GitHub Copilot untuk Golang 2026: Setup, Chat, Workspace, PR Review

 12021: GitHub Copilot v1
 2  → Inline completion, satu baris atau blok kecil
 3  → "Type to trigger, Tab to accept"
 4
 52023: Copilot Chat
 6  → Chat interface di IDE
 7  → /commands: /explain, /fix, /tests, /doc
 8  → @workspace untuk context seluruh repo
 9
102024: Copilot Workspace (github.com)
11  → Issue → Plan → PR, semua di browser
12  → Copilot understands full repository
13
142025-2026: Copilot Agent Mode
15  → Multi-step autonomous tasks
16  → Integration dengan GitHub Actions
17  → PR review yang sophisticated
18  → Copilot Extensions (custom tools)

 1# Install VS Code extensions
 2code --install-extension GitHub.copilot
 3code --install-extension GitHub.copilot-chat
 4
 5# Login
 6# Cmd/Ctrl+Shift+P → "GitHub Copilot: Sign in with GitHub"
 7
 8# Verify Go extension
 9code --install-extension golang.go
10
11# Verify Copilot active
12# Bottom status bar: Copilot icon (active = circle, inactive = strikethrough)
13
14# Test inline completion
15# Buka file Go, ketik function signature, tunggu suggestions
16func CancelOrder(ctx context.Context, orderID uuid.UUID) error {
17    // → Copilot akan suggest implementation

 1# .github/copilot-instructions.md
 2# Santekno Shop — GitHub Copilot Instructions
 3
 4## Project Overview
 5Go 1.22 e-commerce service. Clean Architecture.
 6High-traffic, distributed system. Production-critical code.
 7
 8## Architecture — STRICT RULES
 9Layer order: handler → usecase → repository → domain
10- handler: ONLY calls usecase interfaces
11- usecase: ONLY uses domain + repository interfaces
12- repository: ONLY returns domain types
13- domain: ZERO external imports
14
15## CRITICAL Go Conventions
16
17### Error Handling
18Repository not-found: ALWAYS return (nil, nil) — never return an error
19All error wraps: fmt.Errorf("package.FunctionName: %w", err)
20HTTP errors: {"error": "UPPERCASE_ERROR_CODE"}
21
22### Types
23Monetary values: ALWAYS int64 cents (50000 = Rp 500.00)
24Primary keys: ALWAYS UUID (github.com/google/uuid)
25Never: float64, float32 for money
26
27### Context
28Always pass ctx as FIRST parameter
29Always propagate ctx to all downstream calls
30
31## Testing
32Framework: github.com/stretchr/testify/suite
33Mocking: go.uber.org/mock/gomock (NOT testify/mock)
34No real DB in unit tests — always mock repository
35Integration tests: //go:build integration
36
37## Exact Package Paths (critical — no alternatives)
38DB: github.com/jackc/pgx/v5
39Cache: github.com/redis/go-redis/v9
40HTTP: github.com/labstack/echo/v4
41Kafka: github.com/confluentinc/confluent-kafka-go/v2
42UUID: github.com/google/uuid
43Logging: github.com/rs/zerolog
44
45## Go Version: 1.22
46NO features from Go 1.23+: range-over-func, slices.Collect, iter.Seq
47
48## What NEVER to do
49- NEVER float64 for monetary values
50- NEVER return pgx.ErrNoRows from usecase
51- NEVER ignore error with _ (in non-test code)
52- NEVER import delivery from usecase
53- NEVER interface with > 5 methods without splitting
54```

 1// Scenario 1: Function signature → Copilot complete implementation
 2func (r *orderRepository) CancelWithStockRestore(
 3    ctx context.Context,
 4    orderID uuid.UUID,
 5) error {
 6    // → Copilot suggest: transaction-based implementation
 7    // Accept dengan Tab, atau Alt+] untuk next suggestion
 8
 9// Scenario 2: Struct → complete semua fields
10type CancelOrderInput struct {
11    // → Copilot suggest: OrderID uuid.UUID, UserID uuid.UUID
12    // Berdasarkan pattern dari struct lain di codebase
13
14// Scenario 3: Error handling boilerplate
15order, err := uc.repo.GetByIDAndUserID(ctx, input.OrderID, input.UserID)
16// → Copilot suggest:
17//   if err != nil {
18//       return fmt.Errorf("cancelOrder.Execute: %w", err)
19//   }
20//   if order == nil {
21//       return domain.ErrOrderNotFound
22//   }
23
24// Scenario 4: SQL query
25const queryGetOrder = `
26    SELECT id, user_id, status, total_amount, created_at
27    FROM orders
28    WHERE -- Copilot suggest: id = $1 AND deleted_at IS NULL
29
30// Scenario 5: Test case
31func (s *CancelOrderSuite) Test
32// → Copilot suggest multiple completions:
33//   TestCancelOrder_PendingOrder_Success
34//   TestCancelOrder_NotFound_ReturnsError
35//   TestCancelOrder_WindowExpired_ReturnsError

