perf(bridge): optimize map and array binding to eliminate allocation overhead

[repyh]

Optimization to bridge/core resolving memory bloat (Optimization Debt) resulting from repetitive allocation overhead during Go to Javascript bridge reflection mapping. Tested natively yielding massive throughput improvements.

---

PR created automatically by Jules for task 10221715549259321240 started by @repyh

Summary by CodeRabbit

• New Features

  • Expose Go byte slices as JavaScript Uint8Array copies for improved binary data handling.

• Refactor

  • Optimized Go↔JS bridge for slice and map conversions with faster iteration and more efficient key formatting.

• Chore

  • Build/run tooling now skips uninspected external imports when generating shims.
  • Updated example dependency to gin v1.11.0.

[google-labs-jules]

👋 Jules, reporting for duty! I'm here to lend a hand with this pull request.

When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down.

I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job!

For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with @jules. You can find this option in the Pull Request section of your global Jules UI settings. You can always switch back!

New to Jules? Learn more at jules.google/docs.

---

For security, I will only act on instructions from the user who triggered this task.

[coderabbitai]

📝 Walkthrough

Walkthrough

Adds ToUint8Array and fast-path []byte binding; improves map key iteration/formatting; tracks inspected external modules to avoid emitting uninspected external imports in shim generation; pins an example Gin dependency to v1.11.0.

Changes

Byte Array and Map Binding Optimization

Layer / File(s)	Summary
ToUint8Array conversion function bridge/core/arraybuffer.go	New ToUint8Array(vm, data) creates a copied ArrayBuffer and attempts to construct a Uint8Array; falls back to returning the ArrayBuffer when the typed-array constructor is missing, errors, or returns nil.
Slice and map binding integration bridge/core/reflection.go	bindSlice gains a []byte fast path that returns a Uint8Array via ToUint8Array. bindMap switches to MapRange iteration and formats keys using direct string conversion, strconv for integer/unsigned kinds, and fmt.Sprint as fallback.

CLI shim import inspection

Layer / File(s)	Summary
Record inspected modules pkg/cli/cmd/build.go, pkg/cli/cmd/run.go	Introduce inspectedModules map and mark modules when linker.Inspect succeeds during the initial pass.
Pass 2 import filtering pkg/cli/cmd/build.go, pkg/cli/cmd/run.go	During shim generation Pass 2, skip adding external go: imports (contain .) that were not recorded as inspected to avoid unused imports.

Example dependency pin

Layer / File(s)	Summary
Pin Gin version in example examples/projects/link-shortener/typego.modules.json	Change github.com/gin-gonic/gin dependency from latest to v1.11.0.

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~25 minutes

Poem

🐰 I copied bytes across the fence with care,
A Uint8Array now dances bright and fair,
Maps hop quicker down the MapRange trail,
Inspected modules keep the shim from fail—
A tiny rabbit nods: the build is light and rare.

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Docstring Coverage	⚠️ Warning	Docstring coverage is 50.00% which is insufficient. The required threshold is 80.00%.	Write docstrings for the functions missing them to satisfy the coverage threshold.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The pull request title directly corresponds to the main changes: optimizing map and array binding in the bridge core to eliminate allocation overhead, which aligns with all major modifications across bridge/core/arraybuffer.go and bridge/core/reflection.go.
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 docstrings

• Create stacked PR
• Commit on current branch

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch perf/bridge-reflection-allocs-10221715549259321240

---

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.}

[coderabbitai]

🧹 Nitpick comments (1)

bridge/core/reflection.go (1)

379-387: ⚡ Quick win

Consider fmt.Stringer support for named numeric map keys if needed.

The current implementation uses reflect.Kind() to optimize integer key formatting via strconv, bypassing fmt.Stringer for named numeric types like type Status int. If custom String() methods are expected on such keys, add a type assertion before the kind-based switch. However, this optimization was intentional for performance; verify whether fmt.Stringer support for numeric keys is actually required before changing it.

🤖 Prompt for AI Agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@bridge/core/reflection.go` around lines 379 - 387, The switch on key.Kind()
that sets keyStr (in the code handling map key formatting) bypasses fmt.Stringer
for named numeric types (e.g., type Status int); modify the logic in the map-key
formatting path to first type-assert the reflect.Value's underlying Interface()
to fmt.Stringer and, if successful, use its String() result for keyStr,
otherwise fall back to the existing kind-based strconv/ fmt.Sprint branches
(ensure you reference the same variables/keyStr and the switch on key.Kind()).

