zeekay
c74dc19e97
The 0.6.93 publish job got all the way to the end — notes verified, GitHub release created with 28 assets, Homebrew formula published — and then died on `npm whoami` with "npm auth failed", while the dedicated npm-auth-check job had validated the very same token an hour earlier in the same run. Both were right. They were talking to different registries. The repo's root .npmrc sets `registry=https://pkg.hanzo.ai/`, and npm gives the project file precedence over the user config that setup-node writes. So a bare `npm whoami` at the repo root asks our own registry to validate an npmjs token. pkg.hanzo.ai answers 200 with a body of `{}`. Older npm shrugged at that — which is why this step passed for 0.6.92 eight hours earlier — and the npm that ships with Node 24 reads it as "not logged in". The runners moved to Node 24 in between; the deprecation notice is in both logs. The publishes themselves were never affected, because each one runs `cd` into a package directory and npm does not search parent directories for .npmrc — so they used the user config and reached npmjs. That is a coincidence holding up the supply chain, not a design. So: name the registry on every npm call that talks to npmjs — whoami, publish, and the `npm view` probes that decide whether a version is already published and what the next version should be. Those last ones matter as much: they were asking a proxy what npmjs contains, and the answer gates both the version bump and the skip-if-already-published check. Also stopped swallowing npm's own error in the publish job's whoami. The generic "npm auth failed" message sent a real investigation toward the token, which was fine the whole time. Verified: cargo nextest run -p code-core --test hanzo_identity -> 4/4 pass; the workflow still parses and all six jobs are intact.
Hanzo Dev
Hanzo Dev is our coding agent. It runs in your terminal, reads and edits the
repository you point it at, runs commands in a sandbox, and drives a browser
when a task needs one. Models are served by Hanzo AI —
enso and the zen5 family — over the metered gateway at api.hanzo.ai.
It ships inside the Hanzo CLI. hanzo dev is the command.
 A session in progress |
 Reviewing a diff |
|---|---|
 Driving a browser |
 Several agents on one task |
Install
curl -fsSL https://hanzo.sh | sh
hanzo auth login
hanzo auth login signs you in through Hanzo IAM and links the machine to your
account. Then, from any repository:
hanzo dev
Give it the task on the command line to run headless instead:
hanzo dev "fix the failing tests in ./core and explain what was wrong"
Choosing a model
Model ids come from the gateway, which is the only authority on the catalog — there is no allowlist in the client.
hanzo dev --model enso # our frontier model
hanzo dev --model enso-ultra # the largest reasoning tier
hanzo dev --model zen5-coder # tuned for code
Browse everything available with curl https://catalog.hanzo.ai/v1/models.
Backends
Hanzo Dev is the default and the one we build. The same session launcher can also drive two other agents if you already have them installed, so you can keep one set of habits across all three:
hanzo dev # our agent (default)
hanzo dev claude # or: hanzo code --claude
hanzo dev codex # or: hanzo code --codex
hanzo dev is a spelling of hanzo code dev, not a second implementation —
every spelling resolves through the same launcher.
Options
hanzo dev [OPTIONS] [BACKEND|TASK] [TASK] [-- <PASSTHROUGH>...]
--model <MODEL> Gateway model id, e.g. enso, enso-ultra, zen5-coder
--backend <NAME> dev (default) | claude | codex
--brand <BRAND> Tenant for auth: hanzo | lux | zoo | pars | bootnode
--ask Ask before each action instead of auto-approving (alias: --safe)
--no-sandbox Drop the sandbox and auto-approve. Per-invocation, never persisted
--no-route Call the backend's own model account instead of the metered gateway
--no-mcp Do not attach the Hanzo MCP toolset
--project-mcp Also load the repo's own .mcp.json servers (off by default — a repo is untrusted)
--link / --no-link Stream the session to Hanzo cloud, or never
--resume <ID> Resume a prior linked session by its cloud session id
-c, --config <FILE> Use a specific config file
-v, --verbose Increase logging verbosity
Anything after -- is passed verbatim to the backend.
Two defaults worth knowing. Sessions run sandboxed and auto-approve inside that
sandbox; --ask tightens it, --no-sandbox removes it. Model calls route
through api.hanzo.ai so usage is metered on your Hanzo account; --no-route
sends them to the backend's own account instead.
In a session
Type / for the full list. The ones you will reach for:
/plan create a comprehensive plan (multiple agents)
/solve solve a challenging problem (multiple agents)
/code perform a coding task (multiple agents)
/auto work autonomously on long tasks with Auto Drive
/agents create and configure agents
/browser open the internal browser
/chrome connect to a running Chrome over CDP
/diff show the git diff, including untracked files
/review review your changes for potential issues
/undo restore the workspace to the last snapshot
/branch work on a branch in a worktree
/merge merge the worktree branch back to the default
/model choose model and reasoning effort
/reasoning change reasoning effort (minimal/low/medium/high)
/theme switch color themes
/status session configuration and token usage
/limits weekly and hourly rate limits
/mcp manage MCP servers (status/on/off/add)
/init write an AGENTS.md for this repository
/resume resume a past session for this folder
/new start a new chat
Full list with descriptions: docs/slash-commands.md.
Project context
Run /init in a repository and Hanzo Dev writes an AGENTS.md describing what
it found. Edit that file — it is read at the start of every session in that
directory, so it is where project conventions, architecture notes and "do not
touch this" rules belong.
Tools
The Hanzo MCP toolset is attached by default: filesystem, shell, browser, and
the rest of the Hanzo surface. Add your own servers with /mcp add, or per
repository in .mcp.json — the latter is off unless you pass --project-mcp,
because a repository you just cloned should not get to run a server with your
session's key.
Documentation
Building from source
git clone https://github.com/hanzoai/dev.git
cd dev
./build-fast.sh
./build-fast.sh is the required check — it must pass cleanly, warnings
included. See DEVELOPING.md and LLM.md for the
workspace layout and the rules that apply inside it.
Contributing
Branch, make the change, make ./build-fast.sh pass, open a pull request.
Bugs and feature requests: github.com/hanzoai/dev/issues.
License
Apache-2.0 — see LICENSE.
Lineage
Hanzo Dev is a fork of just-every/code, which is
itself a fork of openai/codex. Both are Apache-2.0,
and this repository preserves the upstream LICENSE and NOTICE. Hanzo Dev is not
affiliated with, sponsored by, or endorsed by either project.