 1# /explain — understand existing code
 2# Select fungsi yang complex, lalu:
 3/explain
 4# "This function implements the repository pattern for order cancellation.
 5#  It uses a database transaction to atomically cancel the order and
 6#  restore stock levels..."
 7
 8# /tests — generate tests untuk selected code
 9# Select CancelOrderUseCase.Execute, lalu:
10/tests
11# Generate: testify/suite tests berdasarkan function signature dan behavior
12
13# /fix — fix error yang di-paste
14/fix
15# Error: cannot use order (variable of type *domain.Order) as type domain.Order
16# Fix: dereference atau update signature
17
18# /doc — generate godoc
19# Select fungsi, lalu:
20/doc
21# // Execute cancels an order if it meets the cancellation criteria.
22# // It verifies that the order belongs to the specified user,
23# // is in PENDING status, and was created within the cancellation window.
24
25# @workspace — context-aware questions
26@workspace What pattern does this project use for handling not-found from repository?
27# → Copilot scan codebase, find examples, answer dengan actual code dari project
28
29@workspace What's the testing pattern for usecase tests in this project?
30# → Copilot show actual test structure dari existing tests

 1Workflow:
 2
 31. Buat atau buka GitHub Issue:
 4   Title: "Cancel order tidak restore stock saat Kafka publish gagal"
 5   Body: "Ketika order di-cancel dan Kafka publish event gagal,
 6          stock sudah di-restore di DB tapi order tetap CANCELLED.
 7          Ini menyebabkan inconsistency..."
 8
 92. Click "Open in Copilot Workspace"
10   (tombol ada di kanan atas issue page)
11
123. Copilot Workspace analyze:
13   → Baca seluruh repository
14   → Understand issue context
15   → Generate implementation plan
16
174. Plan yang di-generate:
18   "File yang akan diubah:
19    1. internal/usecase/order/cancel_order.go
20       - Implementasi outbox pattern untuk Kafka
21    2. internal/repository/postgres/order_repository.go
22       - Tambahkan CreateOutboxEvent method
23    3. internal/kafka/publisher.go
24       - Buat publisher yang baca dari outbox table
25    New files:
26    4. internal/domain/outbox/entity.go
27    5. migrations/20260702_add_outbox_table.sql"
28
295. Review plan → approve → Copilot implement
30   → Buat PR dengan implementation
31
326. PR automatically linked ke issue

 1# Setup automatic PR review
 2# .github/workflows/copilot-review.yml
 3
 4name: Copilot Code Review
 5
 6on:
 7  pull_request:
 8    types: [opened, ready_for_review, synchronize]
 9    paths:
10      - '**.go'
11
12jobs:
13  copilot-review:
14    runs-on: ubuntu-latest
15    permissions:
16      pull-requests: write
17      contents: read
18
19    steps:
20      - uses: actions/checkout@v4
21        with:
22          fetch-depth: 0
23
24      - name: Copilot Code Review
25        uses: github/copilot-for-pull-requests@v1
26        with:
27          github-token: ${{ secrets.GITHUB_TOKEN }}
28          review-type: "code-review"
29          # Custom instructions untuk review
30          review-instructions: |
31            Review Go code untuk Santekno Shop e-commerce.
32
33            CRITICAL checks:
34            1. Error handling: fmt.Errorf("pkg.Method: %w", err) ALWAYS
35            2. Repository not-found: MUST return nil, nil (never error)
36            3. Monetary: int64 cents ONLY (never float64)
37            4. Architecture: no cross-layer imports
38            5. Context: always first parameter, always propagated
39            6. HTTP errors: {"error": "UPPERCASE_CODE"} format
40            7. No _ to ignore errors in non-test code
41
42            Format issues as:
43            CRITICAL: [issue] at [file:line] — [fix]
44            SUGGESTION: [improvement] at [file:line]

