feat: add deterministic Apec query derivation

src/job_research/apec/__init__.py

@@ -0,0 +1,3 @@
+from job_research.apec.query_derivation import derive_apec_queries
+
+__all__ = ["derive_apec_queries"]

src/job_research/apec/query_derivation.py

@@ -0,0 +1,19 @@
+from job_research.models import CandidateProfileOutput
+
+
+def derive_apec_queries(profile: CandidateProfileOutput) -> list[str]:
+    queries: list[str] = []
+    seen: set[str] = set()
+
+    for target_role in profile.target_roles:
+        query = target_role.strip()
+        if not query or query in seen:
+            continue
+
+        seen.add(query)
+        queries.append(query)
+
+        if len(queries) == 5:
+            break
+
+    return queries

tests/apec/test_query_derivation.py

@@ -0,0 +1,26 @@
+from job_research.apec.query_derivation import derive_apec_queries
+from job_research.models import CandidateProfileOutput
+
+
+def test_derive_apec_queries_preserves_order_dedupes_and_caps_at_five() -> None:
+    profile = CandidateProfileOutput(
+        target_roles=[
+            "Data Engineer",
+            "Analytics Engineer",
+            "Data Engineer",
+            "BI Engineer",
+            "Junior Data Platform Engineer",
+            "ML Engineer",
+            "Backend Engineer",
+        ]
+    )
+
+    queries = derive_apec_queries(profile)
+
+    assert queries == [
+        "Data Engineer",
+        "Analytics Engineer",
+        "BI Engineer",
+        "Junior Data Platform Engineer",
+        "ML Engineer",
+    ]