Fix: the header information set by the client being lost. #686
Conversation
WalkthroughlistByPage now accepts an Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes Possibly related PRs
Suggested labels
Pre-merge checks and finishing touches❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✨ Finishing touches
📜 Recent review detailsConfiguration used: Repository UI Review profile: CHILL Plan: Pro 📒 Files selected for processing (1)
🚧 Files skipped from review as they are similar to previous changes (1)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
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. Comment |
button-chen
changed the title
button-chen
changed the title
|
Please check this PR. Thank you. @ezynda3 |
|
Hey @button-chen could you add a quick test that does the following?
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
Fix all issues with AI Agents 🤖
In @mcptest/mcptest_test.go:
- Around line 403-405: The call to client.ListTools currently ignores its
returned error; update the test to capture the result (err :=
client.ListTools(context.Background(), req)) and assert no error using
testify/require (e.g., require.NoError(t, err)) so the test fails when ListTools
returns an error; locate the call that constructs req (mcp.ListToolsRequest) and
the client.ListTools invocation to make this change.
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
mcptest/mcptest_test.go (1)
1-12: Add missing imports.The test references
http.Headerandclient.NewStreamableHttpClientbut the required packages are not imported, causing compilation failures.🔎 Proposed fix to add missing imports
import ( "context" "fmt" + "net/http" "strings" "testing" + "github.com/mark3labs/mcp-go/client" "github.com/mark3labs/mcp-go/mcp" "github.com/mark3labs/mcp-go/mcptest" "github.com/mark3labs/mcp-go/server" )
📜 Review details
Configuration used: Repository UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
mcptest/mcptest_test.go
🧰 Additional context used
📓 Path-based instructions (2)
**/*.go
📄 CodeRabbit inference engine (AGENTS.md)
**/*.go: Order imports: standard library first, then third-party, then local packages (goimports enforces this)
Follow Go naming conventions: exported identifiers in PascalCase; unexported in camelCase; acronyms uppercase (HTTP, JSON, MCP)
Error handling: return sentinel errors, wrap with fmt.Errorf("context: %w", err), and check with errors.Is/As
Prefer explicit types and strongly-typed structs; avoid using any except where protocol flexibility is required (e.g., Arguments any)
All exported types and functions must have GoDoc comments starting with the identifier name; avoid inline comments unless necessary
Functions that are handlers or long-running must accept context.Context as the first parameter
Ensure thread safety for shared state using sync.Mutex and document thread-safety requirements in comments
For JSON: use json struct tags with omitempty for optional fields; use json.RawMessage for flexible/deferred parsing
Files:
mcptest/mcptest_test.go
**/*_test.go
📄 CodeRabbit inference engine (AGENTS.md)
**/*_test.go: Testing: use testify/assert and testify/require
Write table-driven tests using a tests := []struct{ name, ... } pattern
Go test files must end with _test.go
Files:
mcptest/mcptest_test.go
🧠 Learnings (2)
📚 Learning: 2025-04-21T21:26:32.945Z
Learnt from: octo
Repo: mark3labs/mcp-go PR: 149
File: mcptest/mcptest.go:0-0
Timestamp: 2025-04-21T21:26:32.945Z
Learning: In the mcptest package, prefer returning errors from helper functions rather than calling t.Fatalf() directly, giving callers flexibility in how to handle errors.
Applied to files:
mcptest/mcptest_test.go
📚 Learning: 2025-06-23T11:10:42.948Z
Learnt from: floatingIce91
Repo: mark3labs/mcp-go PR: 401
File: server/server.go:1082-1092
Timestamp: 2025-06-23T11:10:42.948Z
Learning: In Go MCP server, ServerTool.Tool field is only used for tool listing and indexing, not for tool execution or middleware. During handleToolCall, only the Handler field is used, so dynamic tools don't need the Tool field populated.
