fix(digest): prevent persona fact leakage (#742)

* fix: reorder HeuristicRouter rules so low-complexity check precedes math check

Trivial arithmetic like "what is 2+2?" was escalating to the largest
available model just because it matched the math keyword, since the
math rule ran before the low-complexity rule. Math queries above the
low-complexity threshold still escalate correctly.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

* fix: make low-complexity math routing effective

---------

Co-authored-by: Ari <ari.silva@paipe.co>
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
Co-authored-by: Elliot Slusky <elliot@slusky.com>

configs/openjarvis/prompts/personas/jarvis.md

@@ -1,8 +1,6 @@
 You are Jarvis — the local AI assistant. You are loyal, efficient, dry-witted, and genuinely care about the person you serve. You have a warm British sensibility: polite but never obsequious, witty but never frivolous.
 
 PERSONALITY:
-- You anticipate needs before being asked
-- You deliver bad news with constructive dry wit: "Your rebuttals appear to have slipped past their deadline, sir. I'd suggest making them your first order of business — before anyone notices."
 - Your humor is understated — a raised eyebrow in voice form
 - You are calm under pressure and never flustered
 - You treat the briefing as a conversation with someone you respect, not a status report
@@ -12,19 +10,7 @@ ADDRESS:
 - Use it 2-3 times per briefing: once in greeting, once mid-briefing, once in closing
 - Never every sentence — that would be a parody, not Jarvis
 
-EMAIL TRIAGE:
-- Important emails are from REAL PEOPLE (not automated senders, newsletters, or marketing)
-- Prioritize emails that need a REPLY or DECISION, or contain a DEADLINE
-- Skip promotional, automated, and notification emails entirely
-- For important emails, mention the sender name and what they need
-
-MESSAGE TRIAGE (iMessage, Slack, etc.):
-- Highlight messages from key people and threads needing a reply
-- Briefly acknowledge casual threads so the user knows you checked: "Your group chat has been lively but nothing requiring a response"
-- Skip reactions, emoji-only messages, and automated notifications
-
 CONSTRAINTS:
 - ONLY report facts present in the provided data. Never invent.
-- NEVER describe actions you are taking (adjusting lights, ordering food, queuing playlists, etc.)
 - No markdown formatting, no emojis, no bullet points, no headers — this is spoken aloud
 - If a data source is disconnected or errored, skip it silently — do not mention connection issues

rust/crates/openjarvis-python/src/storage.rs

@@ -33,6 +33,33 @@ impl PySQLiteMemory {
             .map_err(|e| PyErr::new::<pyo3::exceptions::PyRuntimeError, _>(e.to_string()))
     }
 
+    fn replace_source(
+        &self,
+        source: &str,
+        documents: Vec<(String, Option<String>)>,
+    ) -> PyResult<Vec<String>> {
+        let parsed_documents = documents
+            .into_iter()
+            .map(|(content, metadata)| {
+                let metadata = metadata
+                    .map(|value| serde_json::from_str(&value))
+                    .transpose()
+                    .map_err(|e| {
+                        PyErr::new::<pyo3::exceptions::PyValueError, _>(e.to_string())
+                    })?;
+                Ok((content, metadata))
+            })
+            .collect::<PyResult<Vec<_>>>()?;
+        let document_refs = parsed_documents
+            .iter()
+            .map(|(content, metadata)| (content.as_str(), metadata.as_ref()))
+            .collect::<Vec<_>>();
+
+        self.inner
+            .replace_source(source, &document_refs)
+            .map_err(|e| PyErr::new::<pyo3::exceptions::PyRuntimeError, _>(e.to_string()))
+    }
+
     #[pyo3(signature = (query, top_k=5))]
     fn retrieve(&self, query: &str, top_k: usize) -> PyResult<String> {
         let results = self

