feat(operator): include check cost in Slack alerts - #2282
Draft
tuusberg wants to merge 2 commits into
Draft
Conversation
Contributor
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (1)
🚧 Files skipped from review as they are similar to previous changes (1)
WalkthroughChangesLLM usage attribution
Estimated code review effort: 2 (Simple) | ~10 minutes Sequence Diagram(s)sequenceDiagram
participant CheckExecution
participant AlertAPI
participant SlackDestination
CheckExecution->>AlertAPI: produce CheckResult with LLM usage
AlertAPI->>SlackDestination: pass usage-enriched LLMResult
SlackDestination->>SlackDestination: append cost and token context
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
✅ Deploy Preview for holmes-docs ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
🧹 Nitpick comments (1)
holmes/checks/checks.py (1)
139-164: 📐 Maintainability & Code Quality | 🔵 Trivial | ⚡ Quick winConsider consolidating the PASS/FAIL branches to reduce duplication.
The two
CheckResultconstructions differ only instatusandmessage; the remaining fields (including the four new usage fields) are identical. Consolidating would prevent future field divergence as more metrics are added.♻️ Optional refactor to eliminate duplication
- if check_response.passed: - result = CheckResult( - check_name=check.name, - status=CheckStatus.PASS, - message=f"Check passed. {check_response.rationale}", - query=check.query, - duration=duration, - rationale=check_response.rationale, - total_cost=response.total_cost, - total_tokens=response.total_tokens, - prompt_tokens=response.prompt_tokens, - completion_tokens=response.completion_tokens, - ) - else: - result = CheckResult( - check_name=check.name, - status=CheckStatus.FAIL, - message=f"Check failed. {check_response.rationale}", - query=check.query, - duration=duration, - rationale=check_response.rationale, - total_cost=response.total_cost, - total_tokens=response.total_tokens, - prompt_tokens=response.prompt_tokens, - completion_tokens=response.completion_tokens, - ) + status = CheckStatus.PASS if check_response.passed else CheckStatus.FAIL + verb = "passed" if check_response.passed else "failed" + result = CheckResult( + check_name=check.name, + status=status, + message=f"Check {verb}. {check_response.rationale}", + query=check.query, + duration=duration, + rationale=check_response.rationale, + total_cost=response.total_cost, + total_tokens=response.total_tokens, + prompt_tokens=response.prompt_tokens, + completion_tokens=response.completion_tokens, + )🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@holmes/checks/checks.py` around lines 139 - 164, Consolidate the duplicated CheckResult construction in the check evaluation flow by selecting status and the corresponding message from check_response.passed, then instantiate CheckResult once with the shared fields, including usage metrics. Preserve the existing PASS/FAIL statuses and message text.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Nitpick comments:
In `@holmes/checks/checks.py`:
- Around line 139-164: Consolidate the duplicated CheckResult construction in
the check evaluation flow by selecting status and the corresponding message from
check_response.passed, then instantiate CheckResult once with the shared fields,
including usage metrics. Preserve the existing PASS/FAIL statuses and message
text.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: aa9b0c0f-c513-4aa7-aaaa-a3eec0797ab7
📒 Files selected for processing (6)
holmes/checks/checks.pyholmes/checks/checks_api.pyholmes/checks/models.pyholmes/plugins/destinations/slack/plugin.pytests/checks/test_checks_api.pytests/plugins/destinations/test_slack.py
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.
Summary
Preserves aggregate LLM usage from operator-driven health checks and displays it in Slack failure alerts.
Investigation costand input/output token line in the existing Slack messageWhy
Operator health checks can make several LLM calls. The check usage recorder already receives aggregate stats, but the Slack alert path re-created an empty
LLMResult, discarding that data before formatting the message.Validation
ruff checkfor touched source and test filespytest tests/checks/test_checks_api.py tests/plugins/destinations/test_slack.py --no-cov(3 passed)pytest tests -m 'not llm' -q; its output was truncated by the local runner after progressing through the suite.Summary by CodeRabbit
New Features
Tests