Merge remote-tracking branch 'origin/main' into pr-1848

nanobot/agent/loop.py

@@ -5,7 +5,6 @@ from __future__ import annotations
 import asyncio
 import json
 import re
-import weakref
 from contextlib import AsyncExitStack
 from pathlib import Path
 from typing import TYPE_CHECKING, Any, Awaitable, Callable
@@ -13,7 +12,7 @@ from typing import TYPE_CHECKING, Any, Awaitable, Callable
 from loguru import logger
 
 from nanobot.agent.context import ContextBuilder
-from nanobot.agent.memory import MemoryStore
+from nanobot.agent.memory import MemoryConsolidator
 from nanobot.agent.subagent import SubagentManager
 from nanobot.agent.tools.cron import CronTool
 from nanobot.agent.tools.filesystem import EditFileTool, ListDirTool, ReadFileTool, WriteFileTool
@@ -55,8 +54,8 @@ class AgentLoop:
         max_iterations: int = 40,
         temperature: float = 0.1,
         max_tokens: int = 4096,
-        memory_window: int = 100,
         reasoning_effort: str | None = None,
+        context_window_tokens: int = 65_536,
         brave_api_key: str | None = None,
         web_proxy: str | None = None,
         exec_config: ExecToolConfig | None = None,
@@ -75,8 +74,8 @@ class AgentLoop:
         self.max_iterations = max_iterations
         self.temperature = temperature
         self.max_tokens = max_tokens
-        self.memory_window = memory_window
         self.reasoning_effort = reasoning_effort
+        self.context_window_tokens = context_window_tokens
         self.brave_api_key = brave_api_key
         self.web_proxy = web_proxy
         self.exec_config = exec_config or ExecToolConfig()
@@ -105,11 +104,17 @@ class AgentLoop:
         self._mcp_stack: AsyncExitStack | None = None
         self._mcp_connected = False
         self._mcp_connecting = False
-        self._consolidating: set[str] = set()  # Session keys with consolidation in progress
-        self._consolidation_tasks: set[asyncio.Task] = set()  # Strong refs to in-flight tasks
-        self._consolidation_locks: weakref.WeakValueDictionary[str, asyncio.Lock] = weakref.WeakValueDictionary()
         self._active_tasks: dict[str, list[asyncio.Task]] = {}  # session_key -> tasks
         self._processing_lock = asyncio.Lock()
+        self.memory_consolidator = MemoryConsolidator(
+            workspace=workspace,
+            provider=provider,
+            model=self.model,
+            sessions=self.sessions,
+            context_window_tokens=context_window_tokens,
+            build_messages=self.context.build_messages,
+            get_tool_definitions=self.tools.get_definitions,
+        )
         self._register_default_tools()
 
     def _register_default_tools(self) -> None:
@@ -182,7 +187,7 @@ class AgentLoop:
         initial_messages: list[dict],
         on_progress: Callable[..., Awaitable[None]] | None = None,
     ) -> tuple[str | None, list[str], list[dict]]:
-        """Run the agent iteration loop. Returns (final_content, tools_used, messages)."""
+        """Run the agent iteration loop."""
         messages = initial_messages
         iteration = 0
         final_content = None
@@ -191,9 +196,11 @@ class AgentLoop:
         while iteration < self.max_iterations:
             iteration += 1
 
+            tool_defs = self.tools.get_definitions()
+
             response = await self.provider.chat_with_retry(
                 messages=messages,
-                tools=self.tools.get_definitions(),
+                tools=tool_defs,
                 model=self.model,
                 temperature=self.temperature,
                 max_tokens=self.max_tokens,
@@ -341,8 +348,9 @@ class AgentLoop:
             logger.info("Processing system message from {}", msg.sender_id)
             key = f"{channel}:{chat_id}"
             session = self.sessions.get_or_create(key)
+            await self.memory_consolidator.maybe_consolidate_by_tokens(session)
             self._set_tool_context(channel, chat_id, msg.metadata.get("message_id"))
-            history = session.get_history(max_messages=self.memory_window)
+            history = session.get_history(max_messages=0)
             messages = self.context.build_messages(
                 history=history,
                 current_message=msg.content, channel=channel, chat_id=chat_id,
@@ -350,6 +358,7 @@ class AgentLoop:
             final_content, _, all_msgs = await self._run_agent_loop(messages)
             self._save_turn(session, all_msgs, 1 + len(history))
             self.sessions.save(session)
+            await self.memory_consolidator.maybe_consolidate_by_tokens(session)
             return OutboundMessage(channel=channel, chat_id=chat_id,
                                   content=final_content or "Background task completed.")
 
@@ -362,27 +371,20 @@ class AgentLoop:
         # Slash commands
         cmd = msg.content.strip().lower()
         if cmd == "/new":
-            lock = self._consolidation_locks.setdefault(session.key, asyncio.Lock())
-            self._consolidating.add(session.key)
             try:
-                async with lock:
+                if not await self.memory_consolidator.archive_unconsolidated(session):
-                    snapshot = session.messages[session.last_consolidated:]
+                    return OutboundMessage(
-                    if snapshot:
+                        channel=msg.channel,
-                        temp = Session(key=session.key)
+                        chat_id=msg.chat_id,
-                        temp.messages = list(snapshot)
+                        content="Memory archival failed, session not cleared. Please try again.",
-                        if not await self._consolidate_memory(temp, archive_all=True):
+                    )
-                            return OutboundMessage(
-                                channel=msg.channel, chat_id=msg.chat_id,
-                                content="Memory archival failed, session not cleared. Please try again.",
-                            )
             except Exception:
                 logger.exception("/new archival failed for {}", session.key)
                 return OutboundMessage(
-                    channel=msg.channel, chat_id=msg.chat_id,
+                    channel=msg.channel,
+                    chat_id=msg.chat_id,
                     content="Memory archival failed, session not cleared. Please try again.",
                 )
-            finally:
-                self._consolidating.discard(session.key)
 
             session.clear()
             self.sessions.save(session)
@@ -393,30 +395,14 @@ class AgentLoop:
             return OutboundMessage(channel=msg.channel, chat_id=msg.chat_id,
                                   content="🐈 nanobot commands:\n/new — Start a new conversation\n/stop — Stop the current task\n/help — Show available commands")
 
-        unconsolidated = len(session.messages) - session.last_consolidated
+        await self.memory_consolidator.maybe_consolidate_by_tokens(session)
-        if (unconsolidated >= self.memory_window and session.key not in self._consolidating):
-            self._consolidating.add(session.key)
-            lock = self._consolidation_locks.setdefault(session.key, asyncio.Lock())
-
-            async def _consolidate_and_unlock():
-                try:
-                    async with lock:
-                        await self._consolidate_memory(session)
-                finally:
-                    self._consolidating.discard(session.key)
-                    _task = asyncio.current_task()
-                    if _task is not None:
-                        self._consolidation_tasks.discard(_task)
-
-            _task = asyncio.create_task(_consolidate_and_unlock())
-            self._consolidation_tasks.add(_task)
 
         self._set_tool_context(msg.channel, msg.chat_id, msg.metadata.get("message_id"))
         if message_tool := self.tools.get("message"):
             if isinstance(message_tool, MessageTool):
                 message_tool.start_turn()
 
-        history = session.get_history(max_messages=self.memory_window)
+        history = session.get_history(max_messages=0)
         initial_messages = self.context.build_messages(
             history=history,
             current_message=msg.content,
@@ -441,6 +427,7 @@ class AgentLoop:
 
         self._save_turn(session, all_msgs, 1 + len(history))
         self.sessions.save(session)
+        await self.memory_consolidator.maybe_consolidate_by_tokens(session)
 
         if (mt := self.tools.get("message")) and isinstance(mt, MessageTool) and mt._sent_in_turn:
             return None
@@ -487,13 +474,6 @@ class AgentLoop:
             session.messages.append(entry)
         session.updated_at = datetime.now()
 
