factory/vibe/PRD/ai-back-office/STATUS.md

vibe > PRD > AI back-office > STATUS

STATUS — implementation tracker

Status: 🟢 Current — backlog decomposed into issues (2026-07-11); sharpened with per-issue Execution footers + splits #59/#60 (2026-07-12); execution started — erp#38 shipped, D8 settled (2026-07-15); harness portability proven — erp#63 + #56 closed, Mistral + Ornith admitted to verifier duty (2026-07-18); P1 write-skill + atom sprint — #44/#43 shipped, #39/#40 built awaiting the operator push gate, #54 PR open on its Accept gate (2026-07-19) Last Updated: 2026-07-19 Up: AI back-office hub Related: POC plan · Roadmap (dated plan; actuals and slips land here)

Phase tracker

Phase	Scope	State
0 — Foundations	read skills, sandbox + promote, backups, snapshots, bank reco, email ingest, Telegram gateway MVP	✅ shipped pre-PRD (ledger below)
1 — Flagship pipeline	POC-1 + POC-5	🟡 in progress → erp milestone P1 (erp#38–45, #47 — due 2026-10-09) · #38 ✅ 2026-07-15 (PR erp#62)
2 — Urgent compliance	POC-6 — hard deadline 2026-09-01	⬜ decomposed → erp milestone P2 (erp#46 — due 2026-09-01)
3 — Standing fleet	POC-2, queue, digest + approval cards, harness portability	🟡 in progress → erp milestone P3 (erp#48–50, #59 — due 2026-11-13) + gateway#1/#2 · #63 ✅ 2026-07-18 (PR erp#69: harness home erp:fleet/harness/, Mistral vibe -p + Ornith 35B at verifier parity, builder bench = #56 by Mistral, 0 corrections)
Ledger compliance (cross-cutting)	Dolibarr verifications	⬜ decomposed → erp milestone (erp#51 — due 2026-11-27)
4 — Money loops	POC-3, dunning, cash report	⬜ decomposed → erp milestone P4 (erp#52–53 — due 2026-12-24)
5 — Fiscal autopilot	POC-4, compliance calendar	⬜ decomposed → erp milestone P5 (erp#54–55, #60 — due 2027-05-04)
6 — Emission era	e-invoice emission + e-reporting — hard deadline 2027-09-01	⬜ not yet decomposed (starts 2027-05; requirements captured by erp#46 deliverable 4)

Backlog map

Every phase is decomposed into self-contained issues (context, deliverables, acceptance criteria, dependencies, PRD links); since 2026-07-12 each issue also carries an Execution footer — Blocked by / Blocks / Human gates / Start (worktree + first command) / Done means (evidence comment → PR with Closes #N → doc sweep). How a future session resumes: order open milestones by due date, pick the top issue whose "Blocked by" is clear — and skip issues whose only open step is a [HUMAN] gate (surface those in the digest instead of stalling on them; e.g. erp#46 step 1 is operator-owned). Cold-start entry points as of 2026-07-19: erp#41/#42 (write-skill side, independent), erp#51 (startable today), erp#45 (once the operator pushes the #39/#40 branches — the dual-run journals in fleet/atoms/invoice-extract/eval/2026-07-19/ are its raw material). Operator-gated, not session-startable: #39/#40 push, #54 Accept (PR erp#71), #46 step 1 (Qonto UI), #53 July manual invoice ~07-23. Arbitration: one session = one lane — take the entry issue; an orchestrator may fan the independent lanes out in parallel (#39 ∥ #51 ∥ #41–44 touch disjoint directories); everything else follows due-date order (dates in the phase tracker above). The issue body carries everything; on any doubt the trust order is live system > code > STATUS > leaves. Cross-cutting decisions get their ADRs via factory#22.

