diff --git a/nanobot/agent/memory.py b/nanobot/agent/memory.py
index cdbc49f..93c1825 100644
--- a/nanobot/agent/memory.py
+++ b/nanobot/agent/memory.py
@@ -125,6 +125,13 @@ class MemoryStore:
                 return False
 
             args = response.tool_calls[0].arguments
+            # Some providers return arguments as a JSON string instead of dict
+            if isinstance(args, str):
+                args = json.loads(args)
+            if not isinstance(args, dict):
+                logger.warning("Memory consolidation: unexpected arguments type {}", type(args).__name__)
+                return False
+
             if entry := args.get("history_entry"):
                 if not isinstance(entry, str):
                     entry = json.dumps(entry, ensure_ascii=False)
diff --git a/nanobot/agent/tools/web.py b/nanobot/agent/tools/web.py
index 90cdda8..82eca83 100644
--- a/nanobot/agent/tools/web.py
+++ b/nanobot/agent/tools/web.py
@@ -58,12 +58,17 @@ class WebSearchTool(Tool):
     }
     
     def __init__(self, api_key: str | None = None, max_results: int = 5):
-        self.api_key = api_key or os.environ.get("BRAVE_API_KEY", "")
+        self.api_key = api_key
         self.max_results = max_results
-    
+
     async def execute(self, query: str, count: int | None = None, **kwargs: Any) -> str:
-        if not self.api_key:
-            return "Error: BRAVE_API_KEY not configured"
+        api_key = self.api_key or os.environ.get("BRAVE_API_KEY", "")
+        if not api_key:
+            return (
+                "Error: Brave Search API key not configured. "
+                "Set it in ~/.nanobot/config.json under tools.web.search.apiKey "
+                "(or export BRAVE_API_KEY), then restart the gateway."
+            )
         
         try:
             n = min(max(count or self.max_results, 1), 10)
@@ -71,7 +76,7 @@ class WebSearchTool(Tool):
                 r = await client.get(
                     "https://api.search.brave.com/res/v1/web/search",
                     params={"q": query, "count": n},
-                    headers={"Accept": "application/json", "X-Subscription-Token": self.api_key},
+                    headers={"Accept": "application/json", "X-Subscription-Token": api_key},
                     timeout=10.0
                 )
                 r.raise_for_status()
diff --git a/nanobot/channels/feishu.py b/nanobot/channels/feishu.py
index 2d50d74..480bf7b 100644
--- a/nanobot/channels/feishu.py
+++ b/nanobot/channels/feishu.py
@@ -180,21 +180,25 @@ def _extract_element_content(element: dict) -> list[str]:
     return parts
 
 
-def _extract_post_text(content_json: dict) -> str:
-    """Extract plain text from Feishu post (rich text) message content.
+def _extract_post_content(content_json: dict) -> tuple[str, list[str]]:
+    """Extract text and image keys from Feishu post (rich text) message content.
     
     Supports two formats:
     1. Direct format: {"title": "...", "content": [...]}
     2. Localized format: {"zh_cn": {"title": "...", "content": [...]}}
+    
+    Returns:
+        (text, image_keys) - extracted text and list of image keys
     """
-    def extract_from_lang(lang_content: dict) -> str | None:
+    def extract_from_lang(lang_content: dict) -> tuple[str | None, list[str]]:
         if not isinstance(lang_content, dict):
-            return None
+            return None, []
         title = lang_content.get("title", "")
         content_blocks = lang_content.get("content", [])
         if not isinstance(content_blocks, list):
-            return None
+            return None, []
         text_parts = []
+        image_keys = []
         if title:
             text_parts.append(title)
         for block in content_blocks:
@@ -209,22 +213,36 @@ def _extract_post_text(content_json: dict) -> str:
                         text_parts.append(element.get("text", ""))
                     elif tag == "at":
                         text_parts.append(f"@{element.get('user_name', 'user')}")
-        return " ".join(text_parts).strip() if text_parts else None
+                    elif tag == "img":
+                        img_key = element.get("image_key")
+                        if img_key:
+                            image_keys.append(img_key)
+        text = " ".join(text_parts).strip() if text_parts else None
+        return text, image_keys
     
