Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,8 @@ Only write entries that are worth mentioning to users.

## [Unreleased]

## [0.70] - 2025-12-31

- CLI: Add `--final-message-only` (and `--quiet` alias) to only output the final assistant message in print UI
- LLM: Add `video_in` model capability and support video inputs

Expand Down
2 changes: 2 additions & 0 deletions docs/en/release-notes/changelog.md
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,8 @@ This page documents the changes in each Kimi CLI release.

## [Unreleased]

## 0.70 (2025-12-31)

- CLI: Add `--final-message-only` (and `--quiet` alias) to only output the final assistant message in print UI
- LLM: Add `video_in` model capability and support video inputs
Comment on lines +7 to 10

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P1 Badge Regenerate the English changelog instead of editing it

The docs guide in docs/AGENTS.md states that docs/en/release-notes/changelog.md is auto-generated from the root CHANGELOG.md via docs/scripts/sync-changelog.mjs and should not be edited manually. Editing it directly here means the next npm run sync/docs build will overwrite this entry, so the 0.70 notes can disappear or diverge. Update CHANGELOG.md and regenerate the English changelog instead of committing manual edits to this file.

Useful? React with 👍 / 👎.


Expand Down
2 changes: 2 additions & 0 deletions docs/zh/release-notes/changelog.md
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,8 @@

## [Unreleased]

## 0.70 (2025-12-31)

- CLI:添加 `--final-message-only`(及 `--quiet` 别名),在 Print 模式下仅输出最终的 assistant 消息
- LLM:添加 `video_in` 模型能力,支持视频输入

Expand Down
3 changes: 3 additions & 0 deletions packages/kosong/CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,9 @@

## [Unreleased]


## [0.36.0] - 2025-12-31

- Add `VideoURLPart` content part

## [0.35.1-4] - 2025-12-26
Expand Down
2 changes: 1 addition & 1 deletion packages/kosong/pyproject.toml
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
[project]
name = "kosong"
version = "0.35.4"
version = "0.36.0"
description = "The LLM abstraction layer for modern AI agent applications."
readme = "README.md"
requires-python = ">=3.12"
Expand Down
4 changes: 2 additions & 2 deletions pyproject.toml
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
[project]
name = "kimi-cli"
version = "0.69"
version = "0.70"
description = "Kimi CLI is your next CLI agent."
readme = "README.md"
requires-python = ">=3.12"
Expand All @@ -9,7 +9,7 @@ dependencies = [
"aiofiles==25.1.0",
"aiohttp==3.13.2",
"typer==0.21.0",
"kosong[contrib]==0.35.4",
"kosong[contrib]==0.36.0",
"loguru==0.7.3",
"prompt-toolkit==3.0.52",
"pillow==12.0.0",
Expand Down
122 changes: 38 additions & 84 deletions tests/test_default_agent.py
Original file line number Diff line number Diff line change
Expand Up @@ -39,18 +39,7 @@ async def test_default_agent(runtime: Runtime):

When responding to the user, you MUST use the SAME language as the user, unless explicitly instructed to do otherwise.

# Guidelines

At any time, you should be HELPFUL and POLITE, CONCISE and ACCURATE, PATIENT and THOROUGH.

- Never diverge from the requirements and the goals of the task you work on. Stay on track.
- Never give the user more than what they want.
- Try your best to avoid any hallucination. Do fact checking before providing any factual information.
- Think twice before you act.
- Do not give up too early.
- ALWAYS, keep it stupidly simple. Do not overcomplicate things.

## For coding tasks
# General Guidelines for Coding

When building something from scratch, you should:

Expand All @@ -70,7 +59,7 @@ async def test_default_agent(runtime: Runtime):

DO NOT run `git commit`, `git push`, `git reset`, `git rebase` and/or do any other git mutations unless explicitly asked to do so. Ask for confirmation each time when you need to do git mutations, even if the user has confirmed in earlier conversations.

## For non-coding tasks
# General Guidelines for Research and Data Processing

The user may ask you to research on certain topics, or process certain multimedia files or folders. You must understand the user's requirements thoroughly, ask for clarification before you start if needed.

Expand All @@ -81,29 +70,6 @@ async def test_default_agent(runtime: Runtime):
- When working on images, videos, PDFs, docs, spreadsheets, presentations, or other multimedia files, you may need to use proper shell commands or Python tools to process them. Detect if there are already such tools in the environment. If you have to install them, you MUST ensure that any third-party packages are installed in a virtual environment.
- Avoid installing or deleting anything to/from outside of the current working directory. If you have to do so, ask the user for confirmation.

