[None][test] update coderabbit prompt - #16478
Conversation
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 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.
Inline comments:
In @.coderabbit.yaml:
- Around line 41-46: Update the coverage-summary rules in the configuration
section to distinguish list-only changes under tests/integration/test_lists/
from test-code changes: report the touched test-db/ or qa/ files without
requiring changed test functions, and use a “needs follow-up” verdict when
cbts_touchmap.sqlite or the CBTS report is unavailable. Preserve the existing
summary requirements for changes that include test code.
🪄 Autofix (Beta)
❌ Autofix failed (check again to retry)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Enterprise
Run ID: 8df6d1da-161e-449f-af60-1071a1a3f95a
📒 Files selected for processing (1)
.coderabbit.yaml
There was a problem hiding this comment.
♻️ Duplicate comments (1)
.coderabbit.yaml (1)
38-46: 🎯 Functional Correctness | 🟡 Minor | ⚡ Quick winSeparate test-list-only changes from test-code coverage.
This generic
tests/**instruction still requires changed test functions and per-test list membership for list-only edits undertests/integration/test_lists/**. Add a dedicated branch that reports the touchedtest-db/orqa/files and returns needs follow-up when CBTS data is unavailable, while preserving the current checklist for changes that include test code.🤖 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 @.coderabbit.yaml around lines 38 - 46, Update the tests/** review instructions in .coderabbit.yaml to add a dedicated branch for changes limited to tests/integration/test_lists/**. For list-only edits, report the touched test-db/ or qa/ files and return a needs follow-up coverage verdict when CBTS data is unavailable; retain the existing changed-test-function and membership checklist when test code is also modified.
🧹 Nitpick comments (1)
tests/integration/defs/test_e2e.py (1)
1917-1917: 📐 Maintainability & Code Quality | 🔵 TrivialTest coverage summary
- Modified: existing
test_multi_nodes_evalparametrization; no test functions were added or removed.- Test-list membership: present in
tests/integration/test_lists/qa/llm_function_multinode.txt:6.- No
test-dbsynchronization is required because QA lists are independently maintained.- Verdict: sufficient for manual QA registration. Run with
LLM_MODELS_ROOTset and GPU/model access available.🤖 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 `@tests/integration/defs/test_e2e.py` at line 1917, No code changes are required; retain the GLM-5-NVFP4 entry in the existing test_multi_nodes_eval parametrization and proceed with manual QA using the documented environment and model access.Source: Path instructions
🤖 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.
Duplicate comments:
In @.coderabbit.yaml:
- Around line 38-46: Update the tests/** review instructions in .coderabbit.yaml
to add a dedicated branch for changes limited to
tests/integration/test_lists/**. For list-only edits, report the touched
test-db/ or qa/ files and return a needs follow-up coverage verdict when CBTS
data is unavailable; retain the existing changed-test-function and membership
checklist when test code is also modified.
---
Nitpick comments:
In `@tests/integration/defs/test_e2e.py`:
- Line 1917: No code changes are required; retain the GLM-5-NVFP4 entry in the
existing test_multi_nodes_eval parametrization and proceed with manual QA using
the documented environment and model access.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Enterprise
Run ID: 6ad0a2e2-c9a5-41e9-9b24-8de2a1a5b599
📒 Files selected for processing (3)
.coderabbit.yamltests/integration/defs/test_e2e.pytests/integration/test_lists/qa/llm_function_multinode.txt
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 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.
Inline comments:
In `@tests/integration/defs/test_e2e.py`:
- Line 1917: Add the GLM-5-NVFP4 test case to the appropriate
tests/integration/test_lists/test-db/ CI list, matching the existing test
identifier and formatting used by nearby entries. Ensure
test_multi_nodes_eval[GLM-5-NVFP4-tp16-mmlu] is included if this case is
intended to run in CI.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Enterprise
Run ID: cd1dc093-8af2-41ae-8da7-16be1c9a8b00
📒 Files selected for processing (3)
.coderabbit.yamltests/integration/defs/test_e2e.pytests/integration/test_lists/qa/llm_function_multinode.txt
Signed-off-by: Xin He (SW-GPU) <200704525+xinhe-nv@users.noreply.github.com>
|
/bot skip --comment "only change coderabbit" |
|
PR_Github #60682 [ skip ] triggered by Bot. Commit: |
|
PR_Github #60682 [ skip ] completed with state |
Dev Engineer Review
.coderabbit.yamlto enable incremental auto-reviews (reviews.auto_review.auto_incremental_review: false → true).reviews.collapse_walkthrough: true → false).reviews.high_level_summary_instructionsto always require separate Dev Engineer Review and QA Engineer Review sections.tests/**review guidance to ensure QA coverage feedback is actionable and distinguishes:tests/integration/test_lists/**(driven bytest-db/+qa/list entries), vstests/integration/test_lists/and report coverage based on CBTS availability, using “needs follow-up” when inputs are unavailable).QA Engineer Review
No test changes.
Description
Test Coverage
PR Checklist
Please review the following before submitting your PR:
PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.
PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.
Test cases are provided for new code paths (see test instructions)
If PR introduces API changes, an appropriate PR label is added - either
api-compatibleorapi-breaking. Forapi-breaking, includeBREAKINGin the PR title.Any new dependencies have been scanned for license and vulnerabilities
CODEOWNERS updated if ownership changes
Documentation updated as needed
Update tava architecture diagram if there is a significant design change in PR.
The reviewers assigned automatically/manually are appropriate for the PR.
Please check this after reviewing the above items as appropriate for this PR.
GitHub Bot Help
To see a list of available CI bot commands, please comment
/bot help.