Bump the npm group in /eng/harness-evaluation with 2 updates by dependabot[bot] · Pull Request #39115 · dotnet/efcore

dependabot · 2026-09-28T17:27:19Z

Bumps the npm group in /eng/harness-evaluation with 2 updates: @microsoft/vally and @microsoft/vally-cli.

Updates @microsoft/vally from 0.16.0 to 0.17.0

Updates @microsoft/vally-cli from 0.16.0 to 0.17.0

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

@dependabot rebase will rebase this PR
@dependabot recreate will recreate this PR, overwriting any edits that have been made to it
@dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
@dependabot ignore <dependency name> major version will close this group update PR and stop Dependabot creating any more for the specific dependency's major version (unless you unignore this specific dependency's major version or upgrade to it yourself)
@dependabot ignore <dependency name> minor version will close this group update PR and stop Dependabot creating any more for the specific dependency's minor version (unless you unignore this specific dependency's minor version or upgrade to it yourself)
@dependabot ignore <dependency name> will close this group update PR and stop Dependabot creating any more for the specific dependency (unless you unignore this specific dependency or upgrade to it yourself)
@dependabot unignore <dependency name> will remove all of the ignore conditions of the specified dependency
@dependabot unignore <dependency name> <ignore condition> will remove the ignore condition of the specified dependency and ignore conditions

Bumps the npm group in /eng/harness-evaluation with 2 updates: @microsoft/vally and @microsoft/vally-cli. Updates `@microsoft/vally` from 0.16.0 to 0.17.0 Updates `@microsoft/vally-cli` from 0.16.0 to 0.17.0 --- updated-dependencies: - dependency-name: "@microsoft/vally" dependency-version: 0.17.0 dependency-type: direct:development update-type: version-update:semver-minor dependency-group: npm - dependency-name: "@microsoft/vally-cli" dependency-version: 0.17.0 dependency-type: direct:development update-type: version-update:semver-minor dependency-group: npm ... Signed-off-by: dependabot[bot] <support@github.com>

github-code-quality · 2026-09-28T17:55:19Z

Code Coverage Overview

Languages: C#

C# / code-coverage

The overall line coverage in commit d08c1ba in the dependabot/npm_and_y... branch remains at 76%, unchanged from commit ac7beba in the main branch.

Show a line coverage summary of the most impacted files.

File	`main` ac7beba	`dependabot/npm_and_y...` d08c1ba	+/-
`src/EFCore.Rela...delValidator.cs`	96%	96%	0%
`src/EFCore.Sqli...SqlGenerator.cs`	97%	97%	0%
`src/EFCore.Rela...ationalModel.cs`	94%	96%	+2%
`src/EFCore.Rela...nalJsonIndex.cs`	60%	62%	+2%
`src/EFCore.Rela...CommandBatch.cs`	90%	94%	+4%
`src/EFCore.Rela...redProcedure.cs`	78%	88%	+10%
`src/EFCore.SqlS...SqlGenerator.cs`	84%	96%	+12%
`src/EFCore.Rela...ationCommand.cs`	85%	98%	+13%
`src/EFCore.Rela...CommandBatch.cs`	65%	89%	+24%
`src/EFCore.Rela...edureBuilder.cs`	62%	88%	+26%

_{Updated October 02, 2026 02:11 UTC}

…on/npm-19a50c1d78

github-actions · 2026-10-05T21:12:50Z

Agent evaluation: `change-tracking`

Status: ✅ passed for 57a3cbe4be0bc5e5e7f44195abf70be3d505c6c3
Treatment quality threshold: ✅ passed
Required skill activation change-tracking: ✅ passed

Model: gpt-5.6-sol

Quality score (treatment relative to control): $\color{green}{\mathbf{0.16}}$ (3 wins, 1 ties, 1 losses).

Treatment grades by stimulus

Stimulus	Successful trials	Mean score	Token delta	Grader passes
diagnose-temporary-value-snapshot-transition	5/5	1.00	$\color{red}{\mathbf{+64{,}224\ tokens}}$	file-matches analysis.md /(InternalEnti…/: 5/5 prompt: 5/5 token-budget max 2000000: 5/5

Previous result from PR #39087 provides the baseline.