-    async def _consolidate_memory(self, session, archive_all: bool = False) -> bool:
-        """Delegate to MemoryStore.consolidate(). Returns True on success."""
-        return await MemoryStore(self.workspace).consolidate(
-            session, self.provider, self.model,
-            archive_all=archive_all, memory_window=self.memory_window,
-        )
-
     async def process_direct(
         self,
         content: str,

nanobot/agent/memory.py

@@ -2,17 +2,19 @@
 
 from __future__ import annotations
 
+import asyncio
 import json
+import weakref
 from pathlib import Path
-from typing import TYPE_CHECKING
+from typing import TYPE_CHECKING, Any, Callable
 
 from loguru import logger
 
-from nanobot.utils.helpers import ensure_dir
+from nanobot.utils.helpers import ensure_dir, estimate_message_tokens, estimate_prompt_tokens_chain
 
 if TYPE_CHECKING:
     from nanobot.providers.base import LLMProvider
-    from nanobot.session.manager import Session
+    from nanobot.session.manager import Session, SessionManager
 
 
 _SAVE_MEMORY_TOOL = [
@@ -26,7 +28,7 @@ _SAVE_MEMORY_TOOL = [
                 "properties": {
                     "history_entry": {
                         "type": "string",
-                        "description": "A paragraph (2-5 sentences) summarizing key events/decisions/topics. "
+                        "description": "A paragraph summarizing key events/decisions/topics. "
                         "Start with [YYYY-MM-DD HH:MM]. Include detail useful for grep search.",
                     },
                     "memory_update": {
@@ -42,6 +44,20 @@ _SAVE_MEMORY_TOOL = [
 ]
 
 
+def _ensure_text(value: Any) -> str:
+    """Normalize tool-call payload values to text for file storage."""
+    return value if isinstance(value, str) else json.dumps(value, ensure_ascii=False)
+
+
+def _normalize_save_memory_args(args: Any) -> dict[str, Any] | None:
+    """Normalize provider tool-call arguments to the expected dict shape."""
+    if isinstance(args, str):
+        args = json.loads(args)
+    if isinstance(args, list):
+        return args[0] if args and isinstance(args[0], dict) else None
+    return args if isinstance(args, dict) else None
+
+
 class MemoryStore:
     """Two-layer memory: MEMORY.md (long-term facts) + HISTORY.md (grep-searchable log)."""
 
@@ -66,40 +82,27 @@ class MemoryStore:
         long_term = self.read_long_term()
         return f"## Long-term Memory\n{long_term}" if long_term else ""
 
+    @staticmethod
+    def _format_messages(messages: list[dict]) -> str:
+        lines = []
+        for message in messages:
+            if not message.get("content"):
+                continue
+            tools = f" [tools: {', '.join(message['tools_used'])}]" if message.get("tools_used") else ""
+            lines.append(
+                f"[{message.get('timestamp', '?')[:16]}] {message['role'].upper()}{tools}: {message['content']}"
+            )
+        return "\n".join(lines)
+
     async def consolidate(
         self,
-        session: Session,
+        messages: list[dict],
         provider: LLMProvider,
         model: str,
-        *,
-        archive_all: bool = False,
-        memory_window: int = 50,
     ) -> bool:
-        """Consolidate old messages into MEMORY.md + HISTORY.md via LLM tool call.
+        """Consolidate the provided message chunk into MEMORY.md + HISTORY.md."""
-
+        if not messages:
-        Returns True on success (including no-op), False on failure.
+            return True
-        """
-        if archive_all:
-            old_messages = session.messages
-            keep_count = 0
-            logger.info("Memory consolidation (archive_all): {} messages", len(session.messages))
-        else:
-            keep_count = memory_window // 2
-            if len(session.messages) <= keep_count:
-                return True
-            if len(session.messages) - session.last_consolidated <= 0:
-                return True
-            old_messages = session.messages[session.last_consolidated:-keep_count]
-            if not old_messages:
-                return True
-            logger.info("Memory consolidation: {} to consolidate, {} keep", len(old_messages), keep_count)
-
-        lines = []
-        for m in old_messages:
-            if not m.get("content"):
-                continue
-            tools = f" [tools: {', '.join(m['tools_used'])}]" if m.get("tools_used") else ""
-            lines.append(f"[{m.get('timestamp', '?')[:16]}] {m['role'].upper()}{tools}: {m['content']}")
 
         current_memory = self.read_long_term()
         prompt = f"""Process this conversation and call the save_memory tool with your consolidation.
@@ -108,7 +111,7 @@ class MemoryStore:
 {current_memory or "(empty)"}
 
 ## Conversation to Process
-{chr(10).join(lines)}"""
+{self._format_messages(messages)}"""
 
         try:
             response = await provider.chat_with_retry(
@@ -124,34 +127,158 @@ class MemoryStore:
                 logger.warning("Memory consolidation: LLM did not call save_memory, skipping")
                 return False
 
-            args = response.tool_calls[0].arguments
+            args = _normalize_save_memory_args(response.tool_calls[0].arguments)
-            # Some providers return arguments as a JSON string instead of dict
+            if args is None:
-            if isinstance(args, str):
+                logger.warning("Memory consolidation: unexpected save_memory arguments")
-                args = json.loads(args)
-            # Some providers return arguments as a list (handle edge case)
-            if isinstance(args, list):
-                if args and isinstance(args[0], dict):
-                    args = args[0]
-                else:
-                    logger.warning("Memory consolidation: unexpected arguments as empty or non-dict list")
-                    return False
-            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):
+                self.append_history(_ensure_text(entry))
-                    entry = json.dumps(entry, ensure_ascii=False)
-                self.append_history(entry)
             if update := args.get("memory_update"):
-                if not isinstance(update, str):
+                update = _ensure_text(update)
-                    update = json.dumps(update, ensure_ascii=False)
                 if update != current_memory:
                     self.write_long_term(update)
 
-            session.last_consolidated = 0 if archive_all else len(session.messages) - keep_count
+            logger.info("Memory consolidation done for {} messages", len(messages))
-            logger.info("Memory consolidation done: {} messages, last_consolidated={}", len(session.messages), session.last_consolidated)
             return True
         except Exception:
             logger.exception("Memory consolidation failed")
             return False
+
+
+class MemoryConsolidator:
+    """Owns consolidation policy, locking, and session offset updates."""
+
+    _MAX_CONSOLIDATION_ROUNDS = 5
+
+    def __init__(
+        self,
+        workspace: Path,
+        provider: LLMProvider,
+        model: str,
+        sessions: SessionManager,
+        context_window_tokens: int,
+        build_messages: Callable[..., list[dict[str, Any]]],
+        get_tool_definitions: Callable[[], list[dict[str, Any]]],
+    ):
+        self.store = MemoryStore(workspace)
+        self.provider = provider
+        self.model = model
+        self.sessions = sessions
+        self.context_window_tokens = context_window_tokens
+        self._build_messages = build_messages
+        self._get_tool_definitions = get_tool_definitions
+        self._locks: weakref.WeakValueDictionary[str, asyncio.Lock] = weakref.WeakValueDictionary()
+
+    def get_lock(self, session_key: str) -> asyncio.Lock:
+        """Return the shared consolidation lock for one session."""
+        return self._locks.setdefault(session_key, asyncio.Lock())
+
+    async def consolidate_messages(self, messages: list[dict[str, object]]) -> bool:
+        """Archive a selected message chunk into persistent memory."""
+        return await self.store.consolidate(messages, self.provider, self.model)
+
+    def pick_consolidation_boundary(
+        self,
+        session: Session,
+        tokens_to_remove: int,
+    ) -> tuple[int, int] | None:
+        """Pick a user-turn boundary that removes enough old prompt tokens."""
+        start = session.last_consolidated
+        if start >= len(session.messages) or tokens_to_remove <= 0:
+            return None
+
+        removed_tokens = 0
+        last_boundary: tuple[int, int] | None = None
+        for idx in range(start, len(session.messages)):
+            message = session.messages[idx]
+            if idx > start and message.get("role") == "user":
+                last_boundary = (idx, removed_tokens)
+                if removed_tokens >= tokens_to_remove:
+                    return last_boundary
+            removed_tokens += estimate_message_tokens(message)
+
+        return last_boundary
+
+    def estimate_session_prompt_tokens(self, session: Session) -> tuple[int, str]:
+        """Estimate current prompt size for the normal session history view."""
+        history = session.get_history(max_messages=0)
+        channel, chat_id = (session.key.split(":", 1) if ":" in session.key else (None, None))
+        probe_messages = self._build_messages(
+            history=history,
+            current_message="[token-probe]",
+            channel=channel,
+            chat_id=chat_id,
+        )
+        return estimate_prompt_tokens_chain(
+            self.provider,
+            self.model,
+            probe_messages,
+            self._get_tool_definitions(),
+        )
+
+    async def archive_unconsolidated(self, session: Session) -> bool:
+        """Archive the full unconsolidated tail for /new-style session rollover."""
+        lock = self.get_lock(session.key)
+        async with lock:
+            snapshot = session.messages[session.last_consolidated:]
+            if not snapshot:
+                return True
+            return await self.consolidate_messages(snapshot)
+
+    async def maybe_consolidate_by_tokens(self, session: Session) -> None:
+        """Loop: archive old messages until prompt fits within half the context window."""
+        if not session.messages or self.context_window_tokens <= 0:
+            return
+
+        lock = self.get_lock(session.key)
+        async with lock:
+            target = self.context_window_tokens // 2
+            estimated, source = self.estimate_session_prompt_tokens(session)
+            if estimated <= 0:
+                return
+            if estimated < self.context_window_tokens:
+                logger.debug(
+                    "Token consolidation idle {}: {}/{} via {}",
+                    session.key,
+                    estimated,
+                    self.context_window_tokens,
+                    source,
+                )
+                return
+
+            for round_num in range(self._MAX_CONSOLIDATION_ROUNDS):
+                if estimated <= target:
+                    return
+
+                boundary = self.pick_consolidation_boundary(session, max(1, estimated - target))
+                if boundary is None:
+                    logger.debug(
+                        "Token consolidation: no safe boundary for {} (round {})",
+                        session.key,
+                        round_num,
+                    )
+                    return
+
+                end_idx = boundary[0]
+                chunk = session.messages[session.last_consolidated:end_idx]
+                if not chunk:
+                    return
+
+                logger.info(
+                    "Token consolidation round {} for {}: {}/{} via {}, chunk={} msgs",
+                    round_num,
+                    session.key,
+                    estimated,
+                    self.context_window_tokens,
+                    source,
+                    len(chunk),
+                )
+                if not await self.consolidate_messages(chunk):
+                    return
+                session.last_consolidated = end_idx
+                self.sessions.save(session)
+
+                estimated, source = self.estimate_session_prompt_tokens(session)
+                if estimated <= 0:
+                    return

