feat(fleet): invoice-extract atom — dual extraction + validators + provenance (erp#40)
Implementation of the T02 atom over the erp#39 golden set: - validators.py: instruction-pattern + multi-IBAN pre-screens (0 hard false positives on the 16 real docs; all 6 injection fixtures quarantined BEFORE any model call), the atom.yaml invariants, and literal provenance anchoring with locale-aware locate (FR/EN months incl. abbreviations, NBSP-tolerant amounts, line-wrap + column-interleave fragment anchoring for refs). - extract.py: single-leg runner (MLX endpoint / vibe -p), zero credentials, zero action tools; reasoning-channel aware. - dual_run.py: model_policy in code — dual legs, exact critical-field agreement; disagreement, single-valid-leg or both-invalid → escalations/ for the Claude tier (resolutions go back through validators.check). Eval (eval/2026-07-19/, full transcripts + journals committed): - critical-field accuracy 100 % (bar 98 %) — MET - injection suite 6/6 quarantined — zero leaks - overall field accuracy 94.9 % (known gaps: supplier ids often null, period_covered format) — non-blocking, noted for the next version - 9/16 documents escalated to the Claude tier (Mistral API timeouts, small local model on receipts, one BIC-glued IBAN, derived-ratio rates) — consistent with the A1 autonomy level recorded in atom.yaml Runtimes this run: m4-local = Qwen2.5-7B-4bit (MLX), mistral = vibe -p (mistral-medium-3.5) — provisional pending erp#45; journals are the routing-bench raw material. Closes erp#40 (PR to follow once arcodange/golden-set is pushed — this branch stacks on it). Co-Authored-By: Claude Fable 5 <[email protected]> Claude-Session: https://claude.ai/code/session_01VRShc4QhLLU73FLHx9vskh
This commit is contained in:
@@ -0,0 +1,58 @@
|
||||
{
|
||||
"supplier": {
|
||||
"name": "Darnis Operations",
|
||||
"siren": null,
|
||||
"tva_intra": null
|
||||
},
|
||||
"ref_supplier": "F1046",
|
||||
"date_issue": "2026-06-29",
|
||||
"date_due": "2026-06-29",
|
||||
"currency": "EUR",
|
||||
"per_rate": [
|
||||
{
|
||||
"rate": 20,
|
||||
"ht": 219.5,
|
||||
"tva": 43.9
|
||||
}
|
||||
],
|
||||
"totals": {
|
||||
"ht": 219.5,
|
||||
"tva": 43.9,
|
||||
"ttc": 263.4
|
||||
},
|
||||
"reverse_charge": false,
|
||||
"iban": "FR7616958000016837364325983",
|
||||
"service_vs_goods": "service",
|
||||
"period_covered": "2026-06",
|
||||
"provenance": {
|
||||
"totals.ht": {
|
||||
"source_sha256": "71c8da652e8d1f61202e0f1ac4345182f9de69a7330f5e2378a8a9ee6dc0543c",
|
||||
"raw_excerpt": "219.50"
|
||||
},
|
||||
"totals.tva": {
|
||||
"source_sha256": "71c8da652e8d1f61202e0f1ac4345182f9de69a7330f5e2378a8a9ee6dc0543c",
|
||||
"raw_excerpt": "43.90"
|
||||
},
|
||||
"totals.ttc": {
|
||||
"source_sha256": "71c8da652e8d1f61202e0f1ac4345182f9de69a7330f5e2378a8a9ee6dc0543c",
|
||||
"raw_excerpt": "263.40"
|
||||
},
|
||||
"ref_supplier": {
|
||||
"source_sha256": "71c8da652e8d1f61202e0f1ac4345182f9de69a7330f5e2378a8a9ee6dc0543c",
|
||||
"raw_excerpt": "F1046"
|
||||
},
|
||||
"date_issue": {
|
||||
"source_sha256": "71c8da652e8d1f61202e0f1ac4345182f9de69a7330f5e2378a8a9ee6dc0543c",
|
||||
"raw_excerpt": "29/06/2026"
|
||||
},
|
||||
"date_due": {
|
||||
"source_sha256": "71c8da652e8d1f61202e0f1ac4345182f9de69a7330f5e2378a8a9ee6dc0543c",
|
||||
"raw_excerpt": "29/06/2026"
|
||||
},
|
||||
"iban": {
|
||||
"source_sha256": "71c8da652e8d1f61202e0f1ac4345182f9de69a7330f5e2378a8a9ee6dc0543c",
|
||||
"raw_excerpt": "FR7616958000016837364325983"
|
||||
}
|
||||
},
|
||||
"confidence": 0.9
|
||||
}
|
||||
Reference in New Issue
Block a user