Langroid

Task constructor takes new param `allow_null_result`, which defaults to True,
and this setting is backward-compatible.
When True, it means an empty or DO-NOT-KNOW result is allowed as a step or task-level result.
For some scenarios it is useful to set it to False; this retains the current pending message
so it can be passed on to a sub-task, or returned as the result of a task.

Agent.base: agent_response(): improve err msg when missing/wrong field in ToolMessage
(Previously only the top-level tool name was being returned; this improves it to show the actual missing/wrong field)

DocChatAgent: new method `get_semantic_search_results` that can be overridden

API Simplifications to reduce boilerplate:
* Auto-select an available OpenAI model (preferring gpt-4-turbo), simplifies defaults.
* Simpler `Task` initialization with default `ChatAgent`.

Fix token usage calc with function-calling

* `VectorStore`: `add_document()` now adds `metadata.id` to documents if absent (affected ChromaDB).
* `DocChatAgent`: default to `lancedb` instead of `qdrant`
* `test_doc_chat_agent`: test with `ChromaDB`, `LanceDB`, `QdrantDB` vector-stores.
* `urls.find_urls()`: fix bug, ensure base URL is at front of list