coulomb/rein-aharness
4
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
rein-aharness/workplans/REINAH-WP-0005-ops-run-claim-loop.md
codex 7c8f7e6a9e fix(workplans): move work-record identifiers onto the repository prefix 
Identifiers predating the PREFIX-WP-NNNN convention were rejected by the canon
registry, so none of this repository's work records could be registered.

One prefix per repository (ADR-007). Existing conforming identifiers keep their
numbers where possible; the pre-convention records take the next free numbers
rather than renumbering work that was already correct.

Projection UUIDs are re-derived from the new canonical ids (ADR-007 decision 2).
Nothing was registered on central under the old identifiers, so no hub record is
orphaned by this.

Refs CUST-WP-0068-T03

Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 2583210@bnt-lap001
Assistant-Session: f2bff2d5-e9b2-4338-92ca-10282a927006
2026-08-25 22:42:27 +02:00

5.4 KiB
Raw Permalink Blame History

id type title domain repo status owner topic_slug priority created updated depends_on related state_hub_workstream_id
REINAH-WP-0005 workplan Ops run claim loop and approach selection agents rein-aharness finished grok rein-aharness high 2026-08-03 2026-08-08
ACTIVITY-WP-0026
ACT-ADR-005
HARNESS-WP-0001
7d023961-af5b-59dc-96ec-85d45f67cfa4

REINAH-WP-0005 — Ops run claim loop and approach selection

Origin

ACT-ADR-005. Closes the dual-clock residual: host systemd timers currently execute Binky/FI while activity-core schedules separately. rein-aharness already polls issue-core (docs/task-intake.md); that path is wrong for internal ops under WP-0022 and issue-core INTENT.

Goal

  1. Claim ops_run from activity-core (not issue-core / not Forgejo).
  2. Select an efficient approach (adapter table) and execute.
  3. Complete/fail the ops_run + domain completion events.
  4. Cut over FI and Binky off dual wall-clock timers once proven.

Tasks

T01 — activity-core ops_run client

id: REINAH-WP-0005-T01
status: done
priority: high
state_hub_task_id: "88918e05-6425-5746-880b-9791754e4992"

Client module (env: ACTIVITY_CORE_URL, worker credential):

  • claim(worker_id, labels=…)
  • heartbeat / complete / fail

Map ops_run → existing TaskSpec (or thin OpsRunSpec). Tests with httpx mock.

Blocked on: ACTIVITY-WP-0026-T01 API shape (can stub against openapi draft).

Done when: unit tests green; CLI poll --source=ops-run prototype optional.

T02 — Approach registry (v1 static)

id: REINAH-WP-0005-T02
status: done
priority: high
state_hub_task_id: "addb9fb3-6233-506c-aea0-987d59a368a0"

Central table/config (code registry, not per-repo cron):

Match (labels / definition id contains) Approach command
research-brief or fi-daily fi-research-brief
rhythm + binky / binky-daily brief-daily
mail-intake mail-scan then optional mail-triage
agent-session run with persona/profile
unmatched fail ops_run with clear reason

Document how to add rows. Prefer cheapest correct path (deterministic before agent session; structured llm-connect before open-ended coding agent).

Done when: pure function tests for match → approach.

T03 — Continuous claim worker

id: REINAH-WP-0005-T03
status: done
priority: high
state_hub_task_id: "b23c3c6f-d826-5cf5-80c1-5a8c424b8ecc"
  • rein-aharness claim-loop (or systemd/service unit): poll interval, lease heartbeat, concurrency 1 default.
  • On success: domain completion already done by approach; close ops_run.
  • On failure: fail ops_run; do not silent drop.
  • Metrics/log for SLA.

Done when: can run against railiance actcore-api with a test ops_run.

T04 — Map FI + Binky definitions

id: REINAH-WP-0005-T04
status: done
priority: high
state_hub_task_id: "12cdf6c0-b847-5d9d-9fc1-c4bc977d8216"
  • FI labels already include research-brief + automated.
  • AGENT_HARNESS_REPO_MAP documented in claim-loop.env.example + ops-run-claim-loop.md.
  • Install: deploy/scripts/install-claim-loop-user.sh.

Prod e2e 2026-08-03: FI trigger → ops_run claimed by rein-aharness@railiance01 → approach fi-research-brief → succeeded (skipped existing brief). User unit rein-aharness-claim-loop.service active. Proof window for timer cutover (T05) starts here.

T05 — Cutover: timers become break-glass

id: REINAH-WP-0005-T05
status: done
priority: medium
state_hub_task_id: "3691c38b-e96c-51d6-a115-015959813afc"

Procedure landed: deploy/docs/timer-cutover.md + FI docs/recurrence-ops.md updated for claim-loop primary / timer break-glass.

Completed on railiance (verified 2026-08-08):

  1. Five-cycle proof table filled from production claim-loop journal (eight clean FI/Binky cycles observed in total).
  2. FI host timer is disabled/inactive; Binky host timer is not installed and inactive.
  3. Install scripts and manual service starts remain documented for break-glass.

Done when: docs + railiance state match; dual-clock residual closed for FI/Binky.

T06 — Deprecate issue-core as ops intake for automation

id: REINAH-WP-0005-T06
status: done
priority: medium
state_hub_task_id: "2fdb2224-be7d-5933-925e-ecf6cd2e4734"
  • docs/task-intake.md: issue-core poll = legacy / external ticket path only.
  • ops_run = primary for activity-core automation labels.
  • No Gitea references; Forgejo only if mentioning self-hosted forge projection.

Done when: docs and CLI help text consistent with ACT-ADR-005.

Acceptance

  • Claim loop does not require Forgejo or issue-core for FI/Binky ops
  • Approach table selects fi-research-brief / brief-daily without host “schedule”
  • Timers demoted after proof window (T05)
  • ACT-ADR-005 / ACTIVITY-WP-0026 contracts implemented

Shipped: ops_run_client, approaches, claim_loop, CLI claim-loop / run --from-ops-run / poll --source=ops-run, unit tests, install + cutover docs.

Residual handoff: REIN-A-0003 captures the separately observed unmatched Binky weekly-review ops run; it does not reopen the completed FI/Binky daily cutover scope.

Out of scope

  • Implementing ops_run schema (ACTIVITY-WP-0026)
  • issue-core Forgejo backend fixes
  • Full glas-harness multi-rein routing