Langroid

Agent: during init, set `config.parsing.token_encoding_model` to the LLM,
so we use the tokenizer specific to the LLM, which helps with accurate token-cost computation.
(only affects OpenAI LLMs currently).

* Fix ChainlitTaskCallbacks - use classmethod not staticmethod, so any derived versions propagate to subtasks
* Handle deviant OpenAI LLM function-call generation (esp w gpt-4o), e.g. functions with name "functions", or "functions xyz"

* Improve LanceDocChatAgent and Query Planner to handle deviations.
* Handle function-call odditities in OpenAI LLM -- they can generate an unnecessary "name" field, which we override with the "request" field from the arguments.

- Tweaks to LanceDocChatAgent and related Agents (QueryPlanner, Critic, etc) to accomodate deviations
- In multi-agent chats, so total cost across all agents, in addition to cumul cost of current agent

Update toml to latest DuckDuckGo (6.0.0) so we no longer get the rate limit error

Support OpenAI GPT-4o -- this is now the default LLM when no model is specified.

To explicitly specify the LLM, you can do, for example:


import langroid.language_models as lm
llm = lm.OpenAIGPT( lm.OpenAIGPTConfig(chat_model = lm.OpenAIChatModel.GPT4o))


And recall you can run most of the example scripts with a model specified via `-m gpt-4o`,
and pytests using `--m gpt-4o`