nanobot/channels/dingtalk.py

@@ -57,6 +57,8 @@ class NanobotDingTalkHandler(CallbackHandler):
             content = ""
             if chatbot_msg.text:
                 content = chatbot_msg.text.content.strip()
+            elif chatbot_msg.extensions.get("content", {}).get("recognition"):
+                content = chatbot_msg.extensions["content"]["recognition"].strip()
             if not content:
                 content = message.data.get("text", {}).get("content", "").strip()
 

nanobot/cli/commands.py

@@ -191,6 +191,8 @@ def onboard():
         save_config(Config())
         console.print(f"[green]✓[/green] Created config at {config_path}")
 
+    console.print("[dim]Config template now uses `maxTokens` + `contextWindowTokens`; `memoryWindow` is no longer a runtime setting.[/dim]")
+
     # Create workspace
     workspace = get_workspace_path()
 
@@ -283,6 +285,16 @@ def _load_runtime_config(config: str | None = None, workspace: str | None = None
     return loaded
 
 
+def _print_deprecated_memory_window_notice(config: Config) -> None:
+    """Warn when running with old memoryWindow-only config."""
+    if config.agents.defaults.should_warn_deprecated_memory_window:
+        console.print(
+            "[yellow]Hint:[/yellow] Detected deprecated `memoryWindow` without "
+            "`contextWindowTokens`. `memoryWindow` is ignored; run "
+            "[cyan]nanobot onboard[/cyan] to refresh your config template."
+        )
+
+
 # ============================================================================
 # Gateway / Server
 # ============================================================================
@@ -310,6 +322,7 @@ def gateway(
         logging.basicConfig(level=logging.DEBUG)
 
     config = _load_runtime_config(config, workspace)
+    _print_deprecated_memory_window_notice(config)
     port = port if port is not None else config.gateway.port
 
     console.print(f"{__logo__} Starting nanobot gateway on port {port}...")
@@ -331,8 +344,8 @@ def gateway(
         temperature=config.agents.defaults.temperature,
         max_tokens=config.agents.defaults.max_tokens,
         max_iterations=config.agents.defaults.max_tool_iterations,
-        memory_window=config.agents.defaults.memory_window,
         reasoning_effort=config.agents.defaults.reasoning_effort,
+        context_window_tokens=config.agents.defaults.context_window_tokens,
         brave_api_key=config.tools.web.search.api_key or None,
         web_proxy=config.tools.web.proxy or None,
         exec_config=config.tools.exec,
@@ -494,6 +507,7 @@ def agent(
     from nanobot.cron.service import CronService
 
     config = _load_runtime_config(config, workspace)
+    _print_deprecated_memory_window_notice(config)
     sync_workspace_templates(config.workspace_path)
 
     bus = MessageBus()
@@ -516,8 +530,8 @@ def agent(
         temperature=config.agents.defaults.temperature,
         max_tokens=config.agents.defaults.max_tokens,
         max_iterations=config.agents.defaults.max_tool_iterations,
-        memory_window=config.agents.defaults.memory_window,
         reasoning_effort=config.agents.defaults.reasoning_effort,
+        context_window_tokens=config.agents.defaults.context_window_tokens,
         brave_api_key=config.tools.web.search.api_key or None,
         web_proxy=config.tools.web.proxy or None,
         exec_config=config.tools.exec,

nanobot/config/schema.py

@@ -228,11 +228,18 @@ class AgentDefaults(Base):
         "auto"  # Provider name (e.g. "anthropic", "openrouter") or "auto" for auto-detection
     )
     max_tokens: int = 8192
+    context_window_tokens: int = 65_536
     temperature: float = 0.1
     max_tool_iterations: int = 40
-    memory_window: int = 100
+    # Deprecated compatibility field: accepted from old configs but ignored at runtime.
+    memory_window: int | None = Field(default=None, exclude=True)
     reasoning_effort: str | None = None  # low / medium / high — enables LLM thinking mode
 
+    @property
+    def should_warn_deprecated_memory_window(self) -> bool:
+        """Return True when old memoryWindow is present without contextWindowTokens."""
+        return self.memory_window is not None and "context_window_tokens" not in self.model_fields_set
+
 
 class AgentsConfig(Base):
     """Agent configuration."""

nanobot/utils/helpers.py

@@ -1,8 +1,12 @@
 """Utility functions for nanobot."""
 
+import json
 import re
 from datetime import datetime
 from pathlib import Path
+from typing import Any
+
+import tiktoken
 
 
 def detect_image_mime(data: bytes) -> str | None:
@@ -68,6 +72,87 @@ def split_message(content: str, max_len: int = 2000) -> list[str]:
     return chunks
 
 
+def estimate_prompt_tokens(
+    messages: list[dict[str, Any]],
+    tools: list[dict[str, Any]] | None = None,
+) -> int:
+    """Estimate prompt tokens with tiktoken."""
+    try:
+        enc = tiktoken.get_encoding("cl100k_base")
+        parts: list[str] = []
+        for msg in messages:
+            content = msg.get("content")
+            if isinstance(content, str):
+                parts.append(content)
+            elif isinstance(content, list):
+                for part in content:
+                    if isinstance(part, dict) and part.get("type") == "text":
+                        txt = part.get("text", "")
+                        if txt:
+                            parts.append(txt)
+        if tools:
+            parts.append(json.dumps(tools, ensure_ascii=False))
+        return len(enc.encode("\n".join(parts)))
+    except Exception:
+        return 0
+
+
+def estimate_message_tokens(message: dict[str, Any]) -> int:
+    """Estimate prompt tokens contributed by one persisted message."""
+    content = message.get("content")
+    parts: list[str] = []
+    if isinstance(content, str):
+        parts.append(content)
+    elif isinstance(content, list):
+        for part in content:
+            if isinstance(part, dict) and part.get("type") == "text":
+                text = part.get("text", "")
+                if text:
+                    parts.append(text)
+            else:
+                parts.append(json.dumps(part, ensure_ascii=False))
+    elif content is not None:
+        parts.append(json.dumps(content, ensure_ascii=False))
+
+    for key in ("name", "tool_call_id"):
+        value = message.get(key)
+        if isinstance(value, str) and value:
+            parts.append(value)
+    if message.get("tool_calls"):
+        parts.append(json.dumps(message["tool_calls"], ensure_ascii=False))
+
+    payload = "\n".join(parts)
+    if not payload:
+        return 1
+    try:
+        enc = tiktoken.get_encoding("cl100k_base")
+        return max(1, len(enc.encode(payload)))
+    except Exception:
+        return max(1, len(payload) // 4)
+
+
+def estimate_prompt_tokens_chain(
+    provider: Any,
+    model: str | None,
+    messages: list[dict[str, Any]],
+    tools: list[dict[str, Any]] | None = None,
+) -> tuple[int, str]:
+    """Estimate prompt tokens via provider counter first, then tiktoken fallback."""
+    provider_counter = getattr(provider, "estimate_prompt_tokens", None)
+    if callable(provider_counter):
+        try:
+            tokens, source = provider_counter(messages, tools, model)
+            if isinstance(tokens, (int, float)) and tokens > 0:
+                return int(tokens), str(source or "provider_counter")
+        except Exception:
+            pass
+
+    estimated = estimate_prompt_tokens(messages, tools)
+    if estimated > 0:
+        return int(estimated), "tiktoken"
+    return 0, "none"
+
+
 def sync_workspace_templates(workspace: Path, silent: bool = False) -> list[str]:
     """Sync bundled templates to workspace. Only creates missing files."""
     from importlib.resources import files as pkg_files