Applied to files:
mcptest/mcptest_test.go
🧬 Code graph analysis (1)
mcptest/mcptest_test.go (6)
server/hooks.go (1)
Hooks(106-141)mcp/tools.go (2)
ListToolsRequest(18-21)ListToolsResult(25-28)server/server.go (3)
NewMCPServer(379-408)WithToolCapabilities(329-336)WithHooks(312-316)server/streamable_http.go (1)
NewTestStreamableHTTPServer(1409-1413)mcp/types.go (4)
InitializeRequest(467-471)Params(211-211)InitializeParams(473-479)Implementation(580-586)client/http.go (1)
NewStreamableHttpClient(11-22)
🪛 GitHub Actions: golangci-lint
mcptest/mcptest_test.go
[error] 386-386: undefined: client
🪛 GitHub Check: lint
mcptest/mcptest_test.go
[failure] 403-403:
missing type in composite literal (typecheck)
[failure] 403-403:
undefined: http
[failure] 386-386:
undefined: client
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: test
🔇 Additional comments (1)
mcptest/mcptest_test.go (1)
356-402: Test structure looks good.The test correctly sets up hooks, creates an MCP server with tool capabilities, initializes a streamable HTTP client, and prepares to validate header propagation through the ListTools flow.
mcptest/mcptest_test.go
Outdated
| req := mcp.ListToolsRequest{Header: http.Header{"X-Test-Header": {"test-header-value"}}} | ||
| client.ListTools(context.Background(), req) | ||
| } |
There was a problem hiding this comment.
Check the error returned by ListTools.
The call to client.ListTools ignores the returned error, which could cause the test to pass silently if the request fails before the hook can validate the header.
🔎 Proposed fix to add error handling
Per coding guidelines, consider using testify/require:
req := mcp.ListToolsRequest{Header: http.Header{"X-Test-Header": {"test-header-value"}}}
- client.ListTools(context.Background(), req)
+ _, err = client.ListTools(ctx, req)
+ if err != nil {
+ t.Fatalf("Failed to list tools: %v", err)
+ }
}Or using testify/require as specified in the coding guidelines:
+ "github.com/stretchr/testify/require"
+
req := mcp.ListToolsRequest{Header: http.Header{"X-Test-Header": {"test-header-value"}}}
- client.ListTools(context.Background(), req)
+ _, err = client.ListTools(ctx, req)
+ require.NoError(t, err, "Failed to list tools")
}As per coding guidelines, tests should use testify/require for error assertions.
Committable suggestion skipped: line range outside the PR's diff.
🧰 Tools
🪛 GitHub Check: lint
[failure] 403-403:
missing type in composite literal (typecheck)
[failure] 403-403:
undefined: http
🤖 Prompt for AI Agents
In @mcptest/mcptest_test.go around lines 403-405, The call to client.ListTools
currently ignores its returned error; update the test to capture the result (err
:= client.ListTools(context.Background(), req)) and assert no error using
testify/require (e.g., require.NoError(t, err)) so the test fails when ListTools
returns an error; locate the call that constructs req (mcp.ListToolsRequest) and
the client.ListTools invocation to make this change.
There was a problem hiding this comment.
Seems like the humans are having a chat. I'll hop back into my burrow for now. If you need me again, just tag @coderabbitai in a new comment, and I'll come hopping out!
There was a problem hiding this comment.
Actionable comments posted: 0
♻️ Duplicate comments (1)
mcptest/mcptest_test.go (1)
406-406: Check the error returned byListTools.The call to
client.ListToolsignores the returned error, which could cause the test to pass silently if the request fails before the hook can validate the header. This was also flagged by the linter and pipeline.🔎 Proposed fix using testify/require
Per coding guidelines, use
testify/requirefor error assertions:+import ( + "github.com/stretchr/testify/require" +) + req := mcp.ListToolsRequest{Header: http.Header{"X-Test-Header": {"test-header-value"}}} - client.ListTools(context.Background(), req) + _, err = client.ListTools(ctx, req) + require.NoError(t, err, "Failed to list tools") }As per coding guidelines, tests should use
testify/requirefor error assertions.