Download Vally reports · View workflow run

github-actions · 2026-10-05T21:13:01Z

Agent evaluation: `copilot-instructions`

Status: ❌ failed for 57a3cbe4be0bc5e5e7f44195abf70be3d505c6c3
Treatment quality threshold: ❌ failed

Model: gpt-5.6-sol

Quality score (treatment relative to control): $\color{green}{\mathbf{0.05}}$ (4 wins, 9 ties, 2 losses).

Treatment grades by stimulus

Stimulus	Successful trials	Mean score	Token delta	Grader passes
add-a-query-test-through-provider-hierarchies	5/5	0.44	$\color{red}{\mathbf{+62{,}053\ tokens}}$	file-matches test-plan.md /(?i)(?=[\s\S]…/: 5/5 prompt: 1/5 token-budget max 750000: 5/5
design-a-nonshared-provider-query-regression	5/5	0.86	$\color{red}{\mathbf{+24{,}828\ tokens}}$	file-matches regression-pl… /(?i)(?=[\s\S]…/: 5/5 prompt: 4/5 token-budget max 1200000: 5/5
plan-a-provider-independent-async-api	5/5	1.00	$\color{red}{\mathbf{+9{,}485\ tokens}}$	file-matches implementatio… /(?i)(?=[\s\S]…/: 5/5 prompt: 5/5 token-budget max 1000000: 5/5

Previous result from PR #39087 provides the baseline.

Download Vally reports · View workflow run

github-actions · 2026-10-05T21:23:08Z

Agent evaluation: `cosmos-provider`

Status: ✅ passed for 57a3cbe4be0bc5e5e7f44195abf70be3d505c6c3
Treatment quality threshold: ✅ passed
Required skill activation cosmos-provider: ✅ passed

Model: gpt-5.6-sol

Quality score (treatment relative to control): $\color{green}{\mathbf{0.24}}$ (3 wins, 2 ties, 0 losses).

Treatment grades by stimulus

Stimulus	Successful trials	Mean score	Token delta	Grader passes
explain-readitem-discriminator-selection	5/5	1.00	$\color{red}{\mathbf{+30{,}565\ tokens}}$	file-matches analysis.md /(?=[\s\S]*Cos…/: 5/5 prompt: 5/5 token-budget max 2000000: 5/5

Previous result from PR #39087 provides the baseline.

Download Vally reports · View workflow run

github-actions · 2026-10-05T21:39:12Z

Agent evaluation: `make-custom-agent`

Status: ✅ passed for 57a3cbe4be0bc5e5e7f44195abf70be3d505c6c3
Treatment quality threshold: ✅ passed
Required skill activation make-custom-agent: ✅ passed

Model: gpt-5.6-sol

Quality score (treatment relative to control): $\color{green}{\mathbf{0.08}}$ (2 wins, 2 ties, 1 losses).

Treatment grades by stimulus

Stimulus	Successful trials	Mean score	Token delta	Grader passes
create-an-efcore-api-review-agent	5/5	1.00	$\color{green}{\mathbf{-45{,}007\ tokens}}$	file-matches .github/agent… /(?m)^---[\s\S…/: 5/5 file-matches eng/harness-e… /(?m)^name:\s*…/: 5/5 prompt: 5/5 token-budget max 1000000: 5/5

Previous result from PR #39087 provides the baseline.

Download Vally reports · View workflow run

github-actions · 2026-10-05T21:41:27Z

Agent evaluation: `make-github-actions-workflow`

Status: ✅ passed for 57a3cbe4be0bc5e5e7f44195abf70be3d505c6c3
Treatment quality threshold: ✅ passed
Required skill activation make-github-actions-workflow: ✅ passed

Model: gpt-5.6-sol

Quality score (treatment relative to control): 0.00 (0 wins, 5 ties, 0 losses).

Treatment grades by stimulus

Stimulus	Successful trials	Mean score	Token delta	Grader passes
extend-the-release-target-validation-workflow	5/5	1.00	$\color{red}{\mathbf{+22{,}533\ tokens}}$	file-matches .github/workf… /(?=[\s\S]*act…/: 5/5 prompt: 5/5 token-budget max 750000: 5/5

Previous result from PR #39087 provides the baseline.