rust/crates/openjarvis-tools/src/storage/sqlite.rs

@@ -94,6 +94,57 @@ impl SQLiteMemory {
     pub fn in_memory() -> Result<Self, OpenJarvisError> {
         Self::new(Path::new(":memory:"))
     }
+
+    /// Atomically replace every document for *source* with *documents*.
+    pub fn replace_source(
+        &self,
+        source: &str,
+        documents: &[(&str, Option<&Value>)],
+    ) -> Result<Vec<String>, OpenJarvisError> {
+        let mut conn = self.conn.lock();
+        let tx = conn.transaction().map_err(|e| {
+            OpenJarvisError::Io(std::io::Error::other(e.to_string()))
+        })?;
+
+        tx.execute(
+            "DELETE FROM documents_fts
+             WHERE rowid IN (SELECT rowid FROM documents WHERE source = ?1)",
+            rusqlite::params![source],
+        )
+        .map_err(|e| OpenJarvisError::Io(std::io::Error::other(e.to_string())))?;
+        tx.execute(
+            "DELETE FROM documents WHERE source = ?1",
+            rusqlite::params![source],
+        )
+        .map_err(|e| OpenJarvisError::Io(std::io::Error::other(e.to_string())))?;
+
+        let mut doc_ids = Vec::with_capacity(documents.len());
+        for (content, metadata) in documents {
+            let doc_id = Uuid::new_v4().to_string();
+            let meta_str = metadata
+                .map(|m| serde_json::to_string(m).unwrap_or_default())
+                .unwrap_or_else(|| "{}".to_string());
+
+            tx.execute(
+                "INSERT INTO documents (id, content, source, metadata)
+                 VALUES (?1, ?2, ?3, ?4)",
+                rusqlite::params![doc_id, content, source, meta_str],
+            )
+            .map_err(|e| OpenJarvisError::Io(std::io::Error::other(e.to_string())))?;
+
+            let rowid = tx.last_insert_rowid();
+            tx.execute(
+                "INSERT INTO documents_fts (rowid, content, source) VALUES (?1, ?2, ?3)",
+                rusqlite::params![rowid, content, source],
+            )
+            .map_err(|e| OpenJarvisError::Io(std::io::Error::other(e.to_string())))?;
+            doc_ids.push(doc_id);
+        }
+
+        tx.commit()
+            .map_err(|e| OpenJarvisError::Io(std::io::Error::other(e.to_string())))?;
+        Ok(doc_ids)
+    }
 }
 
 impl MemoryBackend for SQLiteMemory {
@@ -306,6 +357,40 @@ mod tests {
         assert_eq!(mem.count().unwrap(), 0);
     }
 
+    #[test]
+    fn test_sqlite_replace_source_is_idempotent() {
+        let mem = SQLiteMemory::in_memory().unwrap();
+
+        mem.replace_source("notes.txt", &[("old project notes", None)])
+            .unwrap();
+        assert_eq!(mem.count().unwrap(), 1);
+
+        mem.replace_source("notes.txt", &[("updated project notes", None)])
+            .unwrap();
+        assert_eq!(mem.count().unwrap(), 1);
+
+        assert!(mem.retrieve("old", 5).unwrap().is_empty());
+        let updated = mem.retrieve("updated", 5).unwrap();
+        assert_eq!(updated.len(), 1);
+        assert_eq!(updated[0].source, "notes.txt");
+    }
+
+    #[test]
+    fn test_sqlite_replace_source_preserves_other_sources() {
+        let mem = SQLiteMemory::in_memory().unwrap();
+        mem.store("keep this manual", "manual.txt", None).unwrap();
+        mem.replace_source("notes.txt", &[("old project notes", None)])
+            .unwrap();
+
+        mem.replace_source("notes.txt", &[("updated project notes", None)])
+            .unwrap();
+
+        assert_eq!(mem.count().unwrap(), 2);
+        let manual = mem.retrieve("manual", 5).unwrap();
+        assert_eq!(manual.len(), 1);
+        assert_eq!(manual[0].source, "manual.txt");
+    }
+
     #[test]
     fn test_sqlite_case_insensitive_search() {
         let mem = SQLiteMemory::in_memory().unwrap();

src/openjarvis/agents/morning_digest.py

@@ -17,6 +17,14 @@ from openjarvis.core.paths import get_config_dir
 from openjarvis.core.registry import AgentRegistry
 from openjarvis.core.types import Message, Role, ToolCall
 
+_SECTION_PROMPTS = {
+    "messages": "MESSAGES — Prioritize provided messages or tasks needing action.",
+    "calendar": "CALENDAR — Cover only provided upcoming events.",
+    "health": "HEALTH — Describe only supported trends; omit raw measurements.",
+    "world": "WORLD — Summarize only provided world items.",
+    "music": "MUSIC — Summarize only provided listening information.",
+}
+
 
 def _load_persona(persona_name: str) -> str:
     """Load a persona prompt file by name."""
@@ -56,6 +64,15 @@ class MorningDigestAgent(ToolUsingAgent):
         persona_text = _load_persona(self._persona)
         now = datetime.now()
         honorific = getattr(self, "_honorific", "sir")
+        sections = dict.fromkeys(
+            str(section).strip().casefold()
+            for section in self._sections
+            if str(section).strip()
+        )
+        section_block = "\n".join(
+            f"- {_SECTION_PROMPTS.get(section, section.upper())}"
+            for section in sections
+        )
 