pyproject.toml

@@ -18,7 +18,7 @@ classifiers = [
 
 dependencies = [
     "typer>=0.20.0,<1.0.0",
-    "litellm>=1.81.5,<2.0.0",
+    "litellm>=1.82.1,<2.0.0",
     "pydantic>=2.12.0,<3.0.0",
     "pydantic-settings>=2.12.0,<3.0.0",
     "websockets>=16.0,<17.0",
@@ -44,6 +44,7 @@ dependencies = [
     "json-repair>=0.57.0,<1.0.0",
     "chardet>=3.0.2,<6.0.0",
     "openai>=2.8.0",
+    "tiktoken>=0.12.0,<1.0.0",
 ]
 
 [project.optional-dependencies]

tests/test_commands.py

@@ -267,6 +267,16 @@ def test_agent_workspace_override_wins_over_config_workspace(mock_agent_runtime,
     assert mock_agent_runtime["agent_loop_cls"].call_args.kwargs["workspace"] == workspace_path
 
 
+def test_agent_warns_about_deprecated_memory_window(mock_agent_runtime):
+    mock_agent_runtime["config"].agents.defaults.memory_window = 100
+
+    result = runner.invoke(app, ["agent", "-m", "hello"])
+
+    assert result.exit_code == 0
+    assert "memoryWindow" in result.stdout
+    assert "contextWindowTokens" in result.stdout
+
+
 def test_gateway_uses_workspace_from_config_by_default(monkeypatch, tmp_path: Path) -> None:
     config_file = tmp_path / "instance" / "config.json"
     config_file.parent.mkdir(parents=True)
@@ -327,6 +337,29 @@ def test_gateway_workspace_option_overrides_config(monkeypatch, tmp_path: Path)
     assert seen["workspace"] == override
     assert config.workspace_path == override
 
+
+def test_gateway_warns_about_deprecated_memory_window(monkeypatch, tmp_path: Path) -> None:
+    config_file = tmp_path / "instance" / "config.json"
+    config_file.parent.mkdir(parents=True)
+    config_file.write_text("{}")
+
+    config = Config()
+    config.agents.defaults.memory_window = 100
+
+    monkeypatch.setattr("nanobot.config.loader.set_config_path", lambda _path: None)
+    monkeypatch.setattr("nanobot.config.loader.load_config", lambda _path=None: config)
+    monkeypatch.setattr("nanobot.cli.commands.sync_workspace_templates", lambda _path: None)
+    monkeypatch.setattr(
+        "nanobot.cli.commands._make_provider",
+        lambda _config: (_ for _ in ()).throw(_StopGateway("stop")),
+    )
+
+    result = runner.invoke(app, ["gateway", "--config", str(config_file)])
+
+    assert isinstance(result.exception, _StopGateway)
+    assert "memoryWindow" in result.stdout
+    assert "contextWindowTokens" in result.stdout
+
 def test_gateway_uses_config_directory_for_cron_store(monkeypatch, tmp_path: Path) -> None:
     config_file = tmp_path / "instance" / "config.json"
     config_file.parent.mkdir(parents=True)

tests/test_config_migration.py

@@ -0,0 +1,88 @@
+import json
+
+from typer.testing import CliRunner
+
+from nanobot.cli.commands import app
+from nanobot.config.loader import load_config, save_config
+
+runner = CliRunner()
+
+
+def test_load_config_keeps_max_tokens_and_warns_on_legacy_memory_window(tmp_path) -> None:
+    config_path = tmp_path / "config.json"
+    config_path.write_text(
+        json.dumps(
+            {
+                "agents": {
+                    "defaults": {
+                        "maxTokens": 1234,
+                        "memoryWindow": 42,
+                    }
+                }
+            }
+        ),
+        encoding="utf-8",
+    )
+
+    config = load_config(config_path)
+
+    assert config.agents.defaults.max_tokens == 1234
+    assert config.agents.defaults.context_window_tokens == 65_536
+    assert config.agents.defaults.should_warn_deprecated_memory_window is True
+
+
+def test_save_config_writes_context_window_tokens_but_not_memory_window(tmp_path) -> None:
+    config_path = tmp_path / "config.json"
+    config_path.write_text(
+        json.dumps(
+            {
+                "agents": {
+                    "defaults": {
+                        "maxTokens": 2222,
+                        "memoryWindow": 30,
+                    }
+                }
+            }
+        ),
+        encoding="utf-8",
+    )
+
+    config = load_config(config_path)
+    save_config(config, config_path)
+    saved = json.loads(config_path.read_text(encoding="utf-8"))
+    defaults = saved["agents"]["defaults"]
+
+    assert defaults["maxTokens"] == 2222
+    assert defaults["contextWindowTokens"] == 65_536
+    assert "memoryWindow" not in defaults
+
+
+def test_onboard_refresh_rewrites_legacy_config_template(tmp_path, monkeypatch) -> None:
+    config_path = tmp_path / "config.json"
+    workspace = tmp_path / "workspace"
+    config_path.write_text(
+        json.dumps(
+            {
+                "agents": {
+                    "defaults": {
+                        "maxTokens": 3333,
+                        "memoryWindow": 50,
+                    }
+                }
+            }
+        ),
+        encoding="utf-8",
+    )
+
+    monkeypatch.setattr("nanobot.config.loader.get_config_path", lambda: config_path)
+    monkeypatch.setattr("nanobot.cli.commands.get_workspace_path", lambda: workspace)
+
+    result = runner.invoke(app, ["onboard"], input="n\n")
+
+    assert result.exit_code == 0
+    assert "contextWindowTokens" in result.stdout
+    saved = json.loads(config_path.read_text(encoding="utf-8"))
+    defaults = saved["agents"]["defaults"]
+    assert defaults["maxTokens"] == 3333
+    assert defaults["contextWindowTokens"] == 65_536
+    assert "memoryWindow" not in defaults

tests/test_consolidate_offset.py

@@ -480,226 +480,35 @@ class TestEmptyAndBoundarySessions:
         assert_messages_content(old_messages, 10, 34)
 
 
-class TestConsolidationDeduplicationGuard:
+class TestNewCommandArchival:
-    """Test that consolidation tasks are deduplicated and serialized."""
+    """Test /new archival behavior with the simplified consolidation flow."""
 
