Upgrade Vally evaluations to 0.14 - #419
Open
Larry Osterman (LarryOsterman) wants to merge 1 commit into
Open
Conversation
Update experiment configuration, consolidate Rust evals, parameterize execution and grader models, and make workers invoke the package-local Vally executable. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Larry Osterman (LarryOsterman)
requested a review
from Govind Kamtamneni (thegovind)
as a code owner
August 28, 2026 22:39
Copilot started reviewing on behalf of
Larry Osterman (LarryOsterman)
August 28, 2026 22:40
View session
Contributor
There was a problem hiding this comment.
Copilot review overview
Review tier: Balanced
Findings: 1
New issues introduced by this change (1)
| Severity | Finding |
|---|---|
 |
tests/run-skill-experiments.ps1 — These overrides can set the generator and grader to the same value (for example, `-Model foo… |
What changed in this PR
Upgrades Vally evaluations to 0.14 and standardizes model separation and skill experiments across Python and Rust scenarios.
Changes:
- Parameterizes generator and grader models across 49 eval specifications.
- Consolidates Rust experiments onto canonical evals with standard program graders.
- Updates Vally dependencies, CI, PowerShell execution, and model-policy validation.
| File | Description |
|---|---|
.github/workflows/run-vally-evaluations.yml |
Upgrades CI Vally CLI to 0.14. |
tests/package.json |
Upgrades Vally dependencies. |
tests/pnpm-workspace.yaml |
Allows required native dependency builds. |
tests/plugins/vally-eval-models.test.ts |
Adds model-separation policy tests. |
tests/run-skill-experiments.ps1 |
Adds model overrides and local Vally execution. |
tests/scenarios/_shared/vally/grader-plugins/rust-cargo-build-failure/package.json |
Upgrades plugin Vally dependency. |
tests/scenarios/agent-framework-azure-ai-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/agent-framework-azure-ai-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-ai-contentsafety-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-ai-contentsafety-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-ai-contentunderstanding-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-ai-contentunderstanding-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-ai-language-conversations-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-ai-language-conversations-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-ai-ml-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-ai-ml-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-ai-projects-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-ai-projects-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-ai-textanalytics-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-ai-textanalytics-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-ai-transcription-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-ai-transcription-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-ai-translation-document-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-ai-translation-document-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-ai-translation-text-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-ai-translation-text-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-ai-vision-imageanalysis-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-ai-vision-imageanalysis-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-ai-voicelive-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-ai-voicelive-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-appconfiguration-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-appconfiguration-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-containerregistry-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-containerregistry-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-cosmos-db-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-cosmos-db-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-cosmos-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-cosmos-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-cosmos-rust/vally/eval.yaml |
Consolidates environment and compatible graders. |
tests/scenarios/azure-cosmos-rust/vally/skill_effectiveness_eval.yaml |
Removes duplicate legacy eval. |
tests/scenarios/azure-cosmos-rust/vally/skill_effectiveness_experiment.yaml |
Targets the canonical eval. |
tests/scenarios/azure-data-tables-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-data-tables-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-eventgrid-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-eventgrid-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-eventhub-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-eventhub-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-eventhub-rust/vally/eval.yaml |
Consolidates environment and compatible graders. |
tests/scenarios/azure-eventhub-rust/vally/skill_effectiveness_eval.yaml |
Removes duplicate legacy eval. |
tests/scenarios/azure-eventhub-rust/vally/skill_effectiveness_experiment.yaml |
Targets the canonical eval. |
tests/scenarios/azure-identity-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-identity-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-identity-rust/vally/eval.yaml |
Consolidates environment and compatible graders. |
tests/scenarios/azure-identity-rust/vally/skill_effectiveness_eval.yaml |
