refactor(workspace): extract layered resolver pipeline for workspace path computation

Replace inline workspace path computation in loop_context.go with composable
WorkspaceLayer pipeline (tenant → team → project → user/chat). Each layer is
a pure function that appends a path segment or is a no-op.

- New workspace_resolver.go: ResolveWorkspace, TenantLayer, TeamLayer,
  ProjectLayer (future), UserChatLayer, SanitizePathSegment
- 16 unit tests covering all layer combinations
- Migrate loop_context.go, loop_history.go, team_tasks_mutations.go
- Move sanitizePathSegment from agent to tools package (exported)
- Zero behavior change — identical paths for all scenarios

internal/agent/loop_utils.go

@@ -10,19 +10,6 @@ import (
 	"github.com/nextlevelbuilder/goclaw/internal/tools"
 )
 
-// sanitizePathSegment makes a userID safe for use as a directory name.
-// Replaces colons, spaces, and other unsafe chars with underscores.
-func sanitizePathSegment(s string) string {
-	var b strings.Builder
-	for _, r := range s {
-		if (r >= 'a' && r <= 'z') || (r >= 'A' && r <= 'Z') || (r >= '0' && r <= '9') || r == '-' || r == '_' {
-			b.WriteRune(r)
-		} else {
-			b.WriteByte('_')
-		}
-	}
-	return b.String()
-}
 
 // scanWebToolResult checks web_fetch/web_search tool results for prompt injection patterns.
 // If detected, prepends a warning (doesn't block — may be false positive).