 1// Pattern 1: Copilot sangat bagus untuk generate SQL
 2const insertOrder = `
 3    INSERT INTO orders (id, user_id, status, total_amount, created_at)
 4    VALUES ($1, $2, $3, $4, NOW())
 5    RETURNING id, created_at
 6`
 7// Copilot auto-complete dengan correct $N placeholders
 8
 9// Pattern 2: Copilot generate mock setup
10func (s *CancelOrderSuite) TestCancelOrder_NotFound() {
11    s.mockRepo.EXPECT().
12        GetByIDAndUserID(gomock.Any(), gomock.Any(), gomock.Any()).
13        Return(nil, nil)  // ← Copilot tahu return (nil, nil) untuk not-found
14
15    err := s.uc.Execute(context.Background(), CancelOrderInput{
16        OrderID: uuid.New(),
17        UserID:  uuid.New(),
18    })
19
20    s.ErrorIs(err, domain.ErrOrderNotFound)
21}
22
23// Pattern 3: Copilot generate struct tags
24type OrderResponse struct {
25    ID          string    `json:"id" validate:"required,uuid"`  // ← Copilot suggest tags
26    Status      string    `json:"status" validate:"oneof=PENDING CONFIRMED"`
27    TotalAmount int64     `json:"total_amount_idr"`  // ← aware dengan naming convention
28    CreatedAt   time.Time `json:"created_at"`
29}

 1# Query 1: Pattern discovery
 2@workspace How does this project handle concurrent access to order cancellation?
 3# Copilot scan codebase, find SELECT FOR UPDATE atau mutex patterns, explain
 4
 5# Query 2: Convention check
 6@workspace What error types are defined in the domain package and when to use each?
 7# Copilot list all domain errors, show examples of usage
 8
 9# Query 3: Integration guidance
10@workspace I need to add a new Kafka consumer. What's the pattern used in this project?
11# Copilot show existing consumer code, explain the pattern
12
13# Query 4: Debugging assistance
14@workspace The TestCancelOrder_AtomicRollback test is failing. What are potential causes?
15# Copilot analyze test + implementation, suggest potential issues
16
17# Query 5: Architecture validation
18@workspace Is there any code that violates the clean architecture rules in this project?
19# Copilot scan for cross-layer imports, report violations
20
21# Query 6: Onboarding
22@workspace I'm new to this project. Give me an overview of how an order is created
23from HTTP request to database.
24# Copilot generate flow explanation untuk new developer

 1GitHub Copilot Enterprise — fitur yang relevan untuk Go teams:
 2
 31. Custom model fine-tuned pada codebase kamu:
 4   → Model yang "tahu" internal packages kamu
 5   → Error types, naming conventions, patterns yang internal
 6
 72. Copilot Knowledge Bases:
 8   → Index internal docs, architecture decision records
 9   → Copilot bisa answer: "Kenapa kita tidak pakai X?"
10
113. Copilot in the CLI:
12   gh copilot suggest "cara run integration test"
13   gh copilot explain "git rebase --onto origin/main HEAD~3"
14
154. Advanced PR review:
16   → More context: full repository, not just diff
17   → Custom review policies per team
18
195. Enterprise compliance:
20   → Audit logs untuk semua Copilot usage
21   → No code training (data tidak dipakai untuk training model)
22   → IP indemnification

 1// Copilot Extensions memungkinkan custom tools di Copilot Chat
 2
 3// Contoh: extension untuk check spec compliance
 4// @spec-check — check apakah PR memenuhi spec
 5
 6// Di Copilot Chat:
 7// @spec-check Does the cancel order implementation in this PR
 8// match the spec at .specify/features/cancel-order/spec.md?
 9
10// Extension custom (Go service yang implement Copilot Extension API):
11// - Baca spec dari repo
12// - Analyze PR diff
13// - Compare ACs vs implementation
14// - Return compliance report
15
16// Extension for Go tooling:
17// @go-check Run go vet and golangci-lint on the changed files
18// → Extension jalankan tools, return hasil ke chat

 1# Method 1: /tests command
 2# Select function, run /tests
 3/tests
 4# Output: test cases berdasarkan function signature
 5
 6# Method 2: Describe behavior
 7# Di Copilot Chat:
 8"Generate unit tests untuk CancelOrderUseCase.Execute.
 9Cover:
10- Happy path (PENDING dalam 30 menit)
11- Not found (return nil, nil dari repo)
12- Status bukan PENDING
13- Window expired (> 30 menit)
14- Concurrent cancel (optimistic lock scenario)
15
16Gunakan testify/suite + gomock pattern dari existing tests di project ini."
17
18# Method 3: From spec
19"Generate tests yang cover semua ACs dari spec ini:
20AC1: Cancel order PENDING dalam 30 menit → success
21AC2: Cancel order CONFIRMED → 409 ORDER_NOT_CANCELLABLE
22AC3: Cancel window expired → 409 CANCEL_WINDOW_EXPIRED
23
24Pattern yang harus digunakan: @file internal/usecase/order/create_order_test.go"