Removes duplicate legacy eval. |
tests/scenarios/azure-identity-rust/vally/skill_effectiveness_experiment.yaml |
Targets the canonical eval. |
tests/scenarios/azure-keyvault-certificates-rust/vally/eval.yaml |
Consolidates environment and compatible graders. |
tests/scenarios/azure-keyvault-certificates-rust/vally/skill_effectiveness_eval.yaml |
Removes duplicate legacy eval. |
tests/scenarios/azure-keyvault-certificates-rust/vally/skill_effectiveness_experiment.yaml |
Targets the canonical eval. |
tests/scenarios/azure-keyvault-keys-rust/vally/eval.yaml |
Consolidates environment and compatible graders. |
tests/scenarios/azure-keyvault-keys-rust/vally/skill_effectiveness_eval.yaml |
Removes duplicate legacy eval. |
tests/scenarios/azure-keyvault-keys-rust/vally/skill_effectiveness_experiment.yaml |
Targets the canonical eval. |
tests/scenarios/azure-keyvault-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-keyvault-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-keyvault-secrets-rust/vally/eval.yaml |
Consolidates environment and compatible graders. |
tests/scenarios/azure-keyvault-secrets-rust/vally/skill_effectiveness_eval.yaml |
Removes duplicate legacy eval. |
tests/scenarios/azure-keyvault-secrets-rust/vally/skill_effectiveness_experiment.yaml |
Targets the canonical eval. |
tests/scenarios/azure-messaging-webpubsubservice-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-messaging-webpubsubservice-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-mgmt-apicenter-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-mgmt-apicenter-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-mgmt-apimanagement-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-mgmt-apimanagement-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-mgmt-botservice-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-mgmt-botservice-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-mgmt-fabric-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-mgmt-fabric-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-monitor-ingestion-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-monitor-ingestion-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-monitor-opentelemetry-exporter-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-monitor-opentelemetry-exporter-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-monitor-opentelemetry-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-monitor-opentelemetry-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-monitor-query-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-monitor-query-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-search-documents-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-search-documents-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-servicebus-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-servicebus-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-speech-to-text-rest-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-speech-to-text-rest-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-storage-blob-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-storage-blob-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-storage-blob-rust/vally/eval-keyvault-encryption.yaml |
Parameterizes models. |
tests/scenarios/azure-storage-blob-rust/vally/eval.yaml |
Consolidates environment and compatible graders. |
tests/scenarios/azure-storage-blob-rust/vally/skill_effectiveness_eval.yaml |
Removes duplicate legacy eval. |
tests/scenarios/azure-storage-blob-rust/vally/skill_effectiveness_experiment.yaml |
Targets the canonical eval. |
tests/scenarios/azure-storage-file-datalake-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-storage-file-datalake-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-storage-file-share-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-storage-file-share-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-storage-queue-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/azure-storage-queue-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/azure-storage-queue-rust/vally/eval.yaml |
Consolidates environment and compatible graders. |
tests/scenarios/azure-storage-queue-rust/vally/skill_effectiveness_eval.yaml |
Removes duplicate legacy eval. |
tests/scenarios/azure-storage-queue-rust/vally/skill_effectiveness_experiment.yaml |
Targets the canonical eval. |
tests/scenarios/fastapi-router-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/fastapi-router-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/m365-agents-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/m365-agents-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
tests/scenarios/pydantic-models-py/vally/eval.yaml |
Parameterizes models. |
tests/scenarios/pydantic-models-py/vally/skill_effectiveness_experiment.yaml |
Standardizes experiment variants. |
Files not reviewed (1)
- tests/package-lock.json: Generated file
💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.
Comment on lines
+1081
to
+1086
| $vallyArgs = @( | ||
| "experiment", "run", "skill_effectiveness_experiment.yaml", | ||
| "--output-dir", $skillOutputRoot, | ||
| "--param", "MODEL=$Model", | ||
| "--param", "GRADER_MODEL=$GraderModel" | ||
| ) |
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
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
gpt-5.6-terraandclaude-sonnet-4.6Validation