bot/docs/tools/runbook.md

title, summary, description, read_when

title	summary	description	read_when
Runbook	Typed workflow runtime for HanzoBot with resumable approval gates.	Typed workflow runtime for HanzoBot — composable pipelines with approval gates.	You want deterministic multi-step workflows with explicit approvals You need to resume a workflow without re-running earlier steps

Runbook

Runbook is a workflow shell that lets HanzoBot run multi-step tool sequences as a single, deterministic operation with explicit approval checkpoints.

Hook

Your assistant can build the tools that manage itself. Ask for a workflow, and 30 minutes later you have a CLI plus pipelines that run as one call. Runbook is the missing piece: deterministic pipelines, explicit approvals, and resumable state.

Why

Today, complex workflows require many back-and-forth tool calls. Each call costs tokens, and the LLM has to orchestrate every step. Runbook moves that orchestration into a typed runtime:

• One call instead of many: HanzoBot runs one Runbook tool call and gets a structured result.
• Approvals built in: Side effects (send email, post comment) halt the workflow until explicitly approved.
• Resumable: Halted workflows return a token; approve and resume without re-running everything.

Why a DSL instead of plain programs?

Runbook is intentionally small. The goal is not "a new language," it's a predictable, AI-friendly pipeline spec with first-class approvals and resume tokens.

• Approve/resume is built in: A normal program can prompt a human, but it can’t pause and resume with a durable token without you inventing that runtime yourself.
• Determinism + auditability: Pipelines are data, so they’re easy to log, diff, replay, and review.
• Constrained surface for AI: A tiny grammar + JSON piping reduces “creative” code paths and makes validation realistic.
• Safety policy baked in: Timeouts, output caps, sandbox checks, and allowlists are enforced by the runtime, not each script.
• Still programmable: Each step can call any CLI or script. If you want JS/TS, generate .runbook files from code.

How it works

HanzoBot launches the local runbook CLI in tool mode and parses a JSON envelope from stdout. If the pipeline pauses for approval, the tool returns a resumeToken so you can continue later.

Pattern: small CLI + JSON pipes + approvals

Build tiny commands that speak JSON, then chain them into a single Runbook call. (Example command names below — swap in your own.)

inbox list --json
inbox categorize --json
inbox apply --json

{
  "action": "run",
  "pipeline": "exec --json --shell 'inbox list --json' | exec --stdin json --shell 'inbox categorize --json' | exec --stdin json --shell 'inbox apply --json' | approve --preview-from-stdin --limit 5 --prompt 'Apply changes?'",
  "timeoutMs": 30000
}

If the pipeline requests approval, resume with the token:

{
  "action": "resume",
  "token": "<resumeToken>",
  "approve": true
}

AI triggers the workflow; Runbook executes the steps. Approval gates keep side effects explicit and auditable.

Example: map input items into tool calls:

gog.gmail.search --query 'newer_than:1d' \
  | hanzo-bot.invoke --tool message --action send --each --item-key message --args-json '{"provider":"telegram","to":"..."}'

JSON-only LLM steps (llm-task)

For workflows that need a structured LLM step, enable the optional llm-task plugin tool and call it from Runbook. This keeps the workflow deterministic while still letting you classify/summarize/draft with a model.

Enable the tool:

{
  "plugins": {
    "entries": {
      "llm-task": { "enabled": true }
    }
  },
  "agents": {
    "list": [
      {
        "id": "main",
        "tools": { "allow": ["llm-task"] }
      }
    ]
  }
}

Use it in a pipeline:

hanzo-bot.invoke --tool llm-task --action json --args-json '{
  "prompt": "Given the input email, return intent and draft.",
  "input": { "subject": "Hello", "body": "Can you help?" },
  "schema": {
    "type": "object",
    "properties": {
      "intent": { "type": "string" },
      "draft": { "type": "string" }
    },
    "required": ["intent", "draft"],
    "additionalProperties": false
  }
}'

See LLM Task for details and configuration options.

Workflow files (.runbook)

Runbook can run YAML/JSON workflow files with name, args, steps, env, condition, and approval fields. In HanzoBot tool calls, set pipeline to the file path.

name: inbox-triage
args:
  tag:
    default: "family"
steps:
  - id: collect
    command: inbox list --json
  - id: categorize
    command: inbox categorize --json
    stdin: $collect.stdout
  - id: approve
    command: inbox apply --approve
    stdin: $categorize.stdout
    approval: required
  - id: execute
    command: inbox apply --execute
    stdin: $categorize.stdout
    condition: $approve.approved

Notes:

• stdin: $step.stdout and stdin: $step.json pass a prior step’s output.
• condition (or when) can gate steps on $step.approved.

Install Runbook

Install the Runbook CLI on the same host that runs the HanzoBot Gateway (see the Runbook repo), and ensure runbook is on PATH.

