "Use fact_store(action='add') to store durable structured facts about people, projects, preferences, decisions.\n"
+                "Use fact_store(action='observe') to synthesize higher-order observations with evidence.\n"
                 "Use fact_feedback to rate facts after using them (trains trust scores)."
             )
         return (
             f"# Holographic Memory\n"
             f"Active. {total} facts stored with entity resolution and trust scoring.\n"
-            f"Use fact_store to search, probe entities, reason across entities, or add facts.\n"
+            f"Use fact_store to search, probe entities, reason across entities, or synthesize observations.\n"
             f"Use fact_feedback to rate facts after using them (trains trust scores)."
         )
 
     def prefetch(self, query: str, *, session_id: str = "") -> str:
-        if not self._retriever or not query:
+        if not query:
             return ""
+
+        parts = []
+        raw_results = []
         try:
-            results = self._retriever.search(query, min_trust=self._min_trust, limit=5)
-            if not results:
-                return ""
+            if self._retriever:
+                raw_results = self._retriever.search(query, min_trust=self._min_trust, limit=5)
+        except Exception as e:
+            logger.debug("Holographic prefetch fact search failed: %s", e)
+            raw_results = []
+
+        observations = []
+        try:
+            if self._observation_synth:
+                observations = self._observation_synth.observe(
+                    query,
+                    min_confidence=self._observation_min_confidence,
+                    limit=3,
+                    refresh=True,
+                )
+        except Exception as e:
+            logger.debug("Holographic prefetch observation search failed: %s", e)
+            observations = []
+
+        if not raw_results and observations:
+            seen_fact_ids = set()
+            evidence_backfill = []
+            for observation in observations:
+                for evidence in observation.get("evidence", []):
+                    fact_id = evidence.get("fact_id")
+                    if fact_id in seen_fact_ids:
+                        continue
+                    seen_fact_ids.add(fact_id)
+                    evidence_backfill.append(evidence)
+            raw_results = evidence_backfill[:5]
+
+        if raw_results:
             lines = []
-            for r in results:
+            for r in raw_results:
                 trust = r.get("trust_score", r.get("trust", 0))
                 lines.append(f"- [{trust:.1f}] {r.get('content', '')}")
-            return "## Holographic Memory\n" + "\n".join(lines)
-        except Exception as e:
-            logger.debug("Holographic prefetch failed: %s", e)
-            return ""
+            parts.append("## Holographic Memory\n" + "\n".join(lines))
+
+        if observations:
+            lines = []
+            for observation in observations:
+                evidence_ids = ", ".join(
+                    f"#{item['fact_id']}" for item in observation.get("evidence", [])[:3]
+                ) or "none"
+                lines.append(
+                    f"- [{observation.get('confidence', 0.0):.2f}] "
+                    f"{observation.get('observation_type', 'observation')}: "
+                    f"{observation.get('summary', '')} "
+                    f"(evidence: {evidence_ids})"
+                )
+            parts.append("## Holographic Observations\n" + "\n".join(lines))
+
+        return "\n\n".join(parts)
 
     def sync_turn(self, user_content: str, assistant_content: str, *, session_id: str = "") -> None:
         # Holographic memory stores explicit facts via tools, not auto-sync.
@@ -252,6 +309,7 @@ class HolographicMemoryProvider(MemoryProvider):
     def shutdown(self) -> None:
         self._store = None
         self._retriever = None
+        self._observation_synth = None
 
     # -- Tool handlers -------------------------------------------------------
 
@@ -305,6 +363,19 @@ class HolographicMemoryProvider(MemoryProvider):
                 )
                 return json.dumps({"results": results, "count": len(results)})
 
+            elif action == "observe":
+                synthesizer = self._observation_synth
+                if not synthesizer:
+                    return tool_error("Observation synthesizer is not initialized")
+                observations = synthesizer.observe(
+                    args.get("query", ""),
+                    observation_type=args.get("observation_type"),
+                    min_confidence=float(args.get("min_confidence", self._observation_min_confidence)),
+                    limit=int(args.get("limit", 10)),
+                    refresh=True,
+                )
+                return json.dumps({"observations": observations, "count": len(observations)})
+
             elif action == "contradict":
                 results = retriever.contradict(
                     category=args.get("category"),

