klaude-code 1.2.10__py3-none-any.whl → 1.2.11__py3-none-any.whl

klaude_code/cli/main.py

@@ -3,7 +3,6 @@ import datetime
 import os
 import subprocess
 import sys
-import uuid
 from importlib.metadata import PackageNotFoundError
 from importlib.metadata import version as pkg_version
 
@@ -340,8 +339,8 @@ def main_callback(
                 return
 
         # Resolve session id before entering asyncio loop
+        # session_id=None means create a new session
         session_id: str | None = None
-        is_new_session = False
         if resume:
             session_id = resume_select_session()
             if session_id is None:
@@ -349,10 +348,7 @@ def main_callback(
         # If user didn't pick, allow fallback to --continue
         if session_id is None and continue_:
             session_id = Session.most_recent_session_id()
-        # If still no session_id, generate a new one for a new session
-        if session_id is None:
-            session_id = uuid.uuid4().hex
-            is_new_session = True
+        # If still no session_id, leave as None to create a new session
 
         debug_enabled, debug_filters = resolve_debug_settings(debug, debug_filter)
 
@@ -367,6 +363,5 @@ def main_callback(
             run_interactive(
                 init_config=init_config,
                 session_id=session_id,
-                is_new_session=is_new_session,
             )
         )

klaude_code/cli/runtime.py

@@ -1,6 +1,5 @@
 import asyncio
 import sys
-import uuid
 from dataclasses import dataclass
 from typing import Any, Protocol
 
@@ -15,7 +14,6 @@ from klaude_code.core.executor import Executor
 from klaude_code.core.manager import build_llm_clients
 from klaude_code.protocol import events, op
 from klaude_code.protocol.model import UserInputPayload
-from klaude_code.protocol.sub_agent import iter_sub_agent_profiles
 from klaude_code.trace import DebugType, log, set_debug_logging
 from klaude_code.ui.modes.repl import build_repl_status_snapshot
 from klaude_code.ui.modes.repl.input_prompt_toolkit import REPLStatusSnapshot
@@ -97,11 +95,9 @@ async def initialize_app_components(init_config: AppInitConfig) -> AppComponents
 
     # Initialize LLM clients
     try:
-        enabled_sub_agents = [p.name for p in iter_sub_agent_profiles()]
         llm_clients = build_llm_clients(
             config,
             model_override=init_config.model,
-            enabled_sub_agents=enabled_sub_agents,
         )
     except ValueError as exc:
         if init_config.model:
@@ -207,12 +203,14 @@ async def run_exec(init_config: AppInitConfig, input_content: str) -> None:
     components = await initialize_app_components(init_config)
 
     try:
-        # Generate a new session ID for exec mode
-        session_id = uuid.uuid4().hex
-
-        await components.executor.submit_and_wait(op.InitAgentOperation(session_id=session_id, is_new_session=True))
+        # Initialize a new session (session_id=None means create new)
+        await components.executor.submit_and_wait(op.InitAgentOperation())
         await components.event_queue.join()
 
+        # Get the session_id from the newly created agent
+        session_ids = components.executor.context.agent_manager.active_session_ids()
+        session_id = session_ids[0] if session_ids else None
+
         # Submit the input content directly
         await components.executor.submit_and_wait(
             op.UserInputOperation(input=UserInputPayload(text=input_content), session_id=session_id)
@@ -224,11 +222,12 @@ async def run_exec(init_config: AppInitConfig, input_content: str) -> None:
         await cleanup_app_components(components)
 
 
-async def run_interactive(
-    init_config: AppInitConfig, session_id: str | None = None, *, is_new_session: bool = False
-) -> None:
-    """Run the interactive REPL using the provided configuration."""
+async def run_interactive(init_config: AppInitConfig, session_id: str | None = None) -> None:
+    """Run the interactive REPL using the provided configuration.
 
