arcodangeandClaude Fable 5
e9d4a2bcb2
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
72 lines
2.0 KiB
JSON
72 lines
2.0 KiB
JSON
{
|
|
"stage": "escalation",
|
|
"flags": [],
|
|
"legs": [
|
|
{
|
|
"runtime": "mlx",
|
|
"model": "mlx-community/Qwen2.5-7B-Instruct-4bit",
|
|
"valid": false,
|
|
"validated": null,
|
|
"invariant_failures": [
|
|
"critical field absent: date_issue"
|
|
],
|
|
"error": null
|
|
},
|
|
{
|
|
"runtime": "vibe",
|
|
"model": "vibe-active-model",
|
|
"valid": true,
|
|
"validated": {
|
|
"supplier": {
|
|
"name": "Anthropic Ireland, Limited",
|
|
"siren": null,
|
|
"tva_intra": null
|
|
},
|
|
"ref_supplier": "9BF0758D-695749",
|
|
"date_issue": "2026-04-12",
|
|
"date_due": null,
|
|
"currency": "EUR",
|
|
"per_rate": [
|
|
{
|
|
"rate": 0,
|
|
"ht": 180.0,
|
|
"tva": 0
|
|
}
|
|
],
|
|
"totals": {
|
|
"ht": 180.0,
|
|
"tva": 0,
|
|
"ttc": 180.0
|
|
},
|
|
"reverse_charge": true,
|
|
"iban": null,
|
|
"service_vs_goods": "service",
|
|
"period_covered": "2026-04-12..2027-04-12",
|
|
"provenance": {
|
|
"totals.ht": {
|
|
"source_sha256": "d105ccd3c0fac6a810e660789aaadf21f4267e1e1cd70dbab71a0e3c42213e39",
|
|
"raw_excerpt": "180"
|
|
},
|
|
"totals.tva": {
|
|
"source_sha256": "d105ccd3c0fac6a810e660789aaadf21f4267e1e1cd70dbab71a0e3c42213e39",
|
|
"raw_excerpt": "(reverse charge: TVA 0 not printed)"
|
|
},
|
|
"totals.ttc": {
|
|
"source_sha256": "d105ccd3c0fac6a810e660789aaadf21f4267e1e1cd70dbab71a0e3c42213e39",
|
|
"raw_excerpt": "180"
|
|
},
|
|
"ref_supplier": {
|
|
"source_sha256": "d105ccd3c0fac6a810e660789aaadf21f4267e1e1cd70dbab71a0e3c42213e39",
|
|
"raw_excerpt": "9BF0758D-695749"
|
|
},
|
|
"date_issue": {
|
|
"source_sha256": "d105ccd3c0fac6a810e660789aaadf21f4267e1e1cd70dbab71a0e3c42213e39",
|
|
"raw_excerpt": "April 12, 2026"
|
|
}
|
|
}
|
|
},
|
|
"invariant_failures": [],
|
|
"error": null
|
|
}
|
|
]
|
|
} |