Update Fly.io scaling configuration (flyio-scale-from-ui)

[fly-io]

This PR was automatically generated by the Fly.io dashboard after a scale operation updated the machine sizes.

Merging keeps your packages/kit/fly.toml in sync so the next fly deploy uses the new sizes.

Summary by CodeRabbit

• Chores
  • Updated deployment configuration with optimized VM resource settings, including adjusted memory allocation and CPU configuration.

[hyochan]

/gemini review

[hyochan]

@coderabbitai review

[coderabbitai]

✅ Action performed

Review finished.

Note: CodeRabbit is an incremental review system and does not re-review already reviewed commits. This command is applicable only when automatic reviews are paused.

[coderabbitai]

Important

Review skipped

Bot user detected.

To trigger a single review, invoke the @coderabbitai review command.

⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro

Run ID: d4598c43-a53c-4d64-bc32-93b918a59437

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Use the checkbox below for a quick retry:

• 🔍 Trigger review

📝 Walkthrough

Walkthrough

The Fly deployment configuration is updated with a generated-file header and optimized VM settings. Memory is reduced from 512mb to 256mb with explicit CPU and memory allocation fields, and a process declaration is added alongside documentation linking to Fly's configuration reference.

Changes

Fly deployment configuration

Layer / File(s)	Summary
VM resource and configuration header packages/kit/fly.toml	Added a generated-file header comment documenting the configuration source. Updated the [[vm]] section to reduce memory to 256mb and explicitly specify CPU kind (shared), CPU count (1), and process allocation (['app']).

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Poem

A rabbit hops through configs fine,
256 megs will serve just fine,
With headers clear and CPUs shared,
The Fly deployment, now prepared! 🐰✨

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title clearly describes the main change: updating Fly.io scaling configuration in the fly.toml file, which is exactly what the changeset does.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch flyio-scale-from-ui

---

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

• X
• Mastodon
• Reddit
• LinkedIn

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[gemini-code-assist]

Code Review

This pull request updates the Fly.io configuration in packages/kit/fly.toml by adding boilerplate comments and adjusting the VM resources, notably reducing the memory from 512MB to 256MB. However, reducing the memory to 256MB for a Bun server running a Hono API with heavy dependencies poses a high risk of Out-Of-Memory (OOM) crashes. It is recommended to revert this change and maintain at least 512MB of memory to ensure application stability.

Important

The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.

[gemini-code-assist]

Reducing the VM memory to 256MB for a compiled Bun server (openiap-kit-server) running a Hono API with multiple heavy dependencies (such as googleapis, @sentry/bun, and convex) carries a high risk of Out-Of-Memory (OOM) crashes. The compiled Bun binary itself has a non-trivial baseline memory footprint, and garbage collection overhead under concurrent requests can easily exceed 256MB. It is highly recommended to maintain at least 512MB of memory to guarantee application stability and prevent unexpected downtime.

Suggested change

	memory = '256mb'
	cpu_kind = 'shared'
	cpus = 1
	memory_mb = 256
	memory = '512mb'
	cpu_kind = 'shared'
	cpus = 1
	memory_mb = 512

[hyochan]

Closing per maintainer request. The scaling concern is being handled by keeping the app VM at 512 MB.