     # Try direct format first
     if "content" in content_json:
-        result = extract_from_lang(content_json)
-        if result:
-            return result
+        text, images = extract_from_lang(content_json)
+        if text or images:
+            return text or "", images
     
     # Try localized format
     for lang_key in ("zh_cn", "en_us", "ja_jp"):
         lang_content = content_json.get(lang_key)
-        result = extract_from_lang(lang_content)
-        if result:
-            return result
+        text, images = extract_from_lang(lang_content)
+        if text or images:
+            return text or "", images
     
-    return ""
+    return "", []
+
+
+def _extract_post_text(content_json: dict) -> str:
+    """Extract plain text from Feishu post (rich text) message content.
+    
+    Legacy wrapper for _extract_post_content, returns only text.
+    """
+    text, _ = _extract_post_content(content_json)
+    return text
 
 
 class FeishuChannel(BaseChannel):
@@ -691,9 +709,17 @@ class FeishuChannel(BaseChannel):
                     content_parts.append(text)
 
             elif msg_type == "post":
-                text = _extract_post_text(content_json)
+                text, image_keys = _extract_post_content(content_json)
                 if text:
                     content_parts.append(text)
+                # Download images embedded in post
+                for img_key in image_keys:
+                    file_path, content_text = await self._download_and_save_media(
+                        "image", {"image_key": img_key}, message_id
+                    )
+                    if file_path:
+                        media_paths.append(file_path)
+                    content_parts.append(content_text)
 
             elif msg_type in ("image", "audio", "file", "media"):
                 file_path, content_text = await self._download_and_save_media(msg_type, content_json, message_id)
diff --git a/nanobot/cli/commands.py b/nanobot/cli/commands.py
index 90b9f44..ca71694 100644
--- a/nanobot/cli/commands.py
+++ b/nanobot/cli/commands.py
@@ -360,19 +360,19 @@ def gateway(
         return "cli", "direct"
 
     # Create heartbeat service
-    async def on_heartbeat(prompt: str) -> str:
-        """Execute heartbeat through the agent."""
+    async def on_heartbeat_execute(tasks: str) -> str:
+        """Phase 2: execute heartbeat tasks through the full agent loop."""
         channel, chat_id = _pick_heartbeat_target()
 
         async def _silent(*_args, **_kwargs):
             pass
 
         return await agent.process_direct(
-            prompt,
+            tasks,
             session_key="heartbeat",
             channel=channel,
             chat_id=chat_id,
-            on_progress=_silent,  # suppress: heartbeat should not push progress to external channels
+            on_progress=_silent,
         )
 
     async def on_heartbeat_notify(response: str) -> None:
@@ -383,12 +383,15 @@ def gateway(
             return  # No external channel available to deliver to
         await bus.publish_outbound(OutboundMessage(channel=channel, chat_id=chat_id, content=response))
 
+    hb_cfg = config.gateway.heartbeat
     heartbeat = HeartbeatService(
         workspace=config.workspace_path,
-        on_heartbeat=on_heartbeat,
+        provider=provider,
+        model=agent.model,
+        on_execute=on_heartbeat_execute,
         on_notify=on_heartbeat_notify,
-        interval_s=30 * 60,  # 30 minutes
-        enabled=True
+        interval_s=hb_cfg.interval_s,
+        enabled=hb_cfg.enabled,
     )
     
     if channels.enabled_channels:
diff --git a/nanobot/config/schema.py b/nanobot/config/schema.py
index fe8dd83..215f38d 100644
--- a/nanobot/config/schema.py
+++ b/nanobot/config/schema.py
@@ -228,11 +228,19 @@ class ProvidersConfig(Base):
     github_copilot: ProviderConfig = Field(default_factory=ProviderConfig)  # Github Copilot (OAuth)
 
 
+class HeartbeatConfig(Base):
+    """Heartbeat service configuration."""
+
+    enabled: bool = True
+    interval_s: int = 30 * 60  # 30 minutes
+
+
 class GatewayConfig(Base):
     """Gateway/server configuration."""
 
     host: str = "0.0.0.0"
     port: int = 18790
+    heartbeat: HeartbeatConfig = Field(default_factory=HeartbeatConfig)
 
 
 class WebSearchConfig(Base):
diff --git a/nanobot/heartbeat/service.py b/nanobot/heartbeat/service.py
index cb1a1c7..e534017 100644
--- a/nanobot/heartbeat/service.py
+++ b/nanobot/heartbeat/service.py
@@ -1,80 +1,110 @@
 """Heartbeat service - periodic agent wake-up to check for tasks."""
 
