[github-actions]

Automated synchronization with the latest published command-code CLI package.

This updates only machine-readable compatibility metadata:

• CLI version used in the x-command-code-version header
• image-input capabilities
• reasoning capability and selectable effort levels
• model-specific maximum output limits
• documented catalog snapshot version

Pricing remains review-only because CLI documentation does not represent every pricing tier and temporary promotion used by the provider.

[karaaslanz]

Reviewed exact head 6fd67655b518d7b9c12b3cd226d33950a54f7235 as a catalog-only synchronization change.

Independent checks:

• Downloaded the published command-code@1.81.0 npm tarball; its package manifest confirms version 1.81.0.
• Inspected the bundled reference/models.md: new meta/muse-wonder-1.0 is present, with low, medium, high, xhigh reasoning effort choices. This matches the new generated effort-map entry.
• The PR patch updates the README/catalog version together and adds the new model consistently to input modality, reasoning and efforts. Pricing remains review-only as documented.
• On a clean detached checkout of this exact head, npm run typecheck PASS and git diff --check PASS on Windows.

Limits: I did not run the full suite or a live authenticated model request, so this does not independently prove image support. The hosted workflows show action_required, not green CI. No blocking mismatch was found in the catalog version / effort synchronization reviewed.

[github-actions]

Dependency Review

✅ No vulnerabilities or license issues or OpenSSF Scorecard issues found.

Scanned Files

None

[github-actions]

Memory benchmark

Compared base b61093d with PR head 6fd6765 on the same GitHub-hosted darwin runner. Lower values are better.

Metric	Base	PR	PR − Base	Change
Stable RSS	120.7 MiB ± 0.2 MiB	120.6 MiB ± 0.5 MiB	-0.4 MiB ± 0.1 MiB	-0.3%
Physical footprint	67.0 MiB ± 0.6 MiB	67.0 MiB ± 0.4 MiB	+0.1 MiB ± 0.6 MiB	+0.1%
Physical peak	78.1 MiB ± 0.6 MiB	78.0 MiB ± 1.0 MiB	+0.4 MiB ± 0.8 MiB	+0.5%

Interpretation: Differences larger than their measured MAD: Stable RSS -0.4 MiB ± 0.1 MiB.

Extension overhead above pi baseline

Metric	Base overhead	PR overhead	Difference
Stable RSS	+7.1 MiB ± 0.2 MiB	+6.7 MiB ± 0.2 MiB	-0.4 MiB ± 0.1 MiB
Physical footprint	+3.5 MiB ± 1.3 MiB	+3.9 MiB ± 1.3 MiB	+0.1 MiB ± 0.6 MiB
Physical peak	+5.8 MiB ± 1.4 MiB	+5.4 MiB ± 1.7 MiB	+0.4 MiB ± 0.8 MiB

Values are medians of 6 alternating, paired runs. The value after ± is the median absolute deviation (MAD). Each process was sampled 12 times after a 2500 ms warm-up.

Environment: pi 0.84.4, Bun 1.4.0, darwin arm64. RSS comes from ps; physical footprint and peak come from macOS footprint.

This is a comparative signal, not a pass/fail threshold. GitHub-hosted runner noise can affect absolute values.

[patlux]

Superseded by merged #153, which includes the metadata refresh plus reviewed pricing, updated fixtures, and the CLI 1.82.4 parser fix. The integrated catalog/pricing checks pass for CLI 1.82.4 and all 93 currently advertised API models.