plugins/memory/holographic/observations.py

@@ -0,0 +1,249 @@
+"""Higher-order observation synthesis for holographic memory.
+
+Builds grounded observations from accumulated facts and keeps them in a
+separate retrieval layer with explicit evidence links back to supporting facts.
+"""
+
+from __future__ import annotations
+
+import re
+from typing import Any
+
+from .store import MemoryStore
+
+_TOKEN_RE = re.compile(r"[a-z0-9_]+")
+_HIGHER_ORDER_CUES = {
+    "prefer",
+    "preference",
+    "preferences",
+    "style",
+    "pattern",
+    "patterns",
+    "behavior",
+    "behaviour",
+    "habit",
+    "habits",
+    "workflow",
+    "direction",
+    "trajectory",
+    "strategy",
+    "tend",
+    "usually",
+}
+
+_OBSERVATION_PATTERNS = [
+    {
+        "observation_type": "recurring_preference",
+        "subject": "communication_style",
+        "categories": {"user_pref", "general"},
+        "labels": {
+            "concise": ["concise", "terse", "brief", "short", "no fluff"],
+            "result_first": ["result-only", "result only", "outcome only", "quick", "quickly"],
+            "silent_ops": ["silent", "no status", "no repetitive status", "no questions"],
+        },
+        "summary_prefix": "Recurring preference",
+    },
+    {
+        "observation_type": "stable_direction",
+        "subject": "project_direction",
+        "categories": {"project", "general", "tool"},
+        "labels": {
+            "local_first": ["local-first", "local first", "local-only", "local only", "ollama", "own hardware"],
+            "gitea_first": ["gitea-first", "gitea first", "forge", "pull request", "pr flow", "issue flow"],
+            "ansible": ["ansible", "playbook", "role", "deploy via ansible"],
+        },
+        "summary_prefix": "Stable direction",
+    },
+    {
+        "observation_type": "behavioral_pattern",
+        "subject": "operator_workflow",
+        "categories": {"general", "project", "tool", "user_pref"},
+        "labels": {
+            "commit_early": ["commit early", "commits early", "commit after", "wip commit"],
+            "pr_first": ["open pr", "push a pr", "pull request", "pr immediately", "create pr"],
+            "dedup_guard": ["no dupes", "no duplicates", "avoid duplicate", "existing pr"],
+        },
+        "summary_prefix": "Behavioral pattern",
+    },
+]
+
+_TYPE_QUERY_HINTS = {
+    "recurring_preference": {"prefer", "preference", "style", "communication", "likes", "wants"},
+    "stable_direction": {"direction", "trajectory", "strategy", "project", "roadmap", "moving"},
+    "behavioral_pattern": {"pattern", "behavior", "workflow", "habit", "operator", "agent", "usually"},
+}
+
+
+class ObservationSynthesizer:
+    """Synthesizes grounded observations from facts and retrieves them by query."""
+
+    def __init__(self, store: MemoryStore):
+        self.store = store
+
+    def synthesize(
+        self,
+        *,
+        persist: bool = True,
+        min_confidence: float = 0.6,
+        limit: int = 10,
+    ) -> list[dict[str, Any]]:
+        facts = self.store.list_facts(min_trust=0.0, limit=1000)
+        observations: list[dict[str, Any]] = []
+
+        for pattern in _OBSERVATION_PATTERNS:
+            candidate = self._build_candidate(pattern, facts, min_confidence=min_confidence)
+            if not candidate:
+                continue
+
+            if persist:
+                candidate["observation_id"] = self.store.upsert_observation(
+                    candidate["observation_type"],
+                    candidate["subject"],
+                    candidate["summary"],
+                    candidate["confidence"],
+                    candidate["evidence_fact_ids"],
+                    metadata=candidate["metadata"],
+                )
+
+            candidate["evidence"] = self._expand_evidence(candidate["evidence_fact_ids"])
+            candidate["evidence_count"] = len(candidate["evidence"])
+            candidate.pop("evidence_fact_ids", None)
+            observations.append(candidate)
+
+        observations.sort(
+            key=lambda item: (item["confidence"], item.get("evidence_count", 0)),
+            reverse=True,
+        )
+        return observations[:limit]
+
+    def observe(
+        self,
+        query: str = "",
+        *,
+        observation_type: str | None = None,
+        min_confidence: float = 0.6,
+        limit: int = 10,
+        refresh: bool = True,
+    ) -> list[dict[str, Any]]:
+        if refresh:
+            self.synthesize(persist=True, min_confidence=min_confidence, limit=limit)
+
+        observations = self.store.list_observations(
+            observation_type=observation_type,
+            min_confidence=min_confidence,
