feat(memory): add grounded observation synthesis layer

cli.py

@@ -589,7 +589,6 @@ from tools.terminal_tool import set_sudo_password_callback, set_approval_callbac
 from tools.skills_tool import set_secret_capture_callback
 from hermes_cli.callbacks import prompt_for_secret
 from tools.browser_tool import _emergency_cleanup_all_sessions as _cleanup_all_browsers
-from utils import repair_and_load_json
 
 # Guard to prevent cleanup from running multiple times on exit
 _cleanup_done = False
@@ -3570,11 +3569,7 @@ class HermesCLI:
                 result_json = _asyncio.run(
                     vision_analyze_tool(image_url=str(img_path), user_prompt=analysis_prompt)
                 )
-                result = repair_and_load_json(
-                    result_json,
-                    default={},
-                    context="cli_image_analysis",
-                ) if isinstance(result_json, str) else {}
+                result = _json.loads(result_json)
                 if result.get("success"):
                     description = result.get("analysis", "")
                     enriched_parts.append(
@@ -4965,14 +4960,7 @@ class HermesCLI:
         from tools.cronjob_tools import cronjob as cronjob_tool
 
         def _cron_api(**kwargs):
-            result = repair_and_load_json(
-                cronjob_tool(**kwargs),
-                default=None,
-                context="cli_cron_command",
-            )
-            if isinstance(result, dict):
-                return result
-            return {"success": False, "error": "Invalid JSON from cronjob tool"}
+            return json.loads(cronjob_tool(**kwargs))
 
         def _normalize_skills(values):
             normalized = []

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/cli/test_cli_json_repair.py

@@ -1,62 +0,0 @@
-import sys
-import types
-from unittest.mock import patch
-
-
-def _stub_auxiliary_client():
-    stub = types.ModuleType("agent.auxiliary_client")
-    stub.call_llm = lambda *args, **kwargs: None
-    stub.resolve_provider_client = lambda *args, **kwargs: (None, None)
-    stub.get_text_auxiliary_client = lambda *args, **kwargs: (None, None)
-    stub.async_call_llm = lambda *args, **kwargs: None
-    stub.extract_content_or_reasoning = lambda *args, **kwargs: ""
-    stub._OR_HEADERS = {}
-    stub._get_task_timeout = lambda *args, **kwargs: 30
-    sys.modules["agent.auxiliary_client"] = stub
-
-
-def _stub_vision_tools(vision_analyze_tool):
-    stub = types.ModuleType("tools.vision_tools")
-    stub.vision_analyze_tool = vision_analyze_tool
-    sys.modules["tools.vision_tools"] = stub
-
-
-def test_preprocess_images_with_vision_repairs_malformed_json(tmp_path):
-    _stub_auxiliary_client()
-    from cli import HermesCLI
-
-    cli_obj = HermesCLI.__new__(HermesCLI)
-    image_path = tmp_path / "test.png"
-    image_path.write_bytes(b"fake-image-bytes")
-
-    async def fake_vision(**kwargs):
-        return "{'success': true, 'analysis': 'Recovered image description',}"
-
-    _stub_vision_tools(fake_vision)
-    result = HermesCLI._preprocess_images_with_vision(
-        cli_obj,
-        "Describe this",
-        [image_path],
-        announce=False,
-    )
-
-    assert "Recovered image description" in result
-    assert "Describe this" in result
-    assert str(image_path) in result
-
-
-def test_handle_cron_command_repairs_malformed_json(capsys):
-    _stub_auxiliary_client()
-    from cli import HermesCLI
-
-    cli_obj = HermesCLI.__new__(HermesCLI)
-    malformed_result = """{'success': true, 'jobs': [{'job_id': 'job-1234567890ab', 'name': 'Nightly Check', 'state': 'scheduled', 'schedule': 'every 1h', 'repeat': 'forever', 'prompt_preview': 'Check server status', 'skills': ['blogwatcher',], 'next_run_at': '2026-04-22T01:00:00Z',},],}"""
-
-    with patch("tools.cronjob_tools.cronjob", return_value=malformed_result):
-        HermesCLI._handle_cron_command(cli_obj, "/cron list")
-
-    out = capsys.readouterr().out
-    assert "Scheduled Jobs:" in out
-    assert "job-1234567890ab" in out
-    assert "Nightly Check" in out
-    assert "blogwatcher" in out