🧹 Nitpick comments (2)
mcptest/mcptest_test.go (2)
388-392: Remove unnecessaryreturnstatements aftert.Fatalf.The
t.Fatalffunction already terminates the test, making the subsequentreturnstatements on lines 391 and 396 redundant.🔎 Proposed fix
client, err := client.NewStreamableHttpClient(testServer.URL) if err != nil { t.Fatalf("Create client failed %v", err) - return } ctx := context.Background() if err := client.Start(ctx); err != nil { t.Fatalf("Failed to start client: %v", err) - return }Also applies to: 393-397
358-407: Consider usingtestify/requirethroughout the test.While the test correctly validates header propagation, the coding guidelines specify using
testify/requirefor error assertions. The test currently usest.Fatalfdirectly, which works but doesn't align with project standards.Example conversion
+import ( + "github.com/stretchr/testify/require" +) + func TestListToolsWithHeader(t *testing.T) { // ... hook setup ... client, err := client.NewStreamableHttpClient(testServer.URL) - if err != nil { - t.Fatalf("Create client failed %v", err) - } + require.NoError(t, err, "Create client failed") + ctx := context.Background() - if err := client.Start(ctx); err != nil { - t.Fatalf("Failed to start client: %v", err) - } + err = client.Start(ctx) + require.NoError(t, err, "Failed to start client") _, err = client.Initialize(ctx, initRequest) - if err != nil { - t.Fatalf("Failed to initialize: %v\n", err) - } + require.NoError(t, err, "Failed to initialize")As per coding guidelines, this improves consistency across the test suite.
📜 Review details
Configuration used: Repository UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
mcptest/mcptest_test.go
🧰 Additional context used
📓 Path-based instructions (2)
**/*.go
📄 CodeRabbit inference engine (AGENTS.md)
**/*.go: Order imports: standard library first, then third-party, then local packages (goimports enforces this)
Follow Go naming conventions: exported identifiers in PascalCase; unexported in camelCase; acronyms uppercase (HTTP, JSON, MCP)
Error handling: return sentinel errors, wrap with fmt.Errorf("context: %w", err), and check with errors.Is/As
Prefer explicit types and strongly-typed structs; avoid using any except where protocol flexibility is required (e.g., Arguments any)
All exported types and functions must have GoDoc comments starting with the identifier name; avoid inline comments unless necessary
Functions that are handlers or long-running must accept context.Context as the first parameter
Ensure thread safety for shared state using sync.Mutex and document thread-safety requirements in comments
For JSON: use json struct tags with omitempty for optional fields; use json.RawMessage for flexible/deferred parsing
Files:
mcptest/mcptest_test.go
**/*_test.go
📄 CodeRabbit inference engine (AGENTS.md)
**/*_test.go: Testing: use testify/assert and testify/require
Write table-driven tests using a tests := []struct{ name, ... } pattern
Go test files must end with _test.go
Files:
mcptest/mcptest_test.go
🧠 Learnings (4)
📚 Learning: 2025-04-21T21:26:32.945Z
Learnt from: octo
Repo: mark3labs/mcp-go PR: 149
File: mcptest/mcptest.go:0-0
Timestamp: 2025-04-21T21:26:32.945Z
Learning: In the mcptest package, prefer returning errors from helper functions rather than calling t.Fatalf() directly, giving callers flexibility in how to handle errors.
Applied to files:
mcptest/mcptest_test.go
📚 Learning: 2025-10-13T09:35:20.180Z
Learnt from: CR
Repo: mark3labs/mcp-go PR: 0
File: AGENTS.md:0-0
Timestamp: 2025-10-13T09:35:20.180Z
Learning: Applies to **/*_test.go : Testing: use testify/assert and testify/require
Applied to files:
mcptest/mcptest_test.go
📚 Learning: 2025-06-23T11:10:42.948Z
Learnt from: floatingIce91
Repo: mark3labs/mcp-go PR: 401
File: server/server.go:1082-1092
Timestamp: 2025-06-23T11:10:42.948Z
Learning: In Go MCP server, ServerTool.Tool field is only used for tool listing and indexing, not for tool execution or middleware. During handleToolCall, only the Handler field is used, so dynamic tools don't need the Tool field populated.