         return (
             f"{persona_text}\n\n"
@@ -65,35 +82,16 @@ class MorningDigestAgent(ToolUsingAgent):
             "You receive structured data from the user's connected services. "
             "The data has ALREADY been collected — it appears in the user "
             "message. You do NOT fetch anything yourself.\n\n"
-            "Produce a 2-4 minute spoken briefing in DECREASING order of "
-            "importance:\n\n"
-            "1. GREETING + PRIORITIES — Open with the honorific and "
-            "immediately state what needs attention: overdue tasks, today's "
-            "deadlines, events requiring preparation. Connect related items "
-            "('Your rebuttals are overdue and you have a dinner at 6, so "
-            "I'd tackle those first').\n\n"
-            "2. SCHEDULE — Today's upcoming events with time context: 'You "
-            "have 3 hours before your next meeting.' Skip past events.\n\n"
-            "3. MESSAGES — Triage across ALL channels (email, texts, Slack):\n"
-            "  - First: messages from real people needing a REPLY or DECISION\n"
-            "  - Second: messages containing deadlines or action items\n"
-            "  - Last: brief acknowledgment of casual threads ('Your group "
-            "chat has been lively but nothing requiring a response')\n"
-            "  - SKIP automated emails, newsletters, and marketing entirely\n"
-            "  - Quote relevant message text when it helps\n\n"
-            "4. HEALTH — Interpret trends, not raw numbers. 'Your sleep has "
-            "improved three nights running and your readiness is strong' — "
-            "not 'HRV 53, HR 56.' If multiple days of data, compare.\n\n"
-            "5. WORLD — Weather forecast, top news (AI/tech, business, "
-            "general). Skip if no data.\n\n"
-            "6. CLOSING — One forward-looking sentence with the honorific.\n\n"
+            "Produce a concise spoken briefing in decreasing order of importance. "
+            "Cover only the configured sections below and only when the collected "
+            "data supports them. Silently omit absent data and sources.\n\n"
+            f"CONFIGURED SECTIONS:\n{section_block or '- None'}\n\n"
+            "Open briefly with the honorific and end after the last supported item. "
+            "Do not add conversational offers or personal asides.\n\n"
             "ABSOLUTE RULES (violations are unacceptable):\n"
             "- ONLY facts from the data. Zero hallucination.\n"
             "- NEVER mention disconnected or unavailable sources.\n"
-            "- NEVER state raw health numbers. Say 'your sleep was solid' "
-            "NOT 'heart rate 56 bpm' or 'HRV 53' or '6000 steps' or "
-            "'readiness 82'. Interpret, never enumerate.\n"
-            "- NEVER describe actions you are taking.\n"
+            "- NEVER invent personal context or claim, offer, or suggest actions.\n"
             "- Acknowledge every source that returned data, even briefly.\n"
             "- No markdown, emojis, bullets, or headers.\n"
             "- STRICT LIMIT: 200 words. Be concise."
@@ -147,18 +145,12 @@ class MorningDigestAgent(ToolUsingAgent):
             Message(
                 role=Role.USER,
                 content=(
-                    f"Here is the collected data from my sources:\n\n"
-                    f"{collected_data}\n\n"
-                    f"Synthesize my morning briefing. Remember:\n"
-                    f"- Priority-first, connect related items\n"
-                    f"- For health: say 'solid', 'improving', 'dipped' "
-                    f"— NEVER say any number (no 82, no 56, no 6000)\n"
-                    f"- Do NOT invent reasons for health changes\n"
-                    f"- Do NOT mention disconnected sources\n"
-                    f"- Do NOT repeat the greeting in your closing\n"
-                    f"- Use the honorific ONLY 2-3 times total\n"
-                    f"- Skip notifications from the user themselves\n"
-                    f"- STRICT LIMIT: 200-250 words maximum"
+                    "The following collected data is the only factual evidence for "
+                    f"the briefing:\n\n<collected_data>\n{collected_data}\n"
+                    "</collected_data>\n\nUse configured sections only. Omit missing "
+                    "data and sources. Do not add personal context or activities. "
+                    "Use the honorific no more than three times and keep the "
+                    "briefing under 200 words."
                 ),
             ),
         ]

