activity-core/workplans/ACTIVITY-WP-0042-platform-backup-restore-evidence-scheduling.md
tegwick dcb5f7ddef
All checks were successful
CI Smoke / host-smoke (push) Successful in 0s
CI Smoke / container-smoke (push) Successful in 1s
Build and Publish Container Image / build-and-push (push) Successful in 1m22s
Keep backup subprocess output out of workflow evidence
Sanitize failures and returned summaries at the adapter boundary. Allowlist backup status values and preserve failure exit codes. Verify synthetic sensitive output cannot survive Python traceback or Temporal failure serialization.

Decision-Class: strengthen-existing-evidence-boundary

Delegation: explicit-user-task; Emergent-Security-A6

Evidence: full-suite-676-passed-1-skipped; final-focused-48-passed; no-new-lint-findings

Assistant: codex
Assistant-Model: gpt-6-astra
Assistant-Session: 01a100de-2e1c-7e23-9ae9-2da0e0499411
2026-10-03 14:57:31 +02:00

10 KiB

id type title domain repo status owner topic_slug created updated state_hub_workstream_id
ACTIVITY-WP-0042 workplan Scheduling role for recurring platform backup/restore evidence runs infotech activity-core active codex activity-core 2026-10-03 2026-10-03 e1bfb5a4-e647-592d-883f-fe8728ad2f5f

Origin: State Hub message e3668cd9 from railiance-platform (RPF-WP-0036-T03, RPF-WP-0038-T04) proposing activity-core as execution owner for recurring backup/restore evidence runs. Scheduling/dispatch remains within the existing activity-core intent and the platform owner's scheduling-only consent. The user directed continuation under Emergent Security on 2026-10-03; offline contract development is active. New recovery execution and live activation remain gated.

Facts from the repo (2026-10-03):

  • daily-cnpg-option-a-backup already runs a cron-scheduled bounded operation (cnpg_option_a_backup, ACT-ADR-007) with state-hub-progress evidence. Its definition targets the Nextcloud lane and covers forgejo-db, net-kingdom-pg, state-hub-db; it does not cover apps-pg/platform-pg/platform-pg-2 or the Scaleway primary, and it never performs restores.
  • ACT-ADR-007 allowlist is closed. A restore-evidence or Scaleway-backup run needs a new code-registered operation plus an ADR successor, tests, a credential route and an evidence contract. A definition string cannot add one.
  • The old expired-token finding is superseded: RPF-WP-0045 replaced static tokens with Kubernetes auth. On 2026-10-03, read-only railiance01 inspection confirmed openbao-activity-core Ready/Valid and actcore-backup-offsite Ready/SecretSynced (refresh 09:29:02Z). This verifies the existing Nextcloud lane only; new recovery authority and credential scope remain unapproved.

Decide whether activity-core accepts the scheduling role

id: ACTIVITY-WP-0042-T01
status: done
needs_human: false
decision_id: 5ec92a02-cb0b-466d-9aaf-9da5ffc6c92d
blocking_reason: null
priority: high
state_hub_task_id: "2a368988-2611-596a-a847-82c048bd179e"

Founder decision. Options: accept scheduling only (when/what/where; S3 keeps validators, cadence, expiry and evidence), accept scheduling plus a bounded operation, or decline. Needs: restore execution stays with an S3-owned tool invoked as a fixed bounded operation; approval-engine authority supplied per run; no general executor behaviour.

2026-10-03 (CUST-WP-0075 inbox sweep): railiance-platform replied (message 0638c13b) asking activity-core to proceed under its conditions, because "roles tie to the source repo". That is the S3 owner's consent. It does not resolve this founder gate, so T01 stays waiting on D2 and the plan stays proposed. It also asks activity-core to declare atm-backup-daily, which remains T03's founder confirmation. activity-core replied with the same position.

2026-10-03: human gate routed to hub decision 89f1058f-33bc-47a8-8a49-0b44d426c67e (D2: ArgoCD owns production: go-ahead sequence for railiance-apps-root, issue-core, policy-nexus and activity-core automation) by CUST-WP-0075; resolving that decision raises C-40 here.

2026-10-03 superseding scope clarification: the user explicitly directed continuation under emergent-security/emergent-security-agent.md. Apply C4, A2 and A6 to the already-owned scheduling/dispatch role in INTENT.md, with platform owner consent in message 0638c13b. No new responsibility or runtime capability is being claimed (C3/A5). The redundant blanket role gate is closed; proceed with offline contract code/tests. Per-run authority remains an executing platform enforcement point's responsibility (C2/C9). This is an autonomous scope clarification, not a human answer to D2; D2's other gates and T03 remain.

Admit a bounded operation and credential lane

id: ACTIVITY-WP-0042-T02
status: progress
depends_on: [ACTIVITY-WP-0042-T01, ACTIVITY-WP-0042-T05]
priority: medium
state_hub_task_id: "250c6e8e-7281-5dec-9a92-06081b8c96bb"

Offline contract development is authorized by the explicit task and existing scheduling scope. Actual operation admission waits on T05. Any new local bounded operation still requires a successor to ACT-ADR-007, registry entry (target bounds, timeout, idempotency, dry_run explicit), tests, credential route via OpenBao (owner railiance-platform; existing store health verified), and non-secret evidence mode. Scheduled caller satisfies RPF-WP-0038-T04 only once recurring tiered scheduling and retention are accepted by their owners.

