ci(deps): Bump the github-actions group with 2 updates

[dependabot]

Bumps the github-actions group with 2 updates: pnpm/action-setup and github/codeql-action.

Updates pnpm/action-setup from 6.0.3 to 6.0.5

Release notes

Sourced from pnpm/action-setup's releases.

v6.0.5

What's Changed

• fix: append (not prepend) action node dir to PATH for npm bootstrap by @​zkochan in pnpm/action-setup#241

Full Changelog: pnpm/action-setup@v6.0.4...v6.0.5

v6.0.4

What's Changed

• fix: use npm co-located with the action node binary by @​benquarmby in pnpm/action-setup#239

New Contributors

• @​benquarmby made their first contribution in pnpm/action-setup#239

Full Changelog: pnpm/action-setup@v6.0.3...v6.0.4

Commits

• 8912a91 fix: append (not prepend) action node dir to PATH for npm bootstrap (#241)
• 26f6d4f fix: use npm co-located with the action node binary (#239)
• See full diff in compare view

Updates github/codeql-action from 4.35.2 to 4.35.3

Release notes

Sourced from github/codeql-action's releases.

v4.35.3

• Upcoming breaking change: Add a deprecation warning for customers using CodeQL version 2.19.3 and earlier. These versions of CodeQL were discontinued on 9 April 2026 alongside GitHub Enterprise Server 3.15, and will be unsupported by the next minor release of the CodeQL Action. #3837
• Configurations for private registries that use Cloudsmith or GCP OIDC are now accepted. #3850
• Best-effort connection tests for private registries now use GET requests instead of HEAD for better compatibility with various registry implementations. For NuGet feeds, the test is now always performed against the service index. #3853
• Fixed a bug where two diagnostics produced within the same millisecond could overwrite each other on disk, causing one of them to be lost. #3852
• Update default CodeQL bundle version to 2.25.3. #3865

Changelog

Sourced from github/codeql-action's changelog.

CodeQL Action Changelog

See the releases page for the relevant changes to the CodeQL CLI and language packs.

[UNRELEASED]

No user facing changes.

4.35.4 - 07 May 2026

• Update default CodeQL bundle version to 2.25.4. #3881

4.35.3 - 01 May 2026

• Upcoming breaking change: Add a deprecation warning for customers using CodeQL version 2.19.3 and earlier. These versions of CodeQL were discontinued on 9 April 2026 alongside GitHub Enterprise Server 3.15, and will be unsupported by the next minor release of the CodeQL Action. #3837
• Configurations for private registries that use Cloudsmith or GCP OIDC are now accepted. #3850
• Best-effort connection tests for private registries now use GET requests instead of HEAD for better compatibility with various registry implementations. For NuGet feeds, the test is now always performed against the service index. #3853
• Fixed a bug where two diagnostics produced within the same millisecond could overwrite each other on disk, causing one of them to be lost. #3852
• Update default CodeQL bundle version to 2.25.3. #3865

4.35.2 - 15 Apr 2026

• The undocumented TRAP cache cleanup feature that could be enabled using the CODEQL_ACTION_CLEANUP_TRAP_CACHES environment variable is deprecated and will be removed in May 2026. If you are affected by this, we recommend disabling TRAP caching by passing the trap-caching: false input to the init Action. #3795
• The Git version 2.36.0 requirement for improved incremental analysis now only applies to repositories that contain submodules. #3789
• Python analysis on GHES no longer extracts the standard library, relying instead on models of the standard library. This should result in significantly faster extraction and analysis times, while the effect on alerts should be minimal. #3794
• Fixed a bug in the validation of OIDC configurations for private registries that was added in CodeQL Action 4.33.0 / 3.33.0. #3807
• Update default CodeQL bundle version to 2.25.2. #3823

4.35.1 - 27 Mar 2026

• Fix incorrect minimum required Git version for improved incremental analysis: it should have been 2.36.0, not 2.11.0. #3781

4.35.0 - 27 Mar 2026

• Reduced the minimum Git version required for improved incremental analysis from 2.38.0 to 2.11.0. #3767
• Update default CodeQL bundle version to 2.25.1. #3773

4.34.1 - 20 Mar 2026

• Downgrade default CodeQL bundle version to 2.24.3 due to issues with a small percentage of Actions and JavaScript analyses. #3762

4.34.0 - 20 Mar 2026

• Added an experimental change which disables TRAP caching when improved incremental analysis is enabled, since improved incremental analysis supersedes TRAP caching. This will improve performance and reduce Actions cache usage. We expect to roll this change out to everyone in March. #3569
• We are rolling out improved incremental analysis to C/C++ analyses that use build mode none. We expect this rollout to be complete by the end of April 2026. #3584
• Update default CodeQL bundle version to 2.25.0. #3585

