memory: Feature conversational retrieval interface fix and rename

[nidzola]

PR Checklist

• Read the Contributing documentation.
• Read the Code of conduct documentation.
• Name your Pull Request title clearly, concisely, and prefixed with the name of the primarily affected package you changed according to Good commit messages (such as memory: add interfaces for X, Y or util: add whizzbang helpers).
• Check that there isn't already a PR that solves the problem the same way to avoid creating a duplicate.
• Provide a description in this PR that addresses what the PR is solving, or reference the issue that it solves (e.g. Fixes #123).
• Describes the source of new concepts.
• References existing implementations as appropriate.
• Contains test coverage for new functions.
• Passes all golangci-lint checks.

Description

• this PR fixes the Conversational retrieval interface to accept schema.Memory instead of the memory.Buffer, by that we can in future pass in any memory that we need (for example Buffer, TokenBuffer or any other that we add).
• I've also renamed Buffer to be ConversationBuffer and TokenBuffer to be ConversationTokenBuffer so that we are closer to the langchain python implementation, so that it is easier on the eyes when we are comparing what is what.
• updated ChatMessageHistory schema to support errors, we need that when we port in psql, mongo or any other driven history, so that we don't swallow the errors when/if we have them

[nidzola]

@tmc if you could check this out, would like to merge it, b/c it fixes the Conversational retrieval.