Establish prompt engineering baseline with Gold Standard tests

- introduce Gold Standard evaluation corpus
- document decision taxonomy
- define prompt-engineering methodology
- add regression workflow
- establish Prompt Version 2 baseline
- validate decision_simple, decision_deferred and decision_none

src/meeting_lab/llm/prompts.py

@@ -0,0 +1,51 @@
+from __future__ import annotations
+
+import json
+from pathlib import Path
+from typing import Any, Iterable
+
+
+PROJECT_ROOT = Path(__file__).resolve().parents[3]
+PROMPTS_DIR = PROJECT_ROOT / "prompts"
+
+
+def load_prompt(name: str, prompts_dir: Path = PROMPTS_DIR) -> str:
+    path = prompts_dir / name
+    return path.read_text(encoding="utf-8").strip()
+
+
+def load_existing_prompts(
+    names: Iterable[str],
+    prompts_dir: Path = PROMPTS_DIR,
+) -> list[str]:
+    prompts: list[str] = []
+    for name in names:
+        text = load_prompt(name, prompts_dir)
+        if text:
+            prompts.append(text)
+    return prompts
+
+
+def build_extraction_prompt(
+    source_name: str,
+    transcript: str,
+    output_schema: dict[str, Any],
+    task_prompt_names: Iterable[str] = ("decisions.md",),
+    prompts_dir: Path = PROMPTS_DIR,
+) -> str:
+    schema_text = json.dumps(output_schema, ensure_ascii=False, indent=2)
+    prompt_parts = [
+        load_prompt("common.md", prompts_dir),
+        *load_existing_prompts(task_prompt_names, prompts_dir),
+        f"""Quelldatei:
+{source_name}
+
+Erwartete JSON-Struktur:
+{schema_text}
+
+TRANSKRIPT:
+--- BEGINN TRANSKRIPT ---
+{transcript}
+--- ENDE TRANSKRIPT ---""",
+    ]
+    return "\n\n".join(part for part in prompt_parts if part).strip() + "\n"