Route llm rule criteria through the instruct service - #1433
Merged
iceljc merged 1 commit intoSep 11, 2026
Merged
Conversation
LlmCriteriaEvaluator called the chat completion provider directly, so the
criteria check never showed up in the instruction log. Run it through
IInstructService.Execute instead, which emits the IInstructHook events that
InstructionLogHook persists.
Two supporting changes make Execute a faithful drop-in:
- IInstructService.Execute takes an optional renderData, threaded into
RenderTemplate/RenderInstruction. The rule engine evaluates criteria before
SetConversationId, so the conversation state is still empty and the default
CollectRenderData path would render the criteria template with no state. The
evaluator passes the trigger states instead.
- CodeInstructOptions.Disabled skips RunCode. The llm evaluator's template name
can be {trigger}_criteria, which collides with CodeCriteriaEvaluator's
{trigger}_criteria.py, so an explicit mode "llm" could otherwise be hijacked
into a code run.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
(cherry picked from commit 8594362)
Contributor
Qodo reviews are paused for this user.Troubleshooting steps vary by plan Learn more → On a Teams plan? Using GitHub Enterprise Server, GitLab Self-Managed, or Bitbucket Data Center? |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
LlmCriteriaEvaluator called the chat completion provider directly, so the criteria check never showed up in the instruction log. Run it through IInstructService.Execute instead, which emits the IInstructHook events that InstructionLogHook persists.
Two supporting changes make Execute a faithful drop-in:
IInstructService.Execute takes an optional renderData, threaded into RenderTemplate/RenderInstruction. The rule engine evaluates criteria before SetConversationId, so the conversation state is still empty and the default CollectRenderData path would render the criteria template with no state. The evaluator passes the trigger states instead.
CodeInstructOptions.Disabled skips RunCode. The llm evaluator's template name can be {trigger}_criteria, which collides with CodeCriteriaEvaluator's {trigger}_criteria.py, so an explicit mode "llm" could otherwise be hijacked into a code run.
(cherry picked from commit 8594362)