fix(llm): restore LLM explanations in shared conversation engine - #245
Merged
Conversation
PR #240 made queries deterministic, so free-form explain/question messages stopped reaching the provider and instead dumped the raw workspace summary. When completion is enabled and the resolved plan is a conversational QueryPlan, execute the query for grounded facts, then ask the provider to phrase a prose answer. /context and /describe remain deterministic; failure or empty responses fall back to the raw facts. - Update the Python and web simulators to handle text synthesis requests. - Add engine tests for synthesis, fallback, and slash-command determinism.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
PR #240 made queries deterministic, so free-form explain/question messages
stopped reaching the provider and instead dumped the raw workspace summary.
When completion is enabled and the resolved plan is a conversational QueryPlan,
execute the query for grounded facts, then ask the provider to phrase a prose
answer. /context and /describe remain deterministic; failure or empty responses
fall back to the raw facts.