Repo	Issues
erp	P1: #38 fleet scaffold ✅ 2026-07-15 (D8 settled, PR erp#62) · #39 golden set+injection fixtures (built 2026-07-18 — 16 invoices + 6 injection + 1824 mails + scorer, local branch arcodange/golden-set; push+PR = operator step, #39 evidence) · #40 invoice-extract atom (built 2026-07-19 — critical-field 100 %, 6/6 injections quarantined pre-model, local branch stacks on #39's, #40 evidence) · #41 provenance checker · #42 compliance linter · #43 GED attach op ✅ 2026-07-19 (PR erp#72) · #44 idempotency keys ✅ 2026-07-19 (PR erp#70 — the 2026-07-11 manifest-B replays 5/5 deduped) · #45 POC-5 routing bench (D5) · #47 POC-1 exit gate (umbrella) — P2: #46 POC-6 Qonto-as-PA (D4; step 1 = [HUMAN] Qonto UI) — P3: #48 T13 drift watchdog · #59 T14 backup freshness+drill · #49 T17 second-brain hooks (D7; meeting lane D9 parked) · #50 POC-2 Pi sentinel (D6) — Compliance: #51 Dolibarr verifications (FEC/BlockedLog, startable today) — P4: #52 POC-3 reco+payments · #53 T05 client invoice (D3, ⚠️ July manual ~07-23) · #65 client-dossier ops (phase 1 ✅ 07-15) · #67 official-doc drafting skill (T18) — P5: #54 fiscal profile+calendar files+ADC register (PR erp#71 open — merging it = Accepting adc-001…005, operator act) · #60 T11 reminder loop · #55 POC-4 TVA dry-runs — Ops (post-replay): #57 bucket C + document gaps (#56 ✅ 2026-07-18, PR erp#68 — authored by the Mistral builder bench)
telegram-gateway	#1 Postgres durable queue (D1) · #2 daily digest + approval cards
factory	#22 ADRs as decisions close (D1/D2/D4/D6/D7)

Closure protocol — per milestone

The resume protocol tells a session where to pick up work; this one keeps the doc surface currently true when work lands. Docs describe intent; this file + git describe reality. A Gitea milestone is closed only after the sweep — and the sweep starts with QA, because nothing gets documented as done before it is proven done:

1. QA gate — verify before documenting, and never by yourself. The gate is run by an independent verifier subagent: context-free (no conversation inherited from the closer), prompted to refute — "find why this milestone is NOT actually done" — with the repo, the issues and the run journals as its only inputs (no self-grading). It checks: (a) every closed issue's acceptance criteria re-verified with evidence linked (eval scores, run journals, exit-gate results — not memory of them); (b) the milestone's test suites green: golden-set regressions at their bars, injection fixtures quarantined, linter suites behaving (forbidden manifests rejected, seeded-wrong provenance fixtures FAIL), idempotency replay no-op, watchdog/heartbeat checks where the milestone ships standing loops (QA strategy); (c) any 🧪→✅ flip in the agent-catalog backed by its proving-protocol evidence. Its verdict is posted on the milestone before closure; a refutation the closer cannot resolve with evidence blocks. A milestone that can't pass its own QA doesn't close — it sheds scope back into open issues.
2. Flip the phase row above (✅ + date + PR links) and prune the backlog map of closed issues.
3. Re-baseline the roadmap at the boundary: mark the stream done, re-date downstream engineering bars if they slipped — regulatory diamonds never move; slips shed scope instead. Bump its Last Updated.
4. Truth-pass the affected leaves (no-tombstone — rewrite as currently true, no "previously/now"): the task inventory Today:/Target: lines the milestone changed; the agent-catalog matrix; not yet/candidate claims in architecture, model-fleet, compliance. Bump Last Updated only on files whose claims changed.
5. Sweep the orientation layer: repo AGENTS.md files (map rows, "not yet landed" pointers), touched SKILL.mds, and any guidebook page mapping a changed component (house same-change rule).
6. Doc-surface QA — mechanical + fresh-reader. (a) Run the link/anchor/convention check over the PRD tree (the prd_check pattern: every relative link + heading anchor resolves, breadcrumbs, stamps) — zero broken; (b) deprecation grep: list the claims the milestone retired (read them off the closed issues — e.g. frequency=0, "not yet landed", "no fleet wiring") and grep vibe/ + the repos' AGENTS.md/SKILL.md for them — zero hits or fixed; (c) fresh-reader smoke test: a context-free subagent reads only STATUS + the repo AGENTS.md and must answer "what shipped, what's next, what would you verify before trusting?" correctly — if it lands on a stale claim, real sessions will too.
7. Close the loop outward: ADRs for decisions the milestone settled (factory#22), agent memories updated or pruned, a REX note into the second brain (T17 once live).
8. Only then close the Gitea milestone.