4.33.0 - 16 Mar 2026

• Upcoming change: Starting April 2026, the CodeQL Action will skip collecting file coverage information on pull requests to improve analysis performance. File coverage information will still be computed on non-PR analyses. Pull request analyses will log a warning about this upcoming change. #3562

... (truncated)

Commits

• e46ed2c Merge pull request #3867 from github/update-v4.35.3-8c6e48dbe
• b73d1d1 Add changelog entry for #3853
• 24e0bb0 Reorder changelog entries
• ec298da Update changelog for v4.35.3
• 8c6e48d Merge pull request #3865 from github/update-bundle/codeql-bundle-v2.25.3
• 7190983 Add changelog note
• 2bb2095 Update default bundle to codeql-bundle-v2.25.3
• 7851e55 Merge pull request #3850 from github/mbg/private-registry/cloudsmith-gcp
• 262a15f Add generic non-printable chars test for OIDC configs
• a6109b1 Merge pull request #3853 from github/mbg/start-proxy/improved-checks
• Additional commits viewable in compare view

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

[claude]

LGTM — Dependabot patch bumps for pnpm/action-setup (6.0.3 → 6.0.5) and github/codeql-action (4.35.2 → 4.35.3), both pinned to commit SHAs.

Extended reasoning...

Overview

The PR updates two GitHub Actions used in CI workflows: pnpm/action-setup from v6.0.3 to v6.0.5 (a patch bump fixing how npm is located/PATH'd during action bootstrap) and github/codeql-action from v4.35.2 to v4.35.3 (a patch bump bringing private-registry config improvements and an updated CodeQL bundle). Only .github/workflows/ci.yml and .github/workflows/codeql.yml are touched; references are pinned by full commit SHA with the version as a trailing comment, matching the repo's existing pinning convention.

Security risks

Both actions are pinned to specific commit SHAs (not floating tags), so the upgrade is reproducible and the supply-chain surface is unchanged from the existing pinning model. Both upstream repositories (pnpm/action-setup, github/codeql-action) are well-known and the changelogs describe non-security-sensitive patch fixes. No workflow permissions, secrets handling, or trigger semantics are modified.

Level of scrutiny

Low. These are minimal, mechanical CI dependency bumps from Dependabot — no application logic, no production code paths, no auth/crypto/permissions touched. The patch bumps carry low blast radius and CI itself will validate them.

Other factors

The bug hunting system found no issues. There are no prior reviews or outstanding comments on the PR. The diff is small (8 line changes total) and entirely within .github/workflows/.

[github-actions]

Experiment Results: 097ab9e

Experiment	Status	Actions
Uppercase (py)	✅ Pass	View GitHub Action Run · View in Langfuse
Uppercase (ts)	✅ Pass	View GitHub Action Run · View in Langfuse
Mixed dir (node)	✅ Pass	View GitHub Action Run · View in Langfuse
Mixed dir (python)	✅ Pass	View GitHub Action Run · View in Langfuse
Regression fixture	❌ Regression	View GitHub Action Run · View in Langfuse

Details

✅ Uppercase (py) (Source)

Score	Value
avg_accuracy	1.000

Item results (3)

Item	Input	Expected	Output	exact_match
1	langfuse	LANGFUSE	LANGFUSE	1.000
2	world	WORLD	WORLD	1.000
3	hello	HELLO	HELLO	1.000

✅ Uppercase (ts) (Source)

Score	Value
avg_accuracy	1.000

Item results (3)

Item	Input	Expected	Output	exact_match
1	langfuse	LANGFUSE	LANGFUSE	1.000
2	world	WORLD	WORLD	1.000
3	hello	HELLO	HELLO	1.000

✅ Mixed dir (node) (Source)

Score	Value
avg_accuracy	1.000

Item results (3)

Item	Input	Expected	Output	exact_match
1	langfuse	LANGFUSE	LANGFUSE	1.000
2	world	WORLD	WORLD	1.000
3	hello	HELLO	HELLO	1.000

✅ Mixed dir (python) (Source)

Score	Value
avg_accuracy	1.000

Item results (3)

Item	Input	Expected	Output	exact_match
1	langfuse	LANGFUSE	LANGFUSE	1.000
2	world	WORLD	WORLD	1.000
3	hello	HELLO	HELLO	1.000

❌ Regression fixture (Source)

RegressionError: synthetic regression triggered by e2e fixture

Item results (3)

Item	Input	Expected	Output	exact_match
1	langfuse	LANGFUSE	LANGFUSE	1.000
2	world	WORLD	WORLD	1.000
3	hello	HELLO	HELLO	1.000