chore: version packages

[github-actions]

This PR was opened by the Changesets release GitHub action. When you're ready to do a release, you can merge this and the packages will be published to npm automatically. If you're not ready to do a release yet, that's fine, whenever you add more changesets to main, this PR will be updated.

Releases

hevy-mcp@3.2.1

Patch Changes

• #681 9e62d02 Thanks @chrisdoc! - promote the hosted Cloudflare MCP endpoint in the README

• #679 d232da2 Thanks @chrisdoc! - update readme

✨ PR Description

Purpose: Release version 3.2.1 of hevy-mcp package with patch updates for README documentation.

Main changes:

• Bump version from 3.2.0 to 3.2.1 in package.json and server.json configuration files
• Add changelog entry documenting README improvements and Cloudflare MCP endpoint promotion
• Remove processed changeset file after version release automation

Generated by LinearB AI and added by gitStream.
_{AI-generated content may contain inaccuracies. Please verify before using.
💡 Tip: You can customize your AI Description using Guidelines Learn how}

[gitstream-cm]

✨ PR Review

This is a Changesets-generated release PR bumping hevy-mcp from 3.2.0 to 3.2.1. Version numbers are consistent across package.json and server.json, and the CHANGELOG entry is properly formatted. One procedural concern exists around the changeset type used for the triggering change.

1 issues detected:

🧹 Maintainability - A docs-only README update was tagged as a `patch` changeset, triggering an avoidable npm release instead of using `npx changeset --empty`.

Details: The patch release was triggered by a README update (PR #679 "update readme"). Per project conventions, documentation-only changes (docs, CI, tests, refactors) should use npx changeset --empty to avoid publishing a new npm version. Using a versioned patch changeset here caused an unnecessary 3.2.0 → 3.2.1 version bump and npm publish.

File: CHANGELOG.md (1-5)

Generated by LinearB AI and added by gitStream.
_{AI-generated content may contain inaccuracies. Please verify before using.
💡 Tip: You can customize your AI Review using Guidelines Learn how}

[github-actions]

MCP tool token cost

Measured with o200k_base over the complete json-serialized mcp tools/list result payload: { tools }.
Targets are advisory and never fail CI.

Metric	Current	Target	Status
Tools	25	≤ 20	Above target
Total tokens	12667	—	—
Average tokens/tool	506.68	< 600	Within target

Change from baseline

Metric	Baseline	Current	Delta
Tools	25	25	0
Total tokens	12667	12667	0
Average tokens/tool	506.68	506.68	0

Per-tool changes

Tool	Baseline	Current	Delta
create-body-measurement	669	669	0
create-exercise-template	421	421	0
create-routine	564	564	0
create-routine-folder	166	166	0
create-workout	655	655	0
get-body-measurement	628	628	0
get-body-measurements	629	629	0
get-exercise-history	808	808	0
get-exercise-template	276	276	0
get-exercise-templates	308	308	0
get-routine	552	552	0
get-routine-folder	245	245	0
get-routine-folders	270	270	0
get-routines	586	586	0
get-training-summary	923	923	0
get-user-info	244	244	0
get-workout	522	522	0
get-workout-count	195	195	0
get-workout-events	670	670	0
get-workouts	540	540	0
search-exercise-templates	426	426	0
search-routines	465	465	0
update-body-measurement	667	667	0
update-routine	562	562	0
update-workout	672	672	0

Per-tool breakdown

Tool	Tokens	Share of total
get-training-summary	923	7.29%
get-exercise-history	808	6.38%
update-workout	672	5.31%
get-workout-events	670	5.29%
create-body-measurement	669	5.28%
update-body-measurement	667	5.27%
create-workout	655	5.17%
get-body-measurements	629	4.97%
get-body-measurement	628	4.96%
get-routines	586	4.63%
create-routine	564	4.45%
update-routine	562	4.44%
get-routine	552	4.36%
get-workouts	540	4.26%
get-workout	522	4.12%
search-routines	465	3.67%
search-exercise-templates	426	3.36%
create-exercise-template	421	3.32%
get-exercise-templates	308	2.43%
get-exercise-template	276	2.18%
get-routine-folders	270	2.13%
get-routine-folder	245	1.93%
get-user-info	244	1.93%
get-workout-count	195	1.54%
create-routine-folder	166	1.31%

Per-tool counts encode each complete tool object independently. The total encodes the complete { tools } envelope, so punctuation and separators mean the per-tool values need not sum exactly to the total.