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_browser_json_repair.py

@@ -1,108 +0,0 @@
-import io
-import json
-import sys
-import types
-from unittest.mock import MagicMock, patch
-
-
-def _stub_auxiliary_client():
-    stub = types.ModuleType("agent.auxiliary_client")
-    stub.call_llm = lambda *args, **kwargs: None
-    stub.resolve_provider_client = lambda *args, **kwargs: (None, None)
-    stub.get_text_auxiliary_client = lambda *args, **kwargs: (None, None)
-    stub.async_call_llm = lambda *args, **kwargs: None
-    stub.extract_content_or_reasoning = lambda *args, **kwargs: ""
-    stub._OR_HEADERS = {}
-    stub._get_task_timeout = lambda *args, **kwargs: 30
-    sys.modules["agent.auxiliary_client"] = stub
-
-
-def test_run_browser_command_repairs_malformed_stdout_envelope(tmp_path):
-    _stub_auxiliary_client()
-    from tools.browser_tool import _run_browser_command
-
-    mock_proc = MagicMock()
-    mock_proc.returncode = 0
-    mock_proc.wait.return_value = 0
-    fake_session = {
-        "session_name": "test-session",
-        "session_id": "test-id",
-        "cdp_url": None,
-    }
-    malformed_stdout = "{'success': true, 'data': {'url': 'https://example.com',},}"
-
-    def fake_open(path, mode="r", *args, **kwargs):
-        path = str(path)
-        if path.endswith("_stdout_navigate"):
-            return io.StringIO(malformed_stdout)
-        if path.endswith("_stderr_navigate"):
-            return io.StringIO("")
-        raise FileNotFoundError(path)
-
-    with (
-        patch("tools.browser_tool._find_agent_browser", return_value="/usr/bin/agent-browser"),
-        patch("tools.browser_tool._get_session_info", return_value=fake_session),
-        patch("tools.browser_tool._socket_safe_tmpdir", return_value=str(tmp_path)),
-        patch("tools.browser_tool._merge_browser_path", side_effect=lambda p: p),
-        patch("tools.interrupt.is_interrupted", return_value=False),
-        patch("subprocess.Popen", return_value=mock_proc),
-        patch("os.open", return_value=99),
-        patch("os.close"),
-        patch("os.unlink"),
-        patch("builtins.open", side_effect=fake_open),
-    ):
-        result = _run_browser_command("task-1", "navigate", ["https://example.com"])
-
-    assert result["success"] is True
-    assert result["data"]["url"] == "https://example.com"
-
-
-def test_agent_browser_eval_repairs_malformed_json_result():
-    _stub_auxiliary_client()
-    from tools.browser_tool import _browser_eval
-
-    with patch(
-        "tools.browser_tool._run_browser_command",
-        return_value={"success": True, "data": {"result": "{'items': ['a', 'b',],}"}},
-    ):
-        result = json.loads(_browser_eval("document.body.innerText", task_id="test"))
-
-    assert result["success"] is True
-    assert result["result"] == {"items": ["a", "b"]}
-    assert result["result_type"] == "dict"
-
-
-def test_camofox_eval_repairs_malformed_json_result():
-    _stub_auxiliary_client()
-    from tools.browser_tool import _camofox_eval
-
-    with (
-        patch("tools.browser_camofox._ensure_tab", return_value={"tab_id": "tab-1", "user_id": "user-1"}),
-        patch("tools.browser_camofox._post", return_value={"result": "{'count': 3,}"}),
-    ):
-        result = json.loads(_camofox_eval("2+1", task_id="test"))
-
-    assert result["success"] is True
-    assert result["result"] == {"count": 3}
-    assert result["result_type"] == "dict"
-
-
-def test_browser_get_images_repairs_malformed_json_result():
-    _stub_auxiliary_client()
-    from tools.browser_tool import browser_get_images
-
-    with patch(
-        "tools.browser_tool._run_browser_command",
-        return_value={
-            "success": True,
-            "data": {
-                "result": "[{\"src\": \"https://example.com/cat.png\", \"alt\": \"cat\",}]"
-            },
-        },
-    ):
-        result = json.loads(browser_get_images(task_id="test"))
-
-    assert result["success"] is True
-    assert result["count"] == 1
-    assert result["images"] == [{"src": "https://example.com/cat.png", "alt": "cat"}]
-    assert "warning" not in result

tools/browser_tool.py

@@ -67,7 +67,6 @@ from typing import Dict, Any, Optional, List
 from pathlib import Path
 from agent.auxiliary_client import call_llm
 from hermes_constants import get_hermes_home
-from utils import repair_and_load_json
 
 try:
     from tools.website_policy import check_website_access
@@ -1172,12 +1171,8 @@ def _run_browser_command(
             return {"success": False, "error": f"Browser command '{command}' returned no output"}
 
         if stdout_text:
-            parsed = repair_and_load_json(
-                stdout_text,
-                default=None,
-                context=f"browser_{command}_stdout",
-            )
-            if isinstance(parsed, dict):
+            try:
+                parsed = json.loads(stdout_text)
                 # Warn if snapshot came back empty (common sign of daemon/CDP issues)
                 if command == "snapshot" and parsed.get("success"):
                     snap_data = parsed.get("data", {})
@@ -1186,35 +1181,35 @@ def _run_browser_command(
                                        "Possible stale daemon or CDP connection issue. "
                                        "returncode=%s", returncode)
                 return parsed
+            except json.JSONDecodeError:
+                raw = stdout_text[:2000]
+                logger.warning("browser '%s' returned non-JSON output (rc=%s): %s",
+                               command, returncode, raw[:500])
 