Enable the tool

Runbook is an optional plugin tool (not enabled by default).

Recommended (additive, safe):

{
  "tools": {
    "alsoAllow": ["runbook"]
  }
}

Or per-agent:

{
  "agents": {
    "list": [
      {
        "id": "main",
        "tools": {
          "alsoAllow": ["runbook"]
        }
      }
    ]
  }
}

Avoid using tools.allow: ["runbook"] unless you intend to run in restrictive allowlist mode.

Note: allowlists are opt-in for optional plugins. If your allowlist only names plugin tools (like runbook), HanzoBot keeps core tools enabled. To restrict core tools, include the core tools or groups you want in the allowlist too.

Example: Email triage

Without Runbook:

User: "Check my email and draft replies"
→ hanzo-bot calls gmail.list
→ LLM summarizes
→ User: "draft replies to #2 and #5"
→ LLM drafts
→ User: "send #2"
→ hanzo-bot calls gmail.send
(repeat daily, no memory of what was triaged)

With Runbook:

{
  "action": "run",
  "pipeline": "email.triage --limit 20",
  "timeoutMs": 30000
}

Returns a JSON envelope (truncated):

{
  "ok": true,
  "status": "needs_approval",
  "output": [{ "summary": "5 need replies, 2 need action" }],
  "requiresApproval": {
    "type": "approval_request",
    "prompt": "Send 2 draft replies?",
    "items": [],
    "resumeToken": "..."
  }
}

User approves → resume:

{
  "action": "resume",
  "token": "<resumeToken>",
  "approve": true
}

One workflow. Deterministic. Safe.

Tool parameters

run

Run a pipeline in tool mode.

{
  "action": "run",
  "pipeline": "gog.gmail.search --query 'newer_than:1d' | email.triage",
  "cwd": "workspace",
  "timeoutMs": 30000,
  "maxStdoutBytes": 512000
}

Run a workflow file with args:

{
  "action": "run",
  "pipeline": "/path/to/inbox-triage.runbook",
  "argsJson": "{\"tag\":\"family\"}"
}

resume

Continue a halted workflow after approval.

{
  "action": "resume",
  "token": "<resumeToken>",
  "approve": true
}

Optional inputs

• cwd: Relative working directory for the pipeline (must stay within the current process working directory).
• timeoutMs: Kill the subprocess if it exceeds this duration (default: 20000).
• maxStdoutBytes: Kill the subprocess if stdout exceeds this size (default: 512000).
• argsJson: JSON string passed to runbook run --args-json (workflow files only).

Output envelope

Runbook returns a JSON envelope with one of three statuses:

• ok → finished successfully
• needs_approval → paused; requiresApproval.resumeToken is required to resume
• cancelled → explicitly denied or cancelled

The tool surfaces the envelope in both content (pretty JSON) and details (raw object).

Approvals

If requiresApproval is present, inspect the prompt and decide:

• approve: true → resume and continue side effects
• approve: false → cancel and finalize the workflow

Use approve --preview-from-stdin --limit N to attach a JSON preview to approval requests without custom jq/heredoc glue. Resume tokens are now compact: Runbook stores workflow resume state under its state dir and hands back a small token key.

OpenProse

OpenProse pairs well with Runbook: use /prose to orchestrate multi-agent prep, then run a Runbook pipeline for deterministic approvals. If a Prose program needs Runbook, allow the runbook tool for sub-agents via tools.subagents.tools. See OpenProse.

Safety

• Local subprocess only — no network calls from the plugin itself.
• No secrets — Runbook doesn't manage OAuth; it calls HanzoBot tools that do.
• Sandbox-aware — disabled when the tool context is sandboxed.
• Hardened — fixed executable name (runbook) on PATH; timeouts and output caps enforced.

Troubleshooting

• runbook subprocess timed out → increase timeoutMs, or split a long pipeline.
• runbook output exceeded maxStdoutBytes → raise maxStdoutBytes or reduce output size.
• runbook returned invalid JSON → ensure the pipeline runs in tool mode and prints only JSON.
• runbook failed (code …) → run the same pipeline in a terminal to inspect stderr.

Learn more

• Plugins
• Plugin tool authoring

Case study: community workflows

One public example: a “second brain” CLI + Runbook pipelines that manage three Markdown vaults (personal, partner, shared). The CLI emits JSON for stats, inbox listings, and stale scans; Runbook chains those commands into workflows like weekly-review, inbox-triage, memory-consolidation, and shared-task-sync, each with approval gates. AI handles judgment (categorization) when available and falls back to deterministic rules when not.

• Thread: https://x.com/plattenschieber/status/2014508656335770033
• Repo: https://github.com/bloomedai/brain-cli