Files
dc605b911e feat(mcp): expand CRUD server to near-complete CLI parity (#1440)
* feat(mcp): expand CRUD MCP server to near-complete CLI parity

Closes the CLI-vs-MCP tool coverage gap identified by auditing every
`goclaw` CLI command against the existing goclaw_* MCP tool set. Adds
skill grant/revoke, agent skill pin/unpin, and full CRUD/inspection
surfaces for memory, knowledge graph (including dedup/merge/prune),
tenants, providers, LLM traces, channel contacts, pending messages,
audit activity, system config, tenant storage (list/size/delete/move),
scoped agent config export/import, secure-CLI binary registry, and a
DB-backed health check.

Deliberately out of scope, documented inline where relevant:
- `goclaw credentials`: confirmed CLI-local (~/.goclaw/config.yaml +
  keychain), no server resource to wrap. goclaw_secure_cli_binaries_*
  covers the closest real, previously-uncovered server resource instead.
- Full tar-archive agent export/import (KG + workspace files): the CLI's
  version streams a multi-section archive with progress events, a shape
  that doesn't map to a single MCP tool call. Config + context files
  (the portable "brain") is covered.
- `kg extract` (LLM-driven text extraction): goclaw_kg_ingest accepts
  the same Entity/Relation shapes the extractor produces, so a caller
  can run extraction itself and hand off the result.

Wires 8 new store dependencies (Memory, KnowledgeGraph, Tracing,
Contacts, PendingMessages, Activity, SystemConfigs, SecureCLI) through
gateway.Server setters -> cmd/gateway.go -> CRUDDeps, following the
existing Providers/Tenants pattern. Storage and secure-CLI-binary
handlers duplicate internal/http's path-escape/symlink-hiding
validation logic (documented inline) since internal/http already
imports internal/mcp and the reverse would cycle.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

* fix(mcp): return sessionKey in goclaw_chat_send response for persistent conversations

The goclaw_chat_send tool creates a new session internally when sessionKey is
empty, but never returned the key to the caller. This prevented using
goclaw_chat_history to fetch previous messages in the session.

Add SessionKey field to ChatSendResult so callers can:
1. Start a new agent chat without providing sessionKey
2. Receive the sessionKey back in the response
3. Use that sessionKey for follow-up messages and history queries

Fixes the training loop pattern: start chat → get sessionKey → call
goclaw_chat_history with that key → iterate skill based on actual failures.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

* feat(mcp): add timing diagnostics to goclaw_chat_send for timeout troubleshooting

Log request arrival, processing duration, and errors with millisecond precision.
Helps identify whether timeouts occur at MCP client→goclaw, goclaw→ollama, or
during agent execution. Critical for production debugging.

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>

* fix(gateway): add http.Server timeouts for defensive timeout handling

Set explicit timeouts in http.Server:
- ReadTimeout: 1h (allow large uploads, long-running agent operations)
- WriteTimeout: 1h (allow streaming responses to slow clients)
- IdleTimeout: 30s (close idle keep-alive connections quickly)

Provides defense-in-depth when Nginx/Traefik timeouts are misconfigured.
Matches Nginx timeout (3600s) to prevent race conditions.

Timeout chain: traefik 3600s = nginx 3600s = goclaw 3600s

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>

---------

Co-authored-by: Bruno Clermont <bruno.clermont@gmail.com>
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-16 01:56:03 +07:00

84 lines
3.1 KiB
Go

package mcp
import (
"context"
"fmt"
"github.com/google/uuid"
mcpgo "github.com/mark3labs/mcp-go/mcp"
mcpserver "github.com/mark3labs/mcp-go/server"
"github.com/nextlevelbuilder/goclaw/internal/store"
)
// registerTracesCRUDTools registers the goclaw_traces_* MCP tools backed by
// store.TracingStore — closes a CLI-vs-MCP coverage gap (the `goclaw traces
// get/list` commands had no MCP equivalent; goclaw_run_timeline_get covers a
// different, run-oriented view). Read-only: trace/span data is written by
// the tracing pipeline itself (internal/tracing), not by operators.
func registerTracesCRUDTools(srv *mcpserver.MCPServer, tracing store.TracingStore) {
srv.AddTool(mcpgo.NewTool("goclaw_traces_list",
mcpgo.WithDescription("List LLM call traces, optionally filtered by agent/user/session/status."),
mcpgo.WithString("agent_id", mcpgo.Description("Filter by agent UUID.")),
mcpgo.WithString("user_id", mcpgo.Description("Filter by user ID.")),
mcpgo.WithString("session_key", mcpgo.Description("Filter by session key.")),
mcpgo.WithString("status", mcpgo.Description("Filter by status (e.g. \"success\", \"error\").")),
mcpgo.WithNumber("limit", mcpgo.Description("Maximum traces to return; defaults to 50.")),
mcpgo.WithNumber("offset", mcpgo.Description("Pagination offset.")),
mcpgo.WithReadOnlyHintAnnotation(true),
), handleTracesList(tracing))
srv.AddTool(mcpgo.NewTool("goclaw_traces_get",
mcpgo.WithDescription("Get a single trace and its spans by UUID."),
mcpgo.WithString("id", mcpgo.Required(), mcpgo.Description("Trace UUID.")),
mcpgo.WithReadOnlyHintAnnotation(true),
), handleTracesGet(tracing))
}
func handleTracesList(tracing store.TracingStore) mcpserver.ToolHandlerFunc {
return func(ctx context.Context, req mcpgo.CallToolRequest) (*mcpgo.CallToolResult, error) {
opts := store.TraceListOpts{
UserID: req.GetString("user_id", ""),
SessionKey: req.GetString("session_key", ""),
Status: req.GetString("status", ""),
Limit: intArg(req, "limit", 50),
Offset: intArg(req, "offset", 0),
}
if agentIDStr := req.GetString("agent_id", ""); agentIDStr != "" {
agentID, err := uuid.Parse(agentIDStr)
if err != nil {
return toolError("traces.list", fmt.Errorf("invalid agent_id: %w", err))
}
opts.AgentID = &agentID
}
traces, err := tracing.ListTraces(ctx, opts)
if err != nil {
return toolError("traces.list", err)
}
return jsonToolResult(traces)
}
}
func handleTracesGet(tracing store.TracingStore) mcpserver.ToolHandlerFunc {
return func(ctx context.Context, req mcpgo.CallToolRequest) (*mcpgo.CallToolResult, error) {
idStr, err := req.RequireString("id")
if err != nil {
return toolError("traces.get", err)
}
id, err := uuid.Parse(idStr)
if err != nil {
return toolError("traces.get", fmt.Errorf("invalid id: %w", err))
}
trace, err := tracing.GetTrace(ctx, id)
if err != nil {
return toolError("traces.get", err)
}
spans, err := tracing.GetTraceSpans(ctx, id)
if err != nil {
return toolError("traces.get", err)
}
return jsonToolResult(map[string]any{"trace": trace, "spans": spans})
}
}