feat: structured content blocks for user messages#158
Merged
Conversation
- Add ContextContent pydantic model (content_type, content, metadata) - Replace XML-in-string context with typed content blocks - Time gap is now a context block (time_since_last_message), not XML injection - All three LLM providers render context blocks as semantic XML tags - History endpoint returns context blocks as structured data - render_context() generates XML with attributes from metadata - _retain_user_content() strips context blocks on re-entry (non-mutating)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
ContextContentpydantic model withcontent_type,content,metadatafieldstime_since_last_messagecontext block_retain_user_contentstrips context blocks on re-entry (non-mutating)render_context()incore/content.pyis the single rendering point