mirror of
https://github.com/coder/coder.git
synced 2026-09-23 22:20:22 +08:00
Kyle Carberry
27ecd17991
Two MCP code paths both spawned the servers declared in a workspace's `.mcp.json`: the persistent engine in `agent/x/agentmcp` (which owns tool-call execution via `CallTool`) and an ephemeral one-shot runner in `agent/agentcontext` (`mcprunner.go`) that connected, listed tools, and immediately closed each server purely for discovery. Every declared server was launched twice, and the discovery path duplicated the engine's `.mcp.json` parse, transport-build, env-resolve, and connect logic. This makes `agent/x/agentmcp` the single persistent MCP engine. The `agentcontext` manager now reads that engine's per-server catalog in-process through an injected `MCPCatalog` option and surfaces each server as a `KindMCPServer` resource. The engine wires `SetOnReload` to the manager's `Trigger`, so a reload (startup connect or `.mcp.json` edit) re-resolves and re-pushes the pinned resources. Tool-call execution is unchanged: it still flows through the engine's `CallTool` over `POST /api/v0/mcp/call-tool`. The now-dead HTTP discovery surface is removed: the agent `GET /api/v0/mcp/tools` route with `agentmcp.API.handleListTools`, and `workspacesdk.AgentConn.ListMCPTools` with `ListMCPToolsResponse` (mock regenerated). The change nets roughly `-1370` lines, mostly the deleted duplicate runner and its tests. <details> <summary>Decision log</summary> The merge of #26585 made pinned `chat_context_resources` the sole source of workspace context, which surfaced the duplicate spawning. Two options were considered: - **Option A + dependency injection (chosen):** keep `agent/x/agentmcp` as the single persistent engine; `agentcontext` consumes its catalog in-process and stays the orchestrator/owner at the API boundary (it still pushes `KindMCPServer` resources). This is low-risk because `agentcontext` already exposed the `resolver.MCPResources` seam, so the change just rebinds it from the ephemeral runner to the shared engine. - **Option B (rejected):** reimplement persistent pooling, reconnect, singleflight, and race handling inside `agentcontext` and delete `agentmcp`. Too broad, and it discards the engine's tested lifecycle for no behavioral gain. `agentcontext`'s discovery was never what kept servers alive; its runner closed each server immediately after listing tools. The component holding persistent connections was always `agentmcp`, which is why execution already lived there. Consolidating onto it removes the duplicated stack rather than a whole package: both packages survive with distinct roles (`agentmcp` is the engine, `agentcontext` is the orchestrator/owner). </details> Coder Agents generated on behalf of @kylecarbs
56 lines
1.5 KiB
Go
56 lines
1.5 KiB
Go
package agentmcp
|
|
|
|
import (
|
|
"bytes"
|
|
"encoding/json"
|
|
"net/http"
|
|
"net/http/httptest"
|
|
"testing"
|
|
|
|
"github.com/stretchr/testify/require"
|
|
|
|
"cdr.dev/slog/v3/sloggers/slogtest"
|
|
"github.com/coder/coder/v2/agent/agentexec"
|
|
"github.com/coder/coder/v2/codersdk/workspacesdk"
|
|
"github.com/coder/coder/v2/testutil"
|
|
)
|
|
|
|
// TestHandleCallTool_ErrorMapping verifies the call-tool handler maps
|
|
// Manager errors to the right HTTP status codes. Tool discovery is no
|
|
// longer served over HTTP (the agentcontext manager reads the catalog
|
|
// in-process), so only the execution endpoint is exercised here.
|
|
func TestHandleCallTool_ErrorMapping(t *testing.T) {
|
|
t.Parallel()
|
|
|
|
ctx := testutil.Context(t, testutil.WaitShort)
|
|
logger := slogtest.Make(t, nil)
|
|
m := NewManager(ctx, logger, agentexec.DefaultExecer, nil)
|
|
t.Cleanup(func() { _ = m.Close() })
|
|
|
|
api := NewAPI(m)
|
|
|
|
cases := []struct {
|
|
name string
|
|
toolName string
|
|
wantCode int
|
|
}{
|
|
{name: "InvalidToolName", toolName: "noseparator", wantCode: http.StatusBadRequest},
|
|
{name: "UnknownServer", toolName: "ghost__echo", wantCode: http.StatusNotFound},
|
|
}
|
|
for _, tc := range cases {
|
|
t.Run(tc.name, func(t *testing.T) {
|
|
t.Parallel()
|
|
|
|
body, err := json.Marshal(workspacesdk.CallMCPToolRequest{ToolName: tc.toolName})
|
|
require.NoError(t, err)
|
|
req := httptest.NewRequest(http.MethodPost, "/call-tool", bytes.NewReader(body))
|
|
req.Header.Set("Content-Type", "application/json")
|
|
rec := httptest.NewRecorder()
|
|
|
|
api.Routes().ServeHTTP(rec, req)
|
|
|
|
require.Equal(t, tc.wantCode, rec.Code)
|
|
})
|
|
}
|
|
}
|