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
2026-07-19 00:31:21 +02:00
parent bdd3d63b61
commit e9d4a2bcb2
38 changed files with 1678 additions and 44 deletions
@@ -0,0 +1,82 @@
+{
+  "stage": "escalation",
+  "flags": [
+    "multi-iban: 2 distinct valid IBANs — IBAN choice must be escalated"
+  ],
+  "legs": [
+    {
+      "runtime": "mlx",
+      "model": "mlx-community/Qwen2.5-7B-Instruct-4bit",
+      "valid": false,
+      "validated": null,
+      "invariant_failures": [
+        "arithmetic: sum(per_rate.ht) != totals.ht"
+      ],
+      "error": null
+    },
+    {
+      "runtime": "vibe",
+      "model": "vibe-active-model",
+      "valid": true,
+      "validated": {
+        "supplier": {
+          "name": "Darnis Operations",
+          "siren": "920267531",
+          "tva_intra": "FR51920267531"
+        },
+        "ref_supplier": "F1042",
+        "date_issue": "2026-03-31",
+        "date_due": "2026-03-31",
+        "currency": "EUR",
+        "per_rate": [
+          {
+            "rate": 20,
+            "ht": 255.0,
+            "tva": 51.0
+          }
+        ],
+        "totals": {
+          "ht": 255.0,
+          "tva": 51.0,
+          "ttc": 306.0
+        },
+        "reverse_charge": false,
+        "iban": "FR7616958000016837364325983",
+        "service_vs_goods": "service",
+        "period_covered": "2026-03",
+        "provenance": {
+          "totals.ht": {
+            "source_sha256": "be30079c3fd5606c310616712ec17c0d97289eee548c85b9bc79df76b5332e25",
+            "raw_excerpt": "255"
+          },
+          "totals.tva": {
+            "source_sha256": "be30079c3fd5606c310616712ec17c0d97289eee548c85b9bc79df76b5332e25",
+            "raw_excerpt": "51"
+          },
+          "totals.ttc": {
+            "source_sha256": "be30079c3fd5606c310616712ec17c0d97289eee548c85b9bc79df76b5332e25",
+            "raw_excerpt": "306"
+          },
+          "ref_supplier": {
+            "source_sha256": "be30079c3fd5606c310616712ec17c0d97289eee548c85b9bc79df76b5332e25",
+            "raw_excerpt": "F1042"
+          },
+          "date_issue": {
+            "source_sha256": "be30079c3fd5606c310616712ec17c0d97289eee548c85b9bc79df76b5332e25",
+            "raw_excerpt": "31/03/2026"
+          },
+          "date_due": {
+            "source_sha256": "be30079c3fd5606c310616712ec17c0d97289eee548c85b9bc79df76b5332e25",
+            "raw_excerpt": "31/03/2026"
+          },
+          "iban": {
+            "source_sha256": "be30079c3fd5606c310616712ec17c0d97289eee548c85b9bc79df76b5332e25",
+            "raw_excerpt": "FR7616958000016837364325983"
+          }
+        }
+      },
+      "invariant_failures": [],
+      "error": null
+    }
+  ]
+}