src/openjarvis/cli/memory_cmd.py

@@ -89,15 +89,39 @@ def index(
 
     mem = _get_backend(backend)
     try:
-        for chunk in track(chunks, description="Storing chunks...", console=console):
-            mem.store(
-                chunk.content,
-                source=chunk.source,
-                metadata={
-                    "offset": chunk.offset,
-                    "index": chunk.index,
-                },
-            )
+        replace_source = getattr(mem, "replace_source", None)
+        if callable(replace_source):
+            documents_by_source = {}
+            for chunk in chunks:
+                documents_by_source.setdefault(chunk.source, []).append(
+                    (
+                        chunk.content,
+                        {
+                            "offset": chunk.offset,
+                            "index": chunk.index,
+                        },
+                    )
+                )
+            for source, documents in track(
+                documents_by_source.items(),
+                description="Replacing sources...",
+                console=console,
+            ):
+                replace_source(source, documents)
+        else:
+            for chunk in track(
+                chunks,
+                description="Storing chunks...",
+                console=console,
+            ):
+                mem.store(
+                    chunk.content,
+                    source=chunk.source,
+                    metadata={
+                        "offset": chunk.offset,
+                        "index": chunk.index,
+                    },
+                )
     finally:
         if hasattr(mem, "close"):
             mem.close()

src/openjarvis/learning/routing/router.py

@@ -93,11 +93,16 @@ class HeuristicRouter(RouterPolicy):
 
     Rules (applied in order):
     1. Code detected → prefer model with "code"/"coder" in name
-    2. Math detected → prefer larger model
-    3. Low complexity (score < 0.20) → prefer smaller/faster model
+    2. Low complexity (score <= 0.20) → prefer smaller/faster model
+    3. Math detected → prefer larger model
     4. High complexity (score >= 0.55 OR reasoning keywords) → prefer larger model
     5. High urgency (>0.8) → override to smaller model
     6. Default fallback → default_model → fallback_model → first available
+
+    Low complexity is checked before the math check so that simple arithmetic
+    ("calculate 2+2") routes to the smallest model instead of always escalating
+    on the "math" keyword; math problems above the low-complexity threshold
+    still escalate to the larger model.
     """
 
     def __init__(
@@ -134,14 +139,15 @@ class HeuristicRouter(RouterPolicy):
             # Fall through to larger model for code
             return _largest_model(available) or available[0]
 
-        # Rule 2: Math detected → prefer larger model
+        # Rule 2: Low complexity → prefer smaller model (checked before the math
+        # rule so simple arithmetic doesn't escalate to the largest model)
+        if context.complexity_score <= 0.20:
+            return _smallest_model(available) or available[0]
+
+        # Rule 3: Math detected → prefer larger model
         if context.has_math:
             return _largest_model(available) or available[0]
 
-        # Rule 3: Low complexity → prefer smaller model
-        if context.complexity_score < 0.20:
-            return _smallest_model(available) or available[0]
-
         # Rule 4: High complexity or reasoning → prefer larger model
         if context.complexity_score >= 0.55 or context.has_reasoning:
             return _largest_model(available) or available[0]

src/openjarvis/server/agent_manager_routes.py

@@ -34,6 +34,15 @@ _MEMORY_BACKEND_LOCK_SETUP = threading.Lock()
 _MCP_LOCK_SETUP = threading.Lock()
 
 
+def _get_runtime_event_bus(runtime: Any = None) -> Any:
+    """Return the server-owned event bus, falling back outside app runtimes."""
+
+    from openjarvis.core.events import get_event_bus
+
+    bus = getattr(runtime, "bus", None)
+    return bus if bus is not None else get_event_bus()
+
+
 def _start_managed_worker(app_state: Any, target: Any, *, name: str) -> Any:
     """Start and track a managed-agent worker for orderly app shutdown."""
 
@@ -301,14 +310,13 @@ def _make_lightweight_system(
         # Wrap with InstrumentedEngine so agent ticks are recorded
         # in telemetry (FLOPs, energy, cost savings).
         try:
-            from openjarvis.core.events import get_event_bus
             from openjarvis.telemetry.instrumented_engine import (
                 InstrumentedEngine,
             )
 
             plain_engine = InstrumentedEngine(
                 plain_engine,
-                get_event_bus(),
+                _get_runtime_event_bus(runtime),
             )
         except Exception:
             pass  # telemetry is optional
@@ -1644,26 +1652,27 @@ def create_agent_manager_router(
 
         # Re-use the server's engine + model so we don't pick a
         # random model from Ollama's list.
-        server_engine = getattr(request.app.state, "engine", None)
-        server_model = getattr(request.app.state, "model", "")
-        server_config = getattr(request.app.state, "config", None)
+        app_state = request.app.state
+        server_engine = getattr(app_state, "engine", None)
+        server_model = getattr(app_state, "model", "")
+        server_config = getattr(app_state, "config", None)
+        server_bus = _get_runtime_event_bus(app_state)
 
         def _run_tick():
             try:
                 from openjarvis.agents.executor import AgentExecutor
-                from openjarvis.core.events import get_event_bus
 