+    If session_id is None, a new session is created with an auto-generated ID.
+    If session_id is provided, attempts to resume that session.
+    """
     components = await initialize_app_components(init_config)
 
     # No theme persistence from CLI anymore; config.theme controls theme when set.
@@ -236,8 +235,10 @@ async def run_interactive(
     # Create status provider for bottom toolbar
     def _status_provider() -> REPLStatusSnapshot:
         agent: Agent | None = None
-        if session_id and session_id in components.executor.context.active_agents:
-            agent = components.executor.context.active_agents[session_id]
+        # Get the first active agent (there should only be one in interactive mode)
+        active_agents = components.executor.context.active_agents
+        if active_agents:
+            agent = next(iter(active_agents.values()), None)
 
         # Check for updates (returns None if uv not available)
         update_message = get_update_message()
@@ -279,10 +280,13 @@ async def run_interactive(
     restore_sigint = install_sigint_double_press_exit(_show_toast_once, _hide_progress)
 
     try:
-        await components.executor.submit_and_wait(
-            op.InitAgentOperation(session_id=session_id, is_new_session=is_new_session)
-        )
+        await components.executor.submit_and_wait(op.InitAgentOperation(session_id=session_id))
         await components.event_queue.join()
+
+        # Get the actual session_id (may have been auto-generated if None was passed)
+        active_session_ids = components.executor.context.agent_manager.active_session_ids()
+        active_session_id = active_session_ids[0] if active_session_ids else session_id
+
         # Input
         await input_provider.start()
         async for user_input in input_provider.iter_inputs():
@@ -293,7 +297,7 @@ async def run_interactive(
                 continue
             # Submit user input operation - directly use the payload from iter_inputs
             submission_id = await components.executor.submit(
-                op.UserInputOperation(input=user_input, session_id=session_id)
+                op.UserInputOperation(input=user_input, session_id=active_session_id)
             )
             # If it's an interactive command (e.g., /model), avoid starting the ESC monitor
             # to prevent TTY conflicts with interactive prompts (questionary/prompt_toolkit).
@@ -302,7 +306,7 @@ async def run_interactive(
             else:
                 # Esc monitor for long-running, interruptible operations
                 async def _on_esc_interrupt() -> None:
-                    await components.executor.submit(op.InterruptOperation(target_session_id=session_id))
+                    await components.executor.submit(op.InterruptOperation(target_session_id=active_session_id))
 
                 stop_event, esc_task = start_esc_interrupt_monitor(_on_esc_interrupt)
                 # Wait for this specific task to complete before accepting next input

klaude_code/core/agent.py

@@ -122,6 +122,7 @@ class Agent:
         self.session: Session = session
         self.profile: AgentProfile = profile
         self._current_task: TaskExecutor | None = None
+        self._prev_context_token: int = 0  # Track context size from previous task for delta calculation
         if not self.session.model_name and model_name:
             self.session.model_name = model_name
 
@@ -169,6 +170,12 @@ class Agent:
 
         try:
             async for event in task.run(user_input):
+                # Compute context_delta for TaskMetadataEvent
+                if isinstance(event, events.TaskMetadataEvent):
+                    usage = event.metadata.main.usage
+                    if usage is not None and usage.context_token is not None:
+                        usage.context_delta = usage.context_token - self._prev_context_token
+                        self._prev_context_token = usage.context_token
                 yield event
         finally:
             self._current_task = None

klaude_code/core/executor.py

@@ -114,10 +114,7 @@ class ExecutorContext:
 
     async def handle_init_agent(self, operation: op.InitAgentOperation) -> None:
         """Initialize an agent for a session and replay history to UI."""
-        if operation.session_id is None:
-            raise ValueError("session_id cannot be None")
-
-        await self.agent_manager.ensure_agent(operation.session_id, is_new_session=operation.is_new_session)
+        await self.agent_manager.ensure_agent(operation.session_id)
 
     async def handle_user_input(self, operation: op.UserInputOperation) -> None:
         """Handle a user input operation by running it through an agent."""

klaude_code/core/manager/agent_manager.py

@@ -38,13 +38,19 @@ class AgentManager:
 
         await self._event_queue.put(event)
 
