Operator request 2026-07-11: decompose the PRD into less-high-level,
unambiguous work items. 23 self-contained issues filed (context,
deliverables, acceptance criteria, dependencies, PRD links): erp#38-57
across 6 dated milestones (P1 flagship, P2 e-invoicing hard 09-01,
P3 standing fleet, ledger compliance, P4 money loops, P5 fiscal),
telegram-gateway#1-2 (queue D1 + digest/cards), factory#22 (ADR
tracking for D1/D2/D4/D6/D7). STATUS phase tracker now points each
phase at its milestone; resume protocol for future sessions: pick the
top unblocked issue of the earliest open milestone.
Co-Authored-By: Claude Fable 5 <[email protected]>
Operator requirement (2026-07-11): mechanical measures against
hallucinated values in agent-performed edits. Four deterministic
layers in agent-architecture: (1) no free-text critical fields —
code copies values from validated extraction/bank-feed payloads,
the model never re-types them; (2) provenance anchors per critical
field {source_sha256, raw_excerpt} re-verified by a deterministic
checker against re-extracted source text (locale-normalized);
(3) cross-system corroboration against FRESH bank pulls + arithmetic
/checksum invariants; (4) read-back closes the loop. A failed check
refuses, never repairs. Woven into hub goal, C1 strategy, and QA
write-path (seeded-wrong-value fixtures must FAIL). Proven live:
the books-regularization pack shipped with a standalone
verify-provenance checker — 36 field-level checks green against
source PDFs + fresh Qonto/Wise feeds before the human gate.
Co-Authored-By: Claude Fable 5 <[email protected]>
New agent-catalog.md leaf answering three operator directions:
(1) the document surface agents read is now specified — AGENTS.md
orientation maps, SKILL.md with trigger-carrying descriptions
(Use-when/SKIP-for), atom.yaml registry contracts, thin prompt.md
files (no business rules in prompts — rules live in profile files
and validators), schema'd fiscal.yaml/calendar.yaml with
effective_from dates, [AGENT]/[HUMAN] runbooks, env-var-indirected
.mcp.json; same-change freshness rule extended to the fleet.
(2) hermes's telegram-gateway confirmed as THE human channel when
available (cluster-served cards, email fallback; D1 operator-endorsed).
(3) the categorization to prove: seven agent classes (incl. the
LLM-free deterministic controller) and a T01-T17 assignment matrix
with per-row proof gates and statuses (proven / to-prove / not-built),
re-scored monthly from run journals (fallback rate >20% = wrong cell).
New D8 (fleet code home, leaning erp fleet/).
Co-Authored-By: Claude Fable 5 <[email protected]>
New roadmap.md: mermaid Gantt (validated) putting the six phases on
calendar time from baseline 2026-07-11 — P2 e-invoicing opens the plan
(ADR D4 target 08-14, two-week fallback before the hard 09-01), P1
flagship in parallel (golden set first, A2 earned ~10-09), ledger-
compliance verifications early September (FY-2026 FEC depends on the
accounting-module answer), P3 standing fleet through autumn (sentinel
24/7 ~11-13), P4 money-loop exit over December, P5 riding the fiscal
calendar (acompte 12-15, CA3 switch 01-01, Q1 filing April, CA12 early
May, AG 06-30), P6 e-reporting proven months before 2027-09-01.
Immovable-milestone table, dependency notes, re-baselining rule
(engineering bars slide, diamonds don't — slips shed scope instead).
Wired: hub pointer + leaves row, poc-plan/STATUS backlinks.
Co-Authored-By: Claude Fable 5 <[email protected]>
New compliance.md leaf: French bookkeeping obligations mapped to fleet
mechanisms — inaltérabilité (L.123-22) via an append-only production
ledger grammar (create/validate/pay/avoir, never mutate a validated
document) enforced by a promote-plan compliance linter; FEC (L.47 A
LPF) with quarterly export + Test Compta Demat validation (accounting-
module binding flagged as unverified gap); piste d'audit fiable (289
VII CGI) framed as a by-product of journals + tx-id reco + monthly
packs; retention, numbering, copie fiable; loi anti-fraude scoped out
(B2B-only) with BlockedLog as sandbox-first belt-and-braces.
New Environments section in agent-architecture: prod = the ledger
(grammar-bound), sandbox = disposable iso-prod rehearsal (exempt, never
wired to production third parties); side_effect_class -> environment/
credential mapping; POCs write on sandbox only; evals target fresh
checkpoints; irreversible-by-design features trial on checkpoints.
Woven through hub (goal, requirement, success criteria, leaves table),
T03/T05/T15 guardrails, QA (linter suite, pure-append snapshots, FEC
cadence, PAF evidence framing), C2, POC-1 exit criteria.