Download Vally reports · View workflow run

github-actions · 2026-10-05T21:55:05Z

Agent evaluation: `make-instructions`

Status: ✅ passed for 57a3cbe4be0bc5e5e7f44195abf70be3d505c6c3
Treatment quality threshold: ✅ passed
Required skill activation make-instructions: ✅ passed

Model: gpt-5.6-sol

Quality score (treatment relative to control): 0.00 (1 wins, 3 ties, 1 losses).

Treatment grades by stimulus

Stimulus	Successful trials	Mean score	Token delta	Grader passes
create-query-pipeline-file-instructions	5/5	1.00	$\color{red}{\mathbf{+27{,}246\ tokens}}$	file-matches .github/instr… /(?m)^---[\s\S…/: 5/5 file-matches eng/harness-e… /(?m)(?=[\s\S]…/: 5/5 prompt: 5/5 token-budget max 1000000: 5/5

Previous result from PR #39087 provides the baseline.

Download Vally reports · View workflow run

github-actions · 2026-10-05T22:00:14Z

Agent evaluation: `make-skill`

Status: ✅ passed for 57a3cbe4be0bc5e5e7f44195abf70be3d505c6c3
Treatment quality threshold: ✅ passed
Required skill activation make-skill: ✅ passed

Model: gpt-5.6-sol

Quality score (treatment relative to control): $\color{green}{\mathbf{0.24}}$ (3 wins, 2 ties, 0 losses).

Treatment grades by stimulus

Stimulus	Successful trials	Mean score	Token delta	Grader passes
create-context-pool-diagnostics-skill	5/5	0.95	$\color{red}{\mathbf{+1{,}859{,}574\ tokens}}$	file-matches .agents/skill… /(?m)^---(?=[\…/: 5/5 file-matches eng/harness-e… /(?m)(?=[\s\S]…/: 5/5 prompt: 5/5 token-budget max 1500000: 0/5

Previous result from PR #39087 provides the baseline.

Download Vally reports · View workflow run

github-actions · 2026-10-05T22:02:39Z

Agent evaluation: `migrations`

Status: ✅ passed for 57a3cbe4be0bc5e5e7f44195abf70be3d505c6c3
Treatment quality threshold: ✅ passed
Required skill activation migrations: ✅ passed

Model: gpt-5.6-sol

Quality score (treatment relative to control): $\color{green}{\mathbf{0.08}}$ (2 wins, 2 ties, 1 losses).

Treatment grades by stimulus

Stimulus	Successful trials	Mean score	Token delta	Grader passes
diagnose-an-upgrade-only-spurious-diff	5/5	1.00	$\color{red}{\mathbf{+20{,}098\ tokens}}$	file-matches analysis.md /(SnapshotMode…/: 5/5 prompt: 5/5 token-budget max 2000000: 5/5

Previous result from PR #39087 provides the baseline.

Download Vally reports · View workflow run

github-actions · 2026-10-05T22:13:34Z

Agent evaluation: `model-building`

Status: ✅ passed for 57a3cbe4be0bc5e5e7f44195abf70be3d505c6c3
Treatment quality threshold: ✅ passed
Required skill activation model-building: ✅ passed

Model: gpt-5.6-sol

Quality score (treatment relative to control): $\color{green}{\mathbf{0.16}}$ (2 wins, 3 ties, 0 losses).

Treatment grades by stimulus

Stimulus	Successful trials	Mean score	Token delta	Grader passes
place-a-property-discovery-convention-change	5/5	1.00	$\color{red}{\mathbf{+44{,}132\ tokens}}$	file-matches analysis.md /(ConventionSe…/: 5/5 prompt: 5/5 token-budget max 750000: 5/5

Previous result from PR #39087 provides the baseline.

Download Vally reports · View workflow run

github-actions · 2026-10-05T22:22:18Z

Agent evaluation: `query-pipeline`

Status: ✅ passed for 57a3cbe4be0bc5e5e7f44195abf70be3d505c6c3
Treatment quality threshold: ✅ passed
Required skill activation query-pipeline: ✅ passed

Model: gpt-5.6-sol

Quality score (treatment relative to control): $\color{green}{\mathbf{0.24}}$ (3 wins, 2 ties, 0 losses).