+from __future__ import annotations
+
 import asyncio
 from pathlib import Path
-from typing import Any, Callable, Coroutine
+from typing import TYPE_CHECKING, Any, Callable, Coroutine
 
 from loguru import logger
 
-# Default interval: 30 minutes
-DEFAULT_HEARTBEAT_INTERVAL_S = 30 * 60
+if TYPE_CHECKING:
+    from nanobot.providers.base import LLMProvider
 
-# Token the agent replies with when there is nothing to report
-HEARTBEAT_OK_TOKEN = "HEARTBEAT_OK"
-
-# The prompt sent to agent during heartbeat
-HEARTBEAT_PROMPT = (
-    "Read HEARTBEAT.md in your workspace and follow any instructions listed there. "
-    f"If nothing needs attention, reply with exactly: {HEARTBEAT_OK_TOKEN}"
-)
-
-
-def _is_heartbeat_empty(content: str | None) -> bool:
-    """Check if HEARTBEAT.md has no actionable content."""
-    if not content:
-        return True
-    
-    # Lines to skip: empty, headers, HTML comments, empty checkboxes
-    skip_patterns = {"- [ ]", "* [ ]", "- [x]", "* [x]"}
-    
-    for line in content.split("\n"):
-        line = line.strip()
-        if not line or line.startswith("#") or line.startswith("<!--") or line in skip_patterns:
-            continue
-        return False  # Found actionable content
-    
-    return True
+_HEARTBEAT_TOOL = [
+    {
+        "type": "function",
+        "function": {
+            "name": "heartbeat",
+            "description": "Report heartbeat decision after reviewing tasks.",
+            "parameters": {
+                "type": "object",
+                "properties": {
+                    "action": {
+                        "type": "string",
+                        "enum": ["skip", "run"],
+                        "description": "skip = nothing to do, run = has active tasks",
+                    },
+                    "tasks": {
+                        "type": "string",
+                        "description": "Natural-language summary of active tasks (required for run)",
+                    },
+                },
+                "required": ["action"],
+            },
+        },
+    }
+]
 
 
 class HeartbeatService:
     """
     Periodic heartbeat service that wakes the agent to check for tasks.
 
-    The agent reads HEARTBEAT.md from the workspace and executes any tasks
-    listed there. If it has something to report, the response is forwarded
-    to the user via on_notify. If nothing needs attention, the agent replies
-    HEARTBEAT_OK and the response is silently dropped.
+    Phase 1 (decision): reads HEARTBEAT.md and asks the LLM — via a virtual
+    tool call — whether there are active tasks.  This avoids free-text parsing
+    and the unreliable HEARTBEAT_OK token.
+
+    Phase 2 (execution): only triggered when Phase 1 returns ``run``.  The
+    ``on_execute`` callback runs the task through the full agent loop and
+    returns the result to deliver.
     """
 
