> ## Documentation Index
> Fetch the complete documentation index at: https://docs.mutagent.io/llms.txt
> Use this file to discover all available pages before exploring further.
# What's new
> Dated changes to Helix, the mutagent CLI and the platform, newest first.
Run `helix --version` and `mutagent --version` to see which builds you have. Inside Helix, `/changelog`
prints the notes for the recent Helix releases.
**Helix 0.3.2**
* `/build` runs in two agent steps. First the engineer writes a plan and builds it, tests first; for
an agent deployed by API it edits the agent's definition instead. Then a read-only reviewer checks
the result against the spec and the plan. See [Build](/helix/lifecycle/build).
* A sub-agent stopped for inactivity reports that it failed. It no longer returns the result of its
previous run as if it were new.
* The skills and agents that ship with Helix work from any Helix install.
**Helix 0.3.1**
* Resume a sub-agent you started earlier. Its result ends with its id; resuming and messaging it
accept that id, the short ref from the agent list, or a unique prefix of at least four characters.
See [Sub-agents](/helix/features/sub-agents#resume-a-sub-agent).
* When a sub-agent asks for a model tier you have not configured, you and the model both see a
warning that names the model it runs on instead.
* A question from a session started in the background goes to the session that started it. A person
there answers it; without one, that session's agent answers. If nobody can, the background session
decides for itself and continues instead of waiting.
* Crash messages and the `/bug` notice name the Helix binary you are running.
* Prime mode: a cell that awaits and ends in an `if`, `try` or block returns that statement's value.
**Helix 0.3.0**
* Helix now runs on pi 1.0.
* MCP is on. The MCP servers you already configured work as they are, and their tools reach the model
directly. Helix adds no MCP server of its own. See [MCP servers](/helix/features/mcp).
* `/bug` sends your feedback to the Mutagent team, with an optional note: `/bug the footer is cut off`.
In `helix agent` and `helix --prime`, which have no feedback, it says so in one line and sends
nothing.
* `/thinking` offers every level your model supports, including max. The footer shows the level you
picked.
* [Prime mode](/helix/modes#helix-prime-the-code-first-mode) runs its code cells in a sandbox. File reads, writes and shell commands from a cell go
through the same permission checks and plan mode as any other tool call. Shell output comes back
with its exit code, capped at 1 MiB, with the full output saved to a file. Cells can also find and
call your MCP tools.
* Agent mode and sub-agents run as agents in their own right, without Helix's orchestration prompt on
top.
* Helix keeps the prompt cache warm across turns and in sub-agents, so repeated context costs less.
* Fixes: turning `/cloud` off brings back the model you were using. `helix --prime -p` exits once it
has printed its answer. Sub-agent transcripts survive compaction and resume.
**Helix 0.2.2**
* The installer no longer edits your shell profile. It links `helix` into `~/.local/bin`, creating
it if needed, or into `~/bin` when only that one is on your `PATH`. If the folder is not on your
`PATH`, it prints the line to add yourself and the full path, `~/.mutagent/bin/helix`, which always
works. See [Install Helix](/helix/install).
* Helix runs the mutagent CLI only from your installation. When the CLI isn't installed, Helix tells
you how to install it and stops.
**Helix 0.2.1**
* A question Helix asks you ends with a **Chat about this** row. Choosing it closes the question and
returns you to the chat, so you can talk it over first. Answers you already gave are kept.
* Number keys pick options in a question: in a single-choice question a number selects that option,
in a multi-choice question it ticks or unticks it.
* `helix doctor` names the providers you are signed in to, or says the saved sign-in is empty or
unreadable and how to fix it: type `/login` in Helix, or set a provider key such as `ZAI_API_KEY`.
It never prints a key.
**Helix 0.2.0**
* Helix moves to the 0.2.0 version line, together with the other Mutagent packages. It is the same
Helix as 0.0.38-m0.
**Helix 0.0.38-m0**
* A model response that stalls no longer hangs Helix. When the provider sends no response headers, or
no content for 120 seconds, the request fails and Helix retries it like any other provider error.
`HELIX_STREAM_HEADERS_TIMEOUT_MS` and `HELIX_STREAM_IDLE_TIMEOUT_MS` set the two limits in
milliseconds; `0` turns one off.
**Helix 0.0.37-m0**
* In a git checkout whose origin is on GitHub, `/cloud` starts the sandbox with your repository
checked out, on your current branch when GitHub has it. When the sandbox can't start, `/cloud`
shows what went wrong and the commands that fix it.
* In `/cloud`, the sandbox's tool calls show as the same tool cards as local ones, live and after
`/resume`.
* Asked to print its own installed files, agent definitions or system prompt, Helix declines in one
sentence and offers what it can do instead. Your own project files are unaffected.
* In a question that takes several answers, typing your own answer under **Other** and pressing Enter
checks it and keeps your other choices.
* Evaluation judging is always done by the evaluator agent, so no Gemini key is needed.
**Web app**
* A new **Configuration** page holds the workspace's **LLM Providers**, **Environments** and
**Integrations**, plus the shared **Sandbox Providers** list. LLM providers moved here from
Settings.