-    async def ensure_agent(self, session_id: str, *, is_new_session: bool = False) -> Agent:
-        """Return an existing agent for the session or create a new one."""
-        agent = self._active_agents.get(session_id)
-        if agent is not None:
-            return agent
-
-        session = Session.load(session_id, skip_if_missing=is_new_session)
+    async def ensure_agent(self, session_id: str | None = None) -> Agent:
+        """Return an existing agent for the session or create a new one.
+
+        If session_id is None, a new session is created with an auto-generated ID.
+        If session_id is provided, attempts to load existing session or creates new one.
+        """
+        if session_id is None:
+            session = Session.create()
+        else:
+            agent = self._active_agents.get(session_id)
+            if agent is not None:
+                return agent
+            session = Session.load(session_id)
         profile = self._model_profile_provider.build_profile(self._llm_clients)
         agent = Agent(session=session, profile=profile, model_name=self._llm_clients.main_model_name)
 
@@ -58,9 +64,9 @@ class AgentManager:
             )
         )
 
-        self._active_agents[session_id] = agent
+        self._active_agents[session.id] = agent
         log_debug(
-            f"Initialized agent for session: {session_id}",
+            f"Initialized agent for session: {session.id}",
             style="cyan",
             debug_type=DebugType.EXECUTION,
         )

klaude_code/core/manager/llm_clients_builder.py

@@ -6,8 +6,7 @@ from klaude_code.config import Config
 from klaude_code.core.manager.llm_clients import LLMClients
 from klaude_code.llm.client import LLMClientABC
 from klaude_code.llm.registry import create_llm_client
-from klaude_code.protocol.sub_agent import get_sub_agent_profile
-from klaude_code.protocol.tools import SubAgentType
+from klaude_code.protocol.sub_agent import iter_sub_agent_profiles
 from klaude_code.trace import DebugType, log_debug
 
 
@@ -15,7 +14,6 @@ def build_llm_clients(
     config: Config,
     *,
     model_override: str | None = None,
-    enabled_sub_agents: list[SubAgentType] | None = None,
 ) -> LLMClients:
     """Create an ``LLMClients`` bundle driven by application config."""
 
@@ -43,12 +41,11 @@ def build_llm_clients(
         main_llm_config=llm_config,
     )
 
-    for sub_agent_type in enabled_sub_agents or []:
-        model_name = config.subagent_models.get(sub_agent_type)
+    for profile in iter_sub_agent_profiles():
+        model_name = config.subagent_models.get(profile.name)
         if not model_name:
             continue
 
-        profile = get_sub_agent_profile(sub_agent_type)
         if not profile.enabled_for_model(main_model_name):
             continue
 
@@ -56,6 +53,6 @@ def build_llm_clients(
             sub_llm_config = config.get_model_config(model_name_for_factory)
             return create_llm_client(sub_llm_config)
 
-        clients.register_sub_client_factory(sub_agent_type, _factory)
+        clients.register_sub_client_factory(profile.name, _factory)
 
     return clients

klaude_code/core/prompt.py

@@ -6,8 +6,8 @@ from pathlib import Path
 
 COMMAND_DESCRIPTIONS: dict[str, str] = {
     "rg": "ripgrep - fast text search",
-    "fd": "fd - simple and fast alternative to find",
-    "tree": "tree - directory listing as a tree",
+    "fd": "simple and fast alternative to find",
+    "tree": "directory listing as a tree",
     "sg": "ast-grep - AST-aware code search",
 }
 
@@ -15,7 +15,7 @@ COMMAND_DESCRIPTIONS: dict[str, str] = {
 PROMPT_FILES: dict[str, str] = {
     "main_gpt_5_1": "prompts/prompt-codex-gpt-5-1.md",
     "main_gpt_5_1_codex_max": "prompts/prompt-codex-gpt-5-1-codex-max.md",
-    "main_claude": "prompts/prompt-claude-code.md",
+    "main": "prompts/prompt-claude-code.md",
     "main_gemini": "prompts/prompt-gemini.md",  # https://ai.google.dev/gemini-api/docs/prompting-strategies?hl=zh-cn#agentic-si-template
     # Sub-agent prompts keyed by their name
     "Task": "prompts/prompt-subagent.md",
@@ -49,7 +49,7 @@ def _get_file_key(model_name: str, sub_agent_type: str | None) -> str:
         case name if "gemini" in name:
             return "main_gemini"
         case _:
-            return "main_claude"
+            return "main"
 