     def __init__(
         self,
         workspace: Path,
-        on_heartbeat: Callable[[str], Coroutine[Any, Any, str]] | None = None,
+        provider: LLMProvider,
+        model: str,
+        on_execute: Callable[[str], Coroutine[Any, Any, str]] | None = None,
         on_notify: Callable[[str], Coroutine[Any, Any, None]] | None = None,
-        interval_s: int = DEFAULT_HEARTBEAT_INTERVAL_S,
+        interval_s: int = 30 * 60,
         enabled: bool = True,
     ):
         self.workspace = workspace
-        self.on_heartbeat = on_heartbeat
+        self.provider = provider
+        self.model = model
+        self.on_execute = on_execute
         self.on_notify = on_notify
         self.interval_s = interval_s
         self.enabled = enabled
         self._running = False
         self._task: asyncio.Task | None = None
-    
+
     @property
     def heartbeat_file(self) -> Path:
         return self.workspace / "HEARTBEAT.md"
-    
+
     def _read_heartbeat_file(self) -> str | None:
-        """Read HEARTBEAT.md content."""
         if self.heartbeat_file.exists():
             try:
                 return self.heartbeat_file.read_text(encoding="utf-8")
             except Exception:
                 return None
         return None
-    
+
+    async def _decide(self, content: str) -> tuple[str, str]:
+        """Phase 1: ask LLM to decide skip/run via virtual tool call.
+
+        Returns (action, tasks) where action is 'skip' or 'run'.
+        """
+        response = await self.provider.chat(
+            messages=[
+                {"role": "system", "content": "You are a heartbeat agent. Call the heartbeat tool to report your decision."},
+                {"role": "user", "content": (
+                    "Review the following HEARTBEAT.md and decide whether there are active tasks.\n\n"
+                    f"{content}"
+                )},
+            ],
+            tools=_HEARTBEAT_TOOL,
+            model=self.model,
+        )
+
+        if not response.has_tool_calls:
+            return "skip", ""
+
+        args = response.tool_calls[0].arguments
+        return args.get("action", "skip"), args.get("tasks", "")
+
     async def start(self) -> None:
         """Start the heartbeat service."""
         if not self.enabled:
@@ -83,18 +113,18 @@ class HeartbeatService:
         if self._running:
             logger.warning("Heartbeat already running")
             return
-        
+
         self._running = True
         self._task = asyncio.create_task(self._run_loop())
         logger.info("Heartbeat started (every {}s)", self.interval_s)
-    
+
     def stop(self) -> None:
         """Stop the heartbeat service."""
         self._running = False
         if self._task:
             self._task.cancel()
             self._task = None
-    
+
     async def _run_loop(self) -> None:
         """Main heartbeat loop."""
         while self._running:
@@ -106,32 +136,38 @@ class HeartbeatService:
                 break
             except Exception as e:
                 logger.error("Heartbeat error: {}", e)
-    
+
     async def _tick(self) -> None:
         """Execute a single heartbeat tick."""
         content = self._read_heartbeat_file()
-        
-        # Skip if HEARTBEAT.md is empty or doesn't exist
-        if _is_heartbeat_empty(content):
-            logger.debug("Heartbeat: no tasks (HEARTBEAT.md empty)")
+        if not content:
+            logger.debug("Heartbeat: HEARTBEAT.md missing or empty")
             return
-        
+
         logger.info("Heartbeat: checking for tasks...")
-        
-        if self.on_heartbeat:
-            try:
-                response = await self.on_heartbeat(HEARTBEAT_PROMPT)
-                if HEARTBEAT_OK_TOKEN in response.upper():
-                    logger.info("Heartbeat: OK (nothing to report)")
-                else:
+
+        try:
+            action, tasks = await self._decide(content)
+
+            if action != "run":
+                logger.info("Heartbeat: OK (nothing to report)")
+                return
+
+            logger.info("Heartbeat: tasks found, executing...")
+            if self.on_execute:
+                response = await self.on_execute(tasks)
+                if response and self.on_notify:
                     logger.info("Heartbeat: completed, delivering response")
-                    if self.on_notify:
-                        await self.on_notify(response)
-            except Exception:
-                logger.exception("Heartbeat execution failed")
-    
+                    await self.on_notify(response)
+        except Exception:
+            logger.exception("Heartbeat execution failed")
+
     async def trigger_now(self) -> str | None:
         """Manually trigger a heartbeat."""
-        if self.on_heartbeat:
-            return await self.on_heartbeat(HEARTBEAT_PROMPT)
-        return None
+        content = self._read_heartbeat_file()
+        if not content:
+            return None
+        action, tasks = await self._decide(content)
+        if action != "run" or not self.on_execute:
+            return None
+        return await self.on_execute(tasks)
diff --git a/nanobot/session/manager.py b/nanobot/session/manager.py
index 5f23dc2..d59b7c9 100644
--- a/nanobot/session/manager.py
+++ b/nanobot/session/manager.py
@@ -43,9 +43,18 @@ class Session:
         self.updated_at = datetime.now()
     