Applied to files:
mcptest/mcptest_test.go
📚 Learning: 2025-06-30T07:13:17.052Z
Learnt from: ezynda3
Repo: mark3labs/mcp-go PR: 461
File: server/sampling.go:22-26
Timestamp: 2025-06-30T07:13:17.052Z
Learning: In the mark3labs/mcp-go project, the MCPServer.capabilities field is a struct value (serverCapabilities), not a pointer, so it cannot be nil and doesn't require nil checking. Only pointer fields within the capabilities struct should be checked for nil.
Applied to files:
mcptest/mcptest_test.go
🧬 Code graph analysis (1)
mcptest/mcptest_test.go (6)
server/hooks.go (1)
Hooks(106-141)mcp/tools.go (2)
ListToolsRequest(18-21)ListToolsResult(25-28)server/server.go (2)
WithToolCapabilities(329-336)WithHooks(312-316)server/streamable_http.go (1)
NewTestStreamableHTTPServer(1409-1413)mcp/types.go (4)
InitializeRequest(467-471)Params(211-211)InitializeParams(473-479)Implementation(580-586)client/http.go (1)
NewStreamableHttpClient(11-22)
🪛 GitHub Actions: golangci-lint
mcptest/mcptest_test.go
[error] 406-406: Error return value of client.ListTools is not checked (errcheck)
🪛 GitHub Check: lint
mcptest/mcptest_test.go
[failure] 406-406:
Error return value of client.ListTools is not checked (errcheck)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: test
🔇 Additional comments (1)
mcptest/mcptest_test.go (1)
6-6: LGTM! Imports are appropriate.The added imports for
net/httpand the client package are necessary for the new header propagation test.Also applies to: 10-10
There was a problem hiding this comment.
Actionable comments posted: 1
Fix all issues with AI Agents 🤖
In @mcptest/mcptest_test.go:
- Around line 388-412: Add the testify/require import
("github.com/stretchr/testify/require") and replace all t.Fatalf error
assertions in this test with require helpers: use require.NoError(t, err, "...")
for client.NewStreamableHttpClient, client.Start, client.Initialize and
client.ListTools error checks, and replace the header comparison t.Fatalf with
require.Equal(t, expectedHeaderValue, gotHeaderValue). Remove any trailing
returns after the former t.Fatalf calls since require will fail the test for
you.
🧹 Nitpick comments (2)
mcptest/mcptest_test.go (2)
406-406: Use the existingctxvariable for consistency.Line 406 creates a new context with
context.Background(), butctxwas already defined on line 393 and used for previous operations. Using the same context throughout the test improves consistency.🔎 Proposed fix
req := mcp.ListToolsRequest{Header: http.Header{"X-Test-Header": {expectedHeaderValue}}} - _, err = client.ListTools(context.Background(), req) + _, err = client.ListTools(ctx, req) if err != nil { t.Fatalf("Failed to ListTools: %v\n", err) }
391-391: Remove unnecessaryreturnstatements aftert.Fatalf.The
t.Fatalffunction already terminates test execution, making the subsequentreturnstatements unreachable and redundant.🔎 Proposed fix
client, err := client.NewStreamableHttpClient(testServer.URL) if err != nil { t.Fatalf("Create client failed %v", err) - return } ctx := context.Background() if err := client.Start(ctx); err != nil { t.Fatalf("Failed to start client: %v", err) - return }Also applies to: 396-396
📜 Review details
Configuration used: Repository UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
mcptest/mcptest_test.go
🧰 Additional context used
📓 Path-based instructions (2)
**/*.go
📄 CodeRabbit inference engine (AGENTS.md)
**/*.go: Order imports: standard library first, then third-party, then local packages (goimports enforces this)
Follow Go naming conventions: exported identifiers in PascalCase; unexported in camelCase; acronyms uppercase (HTTP, JSON, MCP)
Error handling: return sentinel errors, wrap with fmt.Errorf("context: %w", err), and check with errors.Is/As
Prefer explicit types and strongly-typed structs; avoid using any except where protocol flexibility is required (e.g., Arguments any)
All exported types and functions must have GoDoc comments starting with the identifier name; avoid inline comments unless necessary
Functions that are handlers or long-running must accept context.Context as the first parameter
Ensure thread safety for shared state using sync.Mutex and document thread-safety requirements in comments
For JSON: use json struct tags with omitempty for optional fields; use json.RawMessage for flexible/deferred parsing
Files:
mcptest/mcptest_test.go
**/*_test.go
📄 CodeRabbit inference engine (AGENTS.md)
**/*_test.go: Testing: use testify/assert and testify/require
Write table-driven tests using a tests := []struct{ name, ... } pattern
Go test files must end with _test.go
Files:
mcptest/mcptest_test.go
🧠 Learnings (4)
📚 Learning: 2025-04-21T21:26:32.945Z
Learnt from: octo
Repo: mark3labs/mcp-go PR: 149
File: mcptest/mcptest.go:0-0
Timestamp: 2025-04-21T21:26:32.945Z
Learning: In the mcptest package, prefer returning errors from helper functions rather than calling t.Fatalf() directly, giving callers flexibility in how to handle errors.