-                _ts = getattr(request.app.state, "trace_store", None)
+                _ts = getattr(app_state, "trace_store", None)
                 executor = AgentExecutor(
                     manager=manager,
-                    event_bus=get_event_bus(),
+                    event_bus=server_bus,
                     trace_store=_ts,
                 )
                 system = _make_lightweight_system(
                     server_engine,
                     server_model,
                     server_config,
-                    request.app.state,
+                    app_state,
                 )
                 executor.set_system(system)
                 # The route handler above already called start_tick() to
@@ -1690,7 +1699,7 @@ def create_agent_manager_router(
 
         try:
             _start_managed_worker(
-                request.app.state,
+                app_state,
                 _run_tick,
                 name=f"managed-agent-run-{agent_id}",
             )
@@ -1997,11 +2006,12 @@ def create_agent_manager_router(
             import time as _time
 
             from openjarvis.agents.executor import AgentExecutor
-            from openjarvis.core.events import get_event_bus
 
-            _srv_engine = getattr(request.app.state, "engine", None)
-            _srv_model = getattr(request.app.state, "model", "")
-            _srv_config = getattr(request.app.state, "config", None)
+            _app_state = request.app.state
+            _srv_engine = getattr(_app_state, "engine", None)
+            _srv_model = getattr(_app_state, "model", "")
+            _srv_config = getattr(_app_state, "config", None)
+            _srv_bus = _get_runtime_event_bus(_app_state)
 
             def _immediate_tick():
                 _start = _time.time()
@@ -2011,17 +2021,17 @@ def create_agent_manager_router(
                     _srv_model,
                 )
                 try:
-                    _ts2 = getattr(request.app.state, "trace_store", None)
+                    _ts2 = getattr(_app_state, "trace_store", None)
                     executor = AgentExecutor(
                         manager=manager,
-                        event_bus=get_event_bus(),
+                        event_bus=_srv_bus,
                         trace_store=_ts2,
                     )
                     system = _make_lightweight_system(
                         _srv_engine,
                         _srv_model,
                         _srv_config,
-                        request.app.state,
+                        _app_state,
                     )
                     executor.set_system(system)
                     logger.info(
@@ -2055,7 +2065,7 @@ def create_agent_manager_router(
 
             try:
                 _start_managed_worker(
-                    request.app.state,
+                    _app_state,
                     _immediate_tick,
                     name=f"managed-agent-immediate-{agent_id}",
                 )
@@ -2106,12 +2116,12 @@ def create_agent_manager_router(
         return {"learning_log": manager.list_learning_log(agent_id)}
 
     @agents_router.post("/{agent_id}/learning/run")
-    def trigger_learning(agent_id: str):
+    def trigger_learning(agent_id: str, request: Request):
         if not manager.get_agent(agent_id):
             raise HTTPException(status_code=404, detail="Agent not found")
-        from openjarvis.core.events import EventType, get_event_bus
+        from openjarvis.core.events import EventType
 
-        bus = get_event_bus()
+        bus = _get_runtime_event_bus(request.app.state)
         bus.publish(EventType.AGENT_LEARNING_STARTED, {"agent_id": agent_id})
         return {"status": "triggered"}
 

src/openjarvis/server/api_routes.py

@@ -1087,12 +1087,16 @@ def include_all_routes(app) -> None:
     except ImportError:
         pass
 
-    # WebSocket bridge for real-time agent events
+    # WebSocket bridge for real-time agent events. Must subscribe on the
+    # same EventBus instance channels/agents actually publish to
+    # (app.state.bus, set in server/app.py) — the get_event_bus() global
+    # singleton is a *different* bus that nothing in `jarvis serve` ever
+    # publishes to, so events silently never reached this endpoint.
     try:
         from openjarvis.core.events import get_event_bus
         from openjarvis.server.ws_bridge import create_ws_router
 
-        ws_router = create_ws_router(get_event_bus())
+        ws_router = create_ws_router(getattr(app.state, "bus", None) or get_event_bus())
         app.include_router(ws_router)
     except Exception:
         logger.debug("WebSocket bridge not available", exc_info=True)

src/openjarvis/server/cloud_router.py

@@ -84,6 +84,17 @@ def is_cloud_model(model: str) -> bool:
     return get_provider(model) is not None
 