When using Python to process these multimedia files, follow these guidelines:

- PREFER using only built-in modules. When the script to run only involves built-in modules, you can run it directly with `python` or `python3`. For example:
```
python3 <script> # run scripts with the system Python interpreter
python3 -c "<code>" # run code snippets with the system Python interpreter
```
- If third-party packages are required, PREFER using `uv` (a Python project management tool). For example:
```
uv venv # create a new virtual environment at `./.venv`
uv pip install <package> # install packages into the venv
uv run python <script> # run scripts with the venv's Python interpreter
uv run python -c "<code>" # run code snippets with the venv's Python interpreter
```
- If `uv` is not available, use `python` or `python3` with virtual environment. For example:
```
python3 -m venv .venv # create a new virtual environment at `./.venv`
./.venv/bin/pip install <package> # install packages into the venv
./.venv/bin/python <script> # run scripts with the venv's Python interpreter
./.venv/bin/python -c "<code>" # run code snippets with the venv's Python interpreter
# on Windows, use `.\\.venv\\Scripts\\pip` and `.\\.venv\\Scripts\\python` instead
```

# Working Environment

## Operating System
Expand All @@ -126,7 +92,7 @@ async def test_default_agent(runtime: Runtime):

Use this as your basic understanding of the project structure.

## Project Information
# Project Information

Markdown files named `AGENTS.md` usually contain the background, structure, coding styles, user preferences and other relevant information about the project. You should use this information to understand the project and the user's preferences. `AGENTS.md` files may exist at different locations in the project, but typically there is one in the project root.

Expand All @@ -150,11 +116,11 @@ async def test_default_agent(runtime: Runtime):

If you modified any files/styles/structures/configurations/workflows/... mentioned in `AGENTS.md` files, you MUST update the corresponding `AGENTS.md` files to keep them up-to-date.

## Skills
# Skills

Skills are reusable, composable capabilities that enhance your abilities. Each skill is a self-contained directory with a `SKILL.md` file that contains instructions, examples, and/or reference material.

### What are skills?
## What are skills?

Skills are modular extensions that provide:

Expand All @@ -163,15 +129,26 @@ async def test_default_agent(runtime: Runtime):
- Tool integrations: Pre-configured tool chains for specific operations
- Reference material: Documentation, templates, and examples

### Available skills
## Available skills

No skills found.

### How to use skills
## How to use skills

Identify the skills that are likely to be useful for the tasks you are currently working on, read the `SKILL.md` file for detailed instructions, guidelines, scripts and more.

Only read skill details when needed to conserve the context window.\
Only read skill details when needed to conserve the context window.

# Ultimate Reminders

At any time, you should be HELPFUL and POLITE, CONCISE and ACCURATE, PATIENT and THOROUGH.

- Never diverge from the requirements and the goals of the task you work on. Stay on track.
- Never give the user more than what they want.
- Try your best to avoid any hallucination. Do fact checking before providing any factual information.
- Think twice before you act.
- Do not give up too early.
- ALWAYS, keep it stupidly simple. Do not overcomplicate things.\
Copy link

Copilot AI Dec 31, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

There is a trailing backslash at the end of this line that should be removed. The source file (src/kimi_cli/agents/default/system.md) does not have a backslash at the end of the corresponding line, and the similar line above (line 140) also correctly has no backslash. This trailing backslash should be removed for consistency.

Suggested change
- ALWAYS, keep it stupidly simple. Do not overcomplicate things.\
- ALWAYS, keep it stupidly simple. Do not overcomplicate things.

Copilot uses AI. Check for mistakes.
"""
)
assert agent.toolset.tools == snapshot(
Expand Down Expand Up @@ -667,18 +644,7 @@ async def test_default_agent(runtime: Runtime):

When responding to the user, you MUST use the SAME language as the user, unless explicitly instructed to do otherwise.

# Guidelines

At any time, you should be HELPFUL and POLITE, CONCISE and ACCURATE, PATIENT and THOROUGH.

- Never diverge from the requirements and the goals of the task you work on. Stay on track.
- Never give the user more than what they want.
- Try your best to avoid any hallucination. Do fact checking before providing any factual information.
- Think twice before you act.
- Do not give up too early.
- ALWAYS, keep it stupidly simple. Do not overcomplicate things.

## For coding tasks
# General Guidelines for Coding

When building something from scratch, you should:

Expand All @@ -698,7 +664,7 @@ async def test_default_agent(runtime: Runtime):

DO NOT run `git commit`, `git push`, `git reset`, `git rebase` and/or do any other git mutations unless explicitly asked to do so. Ask for confirmation each time when you need to do git mutations, even if the user has confirmed in earlier conversations.