     def get_history(self, max_messages: int = 500) -> list[dict[str, Any]]:
-        """Get recent messages in LLM format, preserving tool metadata."""
+        """Return unconsolidated messages for LLM input, aligned to a user turn."""
+        unconsolidated = self.messages[self.last_consolidated:]
+        sliced = unconsolidated[-max_messages:]
+
+        # Drop leading non-user messages to avoid orphaned tool_result blocks
+        for i, m in enumerate(sliced):
+            if m.get("role") == "user":
+                sliced = sliced[i:]
+                break
+
         out: list[dict[str, Any]] = []
-        for m in self.messages[-max_messages:]:
+        for m in sliced:
             entry: dict[str, Any] = {"role": m["role"], "content": m.get("content", "")}
             for k in ("tool_calls", "tool_call_id", "name"):
                 if k in m:
diff --git a/nanobot/templates/TOOLS.md b/nanobot/templates/TOOLS.md
index 757edd2..51c3a2d 100644
--- a/nanobot/templates/TOOLS.md
+++ b/nanobot/templates/TOOLS.md
@@ -10,27 +10,6 @@ This file documents non-obvious constraints and usage patterns.
 - Output is truncated at 10,000 characters
 - `restrictToWorkspace` config can limit file access to the workspace
 
-## Cron — Scheduled Reminders
+## cron — Scheduled Reminders
 
-Use `exec` to create scheduled reminders:
-
-```bash
-# Recurring: every day at 9am
-nanobot cron add --name "morning" --message "Good morning!" --cron "0 9 * * *"
-
-# With timezone (--tz only works with --cron)
-nanobot cron add --name "standup" --message "Standup time!" --cron "0 10 * * 1-5" --tz "Asia/Shanghai"
-
-# Recurring: every 2 hours
-nanobot cron add --name "water" --message "Drink water!" --every 7200
-
-# One-time: specific ISO time
-nanobot cron add --name "meeting" --message "Meeting starts now!" --at "2025-01-31T15:00:00"
-
-# Deliver to a specific channel/user
-nanobot cron add --name "reminder" --message "Check email" --at "2025-01-31T09:00:00" --deliver --to "USER_ID" --channel "CHANNEL"
-
-# Manage jobs
-nanobot cron list
-nanobot cron remove <job_id>
-```
+- Please refer to cron skill for usage.
diff --git a/tests/test_memory_consolidation_types.py b/tests/test_memory_consolidation_types.py
new file mode 100644
index 0000000..375c802
--- /dev/null
+++ b/tests/test_memory_consolidation_types.py
@@ -0,0 +1,147 @@
+"""Test MemoryStore.consolidate() handles non-string tool call arguments.
+
+Regression test for https://github.com/HKUDS/nanobot/issues/1042
+When memory consolidation receives dict values instead of strings from the LLM
+tool call response, it should serialize them to JSON instead of raising TypeError.
+"""
+
+import json
+from pathlib import Path
+from unittest.mock import AsyncMock, MagicMock
+
+import pytest
+
+from nanobot.agent.memory import MemoryStore
+from nanobot.providers.base import LLMResponse, ToolCallRequest
+
+
+def _make_session(message_count: int = 30, memory_window: int = 50):
+    """Create a mock session with messages."""
+    session = MagicMock()
+    session.messages = [
+        {"role": "user", "content": f"msg{i}", "timestamp": "2026-01-01 00:00"}
+        for i in range(message_count)
+    ]
+    session.last_consolidated = 0
+    return session
+
+
+def _make_tool_response(history_entry, memory_update):
+    """Create an LLMResponse with a save_memory tool call."""
+    return LLMResponse(
+        content=None,
+        tool_calls=[
+            ToolCallRequest(
+                id="call_1",
+                name="save_memory",
+                arguments={
+                    "history_entry": history_entry,
+                    "memory_update": memory_update,
+                },
+            )
+        ],
+    )
+
+
+class TestMemoryConsolidationTypeHandling:
+    """Test that consolidation handles various argument types correctly."""
+
+    @pytest.mark.asyncio
+    async def test_string_arguments_work(self, tmp_path: Path) -> None:
+        """Normal case: LLM returns string arguments."""