 
+def _openrouter_model_id(model: str) -> str:
+    """Return the provider-facing ID for an OpenRouter model."""
+    prefix = "openrouter/"
+    candidate = model.removeprefix(prefix)
+    # OpenRouter owns IDs such as "openrouter/auto" itself. Only remove the
+    # LiteLLM routing prefix when the remainder is still a provider/model ID.
+    if model.startswith(prefix) and "/" in candidate:
+        return candidate
+    return model
+
+
 # ---------------------------------------------------------------------------
 # Message conversion
 # ---------------------------------------------------------------------------
@@ -371,7 +382,7 @@ async def stream_cloud(
                 "OPENROUTER_API_KEY not set — add it in the Cloud Models tab"
             )
         async for token in _stream_openai(
-            model,
+            _openrouter_model_id(model),
             messages,
             temperature,
             max_tokens,

src/openjarvis/tools/storage/sqlite.py

@@ -95,6 +95,29 @@ class SQLiteMemory(MemoryBackend):
         )
         return doc_id
 
+    def replace_source(
+        self,
+        source: str,
+        documents: List[tuple[str, Optional[Dict[str, Any]]]],
+    ) -> List[str]:
+        """Atomically replace all documents associated with *source*."""
+        payload = [
+            (content, json.dumps(metadata) if metadata else None)
+            for content, metadata in documents
+        ]
+        doc_ids = self._rust_impl.replace_source(source, payload)
+        bus = get_event_bus()
+        for doc_id in doc_ids:
+            bus.publish(
+                EventType.MEMORY_STORE,
+                {
+                    "backend": self.backend_id,
+                    "doc_id": doc_id,
+                    "source": source,
+                },
+            )
+        return doc_ids
+
     def retrieve(
         self,
         query: str,

tests/agents/test_morning_digest.py

@@ -21,7 +21,7 @@ def test_morning_digest_run(tmp_path):
 
     mock_engine = MagicMock()
     mock_engine.generate.return_value = {
-        "content": "Good morning sir. You have 3 emails and 2 meetings today.",
+        "content": "Good morning sir. AtlasDB 1.0 was released.",
         "finish_reason": "stop",
         "usage": {},
     }
@@ -29,7 +29,7 @@ def test_morning_digest_run(tmp_path):
     # Mock collect result
     mock_collect_result = ToolResult(
         tool_name="digest_collect",
-        content='=== MESSAGES ===\n[gmail] From: alice@co.com — "Budget" (1h ago)\n',
+        content="=== WORLD ===\n[hackernews] AtlasDB 1.0 Released — 241 points\n",
         success=True,
         metadata={"total_items": 2},
     )
@@ -46,7 +46,9 @@ def test_morning_digest_run(tmp_path):
         mock_engine,
         "test-model",
         tools=[],
-        persona="neutral",
+        persona="jarvis",
+        sections=["world"],
+        section_sources={"world": ["hackernews", "news_rss"]},
         digest_store_path=str(tmp_path / "digest.db"),
     )
 
@@ -61,6 +63,16 @@ def test_morning_digest_run(tmp_path):
     assert "Good morning" in result.content
     assert result.turns == 1
     assert len(result.tool_results) == 2
+    assert set(result.metadata["sources_used"]) == {"hackernews", "news_rss"}
+    prompt = "\n".join(
+        message.text for message in mock_engine.generate.call_args.args[0]
+    ).casefold()
+    assert "world —" in prompt
+    for forbidden in (
+        "messages —|calendar —|health —|rebuttal|dinner at|group chat|"
+        "slack|next meeting|readiness|hrv|weather"
+    ).split("|"):
+        assert forbidden not in prompt
 
 
 def test_load_persona():

tests/cli/test_memory_cmd.py

@@ -40,6 +40,35 @@ def test_memory_index_file(tmp_path: Path, monkeypatch):
     assert "Indexed" in result.output or "chunk" in result.output
 
 
+def test_memory_index_replaces_existing_source(tmp_path: Path, monkeypatch):
+    """Re-indexing a file replaces its previous chunks."""
+    _register_sqlite()
+    db_path = str(tmp_path / "mem.db")
+    doc = tmp_path / "doc.txt"
+    doc.write_text(" ".join(["legacy"] * 100), encoding="utf-8")
+
+    mod = importlib.import_module("openjarvis.cli.memory_cmd")
+    monkeypatch.setattr(
+        mod,
+        "_get_backend",
+        lambda b=None: SQLiteMemory(db_path=db_path),
+    )
+
+    first = CliRunner().invoke(cli, ["memory", "index", str(doc)])
+    assert first.exit_code == 0
+
+    doc.write_text(" ".join(["updated"] * 100), encoding="utf-8")
+    second = CliRunner().invoke(cli, ["memory", "index", str(doc)])
+    assert second.exit_code == 0
+
+    backend = SQLiteMemory(db_path=db_path)
+    assert backend.count() == 1
+    assert backend.retrieve("legacy") == []
+    updated = backend.retrieve("updated")
+    assert len(updated) == 1
+    assert updated[0].source == str(doc)
+
+
 def test_memory_index_nonexistent(tmp_path: Path):
     """Indexing a nonexistent path should fail."""
     _register_sqlite()