-    @pytest.mark.asyncio
+    @staticmethod
-    async def test_consolidation_guard_prevents_duplicate_tasks(self, tmp_path: Path) -> None:
+    def _make_loop(tmp_path: Path):
-        """Concurrent messages above memory_window spawn only one consolidation task."""
         from nanobot.agent.loop import AgentLoop
-        from nanobot.bus.events import InboundMessage
         from nanobot.bus.queue import MessageBus
         from nanobot.providers.base import LLMResponse
 
         bus = MessageBus()
         provider = MagicMock()
         provider.get_default_model.return_value = "test-model"
+        provider.estimate_prompt_tokens.return_value = (10_000, "test")
         loop = AgentLoop(
-            bus=bus, provider=provider, workspace=tmp_path, model="test-model", memory_window=10
+            bus=bus,
+            provider=provider,
+            workspace=tmp_path,
+            model="test-model",
+            context_window_tokens=1,
         )
-
+        loop.provider.chat_with_retry = AsyncMock(return_value=LLMResponse(content="ok", tool_calls=[]))
-        loop.provider.chat = AsyncMock(return_value=LLMResponse(content="ok", tool_calls=[]))
         loop.tools.get_definitions = MagicMock(return_value=[])
-
+        return loop
-        session = loop.sessions.get_or_create("cli:test")
-        for i in range(15):
-            session.add_message("user", f"msg{i}")
-            session.add_message("assistant", f"resp{i}")
-        loop.sessions.save(session)
-
-        consolidation_calls = 0
-
-        async def _fake_consolidate(_session, archive_all: bool = False) -> None:
-            nonlocal consolidation_calls
-            consolidation_calls += 1
-            await asyncio.sleep(0.05)
-
-        loop._consolidate_memory = _fake_consolidate  # type: ignore[method-assign]
-
-        msg = InboundMessage(channel="cli", sender_id="user", chat_id="test", content="hello")
-        await loop._process_message(msg)
-        await loop._process_message(msg)
-        await asyncio.sleep(0.1)
-
-        assert consolidation_calls == 1, (
-            f"Expected exactly 1 consolidation, got {consolidation_calls}"
-        )
-
-    @pytest.mark.asyncio
-    async def test_new_command_guard_prevents_concurrent_consolidation(
-        self, tmp_path: Path
-    ) -> None:
-        """/new command does not run consolidation concurrently with in-flight consolidation."""
-        from nanobot.agent.loop import AgentLoop
-        from nanobot.bus.events import InboundMessage
-        from nanobot.bus.queue import MessageBus
-        from nanobot.providers.base import LLMResponse
-
-        bus = MessageBus()
-        provider = MagicMock()
-        provider.get_default_model.return_value = "test-model"
-        loop = AgentLoop(
-            bus=bus, provider=provider, workspace=tmp_path, model="test-model", memory_window=10
-        )
-
-        loop.provider.chat = AsyncMock(return_value=LLMResponse(content="ok", tool_calls=[]))
-        loop.tools.get_definitions = MagicMock(return_value=[])
-
-        session = loop.sessions.get_or_create("cli:test")
-        for i in range(15):
-            session.add_message("user", f"msg{i}")
-            session.add_message("assistant", f"resp{i}")
-        loop.sessions.save(session)
-
-        consolidation_calls = 0
-        active = 0
-        max_active = 0
-
-        async def _fake_consolidate(_session, archive_all: bool = False) -> None:
-            nonlocal consolidation_calls, active, max_active
-            consolidation_calls += 1
-            active += 1
-            max_active = max(max_active, active)
-            await asyncio.sleep(0.05)
-            active -= 1
-
-        loop._consolidate_memory = _fake_consolidate  # type: ignore[method-assign]
-
-        msg = InboundMessage(channel="cli", sender_id="user", chat_id="test", content="hello")
-        await loop._process_message(msg)
-
-        new_msg = InboundMessage(channel="cli", sender_id="user", chat_id="test", content="/new")
-        await loop._process_message(new_msg)
-        await asyncio.sleep(0.1)
-
-        assert consolidation_calls == 2, (
-            f"Expected normal + /new consolidations, got {consolidation_calls}"
-        )
-        assert max_active == 1, (
-            f"Expected serialized consolidation, observed concurrency={max_active}"
-        )
-
-    @pytest.mark.asyncio
-    async def test_consolidation_tasks_are_referenced(self, tmp_path: Path) -> None:
-        """create_task results are tracked in _consolidation_tasks while in flight."""
-        from nanobot.agent.loop import AgentLoop
-        from nanobot.bus.events import InboundMessage
-        from nanobot.bus.queue import MessageBus
-        from nanobot.providers.base import LLMResponse
-
-        bus = MessageBus()
-        provider = MagicMock()
-        provider.get_default_model.return_value = "test-model"
-        loop = AgentLoop(
-            bus=bus, provider=provider, workspace=tmp_path, model="test-model", memory_window=10
-        )
-
-        loop.provider.chat = AsyncMock(return_value=LLMResponse(content="ok", tool_calls=[]))
-        loop.tools.get_definitions = MagicMock(return_value=[])
-
-        session = loop.sessions.get_or_create("cli:test")
-        for i in range(15):
-            session.add_message("user", f"msg{i}")
-            session.add_message("assistant", f"resp{i}")
-        loop.sessions.save(session)
-
-        started = asyncio.Event()
-
-        async def _slow_consolidate(_session, archive_all: bool = False) -> None:
-            started.set()
-            await asyncio.sleep(0.1)
-
-        loop._consolidate_memory = _slow_consolidate  # type: ignore[method-assign]
-
-        msg = InboundMessage(channel="cli", sender_id="user", chat_id="test", content="hello")
-        await loop._process_message(msg)
-
-        await started.wait()
-        assert len(loop._consolidation_tasks) == 1, "Task must be referenced while in-flight"
-
-        await asyncio.sleep(0.15)
-        assert len(loop._consolidation_tasks) == 0, (
-            "Task reference must be removed after completion"
-        )
-
-    @pytest.mark.asyncio
-    async def test_new_waits_for_inflight_consolidation_and_preserves_messages(
-        self, tmp_path: Path
-    ) -> None:
-        """/new waits for in-flight consolidation and archives before clear."""
-        from nanobot.agent.loop import AgentLoop
-        from nanobot.bus.events import InboundMessage
-        from nanobot.bus.queue import MessageBus
-        from nanobot.providers.base import LLMResponse
-
-        bus = MessageBus()
-        provider = MagicMock()
-        provider.get_default_model.return_value = "test-model"
-        loop = AgentLoop(
-            bus=bus, provider=provider, workspace=tmp_path, model="test-model", memory_window=10
-        )
-
-        loop.provider.chat = AsyncMock(return_value=LLMResponse(content="ok", tool_calls=[]))
-        loop.tools.get_definitions = MagicMock(return_value=[])
-
-        session = loop.sessions.get_or_create("cli:test")
-        for i in range(15):
-            session.add_message("user", f"msg{i}")
-            session.add_message("assistant", f"resp{i}")
-        loop.sessions.save(session)
-
-        started = asyncio.Event()
-        release = asyncio.Event()
-        archived_count = 0
-
-        async def _fake_consolidate(sess, archive_all: bool = False) -> bool:
-            nonlocal archived_count
-            if archive_all:
-                archived_count = len(sess.messages)
-                return True
-            started.set()
-            await release.wait()
-            return True
-
-        loop._consolidate_memory = _fake_consolidate  # type: ignore[method-assign]
-
-        msg = InboundMessage(channel="cli", sender_id="user", chat_id="test", content="hello")
-        await loop._process_message(msg)
-        await started.wait()
-
-        new_msg = InboundMessage(channel="cli", sender_id="user", chat_id="test", content="/new")
-        pending_new = asyncio.create_task(loop._process_message(new_msg))
-
-        await asyncio.sleep(0.02)
-        assert not pending_new.done(), "/new should wait while consolidation is in-flight"
-
-        release.set()
-        response = await pending_new
-        assert response is not None
-        assert "new session started" in response.content.lower()
-        assert archived_count > 0, "Expected /new archival to process a non-empty snapshot"
-
-        session_after = loop.sessions.get_or_create("cli:test")
-        assert session_after.messages == [], "Session should be cleared after successful archival"
 
     @pytest.mark.asyncio
     async def test_new_does_not_clear_session_when_archive_fails(self, tmp_path: Path) -> None:
-        """/new must keep session data if archive step reports failure."""
-        from nanobot.agent.loop import AgentLoop
         from nanobot.bus.events import InboundMessage
-        from nanobot.bus.queue import MessageBus
-        from nanobot.providers.base import LLMResponse
-
-        bus = MessageBus()
-        provider = MagicMock()
-        provider.get_default_model.return_value = "test-model"
-        loop = AgentLoop(
-            bus=bus, provider=provider, workspace=tmp_path, model="test-model", memory_window=10
-        )
-
-        loop.provider.chat = AsyncMock(return_value=LLMResponse(content="ok", tool_calls=[]))
-        loop.tools.get_definitions = MagicMock(return_value=[])
 