 
 def _build_env_info(model_name: str) -> str:

klaude_code/core/prompts/prompt-claude-code.md

@@ -84,15 +84,4 @@ assistant: [Uses the Explore tool to find the files that handle client errors in
 <example>
 user: What is the codebase structure?
 assistant: [Uses the Explore tool]
-</example>
-
-## Memory
-MEMORY PROTOCOL:
-1. Use the `view` command of your `Memory` tool to check for earlier progress.
-2. ... (work on the task) ...
-     - As you make progress, record status / progress / thoughts etc in your memory.
-ASSUME INTERRUPTION: Your context window might be reset at any moment, so you risk losing any progress that is not recorded in your memory directory.
-
-Note: when editing your memory folder, always try to keep its content up-to-date, coherent and organized. You can rename or delete files that are no longer relevant. Do not create new files unless necessary.
-
-Only write down information relevant to current project in your memory system.
+</example>

klaude_code/core/prompts/prompt-minimal.md

@@ -0,0 +1,12 @@
+You are an interactive CLI tool. Use the tools available to you to assist the user.
+
+## Guidelines
+- Never use emojis.
+- Your output will be displayed on a command line interface. Your responses should be short and concise.
+- Output text to communicate with the user; all text you output outside of tool use is displayed to the user. Only use tools to complete tasks. Never use tools like Bash or code comments as means to communicate with the user during the session.
+- NEVER create Markdown files unless they're absolutely necessary for achieving your goal.
+- Use TodoWrite tool to help you manage and plan tasks.
+- For maximum efficiency, whenever you need to perform multiple independent operations, invoke all relevant tools simultaneously rather than sequentially.
+
+## Professional objectivity
+Prioritize technical accuracy and truthfulness over validating the user's beliefs. Focus on facts and problem-solving, providing direct, objective technical info without any unnecessary superlatives, praise, or emotional validation. It is best for the user if you honestly applies the same rigorous standards to all ideas and disagrees when necessary, even if it may not be what the user wants to hear. Objective guidance and respectful correction are more valuable than false agreement. Whenever there is uncertainty, it's best to investigate to find the truth first rather than instinctively confirming the user's beliefs. Avoid using over-the-top validation or excessive praise when responding to users such as "You're absolutely right" or similar phrases.

klaude_code/core/task.py

@@ -29,9 +29,11 @@ class MetadataAccumulator:
         self._sub_agent_metadata: list[model.TaskMetadata] = []
         self._throughput_weighted_sum: float = 0.0
         self._throughput_tracked_tokens: int = 0
+        self._turn_count: int = 0
 
     def add(self, turn_metadata: model.ResponseMetadataItem) -> None:
         """Merge a turn's metadata into the accumulated state."""
+        self._turn_count += 1
         main = self._main
         usage = turn_metadata.usage
 
@@ -43,6 +45,7 @@ class MetadataAccumulator:
             acc_usage.cached_tokens += usage.cached_tokens
             acc_usage.reasoning_tokens += usage.reasoning_tokens
             acc_usage.output_tokens += usage.output_tokens
+            acc_usage.last_turn_output_token = usage.output_tokens
             acc_usage.currency = usage.currency
 
             if usage.context_token is not None:
@@ -91,6 +94,7 @@ class MetadataAccumulator:
                 main.usage.throughput_tps = None
 
         main.task_duration_s = task_duration_s
+        main.turn_count = self._turn_count
         return model.TaskMetadataItem(main=main, sub_agent_task_metadata=self._sub_agent_metadata)
 