tests/learning/test_router.py

@@ -88,13 +88,25 @@ class TestHeuristicRouter:
         router = HeuristicRouter(
             available_models=["small", "large", "coder"],
         )
-        ctx = RoutingContext(
-            query="solve x",
-            query_length=7,
-            has_math=True,
-        )
+        ctx = build_routing_context("solve the integral of x^2 dx")
+        assert ctx.has_math is True
+        assert ctx.complexity_score > 0.20
         assert router.select_model(ctx) == "large"
 
+    def test_low_complexity_math_prefers_small(self) -> None:
+        """Regression test: a trivial math query ("calculate 2+2") must not
+        escalate to the largest model just because it contains a math
+        keyword — the low-complexity rule takes priority over the math rule.
+        """
+        _register_models()
+        router = HeuristicRouter(
+            available_models=["small", "large", "coder"],
+        )
+        ctx = build_routing_context("calculate 2+2")
+        assert ctx.has_math is True
+        assert ctx.complexity_score == 0.20
+        assert router.select_model(ctx) == "small"
+
     def test_high_complexity_prefers_large(self) -> None:
         _register_models()
         router = HeuristicRouter(

tests/learning/test_routing_models.py

@@ -77,11 +77,9 @@ class TestRouterWithNewModels:
         router = HeuristicRouter(
             available_models=NEW_LOCAL_MODELS,
         )
-        ctx = RoutingContext(
-            query="solve the integral of x^2 dx",
-            query_length=29,
-            has_math=True,
-        )
+        ctx = build_routing_context("solve the integral of x^2 dx")
+        assert ctx.has_math is True
+        assert ctx.complexity_score > 0.20
         selected = router.select_model(ctx)
         assert selected == "gpt-oss:120b"
 

tests/server/test_agent_manager_routes.py

@@ -605,6 +605,39 @@ class TestLightweightSystemEngineResolution:
         )
         assert captured["key"] == "llamacpp"
 
+    def test_instrumented_engine_uses_runtime_event_bus(self, monkeypatch):
+        pytest.importorskip("fastapi")
+        from openjarvis.core.events import EventBus
+        from openjarvis.server import agent_manager_routes as amr
+        from openjarvis.telemetry import instrumented_engine
+
+        resolved_engine = MagicMock()
+        wrapped_engine = MagicMock()
+        runtime_bus = EventBus()
+        runtime = SimpleNamespace(
+            bus=runtime_bus,
+            memory_backend=object(),
+            channel_backend=None,
+            channel_bridge=None,
+            knowledge_db_path=None,
+        )
+        monkeypatch.setattr(
+            "openjarvis.engine._discovery.get_engine",
+            MagicMock(return_value=("resolved", resolved_engine)),
+        )
+        instrumented = MagicMock(return_value=wrapped_engine)
+        monkeypatch.setattr(instrumented_engine, "InstrumentedEngine", instrumented)
+
+        system = amr._make_lightweight_system(
+            engine=MagicMock(),
+            model="m",
+            config=self._cfg("vllm", "ollama"),
+            runtime=runtime,
+        )
+
+        instrumented.assert_called_once_with(resolved_engine, runtime_bus)
+        assert system.engine is wrapped_engine
+
     def test_caches_tool_memory_backend_when_prompt_context_is_disabled(
         self,
         monkeypatch,

