Fixed the issue - limit parameter not working in QdrantVectorSearchTool

[Kavi-25]

🩹 Fix: QdrantVectorSearchTool returns only one result when limit > 1

Root Cause:
The query_points() method returns a QueryResponse object whose points attribute holds the list of ScoredPoint results.
However, when iterating directly over the search_result object, Pydantic’s BaseModel.iter yields key-value pairs (e.g. ('points', [points])).
As a result, the loop consumed only one iteration, producing a single record instead of the full result set.

Fix:
Iterate over search_result.points explicitly rather than over search_result itself:

❌ Before

for point in search_results:
result = {
"metadata": point[1][0].payload.get("metadata", {}),
"context": point[1][0].payload.get("text", ""),
"distance": point[1][0].score,
}
results.append(result)

✅ After

for point in search_results.points:
result = {
"metadata": point.payload.get("metadata", {}),
"context": point.payload.get("text", ""),
"distance": point.score,
}
results.append(result)

Outcome:
QdrantVectorSearchTool now respects the limit parameter and correctly returns all requested points.

Impact:
This fix ensures proper pagination and multi-result behavior in all vector search queries.