+        loop = self._make_loop(tmp_path)
         session = loop.sessions.get_or_create("cli:test")
         for i in range(5):
             session.add_message("user", f"msg{i}")
@@ -707,111 +516,61 @@ class TestConsolidationDeduplicationGuard:
         loop.sessions.save(session)
         before_count = len(session.messages)
 
-        async def _failing_consolidate(sess, archive_all: bool = False) -> bool:
+        async def _failing_consolidate(_messages) -> bool:
-            if archive_all:
+            return False
-                return False
-            return True
 
-        loop._consolidate_memory = _failing_consolidate  # type: ignore[method-assign]
+        loop.memory_consolidator.consolidate_messages = _failing_consolidate  # type: ignore[method-assign]
 
         new_msg = InboundMessage(channel="cli", sender_id="user", chat_id="test", content="/new")
         response = await loop._process_message(new_msg)
 
         assert response is not None
         assert "failed" in response.content.lower()
-        session_after = loop.sessions.get_or_create("cli:test")
+        assert len(loop.sessions.get_or_create("cli:test").messages) == before_count
-        assert len(session_after.messages) == before_count, (
-            "Session must remain intact when /new archival fails"
-        )
 
     @pytest.mark.asyncio
-    async def test_new_archives_only_unconsolidated_messages_after_inflight_task(
+    async def test_new_archives_only_unconsolidated_messages(self, tmp_path: Path) -> None:
-        self, tmp_path: Path
-    ) -> None:
-        """/new should archive only messages not yet consolidated by prior task."""
-        from nanobot.agent.loop import AgentLoop
         from nanobot.bus.events import InboundMessage
-        from nanobot.bus.queue import MessageBus
-        from nanobot.providers.base import LLMResponse
-
-        bus = MessageBus()
-        provider = MagicMock()
-        provider.get_default_model.return_value = "test-model"
-        loop = AgentLoop(
-            bus=bus, provider=provider, workspace=tmp_path, model="test-model", memory_window=10
-        )
-
-        loop.provider.chat = AsyncMock(return_value=LLMResponse(content="ok", tool_calls=[]))
-        loop.tools.get_definitions = MagicMock(return_value=[])
 
+        loop = self._make_loop(tmp_path)
         session = loop.sessions.get_or_create("cli:test")
         for i in range(15):
             session.add_message("user", f"msg{i}")
             session.add_message("assistant", f"resp{i}")
+        session.last_consolidated = len(session.messages) - 3
         loop.sessions.save(session)
 
-        started = asyncio.Event()
-        release = asyncio.Event()
         archived_count = -1
 
-        async def _fake_consolidate(sess, archive_all: bool = False) -> bool:
+        async def _fake_consolidate(messages) -> bool:
             nonlocal archived_count
-            if archive_all:
+            archived_count = len(messages)
-                archived_count = len(sess.messages)
-                return True
-
-            started.set()
-            await release.wait()
-            sess.last_consolidated = len(sess.messages) - 3
             return True
 
-        loop._consolidate_memory = _fake_consolidate  # type: ignore[method-assign]
+        loop.memory_consolidator.consolidate_messages = _fake_consolidate  # type: ignore[method-assign]
-
-        msg = InboundMessage(channel="cli", sender_id="user", chat_id="test", content="hello")
-        await loop._process_message(msg)
-        await started.wait()
 
         new_msg = InboundMessage(channel="cli", sender_id="user", chat_id="test", content="/new")
-        pending_new = asyncio.create_task(loop._process_message(new_msg))
+        response = await loop._process_message(new_msg)
-        await asyncio.sleep(0.02)
-        assert not pending_new.done()
-
-        release.set()
-        response = await pending_new
 
         assert response is not None
         assert "new session started" in response.content.lower()
-        assert archived_count == 3, (
+        assert archived_count == 3
-            f"Expected only unconsolidated tail to archive, got {archived_count}"
-        )
 
     @pytest.mark.asyncio
     async def test_new_clears_session_and_responds(self, tmp_path: Path) -> None:
-        """/new clears session and returns confirmation."""
-        from nanobot.agent.loop import AgentLoop
         from nanobot.bus.events import InboundMessage
-        from nanobot.bus.queue import MessageBus
-        from nanobot.providers.base import LLMResponse
-
-        bus = MessageBus()
-        provider = MagicMock()
-        provider.get_default_model.return_value = "test-model"
-        loop = AgentLoop(
-            bus=bus, provider=provider, workspace=tmp_path, model="test-model", memory_window=10
-        )
-        loop.provider.chat = AsyncMock(return_value=LLMResponse(content="ok", tool_calls=[]))
-        loop.tools.get_definitions = MagicMock(return_value=[])
 
+        loop = self._make_loop(tmp_path)
         session = loop.sessions.get_or_create("cli:test")
         for i in range(3):
             session.add_message("user", f"msg{i}")
             session.add_message("assistant", f"resp{i}")
         loop.sessions.save(session)
 
-        async def _ok_consolidate(sess, archive_all: bool = False) -> bool:
+        async def _ok_consolidate(_messages) -> bool:
             return True
 
-        loop._consolidate_memory = _ok_consolidate  # type: ignore[method-assign]
+        loop.memory_consolidator.consolidate_messages = _ok_consolidate  # type: ignore[method-assign]
 
         new_msg = InboundMessage(channel="cli", sender_id="user", chat_id="test", content="/new")
         response = await loop._process_message(new_msg)

tests/test_dingtalk_channel.py

@@ -1,9 +1,11 @@
+import asyncio
 from types import SimpleNamespace
 
 import pytest
 
 from nanobot.bus.queue import MessageBus
-from nanobot.channels.dingtalk import DingTalkChannel
+import nanobot.channels.dingtalk as dingtalk_module
+from nanobot.channels.dingtalk import DingTalkChannel, NanobotDingTalkHandler
 from nanobot.config.schema import DingTalkConfig
 
 
@@ -64,3 +66,46 @@ async def test_group_send_uses_group_messages_api() -> None:
     assert call["url"] == "https://api.dingtalk.com/v1.0/robot/groupMessages/send"
     assert call["json"]["openConversationId"] == "conv123"
     assert call["json"]["msgKey"] == "sampleMarkdown"
+
+
+@pytest.mark.asyncio
+async def test_handler_uses_voice_recognition_text_when_text_is_empty(monkeypatch) -> None:
+    bus = MessageBus()
+    channel = DingTalkChannel(
+        DingTalkConfig(client_id="app", client_secret="secret", allow_from=["user1"]),
+        bus,
+    )
+    handler = NanobotDingTalkHandler(channel)
+
+    class _FakeChatbotMessage:
+        text = None
+        extensions = {"content": {"recognition": "voice transcript"}}
+        sender_staff_id = "user1"
+        sender_id = "fallback-user"
+        sender_nick = "Alice"
+        message_type = "audio"
+
+        @staticmethod
+        def from_dict(_data):
+            return _FakeChatbotMessage()
+
+    monkeypatch.setattr(dingtalk_module, "ChatbotMessage", _FakeChatbotMessage)
+    monkeypatch.setattr(dingtalk_module, "AckMessage", SimpleNamespace(STATUS_OK="OK"))
+
+    status, body = await handler.process(
+        SimpleNamespace(
+            data={
+                "conversationType": "2",
+                "conversationId": "conv123",
+                "text": {"content": ""},
+            }
+        )
+    )
+
+    await asyncio.gather(*list(channel._background_tasks))
+    msg = await bus.consume_inbound()
+
+    assert (status, body) == ("OK", "OK")
+    assert msg.content == "voice transcript"
+    assert msg.sender_id == "user1"
+    assert msg.chat_id == "group:conv123"