 1Morning: Review tasks + plan
 2  Copilot Chat: "@workspace Apa dependencies dari Cancel Order feature?"
 3
 4Coding (bulk):
 5  → Inline completions untuk error handling, SQL, struct tags
 6  → Sangat smooth, tidak perlu switch context
 7
 8Stuck point:
 9  Copilot Chat: "/explain fungsi ini"
10  Copilot Chat: "@workspace Bagaimana pattern untuk [specific thing]?"
11
12Implement feature:
13  Copilot Chat: "Implement method ini sesuai spec: @specs/order/cancel-order.md (AC1-AC10, EC1-EC4)
14  Ikuti pattern dari @file existing-feature.go"
15
16Before PR:
17  Copilot Chat: "Review perubahan saya untuk error/architecture violations"
18
19PR submitted:
20  → Copilot auto-review via GitHub Actions (07.7)
21  → Human reviewer hanya review architecture + business logic

 1Pilih GitHub Copilot jika:
 2
 3✅ Tim heavily invested di GitHub (Actions, Projects, dll.)
 4✅ Butuh PR review automation yang reliable
 5✅ Tim heterogeneous (senior + junior) — inline smooth + /explain
 6✅ Enterprise compliance adalah requirement (SOC2, audit logs)
 7✅ Budget: $10/dev (individual) atau $19 (business)
 8✅ Issue-driven development adalah workflow inti
 9
10❌ Jangan pilih Copilot jika:
11   → SDD workflow adalah prioritas (pakai Claude Code + Spec Kit)
12   → Butuh autonomous complex tasks (pakai Claude Code)
13   → Go idiom quality adalah standar tertinggi non-negotiable (Claude Code)

 1# .github/workflows/go-ci-with-copilot.yml
 2name: Go CI + Copilot
 3
 4on: [push, pull_request]
 5
 6jobs:
 7  # Stage 1: Standard Go checks (no AI)
 8  go-standard:
 9    runs-on: ubuntu-latest
10    steps:
11      - uses: actions/checkout@v4
12      - uses: actions/setup-go@v5
13        with:
14          go-version: '1.22'
15      - run: go build ./...
16      - run: go test -race ./...
17      - run: go vet ./...
18      - uses: golangci/golangci-lint-action@v6
19
20  # Stage 2: Copilot PR Review (AI-powered)
21  copilot-review:
22    runs-on: ubuntu-latest
23    if: github.event_name == 'pull_request'
24    permissions:
25      pull-requests: write
26      contents: read
27    steps:
28      - uses: actions/checkout@v4
29      - name: Copilot Code Review
30        uses: github/copilot-for-pull-requests@v1
31        with:
32          github-token: ${{ secrets.GITHUB_TOKEN }}
33          review-instructions: |
34            [custom instructions dari 07.7]

 1Copilot performance di Santekno Shop benchmark:
 2
 3Overall: 80.2/100
 4
 5By scenario:
 6  S1 (Implement dari spec): 82/100
 7  S2 (Write unit tests):     78/100
 8  S3 (Refactoring):          79/100
 9  S4 (Debug race condition): 82/100
10  S5 (OpenAPI gen):          80/100
11
12Where Copilot stands out vs others:
13  PR review quality:            ⭐⭐⭐⭐⭐ (best of all tools)
14  Inline suggestion smoothness: ⭐⭐⭐⭐⭐ (best of all tools)
15  GitHub integration:           ⭐⭐⭐⭐⭐ (obvious)
16
17Where Copilot lags:
18  Go idiom correctness:  ⭐⭐⭐ (vs Claude Code ⭐⭐⭐⭐⭐)
19  Complex reasoning:     ⭐⭐⭐ (vs Claude Code ⭐⭐⭐⭐⭐)
20  Context retention:     ⭐⭐⭐ (vs Claude Code ⭐⭐⭐⭐⭐)

 1# Setelah specify audit generate report:
 2# specify audit --feature cancel-order --output markdown > audit-report.md
 3
 4# Di Copilot Chat:
 5"Baca audit report ini dan implement fixes untuk semua CRITICAL issues:
 6@audit-report.md
 7
 8Prioritaskan:
 91. Missing AC implementations
102. Architecture violations
113. Missing test coverage"
12
13# Copilot akan implement fixes berdasarkan audit report
14# Kemudian: specify audit lagi untuk verify score naik

