Packages

@flue/sdk

2.3.1 · 18 Nov 2026Apache-2.0309.1k / weekRepositoryHomepagenpmAtom feed

Upgrading @flue/sdk From 0.3.11 to 0.4.0

1 release in betweenevery note read

Other targets from 0.3.11Newest 0.x0.11.1Latest2.3.1
  1. 0.3.11yours
  2. 0.4.0target
12
changes to make
0
advisories fixed
21
new
0
fixes

Before you upgrade

Tick each one off as you go
  • Breaking0.4.0
  • Breaking0.4.0
  • Breaking0.4.0
  • Breaking0.4.0
  • Breaking0.4.0
  • Breaking0.4.0
  • Breaking0.4.0
  • Breaking0.4.0
  • Breaking0.4.0
  • Breaking0.4.0

Release by release

  1. 0.4.0

    Migration needed10 May 202621 new
    • Breaking

      There are some breaking changes to be aware of, when upgrading from v0.3 to v0.4.

    • Breaking

      commands and defineCommand are removed. The original idea — register first-party CLI tools the agent could shell out to — only worked under just-bash and saw little real use. The same surface is better expressed today by passing env to scope what a connector sees, or by choosing a sandbox connector that gives you the isolation you want. just-bash itself still supports custom commands — you just register them on your bash instance directly instead of through Flue's helper. Removed: the commands?: option on init() / prompt() / skill() / task() / shell(); the Command, CommandDef, CommandOptions, CommandExecutor, CommandExecutorResult types; the defineCommand export from @flue/sdk/node and @flue/sdk/cloudflare; the command_start / command_end FlueEvent variants; and the BashLike.registerCommand / SessionEnv.scope connector hooks.

    • Breaking

      Default thinkingLevel changed from 'off' to 'medium'. Reasoning-capable models (e.g. gpt-5, claude-opus-4-7) will now reason by default on every prompt() / skill() / task() call. Non-reasoning models are unaffected (clamped to 'off' per the model's thinkingLevelMap). To restore the old behavior, set thinkingLevel: 'off' explicitly on init(), your role frontmatter, or the call options.

    • Breaking

      sandbox: 'local' now runs locally. Originally, 'local' was a half-isolated layer — a just-bash subprocess with a ReadWriteFs / MountableFs overlay mounting process.cwd() at /workspace. That made sense when every Flue agent ran on a developer laptop, but increasingly people are deploying the agent itself inside a real sandbox (a container, a microVM, a Cloudflare Sandbox), where wrapping the host in a second virtual filesystem is pure overhead — and actively confusing, because paths get remapped twice. sandbox: 'local' now binds directly to the host: exec runs through the user's shell with full process.env, file methods hit the real filesystem, default cwd is process.cwd(), and there are no path remappings or command restrictions. Agents that hard-coded /workspace paths must migrate to real host paths. If you want isolation on a developer laptop, reach for a real sandbox connector (Daytona, E2B, Mirage, etc.).

2 other lines we could not sort, mostly version bumps
  • With the new 'local' sandbox, the host shell is exposed directly. The agent's bash tool can run gh issue view, npm test, etc. with whatever's on $PATH and whatever env you launched flue with. The runner / container / VM is the isolation boundary.

    0.4.0
  • For non-'local' sandboxes, install the binaries inside the sandbox image, or wrap the operation as a custom tool with init({ tools: [...] }). Tools have a structured parameter schema, are visible to the model directly, and recover the "secrets stay on the host" property — the tool reads process.env, the agent only sees the tool's params and result.

    0.4.0

A whole project to check? Paste its package.json in the dependency check: every deprecated, outdated or vulnerable dependency, with what to upgrade to. Free, no account.