## For non-coding tasks
# General Guidelines for Research and Data Processing

The user may ask you to research on certain topics, or process certain multimedia files or folders. You must understand the user's requirements thoroughly, ask for clarification before you start if needed.

Expand All @@ -709,29 +675,6 @@ async def test_default_agent(runtime: Runtime):
- When working on images, videos, PDFs, docs, spreadsheets, presentations, or other multimedia files, you may need to use proper shell commands or Python tools to process them. Detect if there are already such tools in the environment. If you have to install them, you MUST ensure that any third-party packages are installed in a virtual environment.
- Avoid installing or deleting anything to/from outside of the current working directory. If you have to do so, ask the user for confirmation.

When using Python to process these multimedia files, follow these guidelines:

- PREFER using only built-in modules. When the script to run only involves built-in modules, you can run it directly with `python` or `python3`. For example:
```
python3 <script> # run scripts with the system Python interpreter
python3 -c "<code>" # run code snippets with the system Python interpreter
```
- If third-party packages are required, PREFER using `uv` (a Python project management tool). For example:
```
uv venv # create a new virtual environment at `./.venv`
uv pip install <package> # install packages into the venv
uv run python <script> # run scripts with the venv's Python interpreter
uv run python -c "<code>" # run code snippets with the venv's Python interpreter
```
- If `uv` is not available, use `python` or `python3` with virtual environment. For example:
```
python3 -m venv .venv # create a new virtual environment at `./.venv`
./.venv/bin/pip install <package> # install packages into the venv
./.venv/bin/python <script> # run scripts with the venv's Python interpreter
./.venv/bin/python -c "<code>" # run code snippets with the venv's Python interpreter
# on Windows, use `.\\.venv\\Scripts\\pip` and `.\\.venv\\Scripts\\python` instead
```

# Working Environment

## Operating System
Expand All @@ -754,7 +697,7 @@ async def test_default_agent(runtime: Runtime):

Use this as your basic understanding of the project structure.

## Project Information
# Project Information

Markdown files named `AGENTS.md` usually contain the background, structure, coding styles, user preferences and other relevant information about the project. You should use this information to understand the project and the user's preferences. `AGENTS.md` files may exist at different locations in the project, but typically there is one in the project root.

Expand All @@ -778,11 +721,11 @@ async def test_default_agent(runtime: Runtime):

If you modified any files/styles/structures/configurations/workflows/... mentioned in `AGENTS.md` files, you MUST update the corresponding `AGENTS.md` files to keep them up-to-date.

## Skills
# Skills

Skills are reusable, composable capabilities that enhance your abilities. Each skill is a self-contained directory with a `SKILL.md` file that contains instructions, examples, and/or reference material.

### What are skills?
## What are skills?

Skills are modular extensions that provide:

Expand All @@ -791,15 +734,26 @@ async def test_default_agent(runtime: Runtime):
- Tool integrations: Pre-configured tool chains for specific operations
- Reference material: Documentation, templates, and examples

### Available skills
## Available skills

No skills found.

### How to use skills
## How to use skills

Identify the skills that are likely to be useful for the tasks you are currently working on, read the `SKILL.md` file for detailed instructions, guidelines, scripts and more.

Only read skill details when needed to conserve the context window.\
Only read skill details when needed to conserve the context window.

# Ultimate Reminders

At any time, you should be HELPFUL and POLITE, CONCISE and ACCURATE, PATIENT and THOROUGH.

- Never diverge from the requirements and the goals of the task you work on. Stay on track.
- Never give the user more than what they want.
- Try your best to avoid any hallucination. Do fact checking before providing any factual information.
- Think twice before you act.
- Do not give up too early.
- ALWAYS, keep it stupidly simple. Do not overcomplicate things.\
Copy link

Copilot AI Dec 31, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

There is a trailing backslash at the end of this line that should be removed. The source file (src/kimi_cli/agents/default/system.md) does not have a backslash at the end of the corresponding line, and the similar line above (line 745) also correctly has no backslash. This trailing backslash should be removed for consistency.

Suggested change
- ALWAYS, keep it stupidly simple. Do not overcomplicate things.\
- ALWAYS, keep it stupidly simple. Do not overcomplicate things.

Copilot uses AI. Check for mistakes.
""",
[
"Shell",
Expand Down
4 changes: 2 additions & 2 deletions uv.lock

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.