runbook-tutorials/workplans/RBT-WP-0006-execution-mode-and-pack-index.md
custodian-sync 32dbf75d5a
Some checks are pending
CI Smoke / host-smoke (push) Waiting to run
CI Smoke / container-smoke (push) Waiting to run
Tests / tests (push) Waiting to run
Work Records / validate (push) Waiting to run
chore(consistency): renormalize lifecycle state [auto]
Updated by fix-consistency on 2026-09-29:
  - workplan status: backlog → active

Assistant: claude-code
Assistant-Model: sonnet
Assistant-Process: 295952@bnt-lap001
Assistant-Session: e93f64ad-516c-46eb-9666-aad8d300c477
2026-09-29 21:46:10 +02:00

4 KiB

id type title domain repo status flavor owner topic_slug created updated depends_on state_hub_workstream_id
RBT-WP-0006 workplan Execution mode and multi-repo pack index infotech runbook-tutorials active implementation claude stack 2026-09-29 2026-09-29
RBT-WP-0004
35196f02-7cb9-5706-9529-1cba9c736058

Goal

Backlog (2026-09-29). Later capabilities, deliberately not started, each waiting for a decision from Bernd: opt-in execution of steps (auto-pilot), discovery of packs across the estate, a runbook-aware feedback assistant, dependencies between runbooks, a terminal walk-through, the v0.3 design that closes the gaps in docs/console-mapping.md, and an optional security and code review. Nothing here blocks the finished runbook-tutorials workplans.

Opt-in, audited step execution

id: RBT-WP-0006-T01
status: wait
needs_human: true
blocking_reason: "Needs a decision on which identity runs the command."
priority: low
state_hub_task_id: "0424deab-3b51-5222-80b1-54c0ea26928d"

Per-step execute: true allowed only for read-only steps first, with an explicit operator confirmation, timeouts, and an audit record. Needs a decision on which identity runs the command.

Cross-repo pack index

id: RBT-WP-0006-T02
status: wait
needs_human: true
blocking_reason: "Needs a decision on scan scope."
priority: low
state_hub_task_id: "0cfb69bc-dc7e-5960-8359-64c49a742a6e"

rtut list --estate scans registered repos for runbooks/*/pack.yaml and publishes a capability entry in the registry. Needs a decision on scan scope.

Runbook-aware feedback assistant

id: RBT-WP-0006-T03
status: wait
needs_human: true
blocking_reason: "Needs decisions on access, identity and what is sent where."
priority: low
state_hub_task_id: "ce82d1ae-76a3-59c8-9d26-4813e8dc9745"

Operator feedback on a step feeds an assistant that knows the runbook and may diagnose the deployment (read-only access first), giving a feedback, retry, feedback, confirm loop. Needs decisions on access, identity and what is sent where.

Dependencies between runbooks

id: RBT-WP-0006-T04
status: wait
needs_human: true
blocking_reason: "Needs a decision on how a pack in another repo is identified and trusted."
priority: low
state_hub_task_id: "acd969c3-3bd4-5953-9f9a-8ad8c5d8e380"

Packs declare requires_packs with a required result (exercised, or a named gate passed), instead of deeper nesting (v0.2 caps nesting at three levels). Needs a decision on how a pack in another repo is identified and trusted.

Terminal walk-through

id: RBT-WP-0006-T05
status: wait
needs_human: true
blocking_reason: "Needs a decision whether hosts without a browser justify it; the CLI already covers v0.1 runs (moved from RBT-WP-0004-T03)."
priority: low

rtut run <pack> walking a run in the terminal, for hosts without a browser. v0.2 runs can be driven from the engine and the UI, not yet from a terminal.

v0.3: close the console gaps

id: RBT-WP-0006-T06
status: wait
needs_human: true
blocking_reason: "Needs a decision to start a v0.3 design: conditional applicability (G1), longer horizons (G2), gate recheck (G3), value predicates (G4), local-only attributes (G5), outputs feeding later members (G7). G6 is T01."
priority: medium

The gaps in docs/console-mapping.md. Closing G1, G3 and G7 is also the precondition for extracting the console's engine parts and for modeling the security bootstrap as a project (the cancelled RBT-WP-0005-T04).

Security and code review

id: RBT-WP-0006-T07
status: wait
needs_human: true
blocking_reason: "Optional follow-up agreed with Bernd on 2026-09-29: the workplans close without it. Needs a decision when to run it."
priority: medium

Run the security review and the code review over the engine and the UI: it serves files (artefacts, records), writes YAML (projects, attribute sets), uses shell=True for operator-confirmed verify commands, and takes form input on localhost. Also first execution of .forgejo/workflows/tests.yaml on a real runner.