Treatment grades by stimulus

Stimulus	Successful trials	Mean score	Token delta	Grader passes
place-and-validate-a-where-translation-change	5/5	0.89	$\color{red}{\mathbf{+30{,}014\ tokens}}$	file-matches analysis.md /(?=[\s\S]*Sel…/: 3/5 prompt: 5/5 token-budget max 750000: 5/5

Previous result from PR #39087 provides the baseline.

Download Vally reports · View workflow run

github-actions · 2026-10-05T22:30:55Z

Agent evaluation: `run-apichief`

Status: ✅ passed for 57a3cbe4be0bc5e5e7f44195abf70be3d505c6c3
Treatment quality threshold: ✅ passed
Required skill activation run-apichief: ✅ passed

Model: gpt-5.6-sol

Quality score (treatment relative to control): $\color{green}{\mathbf{0.20}}$ (1 wins, 4 ties, 0 losses).

Treatment grades by stimulus

Stimulus	Successful trials	Mean score	Token delta	Grader passes
plan-an-efcore-baseline-refresh	5/5	0.87	$\color{green}{\mathbf{-15{,}882\ tokens}}$	file-matches apichief-plan… /(?=[\s\S]*res…/: 5/5 prompt: 4/5 token-budget max 750000: 5/5

Previous result from PR #39087 provides the baseline.

Download Vally reports · View workflow run

github-actions · 2026-10-05T22:36:11Z

Agent evaluation: `scaffolding`

Status: ✅ passed for 57a3cbe4be0bc5e5e7f44195abf70be3d505c6c3
Treatment quality threshold: ✅ passed
Required skill activation scaffolding: ✅ passed

Model: gpt-5.6-sol

Quality score (treatment relative to control): $\color{green}{\mathbf{0.08}}$ (1 wins, 4 ties, 0 losses).

Treatment grades by stimulus

Stimulus	Successful trials	Mean score	Token delta	Grader passes
place-a-database-model-shape-change	5/5	1.00	$\color{green}{\mathbf{-30{,}057\ tokens}}$	file-matches analysis.md /IDatabaseMode…/: 5/5 prompt: 5/5 token-budget max 750000: 5/5

Previous result from PR #39087 provides the baseline.

Download Vally reports · View workflow run

github-actions · 2026-10-05T22:50:11Z

Agent evaluation: `servicing-pr`

Status: ✅ passed for 57a3cbe4be0bc5e5e7f44195abf70be3d505c6c3
Treatment quality threshold: ✅ passed
Required skill activation servicing-pr: ✅ passed

Model: gpt-5.6-sol

Quality score (treatment relative to control): $\color{green}{\mathbf{0.16}}$ (3 wins, 1 ties, 1 losses).

Treatment grades by stimulus

Stimulus	Successful trials	Mean score	Token delta	Grader passes
draft-a-change-tracking-servicing-pr	5/5	1.00	$\color{red}{\mathbf{+7{,}394\ tokens}}$	file-matches servicing-pr.… /[release/10\…/: 5/5 prompt: 5/5 token-budget max 750000: 5/5

Previous result from PR #39087 provides the baseline.

Download Vally reports · View workflow run

github-actions · 2026-10-05T22:51:34Z

Agent evaluation: `sqlite-adonet`

Status: ✅ passed for 57a3cbe4be0bc5e5e7f44195abf70be3d505c6c3
Treatment quality threshold: ✅ passed
Required skill activation sqlite-adonet: ✅ passed

Model: gpt-5.6-sol

Quality score (treatment relative to control): $\color{green}{\mathbf{0.16}}$ (3 wins, 1 ties, 1 losses).

Treatment grades by stimulus

Stimulus	Successful trials	Mean score	Token delta	Grader passes
diagnose-reused-command-state	5/5	0.87	$\color{green}{\mathbf{-17{,}458\ tokens}}$	file-matches analysis.md /Sqlite(Connec…/: 5/5 prompt: 4/5 token-budget max 750000: 5/5

Previous result from PR #39087 provides the baseline.

