fix(hyperguild): remove redundant subcommand prefixes from error messages

dispatch() already prefixes errors with 'hyperguild <subcmd>: ', so
handlers re-prefixing with their own name produced stuttered output
like 'hyperguild brain: brain query: topic required'. Strip the
redundant prefixes from the seven affected errors.New / fmt.Errorf
calls in brain.go and mode.go.

Also fix the LITELLM_BASE_URL usage text — it's optional (empty
falls through to airplane tier), not required, matching the
README.

cmd/hyperguild/brain.go

@@ -11,7 +11,7 @@ import (
 
 func runBrain(ctx context.Context, args []string, stdin io.Reader, stdout, stderr io.Writer) error {
 	if len(args) == 0 {
-		return errors.New("brain: subcommand required (query|write)")
+		return errors.New("subcommand required (query|write)")
 	}
 	switch args[0] {
 	case "query":
@@ -19,7 +19,7 @@ func runBrain(ctx context.Context, args []string, stdin io.Reader, stdout, stder
 	case "write":
 		return runBrainWrite(ctx, args[1:], stdin, stdout, stderr)
 	default:
-		return fmt.Errorf("brain: unknown subcommand: %s (expected query|write)", args[0])
+		return fmt.Errorf("unknown subcommand: %s (expected query|write)", args[0])
 	}
 }
 
@@ -32,7 +32,7 @@ func runBrainQuery(ctx context.Context, args []string, _ io.Reader, stdout, stde
 		return fmt.Errorf("parse flags: %w", err)
 	}
 	if fs.NArg() < 1 {
-		return errors.New("brain query: topic required")
+		return errors.New("topic required")
 	}
 	topic := fs.Arg(0)
 
@@ -59,7 +59,7 @@ func runBrainWrite(ctx context.Context, args []string, stdin io.Reader, stdout,
 		return fmt.Errorf("parse flags: %w", err)
 	}
 	if fs.NArg() < 2 {
-		return errors.New("brain write: type and slug required (e.g. brain write knowledge my-slug)")
+		return errors.New("type and slug required (e.g. brain write knowledge my-slug)")
 	}
 	kind := fs.Arg(0)
 	slug := fs.Arg(1)