Between milestones, the continuous rule stands: a PR that makes any documented claim false updates that doc in the same PR — a change that leaves its docs stale is an incomplete change.

Reader's half — trust order. Any session, before acting on a versionable claim (a path exists, a flag's value, a status emoji): verify against live system > code/git log > this STATUS > PRD leaves > agent memories/plans. A page whose Last Updated predates the newest closed milestone in its area is suspect — verify before relying on it.

Foundation ledger (shipped pre-PRD)

The bricks this PRD builds on, in the erp, factory and tools repos:

Brick	What it gives the fleet	Key PRs
Read-only skill catalogue + bin/arcodange CLI	invoices, payments, TVA (collectée/déductible/summary), thirdparty completeness, recurring templates, snapshots — the fleet's A3 read layer	erp (V1–V8 skill series)
Multi-env: erp-sandbox live in-cluster	the rehearsal environment (ADR 0002)	factory #15–#18, erp #11–#12, tools #2–#3
Sandbox write skill (fiches, invoices, payments, avoirs)	the A2 write layer, host-guarded to the sandbox	erp #21, #22, #25
Promote flow (manifests, business-key lookup, prod gate)	the ADR-0003 capstone: rehearse → review → human-gated prod apply (ADR 0003, factory #19)	erp #23, #24
Deterministic payment↔bank linkage	transaction_id end-to-end: record with the feed id, reconcile by id (PASS 0)	erp #26–#28
Sandbox checkpoint lifecycle + CLI	iso-prod refresh, write-agent provisioning, .env relink	erp #29, #30, #35
Dedicated Dolibarr backup (daily CronJob, 10 y retention, tested restore)	the evidence/recovery floor	erp #31–#34, tools #5
Bank reco + email ingest skills	Qonto/Wise feeds, Zoho books@/bureaux@ ingestion (read-only)	erp (skill series)
telegram-gateway MVP	the human channel's transport (webhook echo proven; queue + async handlers roadmapped)	telegram-gateway repo
Second brain (Obsidian vault + automation)	the fleet's knowledge layer: PARA vault git-synced, sb.py jobs (digest / inbox triage / daily / Gitea-ingest) on the hermes cron ticker, local Ornith runtime, mcp-obsidian access	SecondBrain repo

PR log (this PRD)

Date	PR	What shipped
2026-07-11	factory#21	PRD authored: hub + task inventory + agent architecture + model fleet + challenges + POC plan + QA strategy.
2026-07-18	erp#68	#56 known-patterns fix — authored end-to-end by the Mistral runtime (vibe -p) under the builder bench; acceptance bank match clean (0 UNKNOWN).
2026-07-18	erp#69	#63 harness portability: fleet/harness/ (verifier tests, run-verifier.sh, vibe-builder.sh) + parity/bench evidence — Mistral + Ornith admitted to verifier duty (blind-judged, 16/16 unanimous).
2026-07-18	factory#31	Cross-family verification rule codified in the qa-strategy; STATUS truth-pass for #56/#63/#39.
2026-07-19	erp#70	#44 idempotency keys — replay is a no-op, proven live (historic manifest-B 5/5 deduped).
2026-07-19	erp#71 (open)	#54 fiscal profile + calendar + ADC register — awaiting the operator Accept gate.
2026-07-19	erp#72	#43 GED attach op — idempotent by (object, filename, sha256), rehearsed live (4 created → 4 deduped).
2026-07-19	this PR	STATUS truth-pass for #43/#44/#40/#54; entry points re-baselined.