Download Vally reports · View workflow run

github-actions · 2026-10-05T22:55:15Z

Agent evaluation: `tooling`

Status: ❌ failed for 57a3cbe4be0bc5e5e7f44195abf70be3d505c6c3
Treatment quality threshold: ❌ failed
Required skill activation tooling: ✅ passed

Model: gpt-5.6-sol

Quality score (treatment relative to control): $\color{green}{\mathbf{0.08}}$ (2 wins, 2 ties, 1 losses).

Treatment grades by stimulus

Stimulus	Successful trials	Mean score	Token delta	Grader passes
thread-a-migrations-add-option	5/5	0.61	$\color{red}{\mathbf{+62{,}167\ tokens}}$	file-matches tooling-plan.… /suppress-summ…/: 5/5 prompt: 2/5 token-budget max 750000: 3/5

Previous result from PR #39087 provides the baseline.

Download Vally reports · View workflow run

github-actions · 2026-10-05T23:04:53Z

Agent evaluation: `triage`

Status: ✅ passed for 57a3cbe4be0bc5e5e7f44195abf70be3d505c6c3
Treatment quality threshold: ✅ passed
Required skill activation triage: ✅ passed

Model: gpt-5.6-sol

Quality score (treatment relative to control): $\color{green}{\mathbf{0.52}}$ (7 wins, 3 ties, 0 losses).

Treatment grades by stimulus

Stimulus	Successful trials	Mean score	Token delta	Grader passes
stop-on-a-security-sensitive-relational-report	5/5	1.00	$\color{green}{\mathbf{-70{,}936\ tokens}}$	file-not-exists triage-report.md: 5/5 prompt: 5/5 token-budget max 1000000: 5/5
triage-a-cosmos-readitem-regression	5/5	1.00	$\color{green}{\mathbf{-32{,}878\ tokens}}$	file-matches triage-report… /AI Triage[\s\…/: 5/5 prompt: 5/5 token-budget max 1000000: 5/5

Previous result from PR #39087 provides the baseline.

Download Vally reports · View workflow run

github-actions · 2026-10-05T23:10:57Z

Agent evaluation: `update-pipeline`

Status: ✅ passed for 57a3cbe4be0bc5e5e7f44195abf70be3d505c6c3
Treatment quality threshold: ✅ passed
Required skill activation update-pipeline: ✅ passed

Model: gpt-5.6-sol

Quality score (treatment relative to control): $\color{green}{\mathbf{0.24}}$ (4 wins, 0 ties, 1 losses).

Treatment grades by stimulus

Stimulus	Successful trials	Mean score	Token delta	Grader passes
diagnose-fk-ordering-and-concurrency	5/5	1.00	$\color{green}{\mathbf{-187{,}555\ tokens}}$	file-matches analysis.md /CommandBatchP…/: 5/5 prompt: 5/5 token-budget max 750000: 5/5

Previous result from PR #39087 provides the baseline.

Download Vally reports · View workflow run

dependabot Bot added the area-infrastructure label Sep 28, 2026

dependabot Bot requested review from AndriySvyryd and wtgodbe as code owners September 28, 2026 17:27

Remove deprecated output_delivery

83151de

github-actions Bot added the area-harness label Oct 2, 2026

Merge branch 'main' into dependabot/npm_and_yarn/eng/harness-evaluati…

d08c1ba

…on/npm-19a50c1d78

AndriySvyryd force-pushed the dependabot/npm_and_yarn/eng/harness-evaluation/npm-19a50c1d78 branch from 9460e9f to d08c1ba Compare October 2, 2026 01:41

AndriySvyryd enabled auto-merge (squash) October 5, 2026 20:35

wtgodbe approved these changes Oct 5, 2026

View reviewed changes

AndriySvyryd merged commit 57a3cbe into main Oct 5, 2026
24 checks passed

AndriySvyryd deleted the dependabot/npm_and_yarn/eng/harness-evaluation/npm-19a50c1d78 branch October 5, 2026 20:56

dotnet-maestro Bot mentioned this pull request Oct 6, 2026

[main] Source code updates from dotnet/efcore dotnet/dotnet#9975

Merged

dotnet-milestone-bot Bot added this to the 12.0-preview1 milestone Oct 6, 2026

Conversation

dependabot Bot commented on behalf of github Sep 28, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

github-code-quality Bot commented Sep 28, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Code Coverage Overview

C# / code-coverage

Uh oh!

