feat(runtime): implement single-article consolidation runtime and modularize codebase

2026-08-24 00:14:07 -03:00
parent e1e0be1353
commit 23de7d8fe7
176 changed files with 266754 additions and 10179 deletions
@@ -0,0 +1,126 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://schemas.aftech.internal/article-consolidation/v1/candidates-payload.schema.json",
+  "x-contract-version": "1.0.0",
+  "title": "CandidatesPayload",
+  "description": "Normalized candidate payload supplied to LLM hygiene prompt (projection of internal CandidateObjects)",
+  "type": "object",
+  "required": [
+    "language",
+    "selected_extractor",
+    "metadata_candidates",
+    "block_candidates",
+    "link_candidates",
+    "image_candidates"
+  ],
+  "properties": {
+    "language": {
+      "type": "string"
+    },
+    "selected_extractor": {
+      "type": "string",
+      "enum": ["trafilatura", "newspaper4k", "readability"]
+    },
+    "metadata_candidates": {
+      "type": "object",
+      "required": ["title_candidates", "subtitle_candidates", "author_candidates"],
+      "properties": {
+        "title_candidates": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "required": ["candidate_id", "source", "text"],
+            "properties": {
+              "candidate_id": { "type": "string" },
+              "source": { "type": "string" },
+              "text": { "type": "string" }
+            },
+            "additionalProperties": false
+          }
+        },
+        "subtitle_candidates": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "required": ["candidate_id", "source", "text"],
+            "properties": {
+              "candidate_id": { "type": "string" },
+              "source": { "type": "string" },
+              "text": { "type": "string" }
+            },
+            "additionalProperties": false
+          }
+        },
+        "author_candidates": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "required": ["candidate_id", "source", "text"],
+            "properties": {
+              "candidate_id": { "type": "string" },
+              "source": { "type": "string" },
+              "text": { "type": "string" }
+            },
+            "additionalProperties": false
+          }
+        }
+      },
+      "additionalProperties": false
+    },
+    "block_candidates": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "required": ["candidate_id", "type", "order_index", "text", "source_extractor"],
+        "properties": {
+          "candidate_id": { "type": "string" },
+          "type": {
+            "type": "string",
+            "enum": ["paragraph", "heading", "list_item", "quote"]
+          },
+          "order_index": { "type": "integer" },
+          "text": { "type": "string" },
+          "source_extractor": {
+            "type": "string",
+            "enum": ["trafilatura", "newspaper4k", "readability"]
+          },
+          "equivalences": {
+            "type": "array",
+            "items": { "type": "string" }
+          }
+        },
+        "additionalProperties": false
+      }
+    },
+    "link_candidates": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "required": ["candidate_id", "url", "anchor_text", "parent_block_id"],
+        "properties": {
+          "candidate_id": { "type": "string" },
+          "url": { "type": "string" },
+          "anchor_text": { "type": "string" },
+          "parent_block_id": { "type": "string" }
+        },
+        "additionalProperties": false
+      }
+    },
+    "image_candidates": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "required": ["candidate_id", "url"],
+        "properties": {
+          "candidate_id": { "type": "string" },
+          "url": { "type": "string" },
+          "alt": { "type": ["string", "null"] },
+          "caption": { "type": ["string", "null"] },
+          "parent_block_id": { "type": ["string", "null"] }
+        },
+        "additionalProperties": false
+      }
+    }
+  },
+  "additionalProperties": false
+}