+        store = MemoryStore(tmp_path)
+        provider = AsyncMock()
+        provider.chat = AsyncMock(
+            return_value=_make_tool_response(
+                history_entry="[2026-01-01] User discussed testing.",
+                memory_update="# Memory\nUser likes testing.",
+            )
+        )
+        session = _make_session(message_count=60)
+
+        result = await store.consolidate(session, provider, "test-model", memory_window=50)
+
+        assert result is True
+        assert store.history_file.exists()
+        assert "[2026-01-01] User discussed testing." in store.history_file.read_text()
+        assert "User likes testing." in store.memory_file.read_text()
+
+    @pytest.mark.asyncio
+    async def test_dict_arguments_serialized_to_json(self, tmp_path: Path) -> None:
+        """Issue #1042: LLM returns dict instead of string — must not raise TypeError."""
+        store = MemoryStore(tmp_path)
+        provider = AsyncMock()
+        provider.chat = AsyncMock(
+            return_value=_make_tool_response(
+                history_entry={"timestamp": "2026-01-01", "summary": "User discussed testing."},
+                memory_update={"facts": ["User likes testing"], "topics": ["testing"]},
+            )
+        )
+        session = _make_session(message_count=60)
+
+        result = await store.consolidate(session, provider, "test-model", memory_window=50)
+
+        assert result is True
+        assert store.history_file.exists()
+        history_content = store.history_file.read_text()
+        parsed = json.loads(history_content.strip())
+        assert parsed["summary"] == "User discussed testing."
+
+        memory_content = store.memory_file.read_text()
+        parsed_mem = json.loads(memory_content)
+        assert "User likes testing" in parsed_mem["facts"]
+
+    @pytest.mark.asyncio
+    async def test_string_arguments_as_raw_json(self, tmp_path: Path) -> None:
+        """Some providers return arguments as a JSON string instead of parsed dict."""
+        store = MemoryStore(tmp_path)
+        provider = AsyncMock()
+
+        # Simulate arguments being a JSON string (not yet parsed)
+        response = LLMResponse(
+            content=None,
+            tool_calls=[
+                ToolCallRequest(
+                    id="call_1",
+                    name="save_memory",
+                    arguments=json.dumps({
+                        "history_entry": "[2026-01-01] User discussed testing.",
+                        "memory_update": "# Memory\nUser likes testing.",
+                    }),
+                )
+            ],
+        )
+        provider.chat = AsyncMock(return_value=response)
+        session = _make_session(message_count=60)
+
+        result = await store.consolidate(session, provider, "test-model", memory_window=50)
+
+        assert result is True
+        assert "User discussed testing." in store.history_file.read_text()
+
+    @pytest.mark.asyncio
+    async def test_no_tool_call_returns_false(self, tmp_path: Path) -> None:
+        """When LLM doesn't use the save_memory tool, return False."""
+        store = MemoryStore(tmp_path)
+        provider = AsyncMock()
+        provider.chat = AsyncMock(
+            return_value=LLMResponse(content="I summarized the conversation.", tool_calls=[])
+        )
+        session = _make_session(message_count=60)
+
+        result = await store.consolidate(session, provider, "test-model", memory_window=50)
+
+        assert result is False
+        assert not store.history_file.exists()
+
+    @pytest.mark.asyncio
+    async def test_skips_when_few_messages(self, tmp_path: Path) -> None:
+        """Consolidation should be a no-op when messages < keep_count."""
+        store = MemoryStore(tmp_path)
+        provider = AsyncMock()
+        session = _make_session(message_count=10)
+
+        result = await store.consolidate(session, provider, "test-model", memory_window=50)
+
+        assert result is True
+        provider.chat.assert_not_called()