tests/test_loop_consolidation_tokens.py

@@ -0,0 +1,190 @@
+from unittest.mock import AsyncMock, MagicMock
+
+import pytest
+
+from nanobot.agent.loop import AgentLoop
+import nanobot.agent.memory as memory_module
+from nanobot.bus.queue import MessageBus
+from nanobot.providers.base import LLMResponse
+
+
+def _make_loop(tmp_path, *, estimated_tokens: int, context_window_tokens: int) -> AgentLoop:
+    provider = MagicMock()
+    provider.get_default_model.return_value = "test-model"
+    provider.estimate_prompt_tokens.return_value = (estimated_tokens, "test-counter")
+    provider.chat_with_retry = AsyncMock(return_value=LLMResponse(content="ok", tool_calls=[]))
+
+    loop = AgentLoop(
+        bus=MessageBus(),
+        provider=provider,
+        workspace=tmp_path,
+        model="test-model",
+        context_window_tokens=context_window_tokens,
+    )
+    loop.tools.get_definitions = MagicMock(return_value=[])
+    return loop
+
+
+@pytest.mark.asyncio
+async def test_prompt_below_threshold_does_not_consolidate(tmp_path) -> None:
+    loop = _make_loop(tmp_path, estimated_tokens=100, context_window_tokens=200)
+    loop.memory_consolidator.consolidate_messages = AsyncMock(return_value=True)  # type: ignore[method-assign]
+
+    await loop.process_direct("hello", session_key="cli:test")
+
+    loop.memory_consolidator.consolidate_messages.assert_not_awaited()
+
+
+@pytest.mark.asyncio
+async def test_prompt_above_threshold_triggers_consolidation(tmp_path, monkeypatch) -> None:
+    loop = _make_loop(tmp_path, estimated_tokens=1000, context_window_tokens=200)
+    loop.memory_consolidator.consolidate_messages = AsyncMock(return_value=True)  # type: ignore[method-assign]
+    session = loop.sessions.get_or_create("cli:test")
+    session.messages = [
+        {"role": "user", "content": "u1", "timestamp": "2026-01-01T00:00:00"},
+        {"role": "assistant", "content": "a1", "timestamp": "2026-01-01T00:00:01"},
+        {"role": "user", "content": "u2", "timestamp": "2026-01-01T00:00:02"},
+    ]
+    loop.sessions.save(session)
+    monkeypatch.setattr(memory_module, "estimate_message_tokens", lambda _message: 500)
+
+    await loop.process_direct("hello", session_key="cli:test")
+
+    assert loop.memory_consolidator.consolidate_messages.await_count >= 1
+
+
+@pytest.mark.asyncio
+async def test_prompt_above_threshold_archives_until_next_user_boundary(tmp_path, monkeypatch) -> None:
+    loop = _make_loop(tmp_path, estimated_tokens=1000, context_window_tokens=200)
+    loop.memory_consolidator.consolidate_messages = AsyncMock(return_value=True)  # type: ignore[method-assign]
+
+    session = loop.sessions.get_or_create("cli:test")
+    session.messages = [
+        {"role": "user", "content": "u1", "timestamp": "2026-01-01T00:00:00"},
+        {"role": "assistant", "content": "a1", "timestamp": "2026-01-01T00:00:01"},
+        {"role": "user", "content": "u2", "timestamp": "2026-01-01T00:00:02"},
+        {"role": "assistant", "content": "a2", "timestamp": "2026-01-01T00:00:03"},
+        {"role": "user", "content": "u3", "timestamp": "2026-01-01T00:00:04"},
+    ]
+    loop.sessions.save(session)
+
+    token_map = {"u1": 120, "a1": 120, "u2": 120, "a2": 120, "u3": 120}
+    monkeypatch.setattr(memory_module, "estimate_message_tokens", lambda message: token_map[message["content"]])
+
+    await loop.memory_consolidator.maybe_consolidate_by_tokens(session)
+
+    archived_chunk = loop.memory_consolidator.consolidate_messages.await_args.args[0]
+    assert [message["content"] for message in archived_chunk] == ["u1", "a1", "u2", "a2"]
+    assert session.last_consolidated == 4
+
+
+@pytest.mark.asyncio
+async def test_consolidation_loops_until_target_met(tmp_path, monkeypatch) -> None:
+    """Verify maybe_consolidate_by_tokens keeps looping until under threshold."""
+    loop = _make_loop(tmp_path, estimated_tokens=0, context_window_tokens=200)
+    loop.memory_consolidator.consolidate_messages = AsyncMock(return_value=True)  # type: ignore[method-assign]
+
+    session = loop.sessions.get_or_create("cli:test")
+    session.messages = [
+        {"role": "user", "content": "u1", "timestamp": "2026-01-01T00:00:00"},
+        {"role": "assistant", "content": "a1", "timestamp": "2026-01-01T00:00:01"},
+        {"role": "user", "content": "u2", "timestamp": "2026-01-01T00:00:02"},
+        {"role": "assistant", "content": "a2", "timestamp": "2026-01-01T00:00:03"},
+        {"role": "user", "content": "u3", "timestamp": "2026-01-01T00:00:04"},
+        {"role": "assistant", "content": "a3", "timestamp": "2026-01-01T00:00:05"},
+        {"role": "user", "content": "u4", "timestamp": "2026-01-01T00:00:06"},
+    ]
+    loop.sessions.save(session)
+
+    call_count = [0]
+    def mock_estimate(_session):
+        call_count[0] += 1
+        if call_count[0] == 1:
+            return (500, "test")
+        if call_count[0] == 2:
+            return (300, "test")
+        return (80, "test")
+
+    loop.memory_consolidator.estimate_session_prompt_tokens = mock_estimate  # type: ignore[method-assign]
+    monkeypatch.setattr(memory_module, "estimate_message_tokens", lambda _m: 100)
+
+    await loop.memory_consolidator.maybe_consolidate_by_tokens(session)
+
+    assert loop.memory_consolidator.consolidate_messages.await_count == 2
+    assert session.last_consolidated == 6
+
+
+@pytest.mark.asyncio
+async def test_consolidation_continues_below_trigger_until_half_target(tmp_path, monkeypatch) -> None:
+    """Once triggered, consolidation should continue until it drops below half threshold."""
+    loop = _make_loop(tmp_path, estimated_tokens=0, context_window_tokens=200)
+    loop.memory_consolidator.consolidate_messages = AsyncMock(return_value=True)  # type: ignore[method-assign]
+
+    session = loop.sessions.get_or_create("cli:test")
+    session.messages = [
+        {"role": "user", "content": "u1", "timestamp": "2026-01-01T00:00:00"},
+        {"role": "assistant", "content": "a1", "timestamp": "2026-01-01T00:00:01"},
+        {"role": "user", "content": "u2", "timestamp": "2026-01-01T00:00:02"},
+        {"role": "assistant", "content": "a2", "timestamp": "2026-01-01T00:00:03"},
+        {"role": "user", "content": "u3", "timestamp": "2026-01-01T00:00:04"},
+        {"role": "assistant", "content": "a3", "timestamp": "2026-01-01T00:00:05"},
+        {"role": "user", "content": "u4", "timestamp": "2026-01-01T00:00:06"},
+    ]
+    loop.sessions.save(session)
+
+    call_count = [0]
+
+    def mock_estimate(_session):
+        call_count[0] += 1
+        if call_count[0] == 1:
+            return (500, "test")
+        if call_count[0] == 2:
+            return (150, "test")
+        return (80, "test")
+
+    loop.memory_consolidator.estimate_session_prompt_tokens = mock_estimate  # type: ignore[method-assign]
+    monkeypatch.setattr(memory_module, "estimate_message_tokens", lambda _m: 100)
+
+    await loop.memory_consolidator.maybe_consolidate_by_tokens(session)
+
+    assert loop.memory_consolidator.consolidate_messages.await_count == 2
+    assert session.last_consolidated == 6
+
+
+@pytest.mark.asyncio
+async def test_preflight_consolidation_before_llm_call(tmp_path, monkeypatch) -> None:
+    """Verify preflight consolidation runs before the LLM call in process_direct."""
+    order: list[str] = []
+
+    loop = _make_loop(tmp_path, estimated_tokens=0, context_window_tokens=200)
+
+    async def track_consolidate(messages):
+        order.append("consolidate")
+        return True
+    loop.memory_consolidator.consolidate_messages = track_consolidate  # type: ignore[method-assign]
+
+    async def track_llm(*args, **kwargs):
+        order.append("llm")
+        return LLMResponse(content="ok", tool_calls=[])
+    loop.provider.chat_with_retry = track_llm
+
+    session = loop.sessions.get_or_create("cli:test")
+    session.messages = [
+        {"role": "user", "content": "u1", "timestamp": "2026-01-01T00:00:00"},
+        {"role": "assistant", "content": "a1", "timestamp": "2026-01-01T00:00:01"},
+        {"role": "user", "content": "u2", "timestamp": "2026-01-01T00:00:02"},
+    ]
+    loop.sessions.save(session)
+    monkeypatch.setattr(memory_module, "estimate_message_tokens", lambda _m: 500)
+
+    call_count = [0]
+    def mock_estimate(_session):
+        call_count[0] += 1
+        return (1000 if call_count[0] <= 1 else 80, "test")
+    loop.memory_consolidator.estimate_session_prompt_tokens = mock_estimate  # type: ignore[method-assign]
+
+    await loop.process_direct("hello", session_key="cli:test")
+
+    assert "consolidate" in order
+    assert "llm" in order
+    assert order.index("consolidate") < order.index("llm")

tests/test_memory_consolidation_types.py

@@ -7,7 +7,7 @@ tool call response, it should serialize them to JSON instead of raising TypeErro
 
 import json
 from pathlib import Path
-from unittest.mock import AsyncMock, MagicMock
+from unittest.mock import AsyncMock
 
 import pytest
 
@@ -15,15 +15,12 @@ from nanobot.agent.memory import MemoryStore
 from nanobot.providers.base import LLMProvider, LLMResponse, ToolCallRequest
 
