know-cli 0.3.3__tar.gz → 0.3.5__tar.gz

{know_cli-0.3.3 → know_cli-0.3.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: know-cli
-Version: 0.3.3
+Version: 0.3.5
 Summary: Context Intelligence for AI Coding Agents — smart, token-budgeted code context
 Project-URL: Homepage, https://github.com/vic/know-cli
 Project-URL: Repository, https://github.com/vic/know-cli

{know_cli-0.3.3 → know_cli-0.3.5}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "know-cli"
-version = "0.3.3"
+version = "0.3.5"
 description = "Context Intelligence for AI Coding Agents — smart, token-budgeted code context"
 readme = "README.md"
 license = "MIT"

{know_cli-0.3.3 → know_cli-0.3.5}/src/know/lexical_index.py

@@ -217,8 +217,12 @@ class ChunkFTSIndex:
             cleaned = re.sub(r"[^A-Za-z0-9_]+", " ", q).strip()
             if not cleaned:
                 return q
-            # AND all terms for higher precision.
-            return " ".join(cleaned.split())
+            terms = cleaned.split()
+            if len(terms) == 1:
+                return terms[0]
+            # Use OR to avoid over-strict matching on multi-word queries.
+            # Ranking still handled by BM25.
+            return " OR ".join(terms)
 
         query_sanitized = _sanitize(query)
 

{know_cli-0.3.3 → know_cli-0.3.5}/src/know/semantic_search.py

@@ -681,6 +681,53 @@ class SemanticSearcher:
             }
             results.append(out)
 
+        # Hard fallback: plain text grep when hybrid/vector/lexical all miss.
+        # This guarantees useful results for exact keyword queries in TS/React projects.
+        if not results and query.strip():
+            q = query.strip().lower()
+            exts = {".py", ".ts", ".tsx", ".js", ".jsx", ".go", ".rs", ".java", ".cpp", ".c", ".h", ".md"}
+            fallback = []
+            for p in root.rglob("*"):
+                if not p.is_file() or p.suffix.lower() not in exts:
+                    continue
+                rel = str(p.relative_to(root))
+                if path_prefix and not rel.startswith(path_prefix):
+                    continue
+                if type_suffix:
+                    suf = type_suffix if type_suffix.startswith(".") else f".{type_suffix}"
+                    if not rel.endswith(suf):
+                        continue
+                if any(part.startswith(".") or part in {"node_modules", "__pycache__", "venv", ".git", "dist", "build"} for part in p.parts):
+                    continue
+                try:
+                    text = p.read_text(encoding="utf-8", errors="ignore")
+                except Exception:
+                    continue
+                idx = text.lower().find(q)
+                if idx < 0:
+                    continue
+                line_no = text[:idx].count("\n") + 1
+                snippet = _format_snippet(p, line_no, line_no, context=2, include_line_numbers=include_line_numbers)
+                fallback.append((rel, line_no, snippet))
+                if len(fallback) >= top_k:
+                    break
+
+            for i, (rel, line_no, snippet) in enumerate(fallback, start=1):
+                results.append({
+                    "schema": "know.search.v1",
+                    "engine": "text-fallback",
+                    "rank": i,
+                    "doc_id": f"{rel}::line::{line_no}",
+                    "path": rel,
+                    "name": Path(rel).stem,
+                    "chunk_type": "line",
+                    "start_line": line_no,
+                    "end_line": line_no,
+                    "scores": {"rrf": 0.01, "lexical_bm25": None, "vector": None},
+                    "snippet": snippet,
+                    "rationale": {"lexical_available": lexical_available, "vector_available": vector_available},
+                })
+
         return results
 
     def clear_cache(self):
@@ -787,8 +834,8 @@ class SemanticSearcher:
 
         results = []
         for i in top_indices:
-            if similarities[i] <= 0:
-                continue
+            # Keep top-k even when cosine is <= 0. In sparse/short queries,
+            # all scores can be near/under 0 and filtering causes empty results.
             chunk_key = file_paths[i]
             # Parse chunk key: "file_path::name::line_start"
             parts = chunk_key.split("::")