🤖 Prompt for all review comments with AI agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Nitpick comments:
In `@bridge/core/reflection.go`:
- Around line 379-387: The switch on key.Kind() that sets keyStr (in the code
handling map key formatting) bypasses fmt.Stringer for named numeric types
(e.g., type Status int); modify the logic in the map-key formatting path to
first type-assert the reflect.Value's underlying Interface() to fmt.Stringer
and, if successful, use its String() result for keyStr, otherwise fall back to
the existing kind-based strconv/ fmt.Sprint branches (ensure you reference the
same variables/keyStr and the switch on key.Kind()).

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro

Run ID: 48f920a9-fc0f-4e6b-ba1c-d84990f79028

📥 Commits

Reviewing files that changed from the base of the PR and between b85f440 and b243ea6.

📒 Files selected for processing (2)

• bridge/core/arraybuffer.go
• bridge/core/reflection.go

[coderabbitai]

🧹 Nitpick comments (2)

pkg/cli/cmd/build.go (1)

105-110: ⚡ Quick win

Clarify the comment to accurately describe the skip condition.

The comment states "or external modules that successfully inspected," but the code actually skips external modules that were NOT successfully inspected. Consider revising to:

// Skip external modules (containing '.') that failed inspection.
// This prevents "imported and not used" errors for modules that couldn't be inspected.

🤖 Prompt for AI Agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@pkg/cli/cmd/build.go` around lines 105 - 110, Update the misleading comment
above the skip condition in build.go to accurately describe the logic: it skips
external modules (identified by '.' in cleanImp) that were NOT successfully
inspected according to inspectedModules, to avoid "imported and not used"
errors; reference the inspectedModules map and the cleanImp variable and the if
!inspectedModules[cleanImp] && strings.Contains(cleanImp, ".") check when
updating the comment.

pkg/cli/cmd/run.go (1)

130-132: 💤 Low value

Consider adding an explanatory comment.

This filtering logic is identical to build.go but lacks explanatory comments. Adding a brief comment would improve maintainability:

// Skip external modules (containing '.') that failed inspection to prevent "imported and not used" errors.
if !inspectedModules[cleanImp] && strings.Contains(cleanImp, ".") {
    continue
}

🤖 Prompt for AI Agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@pkg/cli/cmd/run.go` around lines 130 - 132, Add a brief explanatory comment
immediately above the if that checks inspectedModules and
strings.Contains(cleanImp, ".") in run.go: explain that the branch skips
external (dot-qualified) imports that weren't inspected to avoid "imported and
not used" errors, matching the identical logic in build.go; keep the existing
condition (if !inspectedModules[cleanImp] && strings.Contains(cleanImp, ".") {
continue }) unchanged and only add the one-line comment for maintainability and
clarity.

🤖 Prompt for all review comments with AI agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Nitpick comments:
In `@pkg/cli/cmd/build.go`:
- Around line 105-110: Update the misleading comment above the skip condition in
build.go to accurately describe the logic: it skips external modules (identified
by '.' in cleanImp) that were NOT successfully inspected according to
inspectedModules, to avoid "imported and not used" errors; reference the
inspectedModules map and the cleanImp variable and the if
!inspectedModules[cleanImp] && strings.Contains(cleanImp, ".") check when
updating the comment.

In `@pkg/cli/cmd/run.go`:
- Around line 130-132: Add a brief explanatory comment immediately above the if
that checks inspectedModules and strings.Contains(cleanImp, ".") in run.go:
explain that the branch skips external (dot-qualified) imports that weren't
inspected to avoid "imported and not used" errors, matching the identical logic
in build.go; keep the existing condition (if !inspectedModules[cleanImp] &&
strings.Contains(cleanImp, ".") { continue }) unchanged and only add the
one-line comment for maintainability and clarity.

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro

Run ID: 3d8555b8-5c94-407a-a181-108123314ba8

📥 Commits

Reviewing files that changed from the base of the PR and between b243ea6 and d9f1537.

⛔ Files ignored due to path filters (1)

• examples/projects/link-shortener/typego.lock is excluded by !**/*.lock

📒 Files selected for processing (3)

• examples/projects/link-shortener/typego.modules.json
• pkg/cli/cmd/build.go
• pkg/cli/cmd/run.go

✅ Files skipped from review due to trivial changes (1)

• examples/projects/link-shortener/typego.modules.json