These files carried no type field at all. Selection is by 'type: workplan', so
they were invisible to every projection while the hub held a record for each —
and a forge-derived reset read those correct records as no longer deriving and
queued them for retirement.
Only the type line is added.
Refs STATE-WP-0083-T05
Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 2583210@bnt-lap001
Assistant-Session: f2bff2d5-e9b2-4338-92ca-10282a927006
qonto-assistant (sibling repo) already shipped Phase 1 (QONTO-WP-0002)
and Phase 2 MCP surface (QONTO-WP-0003), both finished, 31 tests
passing, ahead of this workplan's original sequencing. Reconciled
T02-T04 against what actually landed there instead of duplicating it.
The one piece qonto-assistant explicitly left for this repo -- the
CostRunRate consumer cutover -- is implemented here:
scripts/qonto-costrunrate-refresh.py calls GET /v1/snapshot and writes
dated, redacted evidence under finance/ for a human to reconcile
against CostRunRate.md. Verified end-to-end against a local
fixture-backed qonto-assistant instance (no real credentials); a real
pull against the live account awaits qonto-assistant getting an actual
deployment, called out as a known gap rather than faked.
Workplan closed (status: finished); remaining gaps (OIDC federation,
harness tool profile registration, Phase 3/4) are carried forward in
qonto-assistant's own closure notes, not duplicated here.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Tracks the Phase 1 scope from the architecture blueprint (policy kernel
+ REST, no MCP yet): ratify the five blueprint decisions, service
skeleton with default-deny policy, REST surface + CostRunRate cutover,
smoke tests and closure/handoff to Phase 2.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Align AGENTS, AutonomyPolicy, SCOPE, OperatingRhythm with fleet residual
role (live intakes, not SCOPE prose). Capture BINKY-WP-0006 leftovers as
AWQ-011 (brief-weekly) and AWQ-012 (open-weights retarget).
Host LLM_CONNECT_URL discovery uses ClusterIP when DNS is unreachable;
mail path fails hard if triage fails. Mark T06 done and workplan finished;
update residual docs (OperatingRhythm, cutover runbook, llm-rhythm).
Reject Claude Code (or any coding agent) on railiance01. Mail-scan stays
deterministic; triage/briefs use llm-connect HTTP → structured JSON →
deterministic apply. Document in integrations/railiance-llm-rhythm.md and
rewrite WP-0006 tasks accordingly; timers no longer require_claude.
Live custody path tenants/binky/qonto-api (API_KEY/API_USER). First read-only
thirdparty pull (122 txs): desk 297.50 €/mo, Qonto plan 70.80 €/mo, main
balance 2185.94 €. Evidence under finance/; workplan status finished.
Prepare first-pull path after DEC-2026-004: copy-paste founder provision,
CCR apply, catalog promote, and CostRunRate update steps. T05 still waits
on Red-lane API key provision.
Extend .kaizen/schedule.yml with harness fields for daily rhythm, weekly
mail intake, and weekly review-prep; add task files, onboarding handoff
doc, and cutover gate updates for BINKY-WP-0004-T06.
- Lane 1 (LLM provider): reuse verified — warden catalog
openrouter-llm-connect, policy workload-kv-read-llm-connect-provider-secrets
- Lane 2 (forgejo deploy key): new, per-repo write deploy key design,
founder Red lane
- Lane 3 (mail-scan AppRole): executor-worker-binky-mail bound to the
existing IMAP read policy — closes email checklist item 9's auth
blocker on paper; provisioning founder Red lane
- No secret values anywhere; T04 can proceed on Lane 1 alone
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- .kaizen/schedule.yml scaffolded via schedule init, validates clean
(coach + optimization weekly, tdd-workflow disabled)
- DEC-2026-002 prepared: executor worker in a new small repo, per
ADR-005 boundaries; fallback allows sandbox prototype, no cutover
before resolution
- Decision rationale recorded in the executor assessment
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Evidence from 2binky archive: FSW DATEV pass-through 483,69 EUR/yr, HUB31
desk contract renewed to 2027-04, private-card company costs (bubble.io,
AI subs), open 450 EUR Binect receivable. Audit corrected: desk landlord
is HUB31; Binect is income side.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Company-agnostic flagship-offer template generalized from the Binky
dogfood run. audit-core assessed as home candidate — it owns audit event
logging, not company audits, so the template stays in binky-control.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Headless lane-restricted rhythm session script and enable/disable docs in
OperatingRhythm.md. Crontab installation itself is a one-line founder
action — the permission layer refuses agent-installed persistence, which
is the correct boundary.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Runbook for early-August command day (StB call, DUO backlog, Qonto review,
HR excerpt); all 4 office-hour items marked prepared; workplan status done
in file and hub (workstream finished).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
OperatingRhythm.md (daily brief format, queue hygiene, weekly review),
AutopilotWorkQueue.md seeded with 6 evergreen items, first daily brief
written for 2026-07-16.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
85 repos classified into 12 capability clusters across the four pillars;
activity signal from last-commit dates; IP-evidence note linked to RISK-002.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Findings: filings current through JA 2024; no active StB mandate (RISK-006);
DUO backlog (RISK-007); 4 office-hour items queued; audit template v0 created;
first dogfood evidence entry logged.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Founder edits: Railiance role refined to reliable deployment & operations;
Operational Knowledge added as fourth ecosystem pillar. Edits propagated to
EcosystemMap and DogfoodPolicy. DEC-2026-001 resolved; workplan task
BINKY-WP-0002-T01 closed in file and hub.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