Uh oh!

github-actions Bot commented Oct 5, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Agent evaluation: change-tracking

Treatment grades by stimulus

Uh oh!

github-actions Bot commented Oct 5, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Agent evaluation: copilot-instructions

Treatment grades by stimulus

Uh oh!

github-actions Bot commented Oct 5, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Agent evaluation: cosmos-provider

Treatment grades by stimulus

Uh oh!

github-actions Bot commented Oct 5, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Agent evaluation: make-custom-agent

Treatment grades by stimulus

Uh oh!

github-actions Bot commented Oct 5, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Agent evaluation: make-github-actions-workflow

Treatment grades by stimulus

Uh oh!

github-actions Bot commented Oct 5, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Agent evaluation: make-instructions

Treatment grades by stimulus

Uh oh!

github-actions Bot commented Oct 5, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Agent evaluation: make-skill

Treatment grades by stimulus

Uh oh!

github-actions Bot commented Oct 5, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Agent evaluation: migrations

Treatment grades by stimulus

Uh oh!

github-actions Bot commented Oct 5, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Agent evaluation: model-building

Treatment grades by stimulus

Uh oh!

github-actions Bot commented Oct 5, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Agent evaluation: query-pipeline

Treatment grades by stimulus

Uh oh!

github-actions Bot commented Oct 5, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Agent evaluation: run-apichief

Treatment grades by stimulus

Uh oh!

github-actions Bot commented Oct 5, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Agent evaluation: scaffolding

Treatment grades by stimulus

Uh oh!

github-actions Bot commented Oct 5, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Agent evaluation: servicing-pr

Treatment grades by stimulus

Uh oh!

github-actions Bot commented Oct 5, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Agent evaluation: sqlite-adonet

Treatment grades by stimulus

Uh oh!

dependabot Bot commented on behalf of github Sep 28, 2026 •

edited

Loading

github-code-quality Bot commented Sep 28, 2026 •

edited

Loading

github-actions Bot commented Oct 5, 2026 •

edited

Loading

Agent evaluation: `change-tracking`

github-actions Bot commented Oct 5, 2026 •

edited

Loading

Agent evaluation: `copilot-instructions`

github-actions Bot commented Oct 5, 2026 •

edited

Loading

Agent evaluation: `cosmos-provider`

github-actions Bot commented Oct 5, 2026 •

edited

Loading

Agent evaluation: `make-custom-agent`

github-actions Bot commented Oct 5, 2026 •

edited

Loading

Agent evaluation: `make-github-actions-workflow`

github-actions Bot commented Oct 5, 2026 •

edited

Loading

Agent evaluation: `make-instructions`

github-actions Bot commented Oct 5, 2026 •

edited

Loading

Agent evaluation: `make-skill`

github-actions Bot commented Oct 5, 2026 •

edited

Loading

Agent evaluation: `migrations`

github-actions Bot commented Oct 5, 2026 •

edited

Loading

Agent evaluation: `model-building`

github-actions Bot commented Oct 5, 2026 •

edited

Loading

Agent evaluation: `query-pipeline`

github-actions Bot commented Oct 5, 2026 •

edited

Loading

Agent evaluation: `run-apichief`

github-actions Bot commented Oct 5, 2026 •

edited

Loading

Agent evaluation: `scaffolding`

github-actions Bot commented Oct 5, 2026 •

edited

Loading

Agent evaluation: `servicing-pr`

github-actions Bot commented Oct 5, 2026 •

edited

Loading

Agent evaluation: `sqlite-adonet`

github-actions Bot commented Oct 5, 2026 •

edited

Loading

Agent evaluation: `tooling`

github-actions Bot commented Oct 5, 2026 •

edited

Loading

Agent evaluation: `triage`

github-actions Bot commented Oct 5, 2026 •

edited

Loading

Agent evaluation: `update-pipeline`