+            limit=max(limit * 4, 20),
+        )
+        if not observations:
+            return []
+
+        if not query:
+            return observations[:limit]
+
+        query_tokens = self._tokenize(query)
+        is_higher_order = bool(query_tokens & _HIGHER_ORDER_CUES)
+        ranked: list[dict[str, Any]] = []
+
+        for item in observations:
+            searchable = " ".join(
+                [
+                    item.get("summary", ""),
+                    item.get("subject", ""),
+                    item.get("observation_type", ""),
+                    " ".join(item.get("metadata", {}).get("labels", [])),
+                ]
+            )
+            overlap = self._overlap_score(query_tokens, self._tokenize(searchable))
+            type_bonus = self._type_bonus(query_tokens, item.get("observation_type", ""))
+            if overlap <= 0 and type_bonus <= 0 and not is_higher_order:
+                continue
+            ranked_item = dict(item)
+            ranked_item["score"] = round(item.get("confidence", 0.0) + overlap + type_bonus, 3)
+            ranked.append(ranked_item)
+
+        if not ranked and is_higher_order:
+            ranked = [
+                {**item, "score": round(float(item.get("confidence", 0.0)), 3)}
+                for item in observations
+            ]
+
+        ranked.sort(
+            key=lambda item: (item.get("score", 0.0), item.get("confidence", 0.0), item.get("evidence_count", 0)),
+            reverse=True,
+        )
+        return ranked[:limit]
+
+    def _build_candidate(
+        self,
+        pattern: dict[str, Any],
+        facts: list[dict[str, Any]],
+        *,
+        min_confidence: float,
+    ) -> dict[str, Any] | None:
+        matched_fact_ids: set[int] = set()
+        matched_labels: dict[str, set[int]] = {label: set() for label in pattern["labels"]}
+
+        for fact in facts:
+            if fact.get("category") not in pattern["categories"]:
+                continue
+            haystack = f"{fact.get('content', '')} {fact.get('tags', '')}".lower()
+            local_match = False
+            for label, keywords in pattern["labels"].items():
+                if any(keyword in haystack for keyword in keywords):
+                    matched_labels[label].add(int(fact["fact_id"]))
+                    local_match = True
+            if local_match:
+                matched_fact_ids.add(int(fact["fact_id"]))
+
+        if len(matched_fact_ids) < 2:
+            return None
+
+        active_labels = sorted(label for label, ids in matched_labels.items() if ids)
+        confidence = min(0.95, 0.35 + 0.12 * len(matched_fact_ids) + 0.08 * len(active_labels))
+        confidence = round(confidence, 3)
+        if confidence < min_confidence:
+            return None
+
+        label_summary = ", ".join(label.replace("_", "-") for label in active_labels)
+        subject_text = pattern["subject"].replace("_", " ")
+        summary = (
+            f"{pattern['summary_prefix']}: {subject_text} trends toward {label_summary} "
+            f"based on {len(matched_fact_ids)} supporting facts."
+        )
+        return {
+            "observation_type": pattern["observation_type"],
+            "subject": pattern["subject"],
+            "summary": summary,
+            "confidence": confidence,
+            "metadata": {
+                "labels": active_labels,
+                "evidence_count": len(matched_fact_ids),
+            },
+            "evidence_fact_ids": sorted(matched_fact_ids),
+        }
+
+    def _expand_evidence(self, fact_ids: list[int]) -> list[dict[str, Any]]:
+        facts_by_id = {
+            fact["fact_id"]: fact
+            for fact in self.store.list_facts(min_trust=0.0, limit=1000)
+        }
+        return [facts_by_id[fact_id] for fact_id in fact_ids if fact_id in facts_by_id]
+
+    @staticmethod
+    def _tokenize(text: str) -> set[str]:
+        return set(_TOKEN_RE.findall(text.lower()))
+
+    @staticmethod
+    def _overlap_score(query_tokens: set[str], text_tokens: set[str]) -> float:
+        if not query_tokens or not text_tokens:
+            return 0.0
+        overlap = query_tokens & text_tokens
+        if not overlap:
+            return 0.0
+        return round(len(overlap) / max(len(query_tokens), 1), 3)
+
+    @staticmethod
+    def _type_bonus(query_tokens: set[str], observation_type: str) -> float:
+        hints = _TYPE_QUERY_HINTS.get(observation_type, set())
+        if not hints:
+            return 0.0
+        return 0.25 if query_tokens & hints else 0.0

plugins/memory/holographic/store.py

@@ -3,6 +3,7 @@ SQLite-backed fact store with entity resolution and trust scoring.
 Single-user Hermes memory store plugin.
 """
 