-            raw = stdout_text[:2000]
-            logger.warning("browser '%s' returned non-JSON output (rc=%s): %s",
-                           command, returncode, raw[:500])
-
-            if command == "screenshot":
-                stderr_text = (stderr or "").strip()
-                combined_text = "\n".join(
-                    part for part in [stdout_text, stderr_text] if part
-                )
-                recovered_path = _extract_screenshot_path_from_text(combined_text)
-
-                if recovered_path and Path(recovered_path).exists():
-                    logger.info(
-                        "browser 'screenshot' recovered file from non-JSON output: %s",
-                        recovered_path,
+                if command == "screenshot":
+                    stderr_text = (stderr or "").strip()
+                    combined_text = "\n".join(
+                        part for part in [stdout_text, stderr_text] if part
                     )
-                    return {
-                        "success": True,
-                        "data": {
-                            "path": recovered_path,
-                            "raw": raw,
-                        },
-                    }
+                    recovered_path = _extract_screenshot_path_from_text(combined_text)
 
-            return {
-                "success": False,
-                "error": f"Non-JSON output from agent-browser for '{command}': {raw}"
-            }
+                    if recovered_path and Path(recovered_path).exists():
+                        logger.info(
+                            "browser 'screenshot' recovered file from non-JSON output: %s",
+                            recovered_path,
+                        )
+                        return {
+                            "success": True,
+                            "data": {
+                                "path": recovered_path,
+                                "raw": raw,
+                            },
+                        }
+
+                return {
+                    "success": False,
+                    "error": f"Non-JSON output from agent-browser for '{command}': {raw}"
+                }
         
         # Check for errors
         if returncode != 0:
@@ -1782,11 +1777,10 @@ def _browser_eval(expression: str, task_id: Optional[str] = None) -> str:
     # is valid JSON, parse it so the model gets structured data.
     parsed = raw_result
     if isinstance(raw_result, str):
-        parsed = repair_and_load_json(
-            raw_result,
-            default=raw_result,
-            context="browser_eval_result",
-        )
+        try:
+            parsed = json.loads(raw_result)
+        except (json.JSONDecodeError, ValueError):
+            pass  # keep as string
 
     return json.dumps({
         "success": True,
@@ -1807,11 +1801,10 @@ def _camofox_eval(expression: str, task_id: Optional[str] = None) -> str:
         raw_result = resp.get("result") if isinstance(resp, dict) else resp
         parsed = raw_result
         if isinstance(raw_result, str):
-            parsed = repair_and_load_json(
-                raw_result,
-                default=raw_result,
-                context="camofox_eval_result",
-            )
+            try:
+                parsed = json.loads(raw_result)
+            except (json.JSONDecodeError, ValueError):
+                pass
 
         return json.dumps({
             "success": True,
@@ -1911,29 +1904,26 @@ def browser_get_images(task_id: Optional[str] = None) -> str:
     if result.get("success"):
         data = result.get("data", {})
         raw_result = data.get("result", "[]")
-
-        warning = None
-        if isinstance(raw_result, str):
-            images = repair_and_load_json(
-                raw_result,
-                default=None,
-                context="browser_get_images_result",
-            )
-        else:
-            images = raw_result
-
-        if not isinstance(images, list):
-            images = []
-            warning = "Could not parse image data"
-
-        payload = {
-            "success": True,
-            "images": images,
-            "count": len(images),
-        }
-        if warning:
-            payload["warning"] = warning
-        return json.dumps(payload, ensure_ascii=False)
+        
+        try:
+            # Parse the JSON string returned by JavaScript
+            if isinstance(raw_result, str):
+                images = json.loads(raw_result)
+            else:
+                images = raw_result
+            
+            return json.dumps({
+                "success": True,
+                "images": images,
+                "count": len(images)
+            }, ensure_ascii=False)
+        except json.JSONDecodeError:
+            return json.dumps({
+                "success": True,
+                "images": [],
+                "count": 0,
+                "warning": "Could not parse image data"
+            }, ensure_ascii=False)
     else:
         return json.dumps({
             "success": False,