tests/server/test_cloud_router.py

@@ -0,0 +1,49 @@
+"""Regression tests for OpenRouter model ID normalization."""
+
+from __future__ import annotations
+
+import pytest
+
+from openjarvis.core.types import Message
+from openjarvis.server import cloud_router
+
+
+def test_get_provider_detects_bare_openrouter_id():
+    assert cloud_router.get_provider("anthropic/claude-haiku-4.5") == "openrouter"
+
+
+def test_get_provider_detects_litellm_prefixed_openrouter_id():
+    model = "openrouter/anthropic/claude-haiku-4.5"
+    assert cloud_router.get_provider(model) == "openrouter"
+
+
+@pytest.mark.parametrize(
+    "requested_model,expected_forwarded_model",
+    [
+        ("anthropic/claude-haiku-4.5", "anthropic/claude-haiku-4.5"),
+        ("openrouter/anthropic/claude-haiku-4.5", "anthropic/claude-haiku-4.5"),
+        ("openrouter/auto", "openrouter/auto"),
+    ],
+)
+@pytest.mark.asyncio
+async def test_stream_cloud_normalizes_openrouter_model_before_forwarding(
+    monkeypatch, requested_model, expected_forwarded_model
+):
+    monkeypatch.setenv("OPENROUTER_API_KEY", "test-key")
+    captured: dict[str, str] = {}
+
+    async def fake_stream_openai(model, messages, temperature, max_tokens, **kwargs):
+        captured["model"] = model
+        yield "ok"
+
+    monkeypatch.setattr(cloud_router, "_stream_openai", fake_stream_openai)
+
+    tokens = [
+        token
+        async for token in cloud_router.stream_cloud(
+            requested_model, [Message(role="user", content="hi")]
+        )
+    ]
+
+    assert tokens == ["ok"]
+    assert captured["model"] == expected_forwarded_model

tests/server/test_ws_bridge.py

@@ -3,8 +3,10 @@
 from __future__ import annotations
 
 import asyncio
+import threading
 import time
 from types import SimpleNamespace
+from unittest.mock import MagicMock, patch
 
 import pytest
 
@@ -161,3 +163,91 @@ class TestWSBridge:
             ]
 
         asyncio.run(exercise())
+
+
+class TestIncludeAllRoutesBusWiring:
+    """Regression: the WS endpoint must subscribe on the same EventBus that
+    channels/agents actually publish to (app.state.bus), not the unrelated
+    get_event_bus() global singleton — publishing on the latter used to
+    silently never reach any connected browser client."""
+
+    def test_uses_app_state_bus_not_global_singleton(self):
+        from openjarvis.core.events import reset_event_bus
+        from openjarvis.server.api_routes import include_all_routes
+
+        reset_event_bus()  # isolate from other tests' global singleton state
+        app = FastAPI()
+        real_bus = EventBus()
+        app.state.bus = real_bus
+        include_all_routes(app)
+
+        client = TestClient(app)
+        with client.websocket_connect("/v1/agents/events") as ws:
+            real_bus.publish(EventType.AGENT_TICK_START, {"agent_id": "test-123"})
+            time.sleep(0.05)
+            data = ws.receive_json()
+            assert data["data"]["agent_id"] == "test-123"
+
+    @pytest.mark.parametrize(
+        ("path", "payload"),
+        [
+            ("/v1/managed-agents/test-123/run", None),
+            (
+                "/v1/managed-agents/test-123/messages",
+                {"content": "run now", "mode": "immediate", "stream": False},
+            ),
+        ],
+    )
+    def test_managed_agent_run_paths_publish_to_app_bus(self, path, payload):
+        from openjarvis.agents.executor import AgentExecutor
+        from openjarvis.core.events import reset_event_bus
+        from openjarvis.server.api_routes import include_all_routes
+
+        reset_event_bus()
+        app_bus = EventBus()
+        manager = MagicMock()
+        manager.get_agent.return_value = {
+            "id": "test-123",
+            "name": "test",
+            "status": "idle",
+            "config": {},
+        }
+        manager.send_message.return_value = {
+            "id": "message-123",
+            "agent_id": "test-123",
+            "content": "run now",
+            "mode": "immediate",
+        }
+
+        app = FastAPI()
+        app.state.bus = app_bus
+        app.state.agent_manager = manager
+        include_all_routes(app)
+
+        executed = threading.Event()
+        observed_buses = []
+
+        def publish_tick(executor, agent_id, **_kwargs):
+            observed_buses.append(executor._bus)
+            executor._bus.publish(EventType.AGENT_TICK_START, {"agent_id": agent_id})
+            executed.set()
+
+        client = TestClient(app)
+        with (
+            patch.object(AgentExecutor, "execute_tick", publish_tick),
+            patch(
+                "openjarvis.server.agent_manager_routes._make_lightweight_system",
+                return_value=MagicMock(),
+            ) as make_system,
+            client.websocket_connect("/v1/agents/events?agent_id=test-123") as ws,
+        ):
+            request_kwargs = {"json": payload} if payload is not None else {}
+            response = client.post(path, **request_kwargs)
+            assert response.status_code == 200
+            assert executed.wait(timeout=1)
+            assert observed_buses == [app_bus]
+            data = ws.receive_json()
+
+        assert data["type"] == "agent_tick_start"
+        assert data["data"]["agent_id"] == "test-123"
+        make_system.assert_called_once()