Offline candidate implemented in src/activity_core/recovery_contract.py: closed request/receipt envelopes, explicit mode, run/authority-reference correlation, owner-supplied freshness window, cleanup proof and safe errors. No runner call, credential acquisition or allowlist change. Owner contract acceptance and live proof remain incomplete; T02 is not done.

Answer ops-warden on atm-backup-daily

id: ACTIVITY-WP-0042-T03
status: wait
needs_human: true
decision_id: 89f1058f-33bc-47a8-8a49-0b44d426c67e
blocking_reason: "Founder must confirm whether activity-core's backup worker is the atm-backup-daily unit before declaring to ops-warden."
priority: low
state_hub_task_id: "e1c313dc-9a94-5b7c-b406-604b700bf3eb"

WARDEN-WP-0040 asks which owner declares workload resolution backup-daily for atm-backup-daily. activity-core has no atm-* identity of its own in this repo and no evidence that the actor was minted for its worker. Declare only if the founder confirms activity-core's backup worker is that unit; otherwise the declaring owner is whoever holds the actor's issuance (railiance-platform was also asked). Never infer membership.

2026-10-03: human gate routed to hub decision 89f1058f-33bc-47a8-8a49-0b44d426c67e (D2: ArgoCD owns production: go-ahead sequence for railiance-apps-root, issue-core, policy-nexus and activity-core automation) by CUST-WP-0075; resolving that decision raises C-40 here.

Prepare the concrete scheduling and runner proposal

id: ACTIVITY-WP-0042-T04
status: done
priority: high
state_hub_task_id: "859e8857-ea51-5147-bd3a-70acac1426dc"

User requested investigation and forward progress on 2026-10-03. Reviewed the existing definition, bounded-operation registry, platform recovery entry points, credential route and actor declaration. Removed the stale ESO blocker after a fresh metadata-only check. Concrete recommendation and staged acceptance: docs/platform-recovery-scheduling-plan.md.

Recommend scheduling-only ownership; platform retains the recovery runner and policy. First proposed slice is one disabled/manual apps-pg recovery-evidence operation, with offline contract tests before any live admission. T01 is still an explicit role choice; this investigation does not record acceptance of it or resolve the broader D2 decision. The actor ownership question is separate.

Agree the platform runner contract

id: ACTIVITY-WP-0042-T05
status: wait
priority: high
depends_on: [ACTIVITY-WP-0042-T01]
blocking_reason: "Platform owner must accept the candidate request/receipt contract, execution authority checks, limits and credential scope before runtime wiring."
state_hub_task_id: "a2d95c80-bfc5-54b7-9987-ad3571d9c75f"

Use the contract table in docs/platform-recovery-scheduling-plan.md for an owner review: authority verification, exact target, implementation version, durable run receipts, overlap/retry behavior, cleanup, resource ceilings and credential scope. Existing restore CLIs are not an admitted unattended API. This task records the dependency; no external acceptance or message is claimed. T02 implements/adopts the agreed contract; T03 does not gate offline design.

Decision record — Emergent Security application

  • Decision class: task-scoped code/tests and scheduling-boundary clarification.
  • Delegator: the user who requested ACTIVITY-WP-0042 progress and explicitly directed use of Emergent Security agent guidance in this conversation.
  • Scope: activity-core repository development in the build estate; no tenant effect, production mutation, identity assignment, or recovery credential use.
  • Rules: C4 lowest sufficient scope; A2 proceed within the task; A6 code/tests; C3/A5 no new capability or unowned responsibility; C2/C9 authority enforcement stays with the platform executor; A8 this record and commit evidence.
  • Evidence: INTENT.md scheduling boundary, ACT-ADR-007 existing allowlist, platform consent 0638c13b, offline adversarial contract tests.
  • Outcome: active offline implementation, T01 done; T05 and T03 retain their specific unresolved requirements. The broader D2 decision is unchanged.

Validation (2026-10-03): full activity-core suite 653 passed, 1 skipped; focused recovery-contract/bounded-operation suite 43 passed; Ruff and git diff --check clean. No runtime wiring, new operation registration, credential fetch, or live restore was performed. Decision receipt: 5ec92a02-cb0b-466d-9aaf-9da5ffc6c92d (codex scope clarification; D2 unchanged).

Harden the existing backup evidence boundary

id: ACTIVITY-WP-0042-T06
status: done
priority: high

User requested the follow-up backup error-handling fix. Enforce ACT-ADR-007's existing non-secret evidence constraint and Emergent Security C2/C6/C9 without changing execution scope: discard raw subprocess stderr/targets/errors at the adapter boundary, suppress unsafe exception causes, and allowlist status values. Exercise malformed output, timeout/launch/decode failures, failure exit codes, and Temporal failure serialization with synthetic secret canaries. Preserve normal/degraded backup summaries and surface negative signal exit codes.

Decision class: task-scoped code/tests; delegation: explicit user task and Emergent Security A6; no credentials, live effects, or policy widening.

T06 result: the resolver returns the existing allowlisted evidence shape directly; raw output never escapes in returned results or serialized Temporal failures. Known status values are preserved; unknown status content becomes unknown. Unexpected exit codes cannot claim success, and negative signal codes survive. Validation: 676 passed, 1 skipped in the full suite; final focused backup, bounded-operation and evidence-sink checks 48 passed. Ruff baseline comparison shows no introduced findings (five pre-existing findings remain across the changed files); git diff --check passes. This is source hardening only, not a worker rollout or execution-authority change.