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 +1,96 @@
+"""Contract tests for runtime-config.schema.json."""
+
+from __future__ import annotations
+
+import json
+from pathlib import Path
+
+import jsonschema
+import pytest
+
+from src.runtime.core.config import create_schema_registry, load_runtime_config, load_schema
+
+
+def test_runtime_config_schema_validation_valid():
+    schema = load_schema("runtime-config.schema.json")
+    registry = create_schema_registry()
+    validator = jsonschema.Draft202012Validator(schema, registry=registry)
+
+    valid_config = {
+        "config_version": "1.0.0",
+        "paths": {"output_dir": "out/articles", "sqlite_db": "out/runtime.db"},
+        "roles": {
+            "runtime_primary": {
+                "role_config_version": "1.0.0",
+                "provider": "groq",
+                "model": "llama-3.1-8b-instant",
+                "endpoint_url": "https://api.groq.com/openai/v1",
+                "timeout_seconds": 30,
+                "max_retries": 3,
+                "parameters": {"temperature": 0.0},
+                "hygiene_prompt_version": "1.0.0",
+                "hygiene_schema_version": "1.0.0",
+                "enrichment_prompt_version": "1.0.0",
+                "enrichment_schema_version": "1.0.0",
+            },
+            "runtime_fallback": {
+                "role_config_version": "1.0.0",
+                "provider": "deepseek",
+                "model": "deepseek-chat",
+                "endpoint_url": "https://api.deepseek.com/v1",
+                "timeout_seconds": 30,
+                "max_retries": 3,
+                "parameters": {"temperature": 0.0},
+                "hygiene_prompt_version": "1.0.0",
+                "hygiene_schema_version": "1.0.0",
+                "enrichment_prompt_version": "1.0.0",
+                "enrichment_schema_version": "1.0.0",
+            },
+        },
+        "prompts": {
+            "article_content_hygiene": {
+                "path": "prompts/article_content_hygiene.v1.txt",
+                "version": "1.0.0",
+                "hash": "0000000000000000000000000000000000000000000000000000000000000000",
+            },
+            "article_sentiment_tags": {
+                "path": "prompts/article_sentiment_tags.v1.txt",
+                "version": "1.0.0",
+                "hash": "0000000000000000000000000000000000000000000000000000000000000000",
+            },
+        },
+        "ecp": {
+            "canonical_schema_reference": "specs/006-article-consolidation-runtime/contracts/ecp-snapshot.schema.json",
+            "classifier_module": "src.classifier.InherenceClassifier",
+        },
+        "limits": {"max_input_bytes": 1048576, "context_strategy": "fail_before_provider"},
+        "pricing": {
+            "primary_input_1k": 0.00005,
+            "primary_output_1k": 0.00008,
+            "fallback_input_1k": 0.00014,
+            "fallback_output_1k": 0.00028,
+        },
+        "langfuse": {"environment": "local", "trace_content_policy": "metadata_only"},
+        "sqlite": {"busy_timeout_ms": 5000},
+    }
+
+    errors = list(validator.iter_errors(valid_config))
+    assert len(errors) == 0, f"Schema validation errors: {[e.message for e in errors]}"
+
+
+def test_runtime_config_fixture_loads_successfully():
+    config = load_runtime_config("runtime_config.local.json")
+    assert config.config_version == "1.0.0"
+    assert "runtime_primary" in config.roles
+    assert "runtime_fallback" in config.roles
+    assert config.roles["runtime_primary"].model == "llama-3.1-8b-instant"
+
+
+def test_runtime_config_rejects_powerful_models(tmp_path: Path):
+    valid_base = json.loads(Path("runtime_config.local.json").read_text(encoding="utf-8"))
+    valid_base["roles"]["runtime_primary"]["model"] = "gpt-4o"  # Forbidden powerful model
+    cfg_file = tmp_path / "invalid_cfg.json"
+    cfg_file.write_text(json.dumps(valid_base), encoding="utf-8")
+
+    with pytest.raises(ValueError, match="Forbidden powerful model"):
+        load_runtime_config(cfg_file)