+import json
 import re
 import sqlite3
 import threading
@@ -73,6 +74,28 @@ CREATE TABLE IF NOT EXISTS memory_banks (
     fact_count INTEGER DEFAULT 0,
     updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
 );
+
+CREATE TABLE IF NOT EXISTS observations (
+    observation_id   INTEGER PRIMARY KEY AUTOINCREMENT,
+    observation_type TEXT NOT NULL,
+    subject          TEXT NOT NULL,
+    summary          TEXT NOT NULL,
+    confidence       REAL DEFAULT 0.0,
+    metadata_json    TEXT DEFAULT '{}',
+    created_at       TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
+    updated_at       TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
+    UNIQUE(observation_type, subject)
+);
+
+CREATE TABLE IF NOT EXISTS observation_evidence (
+    observation_id INTEGER REFERENCES observations(observation_id) ON DELETE CASCADE,
+    fact_id        INTEGER REFERENCES facts(fact_id) ON DELETE CASCADE,
+    evidence_weight REAL DEFAULT 1.0,
+    PRIMARY KEY (observation_id, fact_id)
+);
+
+CREATE INDEX IF NOT EXISTS idx_observations_type ON observations(observation_type);
+CREATE INDEX IF NOT EXISTS idx_observations_confidence ON observations(confidence DESC);
 """
 
 # Trust adjustment constants
@@ -128,6 +151,7 @@ class MemoryStore:
     def _init_db(self) -> None:
         """Create tables, indexes, and triggers if they do not exist. Enable WAL mode."""
         self._conn.execute("PRAGMA journal_mode=WAL")
+        self._conn.execute("PRAGMA foreign_keys=ON")
         self._conn.executescript(_SCHEMA)
         # Migrate: add hrr_vector column if missing (safe for existing databases)
         columns = {row[1] for row in self._conn.execute("PRAGMA table_info(facts)").fetchall()}
@@ -346,6 +370,115 @@ class MemoryStore:
             rows = self._conn.execute(sql, params).fetchall()
             return [self._row_to_dict(r) for r in rows]
 