Co-Authored-By: Claude Fable 5 <[email protected]>
Operator direction: Qonto is the capital-deposit bank, a DGFiP-registered
PA with e-invoicing included in every plan, and the fleet's richest
existing API integration. POC-6 rewritten from shortlist to validation
spike (reception + business-API pull + GED archival + 2027 e-reporting
path for the KM export invoices); C12 residual now names the vendor-
concentration trade-off; terminology refreshed PDP -> PA (renamed by the
administration in July 2025); 2027-09 milestone clarified (e-reporting
for export invoices; emission only if a French B2B client arrives).
Co-Authored-By: Claude Fable 5 <[email protected]>
The PARA Obsidian vault (arcodange/SecondBrain — git-synced, sb.py
digest/inbox/gitea-ingest jobs on the hermes cron ticker, local Ornith
model, mcp-obsidian access) enters the PRD as a first-class component:
new T17 knowledge capture & retrieval fiche, knowledge-layer section in
the architecture (ERP = book of record, vault = context + institutional
memory, append-only idempotent deposits, trusted-but-stale retrieval),
hermes/Ornith recognized as the resident M4 runtime (D2 leaning, new D7
cluster<->vault access decision), foundation ledger row, diagram +
goals updated (mermaid revalidated, 231 links/anchors re-checked green).
Co-Authored-By: Claude Fable 5 <[email protected]>
New PRD tree vibe/PRD/ai-back-office/ (hub + 6 leaves + STATUS): task
inventory T01-T16 with mode operatoire, atom/contract architecture on
the ADR-0003 write gate, four-tier model fleet (Claude/Mistral/M4/Pi),
12 challenges with mitigations, POC plan with exit criteria, QA
strategy with autonomy promotion gates. Index row + bidirectional
backlinks (erp guidebook, safe-prod PRD).
Co-Authored-By: Claude Fable 5 <[email protected]>
Records the decision to extend the <app> join key with a second
coordinate <env>, governed by an elision rule (env=prod elides → every
existing app's derived names are byte-identical and its tofu plan is a
no-op; non-prod envs take the <app>-<env> suffix, with the Postgres
owner role staying snake-case <app>_<env>_role).
Motivated by the ERP's incoming write-capable AI-agent skill: it needs
an in-cluster sandbox instance (erp-sandbox) with a prod-like Dolibarr
API + isolated database to rehearse writes before a human promotes them
to prod. The ADR reconciles this against ADR-0001 honestly — ADR-0001
rejected an in-cluster sandbox for INFRA-change rehearsal (shared
fleet-wide control planes); ADR-0002 operates one layer up where the
agent's only reach is the app's HTTP API against an isolated DB, so the
fleet blast radius is not in scope. The two are complementary; ADR-0002
does not supersede ADR-0001.
Also:
- vibe/ADR/README.md: index row for 0002 + Last Updated 2026-06-25
- PRD safe-prod-like-environment README: bidirectional back-link to
ADR-0002 on the Adjacent line + Last Updated 2026-06-25
Authored via the ADR Scribe persona, validated via the Continuity Warden
checklist (no-tombstone, breadcrumb, MADR-lite sections, dead-link scan,
bidirectional links).
Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>
Add a root AGENTS.md (ecosystem map of factory/tools/cms + agent operating
rules + the persona cohort & workflow) and a new vibe/ knowledge base for LLM
agents, modeled on tree-docs conventions and the factory house style.
vibe/ folders (each with a README hub + contribution rules):
- ADR/ optimized MADR-lite; canonical home going forward (doc/adr stays historical)
- PRD/ one subfolder per PRD, mandatory STATUS.md, QA strategy for big ones
- investigations/ single INV-NNN-slug.md, or stub + folder w/ notebooks
- guidebooks/ tree-docs maps; lab-ecosystem guidebook of factory+tools+cms
- runbooks/ [AGENT]/[HUMAN] step procedures (EN; doc/runbooks stays FR)
- shareouts/ dated FR handouts (decks/mp4)
Seed content (first ADR + PRD): a safe, production-like environment to rehearse
risky changes and recovery without touching real prod — local-only sandbox
(k3d + arm64 VMs) with a hard prod/sandbox isolation boundary. Includes
INV-001 (prod blast-radius couplings), the ecosystem guidebook, and a FR shareout.
Conventions enforced: no-tombstone rule, breadcrumb spine, bidirectional
cross-links, theme:base mermaid (MCP-validated) + ordered-list-after-diagram.
Built with a Workflow + persona cohort; 24 files, zero dead links.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
arcodangeandClaude Fable 5