 

klaude_code/core/tool/memory/memory_tool.md

@@ -14,3 +14,7 @@ Usage tips:
 - Check your memory directory before starting tasks to recall previous context
 - Record important decisions, progress, and learnings as you work
 - Keep memory files organized and up-to-date; delete obsolete files
+
+Note: when editing your memory folder, always try to keep its content up-to-date, coherent and organized. You can rename or delete files that are no longer relevant. Do not create new files unless necessary.
+
+Only write down information relevant to current project in your memory system.

klaude_code/core/tool/memory/skill_loader.py

@@ -39,7 +39,7 @@ class SkillLoader:
     USER_SKILLS_DIRS = [
         Path("~/.claude/skills"),
         Path("~/.klaude/skills"),
-        Path("~/.claude/plugins/marketplaces"),
+        # Path("~/.claude/plugins/marketplaces"),
     ]
     # Project-level skills directory
     PROJECT_SKILLS_DIR = Path("./.claude/skills")

klaude_code/core/tool/todo/todo_write_tool.md

@@ -22,161 +22,4 @@ Skip using this tool when:
 
 NOTE that you should not use this tool if there is only one trivial task to do. In this case you are better off just doing the task directly.
 
-#### Examples of When to Use the Todo List
-
-<example>
-User: I want to add a dark mode toggle to the application settings. Make sure you run the tests and build when you're done!
-Assistant: I'll help add a dark mode toggle to your application settings. Let me create a todo list to track this implementation.
-*Creates todo list with the following items:*
-1. Creating dark mode toggle component in Settings page
-2. Adding dark mode state management (context/store)
-3. Implementing CSS-in-JS styles for dark theme
-4. Updating existing components to support theme switching
-5. Running tests and build process, addressing any failures or errors that occur
-*Begins working on the first task*
-
-<reasoning>
-The assistant used the todo list because:
-1. Adding dark mode is a multi-step feature requiring UI, state management, and styling changes
-2. The user explicitly requested tests and build be run afterward
-3. The assistant inferred that tests and build need to pass by adding "Ensure tests and build succeed" as the final task
-</reasoning>
-</example>
-
-<example>
-User: Help me rename the function getCwd to getCurrentWorkingDirectory across my project
-Assistant: Let me first search through your codebase to find all occurrences of 'getCwd'.
-*Uses grep or search tools to locate all instances of getCwd in the codebase*
-Assistant: I've found 15 instances of 'getCwd' across 8 different files. Let me create a todo list to track these changes.
-*Creates todo list with specific items for each file that needs updating*
-
-<reasoning>
-The assistant used the todo list because:
-1. First, the assistant searched to understand the scope of the task
-2. Upon finding multiple occurrences across different files, it determined this was a complex task with multiple steps
-3. The todo list helps ensure every instance is tracked and updated systematically
-4. This approach prevents missing any occurrences and maintains code consistency
-</reasoning>
-</example>
-
-
-<example>
-User: I need to implement these features for my e-commerce site: user registration, product catalog, shopping cart, and checkout flow.
-Assistant: I'll help implement these features. First, let's add all the features to the todo list.
-*Creates a todo list breaking down each feature into specific tasks based on the project architecture*
-Assistant: Let's start with user registration. This will involve creating database models, API endpoints, and frontend forms that integrate with your existing authentication system.
-
-<reasoning>
-The assistant used the todo list because:
-1. The user provided multiple complex features to implement in a comma separated list
-2. The todo list helps organize these large features into manageable tasks
-3. This approach allows for tracking progress across the entire implementation
-</reasoning>
-</example>
-
-<example>
-User: Can you help optimize my React application? It's rendering slowly and has performance issues.</user>
-Assistant: I'll help optimize your React application. First, let me examine your codebase to identify potential performance bottlenecks.
-*Reviews component structure, render patterns, state management, and data fetching*
-Assistant: After analyzing your codebase, I've identified several performance issues. Let me create a todo list to track our optimization efforts.
-*Creates todo list with items like: 1) Implementing memoization for expensive calculations in ProductList, 2) Adding virtualization for long lists in Dashboard, 3) Optimizing image loading in Gallery component, 4) Fixing state update loops in ShoppingCart, 5) Reviewing bundle size and implementing code splitting*
