feat(chat): LLM-backed agent chat + simpler chat targeting#78
Merged
DeveshParagiri merged 3 commits intomainfrom Feb 17, 2026
Merged
feat(chat): LLM-backed agent chat + simpler chat targeting#78DeveshParagiri merged 3 commits intomainfrom
DeveshParagiri merged 3 commits intomainfrom
Conversation
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary\n- make and generate in-character agent replies via LLM (DB-grounded context + chat history)\n- add to quickly discover recent runs and agent IDs\n- default chat targeting behavior: if / are omitted, use latest run and first available agent\n- persist run/agent resolution in ask JSON payload\n- harden OpenAI structured-output extraction for Responses API ( fallback + retry on )\n- make chat session/message persistence work with legacy layouts by using direct SQLite chat table operations in chat command\n- update CLI docs for new chat behavior\n\n## Why\nIssue #69 requested that chat actually converse as the selected agent via LLM. This PR also reduces user friction for trying chat quickly and addresses provider/runtime edge cases found during E2E testing.\n\n## Validation\n- All checks passed!\n- ....................................................................... [100%]
71 passed in 0.92s\n- live checks against :\n - \n - (interactive default resolution)\n - with default run/agent resolution\n\nCloses #69