Applied to files:
mcptest/mcptest_test.go
📚 Learning: 2025-10-13T09:35:20.180Z
Learnt from: CR
Repo: mark3labs/mcp-go PR: 0
File: AGENTS.md:0-0
Timestamp: 2025-10-13T09:35:20.180Z
Learning: Applies to **/*_test.go : Testing: use testify/assert and testify/require
Applied to files:
mcptest/mcptest_test.go
📚 Learning: 2025-06-23T11:10:42.948Z
Learnt from: floatingIce91
Repo: mark3labs/mcp-go PR: 401
File: server/server.go:1082-1092
Timestamp: 2025-06-23T11:10:42.948Z
Learning: In Go MCP server, ServerTool.Tool field is only used for tool listing and indexing, not for tool execution or middleware. During handleToolCall, only the Handler field is used, so dynamic tools don't need the Tool field populated.
Applied to files:
mcptest/mcptest_test.go
📚 Learning: 2025-06-30T07:13:17.052Z
Learnt from: ezynda3
Repo: mark3labs/mcp-go PR: 461
File: server/sampling.go:22-26
Timestamp: 2025-06-30T07:13:17.052Z
Learning: In the mark3labs/mcp-go project, the MCPServer.capabilities field is a struct value (serverCapabilities), not a pointer, so it cannot be nil and doesn't require nil checking. Only pointer fields within the capabilities struct should be checked for nil.
Applied to files:
mcptest/mcptest_test.go
🧬 Code graph analysis (1)
mcptest/mcptest_test.go (4)
mcp/tools.go (2)
ListToolsRequest(18-21)ListToolsResult(25-28)server/streamable_http.go (1)
NewTestStreamableHTTPServer(1409-1413)mcp/types.go (3)
InitializeRequest(467-471)Params(211-211)InitializeParams(473-479)client/http.go (1)
NewStreamableHttpClient(11-22)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: test
🔇 Additional comments (2)
mcptest/mcptest_test.go (2)
6-6: LGTM! Necessary imports for header testing.The
net/httpandclientpackage imports are correctly added to support HTTP header handling and client initialization in the new test.Also applies to: 10-10
358-365: Well-structured header verification setup.The test correctly uses hooks to capture the header value server-side, enabling verification that headers are propagated through the ListTools request path.
| client, err := client.NewStreamableHttpClient(testServer.URL) | ||
| if err != nil { | ||
| t.Fatalf("Create client failed %v", err) | ||
| return | ||
| } | ||
| ctx := context.Background() | ||
| if err := client.Start(ctx); err != nil { | ||
| t.Fatalf("Failed to start client: %v", err) | ||
| return | ||
| } | ||
|
|
||
| // Initialize | ||
| _, err = client.Initialize(ctx, initRequest) | ||
| if err != nil { | ||
| t.Fatalf("Failed to initialize: %v\n", err) | ||
| } | ||
|
|
||
| req := mcp.ListToolsRequest{Header: http.Header{"X-Test-Header": {expectedHeaderValue}}} | ||
| _, err = client.ListTools(context.Background(), req) | ||
| if err != nil { | ||
| t.Fatalf("Failed to ListTools: %v\n", err) | ||
| } | ||
| if expectedHeaderValue != gotHeaderValue { | ||
| t.Fatalf("Expected value is %s, got %s", expectedHeaderValue, gotHeaderValue) | ||
| } |
There was a problem hiding this comment.