 1Features yang sudah available (2026):
 2✅ Copilot in GitHub Mobile
 3✅ Copilot Workspace (Issue → PR)
 4✅ Copilot Extensions API (build custom tools)
 5✅ Copilot in CLI (gh copilot suggest/explain)
 6✅ Fine-tuned custom model (Enterprise)
 7
 8Expected development:
 9🔜 Better agent mode (more autonomous tasks)
10🔜 Deeper IDE integration (tidak hanya VS Code)
11🔜 Copilot for GitHub Projects (planning assistance)
12🔜 Multi-model support (pilih model per task)
13🔜 Better Go-specific training data

 1Developer Journey dengan Copilot:
 2
 31. Planning
 4   GitHub Issues → Copilot Workspace ("Buat plan untuk ini")
 52. Development
 6   VS Code → Copilot inline + Chat
 73. Pre-PR
 8   Copilot Chat → "Review changes saya"
 94. PR submission
10   GitHub → Copilot auto-review (Actions)
115. Code review discussion
12   GitHub PR comments → Copilot suggestions
136. Merge & deployment
14   GitHub Actions → Copilot for CI issues
157. Post-deployment
16   GitHub Issues (bug reports) → Copilot Workspace
17
18Every step covered. No tool switching needed.

 1Data dari tim 5 developer Go:
 2
 3SEBELUM Copilot PR Review (3 bulan baseline):
 4  PR review time average: 47 menit per PR
 5    Architecture & logic review:  25 menit (53%)
 6    Error handling check:          8 menit (17%)
 7    Import & type correctness:     6 menit (13%)
 8    Test coverage check:           5 menit (11%)
 9    Formatting & style:            3 menit ( 6%)
10
11SESUDAH Copilot PR Review (3 bulan):
12  PR review time average: 31 menit per PR (34% reduction)
13    Architecture & logic review:  25 menit (80%) ← fokus di sini
14    Error handling check:          2 menit ( 6%) ← Copilot handled most
15    Import & type correctness:     1 menit ( 3%) ← Copilot handled most
16    Test coverage check:           2 menit ( 6%) ← Copilot flagged gaps
17    Formatting & style:            1 menit ( 3%) ← minimal

 1// Prompt: Generate generic repository interface untuk Santekno Shop
 2
 3// Copilot suggest:
 4type Repository[T any, ID any] interface {
 5    Create(ctx context.Context, entity T) error
 6    GetByID(ctx context.Context, id ID) (*T, error)
 7    Update(ctx context.Context, entity T) error
 8    Delete(ctx context.Context, id ID) error
 9}
10
11// Concrete implementation:
12type OrderRepository = Repository[domain.Order, uuid.UUID]
13type ProductRepository = Repository[domain.Product, uuid.UUID]
14
15// Verdict: Copilot handle basic generics dengan baik.
16// Untuk complex generic constraints (comparable, interface constraints),
17// masih perlu manual guidance. Claude Code lebih baik untuk complex generics.

1Dimensi             | copilot-instructions | CLAUDE.md
2────────────────────┼──────────────────────┼──────────────────
3Retention (session) | Moderate (7/10)      | High (9/10)
4Code block examples | Very effective       | Very effective
5NEVER list          | Effective            | Very effective
6Architecture rules  | Moderate             | High
7Layer separation    | Moderate             | High
8Custom types        | Effective            | Very effective
9Long session        | Degrades to 5/10     | Stays at 8/10

 1Setup phase:
 2□ Install VS Code extension (GitHub.copilot + GitHub.copilot-chat)
 3□ Setup .github/copilot-instructions.md dengan Go conventions
 4□ Enable Copilot in repository settings
 5□ Setup PR review automation (07.7)
 6□ Demo session untuk seluruh tim (45 menit)
 7
 8Day 1-7 (familiarization):
 9□ Gunakan inline completions untuk daily coding
10□ Eksplorasi /explain dan /tests commands
11□ Coba @workspace untuk project-specific questions
12
13Day 8-30 (optimization):
14□ Refine copilot-instructions.md berdasarkan output
15□ Setup PR review automation di semua relevant repos
16□ Combine dengan Claude Code untuk complex tasks
17
18Month 2:
19□ Track: PR review comment count (should decrease)
20□ Track: Time dari spec ke PR ready (should decrease)
21□ Evaluate: apakah worth upgrade ke Business tier?