+    def upsert_observation(
+        self,
+        observation_type: str,
+        subject: str,
+        summary: str,
+        confidence: float,
+        evidence_fact_ids: list[int],
+        metadata: dict | None = None,
+    ) -> int:
+        """Create or update a synthesized observation and its evidence links."""
+        with self._lock:
+            metadata_json = json.dumps(metadata or {}, sort_keys=True)
+            self._conn.execute(
+                """
+                INSERT INTO observations (
+                    observation_type, subject, summary, confidence, metadata_json
+                )
+                VALUES (?, ?, ?, ?, ?)
+                ON CONFLICT(observation_type, subject) DO UPDATE SET
+                    summary = excluded.summary,
+                    confidence = excluded.confidence,
+                    metadata_json = excluded.metadata_json,
+                    updated_at = CURRENT_TIMESTAMP
+                """,
+                (observation_type, subject, summary, confidence, metadata_json),
+            )
+            row = self._conn.execute(
+                """
+                SELECT observation_id
+                FROM observations
+                WHERE observation_type = ? AND subject = ?
+                """,
+                (observation_type, subject),
+            ).fetchone()
+            observation_id = int(row["observation_id"])
+
+            self._conn.execute(
+                "DELETE FROM observation_evidence WHERE observation_id = ?",
+                (observation_id,),
+            )
+            unique_fact_ids = sorted({int(fid) for fid in evidence_fact_ids})
+            if unique_fact_ids:
+                self._conn.executemany(
+                    """
+                    INSERT OR IGNORE INTO observation_evidence (observation_id, fact_id)
+                    VALUES (?, ?)
+                    """,
+                    [(observation_id, fact_id) for fact_id in unique_fact_ids],
+                )
+            self._conn.commit()
+            return observation_id
+
+    def list_observations(
+        self,
+        observation_type: str | None = None,
+        min_confidence: float = 0.0,
+        limit: int = 50,
+    ) -> list[dict]:
+        """List synthesized observations with expanded supporting evidence."""
+        with self._lock:
+            params: list = [min_confidence]
+            observation_clause = ""
+            if observation_type is not None:
+                observation_clause = "AND observation_type = ?"
+                params.append(observation_type)
+            params.append(limit)
+            rows = self._conn.execute(
+                f"""
+                SELECT observation_id, observation_type, subject, summary, confidence,
+                       metadata_json, created_at, updated_at,
+                       (
+                           SELECT COUNT(*)
+                           FROM observation_evidence oe
+                           WHERE oe.observation_id = observations.observation_id
+                       ) AS evidence_count
+                FROM observations
+                WHERE confidence >= ?
+                  {observation_clause}
+                ORDER BY confidence DESC, updated_at DESC
+                LIMIT ?
+                """,
+                params,
+            ).fetchall()
+
+            results = []
+            for row in rows:
+                item = dict(row)
+                try:
+                    item["metadata"] = json.loads(item.pop("metadata_json") or "{}")
+                except json.JSONDecodeError:
+                    item["metadata"] = {}
+                item["evidence"] = self._get_observation_evidence(int(item["observation_id"]))
+                results.append(item)
+            return results
+
+    def _get_observation_evidence(self, observation_id: int) -> list[dict]:
+        rows = self._conn.execute(
+            """
+            SELECT f.fact_id, f.content, f.category, f.tags, f.trust_score,
+                   f.retrieval_count, f.helpful_count, f.created_at, f.updated_at
+            FROM observation_evidence oe
+            JOIN facts f ON f.fact_id = oe.fact_id
+            WHERE oe.observation_id = ?
+            ORDER BY f.trust_score DESC, f.updated_at DESC
+            """,
+            (observation_id,),
+        ).fetchall()
+        return [self._row_to_dict(row) for row in rows]
+
     def record_feedback(self, fact_id: int, helpful: bool) -> dict:
         """Record user feedback and adjust trust asymmetrically.
 

tests/plugins/memory/test_holographic_observations.py

@@ -0,0 +1,96 @@
+import json
+
+import pytest
+
+from plugins.memory.holographic import HolographicMemoryProvider
+from plugins.memory.holographic.store import MemoryStore
+
+
+@pytest.fixture()
+def store(tmp_path):
+    db_path = tmp_path / "memory.db"
+    s = MemoryStore(db_path=str(db_path), default_trust=0.5)
+    yield s
+    s.close()
+
+
+@pytest.fixture()
+def provider(tmp_path):
+    p = HolographicMemoryProvider(
+        config={
+            "db_path": str(tmp_path / "memory.db"),
+            "default_trust": 0.5,
+        }
+    )
+    p.initialize(session_id="test-session")
+    yield p
+    if p._store:
+        p._store.close()
+
+
+class TestObservationSynthesis:
+    def test_observe_action_persists_observation_with_evidence_links(self, provider):
+        fact_ids = [
+            provider._store.add_fact('User prefers concise status updates', category='user_pref'),
+            provider._store.add_fact('User wants result-only replies with no fluff', category='user_pref'),
+        ]
+
+        result = json.loads(
+            provider.handle_tool_call(
+                'fact_store',
+                {
+                    'action': 'observe',
+                    'query': 'What communication style does the user prefer?',
+                    'limit': 5,
+                },
+            )
+        )
+
+        assert result['count'] == 1
+        observation = result['observations'][0]
+        assert observation['observation_type'] == 'recurring_preference'
+        assert observation['confidence'] >= 0.6
+        assert sorted(item['fact_id'] for item in observation['evidence']) == sorted(fact_ids)
+
+        stored = provider._store.list_observations(limit=10)
+        assert len(stored) == 1
+        assert stored[0]['observation_type'] == 'recurring_preference'
+        assert stored[0]['evidence_count'] == 2
+        assert len(provider._store.list_facts(limit=10)) == 2
+
+    def test_observe_action_synthesizes_three_observation_types(self, provider):
+        provider._store.add_fact('User prefers concise updates', category='user_pref')
+        provider._store.add_fact('User wants result-only communication', category='user_pref')
+        provider._store.add_fact('Project is moving to a local-first deployment model', category='project')
+        provider._store.add_fact('Project direction stays Gitea-first for issue and PR flow', category='project')
+        provider._store.add_fact('Operator always commits early before moving on', category='general')
+        provider._store.add_fact('Operator pushes a PR immediately after each meaningful fix', category='general')
+
+        result = json.loads(provider.handle_tool_call('fact_store', {'action': 'observe', 'limit': 10}))
+        types = {item['observation_type'] for item in result['observations']}
+
+        assert {'recurring_preference', 'stable_direction', 'behavioral_pattern'} <= types
+
+    def test_single_fact_does_not_create_overconfident_observation(self, provider):
+        provider._store.add_fact('User prefers concise updates', category='user_pref')
+
+        result = json.loads(
+            provider.handle_tool_call(
+                'fact_store',
+                {'action': 'observe', 'query': 'What does the user prefer?', 'limit': 5},
+            )
+        )
+
+        assert result['count'] == 0
+        assert provider._store.list_observations(limit=10) == []
+
+    def test_prefetch_surfaces_observations_as_separate_layer(self, provider):
+        provider._store.add_fact('User prefers concise updates', category='user_pref')
+        provider._store.add_fact('User wants result-only communication', category='user_pref')
+
+        prefetch = provider.prefetch('What communication style does the user prefer?')
+
+        assert '## Holographic Observations' in prefetch
+        assert '## Holographic Memory' in prefetch
+        assert 'recurring_preference' in prefetch
+        assert 'evidence' in prefetch.lower()