 
-def _make_session(message_count: int = 30, memory_window: int = 50):
+def _make_messages(message_count: int = 30):
-    """Create a mock session with messages."""
+    """Create a list of mock messages."""
-    session = MagicMock()
+    return [
-    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):
@@ -74,9 +71,9 @@ class TestMemoryConsolidationTypeHandling:
             )
         )
         provider.chat_with_retry = provider.chat
-        session = _make_session(message_count=60)
+        messages = _make_messages(message_count=60)
 
-        result = await store.consolidate(session, provider, "test-model", memory_window=50)
+        result = await store.consolidate(messages, provider, "test-model")
 
         assert result is True
         assert store.history_file.exists()
@@ -95,9 +92,9 @@ class TestMemoryConsolidationTypeHandling:
             )
         )
         provider.chat_with_retry = provider.chat
-        session = _make_session(message_count=60)
+        messages = _make_messages(message_count=60)
 
-        result = await store.consolidate(session, provider, "test-model", memory_window=50)
+        result = await store.consolidate(messages, provider, "test-model")
 
         assert result is True
         assert store.history_file.exists()
@@ -131,9 +128,9 @@ class TestMemoryConsolidationTypeHandling:
         )
         provider.chat = AsyncMock(return_value=response)
         provider.chat_with_retry = provider.chat
-        session = _make_session(message_count=60)
+        messages = _make_messages(message_count=60)
 
-        result = await store.consolidate(session, provider, "test-model", memory_window=50)
+        result = await store.consolidate(messages, provider, "test-model")
 
         assert result is True
         assert "User discussed testing." in store.history_file.read_text()
@@ -147,22 +144,22 @@ class TestMemoryConsolidationTypeHandling:
             return_value=LLMResponse(content="I summarized the conversation.", tool_calls=[])
         )
         provider.chat_with_retry = provider.chat
-        session = _make_session(message_count=60)
+        messages = _make_messages(message_count=60)
 
-        result = await store.consolidate(session, provider, "test-model", memory_window=50)
+        result = await store.consolidate(messages, provider, "test-model")
 
         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:
+    async def test_skips_when_message_chunk_is_empty(self, tmp_path: Path) -> None:
-        """Consolidation should be a no-op when messages < keep_count."""
+        """Consolidation should be a no-op when the selected chunk is empty."""
         store = MemoryStore(tmp_path)
         provider = AsyncMock()
         provider.chat_with_retry = provider.chat
-        session = _make_session(message_count=10)
+        messages: list[dict] = []
 
-        result = await store.consolidate(session, provider, "test-model", memory_window=50)
+        result = await store.consolidate(messages, provider, "test-model")
 
         assert result is True
         provider.chat.assert_not_called()
@@ -189,9 +186,9 @@ class TestMemoryConsolidationTypeHandling:
         )
         provider.chat = AsyncMock(return_value=response)
         provider.chat_with_retry = provider.chat
-        session = _make_session(message_count=60)
+        messages = _make_messages(message_count=60)
 
-        result = await store.consolidate(session, provider, "test-model", memory_window=50)
+        result = await store.consolidate(messages, provider, "test-model")
 
         assert result is True
         assert "User discussed testing." in store.history_file.read_text()
@@ -215,9 +212,9 @@ class TestMemoryConsolidationTypeHandling:
         )
         provider.chat = AsyncMock(return_value=response)
         provider.chat_with_retry = provider.chat
-        session = _make_session(message_count=60)
+        messages = _make_messages(message_count=60)
 
-        result = await store.consolidate(session, provider, "test-model", memory_window=50)
+        result = await store.consolidate(messages, provider, "test-model")
 
         assert result is False
 
@@ -239,9 +236,9 @@ class TestMemoryConsolidationTypeHandling:
         )
         provider.chat = AsyncMock(return_value=response)
         provider.chat_with_retry = provider.chat
-        session = _make_session(message_count=60)
+        messages = _make_messages(message_count=60)
 
-        result = await store.consolidate(session, provider, "test-model", memory_window=50)
+        result = await store.consolidate(messages, provider, "test-model")
 
         assert result is False
 
@@ -255,7 +252,7 @@ class TestMemoryConsolidationTypeHandling:
                 memory_update="# Memory\nUser likes testing.",
             ),
         ])
-        session = _make_session(message_count=60)
+        messages = _make_messages(message_count=60)
         delays: list[int] = []
 
         async def _fake_sleep(delay: int) -> None:
@@ -263,7 +260,7 @@ class TestMemoryConsolidationTypeHandling:
 
         monkeypatch.setattr("nanobot.providers.base.asyncio.sleep", _fake_sleep)
 
-        result = await store.consolidate(session, provider, "test-model", memory_window=50)
+        result = await store.consolidate(messages, provider, "test-model")
 
         assert result is True
         assert provider.calls == 2

tests/test_message_tool_suppress.py

@@ -16,7 +16,7 @@ def _make_loop(tmp_path: Path) -> AgentLoop:
     bus = MessageBus()
     provider = MagicMock()
     provider.get_default_model.return_value = "test-model"
-    return AgentLoop(bus=bus, provider=provider, workspace=tmp_path, model="test-model", memory_window=10)
+    return AgentLoop(bus=bus, provider=provider, workspace=tmp_path, model="test-model")
 
 
 class TestMessageToolSuppressLogic:
@@ -33,7 +33,7 @@ class TestMessageToolSuppressLogic:
             LLMResponse(content="", tool_calls=[tool_call]),
             LLMResponse(content="Done", tool_calls=[]),
         ])
-        loop.provider.chat = AsyncMock(side_effect=lambda *a, **kw: next(calls))
+        loop.provider.chat_with_retry = AsyncMock(side_effect=lambda *a, **kw: next(calls))
         loop.tools.get_definitions = MagicMock(return_value=[])
 
         sent: list[OutboundMessage] = []
@@ -58,7 +58,7 @@ class TestMessageToolSuppressLogic:
             LLMResponse(content="", tool_calls=[tool_call]),
             LLMResponse(content="I've sent the email.", tool_calls=[]),
         ])
-        loop.provider.chat = AsyncMock(side_effect=lambda *a, **kw: next(calls))
+        loop.provider.chat_with_retry = AsyncMock(side_effect=lambda *a, **kw: next(calls))
         loop.tools.get_definitions = MagicMock(return_value=[])
 
         sent: list[OutboundMessage] = []
@@ -77,7 +77,7 @@ class TestMessageToolSuppressLogic:
     @pytest.mark.asyncio
     async def test_not_suppress_when_no_message_tool_used(self, tmp_path: Path) -> None:
         loop = _make_loop(tmp_path)
-        loop.provider.chat = AsyncMock(return_value=LLMResponse(content="Hello!", tool_calls=[]))
+        loop.provider.chat_with_retry = AsyncMock(return_value=LLMResponse(content="Hello!", tool_calls=[]))
         loop.tools.get_definitions = MagicMock(return_value=[])
 
         msg = InboundMessage(channel="feishu", sender_id="user1", chat_id="chat123", content="Hi")
@@ -98,7 +98,7 @@ class TestMessageToolSuppressLogic:
             ),
             LLMResponse(content="Done", tool_calls=[]),
         ])
-        loop.provider.chat = AsyncMock(side_effect=lambda *a, **kw: next(calls))
+        loop.provider.chat_with_retry = AsyncMock(side_effect=lambda *a, **kw: next(calls))
         loop.tools.get_definitions = MagicMock(return_value=[])
         loop.tools.execute = AsyncMock(return_value="ok")