* Signing up asks only for your organization's name; Mutagent creates a workspace named
**Default workspace** in it. The next step, **Connect GitHub**, can be skipped.
**LLM providers**
* **OpenRouter** (`openrouter`) and **Z.AI (Coding Plan)** (`zai-coding-plan`) can be added to a
workspace. The default Z.AI model is `glm-5.3`.
**Cloud sessions, GitHub and Slack**
* Cloud sessions, managed agents, and GitHub and Slack runs are in early access: not every account is let in yet.
* A cloud session stopped after 15 minutes of inactivity wakes up when you send it a message. The
web app shows **Waking up…**, then delivers your message, and the conversation continues in the
same thread.
* Connect GitHub and Slack from **Configuration › Integrations**. A Slack thread keeps one session
for up to 1 hour; mention the app in a new message to start another.
**Trace sources**
* Langfuse and OpenObserve can be connected to a workspace with `mutagent integrations sources add`.
**Helix 0.0.36-m0**
* Helix shows its first screen sooner, and internal startup notices no longer appear in the chat box.
* `/cloud` runs the sandbox on a real model: the one given with `--model`, else the workspace default,
else the first workspace model. Turning `/cloud` on or off no longer changes your saved default
model, and `/cloud model` works before the first sandbox starts.
* `/cloud stop` ends the sandbox session again instead of showing an error.
* On the Z.ai coding plan, `--provider zai --model glm-5` picks `glm-5.3-flash`. When your plan does
not include the model you chose, the turn fails once with one line that names the model and
suggests `zai/glm-5.3` or a plan upgrade.
* `/build` offers the Mutagent platform as a target.
**Helix 0.0.35-m0**
* Helix starts faster where it has not run before, such as a new cloud sandbox. It loads the
extensions and harness it ships with instead of recompiling or downloading them at startup.
* Reinstalling or updating Helix while a session is open no longer deletes the files that session
runs from. `helix update` deletes nothing; old builds are removed at a later launch once no running
Helix uses them.
* A cross-session lock problem shows one warning while it lasts instead of one line per tick.
* The installer and `helix update` send a User-Agent naming Helix, its version, platform and channel.
**Helix 0.0.34-m0**
* `/cloud` checks whether cloud sandboxes are enabled for your account before it starts anything.
If they are not, it says so in one line and leaves your local session as it was.
* `/cloud status` shows whether cloud sandboxes are enabled for your account, or tells you to run
`mutagent login` when your sign-in has expired.
**Helix 0.0.33-m0**
* `/cloud` runs your turns in a cloud sandbox while you keep the local session.
`/cloud stop` removes the sandbox and reports `removing`, then `removed`.
* A session is driven by a goal with done-when criteria. The goal cannot be completed until every
criterion has evidence.
* `helix -p "/diagnose …"`, and any other Helix command run headless, runs a real turn and prints
its reply.
* After the curl install, `helix` works in the same terminal when `~/.local/bin` or `~/bin` is on
your `PATH`.
* Web search settings with Exa and Firecrawl; Anthropic and xAI models on Google Vertex AI from
`/login`; plan mode ends with Approve, Keep or Discard.
**mutagent CLI: organizations and workspaces**
* `mutagent login` stores an organization key that works in every workspace you belong to in that
organization, for 30 days.
* `mutagent workspaces use ` selects the workspace every later command works in.
`--workspace ` overrides it for one command, then `MUTAGENT_WORKSPACE_ID`.
* `--org ` checks the key's organization; a mismatch exits 1 and sends nothing.
`mutagent login --org ` signs in to another organization.
* See [Accounts, organizations and workspaces](/get-started/accounts).
* Cloud sessions have two modes, named the same in the CLI, the SDK and the API: **headless** (one
task, the reply printed) and **interactive** (a session you keep sending to).
**Helix 0.0.32-m0**
* A sub-agent can be messaged for as long as it exists, including after it finishes; a message to a
finished sub-agent resumes it.
* Sub-agents can be named when spawned, and `SendMessage`, `StopAgent` and `ListAgents` also reach
other Helix sessions on the same machine.
**Install**
* `mutagent install helix` installs the `helix` binary, the same one the curl installer
puts in `~/.mutagent/bin`. The earlier plug-in install into Claude Code and Codex is retired; see
[Install Helix](/helix/install).
**Managed agents**
* `mutagent agent deploy ` checks, uploads and activates an `agent.md` folder, and
`mutagent helix agent @ -p ""` runs it in a cloud sandbox. `agent check` and
`agent pack` work locally, without a cloud sandbox.
* **Environments**: `mutagent env set` stores the variables and secrets an agent's tools need, per
workspace. Secrets are write-only: they are never printed back.
* `mutagent providers mirror` copies the LLM provider keys you signed in with in Helix into the
current workspace, when you ask it to.
* The Evaluate and Diagnose stages ship inside Helix only. The separate npm installs for them are
retired; install [Helix](/helix/install) instead.
This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.