feat: enforce hard test-tier requirement across all DevPlace workflow agents and feature-builder docs

Update the feature-builder agent prompt, test-maintainer agent, and all four workflow JS files (devii-tool, endpoint, feature, job-service) to codify the DevPlace test standard as a non-optional project requirement: one test file per endpoint, directory tree mirroring the URL/source path, split into three tiers (unit, api, e2e). Add explicit Test phases to devii-tool, endpoint, feature, and job-service workflows, and embed tier-specific test instructions (path mapping, fixture choice, coverage scope) directly in each workflow's meta description and TESTS constant.

devplacepy/services/deepsearch/store.py

@@ -15,8 +15,7 @@ logger = logging.getLogger(__name__)
 TOKEN_PATTERN = re.compile(r"[a-z0-9]+")
 BM25_K1 = 1.5
 BM25_B = 0.75
-HYBRID_VECTOR_WEIGHT = 0.6
-HYBRID_KEYWORD_WEIGHT = 0.4
+RRF_K = 60.0
 DEFAULT_TOP_K = 8
 CANDIDATE_MULTIPLIER = 4
 
@@ -182,18 +181,39 @@ class VectorStore:
         )
         if not candidates:
             return []
+        vector_rank = sorted(
+            candidates, key=lambda chunk: chunk.score, reverse=True
+        )
         keyword = self.keyword_scores(query, candidates)
-        vec_max = max((chunk.score for chunk in candidates), default=0.0) or 1.0
-        kw_max = max(keyword.values(), default=0.0) or 1.0
+        keyword_rank = sorted(
+            candidates, key=lambda chunk: keyword.get(chunk.uid, 0.0), reverse=True
+        )
+        fused: dict[str, float] = {}
+        for rank, chunk in enumerate(vector_rank, start=1):
+            fused[chunk.uid] = fused.get(chunk.uid, 0.0) + 1.0 / (RRF_K + rank)
+        for rank, chunk in enumerate(keyword_rank, start=1):
+            fused[chunk.uid] = fused.get(chunk.uid, 0.0) + 1.0 / (RRF_K + rank)
         for chunk in candidates:
-            vec_norm = max(0.0, chunk.score) / vec_max
-            kw_norm = keyword.get(chunk.uid, 0.0) / kw_max
-            chunk.score = (
-                HYBRID_VECTOR_WEIGHT * vec_norm + HYBRID_KEYWORD_WEIGHT * kw_norm
-            )
+            chunk.score = fused.get(chunk.uid, 0.0)
         candidates.sort(key=lambda chunk: chunk.score, reverse=True)
         return candidates[:top_k]
 
+    def coverage_analytics(self) -> dict:
+        chunks = self.all_chunks()
+        if not chunks:
+            return {"chunks": 0, "domains": 0, "sources": 0, "avg_chunk_chars": 0}
+        domains = {chunk.metadata.get("url", "") for chunk in chunks}
+        domains.discard("")
+        sources = {chunk.source for chunk in chunks}
+        sources.discard("")
+        avg_chars = int(sum(len(chunk.text) for chunk in chunks) / len(chunks))
+        return {
+            "chunks": len(chunks),
+            "domains": len(domains),
+            "sources": len(sources),
+            "avg_chunk_chars": avg_chars,
+        }
+
     def drop(self) -> None:
         try:
             import chromadb