tests/tools/test_tts_kittentts.py

@@ -1,236 +0,0 @@
-"""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/tts_tool.py

@@ -2,14 +2,13 @@
 """
 Text-to-Speech Tool Module
 
-Supports seven TTS providers:
+Supports six 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)
@@ -78,12 +77,6 @@ def _import_sounddevice():
     return sd
 
 
-def _import_kittentts():
-    """Lazy import KittenTTS. Returns the class or raises ImportError."""
-    from kittentts import KittenTTS
-    return KittenTTS
-
-
 # ===========================================================================
 # Defaults
 # ===========================================================================
@@ -93,8 +86,6 @@ 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"
@@ -457,15 +448,6 @@ 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")
@@ -529,51 +511,6 @@ 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
 # ===========================================================================
@@ -685,19 +622,6 @@ 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
@@ -734,10 +658,10 @@ def text_to_speech_tool(
                 "error": f"TTS generation produced no output (provider: {provider})"
             }, ensure_ascii=False)
 
-        # Try Opus conversion for Telegram compatibility only.
-        # Outside Telegram, preserve the caller's explicit output format.
+        # Try Opus conversion for Telegram compatibility
+        # Edge TTS outputs MP3, NeuTTS outputs WAV — both need ffmpeg conversion
         voice_compatible = False
-        if want_opus and provider in ("edge", "neutts", "minimax", "kittentts") and not file_str.endswith(".ogg"):
+        if provider in ("edge", "neutts", "minimax") and not file_str.endswith(".ogg"):
             opus_path = _convert_to_opus(file_str)
             if opus_path:
                 file_str = opus_path
@@ -818,8 +742,6 @@ 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 seven providers:
+Convert text to speech with six providers:
 
 | Provider | Quality | Cost | API Key |
 |----------|---------|------|---------|
@@ -20,7 +20,6 @@ Convert text to speech with seven 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
 
@@ -36,7 +35,7 @@ Convert text to speech with seven providers:
 ```yaml
 # In ~/.hermes/config.yaml
 tts:
-  provider: "edge"              # "edge" | "elevenlabs" | "openai" | "minimax" | "mistral" | "neutts" | "kittentts"
+  provider: "edge"              # "edge" | "elevenlabs" | "openai" | "minimax" | "mistral" | "neutts"
   speed: 1.0                    # Global speed multiplier (provider-specific settings override this)
   edge:
     voice: "en-US-AriaNeural"   # 322 voices, 74 languages
@@ -63,11 +62,6 @@ 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).
@@ -80,7 +74,6 @@ 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
@@ -93,7 +86,7 @@ brew install ffmpeg
 sudo dnf install ffmpeg
 ```
 
-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).
+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).
 
 :::tip
 If you want voice bubbles without installing ffmpeg, switch to the OpenAI, ElevenLabs, or Mistral provider.