-Let's start by implementing memoization for the expensive calculations in your ProductList component.</assistant>
-
-<reasoning>
-The assistant used the todo list because:
-1. First, the assistant examined the codebase to identify specific performance issues
-2. Based on this analysis, it identified multiple optimization opportunities
-3. Performance optimization is a non-trivial task requiring multiple steps
-4. The todo list helps methodically track improvements across different components
-5. This systematic approach ensures all performance bottlenecks are addressed
-</reasoning>
-</example>
-
-#### Examples of When NOT to Use the Todo List
-
-<example>
-User: How do I print 'Hello World' in Python?
-Assistant: In Python, you can print "Hello World" with this simple code:
-
-python
-print("Hello World")
-
-This will output the text "Hello World" to the console when executed.</assistant>
-
-<reasoning>
-The assistant did not use the todo list because this is a single, trivial task that can be completed in one step. There's no need to track multiple tasks or steps for such a straightforward request.
-</reasoning>
-</example>
-
-<example>
-User: What does the git status command do?
-Assistant: The git status command shows the current state of your working directory and staging area. It displays which changes have been staged, which haven't, and which files aren't being tracked by Git. This is a fundamental command for understanding the current state of your repository before making commits.
-
-<reasoning>
-The assistant did not use the todo list because this is an informational request with no actual coding task to complete. The user is simply asking for an explanation, not for the assistant to perform multiple steps or tasks.
-</reasoning>
-</example>
-
-<example>
-User: Can you add a comment to the calculateTotal function to explain what it does?
-Assistant: Sure, let me add a comment to the calculateTotal function to explain what it does.
-* Uses the Edit tool to add a comment to the calculateTotal function *
-
-<reasoning>
-The assistant did not use the todo list because this is a single, straightforward task confined to one location in the code. Adding a comment doesn't require tracking multiple steps or systematic organization.
-</reasoning>
-</example>
-
-<example>
-User: Run npm install for me and tell me what happens.
-Assistant: I'll run the npm install command for you.
-
-*Executes: npm install*
-
-The command completed successfully. Here's the output:
-[Output of npm install command]
-
-All dependencies have been installed according to your package.json file.
-
-<reasoning>
-The assistant did not use the todo list because this is a single command execution with immediate results. There are no multiple steps to track or organize, making the todo list unnecessary for this straightforward task.
-</reasoning>
-</example>
-
-#### Task States and Management
-
-1. **Task States**: Use these states to track progress:
-   - pending: Task not yet started
-   - in_progress: Currently working on (limit to ONE task at a time)
-   - completed: Task finished successfully
-
-   **IMPORTANT**: Task descriptions must have two forms:
-   - content: The imperative form describing what needs to be done (e.g., "Run tests", "Build the project")
-   - activeForm: The present continuous form shown during execution (e.g., "Running tests", "Building the project")
-
-2. **Task Management**:
-   - Update task status in real-time as you work
-   - Mark tasks complete IMMEDIATELY after finishing (don't batch completions)
-   - Exactly ONE task must be in_progress at any time (not less, not more)
-   - Complete current tasks before starting new ones
-   - Remove tasks that are no longer relevant from the list entirely
-
-3. **Task Completion Requirements**:
-   - ONLY mark a task as completed when you have FULLY accomplished it
-   - If you encounter errors, blockers, or cannot finish, keep the task as in_progress
-   - When blocked, create a new task describing what needs to be resolved
-   - Never mark a task as completed if:
-     - Tests are failing
-     - Implementation is partial
-     - You encountered unresolved errors
-     - You couldn't find necessary files or dependencies
-
-4. **Task Breakdown**:
-   - Create specific, actionable items
-   - Break complex tasks into smaller, manageable steps
-   - Use clear, descriptive task names
-   - Always provide both forms:
-     - content: "Fix authentication bug"
-     - activeForm: "Fixing authentication bug"
-
 When in doubt, use this tool. Being proactive with task management demonstrates attentiveness and ensures you complete all requirements successfully.