🛠️ Refactor suggestion | 🟠 Major
Replace t.Fatalf with testify/require per coding guidelines.
The test uses t.Fatalf for error assertions, but the coding guidelines explicitly require using testify/require for test files. Additionally, the past review comment and retrieved learnings confirm this requirement.
🔎 Proposed refactor to use testify/require
Add the import:
import (
"context"
"fmt"
"net/http"
"strings"
"testing"
"github.com/mark3labs/mcp-go/client"
"github.com/mark3labs/mcp-go/mcp"
"github.com/mark3labs/mcp-go/mcptest"
"github.com/mark3labs/mcp-go/server"
+ "github.com/stretchr/testify/require"
)Then update the error handling:
client, err := client.NewStreamableHttpClient(testServer.URL)
- if err != nil {
- t.Fatalf("Create client failed %v", err)
- return
- }
+ require.NoError(t, err, "Create client failed")
+
ctx := context.Background()
- if err := client.Start(ctx); err != nil {
- t.Fatalf("Failed to start client: %v", err)
- return
- }
+ err = client.Start(ctx)
+ require.NoError(t, err, "Failed to start client")
// Initialize
_, err = client.Initialize(ctx, initRequest)
- if err != nil {
- t.Fatalf("Failed to initialize: %v\n", err)
- }
+ require.NoError(t, err, "Failed to initialize")
req := mcp.ListToolsRequest{Header: http.Header{"X-Test-Header": {expectedHeaderValue}}}
_, err = client.ListTools(context.Background(), req)
- if err != nil {
- t.Fatalf("Failed to ListTools: %v\n", err)
- }
- if expectedHeaderValue != gotHeaderValue {
- t.Fatalf("Expected value is %s, got %s", expectedHeaderValue, gotHeaderValue)
- }
+ require.NoError(t, err, "Failed to ListTools")
+ require.Equal(t, expectedHeaderValue, gotHeaderValue, "Header value mismatch")
}As per coding guidelines, test files should use testify/require.
🤖 Prompt for AI Agents
In @mcptest/mcptest_test.go around lines 388-412, Add the testify/require import
("github.com/stretchr/testify/require") and replace all t.Fatalf error
assertions in this test with require helpers: use require.NoError(t, err, "...")
for client.NewStreamableHttpClient, client.Start, client.Initialize and
client.ListTools error checks, and replace the header comparison t.Fatalf with
require.Equal(t, expectedHeaderValue, gotHeaderValue). Remove any trailing
returns after the former t.Fatalf calls since require will fail the test for
you.
There was a problem hiding this comment.
Seems like the humans are having a chat. I'll hop back into my burrow for now. If you need me again, just tag @coderabbitai in a new comment, and I'll come hopping out!
Bro, I've already added the unit tests @ezynda3 |
The test doesn't test |
|
Tip For best results, initiate chat on the files or code changes. 🧩 Analysis chain🏁 Script executed: Length of output: 11089 @ezynda3, you're correct. The test The test should call one of these methods instead:
These To properly test the fix, the test needs to:
|
Yes, I just made the correction. |
|
Tip For best results, initiate chat on the files or code changes. 🧩 Analysis chain🏁 Script executed: Length of output: 11093 @button-chen, confirmed! ✅ The test now correctly calls The test now satisfies all three requirements:
The fix looks good and is now properly tested. Thank you for making the correction! (| |) |
2 participants
Description
For example, the MCP client has the following code
The set X-Tenant-ID for the header was not transmitted to the server.
The problem lies in the code shown in the screenshot:
Type of Change
Checklist
MCP Spec Compliance
Additional Information
Summary by CodeRabbit
Bug Fixes
Tests
✏️ Tip: You can customize this high-level summary in your review settings.